Detection of Depressive Symptoms in College Students Using Multimodal Passive Sensing Data and Light Gradient Boosting Machine: Longitudinal Pilot Study

BackgroundDepression 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. Pass...

Full description

Saved in:
Bibliographic Details
Main Authors: Jessica L Borelli, Yuning Wang, Frances Haofei Li, Lyric N Russo, Marta Tironi, Ken Yamashita, Elayne Zhou, Jocelyn Lai, Brenda Nguyen, Iman Azimi, Christopher Marcotullio, Sina Labbaf, Salar Jafarlou, Nikil Dutt, Amir Rahmani
Format: Article
Language:English
Published: JMIR Publications 2025-06-01
Series:JMIR Formative Research
Online Access:https://formative.jmir.org/2025/1/e67964
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849696836672028672
author Jessica L Borelli
Yuning Wang
Frances Haofei Li
Lyric N Russo
Marta Tironi
Ken Yamashita
Elayne Zhou
Jocelyn Lai
Brenda Nguyen
Iman Azimi
Christopher Marcotullio
Sina Labbaf
Salar Jafarlou
Nikil Dutt
Amir Rahmani
author_facet Jessica L Borelli
Yuning Wang
Frances Haofei Li
Lyric N Russo
Marta Tironi
Ken Yamashita
Elayne Zhou
Jocelyn Lai
Brenda Nguyen
Iman Azimi
Christopher Marcotullio
Sina Labbaf
Salar Jafarlou
Nikil Dutt
Amir Rahmani
author_sort Jessica L Borelli
collection DOAJ
description BackgroundDepression 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. ObjectiveWe leveraged an ensemble machine learning method (light gradient boosting machine) to detect depressive symptoms entirely through passive sensing. MethodsA 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. ResultsThe light gradient boosting machine model achieved an F1-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. ConclusionsFindings 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.
format Article
id doaj-art-077ec3b6735a43cd9b6b34c723f1a1bb
institution DOAJ
issn 2561-326X
language English
publishDate 2025-06-01
publisher JMIR Publications
record_format Article
series JMIR Formative Research
spelling doaj-art-077ec3b6735a43cd9b6b34c723f1a1bb2025-08-20T03:19:20ZengJMIR PublicationsJMIR Formative Research2561-326X2025-06-019e6796410.2196/67964Detection of Depressive Symptoms in College Students Using Multimodal Passive Sensing Data and Light Gradient Boosting Machine: Longitudinal Pilot StudyJessica L Borellihttps://orcid.org/0000-0001-8471-6732Yuning Wanghttps://orcid.org/0000-0001-7351-6866Frances Haofei Lihttps://orcid.org/0000-0002-2612-6336Lyric N Russohttps://orcid.org/0000-0002-3815-3622Marta Tironihttps://orcid.org/0000-0003-0610-6650Ken Yamashitahttps://orcid.org/0009-0009-0509-058XElayne Zhouhttps://orcid.org/0000-0001-9604-9404Jocelyn Laihttps://orcid.org/0000-0002-6457-3313Brenda Nguyenhttps://orcid.org/0009-0004-6480-8292Iman Azimihttps://orcid.org/0000-0001-5003-299XChristopher Marcotulliohttps://orcid.org/0009-0000-0736-5166Sina Labbafhttps://orcid.org/0000-0002-9478-2546Salar Jafarlouhttps://orcid.org/0000-0002-9706-0901Nikil Dutthttps://orcid.org/0000-0002-3060-8119Amir Rahmanihttps://orcid.org/0000-0003-0725-1155 BackgroundDepression 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. ObjectiveWe leveraged an ensemble machine learning method (light gradient boosting machine) to detect depressive symptoms entirely through passive sensing. MethodsA 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. ResultsThe light gradient boosting machine model achieved an F1-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. ConclusionsFindings 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.https://formative.jmir.org/2025/1/e67964
spellingShingle Jessica L Borelli
Yuning Wang
Frances Haofei Li
Lyric N Russo
Marta Tironi
Ken Yamashita
Elayne Zhou
Jocelyn Lai
Brenda Nguyen
Iman Azimi
Christopher Marcotullio
Sina Labbaf
Salar Jafarlou
Nikil Dutt
Amir Rahmani
Detection of Depressive Symptoms in College Students Using Multimodal Passive Sensing Data and Light Gradient Boosting Machine: Longitudinal Pilot Study
JMIR Formative Research
title Detection of Depressive Symptoms in College Students Using Multimodal Passive Sensing Data and Light Gradient Boosting Machine: Longitudinal Pilot Study
title_full Detection of Depressive Symptoms in College Students Using Multimodal Passive Sensing Data and Light Gradient Boosting Machine: Longitudinal Pilot Study
title_fullStr Detection of Depressive Symptoms in College Students Using Multimodal Passive Sensing Data and Light Gradient Boosting Machine: Longitudinal Pilot Study
title_full_unstemmed Detection of Depressive Symptoms in College Students Using Multimodal Passive Sensing Data and Light Gradient Boosting Machine: Longitudinal Pilot Study
title_short Detection of Depressive Symptoms in College Students Using Multimodal Passive Sensing Data and Light Gradient Boosting Machine: Longitudinal Pilot Study
title_sort detection of depressive symptoms in college students using multimodal passive sensing data and light gradient boosting machine longitudinal pilot study
url https://formative.jmir.org/2025/1/e67964
work_keys_str_mv AT jessicalborelli detectionofdepressivesymptomsincollegestudentsusingmultimodalpassivesensingdataandlightgradientboostingmachinelongitudinalpilotstudy
AT yuningwang detectionofdepressivesymptomsincollegestudentsusingmultimodalpassivesensingdataandlightgradientboostingmachinelongitudinalpilotstudy
AT franceshaofeili detectionofdepressivesymptomsincollegestudentsusingmultimodalpassivesensingdataandlightgradientboostingmachinelongitudinalpilotstudy
AT lyricnrusso detectionofdepressivesymptomsincollegestudentsusingmultimodalpassivesensingdataandlightgradientboostingmachinelongitudinalpilotstudy
AT martatironi detectionofdepressivesymptomsincollegestudentsusingmultimodalpassivesensingdataandlightgradientboostingmachinelongitudinalpilotstudy
AT kenyamashita detectionofdepressivesymptomsincollegestudentsusingmultimodalpassivesensingdataandlightgradientboostingmachinelongitudinalpilotstudy
AT elaynezhou detectionofdepressivesymptomsincollegestudentsusingmultimodalpassivesensingdataandlightgradientboostingmachinelongitudinalpilotstudy
AT jocelynlai detectionofdepressivesymptomsincollegestudentsusingmultimodalpassivesensingdataandlightgradientboostingmachinelongitudinalpilotstudy
AT brendanguyen detectionofdepressivesymptomsincollegestudentsusingmultimodalpassivesensingdataandlightgradientboostingmachinelongitudinalpilotstudy
AT imanazimi detectionofdepressivesymptomsincollegestudentsusingmultimodalpassivesensingdataandlightgradientboostingmachinelongitudinalpilotstudy
AT christophermarcotullio detectionofdepressivesymptomsincollegestudentsusingmultimodalpassivesensingdataandlightgradientboostingmachinelongitudinalpilotstudy
AT sinalabbaf detectionofdepressivesymptomsincollegestudentsusingmultimodalpassivesensingdataandlightgradientboostingmachinelongitudinalpilotstudy
AT salarjafarlou detectionofdepressivesymptomsincollegestudentsusingmultimodalpassivesensingdataandlightgradientboostingmachinelongitudinalpilotstudy
AT nikildutt detectionofdepressivesymptomsincollegestudentsusingmultimodalpassivesensingdataandlightgradientboostingmachinelongitudinalpilotstudy
AT amirrahmani detectionofdepressivesymptomsincollegestudentsusingmultimodalpassivesensingdataandlightgradientboostingmachinelongitudinalpilotstudy