Establishment and validation of predictive model of ARDS in critically ill patients

Abstract Background Acute respiratory distress syndrome (ARDS) is a prevalent complication among critically ill patients, constituting around 10% of intensive care unit (ICU) admissions and mortality rates ranging from 35 to 46%. Hence, early recognition and prediction of ARDS are crucial for the ti...

Full description

Saved in:
Bibliographic Details
Main Authors: Senhao Wei, Hua Zhang, Hao Li, Chao Li, Ziyuan Shen, Yiyuan Yin, Zhukai Cong, Zhaojin Zeng, Qinggang Ge, Dongfeng Li, Xi Zhu
Format: Article
Language:English
Published: BMC 2025-01-01
Series:Journal of Translational Medicine
Subjects:
Online Access:https://doi.org/10.1186/s12967-024-06054-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832594465401864192
author Senhao Wei
Hua Zhang
Hao Li
Chao Li
Ziyuan Shen
Yiyuan Yin
Zhukai Cong
Zhaojin Zeng
Qinggang Ge
Dongfeng Li
Xi Zhu
author_facet Senhao Wei
Hua Zhang
Hao Li
Chao Li
Ziyuan Shen
Yiyuan Yin
Zhukai Cong
Zhaojin Zeng
Qinggang Ge
Dongfeng Li
Xi Zhu
author_sort Senhao Wei
collection DOAJ
description Abstract Background Acute respiratory distress syndrome (ARDS) is a prevalent complication among critically ill patients, constituting around 10% of intensive care unit (ICU) admissions and mortality rates ranging from 35 to 46%. Hence, early recognition and prediction of ARDS are crucial for the timely administration of targeted treatment. However, ARDS is frequently underdiagnosed or delayed, and its heterogeneity diminishes the clinical utility of ARDS biomarkers. This study aimed to observe the incidence of ARDS among high-risk patients and develop and validate an ARDS prediction model using machine learning (ML) techniques based on clinical parameters. Methods This prospective cohort study in China was conducted on critically ill patients to derivate and validate the prediction model. The derivation cohort, consisting of 400 patients admitted to the ICU of the Peking University Third Hospital(PUTH) between December 2020 and August 2023, was separated for training and internal validation, and an external data set of 160 patients at the FU YANG People's Hospital from August 2022 to August 2023 was employed for external validation. Least absolute shrinkage and selection operator (LASSO) and multivariate logistic regression were used to screen predictor variables. Multiple ML classification models were integrated to analyze and identify the best models. Several evaluation indexes were used to compare the model performance, including the area under the receiver-operating-characteristic curve (AUC) and decision curve analysis (DCA). SHapley Additive ex Planations (SHAP) is used to interpret ML models. Results 400 critically ill patients were included in the analysis, with 117 developing ARDS during follow-up. The final model included gender, Lung Injury Prediction Score (LIPS), Hepatic Disease, Shock, and combined Lung Contusion. Based on the AUC and DCA in the validation group, the logistic model demonstrated excellent performance, achieving an AUC of 0.836 (95% CI: 0.762–0.910). For external validation, comprising 160 patients, 44 of whom developed ARDS, the AUC was 0.799 (95% CI: 0.723–0.875), significantly outperforming the LIPS score alone. Conclusion Combining the LIPS score with other clinical parameters in a logistic regression model provides a more accurate, clinically applicable, and user-friendly ARDS prediction tool than the LIPS score alone.
format Article
id doaj-art-282fb4f7386d42bbbba88ddd45fcff14
institution Kabale University
issn 1479-5876
language English
publishDate 2025-01-01
publisher BMC
record_format Article
series Journal of Translational Medicine
spelling doaj-art-282fb4f7386d42bbbba88ddd45fcff142025-01-19T12:37:29ZengBMCJournal of Translational Medicine1479-58762025-01-0123111210.1186/s12967-024-06054-1Establishment and validation of predictive model of ARDS in critically ill patientsSenhao Wei0Hua Zhang1Hao Li2Chao Li3Ziyuan Shen4Yiyuan Yin5Zhukai Cong6Zhaojin Zeng7Qinggang Ge8Dongfeng Li9Xi Zhu10Department of Critical Care Medicine, Peking University Third HospitalClinical Epidemiology Research Center, Peking University Third HospitalDepartment of Critical Care Medicine, Fuyang People’s HospitalDepartment of Critical Care Medicine, Peking University Third HospitalDepartment of Critical Care Medicine, Peking University Third HospitalDepartment of Critical Care Medicine, Peking University Third HospitalDepartment of Critical Care Medicine, Peking University Third HospitalDepartment of Critical Care Medicine, Peking University Third HospitalDepartment of Critical Care Medicine, Peking University Third HospitalDepartment of Critical Care Medicine, Fuyang People’s HospitalDepartment of Critical Care Medicine, Peking University Third HospitalAbstract Background Acute respiratory distress syndrome (ARDS) is a prevalent complication among critically ill patients, constituting around 10% of intensive care unit (ICU) admissions and mortality rates ranging from 35 to 46%. Hence, early recognition and prediction of ARDS are crucial for the timely administration of targeted treatment. However, ARDS is frequently underdiagnosed or delayed, and its heterogeneity diminishes the clinical utility of ARDS biomarkers. This study aimed to observe the incidence of ARDS among high-risk patients and develop and validate an ARDS prediction model using machine learning (ML) techniques based on clinical parameters. Methods This prospective cohort study in China was conducted on critically ill patients to derivate and validate the prediction model. The derivation cohort, consisting of 400 patients admitted to the ICU of the Peking University Third Hospital(PUTH) between December 2020 and August 2023, was separated for training and internal validation, and an external data set of 160 patients at the FU YANG People's Hospital from August 2022 to August 2023 was employed for external validation. Least absolute shrinkage and selection operator (LASSO) and multivariate logistic regression were used to screen predictor variables. Multiple ML classification models were integrated to analyze and identify the best models. Several evaluation indexes were used to compare the model performance, including the area under the receiver-operating-characteristic curve (AUC) and decision curve analysis (DCA). SHapley Additive ex Planations (SHAP) is used to interpret ML models. Results 400 critically ill patients were included in the analysis, with 117 developing ARDS during follow-up. The final model included gender, Lung Injury Prediction Score (LIPS), Hepatic Disease, Shock, and combined Lung Contusion. Based on the AUC and DCA in the validation group, the logistic model demonstrated excellent performance, achieving an AUC of 0.836 (95% CI: 0.762–0.910). For external validation, comprising 160 patients, 44 of whom developed ARDS, the AUC was 0.799 (95% CI: 0.723–0.875), significantly outperforming the LIPS score alone. Conclusion Combining the LIPS score with other clinical parameters in a logistic regression model provides a more accurate, clinically applicable, and user-friendly ARDS prediction tool than the LIPS score alone.https://doi.org/10.1186/s12967-024-06054-1ARDSLung injury prediction scorePrediction modelIntensive care unit
spellingShingle Senhao Wei
Hua Zhang
Hao Li
Chao Li
Ziyuan Shen
Yiyuan Yin
Zhukai Cong
Zhaojin Zeng
Qinggang Ge
Dongfeng Li
Xi Zhu
Establishment and validation of predictive model of ARDS in critically ill patients
Journal of Translational Medicine
ARDS
Lung injury prediction score
Prediction model
Intensive care unit
title Establishment and validation of predictive model of ARDS in critically ill patients
title_full Establishment and validation of predictive model of ARDS in critically ill patients
title_fullStr Establishment and validation of predictive model of ARDS in critically ill patients
title_full_unstemmed Establishment and validation of predictive model of ARDS in critically ill patients
title_short Establishment and validation of predictive model of ARDS in critically ill patients
title_sort establishment and validation of predictive model of ards in critically ill patients
topic ARDS
Lung injury prediction score
Prediction model
Intensive care unit
url https://doi.org/10.1186/s12967-024-06054-1
work_keys_str_mv AT senhaowei establishmentandvalidationofpredictivemodelofardsincriticallyillpatients
AT huazhang establishmentandvalidationofpredictivemodelofardsincriticallyillpatients
AT haoli establishmentandvalidationofpredictivemodelofardsincriticallyillpatients
AT chaoli establishmentandvalidationofpredictivemodelofardsincriticallyillpatients
AT ziyuanshen establishmentandvalidationofpredictivemodelofardsincriticallyillpatients
AT yiyuanyin establishmentandvalidationofpredictivemodelofardsincriticallyillpatients
AT zhukaicong establishmentandvalidationofpredictivemodelofardsincriticallyillpatients
AT zhaojinzeng establishmentandvalidationofpredictivemodelofardsincriticallyillpatients
AT qinggangge establishmentandvalidationofpredictivemodelofardsincriticallyillpatients
AT dongfengli establishmentandvalidationofpredictivemodelofardsincriticallyillpatients
AT xizhu establishmentandvalidationofpredictivemodelofardsincriticallyillpatients