1
|
Romero-Ante JD, Chicharro-Luna E, Manrique-Córdoba J, Vicente-Samper JM, Gracia-Sánchez A, Sabater-Navarro JM. Validation of a New Ankle Brachial Index Measurement System Using Pulse Wave Velocity. BIOSENSORS 2024; 14:251. [PMID: 38785725 PMCID: PMC11117512 DOI: 10.3390/bios14050251] [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: 03/05/2024] [Revised: 05/10/2024] [Accepted: 05/14/2024] [Indexed: 05/25/2024]
Abstract
Peripheral artery disease (PAD) is a common circulatory disorder characterized by the accumulation of fats, cholesterol, and other substances in the arteries that restrict blood flow to the extremities, especially the legs. The ankle brachial index (ABI) is a highly reliable and valid non-invasive test for diagnosing PAD. However, the traditional method has limitations. These include the time required, the need for Doppler equipment, the training of clinical staff, and patient discomfort. PWV refers to the speed at which an arterial pressure wave propagates along the arteries, and this speed is conditioned by arterial elasticity and stiffness. To address these limitations, we have developed a system that uses electrocardiogram (ECG) and photoplethysmography (PPG) signals to calculate pulse wave velocity (PWV). We propose determining the ABI based on this calculation. Validation was performed on 22 diabetic patients, and the results demonstrate the accuracy of the system, maintaining a margin of ±0.1 compared with the traditional method. This confirms the correlation between PWV and ABI and positions this technique as a promising alternative to overcome some of the limitations of the conventional method.
Collapse
Affiliation(s)
- Juan David Romero-Ante
- Neuroengineering Biomedical Group, Medical Robotics Unit, Institute of Bioengineering, Miguel Hernández University of Elche, 03202 Elche, Spain
| | - Esther Chicharro-Luna
- Department of Behavioural Sciences and Health, Nursing Area, Faculty of Medicine, Miguel Hernández University of Elche, 03550 San Juan de Alicante, Spain
| | - Juliana Manrique-Córdoba
- Neuroengineering Biomedical Group, Medical Robotics Unit, Institute of Bioengineering, Miguel Hernández University of Elche, 03202 Elche, Spain
| | - José María Vicente-Samper
- Neuroengineering Biomedical Group, Medical Robotics Unit, Institute of Bioengineering, Miguel Hernández University of Elche, 03202 Elche, Spain
| | - Alba Gracia-Sánchez
- Department of Behavioural Sciences and Health, Nursing Area, Faculty of Medicine, Miguel Hernández University of Elche, 03550 San Juan de Alicante, Spain
| | - José María Sabater-Navarro
- Neuroengineering Biomedical Group, Medical Robotics Unit, Institute of Bioengineering, Miguel Hernández University of Elche, 03202 Elche, Spain
| |
Collapse
|
2
|
Urrutia R, Espejo D, Evens N, Guerra M, Sühn T, Boese A, Hansen C, Fuentealba P, Illanes A, Poblete V. Clustering Methods for Vibro-Acoustic Sensing Features as a Potential Approach to Tissue Characterisation in Robot-Assisted Interventions. SENSORS (BASEL, SWITZERLAND) 2023; 23:9297. [PMID: 38067671 PMCID: PMC10708300 DOI: 10.3390/s23239297] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/06/2023] [Revised: 11/06/2023] [Accepted: 11/11/2023] [Indexed: 12/18/2023]
Abstract
This article provides a comprehensive analysis of the feature extraction methods applied to vibro-acoustic signals (VA signals) in the context of robot-assisted interventions. The primary objective is to extract valuable information from these signals to understand tissue behaviour better and build upon prior research. This study is divided into three key stages: feature extraction using the Cepstrum Transform (CT), Mel-Frequency Cepstral Coefficients (MFCCs), and Fast Chirplet Transform (FCT); dimensionality reduction employing techniques such as Principal Component Analysis (PCA), t-Distributed Stochastic Neighbour Embedding (t-SNE), and Uniform Manifold Approximation and Projection (UMAP); and, finally, classification using a nearest neighbours classifier. The results demonstrate that using feature extraction techniques, especially the combination of CT and MFCC with dimensionality reduction algorithms, yields highly efficient outcomes. The classification metrics (Accuracy, Recall, and F1-score) approach 99%, and the clustering metric is 0.61. The performance of the CT-UMAP combination stands out in the evaluation metrics.
Collapse
Affiliation(s)
- Robin Urrutia
- Instituto de Acústica, Facultad de Ciencias de la Ingeniería, Universidad Austral de Chile, Valdivia 5111187, Chile; (R.U.); (V.P.)
- Audio Mining Laboratory (AuMiLab), Instituto de Acústica, Universidad Austral de Chile, Valdivia 5111187, Chile;
| | - Diego Espejo
- Audio Mining Laboratory (AuMiLab), Instituto de Acústica, Universidad Austral de Chile, Valdivia 5111187, Chile;
| | - Natalia Evens
- Instituto de Anatomia, Histologia y Patologia, Facultad de Medicina, Universidad Austral de Chile, Valdivia 5111187, Chile; (N.E.); (M.G.)
| | - Montserrat Guerra
- Instituto de Anatomia, Histologia y Patologia, Facultad de Medicina, Universidad Austral de Chile, Valdivia 5111187, Chile; (N.E.); (M.G.)
| | - Thomas Sühn
- Department of Orthopaedic Surgery, Otto-von-Guericke University Magdeburg, 39120 Magdeburg, Germany;
- SURAG Medical GmbH, 39118 Magdeburg, Germany;
| | - Axel Boese
- INKA Innovation Laboratory for Image Guided Therapy, Otto-von-Guericke University Magdeburg, 39120 Magdeburg, Germany
| | - Christian Hansen
- Research Campus STIMULATE, Otto-von-Guericke University Magdeburg, 39106 Magdeburg, Germany;
| | - Patricio Fuentealba
- Instituto de Electricidad y Electrónica, Facultad de Ciencias de la Ingeniería, Universidad Austral de Chile, Valdivia 5111187, Chile;
| | | | - Victor Poblete
- Instituto de Acústica, Facultad de Ciencias de la Ingeniería, Universidad Austral de Chile, Valdivia 5111187, Chile; (R.U.); (V.P.)
- Audio Mining Laboratory (AuMiLab), Instituto de Acústica, Universidad Austral de Chile, Valdivia 5111187, Chile;
| |
Collapse
|
3
|
Park J, Lee K, Park N, You SC, Ko J. Self-Attention LSTM-FCN model for arrhythmia classification and uncertainty assessment. Artif Intell Med 2023; 142:102570. [PMID: 37316094 DOI: 10.1016/j.artmed.2023.102570] [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: 09/20/2022] [Revised: 04/09/2023] [Accepted: 04/27/2023] [Indexed: 06/16/2023]
Abstract
This paper presents ArrhyMon, a self-attention-based LSTM-FCN model for arrhythmia classification from ECG signal inputs. ArrhyMon targets to detect and classify six different types of arrhythmia apart from normal ECG patterns. To the best of our knowledge, ArrhyMon is the first end-to-end classification model that successfully targets the classification of six detailed arrhythmia types and compared to previous work does not require additional preprocessing and/or feature extraction operations separate from the classification model. ArrhyMon's deep learning model is designed to capture and exploit both global and local features embedded in ECG sequences by integrating fully convolutional network (FCN) layers and a self-attention-based long and short-term memory (LSTM) architecture. Moreover, to enhance its practicality, ArrhyMon incorporates a deep ensemble-based uncertainty model that generates a confidence-level measure for each classification result. We evaluate ArrhyMon's effectiveness using three publicly available arrhythmia datasets (i.e., MIT-BIH, Physionet Cardiology Challenge 2017 and 2020/2021) to show that ArrhyMon achieves state-of-the-art classification performance (average accuracy 99.63%), and that confidence measures show close correlation with subjective diagnosis made from practitioners.
Collapse
Affiliation(s)
- JaeYeon Park
- School of Integrated Technology, College of Computing, Yonsei University, 50 Yonsei-ro, Seodaemun-gu, Seoul, 03722, Republic of Korea
| | - Kichang Lee
- School of Integrated Technology, College of Computing, Yonsei University, 50 Yonsei-ro, Seodaemun-gu, Seoul, 03722, Republic of Korea
| | - Noseong Park
- Department of Artificial Intelligence, College of Computing, Yonsei University, 50 Yonsei-ro, Seodaemun-gu, Seoul, 03722, Republic of Korea
| | - Seng Chan You
- Department of Biomedical Systems Informatics, College of Medicine, Yonsei University, 50-1 Yonsei-ro, Seodaemun-gu, Seoul, 03722, Republic of Korea
| | - JeongGil Ko
- School of Integrated Technology, College of Computing, Yonsei University, 50 Yonsei-ro, Seodaemun-gu, Seoul, 03722, Republic of Korea; Department of Biomedical Systems Informatics, College of Medicine, Yonsei University, 50-1 Yonsei-ro, Seodaemun-gu, Seoul, 03722, Republic of Korea.
| |
Collapse
|
4
|
Gronthy UU, Biswas U, Tapu S, Samad MA, Nahid AA. A Bibliometric Analysis on Arrhythmia Detection and Classification from 2005 to 2022. Diagnostics (Basel) 2023; 13:diagnostics13101732. [PMID: 37238216 DOI: 10.3390/diagnostics13101732] [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: 04/05/2023] [Revised: 04/28/2023] [Accepted: 05/11/2023] [Indexed: 05/28/2023] Open
Abstract
Bibliometric analysis is a widely used technique for analyzing large quantities of academic literature and evaluating its impact in a particular academic field. In this paper bibliometric analysis has been used to analyze the academic research on arrhythmia detection and classification from 2005 to 2022. We have followed PRISMA 2020 framework to identify, filter and select the relevant papers. This study has used the Web of Science database to find related publications on arrhythmia detection and classification. "Arrhythmia detection", "arrhythmia classification" and "arrhythmia detection and classification" are three keywords for gathering the relevant articles. 238 publications in total were selected for this research. In this study, two different bibliometric techniques, "performance analysis" and "science mapping", were applied. Different bibliometric parameters such as publication analysis, trend analysis, citation analysis, and networking analysis have been used to evaluate the performance of these articles. According to this analysis, the three countries with the highest number of publications and citations are China, the USA, and India in terms of arrhythmia detection and classification. The three most significant researchers in this field are those named U. R. Acharya, S. Dogan, and P. Plawiak. Machine learning, ECG, and deep learning are the three most frequently used keywords. A further finding of the study indicates that the popular topics for arrhythmia identification are machine learning, ECG, and atrial fibrillation. This research provides insight into the origins, current status, and future direction of arrhythmia detection research.
Collapse
Affiliation(s)
- Ummay Umama Gronthy
- Electronics and Communication Engineering Discipline, Khulna University, Khulna 9208, Bangladesh
| | - Uzzal Biswas
- Electronics and Communication Engineering Discipline, Khulna University, Khulna 9208, Bangladesh
| | - Salauddin Tapu
- Electronics and Communication Engineering Discipline, Khulna University, Khulna 9208, Bangladesh
| | - Md Abdus Samad
- Department of Information and Communication Engineering, Yeungnam University, Gyeongsan-si 38541, Republic of Korea
| | - Abdullah-Al Nahid
- Electronics and Communication Engineering Discipline, Khulna University, Khulna 9208, Bangladesh
| |
Collapse
|
5
|
Liu Z, Chen Y, Zhang Y, Ran S, Cheng C, Yang G. Diagnosis of arrhythmias with few abnormal ECG samples using metric-based meta learning. Comput Biol Med 2023; 153:106465. [PMID: 36610213 DOI: 10.1016/j.compbiomed.2022.106465] [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: 09/16/2022] [Revised: 12/05/2022] [Accepted: 12/19/2022] [Indexed: 12/29/2022]
Abstract
A major challenge in artificial intelligence based ECG diagnosis lies that it is difficult to obtain sufficient annotated training samples for each rhythm type, especially for rare diseases, which makes many approaches fail to achieve the desired performance with limited ECG records. In this paper, we propose a Meta Siamese Network (MSN) based on metric learning to achieve high accuracy for automatic ECG arrhythmias diagnosis with limited ECG records. First, the ECG signals from three different ECG datasets are preprocessed through resampling, wavelet denoising, R-wave localization, heartbeat segmentation and Z-score normalization. Then, an ECG dataset with limited records is constructed to verify the performance of the proposed model and explore variation of model performance with the sample size. Second, a metric-based meta-learning framework is proposed to address the challenge of few-shot learning for automatic ECG diagnosis of cardiac arrhythmia, and siamese network is employed to achieve arrhythmia diagnosis based on similarity metric. Finally, the N-way K-shot meta-testing strategy is proposed based on the siamese network with double inputs, and the experimental results demonstrate that the proposed strategy can effectively improve the robustness of the proposed model.
Collapse
Affiliation(s)
- Zhenxing Liu
- School of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, China; Engineering Research Center for Metallurgical Automation and Measurement Technology of Ministry of Education, Wuhan, 430081, China
| | - Yujie Chen
- School of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, China; Engineering Research Center for Metallurgical Automation and Measurement Technology of Ministry of Education, Wuhan, 430081, China
| | - Yong Zhang
- School of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, China; Engineering Research Center for Metallurgical Automation and Measurement Technology of Ministry of Education, Wuhan, 430081, China.
| | - Shaolin Ran
- School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China.
| | - Cheng Cheng
- School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China
| | - Guili Yang
- Hospital of WUST, Wuhan University of Science and Technology, Wuhan 430081, China.
| |
Collapse
|
6
|
Wang M, Rahardja S, Fränti P, Rahardja S. Single-lead ECG recordings modeling for end-to-end recognition of atrial fibrillation with dual-path RNN. Biomed Signal Process Control 2023. [DOI: 10.1016/j.bspc.2022.104067] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/14/2022]
|
7
|
A novel proposed CNN-SVM architecture for ECG scalograms classification. Soft comput 2022; 27:4639-4658. [PMID: 36536664 PMCID: PMC9753894 DOI: 10.1007/s00500-022-07729-x] [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] [Accepted: 12/03/2022] [Indexed: 12/23/2022]
Abstract
Nowadays, the number of sudden deaths due to heart disease is increasing with the coronavirus pandemic. Therefore, automatic classification of electrocardiogram (ECG) signals is crucial for diagnosis and treatment. Thanks to deep learning algorithms, classification can be performed without manual feature extraction. In this study, we propose a novel convolutional neural networks (CNN) architecture to detect ECG types. In addition, the proposed CNN can automatically extract features from images. Here, we classify a real ECG dataset using our proposed CNN which includes 34 layers. While this dataset is one-dimensional signals, these are transformed into images (scalograms) using continuous wavelet transform (CWT). In addition, the proposed CNN is compared to known architectures: AlexNet and SqueezeNet for classifying ECG images, and we find it more effective than others. This study, which not only performed CWT but also implemented short-time Fourier transform, examines the success in recognizing ECG types for the proposed CNN. Besides, different split methods: training and testing, and cross-validation are applied in this study. Eventually, CWT and cross-validation are the best pre-processing and split methods for the proposed CNN, respectively. Although the results are quite good, we benefit from support vector machines (SVM) to obtain the best algorithm and for detecting ECG types. Essentially, the main aim of the study increases classification results. In this way, the proposed CNN is utilized as deep feature extractor and combined with SVM. As a conclusion of this study, we achieve the highest accuracy of 99.21% from the proposed CNN-SVM when using CWT. Therefore, we can express that this framework can be used as an aid to clinicians for ECG-type identification.
Collapse
|
8
|
Wu H, Patel KHK, Li X, Zhang B, Galazis C, Bajaj N, Sau A, Shi X, Sun L, Tao Y, Al-Qaysi H, Tarusan L, Yasmin N, Grewal N, Kapoor G, Waks JW, Kramer DB, Peters NS, Ng FS. A fully-automated paper ECG digitisation algorithm using deep learning. Sci Rep 2022; 12:20963. [PMID: 36471089 PMCID: PMC9722713 DOI: 10.1038/s41598-022-25284-1] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2022] [Accepted: 11/28/2022] [Indexed: 12/12/2022] Open
Abstract
There is increasing focus on applying deep learning methods to electrocardiograms (ECGs), with recent studies showing that neural networks (NNs) can predict future heart failure or atrial fibrillation from the ECG alone. However, large numbers of ECGs are needed to train NNs, and many ECGs are currently only in paper format, which are not suitable for NN training. We developed a fully-automated online ECG digitisation tool to convert scanned paper ECGs into digital signals. Using automated horizontal and vertical anchor point detection, the algorithm automatically segments the ECG image into separate images for the 12 leads and a dynamical morphological algorithm is then applied to extract the signal of interest. We then validated the performance of the algorithm on 515 digital ECGs, of which 45 were printed, scanned and redigitised. The automated digitisation tool achieved 99.0% correlation between the digitised signals and the ground truth ECG (n = 515 standard 3-by-4 ECGs) after excluding ECGs with overlap of lead signals. Without exclusion, the performance of average correlation was from 90 to 97% across the leads on all 3-by-4 ECGs. There was a 97% correlation for 12-by-1 and 3-by-1 ECG formats after excluding ECGs with overlap of lead signals. Without exclusion, the average correlation of some leads in 12-by-1 ECGs was 60-70% and the average correlation of 3-by-1 ECGs achieved 80-90%. ECGs that were printed, scanned, and redigitised, our tool achieved 96% correlation with the original signals. We have developed and validated a fully-automated, user-friendly, online ECG digitisation tool. Unlike other available tools, this does not require any manual segmentation of ECG signals. Our tool can facilitate the rapid and automated digitisation of large repositories of paper ECGs to allow them to be used for deep learning projects.
Collapse
Affiliation(s)
- Huiyi Wu
- Imperial College London, National Heart & Lung Institute, London, W12 0NN, UK
| | | | - Xinyang Li
- Imperial College London, National Heart & Lung Institute, London, W12 0NN, UK
| | - Bowen Zhang
- National University of Singapore, Singapore, Singapore
| | | | - Nikesh Bajaj
- Imperial College London, National Heart & Lung Institute, London, W12 0NN, UK
| | - Arunashis Sau
- Imperial College London, National Heart & Lung Institute, London, W12 0NN, UK
- Department of Cardiology, Imperial College Healthcare NHS Trust, London, UK
| | - Xili Shi
- Imperial College London, National Heart & Lung Institute, London, W12 0NN, UK
| | - Lin Sun
- Imperial College London, National Heart & Lung Institute, London, W12 0NN, UK
| | | | - Harith Al-Qaysi
- Department of Cardiology, Imperial College Healthcare NHS Trust, London, UK
| | - Lawrence Tarusan
- Department of Cardiology, Imperial College Healthcare NHS Trust, London, UK
| | - Najira Yasmin
- Department of Cardiology, Imperial College Healthcare NHS Trust, London, UK
| | - Natasha Grewal
- Department of Cardiology, Imperial College Healthcare NHS Trust, London, UK
| | - Gaurika Kapoor
- Department of Cardiology, Imperial College Healthcare NHS Trust, London, UK
| | - Jonathan W Waks
- Harvard-Thorndike Electrophysiology Institute, Beth Israel Deaconess Medical Centre, Harvard Medical School, Boston, MA, USA
| | - Daniel B Kramer
- Imperial College London, National Heart & Lung Institute, London, W12 0NN, UK
- Harvard-Thorndike Electrophysiology Institute, Beth Israel Deaconess Medical Centre, Harvard Medical School, Boston, MA, USA
| | - Nicholas S Peters
- Imperial College London, National Heart & Lung Institute, London, W12 0NN, UK
| | - Fu Siong Ng
- Imperial College London, National Heart & Lung Institute, London, W12 0NN, UK.
- Department of Cardiology, Imperial College Healthcare NHS Trust, London, UK.
- Cardiac Electrophysiology, National Heart and Lung Institute, Imperial College London, 4th floor, Imperial Centre for Translational and Experimental Medicine, Hammersmith Campus, Du Cane Road, London, W12 0NN, UK.
| |
Collapse
|
9
|
Hu Q, Wang D, Yang C. PPG-based blood pressure estimation can benefit from scalable multi-scale fusion neural networks and multi-task learning. Biomed Signal Process Control 2022. [DOI: 10.1016/j.bspc.2022.103891] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
|