Cargando…

Training machine learning models to predict 30-day mortality in patients discharged from the emergency department: a retrospective, population-based registry study

OBJECTIVES: The aim of this work was to train machine learning models to identify patients at end of life with clinically meaningful diagnostic accuracy, using 30-day mortality in patients discharged from the emergency department (ED) as a proxy. DESIGN: Retrospective, population-based registry stud...

Descripción completa

Detalles Bibliográficos
Autores principales: Blom, Mathias Carl, Ashfaq, Awais, Sant'Anna, Anita, Anderson, Philip D, Lingman, Markus
Formato: Online Artículo Texto
Lenguaje:English
Publicado: BMJ Publishing Group 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6701621/
https://www.ncbi.nlm.nih.gov/pubmed/31401594
http://dx.doi.org/10.1136/bmjopen-2018-028015
_version_ 1783445082867761152
author Blom, Mathias Carl
Ashfaq, Awais
Sant'Anna, Anita
Anderson, Philip D
Lingman, Markus
author_facet Blom, Mathias Carl
Ashfaq, Awais
Sant'Anna, Anita
Anderson, Philip D
Lingman, Markus
author_sort Blom, Mathias Carl
collection PubMed
description OBJECTIVES: The aim of this work was to train machine learning models to identify patients at end of life with clinically meaningful diagnostic accuracy, using 30-day mortality in patients discharged from the emergency department (ED) as a proxy. DESIGN: Retrospective, population-based registry study. SETTING: Swedish health services. PRIMARY AND SECONDARY OUTCOME MEASURES: All cause 30-day mortality. METHODS: Electronic health records (EHRs) and administrative data were used to train six supervised machine learning models to predict all-cause mortality within 30 days in patients discharged from EDs in southern Sweden, Europe. PARTICIPANTS: The models were trained using 65 776 ED visits and validated on 55 164 visits from a separate ED to which the models were not exposed during training. RESULTS: The outcome occurred in 136 visits (0.21%) in the development set and in 83 visits (0.15%) in the validation set. The model with highest discrimination attained ROC–AUC 0.95 (95% CI 0.93 to 0.96), with sensitivity 0.87 (95% CI 0.80 to 0.93) and specificity 0.86 (0.86 to 0.86) on the validation set. CONCLUSIONS: Multiple models displayed excellent discrimination on the validation set and outperformed available indexes for short-term mortality prediction interms of ROC–AUC (by indirect comparison). The practical utility of the models increases as the data they were trained on did not require costly de novo collection but were real-world data generated as a by-product of routine care delivery.
format Online
Article
Text
id pubmed-6701621
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher BMJ Publishing Group
record_format MEDLINE/PubMed
spelling pubmed-67016212019-09-02 Training machine learning models to predict 30-day mortality in patients discharged from the emergency department: a retrospective, population-based registry study Blom, Mathias Carl Ashfaq, Awais Sant'Anna, Anita Anderson, Philip D Lingman, Markus BMJ Open Emergency Medicine OBJECTIVES: The aim of this work was to train machine learning models to identify patients at end of life with clinically meaningful diagnostic accuracy, using 30-day mortality in patients discharged from the emergency department (ED) as a proxy. DESIGN: Retrospective, population-based registry study. SETTING: Swedish health services. PRIMARY AND SECONDARY OUTCOME MEASURES: All cause 30-day mortality. METHODS: Electronic health records (EHRs) and administrative data were used to train six supervised machine learning models to predict all-cause mortality within 30 days in patients discharged from EDs in southern Sweden, Europe. PARTICIPANTS: The models were trained using 65 776 ED visits and validated on 55 164 visits from a separate ED to which the models were not exposed during training. RESULTS: The outcome occurred in 136 visits (0.21%) in the development set and in 83 visits (0.15%) in the validation set. The model with highest discrimination attained ROC–AUC 0.95 (95% CI 0.93 to 0.96), with sensitivity 0.87 (95% CI 0.80 to 0.93) and specificity 0.86 (0.86 to 0.86) on the validation set. CONCLUSIONS: Multiple models displayed excellent discrimination on the validation set and outperformed available indexes for short-term mortality prediction interms of ROC–AUC (by indirect comparison). The practical utility of the models increases as the data they were trained on did not require costly de novo collection but were real-world data generated as a by-product of routine care delivery. BMJ Publishing Group 2019-08-10 /pmc/articles/PMC6701621/ /pubmed/31401594 http://dx.doi.org/10.1136/bmjopen-2018-028015 Text en © Author(s) (or their employer(s)) 2019. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ. This is an open access article distributed in accordance with the Creative Commons Attribution Non Commercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited, appropriate credit is given, any changes made indicated, and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/4.0/.
spellingShingle Emergency Medicine
Blom, Mathias Carl
Ashfaq, Awais
Sant'Anna, Anita
Anderson, Philip D
Lingman, Markus
Training machine learning models to predict 30-day mortality in patients discharged from the emergency department: a retrospective, population-based registry study
title Training machine learning models to predict 30-day mortality in patients discharged from the emergency department: a retrospective, population-based registry study
title_full Training machine learning models to predict 30-day mortality in patients discharged from the emergency department: a retrospective, population-based registry study
title_fullStr Training machine learning models to predict 30-day mortality in patients discharged from the emergency department: a retrospective, population-based registry study
title_full_unstemmed Training machine learning models to predict 30-day mortality in patients discharged from the emergency department: a retrospective, population-based registry study
title_short Training machine learning models to predict 30-day mortality in patients discharged from the emergency department: a retrospective, population-based registry study
title_sort training machine learning models to predict 30-day mortality in patients discharged from the emergency department: a retrospective, population-based registry study
topic Emergency Medicine
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6701621/
https://www.ncbi.nlm.nih.gov/pubmed/31401594
http://dx.doi.org/10.1136/bmjopen-2018-028015
work_keys_str_mv AT blommathiascarl trainingmachinelearningmodelstopredict30daymortalityinpatientsdischargedfromtheemergencydepartmentaretrospectivepopulationbasedregistrystudy
AT ashfaqawais trainingmachinelearningmodelstopredict30daymortalityinpatientsdischargedfromtheemergencydepartmentaretrospectivepopulationbasedregistrystudy
AT santannaanita trainingmachinelearningmodelstopredict30daymortalityinpatientsdischargedfromtheemergencydepartmentaretrospectivepopulationbasedregistrystudy
AT andersonphilipd trainingmachinelearningmodelstopredict30daymortalityinpatientsdischargedfromtheemergencydepartmentaretrospectivepopulationbasedregistrystudy
AT lingmanmarkus trainingmachinelearningmodelstopredict30daymortalityinpatientsdischargedfromtheemergencydepartmentaretrospectivepopulationbasedregistrystudy