Cargando…

Predicting death by suicide following an emergency department visit for parasuicide with administrative health care system data and machine learning

BACKGROUND: Suicide is a leading cause of death worldwide and results in a large number of person years of life lost. There is an opportunity to evaluate whether administrative health care system data and machine learning can quantify suicide risk in a clinical setting. METHODS: The objective was to...

Descripción completa

Detalles Bibliográficos
Autores principales: Sanderson, Michael, Bulloch, Andrew GM, Wang, JianLi, Williams, Kimberly G, Williamson, Tyler, Patten, Scott B
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7152812/
https://www.ncbi.nlm.nih.gov/pubmed/32300738
http://dx.doi.org/10.1016/j.eclinm.2020.100281
_version_ 1783521553200185344
author Sanderson, Michael
Bulloch, Andrew GM
Wang, JianLi
Williams, Kimberly G
Williamson, Tyler
Patten, Scott B
author_facet Sanderson, Michael
Bulloch, Andrew GM
Wang, JianLi
Williams, Kimberly G
Williamson, Tyler
Patten, Scott B
author_sort Sanderson, Michael
collection PubMed
description BACKGROUND: Suicide is a leading cause of death worldwide and results in a large number of person years of life lost. There is an opportunity to evaluate whether administrative health care system data and machine learning can quantify suicide risk in a clinical setting. METHODS: The objective was to compare the performance of prediction models that quantify the risk of death by suicide within 90 days of an ED visit for parasuicide with predictors available in administrative health care system data. The modeling dataset was assembled from 5 administrative health care data systems. The data systems contained nearly all of the physician visits, ambulatory care visits, inpatient hospitalizations, and community pharmacy dispenses, of nearly the entire 4.07 million persons in Alberta, Canada. 101 predictors were selected, and these were assembled for each of the 8 quarters (2 years) prior to the quarter of death, resulting in 808 predictors in total for each person. Prediction model performance was validated with 10-fold cross-validation. FINDINGS: The optimal gradient boosted trees prediction model achieved promising discrimination (AUC: 0.88) and calibration that could lead to clinical applications. The 5 most important predictors in the optimal gradient boosted trees model each came from a different administrative health care data system. INTERPRETATION: The combination of predictors from multiple administrative data systems and the combination of personal and ecologic predictors resulted in promising prediction performance. Further research is needed to develop prediction models optimized for implementation in clinical settings. FUNDING: There was no funding for this study.
format Online
Article
Text
id pubmed-7152812
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-71528122020-04-16 Predicting death by suicide following an emergency department visit for parasuicide with administrative health care system data and machine learning Sanderson, Michael Bulloch, Andrew GM Wang, JianLi Williams, Kimberly G Williamson, Tyler Patten, Scott B EClinicalMedicine Research paper BACKGROUND: Suicide is a leading cause of death worldwide and results in a large number of person years of life lost. There is an opportunity to evaluate whether administrative health care system data and machine learning can quantify suicide risk in a clinical setting. METHODS: The objective was to compare the performance of prediction models that quantify the risk of death by suicide within 90 days of an ED visit for parasuicide with predictors available in administrative health care system data. The modeling dataset was assembled from 5 administrative health care data systems. The data systems contained nearly all of the physician visits, ambulatory care visits, inpatient hospitalizations, and community pharmacy dispenses, of nearly the entire 4.07 million persons in Alberta, Canada. 101 predictors were selected, and these were assembled for each of the 8 quarters (2 years) prior to the quarter of death, resulting in 808 predictors in total for each person. Prediction model performance was validated with 10-fold cross-validation. FINDINGS: The optimal gradient boosted trees prediction model achieved promising discrimination (AUC: 0.88) and calibration that could lead to clinical applications. The 5 most important predictors in the optimal gradient boosted trees model each came from a different administrative health care data system. INTERPRETATION: The combination of predictors from multiple administrative data systems and the combination of personal and ecologic predictors resulted in promising prediction performance. Further research is needed to develop prediction models optimized for implementation in clinical settings. FUNDING: There was no funding for this study. Elsevier 2020-02-18 /pmc/articles/PMC7152812/ /pubmed/32300738 http://dx.doi.org/10.1016/j.eclinm.2020.100281 Text en © 2020 Published by Elsevier Ltd. http://creativecommons.org/licenses/by-nc-nd/4.0/ This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Research paper
Sanderson, Michael
Bulloch, Andrew GM
Wang, JianLi
Williams, Kimberly G
Williamson, Tyler
Patten, Scott B
Predicting death by suicide following an emergency department visit for parasuicide with administrative health care system data and machine learning
title Predicting death by suicide following an emergency department visit for parasuicide with administrative health care system data and machine learning
title_full Predicting death by suicide following an emergency department visit for parasuicide with administrative health care system data and machine learning
title_fullStr Predicting death by suicide following an emergency department visit for parasuicide with administrative health care system data and machine learning
title_full_unstemmed Predicting death by suicide following an emergency department visit for parasuicide with administrative health care system data and machine learning
title_short Predicting death by suicide following an emergency department visit for parasuicide with administrative health care system data and machine learning
title_sort predicting death by suicide following an emergency department visit for parasuicide with administrative health care system data and machine learning
topic Research paper
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7152812/
https://www.ncbi.nlm.nih.gov/pubmed/32300738
http://dx.doi.org/10.1016/j.eclinm.2020.100281
work_keys_str_mv AT sandersonmichael predictingdeathbysuicidefollowinganemergencydepartmentvisitforparasuicidewithadministrativehealthcaresystemdataandmachinelearning
AT bullochandrewgm predictingdeathbysuicidefollowinganemergencydepartmentvisitforparasuicidewithadministrativehealthcaresystemdataandmachinelearning
AT wangjianli predictingdeathbysuicidefollowinganemergencydepartmentvisitforparasuicidewithadministrativehealthcaresystemdataandmachinelearning
AT williamskimberlyg predictingdeathbysuicidefollowinganemergencydepartmentvisitforparasuicidewithadministrativehealthcaresystemdataandmachinelearning
AT williamsontyler predictingdeathbysuicidefollowinganemergencydepartmentvisitforparasuicidewithadministrativehealthcaresystemdataandmachinelearning
AT pattenscottb predictingdeathbysuicidefollowinganemergencydepartmentvisitforparasuicidewithadministrativehealthcaresystemdataandmachinelearning