What is the clinical evidence from this study?

Study design: Cohort. Population: Surgical intensive care unit (SICU) readmission (n=982). Intervention: Gradient Boosting machine-learning model vs. Traditional logistic regression methods. Primary outcome: Prediction of SICU readmission (AUROC) (AUROC 0.80, 95% CI 0.73-0.86).

What question did this study set out to answer?

The study aims to create a machine learning model to predict readmission to the surgical intensive care unit.

February 28, 2026

Predicting surgical intensive care unit readmission with machine learning model: Bi-center training and validation

Key Result

A Gradient Boosting model outperformed traditional logistic regression in predicting SICU readmission, achieving an AUROC of 0.80 (95% CI: 0.73-0.86) in external validation.

Key Points

The study aims to create a machine learning model to predict readmission to the surgical intensive care unit.
Retrospective analysis using electronic healthcare records from two hospitals.
Comparison of various machine learning models including logistic regression, gradient boosting, and others.
Development cohort included 982 patients admitted to SICU; external validation conducted with additional patient data.
The gradient boosting model showed an AUROC of 0.82 (95% CI: 0.70-0.93) for predicting SICU readmission in internal validation.
Sixty-eight patients (6.9%) in the development cohort experienced SICU readmission.
The gradient boosting model outperformed traditional regression methods, achieving AUROCs of 0.80, 0.73, 0.70, and 0.65 in external validation.

Study Design

Type

Cohort (n=982)

Multicenter

Yes

Structured PICO

Do machine learning models improve the prediction of surgical intensive care unit readmission compared to traditional regression methods in adult SICU patients?

Population

Adult patients admitted to the surgical intensive care unit (SICU), n=982 in the development cohort.

Intervention

Machine learning models (Gradient Boosting, Logistic Regression, Random Forest, Artificial Neural Networks, Support Vector Machines) to predict SICU readmission

Comparator

Previously published traditional logistic regression methods

Outcome

Prediction of SICU readmission (measured by AUROC)

A Gradient Boosting machine learning model accurately predicts surgical ICU readmission, outperforming traditional logistic regression methods.

Main Result

Effect estimate: AUROC 0.80 (95% CI 0.73-0.86)

Abstract

BACKGROUND Patients readmitted to the surgical intensive care unit (SICU) face a high risk of mortality and increased hospital costs. Identifying patients at risk of SICU readmission is crucial. This study aims to develop a machine-learning (ML) model to predict SICU readmission. METHODS This is a retrospective study based on data collected from the electronic healthcare records of Chang Gung Memorial Hospital. The model development cohort included adult patients admitted to the SICU from July 2020 to December 2022 at the Kaohsiung branch, while the external validation cohort consisted of patients admitted to the SICU from January 2023 to August 2023 at the Linkou branch. Various ML models, including Logistic Regression (LR), Random Forest, Gradient Boosting (GB), Artificial Neural Networks, and Support Vector Machines, were compared to determine the best model. RESULTS Of the 982 patients in the development cohorts, 68 (6.9%) experienced SICU readmission. The GB model outperformed other methods, achieving an AUROC of 0.82 (95% CI: 0.70-0.93) in the internal validation cohort. Eleven features significantly influence SICU readmission, with the central venous catheter usage days, the pre-ICU stay duration, blood urea nitrogen, and carbapenem usage days ranking as the top four important factors. The GB model also surpasses three previously published traditional logistic regression methods in the external validation cohort, with AUROCs of 0.80 (95% CI: 0.73-0.86), 0.73 (95% CI: 0.63-0.83), 0.70 (95% CI: 0.60-0.79), and 0.65 (95% CI: 0.50-0.73), respectively. CONCLUSION Machine learning models offer greater accuracy and reliability compared to traditional regression methods when predicting SICU readmission.

Bookmark