1
|
Chen Z, Liang N, Li H, Zhang H, Li H, Yan L, Hu Z, Chen Y, Zhang Y, Wang Y, Ke D, Shi N. Exploring explainable AI features in the vocal biomarkers of lung disease. Comput Biol Med 2024; 179:108844. [PMID: 38981214 DOI: 10.1016/j.compbiomed.2024.108844] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/02/2024] [Revised: 05/15/2024] [Accepted: 06/04/2024] [Indexed: 07/11/2024]
Abstract
This review delves into the burgeoning field of explainable artificial intelligence (XAI) in the detection and analysis of lung diseases through vocal biomarkers. Lung diseases, often elusive in their early stages, pose a significant public health challenge. Recent advancements in AI have ushered in innovative methods for early detection, yet the black-box nature of many AI models limits their clinical applicability. XAI emerges as a pivotal tool, enhancing transparency and interpretability in AI-driven diagnostics. This review synthesizes current research on the application of XAI in analyzing vocal biomarkers for lung diseases, highlighting how these techniques elucidate the connections between specific vocal features and lung pathology. We critically examine the methodologies employed, the types of lung diseases studied, and the performance of various XAI models. The potential for XAI to aid in early detection, monitor disease progression, and personalize treatment strategies in pulmonary medicine is emphasized. Furthermore, this review identifies current challenges, including data heterogeneity and model generalizability, and proposes future directions for research. By offering a comprehensive analysis of explainable AI features in the context of lung disease detection, this review aims to bridge the gap between advanced computational approaches and clinical practice, paving the way for more transparent, reliable, and effective diagnostic tools.
Collapse
Affiliation(s)
- Zhao Chen
- Institute of Basic Research in Clinical Medicine, China Academy of Chinese Medical Sciences, Beijing, China
| | - Ning Liang
- Institute of Basic Research in Clinical Medicine, China Academy of Chinese Medical Sciences, Beijing, China
| | - Haoyuan Li
- Institute of Basic Research in Clinical Medicine, China Academy of Chinese Medical Sciences, Beijing, China
| | - Haili Zhang
- Institute of Basic Research in Clinical Medicine, China Academy of Chinese Medical Sciences, Beijing, China
| | - Huizhen Li
- Institute of Basic Research in Clinical Medicine, China Academy of Chinese Medical Sciences, Beijing, China
| | - Lijiao Yan
- Institute of Basic Research in Clinical Medicine, China Academy of Chinese Medical Sciences, Beijing, China
| | - Ziteng Hu
- Institute of Basic Research in Clinical Medicine, China Academy of Chinese Medical Sciences, Beijing, China
| | - Yaxin Chen
- Institute of Basic Research in Clinical Medicine, China Academy of Chinese Medical Sciences, Beijing, China
| | - Yujing Zhang
- Institute of Basic Research in Clinical Medicine, China Academy of Chinese Medical Sciences, Beijing, China
| | - Yanping Wang
- Institute of Basic Research in Clinical Medicine, China Academy of Chinese Medical Sciences, Beijing, China
| | - Dandan Ke
- Special Disease Clinic, Huaishuling Branch of Beijing Fengtai Hospital of Integrated Traditional Chinese and Western Medicine, Beijing, China.
| | - Nannan Shi
- State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University, Beijing, China; Institute of Basic Research in Clinical Medicine, China Academy of Chinese Medical Sciences, Beijing, China.
| |
Collapse
|
2
|
Shen J, Zhang X, Lu Y, Ye P, Zhang P, Yan Y. Novel audio characteristic-dependent feature extraction and data augmentation methods for cough-based respiratory disease classification. Comput Biol Med 2024; 179:108843. [PMID: 39029433 DOI: 10.1016/j.compbiomed.2024.108843] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/01/2023] [Revised: 05/08/2024] [Accepted: 06/04/2024] [Indexed: 07/21/2024]
Abstract
Respiratory diseases are one of the major health problems worldwide. Early diagnosis of the disease types is of vital importance. As one of the main symptoms of many respiratory diseases, cough may contain information about different pathological changes in the respiratory system. Therefore, many researchers have used cough sounds to diagnose different diseases through artificial intelligence in recent years. The acoustic features and data augmentation methods commonly used in speech tasks are used to achieve better performance. Although these methods are applicable, previous studies have not considered the characteristics of cough sound signals. In this paper, we designed a cough-based respiratory disease classification system and proposed audio characteristic-dependent feature extraction and data augmentation methods. Firstly, according to the short durations and rapid transition of different cough stages, we proposed maximum overlapping mel-spectrogram to avoid missing inter-frame information caused by traditional framing methods. Secondly, we applied various data augmentation methods to mitigate the problem of limited labeled data. Based on the frequency energy distributions of different diseased cough audios, we proposed a parameter-independent self-energy-based augmentation method to enhance the differences between different frequency bands. Finally, in the model testing stage, we leveraged test-time augmentation to further improve the classification performance by fusing the test results of the original and multiple augmented audios. The proposed methods were validated on the Coswara dataset through stratified four-fold cross-validation. Compared to the baseline model using mel-spectrogram as input, the proposed methods achieved an average absolute performance improvement of 3.33% and 3.10% in macro Area Under the Receiver Operating Characteristic (macro AUC) and Unweighted Average Recall (UAR), respectively. The visualization results through Gradient-weighted Class Activation Mapping (Grad-CAM) showed the contributions of different features to model decisions.
Collapse
Affiliation(s)
- Jiakun Shen
- Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China; University of Chinese Academy of Sciences, Beijing, China.
| | - Xueshuai Zhang
- Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China; University of Chinese Academy of Sciences, Beijing, China.
| | - Yu Lu
- Institute of Information on Traditional Chinese Medicine, China Academy of Chinese Medical Sciences, Beijing, China.
| | - Pengfei Ye
- Children's Hospital Capital Institute of Pediatrics, Beijing, China.
| | - Pengyuan Zhang
- Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China; University of Chinese Academy of Sciences, Beijing, China.
| | - Yonghong Yan
- Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China; University of Chinese Academy of Sciences, Beijing, China.
| |
Collapse
|
3
|
Nkengue MJ, Zeng X, Koehl L, Tao X, Dassonville F, Dumont N, Ye-Lehmann S, Akwa Y, Ye H. An intelligent garment for long COVID-19 real-time monitoring. Comput Biol Med 2024; 181:109067. [PMID: 39182371 DOI: 10.1016/j.compbiomed.2024.109067] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2024] [Revised: 08/13/2024] [Accepted: 08/21/2024] [Indexed: 08/27/2024]
Abstract
As monitoring and diagnostic tools for long COVID-19 cases, wearable systems and supervised learning-based medical image analysis have proven to be useful. Current research on these two technical roadmaps has various drawbacks, despite their respective benefits. Wearable systems allow only the real-time monitoring of physiological parameters (heart rate, temperature, blood oxygen saturation, or SpO2). Therefore, they are unable to conduct in-depth investigations or differentiate COVID-19 from other illnesses that share similar symptoms. Medical image analysis using supervised learning-based models can be used to conduct in-depth analyses and provide precise diagnostic decision support. However, these methods are rarely used for real-time monitoring. In this regard, we present an intelligent garment combining the precision of supervised learning-based models with real-time monitoring capabilities of wearable systems. Given the relevance of electrocardiogram (ECG) signals to long COVID-19 symptom severity, an explainable data fusion strategy based on multiple machine learning models uses heart rate, temperature, SpO2, and ECG signal analysis to accurately assess the patient's health status. Experiments show that the proposed intelligent garment achieves an accuracy of 97.5 %, outperforming most of the existing wearable systems. Furthermore, it was confirmed that the two physiological indicators most significantly affected by the presence of long COVID-19 were SpO2 and the ST intervals of ECG signals.
Collapse
Affiliation(s)
- Marc Junior Nkengue
- Univ. Lille, ENSAIT, Laboratoire Génie et Matériaux Textile (GEMTEX), F-59000, Lille, France; Univ. Lille, Ecole Centrale Lille, F-59000, Lille, France.
| | - Xianyi Zeng
- Univ. Lille, ENSAIT, Laboratoire Génie et Matériaux Textile (GEMTEX), F-59000, Lille, France
| | - Ludovic Koehl
- Univ. Lille, ENSAIT, Laboratoire Génie et Matériaux Textile (GEMTEX), F-59000, Lille, France
| | - Xuyuan Tao
- Univ. Lille, ENSAIT, Laboratoire Génie et Matériaux Textile (GEMTEX), F-59000, Lille, France
| | - François Dassonville
- Univ. Lille, ENSAIT, Laboratoire Génie et Matériaux Textile (GEMTEX), F-59000, Lille, France
| | - Nicolas Dumont
- Univ. Lille, ENSAIT, Laboratoire Génie et Matériaux Textile (GEMTEX), F-59000, Lille, France
| | - Shixin Ye-Lehmann
- Univ. Paris-Saclay, Diseases and Hormones of the Nervous System, F-94000, Paris, France
| | - Yvette Akwa
- Univ. Paris-Saclay, Diseases and Hormones of the Nervous System, F-94000, Paris, France
| | - Hanwen Ye
- Univ. Paris-Saclay, Diseases and Hormones of the Nervous System, F-94000, Paris, France
| |
Collapse
|
4
|
Torborg SR, Kim AYE, Rameau A. New developments in the application of artificial intelligence to laryngology. Curr Opin Otolaryngol Head Neck Surg 2024:00020840-990000000-00141. [PMID: 39146248 DOI: 10.1097/moo.0000000000000999] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/17/2024]
Abstract
PURPOSE OF REVIEW The purpose of this review is to summarize the existing literature on artificial intelligence technology utilization in laryngology, highlighting recent advances and current barriers to implementation. RECENT FINDINGS The volume of publications studying applications of artificial intelligence in laryngology has rapidly increased, demonstrating a strong interest in utilizing this technology. Vocal biomarkers for disease screening, deep learning analysis of videolaryngoscopy for lesion identification, and auto-segmentation of videofluoroscopy for detection of aspiration are a few of the new ways in which artificial intelligence is poised to transform clinical care in laryngology. Increasing collaboration is ongoing to establish guidelines and standards for the field to ensure generalizability. SUMMARY Artificial intelligence tools have the potential to greatly advance laryngology care by creating novel screening methods, improving how data-heavy diagnostics of laryngology are analyzed, and standardizing outcome measures. However, physician and patient trust in artificial intelligence must improve for the technology to be successfully implemented. Additionally, most existing studies lack large and diverse datasets, external validation, and consistent ground-truth references necessary to produce generalizable results. Collaborative, large-scale studies will fuel technological innovation and bring artificial intelligence to the forefront of patient care in laryngology.
Collapse
Affiliation(s)
- Stefan R Torborg
- Sean Parker Institute for the Voice, Department of Otolaryngology-Head and Neck Surgery, Weill Cornell Medicine
- Weill Cornell/Rockefeller/Sloan Kettering Tri-Institutional MD-PhD Program, New York, New York, USA
| | - Ashley Yeo Eun Kim
- Sean Parker Institute for the Voice, Department of Otolaryngology-Head and Neck Surgery, Weill Cornell Medicine
| | - Anaïs Rameau
- Sean Parker Institute for the Voice, Department of Otolaryngology-Head and Neck Surgery, Weill Cornell Medicine
| |
Collapse
|
5
|
Budd J, Baker K, Karoune E, Coppock H, Patel S, Payne R, Tendero Cañadas A, Titcomb A, Hurley D, Egglestone S, Butler L, Mellor J, Nicholson G, Kiskin I, Koutra V, Jersakova R, McKendry RA, Diggle P, Richardson S, Schuller BW, Gilmour S, Pigoli D, Roberts S, Packham J, Thornley T, Holmes C. A large-scale and PCR-referenced vocal audio dataset for COVID-19. Sci Data 2024; 11:700. [PMID: 38937483 PMCID: PMC11211414 DOI: 10.1038/s41597-024-03492-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/22/2024] [Accepted: 06/10/2024] [Indexed: 06/29/2024] Open
Abstract
The UK COVID-19 Vocal Audio Dataset is designed for the training and evaluation of machine learning models that classify SARS-CoV-2 infection status or associated respiratory symptoms using vocal audio. The UK Health Security Agency recruited voluntary participants through the national Test and Trace programme and the REACT-1 survey in England from March 2021 to March 2022, during dominant transmission of the Alpha and Delta SARS-CoV-2 variants and some Omicron variant sublineages. Audio recordings of volitional coughs, exhalations, and speech were collected in the 'Speak up and help beat coronavirus' digital survey alongside demographic, symptom and self-reported respiratory condition data. Digital survey submissions were linked to SARS-CoV-2 test results. The UK COVID-19 Vocal Audio Dataset represents the largest collection of SARS-CoV-2 PCR-referenced audio recordings to date. PCR results were linked to 70,565 of 72,999 participants and 24,105 of 25,706 positive cases. Respiratory symptoms were reported by 45.6% of participants. This dataset has additional potential uses for bioacoustics research, with 11.3% participants self-reporting asthma, and 27.2% with linked influenza PCR test results.
Collapse
Affiliation(s)
- Jobie Budd
- London Centre for Nanotechnology, University College London, London, UK
- Division of Medicine, University College London, London, UK
| | - Kieran Baker
- King's College London, London, UK
- The Alan Turing Institute, London, UK
| | | | - Harry Coppock
- The Alan Turing Institute, London, UK
- Imperial College London, London, UK
| | - Selina Patel
- UK Health Security Agency, London, UK
- Institute of Health Informatics, University College London, London, UK
| | | | - Ana Tendero Cañadas
- UK Health Security Agency, London, UK
- Centre for Stress and Age-Related Disease, School of Applied Sciences, University of Brighton, Brighton, UK
| | | | | | | | | | | | - George Nicholson
- The Alan Turing Institute, London, UK
- University of Oxford, Oxford, UK
| | - Ivan Kiskin
- University of Surrey, Guildford, UK
- The Surrey Institute for People-Centred AI, Centre for Vision, Speech and Signal Processing, Guildford, UK
| | - Vasiliki Koutra
- King's College London, London, UK
- The Alan Turing Institute, London, UK
| | | | - Rachel A McKendry
- London Centre for Nanotechnology, University College London, London, UK
- Division of Medicine, University College London, London, UK
| | | | | | - Björn W Schuller
- The Alan Turing Institute, London, UK
- Imperial College London, London, UK
- CHI, MRI, Technical University of Munich, Munich, Germany
| | - Steven Gilmour
- King's College London, London, UK
- The Alan Turing Institute, London, UK
| | - Davide Pigoli
- King's College London, London, UK
- The Alan Turing Institute, London, UK
| | - Stephen Roberts
- The Alan Turing Institute, London, UK
- University of Oxford, Oxford, UK
| | | | - Tracey Thornley
- UK Health Security Agency, London, UK
- University of Nottingham, Nottingham, UK
| | - Chris Holmes
- The Alan Turing Institute, London, UK
- University of Oxford, Oxford, UK
| |
Collapse
|
6
|
匡 英, 车 波, 李 轩, 刘 磊, 邓 林. [Research on portable airway impedance monitoring device based on expiratory oscillation]. SHENG WU YI XUE GONG CHENG XUE ZA ZHI = JOURNAL OF BIOMEDICAL ENGINEERING = SHENGWU YIXUE GONGCHENGXUE ZAZHI 2024; 41:430-438. [PMID: 38932527 PMCID: PMC11208649 DOI: 10.7507/1001-5515.202309058] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Subscribe] [Scholar Register] [Received: 09/20/2023] [Revised: 03/20/2024] [Indexed: 06/28/2024]
Abstract
Monitoring airway impedance has significant clinical value in accurately assessing and diagnosing pulmonary function diseases at an early stage. To address the issue of large oscillator size and high power consumption in current pulmonary function devices, this study adopts a new strategy of expiration-driven oscillation. A lightweight and low-power airway impedance monitoring system with integrated sensing, control circuitry, and dynamic feedback system, providing visual feedback on the system's status, was developed. The respiratory impedance measurement experiments and statistical comparisons indicated that the system could achieve stable measurement of airway impedance at 5 Hz. The frequency spectrum curves of respiratory impedance ( R and X) showed consistent trends with those obtained from the clinical pulmonary function instrument, specifically the impulse oscillometry system (IOS). The differences between them were all less than 1.1 cm H 2O·s/L. Additionally, there was a significant statistical difference in the respiratory impedance R5 between the exercise and rest groups, which suggests that the system can measure the variability of airway resistance parameters during exercise. Therefore, the impedance monitoring system developed in this study supports subjects in performing handheld, continuous measurements of dynamic changes in airway impedance over an extended period of time. This research provides a foundation for further developing low-power, portable, and even wearable devices for dynamic monitoring of pulmonary function.
Collapse
Affiliation(s)
- 英烽 匡
- 常州大学 微电子与控制工程学院(江苏常州 213164)School of Microelectronics and Control Engineering, Changzhou University, Changzhou, Jiangsu 213164, P. R. China
- 常州大学 生物医学工程与健康科学研究院(江苏常州 213164)Institute of Biomedical Engineering and Health Sciences, Changzhou University, Changzhou, Jiangsu 213164, P. R. China
| | - 波 车
- 常州大学 微电子与控制工程学院(江苏常州 213164)School of Microelectronics and Control Engineering, Changzhou University, Changzhou, Jiangsu 213164, P. R. China
| | - 轩 李
- 常州大学 微电子与控制工程学院(江苏常州 213164)School of Microelectronics and Control Engineering, Changzhou University, Changzhou, Jiangsu 213164, P. R. China
| | - 磊 刘
- 常州大学 微电子与控制工程学院(江苏常州 213164)School of Microelectronics and Control Engineering, Changzhou University, Changzhou, Jiangsu 213164, P. R. China
- 常州大学 生物医学工程与健康科学研究院(江苏常州 213164)Institute of Biomedical Engineering and Health Sciences, Changzhou University, Changzhou, Jiangsu 213164, P. R. China
| | - 林红 邓
- 常州大学 微电子与控制工程学院(江苏常州 213164)School of Microelectronics and Control Engineering, Changzhou University, Changzhou, Jiangsu 213164, P. R. China
- 常州大学 生物医学工程与健康科学研究院(江苏常州 213164)Institute of Biomedical Engineering and Health Sciences, Changzhou University, Changzhou, Jiangsu 213164, P. R. China
| |
Collapse
|
7
|
Wieczorek K, Ananth S, Valazquez-Pimentel D. Acoustic biomarkers in asthma: a systematic review. J Asthma 2024:1-16. [PMID: 38634718 DOI: 10.1080/02770903.2024.2344156] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2024] [Accepted: 04/13/2024] [Indexed: 04/19/2024]
Abstract
OBJECTIVE Current monitoring methods of asthma, such as peak expiratory flow testing, have important limitations. The emergence of automated acoustic sound analysis, capturing cough, wheeze, and inhaler use, offers a promising avenue for improving asthma diagnosis and monitoring. This systematic review evaluated the validity of acoustic biomarkers in supporting the diagnosis of asthma and its monitoring. DATA SOURCES A search was performed using two databases (PubMed and Embase) for all relevant studies published before November 2023. STUDY SELECTION 27 studies were included for analysis. Eligible studies focused on acoustic signals as digital biomarkers in asthma, utilizing recording devices to register or analyze sound. RESULTS Various respiratory acoustic signal types were analyzed, with cough and wheeze being predominant. Data collection methods included smartphones, custom sensors and digital stethoscopes. Across all studies, automated acoustic algorithms achieved average accuracy of cough and wheeze detection of 88.7% (range: 61.0 - 100.0%) with a median of 92.0%. The sensitivity of sound detection ranged from 54.0 to 100.0%, with a median of 90.3%; specificity ranged from 67.0 to 99.7%, with a median of 95.0%. Moreover, 70.4% (19/27) studies had a risk of bias identified. CONCLUSIONS This systematic review establishes the promising role of acoustic biomarkers, particularly cough and wheeze, in supporting the diagnosis of asthma and monitoring. The evidence suggests the potential for clinical integration of acoustic biomarkers, emphasizing the need for further validation in larger, clinically-diverse populations.
Collapse
Affiliation(s)
| | - Sachin Ananth
- London North West University Healthcare Trust, London, UK
| | | |
Collapse
|
8
|
Kosar A, Asif M, Ahmad MB, Akram W, Mahmood K, Kumari S. Towards classification and comprehensive analysis of AI-based COVID-19 diagnostic techniques: A survey. Artif Intell Med 2024; 151:102858. [PMID: 38583369 DOI: 10.1016/j.artmed.2024.102858] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/22/2023] [Revised: 01/02/2024] [Accepted: 03/25/2024] [Indexed: 04/09/2024]
Abstract
The unpredictable pandemic came to light at the end of December 2019, known as the novel coronavirus, also termed COVID-19, identified by the World Health Organization (WHO). The virus first originated in Wuhan (China) and rapidly affected most of the world's population. This outbreak's impact is experienced worldwide because it causes high mortality risk, many cases, and economic falls. Around the globe, the total number of cases and deaths reported till November 12, 2022, were >600 million and 6.6 million, respectively. During the period of COVID-19, several diverse diagnostic techniques have been proposed. This work presents a systematic review of COVID-19 diagnostic techniques in response to such acts. Initially, these techniques are classified into different categories based on their working principle and detection modalities, i.e. chest X-ray imaging, cough sound or respiratory patterns, RT-PCR, antigen testing, and antibody testing. After that, a comparative analysis is performed to evaluate these techniques' efficacy which may help to determine an optimum solution for a particular scenario. The findings of the proposed work show that Artificial Intelligence plays a vital role in developing COVID-19 diagnostic techniques which support the healthcare system. The related work can be a footprint for all the researchers, available under a single umbrella. Additionally, all the techniques are long-lasting and can be used for future pandemics.
Collapse
Affiliation(s)
- Amna Kosar
- Department of Computer Science, Lahore Garrison University, Lahore, Pakistan
| | - Muhammad Asif
- Department of Computer Science, Lahore Garrison University, Lahore, Pakistan
| | - Maaz Bin Ahmad
- College of Computing and Information Sciences, Karachi Institute of Economics and Technology (KIET), Karachi, Pakistan
| | - Waseem Akram
- Graduate School of Engineering Science and Technology, National Yunlin University of Science and Technology, Douliu, Taiwan, ROC
| | - Khalid Mahmood
- Graduate School of Intelligent Data Science, National Yunlin University of Science and Technology, Douliu, Taiwan, ROC.
| | - Saru Kumari
- Departement of Mathematics, Chaudhary Charan Singh University, Meerut, India
| |
Collapse
|
9
|
Robotti C, Costantini G, Saggio G, Cesarini V, Calastri A, Maiorano E, Piloni D, Perrone T, Sabatini U, Ferretti VV, Cassaniti I, Baldanti F, Gravina A, Sakib A, Alessi E, Pietrantonio F, Pascucci M, Casali D, Zarezadeh Z, Zoppo VD, Pisani A, Benazzo M. Machine Learning-based Voice Assessment for the Detection of Positive and Recovered COVID-19 Patients. J Voice 2024; 38:796.e1-796.e13. [PMID: 34965907 PMCID: PMC8616736 DOI: 10.1016/j.jvoice.2021.11.004] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/28/2021] [Revised: 11/17/2021] [Accepted: 11/18/2021] [Indexed: 12/12/2022]
Abstract
Many virological tests have been implemented during the Coronavirus Disease 2019 (COVID-19) pandemic for diagnostic purposes, but they appear unsuitable for screening purposes. Furthermore, current screening strategies are not accurate enough to effectively curb the spread of the disease. Therefore, the present study was conducted within a controlled clinical environment to determine eventual detectable variations in the voice of COVID-19 patients, recovered and healthy subjects, and also to determine whether machine learning-based voice assessment (MLVA) can accurately discriminate between them, thus potentially serving as a more effective mass-screening tool. Three different subpopulations were consecutively recruited: positive COVID-19 patients, recovered COVID-19 patients and healthy individuals as controls. Positive patients were recruited within 10 days from nasal swab positivity. Recovery from COVID-19 was established clinically, virologically and radiologically. Healthy individuals reported no COVID-19 symptoms and yielded negative results at serological testing. All study participants provided three trials for multiple vocal tasks (sustained vowel phonation, speech, cough). All recordings were initially divided into three different binary classifications with a feature selection, ranking and cross-validated RBF-SVM pipeline. This brough a mean accuracy of 90.24%, a mean sensitivity of 91.15%, a mean specificity of 89.13% and a mean AUC of 0.94 across all tasks and all comparisons, and outlined the sustained vowel as the most effective vocal task for COVID discrimination. Moreover, a three-way classification was carried out on an external test set comprised of 30 subjects, 10 per class, with a mean accuracy of 80% and an accuracy of 100% for the detection of positive subjects. Within this assessment, recovered individuals proved to be the most difficult class to identify, and all the misclassified subjects were declared positive; this might be related to mid and short-term vocal traces of COVID-19, even after the clinical resolution of the infection. In conclusion, MLVA may accurately discriminate between positive COVID-19 patients, recovered COVID-19 patients and healthy individuals. Further studies should test MLVA among larger populations and asymptomatic positive COVID-19 patients to validate this novel screening technology and test its potential application as a potentially more effective surveillance strategy for COVID-19.
Collapse
Affiliation(s)
- Carlo Robotti
- Department of Otolaryngology - Head and Neck Surgery, Fondazione IRCCS Policlinico San Matteo, Pavia, Italy; Department of Clinical, Surgical, Diagnostic and Pediatric Sciences, University of Pavia, Pavia, Italy.
| | - Giovanni Costantini
- Department of Electronic Engineering, University of Rome Tor Vergata, Rome, Italy.
| | - Giovanni Saggio
- Department of Electronic Engineering, University of Rome Tor Vergata, Rome, Italy.
| | - Valerio Cesarini
- Department of Electronic Engineering, University of Rome Tor Vergata, Rome, Italy
| | - Anna Calastri
- Department of Otolaryngology - Head and Neck Surgery, Fondazione IRCCS Policlinico San Matteo, Pavia, Italy
| | - Eugenia Maiorano
- Department of Otolaryngology - Head and Neck Surgery, Fondazione IRCCS Policlinico San Matteo, Pavia, Italy
| | - Davide Piloni
- Pneumology Unit, Fondazione IRCCS Policlinico San Matteo, Pavia, Italy
| | - Tiziano Perrone
- Department of Internal Medicine, Fondazione IRCCS Policlinico San Matteo, University of Pavia, Pavia, Italy
| | - Umberto Sabatini
- Department of Internal Medicine, Fondazione IRCCS Policlinico San Matteo, University of Pavia, Pavia, Italy
| | - Virginia Valeria Ferretti
- Clinical Epidemiology and Biometry Unit, Fondazione IRCCS Policlinico San Matteo Foundation, Pavia, Italy
| | - Irene Cassaniti
- Molecular Virology Unit, Microbiology and Virology Department, Fondazione IRCCS Policlinico San Matteo, Pavia, Italy
| | - Fausto Baldanti
- Department of Clinical, Surgical, Diagnostic and Pediatric Sciences, University of Pavia, Pavia, Italy; Molecular Virology Unit, Microbiology and Virology Department, Fondazione IRCCS Policlinico San Matteo, Pavia, Italy
| | - Andrea Gravina
- Otorhinolaryngology Department, University of Rome Tor Vergata, Rome, Italy
| | - Ahmed Sakib
- Otorhinolaryngology Department, University of Rome Tor Vergata, Rome, Italy
| | - Elena Alessi
- Internal Medicine Unit, Ospedale dei Castelli ASL Roma 6, Ariccia, Italy
| | | | - Matteo Pascucci
- Internal Medicine Unit, Ospedale dei Castelli ASL Roma 6, Ariccia, Italy
| | - Daniele Casali
- Department of Electronic Engineering, University of Rome Tor Vergata, Rome, Italy
| | - Zakarya Zarezadeh
- Department of Electronic Engineering, University of Rome Tor Vergata, Rome, Italy
| | - Vincenzo Del Zoppo
- Department of Electronic Engineering, University of Rome Tor Vergata, Rome, Italy
| | - Antonio Pisani
- Department of Brain and Behavioral Sciences, University of Pavia, Pavia, Italy; IRCCS Mondino Foundation, Pavia, Italy
| | - Marco Benazzo
- Department of Otolaryngology - Head and Neck Surgery, Fondazione IRCCS Policlinico San Matteo, Pavia, Italy; Department of Clinical, Surgical, Diagnostic and Pediatric Sciences, University of Pavia, Pavia, Italy
| |
Collapse
|
10
|
Walter JR, Lee JY, Yu L, Kim B, Martell K, Opdycke A, Scheffel J, Felsl I, Patel S, Rangel S, Serao A, Edel C, Bharat A, Xu S. Use of artificial intelligence to develop predictive algorithms of cough and PCR-confirmed COVID-19 infections based on inputs from clinical-grade wearable sensors. Sci Rep 2024; 14:8072. [PMID: 38580712 PMCID: PMC10997665 DOI: 10.1038/s41598-024-57830-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/15/2023] [Accepted: 03/21/2024] [Indexed: 04/07/2024] Open
Abstract
There have been over 769 million cases of COVID-19, and up to 50% of infected individuals are asymptomatic. The purpose of this study aimed to assess the use of a clinical-grade physiological wearable monitoring system, ANNE One, to develop an artificial intelligence algorithm for (1) cough detection and (2) early detection of COVID-19, through the retrospective analysis of prospectively collected physiological data from longitudinal wear of ANNE sensors in a multicenter single arm study of subjects at high risk for COVID-19 due to occupational or home exposures. The study employed a two-fold approach: cough detection algorithm development and COVID-19 detection algorithm development. For cough detection, healthy individuals wore an ANNE One chest sensor during scripted activity. The final performance of the algorithm achieved an F-1 score of 83.3% in twenty-seven healthy subjects during biomarker validation. In the COVID-19 detection algorithm, individuals at high-risk for developing COVID-19 because of recent exposures received ANNE One sensors and completed daily symptom surveys. An algorithm analyzing vital parameters (heart rate, respiratory rate, cough count, etc.) for early COVID-19 detection was developed. The COVID-19 detection algorithm exhibited a sensitivity of 0.47 and specificity of 0.72 for detecting COVID-19 in 325 individuals with recent exposures. Participants demonstrated high adherence (≥ 4 days of wear per week). ANNE One shows promise for detection of COVID-19. Inclusion of respiratory biomarkers (e.g., cough count) enhanced the algorithm's predictive ability. These findings highlight the potential value of wearable devices in early disease detection and monitoring.
Collapse
Affiliation(s)
- Jessica R Walter
- Department of Obstetrics and Gynecology, Northwestern University, Chicago, IL, USA
| | - Jong Yoon Lee
- Sibel Health, Chicago, USA
- Querrey Simpson Institute for Bioelectronics, Northwestern University, Evanston, USA
| | - Lian Yu
- Sibel Health, Chicago, USA
- Querrey Simpson Institute for Bioelectronics, Northwestern University, Evanston, USA
| | - Brandon Kim
- Sibel Health, Chicago, USA
- Querrey Simpson Institute for Bioelectronics, Northwestern University, Evanston, USA
| | - Knute Martell
- Department of Dermatology, Northwestern University Feinberg School of Medicine, Chicago, USA
| | | | | | | | - Soham Patel
- Department of Dermatology, Northwestern University Feinberg School of Medicine, Chicago, USA
| | - Stephanie Rangel
- Department of Dermatology, Northwestern University Feinberg School of Medicine, Chicago, USA
| | - Alexa Serao
- Department of Dermatology, Northwestern University Feinberg School of Medicine, Chicago, USA
| | - Claire Edel
- Department of Dermatology, Northwestern University Feinberg School of Medicine, Chicago, USA
| | - Ankit Bharat
- Department of Surgery, Northwestern University, Chicago, IL, USA
| | - Shuai Xu
- Sibel Health, Chicago, USA.
- Querrey Simpson Institute for Bioelectronics, Northwestern University, Evanston, USA.
- Department of Dermatology, Northwestern University Feinberg School of Medicine, Chicago, USA.
| |
Collapse
|
11
|
Al Hossain F, Tonmoy MTH, Nuvvula S, Chapman BP, Gupta RK, Lover AA, Dinglasan RR, Carreiro S, Rahman T. Syndromic surveillance of population-level COVID-19 burden with cough monitoring in a hospital emergency waiting room. Front Public Health 2024; 12:1279392. [PMID: 38605877 PMCID: PMC11007176 DOI: 10.3389/fpubh.2024.1279392] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/18/2023] [Accepted: 03/11/2024] [Indexed: 04/13/2024] Open
Abstract
Syndromic surveillance is an effective tool for enabling the timely detection of infectious disease outbreaks and facilitating the implementation of effective mitigation strategies by public health authorities. While various information sources are currently utilized to collect syndromic signal data for analysis, the aggregated measurement of cough, an important symptom for many illnesses, is not widely employed as a syndromic signal. With recent advancements in ubiquitous sensing technologies, it becomes feasible to continuously measure population-level cough incidence in a contactless, unobtrusive, and automated manner. In this work, we demonstrate the utility of monitoring aggregated cough count as a syndromic indicator to estimate COVID-19 cases. In our study, we deployed a sensor-based platform (Syndromic Logger) in the emergency room of a large hospital. The platform captured syndromic signals from audio, thermal imaging, and radar, while the ground truth data were collected from the hospital's electronic health record. Our analysis revealed a significant correlation between the aggregated cough count and positive COVID-19 cases in the hospital (Pearson correlation of 0.40, p-value < 0.001). Notably, this correlation was higher than that observed with the number of individuals presenting with fever (ρ = 0.22, p = 0.04), a widely used syndromic signal and screening tool for such diseases. Furthermore, we demonstrate how the data obtained from our Syndromic Logger platform could be leveraged to estimate various COVID-19-related statistics using multiple modeling approaches. Aggregated cough counts and other data, such as people density collected from our platform, can be utilized to predict COVID-19 patient visits related metrics in a hospital waiting room, and SHAP and Gini feature importance-based metrics showed cough count as the important feature for these prediction models. Furthermore, we have shown that predictions based on cough counting outperform models based on fever detection (e.g., temperatures over 39°C), which require more intrusive engagement with the population. Our findings highlight that incorporating cough-counting based signals into syndromic surveillance systems can significantly enhance overall resilience against future public health challenges, such as emerging disease outbreaks or pandemics.
Collapse
Affiliation(s)
- Forsad Al Hossain
- Manning College of Information and Computer Sciences, University of Massachusetts-Amherst, Amherst, MA, United States
| | - M. Tanjid Hasan Tonmoy
- Halıcıoǧlu Data Science Institute, University of California, San Diego, San Diego, CA, United States
| | - Sri Nuvvula
- Department of Emergency Medicine, UMass Chan Medical School, Worcester, MA, United States
| | - Brittany P. Chapman
- Department of Emergency Medicine, UMass Chan Medical School, Worcester, MA, United States
| | - Rajesh K. Gupta
- Halıcıoǧlu Data Science Institute, University of California, San Diego, San Diego, CA, United States
| | - Andrew A. Lover
- School of Public Health & Health Sciences, University of Massachusetts Amherst, Amherst, MA, United States
| | - Rhoel R. Dinglasan
- Infectious Diseases and Immunology, University of Florida, Gainesville, FL, United States
| | - Stephanie Carreiro
- Department of Emergency Medicine, UMass Chan Medical School, Worcester, MA, United States
| | - Tauhidur Rahman
- Halıcıoǧlu Data Science Institute, University of California, San Diego, San Diego, CA, United States
| |
Collapse
|
12
|
Anibal JT, Landa AJ, Hang NTT, Song MJ, Peltekian AK, Shin A, Huth HB, Hazen LA, Christou AS, Rivera J, Morhard RA, Bagci U, Li M, Bensoussan Y, Clifton DA, Wood BJ. Omicron detection with large language models and YouTube audio data. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2024:2022.09.13.22279673. [PMID: 36172131 PMCID: PMC9516853 DOI: 10.1101/2022.09.13.22279673] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 01/04/2023]
Abstract
Publicly available audio data presents a unique opportunity for the development of digital health technologies with large language models (LLMs). In this study, YouTube was mined to collect audio data from individuals with self-declared positive COVID-19 tests as well as those with other upper respiratory infections (URI) and healthy subjects discussing a diverse range of topics. The resulting dataset was transcribed with the Whisper model and used to assess the capacity of LLMs for detecting self-reported COVID-19 cases and performing variant classification. Following prompt optimization, LLMs achieved accuracies of 0.89, 0.97, respectively, in the tasks of identifying self-reported COVID-19 cases and other respiratory illnesses. The model also obtained a mean accuracy of 0.77 at identifying the variant of self-reported COVID-19 cases using only symptoms and other health-related factors described in the YouTube videos. In comparison with past studies, which used scripted, standardized voice samples to capture biomarkers, this study focused on extracting meaningful information from public online audio data. This work introduced novel design paradigms for pandemic management tools, showing the potential of audio data in clinical and public health applications.
Collapse
Affiliation(s)
- James T Anibal
- Center for Interventional Oncology, Radiology and Imaging Sciences, NIH Clinical Center, National Cancer Institute, National Institute of Biomedical Imaging and Bioengineering, National Institutes of Health, 10 Center Dr, Building 10, Room 1C341, MSC 1182, Bethesda, MD 20892-1182 USA
- Computational Health Informatics Lab, Oxford Institute of Biomedical Engineering, University of Oxford, Old Road Campus Research Building, Headington, Oxford OX3 7DQ, United Kingdom
| | - Adam J Landa
- Center for Interventional Oncology, Radiology and Imaging Sciences, NIH Clinical Center, National Cancer Institute, National Institute of Biomedical Imaging and Bioengineering, National Institutes of Health, 10 Center Dr, Building 10, Room 1C341, MSC 1182, Bethesda, MD 20892-1182 USA
| | - Nguyen T T Hang
- Oxford University Clinical Research Unit, Centre for Tropical Medicine, Ho Chi Minh City, Vietnam
| | - Miranda J Song
- Center for Interventional Oncology, Radiology and Imaging Sciences, NIH Clinical Center, National Cancer Institute, National Institute of Biomedical Imaging and Bioengineering, National Institutes of Health, 10 Center Dr, Building 10, Room 1C341, MSC 1182, Bethesda, MD 20892-1182 USA
| | - Alec K Peltekian
- Department of Computer Science, McCormick School of Engineering, Northwestern University, Mudd Hall, 2233 Tech Drive, Third Floor, Evanston, IL, 60208 USA
| | - Ashley Shin
- National Library of Medicine, National Institutes of Health, 8600 Rockville Pike, Bethesda, MD, 20894
| | - Hannah B Huth
- Center for Interventional Oncology, Radiology and Imaging Sciences, NIH Clinical Center, National Cancer Institute, National Institute of Biomedical Imaging and Bioengineering, National Institutes of Health, 10 Center Dr, Building 10, Room 1C341, MSC 1182, Bethesda, MD 20892-1182 USA
| | - Lindsey A Hazen
- Center for Interventional Oncology, Radiology and Imaging Sciences, NIH Clinical Center, National Cancer Institute, National Institute of Biomedical Imaging and Bioengineering, National Institutes of Health, 10 Center Dr, Building 10, Room 1C341, MSC 1182, Bethesda, MD 20892-1182 USA
| | - Anna S Christou
- Center for Interventional Oncology, Radiology and Imaging Sciences, NIH Clinical Center, National Cancer Institute, National Institute of Biomedical Imaging and Bioengineering, National Institutes of Health, 10 Center Dr, Building 10, Room 1C341, MSC 1182, Bethesda, MD 20892-1182 USA
| | - Jocelyne Rivera
- Center for Interventional Oncology, Radiology and Imaging Sciences, NIH Clinical Center, National Cancer Institute, National Institute of Biomedical Imaging and Bioengineering, National Institutes of Health, 10 Center Dr, Building 10, Room 1C341, MSC 1182, Bethesda, MD 20892-1182 USA
| | - Robert A Morhard
- Center for Interventional Oncology, Radiology and Imaging Sciences, NIH Clinical Center, National Cancer Institute, National Institute of Biomedical Imaging and Bioengineering, National Institutes of Health, 10 Center Dr, Building 10, Room 1C341, MSC 1182, Bethesda, MD 20892-1182 USA
| | - Ulas Bagci
- Feinberg School of Medicine, Northwestern University, 420 E Superior St, Chicago, IL 60611 USA
| | - Ming Li
- Center for Interventional Oncology, Radiology and Imaging Sciences, NIH Clinical Center, National Cancer Institute, National Institute of Biomedical Imaging and Bioengineering, National Institutes of Health, 10 Center Dr, Building 10, Room 1C341, MSC 1182, Bethesda, MD 20892-1182 USA
| | - Yael Bensoussan
- Morsani College of Medicine, University of South Florida, Tampa, FL, USA
| | - David A Clifton
- Computational Health Informatics Lab, Oxford Institute of Biomedical Engineering, University of Oxford, Old Road Campus Research Building, Headington, Oxford OX3 7DQ, United Kingdom
| | - Bradford J Wood
- Center for Interventional Oncology, Radiology and Imaging Sciences, NIH Clinical Center, National Cancer Institute, National Institute of Biomedical Imaging and Bioengineering, National Institutes of Health, 10 Center Dr, Building 10, Room 1C341, MSC 1182, Bethesda, MD 20892-1182 USA
| |
Collapse
|
13
|
Asiaee M, Nourbakhsh M, Vahedian-Azimi A, Zare M, Jafari R, Atashi SS, Keramatfar A. The feasibility of using acoustic measures for predicting the Total Opacity Scores of chest computed tomography scans in patients with COVID-19. CLINICAL LINGUISTICS & PHONETICS 2024; 38:97-115. [PMID: 36592050 DOI: 10.1080/02699206.2022.2160659] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/30/2021] [Revised: 12/10/2022] [Accepted: 12/13/2022] [Indexed: 06/17/2023]
Abstract
To study the possibility of using acoustic parameters, i.e., Acoustic Voice Quality Index (AVQI) and Maximum Phonation Time (MPT) for predicting the degree of lung involvement in COVID-19 patients. This cross-sectional case-control study was conducted on the voice samples collected from 163 healthy individuals and 181 patients with COVID-19. Each participant produced a sustained vowel/a/, and a phonetically balanced Persian text containing 36 syllables. AVQI and MPT were measured using Praat scripts. Each patient underwent a non-enhanced chest computed tomographic scan and the Total Opacity score was rated to assess the degree of lung involvement. The results revealed significant differences between patients with COVID-19 and healthy individuals in terms of AVQI and MPT. A significant difference was also observed between male and female participants in AVQI and MPT. The results from the receiver operating characteristic curve analysis and area under the curve indicated that MPT (0.909) had higher diagnostic accuracy than AVQI (0.771). A significant relationship was observed between AVQI and TO scores. In the case of MPT, however, no such relationship was observed. The findings indicated that MPT was a better classifier in differentiating patients from healthy individuals, in comparison with AVQI. The results also showed that AVQI can be used as a predictor of the degree of patients' and recovered individuals' lung involvement. A formula is suggested for calculating the degree of lung involvement using AVQI.
Collapse
Affiliation(s)
- Maral Asiaee
- Department of Linguistics, Faculty of Literature, Alzahra University, Tehran, Iran
| | - Mandana Nourbakhsh
- Department of Linguistics, Faculty of Literature, Alzahra University, Tehran, Iran
| | - Amir Vahedian-Azimi
- Trauma Research Center, Nursing faculty, Baqiyatallah University of Medical Sciences, Tehran, Iran
| | - Mohammad Zare
- Department of Statistics, Faculty of Mathematics and Computer Science, Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran
| | - Ramezan Jafari
- Department of Radiology, Health Research Center, Lifestyle Institute, Baqiyatallah University of Medical Sciences, Tehran, Iran
| | - Seyed Shahab Atashi
- Department of Food and Drug control, Jundishapour University of Medical Sciences, Ahvaz, Iran
| | | |
Collapse
|
14
|
Kapetanidis P, Kalioras F, Tsakonas C, Tzamalis P, Kontogiannis G, Karamanidou T, Stavropoulos TG, Nikoletseas S. Respiratory Diseases Diagnosis Using Audio Analysis and Artificial Intelligence: A Systematic Review. SENSORS (BASEL, SWITZERLAND) 2024; 24:1173. [PMID: 38400330 PMCID: PMC10893010 DOI: 10.3390/s24041173] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/15/2023] [Revised: 02/03/2024] [Accepted: 02/04/2024] [Indexed: 02/25/2024]
Abstract
Respiratory diseases represent a significant global burden, necessitating efficient diagnostic methods for timely intervention. Digital biomarkers based on audio, acoustics, and sound from the upper and lower respiratory system, as well as the voice, have emerged as valuable indicators of respiratory functionality. Recent advancements in machine learning (ML) algorithms offer promising avenues for the identification and diagnosis of respiratory diseases through the analysis and processing of such audio-based biomarkers. An ever-increasing number of studies employ ML techniques to extract meaningful information from audio biomarkers. Beyond disease identification, these studies explore diverse aspects such as the recognition of cough sounds amidst environmental noise, the analysis of respiratory sounds to detect respiratory symptoms like wheezes and crackles, as well as the analysis of the voice/speech for the evaluation of human voice abnormalities. To provide a more in-depth analysis, this review examines 75 relevant audio analysis studies across three distinct areas of concern based on respiratory diseases' symptoms: (a) cough detection, (b) lower respiratory symptoms identification, and (c) diagnostics from the voice and speech. Furthermore, publicly available datasets commonly utilized in this domain are presented. It is observed that research trends are influenced by the pandemic, with a surge in studies on COVID-19 diagnosis, mobile data acquisition, and remote diagnosis systems.
Collapse
Affiliation(s)
- Panagiotis Kapetanidis
- Computer Engineering and Informatics Department, University of Patras, 26504 Patras, Greece (C.T.); (G.K.); (S.N.)
| | - Fotios Kalioras
- Computer Engineering and Informatics Department, University of Patras, 26504 Patras, Greece (C.T.); (G.K.); (S.N.)
| | - Constantinos Tsakonas
- Computer Engineering and Informatics Department, University of Patras, 26504 Patras, Greece (C.T.); (G.K.); (S.N.)
| | - Pantelis Tzamalis
- Computer Engineering and Informatics Department, University of Patras, 26504 Patras, Greece (C.T.); (G.K.); (S.N.)
| | - George Kontogiannis
- Computer Engineering and Informatics Department, University of Patras, 26504 Patras, Greece (C.T.); (G.K.); (S.N.)
| | - Theodora Karamanidou
- Pfizer Center for Digital Innovation, 55535 Thessaloniki, Greece; (T.K.); (T.G.S.)
| | | | - Sotiris Nikoletseas
- Computer Engineering and Informatics Department, University of Patras, 26504 Patras, Greece (C.T.); (G.K.); (S.N.)
| |
Collapse
|
15
|
Das A. Intelligent deep learning-based disease monitoring system in 5G network using multi-disease big data. J Biomol Struct Dyn 2024:1-26. [PMID: 38334127 DOI: 10.1080/07391102.2024.2310785] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2023] [Accepted: 01/20/2024] [Indexed: 02/10/2024]
Abstract
Recently, real-world disease monitoring techniques designed based on wearable medical equipment efficiently minimize the mortality rate. Initially, the data are manually collected from the patients to predict five diseases using 5 G frameworks. Then, the collected data are pre-processed to obtain high-quality data using the techniques like contrast enhancement, median filtering, fill empty space, remove repeated value and stemming. The pre-processed data are taken for extracting the features using a One-Dimensional Convolutional Neural Network (1D-CNN) to obtain the deep features. The parameters like hidden neuron count and epoch are tuned by the proposed Modified Predator Presence Probability-based Squirrel Search-Glowworm Swarm Optimization (MPPP-SSGSO) algorithm to enhance the variance. Then, the extracted features acquired using the 1D-CNN are given to the ensemble boosting-based models for predicting the score, which is combined by comprising approaches like Adaptive Boosting (AdaBoost), eXtreme Gradient Boosting (XGBoost) and Category Boosting (CatBoost). Further, the predicted scores obtained from such models are concatenated and passed to the Ensemble Boosting Scores-based Fuzzy Classifier (EBS-FC) for classifying the five different diseases. Here, the membership function of the fuzzy is optimized by the same developed MPPP-SSGSO algorithm for enhancing accuracy. Experiments are conducted, and validation is performed, which showcased that the recommended framework achieved a better outcome rate than the conventional techniques. Finally, the suggested strategy outperforms the current state-of-the-art methods with an accuracy rate of 91.34%.Communicated by Ramaswamy H. Sarma.
Collapse
Affiliation(s)
- Anupam Das
- Department of CSE, The Assam Royal Global University, Betkuchi, Guwahati, Assam, India
| |
Collapse
|
16
|
Kim J, Choi YS, Lee YJ, Yeo SG, Kim KW, Kim MS, Rahmati M, Yon DK, Lee J. Limitations of the Cough Sound-Based COVID-19 Diagnosis Artificial Intelligence Model and its Future Direction: Longitudinal Observation Study. J Med Internet Res 2024; 26:e51640. [PMID: 38319694 PMCID: PMC10879967 DOI: 10.2196/51640] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/06/2023] [Revised: 11/10/2023] [Accepted: 01/02/2024] [Indexed: 02/07/2024] Open
Abstract
BACKGROUND The outbreak of SARS-CoV-2 in 2019 has necessitated the rapid and accurate detection of COVID-19 to manage patients effectively and implement public health measures. Artificial intelligence (AI) models analyzing cough sounds have emerged as promising tools for large-scale screening and early identification of potential cases. OBJECTIVE This study aimed to investigate the efficacy of using cough sounds as a diagnostic tool for COVID-19, considering the unique acoustic features that differentiate positive and negative cases. We investigated whether an AI model trained on cough sound recordings from specific periods, especially the early stages of the COVID-19 pandemic, were applicable to the ongoing situation with persistent variants. METHODS We used cough sound recordings from 3 data sets (Cambridge, Coswara, and Virufy) representing different stages of the pandemic and variants. Our AI model was trained using the Cambridge data set with subsequent evaluation against all data sets. The performance was analyzed based on the area under the receiver operating curve (AUC) across different data measurement periods and COVID-19 variants. RESULTS The AI model demonstrated a high AUC when tested with the Cambridge data set, indicative of its initial effectiveness. However, the performance varied significantly with other data sets, particularly in detecting later variants such as Delta and Omicron, with a marked decline in AUC observed for the latter. These results highlight the challenges in maintaining the efficacy of AI models against the backdrop of an evolving virus. CONCLUSIONS While AI models analyzing cough sounds offer a promising noninvasive and rapid screening method for COVID-19, their effectiveness is challenged by the emergence of new virus variants. Ongoing research and adaptations in AI methodologies are crucial to address these limitations. The adaptability of AI models to evolve with the virus underscores their potential as a foundational technology for not only the current pandemic but also future outbreaks, contributing to a more agile and resilient global health infrastructure.
Collapse
Affiliation(s)
- Jina Kim
- Department of Biomedical Engineering, Kyung Hee University, Seoul, Republic of Korea
| | - Yong Sung Choi
- Department of Biomedical Engineering, Kyung Hee University, Seoul, Republic of Korea
| | - Young Joo Lee
- Department of Biomedical Engineering, Kyung Hee University, Seoul, Republic of Korea
| | - Seung Geun Yeo
- Department of Biomedical Engineering, Kyung Hee University, Seoul, Republic of Korea
| | - Kyung Won Kim
- Department of Radiology and Research Institute of Radiology, Asan Image Metrics, Clinical Trial Center, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| | - Min Seo Kim
- Medical and Population Genetics and Cardiovascular Disease Initiative, Broad Institute of MIT and Harvard, Cambridge, MA, United States
| | - Masoud Rahmati
- Department of Physical Education and Sport Sciences, Faculty of Literature and Human Sciences, Lorestan University, Khoramabad, Iran
- Department of Physical Education and Sport Sciences, Faculty of Literature and Humanities, Vali-E-Asr University of Rafsanjan, Rafsanjan, Iran
| | - Dong Keon Yon
- Center for Digital Health, Medical Science Research Institute, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, Seoul, Republic of Korea
- Department of Pediatrics, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, Seoul, Republic of Korea
| | - Jinseok Lee
- Department of Biomedical Engineering, Kyung Hee University, Seoul, Republic of Korea
- Department of Electronics and Information Convergence Engineering, Kyung Hee University, Yongin, Republic of Korea
| |
Collapse
|
17
|
Ghrabli S, Elgendi M, Menon C. Identifying unique spectral fingerprints in cough sounds for diagnosing respiratory ailments. Sci Rep 2024; 14:593. [PMID: 38182601 PMCID: PMC10770161 DOI: 10.1038/s41598-023-50371-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/10/2023] [Accepted: 12/19/2023] [Indexed: 01/07/2024] Open
Abstract
Coughing, a prevalent symptom of many illnesses, including COVID-19, has led researchers to explore the potential of cough sound signals for cost-effective disease diagnosis. Traditional diagnostic methods, which can be expensive and require specialized personnel, contrast with the more accessible smartphone analysis of coughs. Typically, coughs are classified as wet or dry based on their phase duration. However, the utilization of acoustic analysis for diagnostic purposes is not widespread. Our study examined cough sounds from 1183 COVID-19-positive patients and compared them with 341 non-COVID-19 cough samples, as well as analyzing distinctions between pneumonia and asthma-related coughs. After rigorous optimization across frequency ranges, specific frequency bands were found to correlate with each respiratory ailment. Statistical separability tests validated these findings, and machine learning algorithms, including linear discriminant analysis and k-nearest neighbors classifiers, were employed to confirm the presence of distinct frequency bands in the cough signal power spectrum associated with particular diseases. The identification of these acoustic signatures in cough sounds holds the potential to transform the classification and diagnosis of respiratory diseases, offering an affordable and widely accessible healthcare tool.
Collapse
Affiliation(s)
- Syrine Ghrabli
- Biomedical and Mobile Health Technology Lab, ETH Zurich, 8008, Zurich, Switzerland
- Department of Physics, ETH Zurich, 8093, Zurich, Switzerland
| | - Mohamed Elgendi
- Biomedical and Mobile Health Technology Lab, ETH Zurich, 8008, Zurich, Switzerland.
| | - Carlo Menon
- Biomedical and Mobile Health Technology Lab, ETH Zurich, 8008, Zurich, Switzerland.
| |
Collapse
|
18
|
Saeed T, Ijaz A, Sadiq I, Qureshi HN, Rizwan A, Imran A. An AI-Enabled Bias-Free Respiratory Disease Diagnosis Model Using Cough Audio. Bioengineering (Basel) 2024; 11:55. [PMID: 38247932 PMCID: PMC10813025 DOI: 10.3390/bioengineering11010055] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/28/2023] [Revised: 12/25/2023] [Accepted: 01/03/2024] [Indexed: 01/23/2024] Open
Abstract
Cough-based diagnosis for respiratory diseases (RDs) using artificial intelligence (AI) has attracted considerable attention, yet many existing studies overlook confounding variables in their predictive models. These variables can distort the relationship between cough recordings (input data) and RD status (output variable), leading to biased associations and unrealistic model performance. To address this gap, we propose the Bias-Free Network (RBF-Net), an end-to-end solution that effectively mitigates the impact of confounders in the training data distribution. RBF-Net ensures accurate and unbiased RD diagnosis features, emphasizing its relevance by incorporating a COVID-19 dataset in this study. This approach aims to enhance the reliability of AI-based RD diagnosis models by navigating the challenges posed by confounding variables. A hybrid of a Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks is proposed for the feature encoder module of RBF-Net. An additional bias predictor is incorporated in the classification scheme to formulate a conditional Generative Adversarial Network (c-GAN) that helps in decorrelating the impact of confounding variables from RD prediction. The merit of RBF-Net is demonstrated by comparing classification performance with a State-of-The-Art (SoTA) Deep Learning (DL) model (CNN-LSTM) after training on different unbalanced COVID-19 data sets, created by using a large-scale proprietary cough data set. RBF-Net proved its robustness against extremely biased training scenarios by achieving test set accuracies of 84.1%, 84.6%, and 80.5% for the following confounding variables-gender, age, and smoking status, respectively. RBF-Net outperforms the CNN-LSTM model test set accuracies by 5.5%, 7.7%, and 8.2%, respectively.
Collapse
Affiliation(s)
- Tabish Saeed
- AI4Networks Research Center, Department of Electrical & Computer Engineering, University of Oklahoma, Tulsa, OK 74135, USA; (H.N.Q.); (A.I.)
| | - Aneeqa Ijaz
- AI4Networks Research Center, Department of Electrical & Computer Engineering, University of Oklahoma, Tulsa, OK 74135, USA; (H.N.Q.); (A.I.)
| | - Ismail Sadiq
- James Watt School of Engineering, University of Glasgow, Glasgow G12 8QQ, UK;
| | - Haneya Naeem Qureshi
- AI4Networks Research Center, Department of Electrical & Computer Engineering, University of Oklahoma, Tulsa, OK 74135, USA; (H.N.Q.); (A.I.)
| | - Ali Rizwan
- AI4lyf, Bahria Town Lahore, Lahore 54000, Pakistan;
| | - Ali Imran
- AI4Networks Research Center, Department of Electrical & Computer Engineering, University of Oklahoma, Tulsa, OK 74135, USA; (H.N.Q.); (A.I.)
- James Watt School of Engineering, University of Glasgow, Glasgow G12 8QQ, UK;
| |
Collapse
|
19
|
Badnjević A, Pokvić LG, Smajlhodžić-Deljo M, Spahić L, Bego T, Meseldžić N, Prnjavorac L, Prnjavorac B, Bedak O. Application of artificial intelligence for the classification of the clinical outcome and therapy in patients with viral infections: The case of COVID-19. Technol Health Care 2024; 32:1859-1870. [PMID: 37840512 DOI: 10.3233/thc-230917] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/17/2023]
Abstract
BACKGROUND With the end of the coronavirus disease 2019 (COVID-19) pandemic, it becomes intriguing to observe the impact of innovative digital technologies on the diagnosis and management of diseases, in order to improve clinical outcomes for patients. OBJECTIVE The research aims to enhance diagnostics, prediction, and personalized treatment for patients across three classes of clinical severity (mild, moderate, and severe). What sets this study apart is its innovative approach, wherein classification extends beyond mere disease presence, encompassing the classification of disease severity. This novel perspective lays the foundation for a crucial decision support system during patient triage. METHODS An artificial neural network, as a deep learning technique, enabled the development of a complex model based on the analysis of data collected during the process of diagnosing and treating 1000 patients at the Tešanj General Hospital, Bosnia and Herzegovina. RESULTS The final model achieved a classification accuracy of 82.4% on the validation data set, which testifies to the successful application of the artificial neural network in the classification of clinical outcomes and therapy in patients infected with viral infections. CONCLUSION The results obtained show that expert systems are valuable tools for decision support in healthcare in communities with limited resources and increased demands. The research has the potential to improve patient care for future epidemics and pandemics.
Collapse
Affiliation(s)
- Almir Badnjević
- Department of Pharmaceutical Biochemistry and Laboratory Diagnostics, Faculty of Pharmacy, University of Sarajevo, Sarajevo, Bosnia and Herzegovina
| | - Lejla Gurbeta Pokvić
- Verlab Research Institute for Biomedical Engineering, Medical Devices and Artificial Intelligence, Sarajevo, Bosnia and Herzegovina
| | - Merima Smajlhodžić-Deljo
- Verlab Research Institute for Biomedical Engineering, Medical Devices and Artificial Intelligence, Sarajevo, Bosnia and Herzegovina
| | - Lemana Spahić
- Verlab Research Institute for Biomedical Engineering, Medical Devices and Artificial Intelligence, Sarajevo, Bosnia and Herzegovina
| | - Tamer Bego
- Department of Pharmaceutical Biochemistry and Laboratory Diagnostics, Faculty of Pharmacy, University of Sarajevo, Sarajevo, Bosnia and Herzegovina
| | - Neven Meseldžić
- Department of Pharmaceutical Biochemistry and Laboratory Diagnostics, Faculty of Pharmacy, University of Sarajevo, Sarajevo, Bosnia and Herzegovina
| | | | - Besim Prnjavorac
- Department of Pharmaceutical Biochemistry and Laboratory Diagnostics, Faculty of Pharmacy, University of Sarajevo, Sarajevo, Bosnia and Herzegovina
| | - Omer Bedak
- General Hospital Tešanj, Tešanj, Bosnia and Herzegovina
| |
Collapse
|
20
|
Mootassim-Billah S, Schoentgen J, De Bodt M, Roper N, Digonnet A, Le Tensorer M, Van Nuffelen G, Van Gestel D. Acoustic Analysis of Voluntary Coughs, Throat Clearings, and Induced Reflexive Coughs in a Healthy Population. Dysphagia 2023; 38:1467-1486. [PMID: 37245187 PMCID: PMC10225042 DOI: 10.1007/s00455-023-10574-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/21/2022] [Accepted: 03/31/2023] [Indexed: 05/29/2023]
Abstract
Cough efficacy is considered a reliable predictor of the aspiration risk in head and neck cancer patients with radiation-associated dysphagia. Currently, coughing is assessed perceptually or aerodynamically. The goal of our research is to develop methods of acoustic cough analysis. In this study, we examined in a healthy population the acoustical differences between three protective maneuvers: voluntary cough, voluntary throat clearing, and induced reflexive cough. Forty healthy participants were included in this study. Voluntary cough, voluntary throat clearing, and reflexive cough samples were recorded and analyzed acoustically. Temporal acoustic features were the following: the slope and curvature of the amplitude contour, as well as the average, slope, and curvature of the sample entropy and kurtosis contours of the recorded signal. Spectral features were the relative energy in the frequency bands (0-400 Hz, 400-800 Hz, 800-1600 Hz, 1600 Hz-3200 Hz, > 3200 Hz) as well as the weighted spectral energy. Results showed that, compared to a voluntary cough, a throat clearing starts with a weaker onset pulse and involves oscillations from the onset to the offset (concave curvature of the amplitude contour, p < 0.05), lower average (p < 0.05), and slope (p < 0.05) as well as lower convex curvature (p < 0.05) of the kurtosis contour. An induced reflexive cough starts with a higher and briefer onset burst and includes higher frication noise (larger convexity of the curvature of the amplitude and kurtosis contours (p < 0.05)) compared to a voluntary cough. The conclusion is that voluntary coughs are acoustically significantly different from voluntary throat clearings and induced reflexive coughs.
Collapse
Affiliation(s)
- Sofiana Mootassim-Billah
- Department of Radiation Oncology, Speech Therapy, Institut Jules Bordet, Université Libre de Bruxelles, Brussels, Belgium.
| | - Jean Schoentgen
- Department of Biomechatronics, Université Libre de Bruxelles, Brussels, Belgium
| | - Marc De Bodt
- Department of Otolaryngology and Head and Neck Surgery, University Rehabilitation Center for Communication Disorders, Antwerp University Hospital, Antwerp, Belgium
- Department of Translational Neurosciences, Faculty of Medicine and Health Sciences, University of Antwerp, Antwerp, Belgium
- Department of Logopaedics and Audiological Sciences, Faculty of Medicine and Health Sciences, University of Ghent, Ghent, Belgium
| | - Nicolas Roper
- Department of Oto-Rhino-Laryngology and Head & Neck Surgery, Erasme Hospital, Université Libre de Bruxelles, Brussels, Belgium
| | - Antoine Digonnet
- Department of Surgical Oncology, Head and Neck Surgery Unit, Institut Jules Bordet, Université Libre de Bruxelles, Brussels, Belgium
| | - Mathilde Le Tensorer
- Speech Therapy Unit, Institut Jules Bordet, Hôpital Universitaire de Bruxelles, Université Libre de Bruxelles, Brussels, Belgium
| | - Gwen Van Nuffelen
- Department of Otolaryngology and Head and Neck Surgery, University Rehabilitation Center for Communication Disorders, Antwerp University Hospital, Antwerp, Belgium
- Department of Translational Neurosciences, Faculty of Medicine and Health Sciences, University of Antwerp, Antwerp, Belgium
- Department of Logopaedics and Audiological Sciences, Faculty of Medicine and Health Sciences, University of Ghent, Ghent, Belgium
| | - Dirk Van Gestel
- Department of Radiation Oncology, Head and Neck Unit, Institut Jules Bordet, Université Libre de Bruxelles, Brussels, Belgium
| |
Collapse
|
21
|
Pan X, Hounye AH, Zhao Y, Cao C, Wang J, Abidi MV, Hou M, Xiong L, Chai X. A Digital Mask-Voiceprint System for Postpandemic Surveillance and Tracing Based on the STRONG Strategy. J Med Internet Res 2023; 25:e44795. [PMID: 37856760 PMCID: PMC10660213 DOI: 10.2196/44795] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/04/2022] [Revised: 09/28/2023] [Accepted: 10/18/2023] [Indexed: 10/21/2023] Open
Abstract
Lockdowns and border closures due to COVID-19 imposed mental, social, and financial hardships in many societies. Living with the virus and resuming normal life are increasingly being advocated due to decreasing virus severity and widespread vaccine coverage. However, current trends indicate a continued absence of effective contingency plans to stop the next more virulent variant of the pandemic. The COVID-19-related mask waste crisis has also caused serious environmental problems and virus spreads. It is timely and important to consider how to precisely implement surveillance for the dynamic clearance of COVID-19 and how to efficiently manage discarded masks to minimize disease transmission and environmental hazards. In this viewpoint, we sought to address this issue by proposing an appropriate strategy for intelligent surveillance of infected cases and centralized management of mask waste. Such an intelligent strategy against COVID-19, consisting of wearable mask sample collectors (masklect) and voiceprints and based on the STRONG (Spatiotemporal Reporting Over Network and GPS) strategy, could enable the resumption of social activities and economic recovery and ensure a safe public health environment sustainably.
Collapse
Affiliation(s)
- Xiaogao Pan
- Department of Emergency Medicine, Second Xiangya Hospital, Central South University, Changsha, China
- Emergency Medicine and Difficult Diseases Institute, Central South University, Changsha, China
| | | | - Yuqi Zhao
- Department of Gastroenterology, Second Xiangya Hospital, Central South University, Changsha, China
| | - Cong Cao
- School of Mathematics and Statistics, Central South University, Changsha, China
| | - Jiaoju Wang
- School of Mathematics and Statistics, Central South University, Changsha, China
| | - Mimi Venunye Abidi
- General Surgery Department, Second Xiangya Hospital, Central South University, Changsha, China
| | - Muzhou Hou
- School of Mathematics and Statistics, Central South University, Changsha, China
| | - Li Xiong
- General Surgery Department, Second Xiangya Hospital, Central South University, Changsha, China
| | - Xiangping Chai
- Department of Emergency Medicine, Second Xiangya Hospital, Central South University, Changsha, China
- Emergency Medicine and Difficult Diseases Institute, Central South University, Changsha, China
| |
Collapse
|
22
|
Orlandic L, Teijeiro T, Atienza D. A semi-supervised algorithm for improving the consistency of crowdsourced datasets: The COVID-19 case study on respiratory disorder classification. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2023; 241:107743. [PMID: 37598473 DOI: 10.1016/j.cmpb.2023.107743] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/16/2022] [Revised: 07/12/2023] [Accepted: 08/02/2023] [Indexed: 08/22/2023]
Abstract
BACKGROUND AND OBJECTIVE Cough audio signal classification is a potentially useful tool in screening for respiratory disorders, such as COVID-19. Since it is dangerous to collect data from patients with contagious diseases, many research teams have turned to crowdsourcing to quickly gather cough sound data. The COUGHVID dataset enlisted expert physicians to annotate and diagnose the underlying diseases present in a limited number of recordings. However, this approach suffers from potential cough mislabeling, as well as disagreement between experts. METHODS In this work, we use a semi-supervised learning (SSL) approach - based on audio signal processing tools and interpretable machine learning models - to improve the labeling consistency of the COUGHVID dataset for 1) COVID-19 versus healthy cough sound classification 2) distinguishing wet from dry coughs, and 3) assessing cough severity. First, we leverage SSL expert knowledge aggregation techniques to overcome the labeling inconsistencies and label sparsity in the dataset. Next, our SSL approach is used to identify a subsample of re-labeled COUGHVID audio samples that can be used to train or augment future cough classifiers. RESULTS The consistency of the re-labeled COVID-19 and healthy data is demonstrated in that it exhibits a high degree of inter-class feature separability: 3x higher than that of the user-labeled data. Similarly, the SSL method increases this separability by 11.3x for cough type and 5.1x for severity classifications. Furthermore, the spectral differences in the user-labeled audio segments are amplified in the re-labeled data, resulting in significantly different power spectral densities between healthy and COVID-19 coughs in the 1-1.5 kHz range (p=1.2×10-64), which demonstrates both the increased consistency of the new dataset and its explainability from an acoustic perspective. Finally, we demonstrate how the re-labeled dataset can be used to train a COVID-19 classifier, achieving an AUC of 0.797. CONCLUSIONS We propose a SSL expert knowledge aggregation technique for the field of cough sound classification for the first time, and demonstrate how it can be used to combine the medical knowledge of multiple experts in an explainable fashion, thus providing abundant, consistent data for cough classification tasks.
Collapse
Affiliation(s)
- Lara Orlandic
- Embedded Systems Laboratory (ESL), EPFL, Lausanne, Switzerland.
| | - Tomas Teijeiro
- Embedded Systems Laboratory (ESL), EPFL, Lausanne, Switzerland; Department of Mathematics, University of the Basque Country (UPV/EHU), Spain
| | - David Atienza
- Embedded Systems Laboratory (ESL), EPFL, Lausanne, Switzerland
| |
Collapse
|
23
|
Pentakota P, Rudraraju G, Sripada NR, Mamidgi B, Gottipulla C, Jalukuru C, Palreddy SD, Bhoge NKR, Firmal P, Yechuri V, Jain M, Peddireddi VS, Bhimarasetty DM, Sreenivas S, Prasad K KL, Joshi N, Vijayan S, Turaga S, Avasarala V. Screening COVID-19 by Swaasa AI platform using cough sounds: a cross-sectional study. Sci Rep 2023; 13:18284. [PMID: 37880351 PMCID: PMC10600180 DOI: 10.1038/s41598-023-45104-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/29/2023] [Accepted: 10/16/2023] [Indexed: 10/27/2023] Open
Abstract
The Advent of Artificial Intelligence (AI) has led to the use of auditory data for detecting various diseases, including COVID-19. SARS-CoV-2 infection has claimed more than six million lives to date and therefore, needs a robust screening technique to control the disease spread. In the present study we created and validated the Swaasa AI platform, which uses the signature cough sound and symptoms presented by patients to screen and prioritize COVID-19 patients. We collected cough data from 234 COVID-19 suspects to validate our Convolutional Neural Network (CNN) architecture and Feedforward Artificial Neural Network (FFANN) (tabular features) based algorithm. The final output from both models was combined to predict the likelihood of having the disease. During the clinical validation phase, our model showed a 75.54% accuracy rate in detecting the likely presence of COVID-19, with 95.45% sensitivity and 73.46% specificity. We conducted pilot testing on 183 presumptive COVID subjects, of which 58 were truly COVID-19 positive, resulting in a Positive Predictive Value of 70.73%. Due to the high cost and technical expertise required for currently available rapid screening methods, there is a need for a cost-effective and remote monitoring tool that can serve as a preliminary screening method for potential COVID-19 subjects. Therefore, Swaasa would be highly beneficial in detecting the disease and could have a significant impact in reducing its spread.
Collapse
Affiliation(s)
| | | | | | | | | | - Charan Jalukuru
- Salcit Technologies, Jayabheri Silicon Towers, Hyderabad, India
| | | | | | - Priyanka Firmal
- Salcit Technologies, Jayabheri Silicon Towers, Hyderabad, India
| | - Venkat Yechuri
- Salcit Technologies, Jayabheri Silicon Towers, Hyderabad, India
| | - Manmohan Jain
- Salcit Technologies, Jayabheri Silicon Towers, Hyderabad, India
| | | | | | - S Sreenivas
- Andhra Medical College, Visakhapatnam, India
| | | | | | - Shibu Vijayan
- Qure.Ai Technologies, Oberoi Commerz II, Mumbai, India
| | | | - Vardhan Avasarala
- Otolaryngology - Head and Neck Surgery, Northeast Ohio Medical University, Rootstown, USA
| |
Collapse
|
24
|
Celik G. CovidCoughNet: A new method based on convolutional neural networks and deep feature extraction using pitch-shifting data augmentation for covid-19 detection from cough, breath, and voice signals. Comput Biol Med 2023; 163:107153. [PMID: 37321101 PMCID: PMC10249348 DOI: 10.1016/j.compbiomed.2023.107153] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/09/2023] [Revised: 05/25/2023] [Accepted: 06/07/2023] [Indexed: 06/17/2023]
Abstract
This study proposes a new deep learning-based method that demonstrates high performance in detecting Covid-19 disease from cough, breath, and voice signals. This impressive method, named CovidCoughNet, consists of a deep feature extraction network (InceptionFireNet) and a prediction network (DeepConvNet). The InceptionFireNet architecture, based on Inception and Fire modules, was designed to extract important feature maps. The DeepConvNet architecture, which is made up of convolutional neural network blocks, was developed to predict the feature vectors obtained from the InceptionFireNet architecture. The COUGHVID dataset containing cough data and the Coswara dataset containing cough, breath, and voice signals were used as the data sets. The pitch-shifting technique was used to data augmentation the signal data, which significantly contributed to improving performance. Additionally, Chroma features (CF), Root mean square energy (RMSE), Spectral centroid (SC), Spectral bandwidth (SB), Spectral rolloff (SR), Zero crossing rate (ZCR), and Mel frequency cepstral coefficients (MFCC) feature extraction techniques were used to extract important features from voice signals. Experimental studies have shown that using the pitch-shifting technique improved performance by around 3% compared to raw signals. When the proposed model was used with the COUGHVID dataset (Healthy, Covid-19, and Symptomatic), a high performance of 99.19% accuracy, 0.99 precision, 0.98 recall, 0.98 F1-Score, 97.77% specificity, and 98.44% AUC was achieved. Similarly, when the voice data in the Coswara dataset was used, higher performance was achieved compared to the cough and breath studies, with 99.63% accuracy, 100% precision, 0.99 recall, 0.99 F1-Score, 99.24% specificity, and 99.24% AUC. Moreover, when compared with current studies in the literature, the proposed model was observed to exhibit highly successful performance. The codes and details of the experimental studies can be accessed from the relevant Github page: (https://github.com/GaffariCelik/CovidCoughNet).
Collapse
Affiliation(s)
- Gaffari Celik
- Agri Ibrahim Cecen University, Department of Computer Technology, Agri, Turkey.
| |
Collapse
|
25
|
Duey AH, Rana A, Siddi F, Hussein H, Onnela JP, Smith TR. Daily Pain Prediction Using Smartphone Speech Recordings of Patients With Spine Disease. Neurosurgery 2023; 93:670-677. [PMID: 36995101 DOI: 10.1227/neu.0000000000002474] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/18/2022] [Accepted: 02/02/2023] [Indexed: 03/31/2023] Open
Abstract
BACKGROUND Pain evaluation remains largely subjective in neurosurgical practice, but machine learning provides the potential for objective pain assessment tools. OBJECTIVE To predict daily pain levels using speech recordings from personal smartphones of a cohort of patients with diagnosed neurological spine disease. METHODS Patients with spine disease were enrolled through a general neurosurgical clinic with approval from the institutional ethics committee. At-home pain surveys and speech recordings were administered at regular intervals through the Beiwe smartphone application. Praat audio features were extracted from the speech recordings to be used as input to a K-nearest neighbors (KNN) machine learning model. The pain scores were transformed from a 0 to 10 scale to low and high pain for better discriminative capacity. RESULTS A total of 60 patients were enrolled, and 384 observations were used to train and test the prediction model. Using the KNN prediction model, an accuracy of 71% with a positive predictive value of 0.71 was achieved in classifying pain intensity into high and low. The model showed 0.71 precision for high pain and 0.70 precision for low pain. Recall of high pain was 0.74, and recall of low pain was 0.67. The overall F1 score was 0.73. CONCLUSION Our study uses a KNN to model the relationship between speech features and pain levels collected from personal smartphones of patients with spine disease. The proposed model is a stepping stone for the development of objective pain assessment in neurosurgery clinical practice.
Collapse
Affiliation(s)
- Akiro H Duey
- Department of Neurosurgery, Computational Neuroscience Outcomes Center, Brigham and Women's Hospital, Harvard Medical School, Boston , Massachusetts , USA
- Icahn School of Medicine at Mount Sinai, New York , New York , USA
| | - Aakanksha Rana
- Department of Neurosurgery, Computational Neuroscience Outcomes Center, Brigham and Women's Hospital, Harvard Medical School, Boston , Massachusetts , USA
- McGovern Institute for Brain Research, Massachusetts Institute of Technology, Cambridge , Massachusetts , USA
| | - Francesca Siddi
- Department of Neurosurgery, Computational Neuroscience Outcomes Center, Brigham and Women's Hospital, Harvard Medical School, Boston , Massachusetts , USA
- Departments of Neurosurgery, Leiden University Medical Center, Leiden , The Netherlands
| | - Helweh Hussein
- Department of Neurosurgery, Computational Neuroscience Outcomes Center, Brigham and Women's Hospital, Harvard Medical School, Boston , Massachusetts , USA
| | - Jukka-Pekka Onnela
- Department of Biostatistics, Harvard T. H. Chan School of Public Health, Boston , Massachusetts , USA
| | - Timothy R Smith
- Department of Neurosurgery, Computational Neuroscience Outcomes Center, Brigham and Women's Hospital, Harvard Medical School, Boston , Massachusetts , USA
- Department of Neurosurgery, Brigham and Women's Hospital, Harvard Medical School, Boston , Massachusetts , USA
| |
Collapse
|
26
|
Sara JDS, Orbelo D, Maor E, Lerman LO, Lerman A. Guess What We Can Hear-Novel Voice Biomarkers for the Remote Detection of Disease. Mayo Clin Proc 2023; 98:1353-1375. [PMID: 37661144 PMCID: PMC10043966 DOI: 10.1016/j.mayocp.2023.03.007] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/25/2022] [Revised: 02/08/2023] [Accepted: 03/16/2023] [Indexed: 03/30/2023]
Abstract
The advancement of digital biomarkers and the provision of remote health care greatly progressed during the coronavirus disease 2019 global pandemic. Combining voice/speech data with artificial intelligence and machine-based learning offers a novel solution to the growing demand for telemedicine. Voice biomarkers, obtained from the extraction of characteristic acoustic and linguistic features, are associated with a variety of diseases and even coronavirus disease 2019. In the current review, we (1) describe the basis on which digital voice biomarkers could facilitate "telemedicine," (2) discuss potential mechanisms that may explain the association between voice biomarkers and disease, (3) offer a novel classification system to conceptualize voice biomarkers depending on different methods for recording and analyzing voice/speech samples, (4) outline evidence revealing an association between voice biomarkers and a number of disease states, and (5) describe the process of developing a voice biomarker from recording, storing voice samples, and extracting acoustic and linguistic features relevant to training and testing deep and machine-based learning algorithms to detect disease. We further explore several important future considerations in this area of research, including the necessity for clinical trials and the importance of safeguarding data and individual privacy. To this end, we searched PubMed and Google Scholar to identify studies evaluating the relationship between voice/speech features and biomarkers and various diseases. Search terms included digital biomarker, telemedicine, voice features, voice biomarker, speech features, speech biomarkers, acoustics, linguistics, cardiovascular disease, neurologic disease, psychiatric disease, and infectious disease. The search was limited to studies published in English in peer-reviewed journals between 1980 and the present. To identify potential studies not captured by our database search strategy, we also searched studies listed in the bibliography of relevant publications and reviews.
Collapse
Affiliation(s)
| | - Diana Orbelo
- Division of Otolaryngology, Mayo Clinic College of Medicine and Science, Rochester, MN; Chaim Sheba Medical Center, Tel HaShomer, Israel
| | - Elad Maor
- Sackler School of Medicine, Tel Aviv University, Tel Aviv, Israel
| | - Lilach O Lerman
- Division of Nephrology and Hypertension, Mayo Clinic Rochester, MN
| | - Amir Lerman
- Department of Cardiovascular Medicine, Mayo Clinic College of Medicine and Science, Rochester, MN.
| |
Collapse
|
27
|
Liyanarachchi R, Wijekoon J, Premathilaka M, Vidhanaarachchi S. COVID-19 symptom identification using Deep Learning and hardware emulated systems. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2023; 125:106709. [PMID: 38620194 PMCID: PMC10300286 DOI: 10.1016/j.engappai.2023.106709] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/17/2022] [Revised: 05/27/2023] [Accepted: 06/21/2023] [Indexed: 04/17/2024]
Abstract
The COVID-19 pandemic disrupted regular global activities in every possible way. This pandemic, caused by the transmission of the infectious Coronavirus, is characterized by main symptoms such as fever, fatigue, cough, and loss of smell. A current key focus of the scientific community is to develop automated methods that can effectively identify COVID-19 patients and are also adaptable for foreseen future virus outbreaks. To classify COVID-19 suspects, it is required to use contactless automatic measurements of more than one symptom. This study explores the effectiveness of using Deep Learning combined with a hardware-emulated system to identify COVID-19 patients in Sri Lanka based on two main symptoms: cough and shortness of breath. To achieve this, a Convolutional Neural Network (CNN) based on Transfer Learning was employed to analyze and compare the features of a COVID-19 cough with other types of coughs. Real-time video footage was captured using a FLIR C2 thermal camera and a web camera and subsequently processed using OpenCV image processing algorithms. The objective was to detect the nasal cavities in the video frames and measure the breath cycles per minute, thereby identifying instances of shortness of breath. The proposed method was first tested on crowd-sourced datasets (Coswara, Coughvid, ESC-50, and a dataset from Kaggle) obtained online. It was then applied and verified using a dataset obtained from local hospitals in Sri Lanka. The accuracy of the developed methodologies in diagnosing cough resemblance and recognizing shortness of breath was found to be 94% and 95%, respectively.
Collapse
|
28
|
Fischer A, Aguayo GA, Oustric P, Morin L, Larche J, Benoy C, Fagherazzi G. Co-Design of a Voice-Based Digital Health Solution to Monitor Persisting Symptoms Related to COVID-19 (UpcomingVoice Study): Protocol for a Mixed Methods Study. JMIR Res Protoc 2023; 12:e46103. [PMID: 37335611 DOI: 10.2196/46103] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/30/2023] [Revised: 04/27/2023] [Accepted: 04/28/2023] [Indexed: 06/21/2023] Open
Abstract
BACKGROUND Between 10% and 20% of people with a COVID-19 infection will develop the so-called long COVID syndrome, which is characterized by fluctuating symptoms. Long COVID has a high impact on the quality of life of affected people, who often feel abandoned by the health care system and are demanding new tools to help them manage their symptoms. New digital monitoring solutions could allow them to visualize the evolution of their symptoms and could be tools to communicate with health care professionals (HCPs). The use of voice and vocal biomarkers could facilitate the accurate and objective monitoring of persisting and fluctuating symptoms. However, to assess the needs and ensure acceptance of this innovative approach by its potential users-people with persisting COVID-19-related symptoms, with or without a long COVID diagnosis, and HCPs involved in long COVID care-it is crucial to include them in the entire development process. OBJECTIVE In the UpcomingVoice study, we aimed to define the most relevant aspects of daily life that people with long COVID would like to be improved, assess how the use of voice and vocal biomarkers could be a potential solution to help them, and determine the general specifications and specific items of a digital health solution to monitor long COVID symptoms using vocal biomarkers with its end users. METHODS UpcomingVoice is a cross-sectional mixed methods study and consists of a quantitative web-based survey followed by a qualitative phase based on semistructured individual interviews and focus groups. People with long COVID and HCPs in charge of patients with long COVID will be invited to participate in this fully web-based study. The quantitative data collected from the survey will be analyzed using descriptive statistics. Qualitative data from the individual interviews and the focus groups will be transcribed and analyzed using a thematic analysis approach. RESULTS The study was approved by the National Research Ethics Committee of Luxembourg (number 202208/04) in August 2022 and started in October 2022 with the launch of the web-based survey. Data collection will be completed in September 2023, and the results will be published in 2024. CONCLUSIONS This mixed methods study will identify the needs of people affected by long COVID in their daily lives and describe the main symptoms or problems that would need to be monitored and improved. We will determine how using voice and vocal biomarkers could meet these needs and codevelop a tailored voice-based digital health solution with its future end users. This project will contribute to improving the quality of life and care of people with long COVID. The potential transferability to other diseases will be explored, which will contribute to the deployment of vocal biomarkers in general. TRIAL REGISTRATION ClinicalTrials.gov NCT05546918; https://clinicaltrials.gov/ct2/show/NCT05546918. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID) DERR1-10.2196/46103.
Collapse
Affiliation(s)
- Aurelie Fischer
- Deep Digital Phenotyping Research Unit, Department of Precision Health, Luxembourg Institute of Health, Strassen, Luxembourg
- Université de Lorraine, Nancy, France
| | - Gloria A Aguayo
- Deep Digital Phenotyping Research Unit, Department of Precision Health, Luxembourg Institute of Health, Strassen, Luxembourg
| | | | - Laurent Morin
- Association ApresJ20 COVID Long France, Luce, France
| | - Jerome Larche
- Fédération des Acteurs de la Coordination en Santé-Occitanie, Hôpital La Grave, Toulouse, France
| | - Charles Benoy
- Centre Hospitalier Neuro-Psychiatrique, Ettelbruck, Luxembourg
- Universitäre Psychiatrische Kliniken Basel, Basel, Switzerland
| | - Guy Fagherazzi
- Deep Digital Phenotyping Research Unit, Department of Precision Health, Luxembourg Institute of Health, Strassen, Luxembourg
| |
Collapse
|
29
|
Awais M, Bhuva A, Bhuva D, Fatima S, Sadiq T. Optimized DEC: An effective cough detection framework using optimal weighted Features-aided deep Ensemble classifier for COVID-19. Biomed Signal Process Control 2023:105026. [PMID: 37361196 PMCID: PMC10183638 DOI: 10.1016/j.bspc.2023.105026] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/13/2022] [Revised: 04/17/2023] [Accepted: 05/09/2023] [Indexed: 06/28/2023]
Abstract
Since the year 2019, the entire world has been facing the most hazardous and contagious disease as Corona Virus Disease 2019 (COVID-19). Based on the symptoms, the virus can be identified and diagnosed. Amongst, cough is the primary syndrome to detect COVID-19. Existing method requires a long processing time. Early screening and detection is a complex task. To surmount the research drawbacks, a novel ensemble-based deep learning model is designed on heuristic development. The prime intention of the designed work is to detect COVID-19 disease using cough audio signals. At the initial stage, the source signals are fetched and undergo for signal decomposition phase by Empirical Mean Curve Decomposition (EMCD). Consequently, the decomposed signal is called "Mel Frequency Cepstral Coefficients (MFCC), spectral features, and statistical features". Further, all three features are fused and provide the optimal weighted features with the optimal weight value with the help of "Modified Cat and Mouse Based Optimizer (MCMBO)". Lastly, the optimal weighted features are fed as input to the Optimized Deep Ensemble Classifier (ODEC) that is fused together with various classifiers such as "Radial Basis Function (RBF), Long-Short Term Memory (LSTM), and Deep Neural Network (DNN)". In order to attain the best detection results, the parameters in ODEC are optimized by the MCMBO algorithm. Throughout the validation, the designed method attains 96% and 92% concerning accuracy and precision. Thus, result analysis elucidates that the proposed work achieves the desired detective value that aids practitioners to early diagnose COVID-19 ailments.
Collapse
Affiliation(s)
- Muhammad Awais
- Department of Creative Technologies, Air University, Islamabad, Pakistan
| | - Abhishek Bhuva
- Department of Computer Science, University of Massachusetts Boston, United States
| | - Dipen Bhuva
- Department of EECS, Cleveland State University, United States
| | - Saman Fatima
- Department of Medical Education, The University of Lahore, Lahore, Pakistan
| | - Touseef Sadiq
- Department of Information and Communication Technology, University of Agder, Norway
| |
Collapse
|
30
|
Karbasi Z, Gohari SH, Sabahi A. Bibliometric analysis of the use of artificial intelligence in COVID-19 based on scientific studies. Health Sci Rep 2023; 6:e1244. [PMID: 37152228 PMCID: PMC10158785 DOI: 10.1002/hsr2.1244] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/02/2022] [Revised: 04/11/2023] [Accepted: 04/16/2023] [Indexed: 05/09/2023] Open
Abstract
Background and Aims One such strategy is citation analysis used by researchers for research planning an article referred to by another article receives a "citation." By using bibliometric analysis, the development of research areas and authors' influence can be investigated. The current study aimed to identify and analyze the characteristics of 100 highly cited articles on the use of artificial intelligence concerning COVID-19. Methods On July 27, 2022, this database was searched using the keywords "artificial intelligence" and "COVID-19" in the topic. After extensive searching, all retrieved articles were sorted by the number of citations, and 100 highly cited articles were included based on the number of citations. The following data were extracted: year of publication, type of study, name of journal, country, number of citations, language, and keywords. Results The average number of citations for 100 highly cited articles was 138.54. The top three cited articles with 745, 596, and 549 citations. The top 100 articles were all in English and were published in 2020 and 2021. China was the most prolific country with 19 articles, followed by the United States with 15 articles and India with 10 articles. Conclusion The current bibliometric analysis demonstrated the significant growth of the use of artificial intelligence for COVID-19. Using these results, research priorities are more clearly defined, and researchers can focus on hot topics.
Collapse
Affiliation(s)
- Zahra Karbasi
- Medical Informatics Research Center, Institute for Futures Studies in HealthKerman University of Medical SciencesKermanIran
- Department of Health Information Sciences, Faculty of Management and Medical Information SciencesKerman University of Medical SciencesKermanIran
| | - Sadrieh H. Gohari
- Medical Informatics Research Center, Institute for Futures Studies in HealthKerman University of Medical SciencesKermanIran
| | - Azam Sabahi
- Department of Health Information Technology, Ferdows School of Health and Allied Medical SciencesBirjand University of Medical SciencesBirjandIran
| |
Collapse
|
31
|
Vhaduri S, Dibbo SV, Kim Y. Environment Knowledge-Driven Generic Models to Detect Coughs From Audio Recordings. IEEE OPEN JOURNAL OF ENGINEERING IN MEDICINE AND BIOLOGY 2023; 4:55-66. [PMID: 37255922 PMCID: PMC10226681 DOI: 10.1109/ojemb.2023.3271457] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/08/2022] [Revised: 03/17/2023] [Accepted: 04/25/2023] [Indexed: 06/01/2023] Open
Abstract
Goal: Millions of people are dying due to respiratory diseases, such as COVID-19 and asthma, which are often characterized by some common symptoms, including coughing. Therefore, objective reporting of cough symptoms utilizing environment-adaptive machine-learning models with microphone sensing can directly contribute to respiratory disease diagnosis and patient care. Methods: In this work, we present three generic modeling approaches - unguided, semi-guided, and guided approaches considering three potential scenarios, i.e., when a user has no prior knowledge, some knowledge, and detailed knowledge about the environments, respectively. Results: From detailed analysis with three datasets, we find that guided models are up to 28% more accurate than the unguided models. We find reasonable performance when assessing the applicability of our models using three additional datasets, including two open-sourced cough datasets. Conclusions: Though guided models outperform other models, they require a better understanding of the environment.
Collapse
Affiliation(s)
- Sudip Vhaduri
- Department of Computer and Information TechnologyPurdue UniversityWest LafayetteIN47907USA
| | | | - Yugyeong Kim
- Field Service DepartmentLG ElectronicsEnglewood CliffsNJ07632USA
| |
Collapse
|
32
|
Gürsoy E, Kaya Y. An overview of deep learning techniques for COVID-19 detection: methods, challenges, and future works. MULTIMEDIA SYSTEMS 2023; 29:1603-1627. [PMID: 37261262 PMCID: PMC10039775 DOI: 10.1007/s00530-023-01083-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/16/2022] [Accepted: 03/20/2023] [Indexed: 06/02/2023]
Abstract
The World Health Organization (WHO) declared a pandemic in response to the coronavirus COVID-19 in 2020, which resulted in numerous deaths worldwide. Although the disease appears to have lost its impact, millions of people have been affected by this virus, and new infections still occur. Identifying COVID-19 requires a reverse transcription-polymerase chain reaction test (RT-PCR) or analysis of medical data. Due to the high cost and time required to scan and analyze medical data, researchers are focusing on using automated computer-aided methods. This review examines the applications of deep learning (DL) and machine learning (ML) in detecting COVID-19 using medical data such as CT scans, X-rays, cough sounds, MRIs, ultrasound, and clinical markers. First, the data preprocessing, the features used, and the current COVID-19 detection methods are divided into two subsections, and the studies are discussed. Second, the reported publicly available datasets, their characteristics, and the potential comparison materials mentioned in the literature are presented. Third, a comprehensive comparison is made by contrasting the similar and different aspects of the studies. Finally, the results, gaps, and limitations are summarized to stimulate the improvement of COVID-19 detection methods, and the study concludes by listing some future research directions for COVID-19 classification.
Collapse
Affiliation(s)
- Ercan Gürsoy
- Department of Computer Engineering, Adana Alparslan Turkes Science and Technology University, 01250 Adana, Turkey
| | - Yasin Kaya
- Department of Computer Engineering, Adana Alparslan Turkes Science and Technology University, 01250 Adana, Turkey
| |
Collapse
|
33
|
Yellapu GD, Rudraraju G, Sripada NR, Mamidgi B, Jalukuru C, Firmal P, Yechuri V, Varanasi S, Peddireddi VS, Bhimarasetty DM, Kanisetti S, Joshi N, Mohapatra P, Pamarthi K. Development and clinical validation of Swaasa AI platform for screening and prioritization of pulmonary TB. Sci Rep 2023; 13:4740. [PMID: 36959347 PMCID: PMC10034902 DOI: 10.1038/s41598-023-31772-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/04/2022] [Accepted: 03/16/2023] [Indexed: 03/25/2023] Open
Abstract
Acoustic signal analysis has been employed in various medical devices. However, studies involving cough sound analysis to screen the potential pulmonary tuberculosis (PTB) suspects are very few. The main objective of this cross-sectional validation study was to develop and validate the Swaasa AI platform to screen and prioritize at risk patients for PTB based on the signature cough sound as well as symptomatic information provided by the subjects. The voluntary cough sound data was collected at Andhra Medical College-India. An Algorithm based on multimodal convolutional neural network architecture and feedforward artificial neural network (tabular features) was built and validated on a total of 567 subjects, comprising 278 positive and 289 negative PTB cases. The output from these two models was combined to detect the likely presence (positive cases) of PTB. In the clinical validation phase, the AI-model was found to be 86.82% accurate in detecting the likely presence of PTB with 90.36% sensitivity and 84.67% specificity. The pilot testing of model was conducted at a peripheral health care centre, RHC Simhachalam-India on 65 presumptive PTB cases. Out of which, 15 subjects truly turned out to be PTB positive with a positive predictive value of 75%. The validation results obtained from the model are quite encouraging. This platform has the potential to fulfil the unmet need of a cost-effective PTB screening method. It works remotely, presents instantaneous results, and does not require a highly trained operator. Therefore, it could be implemented in various inaccessible, resource-poor parts of the world.
Collapse
Affiliation(s)
| | | | | | | | - Charan Jalukuru
- Salcit Technologies, Jayabheri Silicon Towers, Hyderabad, India
| | - Priyanka Firmal
- Salcit Technologies, Jayabheri Silicon Towers, Hyderabad, India
| | - Venkat Yechuri
- Salcit Technologies, Jayabheri Silicon Towers, Hyderabad, India
| | | | | | | | | | - Niranjan Joshi
- Centre for Cellular and Molecular Platforms, Bengaluru, India
| | - Prasant Mohapatra
- Department of Computer Science, University of California, Davis, USA
| | | |
Collapse
|
34
|
Qiao Y, Luo J, Cui T, Liu H, Tang H, Zeng Y, Liu C, Li Y, Jian J, Wu J, Tian H, Yang Y, Ren TL, Zhou J. Soft Electronics for Health Monitoring Assisted by Machine Learning. NANO-MICRO LETTERS 2023; 15:66. [PMID: 36918452 PMCID: PMC10014415 DOI: 10.1007/s40820-023-01029-1] [Citation(s) in RCA: 14] [Impact Index Per Article: 14.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 11/22/2022] [Accepted: 01/05/2023] [Indexed: 06/18/2023]
Abstract
Due to the development of the novel materials, the past two decades have witnessed the rapid advances of soft electronics. The soft electronics have huge potential in the physical sign monitoring and health care. One of the important advantages of soft electronics is forming good interface with skin, which can increase the user scale and improve the signal quality. Therefore, it is easy to build the specific dataset, which is important to improve the performance of machine learning algorithm. At the same time, with the assistance of machine learning algorithm, the soft electronics have become more and more intelligent to realize real-time analysis and diagnosis. The soft electronics and machining learning algorithms complement each other very well. It is indubitable that the soft electronics will bring us to a healthier and more intelligent world in the near future. Therefore, in this review, we will give a careful introduction about the new soft material, physiological signal detected by soft devices, and the soft devices assisted by machine learning algorithm. Some soft materials will be discussed such as two-dimensional material, carbon nanotube, nanowire, nanomesh, and hydrogel. Then, soft sensors will be discussed according to the physiological signal types (pulse, respiration, human motion, intraocular pressure, phonation, etc.). After that, the soft electronics assisted by various algorithms will be reviewed, including some classical algorithms and powerful neural network algorithms. Especially, the soft device assisted by neural network will be introduced carefully. Finally, the outlook, challenge, and conclusion of soft system powered by machine learning algorithm will be discussed.
Collapse
Affiliation(s)
- Yancong Qiao
- School of Biomedical Engineering, Shenzhen Campus of Sun Yat-sen University, No. 66, Gongchang Road, Guangming District, Shenzhen, 518107, People's Republic of China.
- Key Laboratory of Sensing Technology and Biomedical Instruments of Guangdong Province, School of Biomedical Engineering, Sun Yat-sen University, Guangzhou, 510275, People's Republic of China.
| | - Jinan Luo
- School of Biomedical Engineering, Shenzhen Campus of Sun Yat-sen University, No. 66, Gongchang Road, Guangming District, Shenzhen, 518107, People's Republic of China
- Key Laboratory of Sensing Technology and Biomedical Instruments of Guangdong Province, School of Biomedical Engineering, Sun Yat-sen University, Guangzhou, 510275, People's Republic of China
| | - Tianrui Cui
- School of Integrated Circuits and Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, 100084, People's Republic of China
| | - Haidong Liu
- School of Biomedical Engineering, Shenzhen Campus of Sun Yat-sen University, No. 66, Gongchang Road, Guangming District, Shenzhen, 518107, People's Republic of China
- Key Laboratory of Sensing Technology and Biomedical Instruments of Guangdong Province, School of Biomedical Engineering, Sun Yat-sen University, Guangzhou, 510275, People's Republic of China
| | - Hao Tang
- School of Biomedical Engineering, Shenzhen Campus of Sun Yat-sen University, No. 66, Gongchang Road, Guangming District, Shenzhen, 518107, People's Republic of China
- Key Laboratory of Sensing Technology and Biomedical Instruments of Guangdong Province, School of Biomedical Engineering, Sun Yat-sen University, Guangzhou, 510275, People's Republic of China
| | - Yingfen Zeng
- School of Integrated Circuits and Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, 100084, People's Republic of China
| | - Chang Liu
- School of Biomedical Engineering, Shenzhen Campus of Sun Yat-sen University, No. 66, Gongchang Road, Guangming District, Shenzhen, 518107, People's Republic of China
- Key Laboratory of Sensing Technology and Biomedical Instruments of Guangdong Province, School of Biomedical Engineering, Sun Yat-sen University, Guangzhou, 510275, People's Republic of China
| | - Yuanfang Li
- School of Biomedical Engineering, Shenzhen Campus of Sun Yat-sen University, No. 66, Gongchang Road, Guangming District, Shenzhen, 518107, People's Republic of China
- Key Laboratory of Sensing Technology and Biomedical Instruments of Guangdong Province, School of Biomedical Engineering, Sun Yat-sen University, Guangzhou, 510275, People's Republic of China
| | - Jinming Jian
- School of Integrated Circuits and Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, 100084, People's Republic of China
| | - Jingzhi Wu
- School of Biomedical Engineering, Shenzhen Campus of Sun Yat-sen University, No. 66, Gongchang Road, Guangming District, Shenzhen, 518107, People's Republic of China
- Key Laboratory of Sensing Technology and Biomedical Instruments of Guangdong Province, School of Biomedical Engineering, Sun Yat-sen University, Guangzhou, 510275, People's Republic of China
| | - He Tian
- School of Integrated Circuits and Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, 100084, People's Republic of China
| | - Yi Yang
- School of Integrated Circuits and Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, 100084, People's Republic of China
| | - Tian-Ling Ren
- School of Integrated Circuits and Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, 100084, People's Republic of China.
| | - Jianhua Zhou
- School of Biomedical Engineering, Shenzhen Campus of Sun Yat-sen University, No. 66, Gongchang Road, Guangming District, Shenzhen, 518107, People's Republic of China.
- Key Laboratory of Sensing Technology and Biomedical Instruments of Guangdong Province, School of Biomedical Engineering, Sun Yat-sen University, Guangzhou, 510275, People's Republic of China.
| |
Collapse
|
35
|
Hunter OF, Perry F, Salehi M, Bandurski H, Hubbard A, Ball CG, Morad Hameed S. Science fiction or clinical reality: a review of the applications of artificial intelligence along the continuum of trauma care. World J Emerg Surg 2023; 18:16. [PMID: 36879293 PMCID: PMC9987401 DOI: 10.1186/s13017-022-00469-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/29/2022] [Accepted: 12/12/2022] [Indexed: 03/08/2023] Open
Abstract
Artificial intelligence (AI) and machine learning describe a broad range of algorithm types that can be trained based on datasets to make predictions. The increasing sophistication of AI has created new opportunities to apply these algorithms within within trauma care. Our paper overviews the current uses of AI along the continuum of trauma care, including injury prediction, triage, emergency department volume, assessment, and outcomes. Starting at the point of injury, algorithms are being used to predict severity of motor vehicle crashes, which can help inform emergency responses. Once on the scene, AI can be used to help emergency services triage patients remotely in order to inform transfer location and urgency. For the receiving hospital, these tools can be used to predict trauma volumes in the emergency department to help allocate appropriate staffing. After patient arrival to hospital, these algorithms not only can help to predict injury severity, which can inform decision-making, but also predict patient outcomes to help trauma teams anticipate patient trajectory. Overall, these tools have the capability to transform trauma care. AI is still nascent within the trauma surgery sphere, but this body of the literature shows that this technology has vast potential. AI-based predictive tools in trauma need to be explored further through prospective trials and clinical validation of algorithms.
Collapse
Affiliation(s)
- Olivia F Hunter
- Department of Surgery, University of British Columbia, Vancouver, Canada
| | - Frances Perry
- Department of Surgery, University of British Columbia, Vancouver, Canada
| | - Mina Salehi
- Department of Surgery, University of British Columbia, Vancouver, Canada
| | | | - Alan Hubbard
- University of California, Berkeley School of Public Health, Berkeley, USA
| | - Chad G Ball
- Department of Surgery, University of Calgary, Calgary, Canada
| | - S Morad Hameed
- Department of Surgery, University of British Columbia, Vancouver, Canada. .,T6 Health Systems, Boston, USA.
| |
Collapse
|
36
|
COVID-19 and human development: An approach for classification of HDI with deep CNN. Biomed Signal Process Control 2023; 81:104499. [PMID: 36530217 PMCID: PMC9742222 DOI: 10.1016/j.bspc.2022.104499] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/21/2022] [Revised: 10/18/2022] [Accepted: 12/01/2022] [Indexed: 12/14/2022]
Abstract
The measures taken during the pandemic have had lasting effects on people's lives and perceptions of the ability of national and multilateral institutions to drive human development. Policies that changed people's behavior were at the heart of containing the spread of the virus. As a result, it has become a systemic human development crisis affecting health, the economy, education, social life, and accumulated gains. This study shows how the relationship of the Human Development Index (HDI), which has combined effects on health, education, and the economy, should be considered in the context of pandemic factors. First, COVID-19 data of the countries received from a public and credible source were extracted and organized into an acceptable structure. Then, we applied statistical feature selection to determine which variables are closely related to HDI and enabled the Deep Convolutional Neural Network (DCNN) model to give more accurate results. The Continuous Wavelet Transform (CWT) and scalogram methods were used for the time-series data visualization. Three different images of each country are combined into a single image to penetrate each other for ease of processing. These images were made suitable for the input of the ResNet-50 network, which is a pre-trained DCNN model, by going through various preprocessing processes. After the training and validation processes, the feature vectors in the fc1000 layer of the network were drawn and given to the Support Vector Machine Classifier (SVMC) input. We achieved total performance metrics of specificity (88.2%), sensitivity (96.5%), precision (99%), F1 Score (94.9%) and MCC (85.9%).
Collapse
|
37
|
Manzella F, Pagliarini G, Sciavicco G, Stan IE. The voice of COVID-19: Breath and cough recording classification with temporal decision trees and random forests. Artif Intell Med 2023; 137:102486. [PMID: 36868683 PMCID: PMC9904537 DOI: 10.1016/j.artmed.2022.102486] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/06/2022] [Revised: 12/27/2022] [Accepted: 12/28/2022] [Indexed: 02/05/2023]
Abstract
Symbolic learning is the logic-based approach to machine learning, and its mission is to provide algorithms and methodologies to extract logical information from data and express it in an interpretable way. Interval temporal logic has been recently proposed as a suitable tool for symbolic learning, specifically via the design of an interval temporal logic decision tree extraction algorithm. In order to improve their performances, interval temporal decision trees can be embedded into interval temporal random forests, mimicking the corresponding schema at the propositional level. In this article we consider a dataset of cough and breath sample recordings of volunteer subjects, labeled with their COVID-19 status, originally collected by the University of Cambridge. By interpreting such recordings as multivariate time series, we study the problem of their automated classification using interval temporal decision trees and forests. While this problem has been approached with the same dataset as well as with other datasets, in all cases, non-symbolic learning methods (usually, deep learning-based) have been applied to solve it; in this article we apply a symbolic approach, and show that it does not only outperform the state-of-the-art obtained with the same dataset, but its results are also superior to those of most non-symbolic techniques applied on other datasets. As an added bonus, thanks to the symbolic nature of our approach, we are also able to extract explicit knowledge to help physicians characterize typical COVID-positive cough and breath.
Collapse
Affiliation(s)
- F Manzella
- Department of Mathematics and Computer Science, University of Ferrara, Italy.
| | - G Pagliarini
- Department of Mathematics and Computer Science, University of Ferrara, Italy.
| | - G Sciavicco
- Department of Mathematics and Computer Science, University of Ferrara, Italy.
| | - I E Stan
- Department of Mathematics and Computer Science, University of Ferrara, Italy.
| |
Collapse
|
38
|
Nguyen LH, Pham NT, Do VH, Nguyen LT, Nguyen TT, Nguyen H, Nguyen ND, Nguyen TT, Nguyen SD, Bhatti A, Lim CP. Fruit-CoV: An efficient vision-based framework for speedy detection and diagnosis of SARS-CoV-2 infections through recorded cough sounds. EXPERT SYSTEMS WITH APPLICATIONS 2023; 213:119212. [PMID: 36407848 PMCID: PMC9639421 DOI: 10.1016/j.eswa.2022.119212] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 12/06/2021] [Revised: 10/20/2022] [Accepted: 11/01/2022] [Indexed: 06/16/2023]
Abstract
COVID-19 is an infectious disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). This deadly virus has spread worldwide, leading to a global pandemic since March 2020. A recent variant of SARS-CoV-2 named Delta is intractably contagious and responsible for more than four million deaths globally. Therefore, developing an efficient self-testing service for SARS-CoV-2 at home is vital. In this study, a two-stage vision-based framework, namely Fruit-CoV, is introduced for detecting SARS-CoV-2 infections through recorded cough sounds. Specifically, audio signals are converted into Log-Mel spectrograms, and the EfficientNet-V2 network is used to extract their visual features in the first stage. In the second stage, 14 convolutional layers extracted from the large-scale Pretrained Audio Neural Networks for audio pattern recognition (PANNs) and the Wavegram-Log-Mel-CNN are employed to aggregate feature representations of the Log-Mel spectrograms and the waveform. Finally, the combined features are used to train a binary classifier. In this study, a dataset provided by the AICovidVN 115M Challenge is employed for evaluation. It includes 7,371 recorded cough sounds collected throughout Vietnam, India, and Switzerland. Experimental results indicate that the proposed model achieves an Area Under the Receiver Operating Characteristic Curve (AUC) score of 92.8% and ranks first on the final leaderboard of the AICovidVN 115M Challenge. Our code is publicly available.
Collapse
Affiliation(s)
- Long H Nguyen
- Faculty of Information Technology, Ton Duc Thang University, Ho Chi Minh City, Vietnam
| | - Nhat Truong Pham
- Division of Computational Mechatronics, Institute for Computational Science, Ton Duc Thang University, Ho Chi Minh City, Vietnam
- Faculty of Electrical and Electronics Engineering, Ton Duc Thang University, Ho Chi Minh City, Vietnam
| | | | - Liu Tai Nguyen
- Faculty of Information Technology, Ton Duc Thang University, Ho Chi Minh City, Vietnam
| | - Thanh Tin Nguyen
- Human Computer Interaction Lab, Sejong University, Seoul, South Korea
| | - Hai Nguyen
- Khoury College of Computer Sciences, Northeastern University, Boston, USA
| | - Ngoc Duy Nguyen
- Institute for Intelligent Systems Research and Innovation, Deakin University, Victoria, Australia
| | - Thanh Thi Nguyen
- School of Information Technology, Deakin University, Victoria, Australia
| | - Sy Dzung Nguyen
- Laboratory for Computational Mechatronics, Institute for Computational Science and Artificial Intelligence, Van Lang University, Ho Chi Minh City, Vietnam
- Faculty of Mechanical-Electrical and Computer Engineering, Van Lang University, Ho Chi Minh City, Vietnam
| | - Asim Bhatti
- Institute for Intelligent Systems Research and Innovation, Deakin University, Victoria, Australia
| | - Chee Peng Lim
- Institute for Intelligent Systems Research and Innovation, Deakin University, Victoria, Australia
| |
Collapse
|
39
|
Artificial Intelligence Functionalities During the COVID-19 Pandemic. Disaster Med Public Health Prep 2023; 17:e336. [PMID: 36847255 DOI: 10.1017/dmp.2023.3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/01/2023]
Abstract
BACKGROUND The coronavirus disease 2019 (COVID-19) pandemic has led us to use virtual solutions and emerging technologies such as artificial intelligence (AI). Recent studies have clearly demonstrated the role of AI in health care and medical practice; however, a comprehensive review can identify potential yet not fulfilled functionalities of such technologies in pandemics. Therefore, this scoping review study aims at assessing AI functionalities in the COVID-19 pandemic in 2022. METHODS A systematic search was carried out in PubMed, Cochran Library, Scopus, Science Direct, ProQuest, and Web of Science from 2019 to May 9, 2022. Researchers selected the articles according to the search keywords. Finally, the articles mentioning the functionalities of AI in the COVID-19 pandemic were evaluated. Two investigators performed this process. RESULTS Initial search resulted in 9123 articles. After reviewing the title, abstract, and full text of these articles, and applying the inclusion and exclusion criteria, 4 articles were selectd for the final analysis. All 4 were cross-sectional studies. Two studies (50%) were performed in the United States, 1 (25%) in Israel, and 1 (25%) in Saudi Arabia. They covered the functionalities of AI in the prediction, detection, and diagnosis of COVID-19. CONCLUSIONS To the extent of the researchers' knowledge, this study is the first scoping review that assesses the AI functionalities in the COVID-19 pandemic. Health-care organizations need decision support technologies and evidence-based apparatuses that can perceive, think, and reason not dissimilar to human beings. Potential functionalities of such technologies can be used to predict mortality, detect, screen, and trace current and former patients, analyze health data, prioritize high-risk patients, and better allocate hospital resources in pandemics, and generally in health-care settings.
Collapse
|
40
|
Ulukaya S, Sarıca AA, Erdem O, Karaali A. MSCCov19Net: multi-branch deep learning model for COVID-19 detection from cough sounds. Med Biol Eng Comput 2023:10.1007/s11517-023-02803-4. [PMID: 36828944 PMCID: PMC9955529 DOI: 10.1007/s11517-023-02803-4] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/29/2022] [Accepted: 01/24/2023] [Indexed: 02/26/2023]
Abstract
Coronavirus has an impact on millions of lives and has been added to the important pandemics that continue to affect with its variants. Since it is transmitted through the respiratory tract, it has had significant effects on public health and social relations. Isolating people who are COVID positive can minimize the transmission, therefore several exams are proposed to detect the virus such as reverse transcription-polymerase chain reaction (RT-PCR), chest X-Ray, and computed tomography (CT). However, these methods suffer from either a low detection rate or high radiation dosage, along with being expensive. In this study, deep neural network-based model capable of detecting coronavirus from only coughing sound, which is fast, remotely operable and has no harmful side effects, has been proposed. The proposed multi-branch model takes M el Frequency Cepstral Coefficients (MFCC), S pectrogram, and C hromagram as inputs and is abbreviated as MSCCov19Net. The system is trained on publicly available crowdsourced datasets, and tested on two unseen (used only for testing) clinical and non-clinical datasets. Experimental outcomes represent that the proposed system outperforms the 6 popular deep learning architectures on four datasets by representing a better generalization ability. The proposed system has reached an accuracy of 61.5 % in Virufy and 90.4 % in NoCoCoDa for unseen test datasets.
Collapse
Affiliation(s)
- Sezer Ulukaya
- Department of Electrical and Electronics Engineering, Trakya University, Edirne, 22030 Turkey
| | - Ahmet Alp Sarıca
- Department of Electrical and Electronics Engineering, Trakya University, Edirne, 22030 Turkey
| | - Oğuzhan Erdem
- Department of Electrical and Electronics Engineering, Trakya University, Edirne, 22030 Turkey
| | - Ali Karaali
- The Irish Longitudinal Study on Ageing (TILDA), School of Medicine, Trinity College Dublin, Dublin, D02 R590 Ireland
| |
Collapse
|
41
|
A Performance Study of CNN Architectures for the Autonomous Detection of COVID-19 Symptoms Using Cough and Breathing. COMPUTERS 2023. [DOI: 10.3390/computers12020044] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/22/2023]
Abstract
Deep learning (DL) methods have the potential to be used for detecting COVID-19 symptoms. However, the rationale for which DL method to use and which symptoms to detect has not yet been explored. In this paper, we present the first performance study which compares various convolutional neural network (CNN) architectures for the autonomous preliminary COVID-19 detection of cough and/or breathing symptoms. We compare and analyze residual networks (ResNets), visual geometry Groups (VGGs), Alex neural networks (AlexNet), densely connected networks (DenseNet), squeeze neural networks (SqueezeNet), and COVID-19 identification ResNet (CIdeR) architectures to investigate their classification performance. We uniquely train and validate both unimodal and multimodal CNN architectures using the EPFL and Cambridge datasets. Performance comparison across all modes and datasets showed that the VGG19 and DenseNet-201 achieved the highest unimodal and multimodal classification performance. VGG19 and DensNet-201 had high F1 scores (0.94 and 0.92) for unimodal cough classification on the Cambridge dataset, compared to the next highest F1 score for ResNet (0.79), with comparable F1 scores to ResNet for the larger EPFL cough dataset. They also had consistently high accuracy, recall, and precision. For multimodal detection, VGG19 and DenseNet-201 had the highest F1 scores (0.91) compared to the other CNN structures (≤0.90), with VGG19 also having the highest accuracy and recall. Our investigation provides the foundation needed to select the appropriate deep CNN method to utilize for non-contact early COVID-19 detection.
Collapse
|
42
|
Zhang B, Ming C. Digital Transformation and Open Innovation Planning of Response to COVID-19 Outbreak: A Systematic Literature Review and Future Research Agenda. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2023; 20:2731. [PMID: 36768096 PMCID: PMC9916385 DOI: 10.3390/ijerph20032731] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 12/30/2022] [Revised: 01/30/2023] [Accepted: 01/31/2023] [Indexed: 06/18/2023]
Abstract
The COVID-19 pandemic highlights the importance of digital technology in a specific region's epidemic prevention and control, and the digital transformation strategy based on the open innovation system is an emerging way to tackle conceivable outbreaks. Based on the bibliometric study of relevant literature data, this paper evaluated the research and development status in this field, and conducted a systematic literature review on the basis of the core articles identified. The results of bibliometric analysis software, including CiteSpace, CitNetExplorer and VOSViewer, showed that the development of relevant research presented rapidity and decentralization, and the evolution process of literature topics further implies the necessity of interdisciplinary and multisectoral collaboration. Furthermore, this paper summarized the specific implementation strategies for constructing an open innovation system, and discussed the role and development plan of digital technology in epidemic prevention and control.
Collapse
Affiliation(s)
- Ben Zhang
- Law School, Huazhong University of Science and Technology, Wuhan 430074, China
- Sino-European Institute for Intellectual Property, Huazhong University of Science and Technology, Wuhan 430074, China
| | - Chenxu Ming
- Sino-European Institute for Intellectual Property, Huazhong University of Science and Technology, Wuhan 430074, China
- School of Management, Huazhong University of Science and Technology, Wuhan 430074, China
| |
Collapse
|
43
|
Davidson C, Caguana OA, Lozano-García M, Arita Guevara M, Estrada-Petrocelli L, Ferrer-Lluis I, Castillo-Escario Y, Ausín P, Gea J, Jané R. Differences in acoustic features of cough by pneumonia severity in patients with COVID-19: a cross-sectional study. ERJ Open Res 2023; 9:00247-2022. [PMID: 37131524 PMCID: PMC9922471 DOI: 10.1183/23120541.00247-2022] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/18/2022] [Accepted: 01/07/2023] [Indexed: 02/05/2023] Open
Abstract
BackgroundAcute respiratory syndrome due to coronavirus 2 (SARS-CoV-2) is characterised by heterogeneous levels of disease severity. It is not necessarily apparent whether a patient will develop a severe disease or not. This cross-sectional study explores whether acoustic properties of the cough sound of patients with coronavirus disease (COVID-19), the illness caused by SARS-CoV-2, correlate with their disease and pneumonia severity, with the aim of identifying patients with a severe disease.MethodsVoluntary cough sounds were recorded using a smartphone in 70 COVID-19 patients within the first 24 h of their hospital arrival, between April 2020 and May 2021. Based on gas exchange abnormalities, patients were classified as mild, moderate, or severe. Time- and frequency-based variables were obtained from each cough effort and analysed using a linear mixed-effects modelling approach.ResultsRecords from 62 patients (37% female) were eligible for inclusion in the analysis, with mild, moderate, and severe groups consisting of 31, 14 and 17 patients respectively. 5 of the parameters examined were found to be significantly different in the cough of patients at different disease levels of severity, with a further 2 parameters found to be affected differently by the disease severity in men and women.ConclusionsWe suggest that all these differences reflect the progressive pathophysiological alterations occurring in the respiratory system of COVID-19 patients, and potentially would provide an easy and cost-effective way to initially stratify patients, identifying those with more severe disease, and thereby most effectively allocate healthcare resources.
Collapse
|
44
|
Fontes C, Corrigan C, Lütge C. Governing AI during a pandemic crisis: Initiatives at the EU level. TECHNOLOGY IN SOCIETY 2023; 72:102204. [PMID: 36777094 PMCID: PMC9894826 DOI: 10.1016/j.techsoc.2023.102204] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/09/2022] [Revised: 01/16/2023] [Accepted: 01/19/2023] [Indexed: 06/18/2023]
Abstract
After the outbreak of Covid-19, the European Commission (EC) promptly took the initiative to lead and coordinate a common European response. The actions unfolded in several directions, paving the way to the uptake of AI-related solutions and placing hope in these tools to face crises, namely of a public health and global nature. In this article, we focus on initiatives for the uptake of AI-related solutions from the experimental level towards implementation. The Repository of AI and Robotics solutions, launched in 2020, is an example of an initiative put forth to leverage and disseminate knowledge on AI, expanding the fields of application and fostering the development and adaptation of cutting-edge technologies to explore how they can assist in tackling specific tasks during a public health crisis. Using this database, the article outlines the promise of AI as a hope for handling specific needs and tasks and how the uptake of such technologies was accelerated during the Covid-19 pandemic. In extension, we frame initiatives for the uptake of AI-enabled solutions from a governance perspective, focusing on the establishment of frameworks for ethical and trustworthy AI by defining principles and standards that aim to protect the underlying values deemed fundamental.
Collapse
Affiliation(s)
- Catarina Fontes
- Technical University of Munich, School of Social Sciences and Technology, Institute for Ethics in Artificial Intelligence, München, 80333, Germany
| | - Caitlin Corrigan
- Technical University of Munich, School of Social Sciences and Technology, Institute for Ethics in Artificial Intelligence, München, 80333, Germany
| | - Christoph Lütge
- Technical University of Munich, School of Social Sciences and Technology, Institute for Ethics in Artificial Intelligence, München, 80333, Germany
| |
Collapse
|
45
|
Campana MG, Delmastro F, Pagani E. Transfer learning for the efficient detection of COVID-19 from smartphone audio data. PERVASIVE AND MOBILE COMPUTING 2023; 89:101754. [PMID: 36741300 PMCID: PMC9884612 DOI: 10.1016/j.pmcj.2023.101754] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/25/2022] [Revised: 01/18/2023] [Accepted: 01/25/2023] [Indexed: 06/12/2023]
Abstract
Disease detection from smartphone data represents an open research challenge in mobile health (m-health) systems. COVID-19 and its respiratory symptoms are an important case study in this area and their early detection is a potential real instrument to counteract the pandemic situation. The efficacy of this solution mainly depends on the performances of AI algorithms applied to the collected data and their possible implementation directly on the users' mobile devices. Considering these issues, and the limited amount of available data, in this paper we present the experimental evaluation of 3 different deep learning models, compared also with hand-crafted features, and of two main approaches of transfer learning in the considered scenario: both feature extraction and fine-tuning. Specifically, we considered VGGish, YAMNET, and L3-Net (including 12 different configurations) evaluated through user-independent experiments on 4 different datasets (13,447 samples in total). Results clearly show the advantages of L3-Net in all the experimental settings as it overcomes the other solutions by 12.3% in terms of Precision-Recall AUC as features extractor, and by 10% when the model is fine-tuned. Moreover, we note that to fine-tune only the fully-connected layers of the pre-trained models generally leads to worse performances, with an average drop of 6.6% with respect to feature extraction. Finally, we evaluate the memory footprints of the different models for their possible applications on commercial mobile devices.
Collapse
Affiliation(s)
- Mattia Giovanni Campana
- Institute for Informatics and Telematics of the National Research Council of Italy (IIT-CNR), Pisa, Italy
| | - Franca Delmastro
- Institute for Informatics and Telematics of the National Research Council of Italy (IIT-CNR), Pisa, Italy
| | - Elena Pagani
- Computer Science Department, University of Milano, Milan, Italy
| |
Collapse
|
46
|
Huang DW, Liu B, Bi J, Wang J, Wang M, Wang H. A coalitional game-based joint monitoring mechanism for combating COVID-19. COMPUTER COMMUNICATIONS 2023; 199:168-176. [PMID: 36589785 PMCID: PMC9793961 DOI: 10.1016/j.comcom.2022.12.020] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/20/2022] [Revised: 11/14/2022] [Accepted: 12/17/2022] [Indexed: 06/17/2023]
Abstract
In the absence of effective treatment for COVID-19, disease prevention and control have become a top priority across the world. However, the general lack of effective cooperation between communities makes it difficult to suppress the community spread of the global pandemic; hence repeated outbreaks of COVID-19 have become the norm. To address this problem, this paper considers community cooperation in disease monitoring and designs a joint epidemic monitoring mechanism, in which adjacent communities cooperate to enhance their monitoring capability. In this work, we formulate the epidemiological monitoring process as a coalitional game. Then, we propose a Shapley value-based payoffs distribution scheme for the coalitional game. A comprehensive analytical framework is developed to evaluate the advantages and sustainability of the cooperation between communities. Experimental results show that the proposed mechanism performs much better than the conventional non-cooperative monitoring design and can greatly increase each community's payoffs.
Collapse
Affiliation(s)
- Da-Wen Huang
- College of Computer Science, Sichuan Normal University, Chengdu, 610066, Sichuan, China
| | - Bing Liu
- Zhejiang Institute of Industry and Information Technology, Hangzhou, Zhejiang, China
| | - Jichao Bi
- State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, 310058, Zhejiang, China
- Zhejiang Institute of Industry and Information Technology, Hangzhou, Zhejiang, China
| | - Jingpei Wang
- State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, 310058, Zhejiang, China
| | - Mengzhi Wang
- State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, 310058, Zhejiang, China
| | - Huan Wang
- Guangdong Institute of Scientific and Technical Information, Guangzhou, Guangdong, China
| |
Collapse
|
47
|
Dissociating COVID-19 from other respiratory infections based on acoustic, motor coordination, and phonemic patterns. Sci Rep 2023; 13:1567. [PMID: 36709368 PMCID: PMC9884222 DOI: 10.1038/s41598-023-27934-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/31/2022] [Accepted: 01/10/2023] [Indexed: 01/30/2023] Open
Abstract
In the face of the global pandemic caused by the disease COVID-19, researchers have increasingly turned to simple measures to detect and monitor the presence of the disease in individuals at home. We sought to determine if measures of neuromotor coordination, derived from acoustic time series, as well as phoneme-based and standard acoustic features extracted from recordings of simple speech tasks could aid in detecting the presence of COVID-19. We further hypothesized that these features would aid in characterizing the effect of COVID-19 on speech production systems. A protocol, consisting of a variety of speech tasks, was administered to 12 individuals with COVID-19 and 15 individuals with other viral infections at University Hospital Galway. From these recordings, we extracted a set of acoustic time series representative of speech production subsystems, as well as their univariate statistics. The time series were further utilized to derive correlation-based features, a proxy for speech production motor coordination. We additionally extracted phoneme-based features. These features were used to create machine learning models to distinguish between the COVID-19 positive and other viral infection groups, with respiratory- and laryngeal-based features resulting in the highest performance. Coordination-based features derived from harmonic-to-noise ratio time series from read speech discriminated between the two groups with an area under the ROC curve (AUC) of 0.94. A longitudinal case study of two subjects, one from each group, revealed differences in laryngeal based acoustic features, consistent with observed physiological differences between the two groups. The results from this analysis highlight the promise of using nonintrusive sensing through simple speech recordings for early warning and tracking of COVID-19.
Collapse
|
48
|
Najaran MHT. An evolutionary ensemble learning for diagnosing COVID-19 via cough signals. INTELLIGENT MEDICINE 2023; 3:S2667-1026(23)00002-5. [PMID: 36743333 PMCID: PMC9882956 DOI: 10.1016/j.imed.2023.01.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 11/22/2022] [Revised: 01/10/2023] [Accepted: 01/11/2023] [Indexed: 01/30/2023]
Abstract
Objective The spread of the COVID-19 disease has caused great concern around the world and detecting the positive cases is crucial in curbing the pandemic. One of the symptoms of the disease is the dry cough it causes. It has previously been shown that cough signals can be used to identify a variety of diseases including tuberculosis, asthma, etc. In this paper, we proposed an algorithm to diagnose via cough signals the COVID-19 disease. Methods The proposed algorithm is an ensemble scheme that consists of a number of base learners, where each base learner uses a different feature extractor method, including statistical approaches and convolutional neural networks (CNN) for automatic feature extraction. Features are extracted from the raw signal and some transforms performed it, including Fourier, wavelet, Hilbert-Huang, and short-term Fourier transforms. The outputs of these base-learners are aggregated via a weighted voting scheme, with the weights optimised via an evolutionary paradigm. This paper also proposes a memetic algorithm for training the CNNs in the base-learners, which combines the speed of gradient descent (GD) algorithms and global search space coverage of the evolutionary algorithms. Results Experiments were performed on the proposed algorithm and different rival algorithms which included a number of CNN architectures in the literature and generic machine learning algorithms. The results suggested that the proposed algorithm achieves better performance compared to the existing algorithms in diagnosing COVID-19 via cough signals. Conclusion This research showed that COVID-19 could be diagnosed via cough signals and CNNs could be employed to process these signals and it may be further improved by the optimization of CNN architecture.
Collapse
|
49
|
Peng P, Jiang K, You M, Xie J, Zhou H, Xu W, Lu J, Li X, Xu Y. Design of an Efficient CNN-based Cough Detection System on Lightweight FPGA. IEEE TRANSACTIONS ON BIOMEDICAL CIRCUITS AND SYSTEMS 2023; PP:116-128. [PMID: 37018680 DOI: 10.1109/tbcas.2023.3236976] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/19/2023]
Abstract
Precisely and automatically detecting the cough sound is of vital clinical importance. Nevertheless, due to privacy protection considerations, transmitting the raw audio data to the cloud is not permitted, and therefore there is a great demand for an efficient, accurate, and low-cost solution at the edge device. To address this challenge, we propose a semi-custom software-hardware co-design methodology to help build the cough detection system. Specifically, we first design a scalable and compact convolutional neural network (CNN) structure that generates many network instances. Second, we develop a dedicated hardware accelerator to perform the inference computation efficiently, and then we find the optimal network instance by applying network design space exploration. Finally, we compile the optimal network and let it run on the hardware accelerator. The experimental results demonstrate that our model achieves 88.8% classification accuracy, 91.2% sensitivity, 86.5% specificity, and 86.5% precision, while the computation complexity is only 1.09M multiply-accumulation (MAC). Additionally, when implemented on a lightweight field programmable gate array (FPGA), the complete cough detection system only occupies 7.9K lookup tables (LUTs), 12.9K flip-flops (FFs), and 41 digital signal processing (DSP) slices, providing 8.3 GOP/s actual inference throughput and total power dissipation of 0.93 W. This framework meets the needs of partial application and can be easily extended or integrated into other healthcare applications.
Collapse
|
50
|
Aptekarev T, Sokolovsky V, Furman E, Kalinina N, Furman G. Application of deep learning for bronchial asthma diagnostics using respiratory sound recordings. PeerJ Comput Sci 2023; 9:e1173. [PMID: 37346621 PMCID: PMC10280228 DOI: 10.7717/peerj-cs.1173] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/25/2022] [Accepted: 11/08/2022] [Indexed: 06/23/2023]
Abstract
Methods of computer-assisted diagnostics that utilize deep learning techniques on recordings of respiratory sounds have been developed to diagnose bronchial asthma. In the course of the study an anonymous database containing audio files of respiratory sound recordings of patients suffering from different respiratory diseases and healthy volunteers has been accumulated and used to train the software and control its operation. The database consists of 1,238 records of respiratory sounds of patients and 133 records of volunteers. The age of tested persons was from 18 months to 47 years. The sound recordings were captured during calm breathing at four points: in the oral cavity, above the trachea, at the chest, the second intercostal space on the right side, and at the point on the back. The developed software provides binary classifications (diagnostics) of the type: "sick/healthy" and "asthmatic patient/non-asthmatic patient and healthy". For small test samples of 50 (control group) to 50 records (comparison group), the diagnostic sensitivity metric of the first classifier was 88%, its specificity metric -86% and accuracy metric -87%. The metrics for the classifier "asthmatic patient/non-asthmatic patient and healthy" were 92%, 82%, and 87%, respectively. The last model applied to analyze 941 records in asthmatic patients indicated the correct asthma diagnosis in 93% of cases. The proposed method is distinguished by the fact that the trained model enables diagnostics of bronchial asthma (including differential diagnostics) with high accuracy irrespective of the patient gender and age, stage of the disease, as well as the point of sound recording. The proposed method can be used as an additional screening method for preclinical bronchial asthma diagnostics and serve as a basis for developing methods of computer assisted patient condition monitoring including remote monitoring and real-time estimation of treatment effectiveness.
Collapse
Affiliation(s)
- Theodore Aptekarev
- Physics Department, Ben-Gurion University of the Negev, Be’er Sheva, Israel
| | | | - Evgeny Furman
- Department of Faculty and Hospital Pediatrics, Perm State Medical University named after Academician E. A. Wagner, Perm, Russia
| | - Natalia Kalinina
- Department of Faculty and Hospital Pediatrics, Perm State Medical University named after Academician E. A. Wagner, Perm, Russia
| | - Gregory Furman
- Physics Department, Ben-Gurion University of the Negev, Be’er Sheva, Israel
- Education Department, Tel-Hai College, Tel-Hai, Upper Galilee, Israel
| |
Collapse
|