Using data processing to understand inconsistency in smartphone behavior among patients with serious mental illness: Results of a digital phenotyping biomarker study

Background: Smartphone-based digital phenotyping can provide novel transdiagnostic markers of mental illness including circadian routines and anhedonia. In proposing transdiagnostic digital phenotypes for circadian routines and anhedonia in depression and bipolar disorder patients, this paper explor...

Full description

Saved in:
Bibliographic Details
Main Authors: Carsten Langholm, Scott Breitinger, Lucy Gray, Fernando Goes, Alex Walker, Ashley Xiong, Cindy Stopel, Peter P. Zandi, Mark A. Frye, John Torous
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Biomarkers in Neuropsychiatry
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666144624000236
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850168044711575552
author Carsten Langholm
Scott Breitinger
Lucy Gray
Fernando Goes
Alex Walker
Ashley Xiong
Cindy Stopel
Peter P. Zandi
Mark A. Frye
John Torous
author_facet Carsten Langholm
Scott Breitinger
Lucy Gray
Fernando Goes
Alex Walker
Ashley Xiong
Cindy Stopel
Peter P. Zandi
Mark A. Frye
John Torous
author_sort Carsten Langholm
collection DOAJ
description Background: Smartphone-based digital phenotyping can provide novel transdiagnostic markers of mental illness including circadian routines and anhedonia. In proposing transdiagnostic digital phenotypes for circadian routines and anhedonia in depression and bipolar disorder patients, this paper explores their derivation, comparison to naive models, and replicability across two different research sites/teams. Methods: 84 participants (bipolar disorder, depression, controls) used the mindLAMP app for 12 weeks to capture digital phenotypes on their personal smartphones. mindLAMP was used to deliver surveys about mood symptoms while collecting device acceleration, geolocation, and screen on/off state. Participant chronotype was derived from this sensor data. Within-participant and between-participant models were created to assess how time-varying features collected through digital phenotyping could predict weekly anhedonia survey responses. Results: Within-person models outperformed between-person models in predicting anhedonia. Chronotype was the strongest predictor of weekly anhedonia scores as indicated by Shapley scores. Shapley scores also revealed that many of the time-varying predictor variables are significant but differ in their direction of action. Discussion: This analysis reveals the meaningful but potentially misleading nature of digital phenotyping signals. Results suggest that each participant has a unique set of relationships between time-varying digital phenotype variables; therefore, it is challenging to predict trends between participants. Bayesian models, with appropriate population priors, may offer the next step for improving the potential of personalized digital phenotyping insights.
format Article
id doaj-art-c8f485e33fe143e0b92aa5f6aa5d2aba
institution OA Journals
issn 2666-1446
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Biomarkers in Neuropsychiatry
spelling doaj-art-c8f485e33fe143e0b92aa5f6aa5d2aba2025-08-20T02:21:04ZengElsevierBiomarkers in Neuropsychiatry2666-14462024-12-011110010510.1016/j.bionps.2024.100105Using data processing to understand inconsistency in smartphone behavior among patients with serious mental illness: Results of a digital phenotyping biomarker studyCarsten Langholm0Scott Breitinger1Lucy Gray2Fernando Goes3Alex Walker4Ashley Xiong5Cindy Stopel6Peter P. Zandi7Mark A. Frye8John Torous9Division of Digital Psychiatry, Beth Israel Deaconess Medical Center, Boston, MA 02115, USADepartment of Psychiatry & Psychology, Mayo Clinic, Rochester, MN 55902, USADivision of Digital Psychiatry, Beth Israel Deaconess Medical Center, Boston, MA 02115, USADepartment of Psychiatry and Behavioral Sciences, Johns Hopkins School of Medicine, Baltimore, MD 21218, USADepartment of Psychiatry and Behavioral Sciences, Johns Hopkins School of Medicine, Baltimore, MD 21218, USADepartment of Psychiatry & Psychology, Mayo Clinic, Rochester, MN 55902, USADepartment of Psychiatry & Psychology, Mayo Clinic, Rochester, MN 55902, USADepartment of Psychiatry and Behavioral Sciences, Johns Hopkins School of Medicine, Baltimore, MD 21218, USADepartment of Psychiatry & Psychology, Mayo Clinic, Rochester, MN 55902, USADivision of Digital Psychiatry, Beth Israel Deaconess Medical Center, Boston, MA 02115, USA; Corresponding author.Background: Smartphone-based digital phenotyping can provide novel transdiagnostic markers of mental illness including circadian routines and anhedonia. In proposing transdiagnostic digital phenotypes for circadian routines and anhedonia in depression and bipolar disorder patients, this paper explores their derivation, comparison to naive models, and replicability across two different research sites/teams. Methods: 84 participants (bipolar disorder, depression, controls) used the mindLAMP app for 12 weeks to capture digital phenotypes on their personal smartphones. mindLAMP was used to deliver surveys about mood symptoms while collecting device acceleration, geolocation, and screen on/off state. Participant chronotype was derived from this sensor data. Within-participant and between-participant models were created to assess how time-varying features collected through digital phenotyping could predict weekly anhedonia survey responses. Results: Within-person models outperformed between-person models in predicting anhedonia. Chronotype was the strongest predictor of weekly anhedonia scores as indicated by Shapley scores. Shapley scores also revealed that many of the time-varying predictor variables are significant but differ in their direction of action. Discussion: This analysis reveals the meaningful but potentially misleading nature of digital phenotyping signals. Results suggest that each participant has a unique set of relationships between time-varying digital phenotype variables; therefore, it is challenging to predict trends between participants. Bayesian models, with appropriate population priors, may offer the next step for improving the potential of personalized digital phenotyping insights.http://www.sciencedirect.com/science/article/pii/S2666144624000236SmartphoneDigital phenotypingMood disordersAnhedonia
spellingShingle Carsten Langholm
Scott Breitinger
Lucy Gray
Fernando Goes
Alex Walker
Ashley Xiong
Cindy Stopel
Peter P. Zandi
Mark A. Frye
John Torous
Using data processing to understand inconsistency in smartphone behavior among patients with serious mental illness: Results of a digital phenotyping biomarker study
Biomarkers in Neuropsychiatry
Smartphone
Digital phenotyping
Mood disorders
Anhedonia
title Using data processing to understand inconsistency in smartphone behavior among patients with serious mental illness: Results of a digital phenotyping biomarker study
title_full Using data processing to understand inconsistency in smartphone behavior among patients with serious mental illness: Results of a digital phenotyping biomarker study
title_fullStr Using data processing to understand inconsistency in smartphone behavior among patients with serious mental illness: Results of a digital phenotyping biomarker study
title_full_unstemmed Using data processing to understand inconsistency in smartphone behavior among patients with serious mental illness: Results of a digital phenotyping biomarker study
title_short Using data processing to understand inconsistency in smartphone behavior among patients with serious mental illness: Results of a digital phenotyping biomarker study
title_sort using data processing to understand inconsistency in smartphone behavior among patients with serious mental illness results of a digital phenotyping biomarker study
topic Smartphone
Digital phenotyping
Mood disorders
Anhedonia
url http://www.sciencedirect.com/science/article/pii/S2666144624000236
work_keys_str_mv AT carstenlangholm usingdataprocessingtounderstandinconsistencyinsmartphonebehavioramongpatientswithseriousmentalillnessresultsofadigitalphenotypingbiomarkerstudy
AT scottbreitinger usingdataprocessingtounderstandinconsistencyinsmartphonebehavioramongpatientswithseriousmentalillnessresultsofadigitalphenotypingbiomarkerstudy
AT lucygray usingdataprocessingtounderstandinconsistencyinsmartphonebehavioramongpatientswithseriousmentalillnessresultsofadigitalphenotypingbiomarkerstudy
AT fernandogoes usingdataprocessingtounderstandinconsistencyinsmartphonebehavioramongpatientswithseriousmentalillnessresultsofadigitalphenotypingbiomarkerstudy
AT alexwalker usingdataprocessingtounderstandinconsistencyinsmartphonebehavioramongpatientswithseriousmentalillnessresultsofadigitalphenotypingbiomarkerstudy
AT ashleyxiong usingdataprocessingtounderstandinconsistencyinsmartphonebehavioramongpatientswithseriousmentalillnessresultsofadigitalphenotypingbiomarkerstudy
AT cindystopel usingdataprocessingtounderstandinconsistencyinsmartphonebehavioramongpatientswithseriousmentalillnessresultsofadigitalphenotypingbiomarkerstudy
AT peterpzandi usingdataprocessingtounderstandinconsistencyinsmartphonebehavioramongpatientswithseriousmentalillnessresultsofadigitalphenotypingbiomarkerstudy
AT markafrye usingdataprocessingtounderstandinconsistencyinsmartphonebehavioramongpatientswithseriousmentalillnessresultsofadigitalphenotypingbiomarkerstudy
AT johntorous usingdataprocessingtounderstandinconsistencyinsmartphonebehavioramongpatientswithseriousmentalillnessresultsofadigitalphenotypingbiomarkerstudy