Cargando…

Predicting the COVID‐19 mortality among Iranian patients using tree‐based models: A cross‐sectional study

BACKGROUND AND AIMS: To explore the use of different machine learning models in prediction of COVID‐19 mortality in hospitalized patients. MATERIALS AND METHODS: A total of 44,112 patients from six academic hospitals who were admitted for COVID‐19 between March 2020 and August 2021 were included in...

Descripción completa

Detalles Bibliográficos
Autores principales: Aghakhani, Amirhossein, Shoshtarian Malak, Jaleh, Karimi, Zahra, Vosoughi, Fardis, Zeraati, Hojjat, Yekaninejad, Mir Saeed
Formato: Online Artículo Texto
Lenguaje:English
Publicado: John Wiley and Sons Inc. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10200963/
https://www.ncbi.nlm.nih.gov/pubmed/37223657
http://dx.doi.org/10.1002/hsr2.1279
_version_ 1785045165853900800
author Aghakhani, Amirhossein
Shoshtarian Malak, Jaleh
Karimi, Zahra
Vosoughi, Fardis
Zeraati, Hojjat
Yekaninejad, Mir Saeed
author_facet Aghakhani, Amirhossein
Shoshtarian Malak, Jaleh
Karimi, Zahra
Vosoughi, Fardis
Zeraati, Hojjat
Yekaninejad, Mir Saeed
author_sort Aghakhani, Amirhossein
collection PubMed
description BACKGROUND AND AIMS: To explore the use of different machine learning models in prediction of COVID‐19 mortality in hospitalized patients. MATERIALS AND METHODS: A total of 44,112 patients from six academic hospitals who were admitted for COVID‐19 between March 2020 and August 2021 were included in this study. Variables were obtained from their electronic medical records. Random forest‐recursive feature elimination was used to select key features. Decision tree, random forest, LightGBM, and XGBoost model were developed. Sensitivity, specificity, accuracy, F‐1 score, and receiver operating characteristic (ROC)‐AUC were used to compare the prediction performance of different models. RESULTS: Random forest‐recursive feature elimination selected following features to include in the prediction model: Age, sex, hypertension, malignancy, pneumonia, cardiac problem, cough, dyspnea, and respiratory system disease. XGBoost and LightGBM showed the best performance with an ROC‐AUC of 0.83 [0.822−0.842] and 0.83 [0.816−0.837] and sensitivity of 0.77. CONCLUSION: XGBoost, LightGBM, and random forest have a relatively high predictive performance in prediction of mortality in COVID‐19 patients and can be applied in hospital settings, however, future research are needed to externally confirm the validation of these models.
format Online
Article
Text
id pubmed-10200963
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher John Wiley and Sons Inc.
record_format MEDLINE/PubMed
spelling pubmed-102009632023-05-23 Predicting the COVID‐19 mortality among Iranian patients using tree‐based models: A cross‐sectional study Aghakhani, Amirhossein Shoshtarian Malak, Jaleh Karimi, Zahra Vosoughi, Fardis Zeraati, Hojjat Yekaninejad, Mir Saeed Health Sci Rep Original Research BACKGROUND AND AIMS: To explore the use of different machine learning models in prediction of COVID‐19 mortality in hospitalized patients. MATERIALS AND METHODS: A total of 44,112 patients from six academic hospitals who were admitted for COVID‐19 between March 2020 and August 2021 were included in this study. Variables were obtained from their electronic medical records. Random forest‐recursive feature elimination was used to select key features. Decision tree, random forest, LightGBM, and XGBoost model were developed. Sensitivity, specificity, accuracy, F‐1 score, and receiver operating characteristic (ROC)‐AUC were used to compare the prediction performance of different models. RESULTS: Random forest‐recursive feature elimination selected following features to include in the prediction model: Age, sex, hypertension, malignancy, pneumonia, cardiac problem, cough, dyspnea, and respiratory system disease. XGBoost and LightGBM showed the best performance with an ROC‐AUC of 0.83 [0.822−0.842] and 0.83 [0.816−0.837] and sensitivity of 0.77. CONCLUSION: XGBoost, LightGBM, and random forest have a relatively high predictive performance in prediction of mortality in COVID‐19 patients and can be applied in hospital settings, however, future research are needed to externally confirm the validation of these models. John Wiley and Sons Inc. 2023-05-21 /pmc/articles/PMC10200963/ /pubmed/37223657 http://dx.doi.org/10.1002/hsr2.1279 Text en © 2023 The Authors. Health Science Reports published by Wiley Periodicals LLC. https://creativecommons.org/licenses/by/4.0/This is an open access article under the terms of the http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
spellingShingle Original Research
Aghakhani, Amirhossein
Shoshtarian Malak, Jaleh
Karimi, Zahra
Vosoughi, Fardis
Zeraati, Hojjat
Yekaninejad, Mir Saeed
Predicting the COVID‐19 mortality among Iranian patients using tree‐based models: A cross‐sectional study
title Predicting the COVID‐19 mortality among Iranian patients using tree‐based models: A cross‐sectional study
title_full Predicting the COVID‐19 mortality among Iranian patients using tree‐based models: A cross‐sectional study
title_fullStr Predicting the COVID‐19 mortality among Iranian patients using tree‐based models: A cross‐sectional study
title_full_unstemmed Predicting the COVID‐19 mortality among Iranian patients using tree‐based models: A cross‐sectional study
title_short Predicting the COVID‐19 mortality among Iranian patients using tree‐based models: A cross‐sectional study
title_sort predicting the covid‐19 mortality among iranian patients using tree‐based models: a cross‐sectional study
topic Original Research
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10200963/
https://www.ncbi.nlm.nih.gov/pubmed/37223657
http://dx.doi.org/10.1002/hsr2.1279
work_keys_str_mv AT aghakhaniamirhossein predictingthecovid19mortalityamongiranianpatientsusingtreebasedmodelsacrosssectionalstudy
AT shoshtarianmalakjaleh predictingthecovid19mortalityamongiranianpatientsusingtreebasedmodelsacrosssectionalstudy
AT karimizahra predictingthecovid19mortalityamongiranianpatientsusingtreebasedmodelsacrosssectionalstudy
AT vosoughifardis predictingthecovid19mortalityamongiranianpatientsusingtreebasedmodelsacrosssectionalstudy
AT zeraatihojjat predictingthecovid19mortalityamongiranianpatientsusingtreebasedmodelsacrosssectionalstudy
AT yekaninejadmirsaeed predictingthecovid19mortalityamongiranianpatientsusingtreebasedmodelsacrosssectionalstudy