亲爱的研友该休息了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

A novel approach for atrial fibrillation-related obstructive sleep apnea detection using enhanced single-lead electrocardiogram features with customized deep learning algorithm

阻塞性睡眠呼吸暂停 心房颤动 睡眠呼吸暂停 心脏病学 铅(地质) 医学 呼吸暂停 内科学 计算机科学 人工智能 地貌学 地质学
作者
Febryan Setiawan,Cheng-Yu Lin,Che‐Wei Lin
出处
期刊:Sleep [Oxford University Press]
卷期号:49 (2)
标识
DOI:10.1093/sleep/zsaf226
摘要

STUDY OBJECTIVES: Atrial fibrillation (AF) and obstructive sleep apnea (OSA) are interrelated conditions that substantially increase the risk of cardiovascular complications. However, concurrent detection of these conditions remains a critical unmet need in clinical practice. Current home sleep apnea test devices often fail to detect arrhythmias essential for diagnosing OSA-associated AF due to limited electrocardiogram (ECG) monitoring capabilities, and their integration with continuous positive airway pressure data for treatment optimization remains underutilized. METHODS: This study introduces SHHDeepNet, an advanced deep learning-based framework designed for the detection of OSA in patients with AF, leveraging enhanced features extracted from single-lead ECG signals. The ECG signals were preprocessed and refined using reconstruction independent component analysis, which isolates statistically independent features for improved data representation. These features were subsequently classified using the customized SHHDeepNet architecture. SHHDeepNet utilizes advanced signal processing and deep learning techniques to enhance ECG-based detection of AF-associated OSA. RESULTS: The framework was validated using overnight ECG recordings from 101 subjects derived from the Sleep Heart Health Study Visit 1 database, encompassing 36 prevalent AF cases, 25 incident AF cases, and 40 OSA cases. Detection performance was evaluated through binary classification (AF AH vs. AF non-AH) and multi-class classification (AF AH, AF non-AH, non-AF AH, and non-AF non-AH). During fivefold cross-validation (fivefold-CV), the framework achieved a binary classification accuracy of 98.22 per cent, sensitivity of 96.8 per cent, specificity of 99 per cent, and an area under the curve (AUC) of 0.9981. For multi-class classification, fivefold-CV yielded 98.36 per cent accuracy, 97.14 per cent sensitivity, 98.77 per cent specificity, and an AUC of 0.9975. Validation using leave-one-subject-out cross-validation achieved a binary classification accuracy of 86.42 per cent, sensitivity of 79.4 per cent, specificity of 90.2 per cent, and an AUC of 0.9372. For multi-class classification under leave-one-subject-out cross-validation, the average accuracy, sensitivity, and F1-score were 86.7 per cent, 72.6 per cent, and 0.7224 per cent, respectively. External validation was performed on a cohort of 123 subjects from the osteoporotic fractures in men database, comprising 68 cases of prevalent AF and 55 cases of OSA. The proposed method achieved a multi-class classification accuracy of 88.51 per cent, sensitivity of 73.50 per cent, specificity of 91.34 per cent, and an AUC of 0.9363. CONCLUSIONS: These findings underscore the significance of simultaneous detection of AF and OSA, providing a more comprehensive evaluation of cardiovascular health. The proposed SHHDeepNet framework offers a promising tool to support clinical decision-making, enhance management strategies, and improve patient outcomes by mitigating the risks associated with these conditions.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Onebyby完成签到,获得积分10
2秒前
3秒前
梦的光点完成签到,获得积分10
5秒前
Hello的应助被南曦采纳,获得10
7秒前
啊唔发布了新的文献求助10
8秒前
FOD完成签到 ,获得积分10
14秒前
29秒前
王哪跑12发布了新的文献求助10
32秒前
飘逸的静柏完成签到,获得积分10
38秒前
wanci的应助被糊糊涂涂采纳,获得10
40秒前
汉堡包的应助被cfyoung采纳,获得10
55秒前
秋风的应助被cfyoung采纳,获得100
55秒前
Jazz5688的应助被cfyoung采纳,获得10
55秒前
bkagyin的应助被cfyoung采纳,获得10
55秒前
科研通AI6.4的应助被cfyoung采纳,获得10
55秒前
Maestro_S的应助被cfyoung采纳,获得10
55秒前
syvshc的应助被cfyoung采纳,获得10
55秒前
斯文败类的应助被cfyoung采纳,获得10
56秒前
syvshc的应助被cfyoung采纳,获得10
56秒前
CodeCraft的应助被cfyoung采纳,获得10
56秒前
58秒前
小巧的孤丹完成签到,获得积分10
58秒前
丘比特的应助被33ovo采纳,获得10
1分钟前
Chenzr发布了新的文献求助10
1分钟前
33ovo完成签到,获得积分10
1分钟前
1分钟前
子平完成签到 ,获得积分0
1分钟前
33ovo发布了新的文献求助10
1分钟前
1分钟前
拼搏的水桃完成签到,获得积分10
1分钟前
佳佳发布了新的文献求助10
1分钟前
体贴雪萍完成签到,获得积分10
1分钟前
1分钟前
2589发布了新的文献求助10
1分钟前
王哪跑12完成签到,获得积分10
1分钟前
科研通AI6.2的应助被王哪跑12采纳,获得10
1分钟前
威武青寒完成签到,获得积分10
1分钟前
跳跃的绿蓉完成签到,获得积分10
2分钟前
2分钟前
情怀的应助被灵巧雨寒采纳,获得10
2分钟前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8185124
求助须知:如何正确求助?哪些是违规求助? 9574047
关于积分的说明 21834014
捐赠科研通 7782575
什么是DOI,文献DOI怎么找? 3434500
关于科研通互助平台的介绍 2558743
邀请新用户注册赠送积分活动 2481201