Automated Respiratory Event Detection Using Deep Neural Networks

多导睡眠图 呼吸暂停 接收机工作特性 呼吸不足 金标准(测试) 计算机科学 人工智能 人工神经网络 睡眠呼吸暂停 公制(单位) 医学 机器学习 统计 模式识别(心理学) 心脏病学 内科学 数学 工程类 运营管理
作者
Thijs E. Nassi,Wolfgang Ganglberger,Haoqi Sun,Abigail A. Bucklin,Siddharth Biswal,Michel J.A.M. van Putten,Robert J. Thomas,M. Brandon Westover
出处
期刊:Cornell University - arXiv 被引量:4
标识
DOI:10.48550/arxiv.2101.04635
摘要

The gold standard to assess respiration during sleep is polysomnography; a technique that is burdensome, expensive (both in analysis time and measurement costs), and difficult to repeat. Automation of respiratory analysis can improve test efficiency and enable accessible implementation opportunities worldwide. Using 9,656 polysomnography recordings from the Massachusetts General Hospital (MGH), we trained a neural network (WaveNet) based on a single respiratory effort belt to detect obstructive apnea, central apnea, hypopnea and respiratory-effort related arousals. Performance evaluation included event-based and recording-based metrics - using an apnea-hypopnea index analysis. The model was further evaluated on a public dataset, the Sleep-Heart-Health-Study-1, containing 8,455 polysomnographic recordings. For binary apnea event detection in the MGH dataset, the neural network obtained an accuracy of 95%, an apnea-hypopnea index $r^2$ of 0.89 and area under the curve for the receiver operating characteristics curve and precision-recall curve of 0.93 and 0.74, respectively. For the multiclass task, we obtained varying performances: 81% of all labeled central apneas were correctly classified, whereas this metric was 46% for obstructive apneas, 29% for respiratory effort related arousals and 16% for hypopneas. The majority of false predictions were misclassifications as another type of respiratory event. Our fully automated method can detect respiratory events and assess the apnea-hypopnea index with sufficient accuracy for clinical utilization. Differentiation of event types is more difficult and may reflect in part the complexity of human respiratory output and some degree of arbitrariness in the clinical thresholds and criteria used during manual annotation.
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
更新
大幅提高文件上传限制,最高150M (2024-4-1)

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
陨落的繁星完成签到,获得积分10
刚刚
huangzsdy完成签到,获得积分10
1秒前
知性的水杯完成签到 ,获得积分10
1秒前
baby的跑男完成签到,获得积分10
1秒前
777发布了新的文献求助10
2秒前
2秒前
LZY完成签到,获得积分10
4秒前
温凊完成签到 ,获得积分10
5秒前
狠毒的小龙虾完成签到,获得积分10
5秒前
Rain完成签到 ,获得积分10
5秒前
菠萝炒蛋加饭完成签到 ,获得积分10
8秒前
娟儿发布了新的文献求助10
9秒前
张曼完成签到,获得积分10
9秒前
seven完成签到,获得积分10
10秒前
Bobby完成签到,获得积分10
10秒前
Zero完成签到,获得积分10
11秒前
joy完成签到,获得积分10
11秒前
Michelle完成签到,获得积分10
11秒前
刘洋完成签到,获得积分10
12秒前
就晚安喽完成签到 ,获得积分10
14秒前
iuhgnor完成签到,获得积分10
14秒前
马小翠完成签到,获得积分10
15秒前
SDY完成签到 ,获得积分10
17秒前
赵某人完成签到,获得积分10
17秒前
ccc完成签到,获得积分10
17秒前
娟儿完成签到,获得积分10
18秒前
KK完成签到,获得积分20
19秒前
SciGPT应助洁净的如风采纳,获得10
21秒前
秋秋儿完成签到,获得积分10
22秒前
wangke完成签到,获得积分10
23秒前
刘雪景完成签到 ,获得积分10
25秒前
25秒前
乐乐应助寒_采纳,获得10
27秒前
31秒前
牙瓜完成签到 ,获得积分10
31秒前
Tip发布了新的文献求助10
32秒前
默默松鼠完成签到 ,获得积分10
32秒前
宁静致远完成签到,获得积分10
32秒前
xianyuerkyt完成签到 ,获得积分10
34秒前
34秒前
高分求助中
Impact of Mitophagy-Related Genes on the Diagnosis and Development of Esophageal Squamous Cell Carcinoma via Single-Cell RNA-seq Analysis and Machine Learning Algorithms 1600
Exploring Mitochondrial Autophagy Dysregulation in Osteosarcoma: Its Implications for Prognosis and Targeted Therapy 1500
LNG地下式貯槽指針(JGA指-107) 1000
LNG地上式貯槽指針 (JGA指 ; 108) 1000
Raising Girls With ADHD: Secrets for Parenting Healthy, Happy Daughters 900
QMS18Ed2 | process management. 2nd ed 600
LNG as a marine fuel—Safety and Operational Guidelines - Bunkering 560
热门求助领域 (近24小时)
化学 医学 材料科学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 物理化学 催化作用 免疫学 细胞生物学 电极
热门帖子
关注 科研通微信公众号,转发送积分 2940708
求助须知:如何正确求助?哪些是违规求助? 2599566
关于积分的说明 6998283
捐赠科研通 2240913
什么是DOI,文献DOI怎么找? 1189693
版权声明 590231
科研通“疑难数据库(出版商)”最低求助积分说明 582402