Jinyu Peng , Yun Li , Chao Liu , Zhi Mao , Hongjun Kang , Feihu Zhou
{"title":"Predicting multiple organ dysfunction syndrome in trauma-induced sepsis: Nomogram and machine learning approaches","authors":"Jinyu Peng , Yun Li , Chao Liu , Zhi Mao , Hongjun Kang , Feihu Zhou","doi":"10.1016/j.jointm.2024.12.008","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>Multiple organ dysfunction syndrome (MODS) is a critical complication in trauma-induced sepsis patients and is associated with a high mortality rate. This study aimed to develop and validate predictive models for MODS in this patient population using a nomogram and machine learning approaches.</div></div><div><h3>Methods</h3><div>This retrospective cohort study utilized data from the Medical Information Mart for Intensive Care-IV 2.2 database, focusing on trauma patients diagnosed with sepsis within the first day of intensive care unit (ICU) admission. Predictive variables were extracted from the initial 24 h of ICU data. The dataset (2008–2019) was divided into a training set (2008–2016) and a temporal validation set (2017–2019). Feature selection was conducted using the Boruta algorithm. Predictive models were developed and validated using a nomogram and various machine learning techniques. Model performance was evaluated based on discrimination, calibration, and decision curve analysis.</div></div><div><h3>Results</h3><div>Among 1295 trauma patients with sepsis, 349 (26.95%) developed MODS. The 28-day mortality rates were 11.21% for non-MODS patients and 23.82% for MODS patients. Key predictors of MODS included the simplified acute physiology score II score, use of mechanical ventilation, and vasopressor administration. In temporal validation, all models significantly outperformed traditional scoring systems (all <em>P</em> <0.05). The nomogram achieved an area under the curve (AUC) of 0.757 (95% confidence interval [CI]: 0.700 to 0.814), while the random forest model demonstrated the highest performance with an AUC of 0.769 (95% CI: 0.712 to 0.826). Calibration plots showed excellent agreement between predicted and observed probabilities, and decision curve analysis indicated a consistently higher net benefit for the newly developed models.</div></div><div><h3>Conclusion</h3><div>The nomogram and machine learning models provide enhanced predictive accuracy for MODS in trauma-induced sepsis patients compared to traditional scoring systems. These tools, accessible via web-based applications, have the potential to improve early risk stratification and guide clinical decision-making, ultimately enhancing outcomes for trauma patients. Further external validation is recommended to confirm their generalizability.</div></div>","PeriodicalId":73799,"journal":{"name":"Journal of intensive medicine","volume":"5 2","pages":"Pages 193-201"},"PeriodicalIF":0.0000,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of intensive medicine","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2667100X25000027","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Background
Multiple organ dysfunction syndrome (MODS) is a critical complication in trauma-induced sepsis patients and is associated with a high mortality rate. This study aimed to develop and validate predictive models for MODS in this patient population using a nomogram and machine learning approaches.
Methods
This retrospective cohort study utilized data from the Medical Information Mart for Intensive Care-IV 2.2 database, focusing on trauma patients diagnosed with sepsis within the first day of intensive care unit (ICU) admission. Predictive variables were extracted from the initial 24 h of ICU data. The dataset (2008–2019) was divided into a training set (2008–2016) and a temporal validation set (2017–2019). Feature selection was conducted using the Boruta algorithm. Predictive models were developed and validated using a nomogram and various machine learning techniques. Model performance was evaluated based on discrimination, calibration, and decision curve analysis.
Results
Among 1295 trauma patients with sepsis, 349 (26.95%) developed MODS. The 28-day mortality rates were 11.21% for non-MODS patients and 23.82% for MODS patients. Key predictors of MODS included the simplified acute physiology score II score, use of mechanical ventilation, and vasopressor administration. In temporal validation, all models significantly outperformed traditional scoring systems (all P <0.05). The nomogram achieved an area under the curve (AUC) of 0.757 (95% confidence interval [CI]: 0.700 to 0.814), while the random forest model demonstrated the highest performance with an AUC of 0.769 (95% CI: 0.712 to 0.826). Calibration plots showed excellent agreement between predicted and observed probabilities, and decision curve analysis indicated a consistently higher net benefit for the newly developed models.
Conclusion
The nomogram and machine learning models provide enhanced predictive accuracy for MODS in trauma-induced sepsis patients compared to traditional scoring systems. These tools, accessible via web-based applications, have the potential to improve early risk stratification and guide clinical decision-making, ultimately enhancing outcomes for trauma patients. Further external validation is recommended to confirm their generalizability.