Borelli Jessica L, Wang Yuning, Li Frances Haofei, Russo Lyric N, Tironi Marta, Yamashita Ken, Zhou Elayne, Lai Jocelyn, Nguyen Brenda, Azimi Iman, Marcotullio Christopher, Labbaf Sina, Jafarlou Salar, Dutt Nikil, Rahmani Amir
Department of Psychological Science, University of California, Irvine, Irvine, CA, United States.
Department of Computing, University of Turku, Turku, Finland.
JMIR Form Res. 2025 Jun 3;9:e67964. doi: 10.2196/67964.
Depression is the top contributor to global disability. Early detection of depression and depressive symptoms enables timely intervention and reduces their physical and social consequences. Prevalence estimates of depression approach 30% among college students. Passive, device-based sensing further enables detection of depressive symptoms at a low burden to the individual.
We leveraged an ensemble machine learning method (light gradient boosting machine) to detect depressive symptoms entirely through passive sensing.
A diverse sample of undergraduate students (N=28; mean age 19.96, SD 1.23 y; 15/28, 54% women; 13/28, 46% Latine; 10/28, 36% Asian; 4/28, 14% non-Latine White; 11/28, 4% other) participated in an intensive longitudinal study. Participants wore 2 devices (an Oura ring for sleep and physiology data, and a Samsung smartwatch for physiology and movement data) and installed the AWARE software on their mobile devices, which collects passive sensing data such as screen time. Participants were derived from a randomized controlled trial of a positive psychology mobile health intervention. They completed a self-report measure of depressive symptoms administered weekly over a 19- to 22-week period.
The light gradient boosting machine model achieved an F-score of 0.744 and a Cohen κ coefficient of 0.474, indicating moderate agreement between the predicted labels and the ground truth. The most predictive features of depressive symptoms were sleep quality and missed mobile interactions.
Findings suggest that data collected from passive sensing devices may provide real-time, low-cost insight into the detection of depressive symptoms in college students and may present an opportunity for future prevention and perhaps intervention.
抑郁症是导致全球残疾的首要因素。早期发现抑郁症及抑郁症状能够实现及时干预，并减轻其对身体和社会造成的后果。据估计，大学生中抑郁症的患病率接近30%。基于设备的被动式传感进一步能够在个体负担较低的情况下检测出抑郁症状。
我们利用一种集成机器学习方法（轻梯度提升机）完全通过被动传感来检测抑郁症状。
一个多样化的本科生样本（N = 28；平均年龄19.96岁，标准差1.23岁；28人中有15人，即54%为女性；28人中有13人，即46%为拉丁裔；28人中有10人，即36%为亚裔；28人中有4人，即14%为非拉丁裔白人；28人中有1人，即4%为其他族裔）参与了一项密集纵向研究。参与者佩戴2种设备（一个用于睡眠和生理数据的奥若拉戒指，以及一个用于生理和运动数据的三星智能手表），并在其移动设备上安装了AWARE软件，该软件收集诸如屏幕使用时间等被动传感数据。参与者来自一项积极心理学移动健康干预的随机对照试验。他们在19至22周的时间里每周完成一次抑郁症状的自我报告测量。
轻梯度提升机模型的F分数为0.744，科恩κ系数为0.474，表明预测标签与真实情况之间存在中等程度的一致性。抑郁症状最具预测性的数据特征是睡眠质量和错过的移动设备交互。
研究结果表明，从被动传感设备收集的数据可能为大学生抑郁症状的检测提供实时、低成本的见解，并可能为未来的预防乃至干预提供机会。
