基于持续学习的心脏健康到情绪健康联合分析  

The joint analysis of heart health and mental health based on continual learning

作　　者：高鸿祥 蔡志鹏[1,2] 李建清[1,2,3] 刘澄玉 GAO Hongxiang;CAI Zhipeng;LI Jianqing;LIU Chengyu(School of Instrument Science and Engineering,Southeast University,Nanjing 210096,P.R.China;State Key Laboratory of Bioelectronics,Southeast University,Nanjing 210096,P.R.China;School of Biomedical Engineering and Informatics,Nanjing Medical University,Nanjing 211166,P.R.China)

机构地区：[1]东南大学仪器科学与工程学院,南京210096 [2]东南大学数字医学工程国家重点实验室,南京210096 [3]南京医科大学生物医学工程与信息学院,南京211166

出　　处：《生物医学工程学杂志》2025年第1期1-8,共8页Journal of Biomedical Engineering

基　　金：国家重点研发计划(2023YFC3603600);国家博士后科学基金(2024M750444);江苏省基础研究自然科学基金(BK20241304)。

摘　　要：心血管疾病和心理障碍已成为威胁人类身心健康的两大主要问题。尽管基于心电图信号的研究为解决这些问题提供了重要契机,但在心电特征的理解以及跨任务知识迁移方面,现有方法仍面临性能瓶颈和适用性不足等挑战。为此,本文设计了一种基于残差网络的多分辨率特征编码网络,能够有效提取心电信号的局部形态特征与全局节律特征,增强特征表达能力。此外,提出的基于模型压缩的持续学习方法通过将简单任务中的结构化知识逐步传递到复杂任务,可有效提升下游任务性能。多分辨率学习模型在心电QRS波群检测、心律失常分类和情绪分类等五个数据库上取得了超越或与当前先进算法相当的性能。持续学习方法在跨领域、跨任务和数据增量的场景下都取得了相较于常规训练方法的显著提升,证明了所提出方法对于心电跨任务知识迁移的能力,为心电多任务学习提供了新路径。Cardiovascular diseases and psychological disorders represent two major threats to human physical and mental health.Research on electrocardiogram(ECG)signals offers valuable opportunities to address these issues.However,existing methods are constrained by limitations in understanding ECG features and transferring knowledge across tasks.To address these challenges,this study developed a multi-resolution feature encoding network based on residual networks,which effectively extracted local morphological features and global rhythm features of ECG signals,thereby enhancing feature representation.Furthermore,a model compression-based continual learning method was proposed,enabling the structured transfer of knowledge from simpler tasks to more complex ones,resulting in improved performance in downstream tasks.The multi-resolution learning model demonstrated superior or comparable performance to state-of-the-art algorithms across five datasets,including tasks such as ECG QRS complex detection,arrhythmia classification,and emotion classification.The continual learning method achieved significant improvements over conventional training approaches in cross-domain,cross-task,and incremental data scenarios.These results highlight the potential of the proposed method for effective cross-task knowledge transfer in ECG analysis and offer a new perspective for multi-task learning using ECG signals.

关 键 词：身心健康 心电图信号 多分辨率 持续学习 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] R318[自动化与计算机技术—控制科学与工程]