What does this research mean for the field?

A machine learning-based predictive model can accurately identify patients at risk of sepsis using routinely collected clinical data in real-world clinical settings in South Korea. Novelty: ClaimNovelty.NOVEL_FINDING. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

The aim is to create a machine learning model to predict sepsis risk using clinical and lab data.

February 28, 2026Open Access

Development of a machine learning–based sepsis prediction model for real-world clinical settings in South Korea: a single-center retrospective study

Key Points

The aim is to create a machine learning model to predict sepsis risk using clinical and lab data.
Analyzed electronic medical records from 22,400 adults with suspected infections.
Classified patients based on systemic inflammatory response syndrome and quick sequential organ failure assessment scores.
Trained and validated four machine learning models through five-fold cross-validation.
Applied Shapley additive explanations to understand predictive variable impacts.
CatBoost model showed the highest predictive performance.
Key predictors included platelet distribution width, alveolar–arterial oxygen difference, procalcitonin, and arterial/alveolar oxygen ratio.
Some variables with no significant univariate results still enhanced model accuracy, indicating complex interactions among factors.
The model demonstrated high accuracy and generalizability in predicting sepsis.

Abstract

Purpose: This study aimed to develop a predictive model for the early identification of patients at risk of sepsis, using routinely available clinical information and laboratory test results collected during the initial phase of patient care. Methods: This retrospective analysis included electronic medical records of 22,400 adult patients who presented with suspected infection to a tertiary care university hospital in Korea between January 2013 and May 2024. Patients were classified according to Systemic Inflammatory Response Syndrome (score ≥ 2) or Quick Sequential Organ Failure Assessment (score ≥ 2), in combination with sepsis-related International Classification of Diseases, 10th revision codes. Four different machine learning models were trained and validated using five-fold cross-validation. In addition, Shapley additive explanations analysis was performed to interpret the contribution and clinical relevance of key predictive variables. Results: Among the evaluated models, CatBoost demonstrated the strongest predictive performance. Notably, platelet distribution width, alveolar–arterial oxygen difference, procalcitonin, and the arterial/alveolar oxygen ratio consistently emerged as major predictors. Importantly, several variables that did not reach statistical significance in univariate analysis nevertheless contributed substantially to overall model performance, highlighting the importance of complex, multidimensional interactions among clinical factors. Conclusion: These findings indicate that a model based on simple, routinely collected clinical data can achieve high predictive accuracy and strong generalizability. Such a tool may support early clinical decision-making by multidisciplinary teams, including nurses, across diverse real-world care settings. Further prospective studies are warranted to validate its clinical utility and to assess its potential effects on patient outcomes.

AI से पूछें

Bookmark

View Full Paper