TY - JOUR
T1 - An AI-assisted All-in-one Integrated Coronary Artery Disease Diagnosis System Using a Portable Heart Sound Sensor with an On-board Executable Lightweight Model
AU - Zhang, Haojie
AU - Tian, Fuze
AU - Tan, Yang
AU - Shen, Lin
AU - Liu, Jingyu
AU - Liu, Jie
AU - Qian, Kun
AU - Han, Yalei
AU - Su, Gong
AU - Hu, Bin
AU - Schuller, Bjorn W.
AU - Yamamoto, Yoshiharu
N1 - Publisher Copyright:
© 2025 IEEE. All rights reserved.
PY - 2025
Y1 - 2025
N2 - Heart sounds play a crucial role in assessing Coronary Artery Disease (CAD). The advancement of Artificial Intelligence (AI) technologies has given rise to Computer Audition (CA)-based methods for CAD detection. However, previous research has focused primarily on analyzing and modeling heart sound data, overlooking practical application scenarios. In this work, we design a pervasive heart sound collection device used for high-quality heart sound data acquisition. Moreover, we introduce an on-board executable lightweight network tailored for the designed portable device, referred to as TYKDModel. Further, heart sound data from 41 CAD patients and 22 non-CAD healthy controls are collected using the developed device. Experimental results show that the TYKDModel exhibits low-computational complexity, with 52.16 K parameters and 5.03 M Floating-Point Operations (FLOPs). When deployed on the board, it requires only 1.10 MB of Random Access Memory (RAM) and 236.27 KB of Read-Only Memory (ROM), and takes around 1.72 seconds to perform a classification. Despite the low computational and spatial complexity, the TYKDModel achieves a notable classification accuracy of 85.2%, specificity of 88.6%, and sensitivity of 82.8% on the board. These results indicate the promising potential of AI-assisted all-in-one integrated system for the diagnosis of heart sound-assisted CAD.
AB - Heart sounds play a crucial role in assessing Coronary Artery Disease (CAD). The advancement of Artificial Intelligence (AI) technologies has given rise to Computer Audition (CA)-based methods for CAD detection. However, previous research has focused primarily on analyzing and modeling heart sound data, overlooking practical application scenarios. In this work, we design a pervasive heart sound collection device used for high-quality heart sound data acquisition. Moreover, we introduce an on-board executable lightweight network tailored for the designed portable device, referred to as TYKDModel. Further, heart sound data from 41 CAD patients and 22 non-CAD healthy controls are collected using the developed device. Experimental results show that the TYKDModel exhibits low-computational complexity, with 52.16 K parameters and 5.03 M Floating-Point Operations (FLOPs). When deployed on the board, it requires only 1.10 MB of Random Access Memory (RAM) and 236.27 KB of Read-Only Memory (ROM), and takes around 1.72 seconds to perform a classification. Despite the low computational and spatial complexity, the TYKDModel achieves a notable classification accuracy of 85.2%, specificity of 88.6%, and sensitivity of 82.8% on the board. These results indicate the promising potential of AI-assisted all-in-one integrated system for the diagnosis of heart sound-assisted CAD.
KW - Artificial Intelligence (AI)-Assisted All-in-one Integrated Diagnosis
KW - Coronary Artery Disease (CAD) Detection
KW - Heart Sound Sensor
KW - On-board Executable Lightweight Model
KW - Portable Diagnostic Device
UR - http://www.scopus.com/inward/record.url?scp=105000160458&partnerID=8YFLogxK
U2 - 10.1109/TMC.2025.3547842
DO - 10.1109/TMC.2025.3547842
M3 - Article
AN - SCOPUS:105000160458
SN - 1536-1233
JO - IEEE Transactions on Mobile Computing
JF - IEEE Transactions on Mobile Computing
ER -