Understanding importance of clinical biomarkers for diagnosis of anxiety disorders using machine learning models.

Anxiety disorders are a group of mental illnesses that cause constant and overwhelming feelings of anxiety and fear. Excessive anxiety can make an individual avoid work, school, family get-togethers, and other social situations that in turn might amplify these symptoms. According to the World Health...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Amita Sharma, Willem J M I Verbeke
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/4169c51943ea493b91ae0170e5d8b46b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:4169c51943ea493b91ae0170e5d8b46b
record_format	dspace
spelling	oai:doaj.org-article:4169c51943ea493b91ae0170e5d8b46b2021-12-02T20:11:23ZUnderstanding importance of clinical biomarkers for diagnosis of anxiety disorders using machine learning models.1932-620310.1371/journal.pone.0251365https://doaj.org/article/4169c51943ea493b91ae0170e5d8b46b2021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0251365https://doaj.org/toc/1932-6203Anxiety disorders are a group of mental illnesses that cause constant and overwhelming feelings of anxiety and fear. Excessive anxiety can make an individual avoid work, school, family get-togethers, and other social situations that in turn might amplify these symptoms. According to the World Health Organization (WHO), one in thirteen persons globally suffers from anxiety. It is high time to understand the roles of various clinical biomarker measures that can diagnose the types of anxiety disorders. In this study, we apply machine learning (ML) techniques to understand the importance of a set of biomarkers with four types of anxiety disorders-Generalized Anxiety Disorder (GAD), Agoraphobia (AP), Social Anxiety Disorder (SAD) and Panic Disorder (PD). We used several machine learning models and extracted the variable importance contributing to a type of anxiety disorder. The study uses a sample of 11,081 Dutch citizens' data collected by the Lifelines, Netherlands. The results show that there are significant and low correlations among GAD, AP, PD and SAD and we extracted the variable importance hierarchy of biomarkers with respect to each type of anxiety disorder which will be helpful in designing the experimental setup for clinical trials related to influence of biomarkers on type of anxiety disorder.Amita SharmaWillem J M I VerbekePublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 5, p e0251365 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Amita Sharma Willem J M I Verbeke Understanding importance of clinical biomarkers for diagnosis of anxiety disorders using machine learning models.
description	Anxiety disorders are a group of mental illnesses that cause constant and overwhelming feelings of anxiety and fear. Excessive anxiety can make an individual avoid work, school, family get-togethers, and other social situations that in turn might amplify these symptoms. According to the World Health Organization (WHO), one in thirteen persons globally suffers from anxiety. It is high time to understand the roles of various clinical biomarker measures that can diagnose the types of anxiety disorders. In this study, we apply machine learning (ML) techniques to understand the importance of a set of biomarkers with four types of anxiety disorders-Generalized Anxiety Disorder (GAD), Agoraphobia (AP), Social Anxiety Disorder (SAD) and Panic Disorder (PD). We used several machine learning models and extracted the variable importance contributing to a type of anxiety disorder. The study uses a sample of 11,081 Dutch citizens' data collected by the Lifelines, Netherlands. The results show that there are significant and low correlations among GAD, AP, PD and SAD and we extracted the variable importance hierarchy of biomarkers with respect to each type of anxiety disorder which will be helpful in designing the experimental setup for clinical trials related to influence of biomarkers on type of anxiety disorder.
format	article
author	Amita Sharma Willem J M I Verbeke
author_facet	Amita Sharma Willem J M I Verbeke
author_sort	Amita Sharma
title	Understanding importance of clinical biomarkers for diagnosis of anxiety disorders using machine learning models.
title_short	Understanding importance of clinical biomarkers for diagnosis of anxiety disorders using machine learning models.
title_full	Understanding importance of clinical biomarkers for diagnosis of anxiety disorders using machine learning models.
title_fullStr	Understanding importance of clinical biomarkers for diagnosis of anxiety disorders using machine learning models.
title_full_unstemmed	Understanding importance of clinical biomarkers for diagnosis of anxiety disorders using machine learning models.
title_sort	understanding importance of clinical biomarkers for diagnosis of anxiety disorders using machine learning models.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/4169c51943ea493b91ae0170e5d8b46b
work_keys_str_mv	AT amitasharma understandingimportanceofclinicalbiomarkersfordiagnosisofanxietydisordersusingmachinelearningmodels AT willemjmiverbeke understandingimportanceofclinicalbiomarkersfordiagnosisofanxietydisordersusingmachinelearningmodels
_version_	1718374878842716160

Understanding importance of clinical biomarkers for diagnosis of anxiety disorders using machine learning models.

Ejemplares similares