【摘要】 充血性心力衰竭是一种常见的致命性临床综合症,本文针对心力衰竭自动检测提出一种基于长短时记忆网络和深度残差神经网络相结合的深度学习网络架构。基于无偏见测试方法,本文提出的方法在权威开放式连续心率数据库PhysioNet上的准确度为99.67%(数据长度为500),98.84%(数据长度为1000)及96.63%(数据长度为2000),这说明该网络模型能够很好地对连续心率的高维特征进行提取,提高分类模型准确度。本文提出的端到端检测模型能够帮助临床医生通过对短期心率的评估来检测心力衰竭,具有十分重要的临床价值和社会意义。更多还原

【Abstract】 Congestive heart failure(CHF) refers to the inability of the heart to pump sufficiently to maintain blood flow to meet the body’s needs, and it is a common, costly and potentially fatal condition. In this paper, a deep learning network architecture based on combination of long short-term memory network and residualneural network is proposed for automatic detection of heart failure. Based on open source database, the proposed method achieved 99.67%, 98.84% and 96.63% accuracy using 500, 1000 and 2000 heartbeats, respectively. The results show that the proposed model can extract the high-dimensional features of continuous heart rate and improve the accuracy of classification model. Our end-to-end system can help clinicians to detect CHF using short-term assessment of the heartbeat, which has very important clinical value and social significance.更多还原