Fundamentals of lung auscultation

Tunable Q-factor wavelet transform based lung signal decomposition and statistical feature extraction for effective lung disease classification

The auscultation is a non-invasive and cost-effective method used for the diagnosis of lung diseases, which are one of the leading causes of death worldwide. However, the efficacy of the auscultation suffers from the limitations of the analog stethoscopes and the subjective nature of human interpretation. To overcome these limitations, the accurate diagnosis of these diseases by employing the computer based automated algorithms applied to the digitized lung sounds has been studied for the last decades. This study proposes a novel approach that uses a Tunable Q-factor Wavelet Transform (TQWT) based statistical feature extraction followed by individual and ensemble learning model training with the aim of lung disease classification. During the learning stage various machine learning algorithms are utilized as the individual learners as well as the hard and soft voting fusion approaches are employed for performance enhancement with the aid of the predictions of individual models. For an objective evaluation of the proposed approach, the study was structured into two main tasks that were investigated in detail by using several sub-tasks to comparison with state-of-the-art studies. Among the sub-tasks which investigates patient-based classification, the highest accuracy obtained for the binary classification was achieved as 97.63% (healthy vs. non-healthy), while accuracy values up to 66.32% for three-class classification (obstructive-related, restrictive-related, and healthy), and 53.42% for five-class classification (asthma, chronic obstructive pulmonary disease, interstitial lung disease, pulmonary infection, and healthy) were obtained. Regarding the other sub-task, which investigates sample-based classification, the proposed approach was superior to almost all previous findings. The proposed method underscores the potential of TQWT based signal decomposition that leverages the power of its adaptive time-frequency resolution property satisfied by Q-factor adjustability. The obtained results are very promising and the proposed approach paves the way for more accurate and automated digital auscultation techniques in clinical settings.

Graph features based classification of bronchial and pleural rub sound signals: the potential of complex network unwrapped

The study presents a novel technique for lung auscultation based on graph theory, emphasizing the potential of graph parameters in distinguishing lung sounds and supporting earlier detection of various respiratory pathologies. The frequency spread and the component magnitudes are revealed from the analysis of eighty-five bronchial (BS) and pleural rub (PS) lung sounds employing the power spectral density (PSD) plot and wavelet scalogram. The low-frequency spread, and persistence of the high-intensity frequency components are visible in BS sounds emanating from the uniform cross-sectional area of the trachea. The frictional rub between the pleurae causes a higher frequency spread of low-intensity intermittent frequency components in PS signals. From the complex networks of BS and PS, the extracted graph features are - graph density ([Formula: see text], transitivity ([Formula: see text], degree centrality ([Formula: see text]), betweenness centrality ([Formula: see text], eigenvector centrality ([Formula: see text]), and graph entropy (En). The high values of [Formula: see text] and [Formula: see text] show a strong correlation between distinct segments of the BS signal originating from a consistent cross-sectional tracheal diameter and, hence, the generation of high-intense low-spread frequency components. An intermittent low-intense and a relatively greater frequency spread in PS signal appear as high [Formula: see text], [Formula: see text], [Formula: see text], and [Formula: see text] values. With these complex network parameters as input attributes, the supervised machine learning techniques- discriminant analyses, support vector machines, k-nearest neighbors, and neural network pattern recognition (PRNN)- classify the signals with more than 90% accuracy, with PRNN having 25 neurons in the hidden layer achieving the highest (98.82%).

A large-scale and PCR-referenced vocal audio dataset for COVID-19

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.

Attention Feature Fusion Network via Knowledge Propagation for Automated Respiratory Sound Classification

Goal: In light of the COVID-19 pandemic, the early diagnosis of respiratory diseases has become increasingly crucial. Traditional diagnostic methods such as computed tomography (CT) and magnetic resonance imaging (MRI), while accurate, often face accessibility challenges. Lung auscultation, a simpler alternative, is subjective and highly dependent on the clinician's expertise. The pandemic has further exacerbated these challenges by restricting face-to-face consultations. This study aims to overcome these limitations by developing an automated respiratory sound classification system using deep learning, facilitating remote and accurate diagnoses. Methods: We developed a deep convolutional neural network (CNN) model that utilizes spectrographic representations of respiratory sounds within an image classification framework. Our model is enhanced with attention feature fusion of low-to-high-level information based on a knowledge propagation mechanism to increase classification effectiveness. This novel approach was evaluated using the ICBHI benchmark dataset and a larger, self-collected Pediatric dataset comprising outpatient children aged 1 to 6 years. Results: The proposed CNN model with knowledge propagation demonstrated superior performance compared to existing state-of-the-art models. Specifically, our model showed higher sensitivity in detecting abnormalities in the Pediatric dataset, indicating its potential for improving the accuracy of respiratory disease diagnosis. Conclusions: The integration of a knowledge propagation mechanism into a CNN model marks a significant advancement in the field of automated diagnosis of respiratory disease. This study paves the way for more accessible and precise healthcare solutions, which is especially crucial in pandemic scenarios.

Sound generation mechanisms in a collapsible tube

Collapsible tubes can be employed to study the sound generation mechanism in the human respiratory system. The goals of this work are (a) to determine the airflow characteristics connected to three different collapse states of a physiological tube and (b) to find a relation between the sound power radiated by the tube and its collapse state. The methodology is based on the implementation of computational fluid dynamics simulation on experimentally validated geometries. The flow is characterized by a radical change of behavior before and after the contact of the lumen. The maximum of the sound power radiated corresponds to the post-buckling configuration. The idea of an acoustic tube law is proposed. The presented results are relevant to the study of self-excited oscillations and wheezing sounds in the lungs.

Acute pleurisy mimicking neck pain in a young volleyball player: a case report

INTRODUCTION

Patients presenting to direct access physiotherapists may present with a serious pathology that mimics a musculoskeletal condition. Recognition of atypical clinical patterns allows for referral to an appropriate provider when a serious pathology is present. This case report details a patient with a pulmonary pathology who presented to a physiotherapist with a complaint of neck and chest pain following medical consultations.

CASE PRESENTATION

A 29-year-old amateur volleyball player arrived at the physiotherapist's clinic five days after experiencing the onset of neck pain. She complained of pain on the right side, which extended to the trapezius, as well as occasional discomfort in the lower lateral and anterior chest. The patient noted that the pain worsened when lying supine or on her left side, and during coughing. After developing symptoms resembling a cold, she sought care at two different emergency clinics where physicians diagnosed seasonal flu and an unrelated muscle strain. Despite treatment, the pain persisted, accompanied by fever and general weakness, disrupting her sleep. Following a review of a medical history and a physical examination, musculoskeletal causes of pain appeared unlikely, prompting consideration of a pulmonary pathology. Referral to a specialist was deemed necessary.

CONCLUSION

This case report highlights the importance of screening for serious pathology in direct access physiotherapy, irrespective of a prior physician consultation.

Assessing the accuracy of pleural puncture sites in patients with pleural effusion as determined by clinical examination versus ultrasound-A single-centre prospective study

INTRODUCTION

This study aimed to ascertain the accuracy of clinical examination for the determination of pleural puncture sites as compared to the use of ultrasonography in patients with pleural effusion.

MATERIAL AND METHODS

A single-centre, prospective, observational study was carried out amongst 115 patients with pleural effusion in a tertiary care hospital in western India. Patients were subjected to clinical assessment for determination of pleural puncture sites and the same were confirmed with ultrasonography. All physicians were blinded to the marking of the previous physician to prevent any influence on their assessment.

RESULTS

The study had 345 physician observations. The overall accuracy of the clinical examination was 94.8%. Multivariate logistic regression of the factors responsible for the accuracy of clinical examination demonstrated a significant role of higher body mass index (BMI) (OR-1.19) and lower zone pleural effusions (OR-4.99) when adjusted for age, gender, side of effusion, and experience of examining doctors. When the effusions were classified according to their location, lower zone pleural effusions and loculated pleural effusions had an error rate of 15.9% and 8.33%, respectively.

CONCLUSION

An ultrasound is the standard of care to assess all pleural effusions and guide the best point for aspiration.

An Accelerometer-Based Wearable Patch for Robust Respiratory Rate and Wheeze Detection Using Deep Learning

Wheezing is a critical indicator of various respiratory conditions, including asthma and chronic obstructive pulmonary disease (COPD). Current diagnosis relies on subjective lung auscultation by physicians. Enabling this capability via a low-profile, objective wearable device for remote patient monitoring (RPM) could offer pre-emptive, accurate respiratory data to patients. With this goal as our aim, we used a low-profile accelerometer-based wearable system that utilizes deep learning to objectively detect wheezing along with respiration rate using a single sensor. The miniature patch consists of a sensitive wideband MEMS accelerometer and low-noise CMOS interface electronics on a small board, which was then placed on nine conventional lung auscultation sites on the patient's chest walls to capture the pulmonary-induced vibrations (PIVs). A deep learning model was developed and compared with a deterministic time-frequency method to objectively detect wheezing in the PIV signals using data captured from 52 diverse patients with respiratory diseases. The wearable accelerometer patch, paired with the deep learning model, demonstrated high fidelity in capturing and detecting respiratory wheezes and patterns across diverse and pertinent settings. It achieved accuracy, sensitivity, and specificity of 95%, 96%, and 93%, respectively, with an AUC of 0.99 on the test set-outperforming the deterministic time-frequency approach. Furthermore, the accelerometer patch outperforms the digital stethoscopes in sound analysis while offering immunity to ambient sounds, which not only enhances data quality and performance for computational wheeze detection by a significant margin but also provides a robust sensor solution that can quantify respiration patterns simultaneously.

Clinical decision support system using a machine learning model to assist simultaneous cardiopulmonary auscultation: Open-label randomized controlled trial

Background

The utility of a clinical decision support system using a machine learning (ML) model for simultaneous cardiac and pulmonary auscultation is unknown.

Objective

This study aimed to develop and evaluate an ML system's utility for cardiopulmonary auscultation.

Methods

First, we developed an ML system for cardiopulmonary auscultation, using cardiopulmonary sound files from our previous study. The technique involved pre-processing, feature extraction, and classification through several neural network layers. After integration, the output class was categorized as "normal," "abnormal," or "undetermined." Second, we evaluated the ML system with 24 junior residents in an open-label randomized controlled trial at a university hospital. Participants were randomly assigned to the ML system group (intervention) or conventional auscultation group (control). During training, participants listened to four cardiac and four pulmonary sounds, all of which were correctly classified. Then, participants classified a series of 16 simultaneous cardiopulmonary sounds. The control group auscultated the sounds using noise-cancelling headphones, while the intervention group did so by watching recommendations from the ML system.

Results

The total scores for correctly identified normal or abnormal cardiopulmonary sounds in the intervention group were significantly higher than those in the control group (366/384 [95.3%] vs. 343/384 [89.3%], P = 0.003). The cardiac test score in the intervention group was better (111/192 [57.8%] vs. 90/192 [46.9%], P = 0.04); there was no significant difference in pulmonary auscultation.

Conclusions

The ML-based system improved the accuracy of cardiopulmonary auscultation for junior residents. This result suggests that the system can assist early-career physicians in accurate screening.

Weighted aggregation through probability based ranking: An optimized federated learning architecture to classify respiratory diseases

Background and Objective Respiratory Diseases are one of the leading chronic illnesses in the world according to the reports by World Health Organization. Diagnosing these respiratory diseases is done through auscultation where a medical professional listens to sounds of air in the lungs for anomalies through a stethoscope. This method necessitates extensive experience and can also be misinterpreted by the medical professional. To address this issue, we introduce an AI-based solution that listens to the lung sounds and classifies the respiratory disease detected. Since the research work deals with medical data that is tightly under wraps due to privacy concerns in the medical field, we introduce a Deep learning solution to classify the diseases and a custom Federated learning (FL) approach to further improve the accuracy of the deep learning model and simultaneously maintain data privacy. Federated Learning architecture maintains data privacy and facilitates a distributed learning system for medical infrastructures. Methods The approach utilizes Generative Adversarial Networks (GAN) based Federated learning approach to ensure data privacy. Generative Adversarial Networks generate new data by synthesizing new lung sounds. This new synthesized data is then converted to spectrograms and trained on a neural network to classify four lung diseases, Heart Attack and Normal breathing patterns. Furthermore, to address performance loss during FL, we also propose a new "Weighted Aggregation through Probability-based Ranking (FedWAPR)" algorithm for optimizing the FL aggregation process. The FedWAPR aggregation takes inspiration from exponential distribution function and ranks better performing clients according to it. Results and Conclusion A test accuracy of about 92% was achieved by the trained model while classifying various respiratory diseases and heart failure. Additionally, we developed a novel FedWAPR approach that significantly outperformed the FedAVG approach for the FL aggregate function. A patient can be checked for respiratory diseases using this improved learning approach without the need for extensive sensitive data recording or for making sure the data sample obtained is secure. In a decentralized training runtime, the trained model successfully classifies various respiratory diseases and heart failure using lung sounds with a test accuracy on par with a centralized model.

Enabling Continuous Breathing-Phase Contextualization via Wearable-Based Impedance Pneumography and Lung Sounds: A Feasibility Study

Chronic respiratory diseases affect millions and are leading causes of death in the US and worldwide. Pulmonary auscultation provides clinicians with critical respiratory health information through the study of Lung Sounds (LS) and the context of the breathing-phase and chest location in which they are measured. Existing auscultation technologies, however, do not enable the simultaneous measurement of this context, thereby potentially limiting computerized LS analysis. In this work, LS and Impedance Pneumography (IP) measurements were obtained from 10 healthy volunteers while performing normal and forced-expiratory (FE) breathing maneuvers using our wearable IP and respiratory sounds (WIRS) system. Simultaneous auscultation was performed with the Eko CORE stethoscope (EKO). The breathing-phase context was extracted from the IP signals and used to compute phase-by-phase (Inspiratory (I), expiratory (E), and their ratio (I:E)) and breath-by-breath acoustic features. Their individual and added value was then elucidated through machine learning analysis. We found that the phase-contextualized features effectively captured the underlying acoustic differences between deep and FE breaths, yielding a maximum F1 Score of 84.1 ±11.4% with the phase-by-phase features as the strongest contributors to this performance. Further, the individual phase-contextualized models outperformed the traditional breath-by-breath models in all cases. The validity of the results was demonstrated for the LS obtained with WIRS, EKO, and their combination. These results suggest that incorporating breathing-phase context may enhance computerized LS analysis. Hence, multimodal sensing systems that enable this, such as WIRS, have the potential to advance LS clinical utility beyond traditional manual auscultation and improve patient care.

Bionanotechnology and bioMEMS (BNM): state-of-the-art applications, opportunities, and challenges

The development of micro- and nanotechnology for biomedical applications has defined the cutting edge of medical technology for over three decades, as advancements in fabrication technology developed originally in the semiconductor industry have been applied to solving ever-more complex problems in medicine and biology. These technologies are ideally suited to interfacing with life sciences, since they are on the scale lengths as cells (microns) and biomacromolecules (nanometers). In this paper, we review the state of the art in bionanotechnology and bioMEMS (collectively BNM), including developments and challenges in the areas of BNM, such as microfluidic organ-on-chip devices, oral drug delivery, emerging technologies for managing infectious diseases, 3D printed microfluidic devices, AC electrokinetics, flexible MEMS devices, implantable microdevices, paper-based microfluidic platforms for cellular analysis, and wearable sensors for point-of-care testing.

Exploring Microphone Technologies for Digital Auscultation Devices

The aim of this work is to present a preliminary study for the design of a digital auscultation system, i.e., a novel wearable device for patient chest auscultation and a digital stethoscope. The development and testing of the electronic stethoscope prototype is reported with an emphasis on the description and selection of sound transduction systems and analog electronic processing. The focus on various microphone technologies, such as micro-electro-mechanical systems (MEMSs), electret condensers, and piezoelectronic diaphragms, intends to emphasize the most suitable transducer for auscultation. In addition, we report on the design and development of a digital acquisition system for the human body for sound recording by using a modular device approach in order to fit the chosen analog and digital mics. Tests were performed on a designed phantom setup, and a qualitative comparison between the sounds recorded with the newly developed acquisition device and those recorded with two commercial digital stethoscopes is reported.

Evolution of the Stethoscope: Advances with the Adoption of Machine Learning and Development of Wearable Devices

The stethoscope has long been used for the examination of patients, but the importance of auscultation has declined due to its several limitations and the development of other diagnostic tools. However, auscultation is still recognized as a primary diagnostic device because it is non-invasive and provides valuable information in real-time. To supplement the limitations of existing stethoscopes, digital stethoscopes with machine learning (ML) algorithms have been developed. Thus, now we can record and share respiratory sounds and artificial intelligence (AI)-assisted auscultation using ML algorithms distinguishes the type of sounds. Recently, the demands for remote care and non-face-to-face treatment diseases requiring isolation such as coronavirus disease 2019 (COVID-19) infection increased. To address these problems, wireless and wearable stethoscopes are being developed with the advances in battery technology and integrated sensors. This review provides the history of the stethoscope and classification of respiratory sounds, describes ML algorithms, and introduces new auscultation methods based on AI-assisted analysis and wireless or wearable stethoscopes.

Deep learning-based lung sound analysis for intelligent stethoscope

Auscultation is crucial for the diagnosis of respiratory system diseases. However, traditional stethoscopes have inherent limitations, such as inter-listener variability and subjectivity, and they cannot record respiratory sounds for offline/retrospective diagnosis or remote prescriptions in telemedicine. The emergence of digital stethoscopes has overcome these limitations by allowing physicians to store and share respiratory sounds for consultation and education. On this basis, machine learning, particularly deep learning, enables the fully-automatic analysis of lung sounds that may pave the way for intelligent stethoscopes. This review thus aims to provide a comprehensive overview of deep learning algorithms used for lung sound analysis to emphasize the significance of artificial intelligence (AI) in this field. We focus on each component of deep learning-based lung sound analysis systems, including the task categories, public datasets, denoising methods, and, most importantly, existing deep learning methods, i.e., the state-of-the-art approaches to convert lung sounds into two-dimensional (2D) spectrograms and use convolutional neural networks for the end-to-end recognition of respiratory diseases or abnormal lung sounds. Additionally, this review highlights current challenges in this field, including the variety of devices, noise sensitivity, and poor interpretability of deep models. To address the poor reproducibility and variety of deep learning in this field, this review also provides a scalable and flexible open-source framework that aims to standardize the algorithmic workflow and provide a solid basis for replication and future extension: https://github.com/contactless-healthcare/Deep-Learning-for-Lung-Sound-Analysis .

Interpretation of lung disease classification with light attention connected module

Lung diseases lead to complications from obstructive diseases, and the COVID-19 pandemic has increased lung disease-related deaths. Medical practitioners use stethoscopes to diagnose lung disease. However, an artificial intelligence model capable of objective judgment is required since the experience and diagnosis of respiratory sounds differ. Therefore, in this study, we propose a lung disease classification model that uses an attention module and deep learning. Respiratory sounds were extracted using log-Mel spectrogram MFCC. Normal and five types of adventitious sounds were effectively classified by improving VGGish and adding a light attention connected module to which the efficient channel attention module (ECA-Net) was applied. The performance of the model was evaluated for accuracy, precision, sensitivity, specificity, f1-score, and balanced accuracy, which were 92.56%, 92.81%, 92.22%, 98.50%, 92.29%, and 95.4%, respectively. We confirmed high performance according to the attention effect. The classification causes of lung diseases were analyzed using gradient-weighted class activation mapping (Grad-CAM), and the performances of their models were compared using open lung sounds measured using a Littmann 3200 stethoscope. The experts' opinions were also included. Our results will contribute to the early diagnosis and interpretation of diseases in patients with lung disease by utilizing algorithms in smart medical stethoscopes.

Bayesian evaluation of the accuracy of a thoracic auscultation scoring system in dairy calves with bronchopneumonia using a standard lung sound nomenclature

BACKGROUND

Although thoracic auscultation (AUSC) in calves is quick and easy to perform, the definition of lung sounds is highly variable and leads to poor to moderate accuracy in diagnosing bronchopneumonia (BP).

HYPOTHESIS/OBJECTIVES

Evaluate the diagnostic accuracy of an AUSC scoring system based on a standard lung sound nomenclature at different cut-off values, accounting for the absence of a gold standard test for BP diagnosis.

ANIMALS

Three hundred thirty-one calves.

METHODS

We considered the following pathological lung sounds: increased breath sounds (score 1), wheezes and crackles (score 2), increased bronchial sounds (score 3), and pleural friction rubs (score 4). Thoracic auscultation was categorized as AUSC1 (positive calves for scores ≥1), AUSC2 (positive calves for scores ≥2), and AUSC3 (positive calves for scores ≥3). The accuracy of AUSC categorizations was determined using 3 imperfect diagnostic tests with a Bayesian latent class model and sensitivity analysis (informative vs weakly informative vs noninformative priors and with vs without covariance between ultrasound and clinical scoring).

RESULTS

Based on the priors used, the sensitivity (95% Bayesian confidence interval [BCI]) of AUSC1 ranged from 0.89 (0.80-0.97) to 0.95 (0.86-0.99), with a specificity (95% BCI) of 0.54 (0.45-0.71) to 0.60 (0.47-0.94). Removing increased breath sounds from the categorizations resulted in increased specificity (ranging between 0.97 [0.93-0.99] and 0.98 [0.94-0.99] for AUSC3) at the cost of decreased sensitivity (0.66 [0.54-0.78] to 0.81 [0.65-0.97]).

CONCLUSIONS AND CLINICAL IMPORTANCE

A standardized definition of lung sounds improved AUSC accuracy for BP diagnosis in calves.

Deep learning diagnostic and severity-stratification for interstitial lung diseases and chronic obstructive pulmonary disease in digital lung auscultations and ultrasonography: clinical protocol for an observational case-control study

BACKGROUND

Interstitial lung diseases (ILD), such as idiopathic pulmonary fibrosis (IPF) and non-specific interstitial pneumonia (NSIP), and chronic obstructive pulmonary disease (COPD) are severe, progressive pulmonary disorders with a poor prognosis. Prompt and accurate diagnosis is important to enable patients to receive appropriate care at the earliest possible stage to delay disease progression and prolong survival. Artificial intelligence-assisted lung auscultation and ultrasound (LUS) could constitute an alternative to conventional, subjective, operator-related methods for the accurate and earlier diagnosis of these diseases. This protocol describes the standardised collection of digitally-acquired lung sounds and LUS images of adult outpatients with IPF, NSIP or COPD and a deep learning diagnostic and severity-stratification approach.

METHODS

A total of 120 consecutive patients (≥ 18 years) meeting international criteria for IPF, NSIP or COPD and 40 age-matched controls will be recruited in a Swiss pulmonology outpatient clinic, starting from August 2022. At inclusion, demographic and clinical data will be collected. Lung auscultation will be recorded with a digital stethoscope at 10 thoracic sites in each patient and LUS images using a standard point-of-care device will be acquired at the same sites. A deep learning algorithm (DeepBreath) using convolutional neural networks, long short-term memory models, and transformer architectures will be trained on these audio recordings and LUS images to derive an automated diagnostic tool. The primary outcome is the diagnosis of ILD versus control subjects or COPD. Secondary outcomes are the clinical, functional and radiological characteristics of IPF, NSIP and COPD diagnosis. Quality of life will be measured with dedicated questionnaires. Based on previous work to distinguish normal and pathological lung sounds, we estimate to achieve convergence with an area under the receiver operating characteristic curve of > 80% using 40 patients in each category, yielding a sample size calculation of 80 ILD (40 IPF, 40 NSIP), 40 COPD, and 40 controls.

DISCUSSION

This approach has a broad potential to better guide care management by exploring the synergistic value of several point-of-care-tests for the automated detection and differential diagnosis of ILD and COPD and to estimate severity. Trial registration Registration: August 8, 2022.

CLINICALTRIALS

gov Identifier: NCT05318599.

Smart Devices Are Poised to Revolutionize the Usefulness of Respiratory Sounds

The association between breathing sounds and respiratory health or disease has been exceptionally useful in the practice of medicine since the advent of the stethoscope. Remote patient monitoring technology and artificial intelligence offer the potential to develop practical means of assessing respiratory function or dysfunction through continuous assessment of breathing sounds when patients are at home, at work, or even asleep. Automated reports such as cough counts or the percentage of the breathing cycles containing wheezes can be delivered to a practitioner via secure electronic means or returned to the clinical office at the first opportunity. This has not previously been possible. The four respiratory sounds that most lend themselves to this technology are wheezes, to detect breakthrough asthma at night and even occupational asthma when a patient is at work; snoring as an indicator of OSA or adequacy of CPAP settings; cough in which long-term recording can objectively assess treatment adequacy; and crackles, which, although subtle and often overlooked, can contain important clinical information when appearing in a home recording. In recent years, a flurry of publications in the engineering literature described construction, usage, and testing outcomes of such devices. Little of this has appeared in the medical literature. The potential value of this technology for pulmonary medicine is compelling. We expect that these tiny, smart devices soon will allow us to address clinical questions that occur away from the clinic.

Evaluating Listening Performance for COVID-19 Detection by Clinicians and Machine Learning: A Comparative Study

BACKGROUND

To date, performance comparisons between men and machines have been performed in many health domains. Yet, machine learning models and human performance comparisons in audio-based respiratory diagnosis remain largely unexplored.

OBJECTIVE

The primary objective of this study is to compare human clinicians and a machine learning model in predicting COVID-19 from respiratory sound recordings.

METHODS

In this study, we compare human clinicians and a machine learning model in predicting COVID-19 from respiratory sound recordings. Prediction performance on 24 audio samples (12 tested positive) made by 36 clinicians with experience in treating COVID-19 or other respiratory illnesses is compared with predictions made by a machine learning model trained on 1,162 samples. Each sample consists of voice, cough, and breathing sound recordings from one subject, and the length of each sample is around 20 seconds. We also investigated whether combining the predictions of the model and human experts could further enhance the performance, in terms of both accuracy and confidence.

RESULTS

The machine learning model outperformed the clinicians, yielding a sensitivity of 0.75 and a specificity of 0.83, while the best performance achieved by the clinician was 0.67 in terms of sensitivity and 0.75 in terms of specificity. Integrating clinicians' and model's predictions, however, could enhance performance further, achieving a sensitivity of 0.83 and a specificity of 0.92.

CONCLUSIONS

Our findings suggest that the clinicians and the machine learning model could make better clinical decisions via a cooperative approach and achieve higher confidence in audio-based respiratory diagnosis.

Physicians' ability to recognize adventitious lung sounds

BACKGROUND

Lung auscultation is an important tool for diagnosing respiratory diseases. However, the ability of observers to recognize respiratory sounds varies considerably and depends on the sound. The present study aimed to assess the auscultatory skills of healthcare professionals and medical students.

METHODS

A total of 295 physicians (185 pediatricians, 69 pulmonologists, and 41 physicians of general/internal medicine and subspecialties), 55 residents, and 50 medical students participated in the survey. They listened to five audio-recorded respiratory sounds and described them in free-form answers.

RESULTS

The rates of correct answers were 55.2% for fine crackles, 74.5% for coarse crackles, 72.2% for wheezes, 18.75% for squawks, and 11.25% for pleural friction rub. The medical specialty was correlated with the correct answers and both pediatricians and physicians of general/internal medicine and subspecialties recognized fewer sounds compared with respiratory physicians (odds ratio [OR]: 0.37; confidence interval [CI]: 0.22-0.62; p < 0.001 and, OR: 0.47; CI: 0.22-0.99, p = 0.048, respectively). Years of experience were negatively correlated with the number of correct answers (OR: 0.73; CI:0.62-0.84; p = 0.001).

CONCLUSIONS

Gaps remain in both terminology and recognition of lung sounds among a wide population of Greek physicians. Less experienced physicians perform better on lung auscultation, indicating that continuing education with critical feedback should be offered.

Emerging Imaging Modalities for Functional Assessment of Donor Lungs Ex Vivo

The severe shortage of functional donor lungs that can be offered to recipients has been a major challenge in lung transplantation. Innovative ex vivo lung perfusion (EVLP) and tissue engineering methodologies are now being developed to repair damaged donor lungs that are deemed unsuitable for transplantation. To assess the efficacy of donor lung reconditioning methods intended to rehabilitate rejected donor lungs, monitoring of lung function with improved spatiotemporal resolution is needed. Recent developments in live imaging are enabling non-destructive, direct, and longitudinal modalities for assessing local tissue and whole lung functions. In this review, we describe how emerging live imaging modalities can be coupled with lung tissue engineering approaches to promote functional recovery of ex vivo donor lungs.

Interstitial Lung Disease: A Focused Review for the Emergency Clinician

BACKGROUND

Interstitial lung disease (ILD) is a group of restrictive pulmonary diseases associated with diffuse interstitial and parenchymal inflammation. Patients can present to the emergency department with severe exacerbation.

OBJECTIVE

This narrative review provides emergency clinicians with the most recent evidence concerning acute exacerbation of ILD (AE-ILD).

DISCUSSION

AE-ILD can present as acute respiratory distress in a patient with a pre-existing ILD diagnosis or as a de novo presentation of ILD, and is associated with significant morbidity and mortality. A variety of underlying triggers may result in AE-ILD. Emergency clinicians must first assess for extraneous causes of respiratory decompensation prior to diagnosing AE-ILD. For a de novo presentation of ILD, emergency physicians should also assess for possible reversible causes. AE-ILD is managed with systemic steroids, immunosuppressants, intravenous antibiotics, supplemental oxygen, and extracorporeal membrane oxygenation in severe cases. Given the high mortality rates in the absence of lung transplantation, early referral to transplant centers is essential to increase chances of survival.

CONCLUSIONS

Emergency clinician knowledge of AE-ILD can improve the evaluation and management of these patients.

Quantification of respiratory sounds by a continuous monitoring system can be used to predict complications after extubation: a pilot study

To show that quantification of abnormal respiratory sounds by our developed device is useful for predicting respiratory failure and airway problems after extubation. A respiratory sound monitoring system was used to collect respiratory sounds in patients undergoing extubation. The recorded respiratory sounds were subsequently analyzed. We defined the composite poor outcome as requiring any of following medical interventions within 48 h as defined below. This composite outcome includes reintubation, surgical airway management, insertion of airway devices, unscheduled use of noninvasive ventilation or high-flow nasal cannula, unscheduled use of inhaled medications, suctioning of sputum by bronchoscopy and unscheduled imaging studies. The quantitative values (QV) for each abnormal respiratory sound and inspiratory sound volume were compared between composite outcome groups and non-outcome groups. Fifty-seven patients were included in this study. The composite outcome occurred in 18 patients. For neck sounds, the QVs of stridor and rhonchi were significantly higher in the outcome group vs the non-outcome group. For anterior thoracic sounds, the QVs of wheezes, rhonchi, and coarse crackles were significantly higher in the outcome group vs the non-outcome group. For bilateral lateral thoracic sounds, the QV of fine crackles was significantly higher in the outcome group vs the non-outcome group. Cervical inspiratory sounds volume (average of five breaths) immediately after extubation was significantly louder in the outcome group vs non-outcome group (63.3 dB vs 54.3 dB, respectively; p < 0.001). Quantification of abnormal respiratory sounds and respiratory volume may predict respiratory failure and airway problems after extubation.

Compressed Sensing Data with Performing Audio Signal Reconstruction for the Intelligent Classification of Chronic Respiratory Diseases

Chronic obstructive pulmonary disease (COPD) concerns the serious decline of human lung functions. These have emerged as one of the most concerning health conditions over the last two decades, after cancer around the world. The early diagnosis of COPD, particularly of lung function degradation, together with monitoring the condition by physicians, and predicting the likelihood of exacerbation events in individual patients, remains an important challenge to overcome. The requirements for achieving scalable deployments of data-driven methods using artificial intelligence for meeting such a challenge in modern COPD healthcare have become of paramount and critical importance. In this study, we have established the experimental foundations for acquiring and indeed generating biomedical observation data, for good performance signal analysis and machine learning that will lead us to the intelligent diagnosis and monitoring of COPD conditions for individual patients. Further, we investigated on the multi-resolution analysis and compression of lung audio signals, while we performed their machine classification under two distinct experiments. These respectively refer to conditions involving (1) "Healthy" or "COPD" and (2) "Healthy", "COPD", or "Pneumonia" classes. Signal reconstruction with the extracted features for machine learning and testing was also performed for securing the integrity of the original audio recordings. These showed high levels of accuracy together with the performances of the selected machine learning-based classifiers using diverse metrics. Our study shows promising levels of accuracy in classifying Healthy and COPD and also Healthy, COPD, and Pneumonia conditions. Further work in this study will be imminently extended to new experiments using multi-modal sensing hardware and data fusion techniques for the development of the next generation diagnosis systems for COPD healthcare of the future.

A machine learning approach to the development and prospective evaluation of a pediatric lung sound classification model

Auscultation, a cost-effective and non-invasive part of physical examination, is essential to diagnose pediatric respiratory disorders. Electronic stethoscopes allow transmission, storage, and analysis of lung sounds. We aimed to develop a machine learning model to classify pediatric respiratory sounds. Lung sounds were digitally recorded during routine physical examinations at a pediatric pulmonology outpatient clinic from July to November 2019 and labeled as normal, crackles, or wheezing. Ensemble support vector machine models were trained and evaluated for four classification tasks (normal vs. abnormal, crackles vs. wheezing, normal vs. crackles, and normal vs. wheezing) using K-fold cross-validation (K = 10). Model performance on a prospective validation set (June to July 2021) was compared with those of pediatricians and non-pediatricians. Total 680 clips were used for training and internal validation. The model accuracies during internal validation for normal vs. abnormal, crackles vs. wheezing, normal vs. crackles, and normal vs. wheezing were 83.68%, 83.67%, 80.94%, and 90.42%, respectively. The prospective validation (n = 90) accuracies were 82.22%, 67.74%, 67.80%, and 81.36%, respectively, which were comparable to pediatrician and non-pediatrician performance. An automated classification model of pediatric lung sounds is feasible and maybe utilized as a screening tool for respiratory disorders in this pandemic era.

The effects of simple graphical and mental visualization of lung sounds in teaching lung auscultation during clinical clerkship: A preliminary study

INTRODUCTION

The study aimed to evaluate visualization-based training's effects on lung auscultation during clinical clerkship (CC) in the Department of Respiratory Medicine on student skills and confidence.

METHODS

The study period was December 2020-November 2021. Overall, 65 students attended a lecture on lung auscultation featuring a simulator (Mr. Lung™). Among them, 35 (visualization group) received additional training wherein they were asked to mentally visualize lung sounds using a graphical visualized lung sounds diagram as an example. All students answered questions on their self-efficacy regarding lung auscultation before and after four weeks of CC. They also took a lung auscultation test with the simulator at the beginning of CC (pre-test) and on the last day of the third week (post-test) (maximum score: 25). We compared the answers in the questionnaire and the test scores between the visualization group and students who only attended the lecture (control group, n = 30). The Wilcoxon signed-rank test and analysis of covariance were used to compare the answers to the questionnaire about confidence in lung auscultation and the scores of the lung auscultation tests before and after the training.

RESULTS

Confidence in auscultation of lung sounds significantly increased in both groups (five-point Likert scale, visualization group: pre-questionnaire median 1 [Interquartile range 1] to post-questionnaire 3 [1], p<0.001; control group: 2 [1] to 3 [1], p<0.001) and was significantly higher in the visualization than in the control group. Test scores increased in both groups (visualization group: pre-test 11 [2] to post-test 15 [4], p<0.001; control group: 11 [5] to 14 [4], p<0.001). However, there were no differences between both groups' pre and post-tests scores (p = 0.623).

CONCLUSION

Visualizing lung sounds may increase medical students' confidence in their lung auscultation skills; this may reduce their resistance to lung auscultation and encourage the repeated auscultation necessary to further improve their long-term auscultation abilities.

The utility of phonocardiograms in real-time remote cardiac auscultation using an internet-connected electronic stethoscope: Open-label randomized controlled pilot trial

Background

We have shown classical cardiac auscultation was superior to remote auscultation. We developed a phonocardiogram system to visualize sounds in remote auscultation.

Objective

This study aimed to evaluate the effect of phonocardiograms on the diagnostic accuracy in remote auscultation using a cardiology patient simulator.

Methods

In this open-label randomized controlled pilot trial, we randomly assigned physicians to the real-time remote auscultation group (control group) or the real-time remote auscultation with the phonocardiogram group (intervention group). Participants attended a training session in which they auscultated 15 sounds with the correct classification. After that, participants attended a test session where they had to classify 10 sounds. The control group auscultated the sounds remotely using an electronic stethoscope, an online medical program and a 4-K TV speaker without watching the TV screen. The intervention group performed auscultation like the control group but watched the phonocardiogram on the TV screen. The primary and secondary outcomes were the total test scores and each sound score, respectively.

Results

A total of 24 participants were included. The total test score in the intervention group (80/120, 66.7%) was higher than that in the control group (66/120, 55.0%), although the difference was statistically insignificant (P = .06). The correct answer rates of each sound were not different. Valvular/irregular rhythm sounds were not misclassified as normal sounds in the intervention group.

Conclusions

Using a phonocardiogram improved the total correct answer rate by more than 10% in remote auscultation, although statistically insignificant. The phonocardiogram could help physicians screen valvular/irregular rhythm sounds from normal sounds.

Trial registration

UMIN-CTR UMIN000045271; https://upload.umin.ac.jp/cgi-open-bin/ctr/ctr_view.cgi?recptno=R000051710.

Reliability and Validity of Computerized Adventitious Respiratory Sounds in People with Bronchiectasis

Background: Computerized adventitious respiratory sounds (ARS), such as crackles and wheezes, have been poorly explored in bronchiectasis, especially their measurement properties. This study aimed to test the reliability and validity of ARS in bronchiectasis. Methods: Respiratory sounds were recorded twice at 4 chest locations on 2 assessment sessions (7 days apart) in people with bronchiectasis and daily sputum expectoration. The total number of crackles, number of wheezes and wheeze occupation rate (%) were the parameters extracted. Results: 28 participants (9 men; 62 ± 12 y) were included. Total number of crackles and wheezes showed moderate within-day (ICC 0.87, 95% CI 0.74−0.94; ICC 0.86, 95% CI 0.71−0.93) and between-day reliability (ICC 0.70, 95% CI 0.43−0.86; ICC 0.78, 95% CI 0.56−0.90) considering all chest locations and both respiratory phases; wheeze occupation rate showed moderate within-day reliability (ICC 0.86, 95% CI 0.71−0.93), but poor between-day reliability (ICC 0.71, 95% CI 0.33−0.87). Bland−Altman plots revealed no systematic bias, but wide limits of agreement, particularly in the between-days analysis. All ARS parameters correlated moderately with the amount of daily sputum expectoration (r > 0.4; p < 0.05). No other significant correlations were observed. Conclusion: ARS presented moderate reliability and were correlated with the daily sputum expectoration in bronchiectasis. The use of sequential measurements may be an option to achieve greater accuracy when ARS are used to monitor or assess the effects of physiotherapy interventions in this population.

Regularity and mechanism of fake crackle noise in an electronic stethoscope

Background: Electronic stethoscopes are widely used for cardiopulmonary auscultation; their audio recordings are used for the intelligent recognition of cardiopulmonary sounds. However, they generate noise similar to a crackle during use, significantly interfering with clinical diagnosis. This paper will discuss the causes, characteristics, and occurrence rules of the fake crackle and establish a reference for improving the reliability of the electronic stethoscope in lung auscultation. Methods: A total of 56 participants with healthy lungs (no underlying pulmonary disease, no recent respiratory symptoms, and no adventitious lung sound, as confirmed by an acoustic stethoscope) were enrolled in this study. A 30-s audio recording was recorded from each of the nine locations of the larynx and lungs of each participant with a 3M Littmann 3200 electronic stethoscope, and the audio was output in diaphragm mode and auscultated by the clinician. The doctor identified the fake crackles and analyzed their frequency spectrum. High-pass and low-pass filters were used to detect the frequency distribution of the fake crackles. Finally, the fake crackle was artificially regenerated to explore its causes. Results: A total of 500 audio recordings were included in the study, with 61 fake crackle audio recordings. Fake crackles were found predominantly in the lower lung. There were significant differences between lower lung and larynx (p < 0.001), lower lung and upper lung (p = 0.005), lower lung and middle lung (p = 0.005), and lower lung and infrascapular region (p = 0.027). Furthermore, more than 90% of fake crackles appeared in the inspiratory phase, similar to fine crackles, significantly interfering with clinical diagnosis. The spectral analysis revealed that the frequency range of fake crackles was approximately 250-1950 Hz. The fake crackle was generated when the diaphragm of the electronic stethoscope left the skin slightly but not completely. Conclusion: Fake crackles are most likely to be heard when using an electronic stethoscope to auscultate bilateral lower lungs, and the frequency of a fake crackle is close to that of a crackle, likely affecting the clinician's diagnosis.

Evaluation of Internet-Connected Real-Time Remote Auscultation: An Open-Label Randomized Controlled Pilot Trial

The utility of remote auscultation was unknown. This study aimed to evaluate internet-connected real-time remote auscultation using cardiopulmonary simulators. In this open-label randomized controlled trial, the physicians were randomly assigned to the real-time remote auscultation group (intervention group) or the classical auscultation group (control group). After the training session, the participants had to classify the ten cardiopulmonary sounds in random order as the test session. In both sessions, the intervention group auscultated with an internet-connected electronic stethoscope. The control group performed direct auscultation using a classical stethoscope. The total scores for correctly identified normal or abnormal cardiopulmonary sounds were 97/100 (97%) in the intervention group and 98/100 (98%) in the control group with no significant difference between the groups (p > 0.99). In cardiac auscultation, the test score in the control group (94%) was superior to that in the intervention group (72%, p < 0.05). Valvular diseases were not misclassified as normal sounds in real-time remote cardiac auscultation. The utility of real-time remote cardiopulmonary auscultation using an internet-connected electronic stethoscope was comparable to that of classical auscultation. Classical cardiac auscultation was superior to real-time remote auscultation. However, real-time remote cardiac auscultation is useful for classifying valvular diseases and normal sounds.

Sensing Devices for Detecting and Processing Acoustic Signals in Healthcare

Acoustic signals are important markers to monitor physiological and pathological conditions, e.g., heart and respiratory sounds. The employment of traditional devices, such as stethoscopes, has been progressively superseded by new miniaturized devices, usually identified as microelectromechanical systems (MEMS). These tools are able to better detect the vibrational content of acoustic signals in order to provide a more reliable description of their features (e.g., amplitude, frequency bandwidth). Starting from the description of the structure and working principles of MEMS, we provide a review of their emerging applications in the healthcare field, discussing the advantages and limitations of each framework. Finally, we deliver a discussion on the lessons learned from the literature, and the open questions and challenges in the field that the scientific community must address in the near future.

SPRSound: Open-Source SJTU Paediatric Respiratory Sound Database

It has proved that the auscultation of respiratory sound has advantage in early respiratory diagnosis. Various methods have been raised to perform automatic respiratory sound analysis to reduce subjective diagnosis and physicians' workload. However, these methods highly rely on the quality of respiratory sound database. In this work, we have developed the first open-access paediatric respiratory sound database, SPRSound. The database consists of 2,683 records and 9,089 respiratory sound events from 292 participants. Accurate label is important to achieve a good prediction for adventitious respiratory sound classification problem. A custom-made sound label annotation software (SoundAnn) has been developed to perform sound editing, sound annotation, and quality assurance evaluation. A team of 11 experienced paediatric physicians is involved in the entire process to establish golden standard reference for the dataset. To verify the robustness and accuracy of the classification model, we have investigated the effects of different feature extraction methods and machine learning classifiers on the classification performance of our dataset. As such, we have achieved a score of 75.22%, 61.57%, 56.71%, and 37.84% for the four different classification challenges at the event level and record level.

A Progressively Expanded Database for Automated Lung Sound Analysis: An Update

We previously established an open-access lung sound database, HF_Lung_V1, and developed deep learning models for inhalation, exhalation, continuous adventitious sound (CAS), and discontinuous adventitious sound (DAS) detection. The amount of data used for training contributes to model accuracy. In this study, we collected larger quantities of data to further improve model performance and explored issues of noisy labels and overlapping sounds. HF_Lung_V1 was expanded to HF_Lung_V2 with a 1.43× increase in the number of audio files. Convolutional neural network–bidirectional gated recurrent unit network models were trained separately using the HF_Lung_V1 (V1_Train) and HF_Lung_V2 (V2_Train) training sets. These were tested using the HF_Lung_V1 (V1_Test) and HF_Lung_V2 (V2_Test) test sets, respectively. Segment and event detection performance was evaluated. Label quality was assessed. Overlap ratios were computed between inhalation, exhalation, CAS, and DAS labels. The model trained using V2_Train exhibited improved performance in inhalation, exhalation, CAS, and DAS detection on both V1_Test and V2_Test. Poor CAS detection was attributed to the quality of CAS labels. DAS detection was strongly influenced by the overlapping of DAS with inhalation and exhalation. In conclusion, collecting greater quantities of lung sound data is vital for developing more accurate lung sound analysis models.

AI Based Diagnosis of Pneumonia

Pneumonia is a lung infection caused by bacteria, viruses and fungi. In this infection, the air sac (alveoli) of the lungs gets inflamed and breathing becomes difficult which causes mild to severe illness among people. They are diagnosed by performing chest X-ray, blood test, pulse oximetry. Pneumonia can also be identified using lung sounds that are recorded in the digital stethoscope. In this proposed work, a software is developed to diagnose pneumonia from the lung sound using gradient boosting algorithm. Lung sounds give enough symptoms for pneumonia identification. Lung sounds are recorded by doctors using Electronic Stethoscope. The recorded lung sounds are processed using audacity software. This software separates the required sound from unwanted noises. The healthy individual's audio files are labelled as 0 and the pneumonia patient's audio files are labelled as 1 for training the algorithm. During diagnosis study and the performance evaluation with various machine learning algorithms like support vector machine and k-nearest neighbours (KNN) algorithms, it was observed that the gradient boosting algorithm exhibits good identification property with 97 percent accuracy. This proposed method also reveals excellent diagnoses of pneumonia over other artificial intelligence and deep learning techniques. This method can also be used to predict Covid affected lungs sounds.

The Effect of a Child Model on Breath-Sounds Examination Skills and Satisfaction on Nursing Students

One of nursing students’ auscultation critical skills is listening to a child’s breathing sounds. Previously, learning this skill required a SimBaby, which was insufficient, causing nursing students to lack proficiency. Therefore, a CHIld Model (CHIM), an innovation emulating breathing sounds, has been invented based on Gagné’s learning theory to solve this insufficiency. This article reports on the CHIM invention, consisting of hardware, software, and programming, and its effect on nursing students’ breath-sounds examination skills and satisfaction. First, the CHIM was assessed for quality and satisfaction by experts. The results were good in quality and had the highest satisfaction for application in actual use. Second, the CHIM was assessed for auscultation skills and satisfaction among nursing students. Forty-four junior nursing students participated. Next, they were randomly divided into experimental and control groups. Then, both were taught the same about respiratory problems with the SimBaby, except the experimental group had training with the CHIM. After that, both groups’ auscultation skills and satisfaction in the experimental group were examined. Finally, the statistical analysis showed that after the intervention was applied, learning with the CHIM was better than without, with the highest satisfaction level. As intended, the CHIM can help effectively enhance students’ learning and proficiency.

A Neural Network-Based Method for Respiratory Sound Analysis and Lung Disease Detection

Background: Respiratory sound analysis represents a research topic of growing interest in recent times. In fact, in this area, there is the potential to automatically infer the abnormalities in the preliminary stages of a lung dysfunction. Methods: In this paper, we propose a method to analyse respiratory sounds in an automatic way. The aim is to show the effectiveness of machine learning techniques in respiratory sound analysis. A feature vector is gathered directly from breath audio and, thus, by exploiting supervised machine learning techniques, we detect if the feature vector is related to a patient affected by a lung disease. Moreover, the proposed method is able to characterise the lung disease in asthma, bronchiectasis, bronchiolitis, chronic obstructive pulmonary disease, pneumonia, and lower or upper respiratory tract infection. Results: A retrospective experimental analysis on 126 patients with 920 recording sessions showed the effectiveness of the proposed method. Conclusion: The experimental analysis demonstrated that it is possible to detect lung disease by exploiting machine learning techniques. We considered several supervised machine learning algorithms, obtaining the most interesting performance with the neural network model, with an F-Measure of 0.983 in lung disease detection and equal to 0.923 in lung disease characterisation, increasing the state-of-the-art performance.

Body Acoustics for the Non-Invasive Diagnosis of Medical Conditions

In the past few decades, many non-invasive monitoring methods have been developed based on body acoustics to investigate a wide range of medical conditions, including cardiovascular diseases, respiratory problems, nervous system disorders, and gastrointestinal tract diseases. Recent advances in sensing technologies and computational resources have given a further boost to the interest in the development of acoustic-based diagnostic solutions. In these methods, the acoustic signals are usually recorded by acoustic sensors, such as microphones and accelerometers, and are analyzed using various signal processing, machine learning, and computational methods. This paper reviews the advances in these areas to shed light on the state-of-the-art, evaluate the major challenges, and discuss future directions. This review suggests that rigorous data analysis and physiological understandings can eventually convert these acoustic-based research investigations into novel health monitoring and point-of-care solutions.

The coming era of a new auscultation system for analyzing respiratory sounds

Auscultation with stethoscope has been an essential tool for diagnosing the patients with respiratory disease. Although auscultation is non-invasive, rapid, and inexpensive, it has intrinsic limitations such as inter-listener variability and subjectivity, and the examination must be performed face-to-face. Conventional stethoscope could not record the respiratory sounds, so it was impossible to share the sounds. Recent innovative digital stethoscopes have overcome the limitations and enabled clinicians to store and share the sounds for education and discussion. In particular, the recordable stethoscope made it possible to analyze breathing sounds using artificial intelligence, especially based on neural network. Deep learning-based analysis with an automatic feature extractor and convoluted neural network classifier has been applied for the accurate analysis of respiratory sounds. In addition, the current advances in battery technology, embedded processors with low power consumption, and integrated sensors make possible the development of wearable and wireless stethoscopes, which can help to examine patients living in areas of a shortage of doctors or those who need isolation. There are still challenges to overcome, such as the analysis of complex and mixed respiratory sounds and noise filtering, but continuous research and technological development will facilitate the transition to a new era of a wearable and smart stethoscope.

Distance-Based Detection of Cough, Wheeze, and Breath Sounds on Wearable Devices

Smart wearable sensors are essential for continuous health-monitoring applications and detection accuracy of symptoms and energy efficiency of processing algorithms are key challenges for such devices. While several machine-learning-based algorithms for the detection of abnormal breath sounds are reported in literature, they are either too computationally expensive to implement into a wearable device or inaccurate in multi-class detection. In this paper, a kernel-like minimum distance classifier (K-MDC) for acoustic signal processing in wearable devices was proposed. The proposed algorithm was tested with data acquired from open-source databases, participants, and hospitals. It was observed that the proposed K-MDC classifier achieves accurate detection in up to 91.23% of cases, and it reaches various detection accuracies with a fewer number of features compared with other classifiers. The proposed algorithm's low computational complexity and classification effectiveness translate to great potential for implementation in health-monitoring wearable devices.

A Wearable Multimodal Sensing System for Tracking Changes in Pulmonary Fluid Status, Lung Sounds, and Respiratory Markers

Heart failure (HF) exacerbations, characterized by pulmonary congestion and breathlessness, require frequent hospitalizations, often resulting in poor outcomes. Current methods for tracking lung fluid and respiratory distress are unable to produce continuous, holistic measures of cardiopulmonary health. We present a multimodal sensing system that captures bioimpedance spectroscopy (BIS), multi-channel lung sounds from four contact microphones, multi-frequency impedance pneumography (IP), temperature, and kinematics to track changes in cardiopulmonary status. We first validated the system on healthy subjects (n = 10) and then conducted a feasibility study on patients (n = 14) with HF in clinical settings. Three measurements were taken throughout the course of hospitalization, and parameters relevant to lung fluid status—the ratio of the resistances at 5 kHz to those at 150 kHz (K)—and respiratory timings (e.g., respiratory rate) were extracted. We found a statistically significant increase in K (p < 0.05) from admission to discharge and observed respiratory timings in physiologically plausible ranges. The IP-derived respiratory signals and lung sounds were sensitive enough to detect abnormal respiratory patterns (Cheyne–Stokes) and inspiratory crackles from patient recordings, respectively. We demonstrated that the proposed system is suitable for detecting changes in pulmonary fluid status and capturing high-quality respiratory signals and lung sounds in a clinical setting.

Interrater reliability of spectrogram for detecting wheezing in children

BACKGROUND

Auscultation is an easy way to evaluate and diagnose patients with lung conditions but has the shortcoming of being subjective. Using the spectrogram, it is possible to visualize wheezing. We therefore conducted a study to compare the efficacy of diagnosing wheezing by auscultation versus diagnosing wheezing by spectrogram.

METHODS

This was an investigation of interrater reliability and agreement in which the subject population consisted of children, and the rater population consisted of pediatric pulmonologists. We recorded 55 respiratory sound files from June to November 2019. Three pediatric pulmonologists listened to the respiratory sound files and assessed whether wheezing was present. All respiratory sound files were also converted into spectrograms; the same pulmonologists viewed these and assessed whether wheezing was present. We tested for interrater reliability and agreement between the auscultation results and spectrographic results and investigated the diagnostic reliability of auscultation versus spectrogram.

RESULTS

Agreement among the three raters of our auscultation respiratory recordings was 88% and reliability was good (κ = 0.76, P < 0.001). Agreement among the three raters of our spectrograms was 83% and reliability was good (κ =0.66, P < 0.001). The level of agreement between each rater's spectrographic findings and diagnosed wheezing was 91%, 75%, and 93%, respectively. Reliability was accordingly very good, moderate, and very good (κ = 0.82, 0.49, 0.85, P < 0.001), respectively.

CONCLUSIONS

A spectrogram may be a valuable tool for evaluating wheezing in children. It may also be used to improve a young clinician's ability to accurately diagnose wheezing in the future.

Telemedicine and artificial intelligence to support self-isolation of COVID-19 patients: Recent updates and challenges

Background

Asymptomatic and high-risk COVID-19 patients are advised to self-isolate at home. However, patients may not realize that the condition is deteriorating until too late.

Objective

This study aims to review various artificial intelligence-based telemedicine research during the COVID-19 outbreak and proposes a framework for developing telemedicine powered by artificial intelligence to monitor progression in COVID-19 patients during isolation at home. It also aims to map challenges using artificial intelligence-based telemedicine in the community.

Methods

A systematic review was performed for the related articles published in 2019-2021 and conducted in the PubMed and ScienceDirect database using the keywords "telemedicine," "artificial intelligence," and "COVID-19". The inclusion criteria were full-text articles and original research written in the English language.

Results

Thirteen articles were included in this review to describe the current application of artificial intelligence-based telemedicine during the COVID-19 pandemic. Various current applications have been implemented, such as for early diagnosis and tracing of contact for the users, to monitor symptoms and decision-making treatment, clinical management, and virtual and remote treatment. We also proposed the framework of telemedicine powered by artificial intelligence for support the self-isolation of COVID-19 patients based on the recent update in technology. However, we identified some challenges for using digital health technologies because of the ethical and practical use, the policy and regulation, and device use both for healthcare workers and patients.

Conclusion

Artificial intelligence promises to improve the practice of medicine in various ways. However, practical applications still need to be explored, and medical professionals also need to adapt to these advances for better healthcare delivery to the public.

Respiratory manifestations in the Ehlers-Danlos syndromes

Persons with the Ehlers-Danlos syndromes (EDS) report a wide range of respiratory symptoms, most commonly shortness of breath, exercise limitation, and cough. Also reported are noisy breathing attributed to asthma, difficulty with deep inhalation, and inspiratory thoracic pain. The literature consists of case reports and small cross-sectional and cohort studies. One case-control study estimated twofold to threefold greater respiratory disease burden among persons with EDS as compared to controls. The differential diagnosis for symptoms is broad. Structural alterations include pectus deformities, scoliosis, recurrent rib subluxations, and tracheobronchomalacia, associated with varying degrees of physiologic impairment. Those with vascular EDS have an increased risk of pneumothorax, intrapulmonary bleeding, cysts, and nonmalignant fibrous nodules. Functional aerodigestive manifestations such as inducible laryngeal obstruction may be misdiagnosed as asthma, with gastro-esophageal dysmotility and reflux as common contributing factors. Inflammatory manifestations include costochondritis, bronchiectasis, and localized respiratory allergic and nonallergic mast cell activation. Cranio-cervical instability can dysregulate respiratory control pathways. There is a need for careful phenotyping using standardized clinical tools and patient-reported outcomes and continuing collaboration with aerodigestive specialists including otolaryngologists and gastroenterologists. Also needed is further evaluation of respiratory symptoms in persons with hypermobility spectrum disorders. Personalized monitoring strategies are invaluable for interpretation and long-term management of respiratory symptoms.