Machine learning-based mortality prediction model for heat-related illness

Abstract In this study, we aimed to develop and validate a machine learning-based mortality prediction model for hospitalized heat-related illness patients. After 2393 hospitalized patients were extracted from a multicentered heat-related illness registry in Japan, subjects were divided into the tra...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Yohei Hirano, Yutaka Kondo, Toru Hifumi, Shoji Yokobori, Jun Kanda, Junya Shimazaki, Kei Hayashida, Takashi Moriya, Masaharu Yagi, Shuhei Takauji, Junko Yamaguchi, Yohei Okada, Yuichi Okano, Hitoshi Kaneko, Tatsuho Kobayashi, Motoki Fujita, Hiroyuki Yokota, Ken Okamoto, Hiroshi Tanaka, Arino Yaguchi
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/a339b3e4021e4bf29780ed3e55dd3c72
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:a339b3e4021e4bf29780ed3e55dd3c72
record_format dspace
spelling oai:doaj.org-article:a339b3e4021e4bf29780ed3e55dd3c722021-12-02T15:37:58ZMachine learning-based mortality prediction model for heat-related illness10.1038/s41598-021-88581-12045-2322https://doaj.org/article/a339b3e4021e4bf29780ed3e55dd3c722021-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-88581-1https://doaj.org/toc/2045-2322Abstract In this study, we aimed to develop and validate a machine learning-based mortality prediction model for hospitalized heat-related illness patients. After 2393 hospitalized patients were extracted from a multicentered heat-related illness registry in Japan, subjects were divided into the training set for development (n = 1516, data from 2014, 2017–2019) and the test set (n = 877, data from 2020) for validation. Twenty-four variables including characteristics of patients, vital signs, and laboratory test data at hospital arrival were trained as predictor features for machine learning. The outcome was death during hospital stay. In validation, the developed machine learning models (logistic regression, support vector machine, random forest, XGBoost) demonstrated favorable performance for outcome prediction with significantly increased values of the area under the precision-recall curve (AUPR) of 0.415 [95% confidence interval (CI) 0.336–0.494], 0.395 [CI 0.318–0.472], 0.426 [CI 0.346–0.506], and 0.528 [CI 0.442–0.614], respectively, compared to that of the conventional acute physiology and chronic health evaluation (APACHE)-II score of 0.287 [CI 0.222–0.351] as a reference standard. The area under the receiver operating characteristic curve (AUROC) values were also high over 0.92 in all models, although there were no statistical differences compared to APACHE-II. This is the first demonstration of the potential of machine learning-based mortality prediction models for heat-related illnesses.Yohei HiranoYutaka KondoToru HifumiShoji YokoboriJun KandaJunya ShimazakiKei HayashidaTakashi MoriyaMasaharu YagiShuhei TakaujiJunko YamaguchiYohei OkadaYuichi OkanoHitoshi KanekoTatsuho KobayashiMotoki FujitaHiroyuki YokotaKen OkamotoHiroshi TanakaArino YaguchiNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-8 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Yohei Hirano
Yutaka Kondo
Toru Hifumi
Shoji Yokobori
Jun Kanda
Junya Shimazaki
Kei Hayashida
Takashi Moriya
Masaharu Yagi
Shuhei Takauji
Junko Yamaguchi
Yohei Okada
Yuichi Okano
Hitoshi Kaneko
Tatsuho Kobayashi
Motoki Fujita
Hiroyuki Yokota
Ken Okamoto
Hiroshi Tanaka
Arino Yaguchi
Machine learning-based mortality prediction model for heat-related illness
description Abstract In this study, we aimed to develop and validate a machine learning-based mortality prediction model for hospitalized heat-related illness patients. After 2393 hospitalized patients were extracted from a multicentered heat-related illness registry in Japan, subjects were divided into the training set for development (n = 1516, data from 2014, 2017–2019) and the test set (n = 877, data from 2020) for validation. Twenty-four variables including characteristics of patients, vital signs, and laboratory test data at hospital arrival were trained as predictor features for machine learning. The outcome was death during hospital stay. In validation, the developed machine learning models (logistic regression, support vector machine, random forest, XGBoost) demonstrated favorable performance for outcome prediction with significantly increased values of the area under the precision-recall curve (AUPR) of 0.415 [95% confidence interval (CI) 0.336–0.494], 0.395 [CI 0.318–0.472], 0.426 [CI 0.346–0.506], and 0.528 [CI 0.442–0.614], respectively, compared to that of the conventional acute physiology and chronic health evaluation (APACHE)-II score of 0.287 [CI 0.222–0.351] as a reference standard. The area under the receiver operating characteristic curve (AUROC) values were also high over 0.92 in all models, although there were no statistical differences compared to APACHE-II. This is the first demonstration of the potential of machine learning-based mortality prediction models for heat-related illnesses.
format article
author Yohei Hirano
Yutaka Kondo
Toru Hifumi
Shoji Yokobori
Jun Kanda
Junya Shimazaki
Kei Hayashida
Takashi Moriya
Masaharu Yagi
Shuhei Takauji
Junko Yamaguchi
Yohei Okada
Yuichi Okano
Hitoshi Kaneko
Tatsuho Kobayashi
Motoki Fujita
Hiroyuki Yokota
Ken Okamoto
Hiroshi Tanaka
Arino Yaguchi
author_facet Yohei Hirano
Yutaka Kondo
Toru Hifumi
Shoji Yokobori
Jun Kanda
Junya Shimazaki
Kei Hayashida
Takashi Moriya
Masaharu Yagi
Shuhei Takauji
Junko Yamaguchi
Yohei Okada
Yuichi Okano
Hitoshi Kaneko
Tatsuho Kobayashi
Motoki Fujita
Hiroyuki Yokota
Ken Okamoto
Hiroshi Tanaka
Arino Yaguchi
author_sort Yohei Hirano
title Machine learning-based mortality prediction model for heat-related illness
title_short Machine learning-based mortality prediction model for heat-related illness
title_full Machine learning-based mortality prediction model for heat-related illness
title_fullStr Machine learning-based mortality prediction model for heat-related illness
title_full_unstemmed Machine learning-based mortality prediction model for heat-related illness
title_sort machine learning-based mortality prediction model for heat-related illness
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/a339b3e4021e4bf29780ed3e55dd3c72
work_keys_str_mv AT yoheihirano machinelearningbasedmortalitypredictionmodelforheatrelatedillness
AT yutakakondo machinelearningbasedmortalitypredictionmodelforheatrelatedillness
AT toruhifumi machinelearningbasedmortalitypredictionmodelforheatrelatedillness
AT shojiyokobori machinelearningbasedmortalitypredictionmodelforheatrelatedillness
AT junkanda machinelearningbasedmortalitypredictionmodelforheatrelatedillness
AT junyashimazaki machinelearningbasedmortalitypredictionmodelforheatrelatedillness
AT keihayashida machinelearningbasedmortalitypredictionmodelforheatrelatedillness
AT takashimoriya machinelearningbasedmortalitypredictionmodelforheatrelatedillness
AT masaharuyagi machinelearningbasedmortalitypredictionmodelforheatrelatedillness
AT shuheitakauji machinelearningbasedmortalitypredictionmodelforheatrelatedillness
AT junkoyamaguchi machinelearningbasedmortalitypredictionmodelforheatrelatedillness
AT yoheiokada machinelearningbasedmortalitypredictionmodelforheatrelatedillness
AT yuichiokano machinelearningbasedmortalitypredictionmodelforheatrelatedillness
AT hitoshikaneko machinelearningbasedmortalitypredictionmodelforheatrelatedillness
AT tatsuhokobayashi machinelearningbasedmortalitypredictionmodelforheatrelatedillness
AT motokifujita machinelearningbasedmortalitypredictionmodelforheatrelatedillness
AT hiroyukiyokota machinelearningbasedmortalitypredictionmodelforheatrelatedillness
AT kenokamoto machinelearningbasedmortalitypredictionmodelforheatrelatedillness
AT hiroshitanaka machinelearningbasedmortalitypredictionmodelforheatrelatedillness
AT arinoyaguchi machinelearningbasedmortalitypredictionmodelforheatrelatedillness
_version_ 1718386190297595904