Predictive modeling of depression and anxiety using electronic health records and a novel machine learning approach with artificial intelligence

Abstract Generalized anxiety disorder (GAD) and major depressive disorder (MDD) are highly prevalent and impairing problems, but frequently go undetected, leading to substantial treatment delays. Electronic health records (EHRs) collect a great deal of biometric markers and patient characteristics t...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Matthew D. Nemesure, Michael V. Heinz, Raphael Huang, Nicholas C. Jacobson
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/7a3200ae1e9343eba56d585102237a2c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7a3200ae1e9343eba56d585102237a2c
record_format	dspace
spelling	oai:doaj.org-article:7a3200ae1e9343eba56d585102237a2c2021-12-02T11:50:40ZPredictive modeling of depression and anxiety using electronic health records and a novel machine learning approach with artificial intelligence10.1038/s41598-021-81368-42045-2322https://doaj.org/article/7a3200ae1e9343eba56d585102237a2c2021-01-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-81368-4https://doaj.org/toc/2045-2322Abstract Generalized anxiety disorder (GAD) and major depressive disorder (MDD) are highly prevalent and impairing problems, but frequently go undetected, leading to substantial treatment delays. Electronic health records (EHRs) collect a great deal of biometric markers and patient characteristics that could foster the detection of GAD and MDD in primary care settings. We approached the problem of predicting MDD and GAD using a novel machine learning pipeline to re-analyze data from an observational study. The pipeline constitutes an ensemble of algorithmically distinct machine learning methods, including deep learning. A sample of 4,184 undergraduate students completed the study, undergoing a general health screening and completing a psychiatric assessment for MDD and GAD. After explicitly excluding all psychiatric information, 59 biomedical and demographic features from the general health survey in addition to a set of engineered features were used for model training. We assessed the model's performance on a held-out test set and found an AUC of 0.73 (sensitivity: 0.66, specificity: 0.7) and 0.67 (sensitivity: 0.55, specificity: 0.7) for GAD, and MDD, respectively. Additionally, we used advanced techniques (SHAP values) to illuminate which features had the greatest impact on prediction for each disease. The top predictive features for MDD were being satisfied with living conditions and having public health insurance. The top predictive features for GAD were vaccinations being up to date and marijuana use. Our results indicate moderate predictive performance for the application of machine learning methods in detection of GAD and MDD based on EHR data. By identifying important predictors of GAD and MDD, these results may be used in future research to aid in the early detection of MDD and GAD.Matthew D. NemesureMichael V. HeinzRaphael HuangNicholas C. JacobsonNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Matthew D. Nemesure Michael V. Heinz Raphael Huang Nicholas C. Jacobson Predictive modeling of depression and anxiety using electronic health records and a novel machine learning approach with artificial intelligence
description	Abstract Generalized anxiety disorder (GAD) and major depressive disorder (MDD) are highly prevalent and impairing problems, but frequently go undetected, leading to substantial treatment delays. Electronic health records (EHRs) collect a great deal of biometric markers and patient characteristics that could foster the detection of GAD and MDD in primary care settings. We approached the problem of predicting MDD and GAD using a novel machine learning pipeline to re-analyze data from an observational study. The pipeline constitutes an ensemble of algorithmically distinct machine learning methods, including deep learning. A sample of 4,184 undergraduate students completed the study, undergoing a general health screening and completing a psychiatric assessment for MDD and GAD. After explicitly excluding all psychiatric information, 59 biomedical and demographic features from the general health survey in addition to a set of engineered features were used for model training. We assessed the model's performance on a held-out test set and found an AUC of 0.73 (sensitivity: 0.66, specificity: 0.7) and 0.67 (sensitivity: 0.55, specificity: 0.7) for GAD, and MDD, respectively. Additionally, we used advanced techniques (SHAP values) to illuminate which features had the greatest impact on prediction for each disease. The top predictive features for MDD were being satisfied with living conditions and having public health insurance. The top predictive features for GAD were vaccinations being up to date and marijuana use. Our results indicate moderate predictive performance for the application of machine learning methods in detection of GAD and MDD based on EHR data. By identifying important predictors of GAD and MDD, these results may be used in future research to aid in the early detection of MDD and GAD.
format	article
author	Matthew D. Nemesure Michael V. Heinz Raphael Huang Nicholas C. Jacobson
author_facet	Matthew D. Nemesure Michael V. Heinz Raphael Huang Nicholas C. Jacobson
author_sort	Matthew D. Nemesure
title	Predictive modeling of depression and anxiety using electronic health records and a novel machine learning approach with artificial intelligence
title_short	Predictive modeling of depression and anxiety using electronic health records and a novel machine learning approach with artificial intelligence
title_full	Predictive modeling of depression and anxiety using electronic health records and a novel machine learning approach with artificial intelligence
title_fullStr	Predictive modeling of depression and anxiety using electronic health records and a novel machine learning approach with artificial intelligence
title_full_unstemmed	Predictive modeling of depression and anxiety using electronic health records and a novel machine learning approach with artificial intelligence
title_sort	predictive modeling of depression and anxiety using electronic health records and a novel machine learning approach with artificial intelligence
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/7a3200ae1e9343eba56d585102237a2c
work_keys_str_mv	AT matthewdnemesure predictivemodelingofdepressionandanxietyusingelectronichealthrecordsandanovelmachinelearningapproachwithartificialintelligence AT michaelvheinz predictivemodelingofdepressionandanxietyusingelectronichealthrecordsandanovelmachinelearningapproachwithartificialintelligence AT raphaelhuang predictivemodelingofdepressionandanxietyusingelectronichealthrecordsandanovelmachinelearningapproachwithartificialintelligence AT nicholascjacobson predictivemodelingofdepressionandanxietyusingelectronichealthrecordsandanovelmachinelearningapproachwithartificialintelligence
_version_	1718395172913414144

Predictive modeling of depression and anxiety using electronic health records and a novel machine learning approach with artificial intelligence

Ejemplares similares