Longitudinal Digital Phenotyping of Multiple Sclerosis Severity Using Passively Sensed Behaviors and Ecological Momentary Assessments.

Zongqi Xia, Prerna Chikersal, Shruthi Venkatesh, Elizabeth Walker, Anind Dey, Mayank Goel
{"title":"Longitudinal Digital Phenotyping of Multiple Sclerosis Severity Using Passively Sensed Behaviors and Ecological Momentary Assessments.","authors":"Zongqi Xia, Prerna Chikersal, Shruthi Venkatesh, Elizabeth Walker, Anind Dey, Mayank Goel","doi":"10.1101/2024.11.02.24316647","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Longitudinal tracking of multiple sclerosis (MS) symptoms in an individual's own environment may improve self-monitoring and clinical management for people with MS (pwMS).</p><p><strong>Objective: </strong>We present a machine learning approach that enables longitudinal monitoring of clinically relevant patient-reported symptoms for pwMS by harnessing passively collected data from sensors in smartphones and fitness trackers.</p><p><strong>Methods: </strong>We divide the collected data into discrete periods for each patient. For each prediction period, we first extract patient-level behavioral features from the current period (action features) and the previous period (context features). Then, we apply a machine learning (ML) approach based on Support Vector Machine with Radial Bias Function Kernel and AdaBoost to predict the presence of depressive symptoms (every two weeks) and high global MS symptom burden, severe fatigue, and poor sleep quality (every four weeks).</p><p><strong>Results: </strong>Between November 16, 2019, and January 24, 2021, 104 pwMS (84.6% women, 93.3% non-Hispanic White, 44.0±11.8 years mean±SD age) from a clinic-based MS cohort completed 12-weeks of data collection, including a subset of 44 pwMS (88.6% women, 95.5% non-Hispanic White, 45.7±11.2 years) who completed 24-weeks of data collection. In total, we collected approximately 12,500 days of passive sensor and behavioral health data from the participants. Among the best-performing models with the least sensor data requirement, ML algorithm predicts depressive symptoms with an accuracy of 80.6% (35.5% improvement over baseline; F1-score: 0.76), high global MS symptom burden with an accuracy of 77.3% (51.3% improvement over baseline; F1-score: 0.77), severe fatigue with an accuracy of 73.8% (45.0% improvement over baseline; F1-score: 0.74), and poor sleep quality with an accuracy of 72.0% (28.1% improvement over baseline; F1-score: 0.70). Further, sensor data were largely sufficient for predicting symptom severity, while the prediction of depressive symptoms benefited from minimal active patient input in the form of response to two brief questions on the day before the prediction point.</p><p><strong>Conclusions: </strong>Our digital phenotyping approach using passive sensors on smartphones and fitness trackers may help patients with real-world, continuous, self-monitoring of common symptoms in their own environment and assist clinicians with better triage of patient needs for timely interventions in MS (and potentially other chronic neurological disorders).</p>","PeriodicalId":94281,"journal":{"name":"medRxiv : the preprint server for health sciences","volume":" ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11643184/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"medRxiv : the preprint server for health sciences","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1101/2024.11.02.24316647","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Longitudinal tracking of multiple sclerosis (MS) symptoms in an individual's own environment may improve self-monitoring and clinical management for people with MS (pwMS).

Objective: We present a machine learning approach that enables longitudinal monitoring of clinically relevant patient-reported symptoms for pwMS by harnessing passively collected data from sensors in smartphones and fitness trackers.

Methods: We divide the collected data into discrete periods for each patient. For each prediction period, we first extract patient-level behavioral features from the current period (action features) and the previous period (context features). Then, we apply a machine learning (ML) approach based on Support Vector Machine with Radial Bias Function Kernel and AdaBoost to predict the presence of depressive symptoms (every two weeks) and high global MS symptom burden, severe fatigue, and poor sleep quality (every four weeks).

Results: Between November 16, 2019, and January 24, 2021, 104 pwMS (84.6% women, 93.3% non-Hispanic White, 44.0±11.8 years mean±SD age) from a clinic-based MS cohort completed 12-weeks of data collection, including a subset of 44 pwMS (88.6% women, 95.5% non-Hispanic White, 45.7±11.2 years) who completed 24-weeks of data collection. In total, we collected approximately 12,500 days of passive sensor and behavioral health data from the participants. Among the best-performing models with the least sensor data requirement, ML algorithm predicts depressive symptoms with an accuracy of 80.6% (35.5% improvement over baseline; F1-score: 0.76), high global MS symptom burden with an accuracy of 77.3% (51.3% improvement over baseline; F1-score: 0.77), severe fatigue with an accuracy of 73.8% (45.0% improvement over baseline; F1-score: 0.74), and poor sleep quality with an accuracy of 72.0% (28.1% improvement over baseline; F1-score: 0.70). Further, sensor data were largely sufficient for predicting symptom severity, while the prediction of depressive symptoms benefited from minimal active patient input in the form of response to two brief questions on the day before the prediction point.

Conclusions: Our digital phenotyping approach using passive sensors on smartphones and fitness trackers may help patients with real-world, continuous, self-monitoring of common symptoms in their own environment and assist clinicians with better triage of patient needs for timely interventions in MS (and potentially other chronic neurological disorders).

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用被动感知行为和生态学瞬间评估对多发性硬化症严重程度进行纵向数字表型。
背景:纵向追踪多发性硬化症(MS)患者在自身环境中的症状,可以改善多发性硬化症患者的自我监测和临床管理:在个人所处环境中对多发性硬化症(MS)症状进行纵向追踪可改善多发性硬化症患者(pwMS)的自我监测和临床管理:我们提出了一种机器学习方法,通过利用智能手机和健身追踪器传感器被动收集的数据,对多发性硬化症患者临床相关的患者报告症状进行纵向监测:方法:我们将收集到的数据划分为每个患者的离散时段。对于每个预测时段,我们首先从当前时段(动作特征)和上一时段(情境特征)中提取患者级别的行为特征。然后,我们应用一种基于支持向量机与径向偏置函数核和 AdaBoost 的机器学习(ML)方法来预测抑郁症状(每两周一次)和高全球多发性硬化症症状负担、严重疲劳和睡眠质量差(每四周一次)的存在:2019年11月16日至2021年1月24日期间,来自诊所的MS队列的104名患者(84.6%为女性,93.3%为非西班牙裔白人,平均年龄(±SD)为44.0±11.8岁)完成了为期12周的数据收集,其中44名患者(88.6%为女性,95.5%为非西班牙裔白人,平均年龄(±SD)为45.7±11.2岁)完成了为期24周的数据收集。我们总共收集了参与者约 12,500 天的被动传感器和行为健康数据。在对传感器数据要求最低的最佳模型中,ML 算法预测抑郁症状的准确率为 80.6%(比基线提高了 35.5%;F1-分数:0.76),预测多发性硬化症症状负担重的准确率为 77.3%(比基线提高了 51.3%)。3%(比基线改善 51.3%;F1 分数:0.77),严重疲劳的准确率为 73.8%(比基线改善 45.0%;F1 分数:0.74),睡眠质量差的准确率为 72.0%(比基线改善 28.1%;F1 分数:0.70)。此外,传感器数据在很大程度上足以预测症状的严重程度,而抑郁症状的预测则得益于患者在预测点前一天对两个简短问题的回答这一最低限度的主动输入:我们使用智能手机和健身追踪器上的被动传感器进行数字表型分析的方法,可以帮助患者在真实世界中对自身环境中的常见症状进行连续、自我监测,并协助临床医生更好地对患者需求进行分流,以便及时干预多发性硬化症(以及其他潜在的慢性神经系统疾病)。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Peer Education Intervention Reduced Sexually Transmitted Infections Among Male Tajik Labor Migrants Who Inject Drugs: Results of a Cluster-randomized Controlled Trial. LD-informed deep learning for Alzheimer's gene loci detection using WGS data. Uncovering causal gene-tissue pairs and variants: A multivariable TWAS method controlling for infinitesimal effects. Unified Clinical Vocabulary Embeddings for Advancing Precision Medicine. Deep phenotyping obesity using EHR data: Promise, Challenges, and Future Directions.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1