Developing personalized algorithms for sensing mental health symptoms in daily life

Abstract The integration of artificial intelligence (AI) and pervasive computing offers new opportunities to sense mental health symptoms and deliver just-in-time adaptive interventions via mobile devices. This pilot study tested personalized versus generalized machine learning models for detecting...

Full description

Saved in:
Bibliographic Details
Main Authors: Adela C. Timmons, Abdullah Aman Tutul, Kleanthis Avramidis, Jacqueline B. Duong, Kayla E. Carta, Sierra N. Walters, Grace A. Jumonville, Alyssa S. Carrasco, Gabrielle F. Freitag, Daniela N. Romero, Matthew W. Ahle, Jonathan S. Comer, Shrikanth S. Narayanan, Ishita P. Khurd, Theodora Chaspari
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:npj Mental Health Research
Online Access:https://doi.org/10.1038/s44184-025-00147-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849331701200715776
author Adela C. Timmons
Abdullah Aman Tutul
Kleanthis Avramidis
Jacqueline B. Duong
Kayla E. Carta
Sierra N. Walters
Grace A. Jumonville
Alyssa S. Carrasco
Gabrielle F. Freitag
Daniela N. Romero
Matthew W. Ahle
Jonathan S. Comer
Shrikanth S. Narayanan
Ishita P. Khurd
Theodora Chaspari
author_facet Adela C. Timmons
Abdullah Aman Tutul
Kleanthis Avramidis
Jacqueline B. Duong
Kayla E. Carta
Sierra N. Walters
Grace A. Jumonville
Alyssa S. Carrasco
Gabrielle F. Freitag
Daniela N. Romero
Matthew W. Ahle
Jonathan S. Comer
Shrikanth S. Narayanan
Ishita P. Khurd
Theodora Chaspari
author_sort Adela C. Timmons
collection DOAJ
description Abstract The integration of artificial intelligence (AI) and pervasive computing offers new opportunities to sense mental health symptoms and deliver just-in-time adaptive interventions via mobile devices. This pilot study tested personalized versus generalized machine learning models for detecting individual and family mental health symptoms as a foundational step toward JITAI development, using data collected through the Colliga app on smart devices. Over a 60-day period, data from 35 families resulted in approximately 14 million data points across 52 data streams. Findings showed that personalized models consistently outperformed generalized models. Model performance varied significantly based on individual factors and symptom profiles, underscoring the need for tailored approaches. These preliminary findings suggest that successful implementation of passive sensing technologies for mental health will require accounting for users’ unique characteristics. Further research with larger samples is needed to refine the models, address data heterogeneity, and develop scalable systems for personalized mental health interventions.
format Article
id doaj-art-bb7740c6f1ce454aacc4ac4b6d6bc9fb
institution Kabale University
issn 2731-4251
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series npj Mental Health Research
spelling doaj-art-bb7740c6f1ce454aacc4ac4b6d6bc9fb2025-08-20T03:46:25ZengNature Portfolionpj Mental Health Research2731-42512025-08-014111910.1038/s44184-025-00147-5Developing personalized algorithms for sensing mental health symptoms in daily lifeAdela C. Timmons0Abdullah Aman Tutul1Kleanthis Avramidis2Jacqueline B. Duong3Kayla E. Carta4Sierra N. Walters5Grace A. Jumonville6Alyssa S. Carrasco7Gabrielle F. Freitag8Daniela N. Romero9Matthew W. Ahle10Jonathan S. Comer11Shrikanth S. Narayanan12Ishita P. Khurd13Theodora Chaspari14University of Texas at AustinTexas A&M UniversityUniversity of Southern CaliforniaUniversity of Texas at AustinUniversity of Texas at AustinUniversity of Texas at AustinUniversity of Texas at AustinUniversity of Texas at AustinFlorida International UniversityUniversity of Texas at AustinColliga AppsFlorida International UniversityUniversity of Southern CaliforniaUniversity of Texas at AustinUniversity of Colorado BoulderAbstract The integration of artificial intelligence (AI) and pervasive computing offers new opportunities to sense mental health symptoms and deliver just-in-time adaptive interventions via mobile devices. This pilot study tested personalized versus generalized machine learning models for detecting individual and family mental health symptoms as a foundational step toward JITAI development, using data collected through the Colliga app on smart devices. Over a 60-day period, data from 35 families resulted in approximately 14 million data points across 52 data streams. Findings showed that personalized models consistently outperformed generalized models. Model performance varied significantly based on individual factors and symptom profiles, underscoring the need for tailored approaches. These preliminary findings suggest that successful implementation of passive sensing technologies for mental health will require accounting for users’ unique characteristics. Further research with larger samples is needed to refine the models, address data heterogeneity, and develop scalable systems for personalized mental health interventions.https://doi.org/10.1038/s44184-025-00147-5
spellingShingle Adela C. Timmons
Abdullah Aman Tutul
Kleanthis Avramidis
Jacqueline B. Duong
Kayla E. Carta
Sierra N. Walters
Grace A. Jumonville
Alyssa S. Carrasco
Gabrielle F. Freitag
Daniela N. Romero
Matthew W. Ahle
Jonathan S. Comer
Shrikanth S. Narayanan
Ishita P. Khurd
Theodora Chaspari
Developing personalized algorithms for sensing mental health symptoms in daily life
npj Mental Health Research
title Developing personalized algorithms for sensing mental health symptoms in daily life
title_full Developing personalized algorithms for sensing mental health symptoms in daily life
title_fullStr Developing personalized algorithms for sensing mental health symptoms in daily life
title_full_unstemmed Developing personalized algorithms for sensing mental health symptoms in daily life
title_short Developing personalized algorithms for sensing mental health symptoms in daily life
title_sort developing personalized algorithms for sensing mental health symptoms in daily life
url https://doi.org/10.1038/s44184-025-00147-5
work_keys_str_mv AT adelactimmons developingpersonalizedalgorithmsforsensingmentalhealthsymptomsindailylife
AT abdullahamantutul developingpersonalizedalgorithmsforsensingmentalhealthsymptomsindailylife
AT kleanthisavramidis developingpersonalizedalgorithmsforsensingmentalhealthsymptomsindailylife
AT jacquelinebduong developingpersonalizedalgorithmsforsensingmentalhealthsymptomsindailylife
AT kaylaecarta developingpersonalizedalgorithmsforsensingmentalhealthsymptomsindailylife
AT sierranwalters developingpersonalizedalgorithmsforsensingmentalhealthsymptomsindailylife
AT graceajumonville developingpersonalizedalgorithmsforsensingmentalhealthsymptomsindailylife
AT alyssascarrasco developingpersonalizedalgorithmsforsensingmentalhealthsymptomsindailylife
AT gabrielleffreitag developingpersonalizedalgorithmsforsensingmentalhealthsymptomsindailylife
AT danielanromero developingpersonalizedalgorithmsforsensingmentalhealthsymptomsindailylife
AT matthewwahle developingpersonalizedalgorithmsforsensingmentalhealthsymptomsindailylife
AT jonathanscomer developingpersonalizedalgorithmsforsensingmentalhealthsymptomsindailylife
AT shrikanthsnarayanan developingpersonalizedalgorithmsforsensingmentalhealthsymptomsindailylife
AT ishitapkhurd developingpersonalizedalgorithmsforsensingmentalhealthsymptomsindailylife
AT theodorachaspari developingpersonalizedalgorithmsforsensingmentalhealthsymptomsindailylife