Depression predictions from GPS-based mobility do not generalize well to large demographically heterogeneous samples

Abstract Depression is one of the most common mental health issues in the United States, affecting the lives of millions of people suffering from it as well as those close to them. Recent advances in research on mobile sensing technologies and machine learning have suggested that a person’s depressi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sandrine R. Müller, Xi (Leslie) Chen, Heinrich Peters, Augustin Chaintreau, Sandra C. Matz
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/75c285a293e64182af3c754c20fef62e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:75c285a293e64182af3c754c20fef62e
record_format	dspace
spelling	oai:doaj.org-article:75c285a293e64182af3c754c20fef62e2021-12-02T15:39:50ZDepression predictions from GPS-based mobility do not generalize well to large demographically heterogeneous samples10.1038/s41598-021-93087-x2045-2322https://doaj.org/article/75c285a293e64182af3c754c20fef62e2021-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-93087-xhttps://doaj.org/toc/2045-2322Abstract Depression is one of the most common mental health issues in the United States, affecting the lives of millions of people suffering from it as well as those close to them. Recent advances in research on mobile sensing technologies and machine learning have suggested that a person’s depression can be passively measured by observing patterns in people’s mobility behaviors. However, the majority of work in this area has relied on highly homogeneous samples, most frequently college students. In this study, we analyse over 57 million GPS data points to show that the same procedure that leads to high prediction accuracy in a homogeneous student sample (N = 57; AUC = 0.82), leads to accuracies only slightly higher than chance in a U.S.-wide sample that is heterogeneous in its socio-demographic composition as well as mobility patterns (N = 5,262; AUC = 0.57). This pattern holds across three different modelling approaches which consider both linear and non-linear relationships. Further analyses suggest that the prediction accuracy is low across different socio-demographic groups, and that training the models on more homogeneous subsamples does not substantially improve prediction accuracy. Overall, the findings highlight the challenge of applying mobility-based predictions of depression at scale.Sandrine R. MüllerXi (Leslie) ChenHeinrich PetersAugustin ChaintreauSandra C. MatzNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Sandrine R. Müller Xi (Leslie) Chen Heinrich Peters Augustin Chaintreau Sandra C. Matz Depression predictions from GPS-based mobility do not generalize well to large demographically heterogeneous samples
description	Abstract Depression is one of the most common mental health issues in the United States, affecting the lives of millions of people suffering from it as well as those close to them. Recent advances in research on mobile sensing technologies and machine learning have suggested that a person’s depression can be passively measured by observing patterns in people’s mobility behaviors. However, the majority of work in this area has relied on highly homogeneous samples, most frequently college students. In this study, we analyse over 57 million GPS data points to show that the same procedure that leads to high prediction accuracy in a homogeneous student sample (N = 57; AUC = 0.82), leads to accuracies only slightly higher than chance in a U.S.-wide sample that is heterogeneous in its socio-demographic composition as well as mobility patterns (N = 5,262; AUC = 0.57). This pattern holds across three different modelling approaches which consider both linear and non-linear relationships. Further analyses suggest that the prediction accuracy is low across different socio-demographic groups, and that training the models on more homogeneous subsamples does not substantially improve prediction accuracy. Overall, the findings highlight the challenge of applying mobility-based predictions of depression at scale.
format	article
author	Sandrine R. Müller Xi (Leslie) Chen Heinrich Peters Augustin Chaintreau Sandra C. Matz
author_facet	Sandrine R. Müller Xi (Leslie) Chen Heinrich Peters Augustin Chaintreau Sandra C. Matz
author_sort	Sandrine R. Müller
title	Depression predictions from GPS-based mobility do not generalize well to large demographically heterogeneous samples
title_short	Depression predictions from GPS-based mobility do not generalize well to large demographically heterogeneous samples
title_full	Depression predictions from GPS-based mobility do not generalize well to large demographically heterogeneous samples
title_fullStr	Depression predictions from GPS-based mobility do not generalize well to large demographically heterogeneous samples
title_full_unstemmed	Depression predictions from GPS-based mobility do not generalize well to large demographically heterogeneous samples
title_sort	depression predictions from gps-based mobility do not generalize well to large demographically heterogeneous samples
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/75c285a293e64182af3c754c20fef62e
work_keys_str_mv	AT sandrinermuller depressionpredictionsfromgpsbasedmobilitydonotgeneralizewelltolargedemographicallyheterogeneoussamples AT xilesliechen depressionpredictionsfromgpsbasedmobilitydonotgeneralizewelltolargedemographicallyheterogeneoussamples AT heinrichpeters depressionpredictionsfromgpsbasedmobilitydonotgeneralizewelltolargedemographicallyheterogeneoussamples AT augustinchaintreau depressionpredictionsfromgpsbasedmobilitydonotgeneralizewelltolargedemographicallyheterogeneoussamples AT sandracmatz depressionpredictionsfromgpsbasedmobilitydonotgeneralizewelltolargedemographicallyheterogeneoussamples
_version_	1718385881011716096

Depression predictions from GPS-based mobility do not generalize well to large demographically heterogeneous samples

Ejemplares similares