Cargando…

A Novel Approach to Clustering Accelerometer Data for Application in Passive Predictions of Changes in Depression Severity

The treatment of mood disorders, which can become a lifelong process, varies widely in efficacy between individuals. Most options to monitor mood rely on subjective self-reports and clinical visits, which can be burdensome and may not portray an accurate representation of what the individual is expe...

Descripción completa

Detalles Bibliográficos
Autores principales: Ross, Mindy K., Tulabandhula, Theja, Bennett, Casey C., Baek, EuGene, Kim, Dohyeon, Hussain, Faraz, Demos, Alexander P., Ning, Emma, Langenecker, Scott A., Ajilore, Olusola, Leow, Alex D.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9920816/
https://www.ncbi.nlm.nih.gov/pubmed/36772625
http://dx.doi.org/10.3390/s23031585
_version_ 1784887162700824576
author Ross, Mindy K.
Tulabandhula, Theja
Bennett, Casey C.
Baek, EuGene
Kim, Dohyeon
Hussain, Faraz
Demos, Alexander P.
Ning, Emma
Langenecker, Scott A.
Ajilore, Olusola
Leow, Alex D.
author_facet Ross, Mindy K.
Tulabandhula, Theja
Bennett, Casey C.
Baek, EuGene
Kim, Dohyeon
Hussain, Faraz
Demos, Alexander P.
Ning, Emma
Langenecker, Scott A.
Ajilore, Olusola
Leow, Alex D.
author_sort Ross, Mindy K.
collection PubMed
description The treatment of mood disorders, which can become a lifelong process, varies widely in efficacy between individuals. Most options to monitor mood rely on subjective self-reports and clinical visits, which can be burdensome and may not portray an accurate representation of what the individual is experiencing. A passive method to monitor mood could be a useful tool for those with these disorders. Some previously proposed models utilized sensors from smartphones and wearables, such as the accelerometer. This study examined a novel approach of processing accelerometer data collected from smartphones only while participants of the open-science branch of the BiAffect study were typing. The data were modeled by von Mises-Fisher distributions and weighted networks to identify clusters relating to different typing positions unique for each participant. Longitudinal features were derived from the clustered data and used in machine learning models to predict clinically relevant changes in depression from clinical and typing measures. Model accuracy was approximately 95%, with 97% area under the ROC curve (AUC). The accelerometer features outperformed the vast majority of clinical and typing features, which suggested that this new approach to analyzing accelerometer data could contribute towards unobtrusive detection of changes in depression severity without the need for clinical input.
format Online
Article
Text
id pubmed-9920816
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-99208162023-02-12 A Novel Approach to Clustering Accelerometer Data for Application in Passive Predictions of Changes in Depression Severity Ross, Mindy K. Tulabandhula, Theja Bennett, Casey C. Baek, EuGene Kim, Dohyeon Hussain, Faraz Demos, Alexander P. Ning, Emma Langenecker, Scott A. Ajilore, Olusola Leow, Alex D. Sensors (Basel) Article The treatment of mood disorders, which can become a lifelong process, varies widely in efficacy between individuals. Most options to monitor mood rely on subjective self-reports and clinical visits, which can be burdensome and may not portray an accurate representation of what the individual is experiencing. A passive method to monitor mood could be a useful tool for those with these disorders. Some previously proposed models utilized sensors from smartphones and wearables, such as the accelerometer. This study examined a novel approach of processing accelerometer data collected from smartphones only while participants of the open-science branch of the BiAffect study were typing. The data were modeled by von Mises-Fisher distributions and weighted networks to identify clusters relating to different typing positions unique for each participant. Longitudinal features were derived from the clustered data and used in machine learning models to predict clinically relevant changes in depression from clinical and typing measures. Model accuracy was approximately 95%, with 97% area under the ROC curve (AUC). The accelerometer features outperformed the vast majority of clinical and typing features, which suggested that this new approach to analyzing accelerometer data could contribute towards unobtrusive detection of changes in depression severity without the need for clinical input. MDPI 2023-02-01 /pmc/articles/PMC9920816/ /pubmed/36772625 http://dx.doi.org/10.3390/s23031585 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Ross, Mindy K.
Tulabandhula, Theja
Bennett, Casey C.
Baek, EuGene
Kim, Dohyeon
Hussain, Faraz
Demos, Alexander P.
Ning, Emma
Langenecker, Scott A.
Ajilore, Olusola
Leow, Alex D.
A Novel Approach to Clustering Accelerometer Data for Application in Passive Predictions of Changes in Depression Severity
title A Novel Approach to Clustering Accelerometer Data for Application in Passive Predictions of Changes in Depression Severity
title_full A Novel Approach to Clustering Accelerometer Data for Application in Passive Predictions of Changes in Depression Severity
title_fullStr A Novel Approach to Clustering Accelerometer Data for Application in Passive Predictions of Changes in Depression Severity
title_full_unstemmed A Novel Approach to Clustering Accelerometer Data for Application in Passive Predictions of Changes in Depression Severity
title_short A Novel Approach to Clustering Accelerometer Data for Application in Passive Predictions of Changes in Depression Severity
title_sort novel approach to clustering accelerometer data for application in passive predictions of changes in depression severity
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9920816/
https://www.ncbi.nlm.nih.gov/pubmed/36772625
http://dx.doi.org/10.3390/s23031585
work_keys_str_mv AT rossmindyk anovelapproachtoclusteringaccelerometerdataforapplicationinpassivepredictionsofchangesindepressionseverity
AT tulabandhulatheja anovelapproachtoclusteringaccelerometerdataforapplicationinpassivepredictionsofchangesindepressionseverity
AT bennettcaseyc anovelapproachtoclusteringaccelerometerdataforapplicationinpassivepredictionsofchangesindepressionseverity
AT baekeugene anovelapproachtoclusteringaccelerometerdataforapplicationinpassivepredictionsofchangesindepressionseverity
AT kimdohyeon anovelapproachtoclusteringaccelerometerdataforapplicationinpassivepredictionsofchangesindepressionseverity
AT hussainfaraz anovelapproachtoclusteringaccelerometerdataforapplicationinpassivepredictionsofchangesindepressionseverity
AT demosalexanderp anovelapproachtoclusteringaccelerometerdataforapplicationinpassivepredictionsofchangesindepressionseverity
AT ningemma anovelapproachtoclusteringaccelerometerdataforapplicationinpassivepredictionsofchangesindepressionseverity
AT langeneckerscotta anovelapproachtoclusteringaccelerometerdataforapplicationinpassivepredictionsofchangesindepressionseverity
AT ajiloreolusola anovelapproachtoclusteringaccelerometerdataforapplicationinpassivepredictionsofchangesindepressionseverity
AT leowalexd anovelapproachtoclusteringaccelerometerdataforapplicationinpassivepredictionsofchangesindepressionseverity
AT rossmindyk novelapproachtoclusteringaccelerometerdataforapplicationinpassivepredictionsofchangesindepressionseverity
AT tulabandhulatheja novelapproachtoclusteringaccelerometerdataforapplicationinpassivepredictionsofchangesindepressionseverity
AT bennettcaseyc novelapproachtoclusteringaccelerometerdataforapplicationinpassivepredictionsofchangesindepressionseverity
AT baekeugene novelapproachtoclusteringaccelerometerdataforapplicationinpassivepredictionsofchangesindepressionseverity
AT kimdohyeon novelapproachtoclusteringaccelerometerdataforapplicationinpassivepredictionsofchangesindepressionseverity
AT hussainfaraz novelapproachtoclusteringaccelerometerdataforapplicationinpassivepredictionsofchangesindepressionseverity
AT demosalexanderp novelapproachtoclusteringaccelerometerdataforapplicationinpassivepredictionsofchangesindepressionseverity
AT ningemma novelapproachtoclusteringaccelerometerdataforapplicationinpassivepredictionsofchangesindepressionseverity
AT langeneckerscotta novelapproachtoclusteringaccelerometerdataforapplicationinpassivepredictionsofchangesindepressionseverity
AT ajiloreolusola novelapproachtoclusteringaccelerometerdataforapplicationinpassivepredictionsofchangesindepressionseverity
AT leowalexd novelapproachtoclusteringaccelerometerdataforapplicationinpassivepredictionsofchangesindepressionseverity