当前位置: X-MOL 学术Sleep Med. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Brief digital sleep questionnaire powered by machine learning prediction models identifies common sleep disorders.
Sleep Medicine ( IF 3.8 ) Pub Date : 2020-03-23 , DOI: 10.1016/j.sleep.2020.03.005
Alan R Schwartz 1 , Mairav Cohen-Zion 2 , Luu V Pham 3 , Amit Gal 4 , Mudiaga Sowho 5 , Francis P Sgambati 3 , Tracy Klopfer 5 , Michelle A Guzman 5 , Erin M Hawks 5 , Tamar Etzioni 6 , Laura Glasner 7 , Eran Druckman 8 , Giora Pillar 6
Affiliation  

Introduction

We developed and validated an abbreviated Digital Sleep Questionnaire (DSQ) to identify common societal sleep disturbances including insomnia, delayed sleep phase syndrome (DSPS), insufficient sleep syndrome (ISS), and risk for obstructive sleep apnea (OSA).

Methods

The DSQ was administered to 3,799 community volunteers, of which 2,113 were eligible and consented to the study. Of those, 247 were interviewed by expert sleep physicians, who diagnosed <2 sleep disorders. Machine Learning (ML) trained and validated separate models for each diagnosis. Regularized linear models generated 15-200 features to optimize diagnostic prediction. Models were trained with five-fold cross-validation (repeated five times), followed by robust validation testing. ElasticNet models were used to classify true positives and negatives; bootstrapping optimized probability thresholds to generate sensitivities, specificities, accuracies, and area under the receiver operating curve (AUC).

Results

Compared to reference subgroups, physician-diagnosed sleep disorders were marked by DSQ evidence of sleeplessness (insomnia, DSPS, OSA), sleep debt (DSPS, ISS), airway obstruction during sleep (OSA), blunted circadian variability in alertness (DSPS), sleepiness (DSPS and ISS), increased alertness (insomnia) and global impairment in sleep-related quality of life (all sleep disorders). ElasticNet models validated each diagnosis with high sensitivity (80 – 83%), acceptable specificity (63 – 69%), high AUC (0.80 – 0.85) and good accuracy (agreement with physician diagnoses, 68 to 73%).

Discussion

A brief DSQ readily engaged and efficiently screened a large population for common sleep disorders. Powered by ML, the DSQ can accurately classify sleep disturbances, demonstrating the potential for improving the sleep, health, productivity and safety of populations.



中文翻译:

由机器学习预测模型提供支持的简短数字睡眠问卷可识别常见的睡眠障碍。

介绍

我们开发并验证了一种简化的数字睡眠问卷 (DSQ),以确定常见的社会睡眠障碍,包括失眠、延迟睡眠阶段综合征 (DSPS)、睡眠不足综合征 (ISS) 和阻塞性睡眠呼吸暂停 (OSA) 的风险。

方法

DSQ 对 3,799 名社区志愿者进行了管理,其中 2,113 人符合条件并同意参与该研究。其中,247 人接受了专家睡眠医师的采访,他们诊断出< 2 种睡眠障碍。机器学习 (ML) 为每个诊断训练和验证单独的模型。正则化线性模型生成 15-200 个特征来优化诊断预测。模型经过五次交叉验证(重复五次)训练,然后进行稳健的验证测试。使用 ElasticNet 模型对真正的正例和负例进行分类;自举优化概率阈值以生成灵敏度、特异性、准确性和接受者操作曲线 (AUC) 下的面积。

结果

与参考亚组相比,医生诊断的睡眠障碍具有 DSQ 失眠证据(失眠、DSPS、OSA)、睡眠欠债(DSPS、ISS)、睡眠期间气道阻塞(OSA)、警觉性昼夜节律变异性迟钝(DSPS)、嗜睡(DSPS 和 ISS)、警觉性增加(失眠)和睡眠相关生活质量的整体损害(所有睡眠障碍)。ElasticNet 模型以高灵敏度 (80 - 83%)、可接受的特异性 (63 - 69%)、高 AUC (0.80 - 0.85) 和良好的准确性(与医生诊断的一致性,68 - 73%)验证了每个诊断。

讨论

一份简短的 DSQ 很容易参与并有效筛查大量人群的常见睡眠障碍。在 ML 的支持下,DSQ 可以准确地对睡眠障碍进行分类,展示了改善人群睡眠、健康、生产力和安全的潜力。

更新日期:2020-03-23
down
wechat
bug