دورية أكاديمية
Intelligent Stethoscope System and Diagnosis Platform With Synchronized Heart Sound and Electrocardiogram Signals
| العنوان: | Intelligent Stethoscope System and Diagnosis Platform With Synchronized Heart Sound and Electrocardiogram Signals |
|---|---|
| المؤلفون: | Shuenn-Yuh Lee, Po-Han Su, Yi-Ting Hsieh, Sheng-Hsin Huang, I-Pei Lee, Ju-Yi Chen |
| المصدر: | IEEE Access, Vol 11, Pp 47420-47431 (2023) |
| بيانات النشر: | IEEE, 2023. |
| سنة النشر: | 2023 |
| المجموعة: | LCC:Electrical engineering. Electronics. Nuclear engineering |
| مصطلحات موضوعية: | Bio-signal acquisition, cardiac auscultation, electrocardiogram, heart sound, machine learning, application software, Electrical engineering. Electronics. Nuclear engineering, TK1-9971 |
| الوصف: | This paper proposes an intelligent stethoscope system that synchronously displays the electrocardiogram (ECG) and heart sound. The instrument, which accelerates auscultation, can be used for the diagnosis of valvular heart disease (VHD) for clinical physicians. The whole system with ECG patch and stethoscope includes four parts, namely, an analog front-end circuit for bio-signal acquisition, a heart sound-classifying integrated circuit with convolution neural network (CNN), a user-friendly application that synchronously displays the heart sound and ECG signals, and a cloud server with heart murmur detection algorithm for human study. In this system, three algorithms are used in processing both ECG and heart sound signals. The first algorithm is a synchronized algorithm, which can align heart sound and ECG signals simultaneously. The second algorithm is a heart sound-classifying algorithm that can distinguish the first (S1) and the second (S2) heart sound in heart sound signals for identifying the systolic and diastolic phases. The accuracies of the algorithm applied to normal heart sound and heart murmur are 100% and 96.7%, respectively. The third algorithm is heart murmur identification, which can detect systolic murmur and has a macro f1 score of 92.5%. The three algorithms proposed are beneficial for physicians in the diagnosis of VHD. After the establishment of the whole system, a CNN-based classification algorithm is also implemented with a $0.18 \mu \text{m}$ standard CMOS process for the demonstration of the edge computing. The machine learning techniques are implemented on the chip to accelerate the classification process. |
| نوع الوثيقة: | article |
| وصف الملف: | electronic resource |
| اللغة: | English |
| تدمد: | 2169-3536 67074448 |
| Relation: | https://ieeexplore.ieee.org/document/10122547/; https://doaj.org/toc/2169-3536 |
| DOI: | 10.1109/ACCESS.2023.3275015 |
| URL الوصول: | https://doaj.org/article/504a55b67074448fb63c1711d9ada94b |
| رقم الأكسشن: | edsdoj.504a55b67074448fb63c1711d9ada94b |
| قاعدة البيانات: | Directory of Open Access Journals |
Full Text Finder | تدمد: | 21693536 67074448 |
|---|---|
| DOI: | 10.1109/ACCESS.2023.3275015 |