Digital phenotyping in bipolar disorder: Using longitudinal Fitbit data and personalized machine learning to predict mood symptomatology.

IF 5.3 2区 医学 Q1 PSYCHIATRY Acta Psychiatrica Scandinavica Pub Date : 2024-10-13 DOI:10.1111/acps.13765
Jessica M Lipschitz, Sidian Lin, Soroush Saghafian, Chelsea K Pike, Katherine E Burdick
{"title":"Digital phenotyping in bipolar disorder: Using longitudinal Fitbit data and personalized machine learning to predict mood symptomatology.","authors":"Jessica M Lipschitz, Sidian Lin, Soroush Saghafian, Chelsea K Pike, Katherine E Burdick","doi":"10.1111/acps.13765","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Effective treatment of bipolar disorder (BD) requires prompt response to mood episodes. Preliminary studies suggest that predictions based on passive sensor data from personal digital devices can accurately detect mood episodes (e.g., between routine care appointments), but studies to date do not use methods designed for broad application. This study evaluated whether a novel, personalized machine learning approach, trained entirely on passive Fitbit data, with limited data filtering could accurately detect mood symptomatology in BD patients.</p><p><strong>Methods: </strong>We analyzed data from 54 adults with BD, who wore Fitbits and completed bi-weekly self-report measures for 9 months. We applied machine learning (ML) models to Fitbit data aggregated over two-week observation windows to detect occurrences of depressive and (hypo)manic symptomatology, which were defined as two-week windows with scores above established clinical cutoffs for the Patient Health Questionnaire-8 (PHQ-8) and Altman Self-Rating Mania Scale (ASRM) respectively.</p><p><strong>Results: </strong>As hypothesized, among several ML algorithms, Binary Mixed Model (BiMM) forest achieved the highest area under the receiver operating curve (ROC-AUC) in the validation process. In the testing set, the ROC-AUC was 86.0% for depression and 85.2% for (hypo)mania. Using optimized thresholds calculated with Youden's J statistic, predictive accuracy was 80.1% for depression (sensitivity of 71.2% and specificity of 85.6%) and 89.1% for (hypo)mania (sensitivity of 80.0% and specificity of 90.1%).</p><p><strong>Conclusion: </strong>We achieved sound performance in detecting mood symptomatology in BD patients using methods designed for broad application. Findings expand upon evidence that Fitbit data can produce accurate mood symptomatology predictions. Additionally, to the best of our knowledge, this represents the first application of BiMM forest for mood symptomatology prediction. Overall, results move the field a step toward personalized algorithms suitable for the full population of patients, rather than only those with high compliance, access to specialized devices, or willingness to share invasive data.</p>","PeriodicalId":108,"journal":{"name":"Acta Psychiatrica Scandinavica","volume":null,"pages":null},"PeriodicalIF":5.3000,"publicationDate":"2024-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Acta Psychiatrica Scandinavica","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1111/acps.13765","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PSYCHIATRY","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Effective treatment of bipolar disorder (BD) requires prompt response to mood episodes. Preliminary studies suggest that predictions based on passive sensor data from personal digital devices can accurately detect mood episodes (e.g., between routine care appointments), but studies to date do not use methods designed for broad application. This study evaluated whether a novel, personalized machine learning approach, trained entirely on passive Fitbit data, with limited data filtering could accurately detect mood symptomatology in BD patients.

Methods: We analyzed data from 54 adults with BD, who wore Fitbits and completed bi-weekly self-report measures for 9 months. We applied machine learning (ML) models to Fitbit data aggregated over two-week observation windows to detect occurrences of depressive and (hypo)manic symptomatology, which were defined as two-week windows with scores above established clinical cutoffs for the Patient Health Questionnaire-8 (PHQ-8) and Altman Self-Rating Mania Scale (ASRM) respectively.

Results: As hypothesized, among several ML algorithms, Binary Mixed Model (BiMM) forest achieved the highest area under the receiver operating curve (ROC-AUC) in the validation process. In the testing set, the ROC-AUC was 86.0% for depression and 85.2% for (hypo)mania. Using optimized thresholds calculated with Youden's J statistic, predictive accuracy was 80.1% for depression (sensitivity of 71.2% and specificity of 85.6%) and 89.1% for (hypo)mania (sensitivity of 80.0% and specificity of 90.1%).

Conclusion: We achieved sound performance in detecting mood symptomatology in BD patients using methods designed for broad application. Findings expand upon evidence that Fitbit data can produce accurate mood symptomatology predictions. Additionally, to the best of our knowledge, this represents the first application of BiMM forest for mood symptomatology prediction. Overall, results move the field a step toward personalized algorithms suitable for the full population of patients, rather than only those with high compliance, access to specialized devices, or willingness to share invasive data.

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
双相情感障碍的数字表型:利用 Fitbit 纵向数据和个性化机器学习预测情绪症状。
背景:双相情感障碍(BD)的有效治疗需要及时应对情绪发作。初步研究表明,基于个人数字设备的被动传感器数据进行预测可以准确检测情绪发作(例如,在常规护理预约之间),但迄今为止的研究并未使用旨在广泛应用的方法。本研究评估了一种新颖的个性化机器学习方法,该方法完全根据 Fitbit 的被动数据进行训练,并进行了有限的数据过滤,能否准确检测出 BD 患者的情绪症状:我们分析了 54 名成年 BD 患者的数据,他们佩戴了 Fitbit 并完成了为期 9 个月的双周自我报告测量。我们将机器学习(ML)模型应用于两周观察窗口汇总的 Fitbit 数据,以检测抑郁症状和(低)躁狂症状的出现,抑郁症状和(低)躁狂症状被定义为两周窗口中患者健康问卷-8(PHQ-8)和 Altman 自评躁狂量表(ASRM)的得分分别高于既定的临床临界值:正如假设的那样,在几种 ML 算法中,二元混合模型(BiMM)森林在验证过程中获得了最高的接收器工作曲线下面积(ROC-AUC)。在测试集中,抑郁症的 ROC-AUC 为 86.0%,(低)躁狂症的 ROC-AUC 为 85.2%。使用尤登 J 统计法计算的优化阈值,抑郁症的预测准确率为 80.1%(灵敏度为 71.2%,特异性为 85.6%),(低)躁狂症的预测准确率为 89.1%(灵敏度为 80.0%,特异性为 90.1%):我们采用设计用于广泛应用的方法,在检测BD患者的情绪症状方面取得了良好的效果。研究结果进一步证明,Fitbit 数据可以准确预测情绪症状。此外,据我们所知,这是 BiMM 森林在情绪症状预测方面的首次应用。总之,研究结果使该领域向适用于所有患者的个性化算法迈进了一步,而不仅仅是那些依从性高、可以使用专用设备或愿意分享侵入性数据的患者。
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
Acta Psychiatrica Scandinavica
Acta Psychiatrica Scandinavica 医学-精神病学
CiteScore
11.20
自引率
3.00%
发文量
135
审稿时长
6-12 weeks
期刊介绍: Acta Psychiatrica Scandinavica acts as an international forum for the dissemination of information advancing the science and practice of psychiatry. In particular we focus on communicating frontline research to clinical psychiatrists and psychiatric researchers. Acta Psychiatrica Scandinavica has traditionally been and remains a journal focusing predominantly on clinical psychiatry, but translational psychiatry is a topic of growing importance to our readers. Therefore, the journal welcomes submission of manuscripts based on both clinical- and more translational (e.g. preclinical and epidemiological) research. When preparing manuscripts based on translational studies for submission to Acta Psychiatrica Scandinavica, the authors should place emphasis on the clinical significance of the research question and the findings. Manuscripts based solely on preclinical research (e.g. animal models) are normally not considered for publication in the Journal.
期刊最新文献
Issue Information Variation of subclinical psychosis as a function of population density across different European settings: Findings from the multi-national EU-GEI study. Risk and timing of postpartum depression in parents of twins compared to parents of singletons. Digital phenotyping in bipolar disorder: Using longitudinal Fitbit data and personalized machine learning to predict mood symptomatology. The risk of diabetes and HbA1c deterioration during antipsychotic drug treatment: A Danish two-cohort study among patients with first-episode schizophrenia.
×
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