Development and multicenter validation of a machine learning model for postoperative sepsis risk in…

AI / informaticsInjury· Feb 2026

Development and multicenter validation of a machine learning model for postoperative sepsis risk in critically Ill traumatic spinal injury patients.

Yixi Wang, Wenzhe Li, Jian Cui … Yuqian Li

Surgical Critical CareAI / informaticsQ1IF 2.3

Stacking machine learning model predicts postoperative sepsis after traumatic spinal injury surgery

Development and multicenter validation of a machine learning model for postoperative sepsis risk in critically Ill traumatic spinal injury patients.

Yixi Wang … Yuqian Li

Injury · Feb 2026 · Q1 in Surgery

Purpose

To develop and validate a machine learning model for postoperative sepsis in critically ill traumatic spinal injury (traumatic spinal injury) patients, a frequent and severe complication without dedicated predictive tools.

Methods

Model development used the MIMIC-IV 3.1 database, with external validation in the eICU-CRD 2.0 database and a Chinese traumatic spinal injury cohort.

n = 808 patients

Results

AUROC, 1.0 is perfect prediction, model discriminates sepsis risk very well

0.918AUC

Training

0.889AUC

Validation

More results

The development cohort comprised 808 patients, with 461 (57.1 %) sepsis cases, and the external validation cohort consisted of 358 patients, with 86 (24.0 %) events.

External validation confirmed consistent performance and effective high-risk stratification.

“

Conclusion

This first validated model for postoperative sepsis in critically ill traumatic spinal injury patients shows relatively robust performance and interpretability, enabling early risk stratification and supporting clinical decision-making.

Development and multicenter validation of a machine learning model for postoperative sepsis risk in critically Ill traumatic spinal injury patients.

Development and multicenter validation of a machine learning model for postoperative sepsis risk in critically Ill traumatic spinal injury patients.

Related papers