Digital phenotyping of sleep patterns among heterogenous samples of Latinx adults using unsupervised learning.
Digital phenotyping of sleep patterns among heterogenous samples of Latinx adults using unsupervised learning.
复制标题
DOI：
10.1016/j.sleep.2021.07.023
复制
发表时间：
2021-09
期刊：
影响因子：
4.8
通讯作者：
Bakken S
中科院分区：
文献类型：
--
作者：
Ensari I;Caceres BA;Jackman KB;Suero-Tejeda N;Shechter A;Odlum ML;Bakken S
本研究旨在使用灵活的无监督机器学习技术，基于客观睡眠数据识别拉丁美洲成年人的睡眠障碍亚型（“表型”）。这项研究是对哥伦比亚大学症状自我管理中心的三项横断面研究数据的二次分析。所有研究都集中在睡眠障碍风险增加的拉丁裔成年人的睡眠健康。使用腕戴式加速度计收集总睡眠时间（TST）、卧床时间（TIB）、入睡后觉醒（WASO）、睡眠效率（SE）、觉醒次数（NOA）和夜间觉醒平均时长等数据。使用依赖于多变量广义线性混合模型的混合物的无监督机器学习方法进行睡眠数据的聚类分析。分析样本包括来自118名成年人（年龄19-77岁）的494天数据。基于偏差指数，3簇模型提供了最佳拟合（即，DΔ~ −75和−17分别来自1-和2-到3-聚类模型）和似然比（Pdiff ~ 0.93）。表型1（n=64）与总体充分SE的可能性更大以及SE和WASO的变异性更小相关。表型2（n=11）的特点是更高的NOA，更大的WASO和TIB比其他表型。表型3（n=43）的特征在于SE、上床时间和觉醒时间的更大变异性。强大的数字数据驱动的建模方法可以用于检测来自异质性患者群体的睡眠表型，并对设计用于管理和早期检测睡眠问题的精确睡眠健康策略具有影响。
This study aimed to identify sleep disturbance subtypes (“phenotypes”) among Latinx adults based on objective sleep data using a flexible unsupervised machine learning technique. This study was a secondary analysis of data from three cross-sectional studies of the Precision in Symptom Self-Management Center at Columbia University. All studies focused on sleep health in Latinx adults at increased risk for sleep disturbance. Data on total sleep time (TST), time in bed (TIB), wake after sleep onset (WASO), sleep efficiency (SE), number of awakenings (NOA) and the mean length of nightly awakenings were collected using wrist-mounted accelerometers. Cluster analysis of the sleep data was conducted using an unsupervised machine learning approach that relies on mixtures of multivariate generalized linear mixed models. The analytic sample included 494 days of data from 118 adults (Ages 19–77). A 3-cluster model provided the best fit based on deviance indices (i.e., DΔ~ −75 and −17 from 1- and 2- to 3-cluster models, respectively) and likelihood ratio (Pdiff ~ 0.93). Phenotype 1 (n=64) was associated with greater likelihood of overall adequate SE and less variability in SE and WASO. Phenotype 2 (n=11) was characterized by higher NOAs, and greater WASO and TIB than the other phenotypes. Phenotype 3 (n=43) was characterized by greater variability in SE, bed times and awakening times. Robust digital data-driven modeling approaches can be useful for detecting sleep phenotypes from heterogenous patient populations, and have implications for designing precision sleep health strategies for management and early detection of sleep problems.
登录
查看更多内容
影响因子：
4.8
作者：
Furihata, Ryuji;Kaneita, Yoshitaka;Uchiyama, Makoto
通讯作者：
Uchiyama, Makoto
影响因子：
3.1
作者：
Caceres, Billy A.;Hickey, Kathleen T.
通讯作者：
Hickey, Kathleen T.
影响因子：
4.1
作者：
Caceres, Billy A.;Hickey, Kathleen T.;Hughes, Tonda L.
通讯作者：
Hughes, Tonda L.
无监督学习技术可识别具有不同临床特征的支气管扩张表型
DOI：
10.5588/ijtld.15.0500
发表时间：
2016-03-01
影响因子：
4
作者：
Guan, W-J.;Jiang, M.;Zhong, N-S.
通讯作者：
Zhong, N-S.
影响因子：
--
作者：
Fong S;Deb S;Yang XS;Zhuang Y
通讯作者：
Zhuang Y