Cargando…

Developing an Interpretable Machine Learning Model to Predict in-Hospital Mortality in Sepsis Patients: A Retrospective Temporal Validation Study

Background: Risk stratification plays an essential role in the decision making for sepsis management, as existing approaches can hardly satisfy the need to assess this heterogeneous population. We aimed to develop and validate a machine learning model to predict in-hospital mortality in critically i...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Shuhe, Dou, Ruoxu, Song, Xiaodong, Lui, Ka Yin, Xu, Jinghong, Guo, Zilu, Hu, Xiaoguang, Guan, Xiangdong, Cai, Changjie
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9917524/
https://www.ncbi.nlm.nih.gov/pubmed/36769564
http://dx.doi.org/10.3390/jcm12030915
_version_ 1784886387629096960
author Li, Shuhe
Dou, Ruoxu
Song, Xiaodong
Lui, Ka Yin
Xu, Jinghong
Guo, Zilu
Hu, Xiaoguang
Guan, Xiangdong
Cai, Changjie
author_facet Li, Shuhe
Dou, Ruoxu
Song, Xiaodong
Lui, Ka Yin
Xu, Jinghong
Guo, Zilu
Hu, Xiaoguang
Guan, Xiangdong
Cai, Changjie
author_sort Li, Shuhe
collection PubMed
description Background: Risk stratification plays an essential role in the decision making for sepsis management, as existing approaches can hardly satisfy the need to assess this heterogeneous population. We aimed to develop and validate a machine learning model to predict in-hospital mortality in critically ill patients with sepsis. Methods: Adult patients fulfilling the definition of Sepsis-3 were included at a large tertiary medical center. Relevant clinical features were extracted within the first 24 h in ICU, re-classified into different genres, and utilized for model development under three strategies: “Basic + Lab”, “Basic + Intervention”, and “Whole” feature sets. Extreme gradient boosting (XGBoost) was compared with logistic regression (LR) and established severity scores. Temporal validation was conducted using admissions from 2017 to 2019. Results: The final cohort included 24,272 patients, of which 4013 patients formed the test cohort for temporal validation. The trained and fine-tuned XGBoost model with the whole feature set showed the best discriminatory ability in the test cohort with AUROC as 0.85, significantly higher than the XGBoost “Basic + Lab” model (0.83), the LR “Whole” model (0.82), SOFA (0.63), SAPS-II (0.73), and LODS score (0.74). The performance in varying subgroups remained robust, and predictors, such as increased urine output and supplemental oxygen therapy, were crucially correlated with improved survival when interpretability was explored. Conclusions: We developed and validated a novel XGBoost-based model and demonstrated significantly improved performance to LR and other scores in predicting the mortality risks of sepsis patients in the hospital using features in the first 24 h.
format Online
Article
Text
id pubmed-9917524
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-99175242023-02-11 Developing an Interpretable Machine Learning Model to Predict in-Hospital Mortality in Sepsis Patients: A Retrospective Temporal Validation Study Li, Shuhe Dou, Ruoxu Song, Xiaodong Lui, Ka Yin Xu, Jinghong Guo, Zilu Hu, Xiaoguang Guan, Xiangdong Cai, Changjie J Clin Med Article Background: Risk stratification plays an essential role in the decision making for sepsis management, as existing approaches can hardly satisfy the need to assess this heterogeneous population. We aimed to develop and validate a machine learning model to predict in-hospital mortality in critically ill patients with sepsis. Methods: Adult patients fulfilling the definition of Sepsis-3 were included at a large tertiary medical center. Relevant clinical features were extracted within the first 24 h in ICU, re-classified into different genres, and utilized for model development under three strategies: “Basic + Lab”, “Basic + Intervention”, and “Whole” feature sets. Extreme gradient boosting (XGBoost) was compared with logistic regression (LR) and established severity scores. Temporal validation was conducted using admissions from 2017 to 2019. Results: The final cohort included 24,272 patients, of which 4013 patients formed the test cohort for temporal validation. The trained and fine-tuned XGBoost model with the whole feature set showed the best discriminatory ability in the test cohort with AUROC as 0.85, significantly higher than the XGBoost “Basic + Lab” model (0.83), the LR “Whole” model (0.82), SOFA (0.63), SAPS-II (0.73), and LODS score (0.74). The performance in varying subgroups remained robust, and predictors, such as increased urine output and supplemental oxygen therapy, were crucially correlated with improved survival when interpretability was explored. Conclusions: We developed and validated a novel XGBoost-based model and demonstrated significantly improved performance to LR and other scores in predicting the mortality risks of sepsis patients in the hospital using features in the first 24 h. MDPI 2023-01-24 /pmc/articles/PMC9917524/ /pubmed/36769564 http://dx.doi.org/10.3390/jcm12030915 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Li, Shuhe
Dou, Ruoxu
Song, Xiaodong
Lui, Ka Yin
Xu, Jinghong
Guo, Zilu
Hu, Xiaoguang
Guan, Xiangdong
Cai, Changjie
Developing an Interpretable Machine Learning Model to Predict in-Hospital Mortality in Sepsis Patients: A Retrospective Temporal Validation Study
title Developing an Interpretable Machine Learning Model to Predict in-Hospital Mortality in Sepsis Patients: A Retrospective Temporal Validation Study
title_full Developing an Interpretable Machine Learning Model to Predict in-Hospital Mortality in Sepsis Patients: A Retrospective Temporal Validation Study
title_fullStr Developing an Interpretable Machine Learning Model to Predict in-Hospital Mortality in Sepsis Patients: A Retrospective Temporal Validation Study
title_full_unstemmed Developing an Interpretable Machine Learning Model to Predict in-Hospital Mortality in Sepsis Patients: A Retrospective Temporal Validation Study
title_short Developing an Interpretable Machine Learning Model to Predict in-Hospital Mortality in Sepsis Patients: A Retrospective Temporal Validation Study
title_sort developing an interpretable machine learning model to predict in-hospital mortality in sepsis patients: a retrospective temporal validation study
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9917524/
https://www.ncbi.nlm.nih.gov/pubmed/36769564
http://dx.doi.org/10.3390/jcm12030915
work_keys_str_mv AT lishuhe developinganinterpretablemachinelearningmodeltopredictinhospitalmortalityinsepsispatientsaretrospectivetemporalvalidationstudy
AT douruoxu developinganinterpretablemachinelearningmodeltopredictinhospitalmortalityinsepsispatientsaretrospectivetemporalvalidationstudy
AT songxiaodong developinganinterpretablemachinelearningmodeltopredictinhospitalmortalityinsepsispatientsaretrospectivetemporalvalidationstudy
AT luikayin developinganinterpretablemachinelearningmodeltopredictinhospitalmortalityinsepsispatientsaretrospectivetemporalvalidationstudy
AT xujinghong developinganinterpretablemachinelearningmodeltopredictinhospitalmortalityinsepsispatientsaretrospectivetemporalvalidationstudy
AT guozilu developinganinterpretablemachinelearningmodeltopredictinhospitalmortalityinsepsispatientsaretrospectivetemporalvalidationstudy
AT huxiaoguang developinganinterpretablemachinelearningmodeltopredictinhospitalmortalityinsepsispatientsaretrospectivetemporalvalidationstudy
AT guanxiangdong developinganinterpretablemachinelearningmodeltopredictinhospitalmortalityinsepsispatientsaretrospectivetemporalvalidationstudy
AT caichangjie developinganinterpretablemachinelearningmodeltopredictinhospitalmortalityinsepsispatientsaretrospectivetemporalvalidationstudy