Zhang Yuezhou, Stewart Callum, Ranjan Yatharth, Conde Pauline, Sankesara Heet, Rashid Zulqarnain, Sun Shaoxiong, Dobson Richard J B, Folarin Amos A
Department of Biostatistics & Health Informatics, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom.
Department of Biostatistics & Health Informatics, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom.
J Affect Disord. 2025 Apr 15;375:412-422. doi: 10.1016/j.jad.2025.01.124. Epub 2025 Jan 30.
Digital phenotyping offers a novel and cost-efficient approach for managing depression and anxiety. Previous studies, often limited to small-to-medium or specific populations, may lack generalizability.
We conducted a cross-sectional analysis of data from 10,129 participants recruited from a UK-based general population between June 2020 and August 2022. Participants shared wearable (Fitbit) data and self-reported questionnaires on depression, anxiety, and mood via a study app. We examined correlations between mental health scores and wearable-derived features, demographics, health variables, and mood assessments. Unsupervised clustering was used to identify behavioural patterns associated with depression and anxiety. Furthermore, we employed XGBoost machine learning models to predict depression and anxiety severity and compared the performance using different subsets of features.
We observed significant associations between the severity of depression and anxiety with several factors, including mood, age, gender, BMI, sleep patterns, physical activity, and heart rate. Clustering analysis revealed that participants simultaneously exhibiting lower physical activity levels and higher heart rates reported more severe symptoms. Prediction models incorporating all types of variables achieved the best performance (R = 0.41, MAE = 3.42 for depression; R = 0.31, MAE = 3.50 for anxiety) compared to those using subsets of variables. Several wearable-derived features were observed to have non-linear relationships with depression and anxiety in the prediction models.
Data collection during the COVID-19 pandemic may introduce biases.
This study identified several indicators for depression and anxiety and highlighted the potential of digital phenotyping and machine learning technologies for rapid screening of mental disorders in general populations.
数字表型分析为管理抑郁症和焦虑症提供了一种新颖且经济高效的方法。以往的研究通常局限于中小规模或特定人群，可能缺乏普遍性。
我们对2020年6月至2022年8月期间从英国普通人群中招募的10129名参与者的数据进行了横断面分析。参与者通过一款研究应用程序分享了可穿戴设备（Fitbit）数据以及关于抑郁、焦虑和情绪的自我报告问卷。我们研究了心理健康评分与可穿戴设备衍生特征、人口统计学特征、健康变量和情绪评估之间的相关性。采用无监督聚类来识别与抑郁和焦虑相关的行为模式。此外，我们使用XGBoost机器学习模型来预测抑郁和焦虑的严重程度，并使用不同的特征子集比较了模型性能。
我们观察到抑郁和焦虑的严重程度与几个因素之间存在显著关联，包括情绪、年龄、性别、体重指数、睡眠模式、身体活动和心率。聚类分析显示，同时表现出较低身体活动水平和较高心率的参与者报告的症状更严重。与使用变量子集的模型相比，纳入所有类型变量的预测模型表现最佳（抑郁的R = 0.41，平均绝对误差 = 3.42；焦虑的R = 0.31，平均绝对误差 = 3.50）。在预测模型中，观察到几个可穿戴设备衍生特征与抑郁和焦虑存在非线性关系。
2019冠状病毒病大流行期间的数据收集可能会引入偏差。
本研究确定了几种抑郁和焦虑的指标，并强调了数字表型分析和机器学习技术在普通人群中快速筛查精神障碍的潜力。
Zotero 插件