Predicting women with depressive symptoms postpartum with machine learning methods

Abstract Postpartum depression (PPD) is a detrimental health condition that affects 12% of new mothers. Despite negative effects on mothers’ and children’s health, many women do not receive adequate care. Preventive interventions are cost-efficient among high-risk women, but our ability to identify...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sam Andersson, Deepti R. Bathula, Stavros I. Iliadis, Martin Walter, Alkistis Skalkidou
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/c6332d34d8c04e7b9d4228989ff34b5b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c6332d34d8c04e7b9d4228989ff34b5b
record_format	dspace
spelling	oai:doaj.org-article:c6332d34d8c04e7b9d4228989ff34b5b2021-12-02T14:26:15ZPredicting women with depressive symptoms postpartum with machine learning methods10.1038/s41598-021-86368-y2045-2322https://doaj.org/article/c6332d34d8c04e7b9d4228989ff34b5b2021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-86368-yhttps://doaj.org/toc/2045-2322Abstract Postpartum depression (PPD) is a detrimental health condition that affects 12% of new mothers. Despite negative effects on mothers’ and children’s health, many women do not receive adequate care. Preventive interventions are cost-efficient among high-risk women, but our ability to identify these is poor. We leveraged the power of clinical, demographic, and psychometric data to assess if machine learning methods can make accurate predictions of postpartum depression. Data were obtained from a population-based prospective cohort study in Uppsala, Sweden, collected between 2009 and 2018 (BASIC study, n = 4313). Sub-analyses among women without previous depression were performed. The extremely randomized trees method provided robust performance with highest accuracy and well-balanced sensitivity and specificity (accuracy 73%, sensitivity 72%, specificity 75%, positive predictive value 33%, negative predictive value 94%, area under the curve 81%). Among women without earlier mental health issues, the accuracy was 64%. The variables setting women at most risk for PPD were depression and anxiety during pregnancy, as well as variables related to resilience and personality. Future clinical models that could be implemented directly after delivery might consider including these variables in order to identify women at high risk for postpartum depression to facilitate individualized follow-up and cost-effectiveness.Sam AnderssonDeepti R. BathulaStavros I. IliadisMartin WalterAlkistis SkalkidouNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-15 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Sam Andersson Deepti R. Bathula Stavros I. Iliadis Martin Walter Alkistis Skalkidou Predicting women with depressive symptoms postpartum with machine learning methods
description	Abstract Postpartum depression (PPD) is a detrimental health condition that affects 12% of new mothers. Despite negative effects on mothers’ and children’s health, many women do not receive adequate care. Preventive interventions are cost-efficient among high-risk women, but our ability to identify these is poor. We leveraged the power of clinical, demographic, and psychometric data to assess if machine learning methods can make accurate predictions of postpartum depression. Data were obtained from a population-based prospective cohort study in Uppsala, Sweden, collected between 2009 and 2018 (BASIC study, n = 4313). Sub-analyses among women without previous depression were performed. The extremely randomized trees method provided robust performance with highest accuracy and well-balanced sensitivity and specificity (accuracy 73%, sensitivity 72%, specificity 75%, positive predictive value 33%, negative predictive value 94%, area under the curve 81%). Among women without earlier mental health issues, the accuracy was 64%. The variables setting women at most risk for PPD were depression and anxiety during pregnancy, as well as variables related to resilience and personality. Future clinical models that could be implemented directly after delivery might consider including these variables in order to identify women at high risk for postpartum depression to facilitate individualized follow-up and cost-effectiveness.
format	article
author	Sam Andersson Deepti R. Bathula Stavros I. Iliadis Martin Walter Alkistis Skalkidou
author_facet	Sam Andersson Deepti R. Bathula Stavros I. Iliadis Martin Walter Alkistis Skalkidou
author_sort	Sam Andersson
title	Predicting women with depressive symptoms postpartum with machine learning methods
title_short	Predicting women with depressive symptoms postpartum with machine learning methods
title_full	Predicting women with depressive symptoms postpartum with machine learning methods
title_fullStr	Predicting women with depressive symptoms postpartum with machine learning methods
title_full_unstemmed	Predicting women with depressive symptoms postpartum with machine learning methods
title_sort	predicting women with depressive symptoms postpartum with machine learning methods
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/c6332d34d8c04e7b9d4228989ff34b5b
work_keys_str_mv	AT samandersson predictingwomenwithdepressivesymptomspostpartumwithmachinelearningmethods AT deeptirbathula predictingwomenwithdepressivesymptomspostpartumwithmachinelearningmethods AT stavrosiiliadis predictingwomenwithdepressivesymptomspostpartumwithmachinelearningmethods AT martinwalter predictingwomenwithdepressivesymptomspostpartumwithmachinelearningmethods AT alkistisskalkidou predictingwomenwithdepressivesymptomspostpartumwithmachinelearningmethods
_version_	1718391394726313984

Predicting women with depressive symptoms postpartum with machine learning methods

Ejemplares similares