Uncovering Social States in Healthy and Clinical Populations Using Digital Phenotyping and Hidden Markov Models: Observational Study

BackgroundBrain-related disorders are characterized by observable behavioral symptoms, for example, social withdrawal. Smartphones can passively collect behavioral data reflecting digital activities such as communication app usage and calls. These data are collected objective...

Full description

Saved in:
Bibliographic Details
Main Authors: Imogen E Leaning, Andrea Costanzo, Raj Jagesar, Lianne M Reus, Pieter Jelle Visser, Martien J H Kas, Christian F Beckmann, Henricus G Ruhé, Andre F Marquand
Format: Article
Language:English
Published: JMIR Publications 2025-04-01
Series:Journal of Medical Internet Research
Online Access:https://www.jmir.org/2025/1/e64007
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849311231595249664
author Imogen E Leaning
Andrea Costanzo
Raj Jagesar
Lianne M Reus
Pieter Jelle Visser
Martien J H Kas
Christian F Beckmann
Henricus G Ruhé
Andre F Marquand
author_facet Imogen E Leaning
Andrea Costanzo
Raj Jagesar
Lianne M Reus
Pieter Jelle Visser
Martien J H Kas
Christian F Beckmann
Henricus G Ruhé
Andre F Marquand
author_sort Imogen E Leaning
collection DOAJ
description BackgroundBrain-related disorders are characterized by observable behavioral symptoms, for example, social withdrawal. Smartphones can passively collect behavioral data reflecting digital activities such as communication app usage and calls. These data are collected objectively in real time, avoiding recall bias, and may, therefore, be a useful tool for measuring behaviors related to social functioning. Despite promising clinical utility, analyzing smartphone data is challenging as datasets often include a range of temporal features prone to missingness. ObjectiveHidden Markov models (HMMs) provide interpretable, lower-dimensional temporal representations of data, allowing for missingness. This study aimed to investigate the HMM as a method for modeling smartphone time series data. MethodsWe applied an HMM to an aggregate dataset of smartphone measures designed to assess phone-related social functioning in healthy controls (HCs) and participants with schizophrenia, Alzheimer disease (AD), and memory complaints. We trained the HMM on a subset of HCs (91/348, 26.1%) and selected a model with socially active and inactive states. Then, we generated hidden state sequences per participant and calculated their “total dwell time,” that is, the percentage of time spent in the socially active state. Linear regression models were used to compare the total dwell time to social and clinical measures in a subset of participants with available measures, and logistic regression was used to compare total dwell times between diagnostic groups and HCs. We primarily reported results from a 2-state HMM but also verified results in HMMs with more hidden states and trained on the whole participant dataset. ResultsWe identified lower total dwell times in participants with AD (26/257, 10.1%) versus withheld HCs (156/257, 60.7%; odds ratio 0.95, 95% CI 0.92-0.97; false discovery rate [FDR]–corrected P<.001), as well as in participants with memory complaints (57/257, 22.2%; odds ratio 0.97, 95% CI 0.96-0.99; FDR-corrected P=.004). The result in the AD group was very robust across HMM variations, whereas the result in the memory complaints group was less robust. We also observed an interaction between the AD group and total dwell time when predicting social functioning (FDR-corrected P=.02). No significant relationships regarding total dwell time were identified for participants with schizophrenia (18/257, 7%; P>.99). ConclusionsWe found the HMM to be a practical, interpretable method for digital phenotyping analysis, providing an objective phenotype that is a possible indicator of social functioning.
format Article
id doaj-art-1bde098ee3ec4822bd7748bfac34e378
institution Kabale University
issn 1438-8871
language English
publishDate 2025-04-01
publisher JMIR Publications
record_format Article
series Journal of Medical Internet Research
spelling doaj-art-1bde098ee3ec4822bd7748bfac34e3782025-08-20T03:53:28ZengJMIR PublicationsJournal of Medical Internet Research1438-88712025-04-0127e6400710.2196/64007Uncovering Social States in Healthy and Clinical Populations Using Digital Phenotyping and Hidden Markov Models: Observational StudyImogen E Leaninghttps://orcid.org/0000-0002-4264-6585Andrea Costanzohttps://orcid.org/0000-0002-7158-634XRaj Jagesarhttps://orcid.org/0000-0002-5320-3341Lianne M Reushttps://orcid.org/0000-0001-6936-242XPieter Jelle Visserhttps://orcid.org/0000-0001-8008-9727Martien J H Kashttps://orcid.org/0000-0002-4471-8618Christian F Beckmannhttps://orcid.org/0000-0002-3373-3193Henricus G Ruhéhttps://orcid.org/0000-0001-6072-0358Andre F Marquandhttps://orcid.org/0000-0001-5903-203X BackgroundBrain-related disorders are characterized by observable behavioral symptoms, for example, social withdrawal. Smartphones can passively collect behavioral data reflecting digital activities such as communication app usage and calls. These data are collected objectively in real time, avoiding recall bias, and may, therefore, be a useful tool for measuring behaviors related to social functioning. Despite promising clinical utility, analyzing smartphone data is challenging as datasets often include a range of temporal features prone to missingness. ObjectiveHidden Markov models (HMMs) provide interpretable, lower-dimensional temporal representations of data, allowing for missingness. This study aimed to investigate the HMM as a method for modeling smartphone time series data. MethodsWe applied an HMM to an aggregate dataset of smartphone measures designed to assess phone-related social functioning in healthy controls (HCs) and participants with schizophrenia, Alzheimer disease (AD), and memory complaints. We trained the HMM on a subset of HCs (91/348, 26.1%) and selected a model with socially active and inactive states. Then, we generated hidden state sequences per participant and calculated their “total dwell time,” that is, the percentage of time spent in the socially active state. Linear regression models were used to compare the total dwell time to social and clinical measures in a subset of participants with available measures, and logistic regression was used to compare total dwell times between diagnostic groups and HCs. We primarily reported results from a 2-state HMM but also verified results in HMMs with more hidden states and trained on the whole participant dataset. ResultsWe identified lower total dwell times in participants with AD (26/257, 10.1%) versus withheld HCs (156/257, 60.7%; odds ratio 0.95, 95% CI 0.92-0.97; false discovery rate [FDR]–corrected P<.001), as well as in participants with memory complaints (57/257, 22.2%; odds ratio 0.97, 95% CI 0.96-0.99; FDR-corrected P=.004). The result in the AD group was very robust across HMM variations, whereas the result in the memory complaints group was less robust. We also observed an interaction between the AD group and total dwell time when predicting social functioning (FDR-corrected P=.02). No significant relationships regarding total dwell time were identified for participants with schizophrenia (18/257, 7%; P>.99). ConclusionsWe found the HMM to be a practical, interpretable method for digital phenotyping analysis, providing an objective phenotype that is a possible indicator of social functioning.https://www.jmir.org/2025/1/e64007
spellingShingle Imogen E Leaning
Andrea Costanzo
Raj Jagesar
Lianne M Reus
Pieter Jelle Visser
Martien J H Kas
Christian F Beckmann
Henricus G Ruhé
Andre F Marquand
Uncovering Social States in Healthy and Clinical Populations Using Digital Phenotyping and Hidden Markov Models: Observational Study
Journal of Medical Internet Research
title Uncovering Social States in Healthy and Clinical Populations Using Digital Phenotyping and Hidden Markov Models: Observational Study
title_full Uncovering Social States in Healthy and Clinical Populations Using Digital Phenotyping and Hidden Markov Models: Observational Study
title_fullStr Uncovering Social States in Healthy and Clinical Populations Using Digital Phenotyping and Hidden Markov Models: Observational Study
title_full_unstemmed Uncovering Social States in Healthy and Clinical Populations Using Digital Phenotyping and Hidden Markov Models: Observational Study
title_short Uncovering Social States in Healthy and Clinical Populations Using Digital Phenotyping and Hidden Markov Models: Observational Study
title_sort uncovering social states in healthy and clinical populations using digital phenotyping and hidden markov models observational study
url https://www.jmir.org/2025/1/e64007
work_keys_str_mv AT imogeneleaning uncoveringsocialstatesinhealthyandclinicalpopulationsusingdigitalphenotypingandhiddenmarkovmodelsobservationalstudy
AT andreacostanzo uncoveringsocialstatesinhealthyandclinicalpopulationsusingdigitalphenotypingandhiddenmarkovmodelsobservationalstudy
AT rajjagesar uncoveringsocialstatesinhealthyandclinicalpopulationsusingdigitalphenotypingandhiddenmarkovmodelsobservationalstudy
AT liannemreus uncoveringsocialstatesinhealthyandclinicalpopulationsusingdigitalphenotypingandhiddenmarkovmodelsobservationalstudy
AT pieterjellevisser uncoveringsocialstatesinhealthyandclinicalpopulationsusingdigitalphenotypingandhiddenmarkovmodelsobservationalstudy
AT martienjhkas uncoveringsocialstatesinhealthyandclinicalpopulationsusingdigitalphenotypingandhiddenmarkovmodelsobservationalstudy
AT christianfbeckmann uncoveringsocialstatesinhealthyandclinicalpopulationsusingdigitalphenotypingandhiddenmarkovmodelsobservationalstudy
AT henricusgruhe uncoveringsocialstatesinhealthyandclinicalpopulationsusingdigitalphenotypingandhiddenmarkovmodelsobservationalstudy
AT andrefmarquand uncoveringsocialstatesinhealthyandclinicalpopulationsusingdigitalphenotypingandhiddenmarkovmodelsobservationalstudy