Key result
A Random Forest machine learning model outperformed the clinical GiS-FI score in predicting 30-day mortality after gastrointestinal cancer surgery in the elderly (AUC 0.822, 95% CI 0.714-0.931).
Why the study?
Frailty in the elderly increases vulnerability to surgical stressors, motivating a comparison between machine learning models and the clinical bedside GiS-FI tool for predicting postoperative mortality and morbidity.
Do machine learning models improve the prediction of 30-day mortality and morbidity compared to the GiS-FI clinical bedside tool in elderly patients undergoing gastrointestinal cancer surgery?
Observational (n=937)
Yes
Do machine learning models improve the prediction of 30-day mortality and morbidity compared to the GiS-FI clinical bedside tool in elderly patients undergoing gastrointestinal cancer surgery?
Effect estimate: AUC 0.822 (95% CI 0.714-0.931)
Machine learning approaches, particularly the Random Forest algorithm, offer enhanced predictive accuracy compared to traditional clinical scores for 30-day mortality risk assessment in elderly cancer patients undergoing gastrointestinal surgery.
ML models may enhance preoperative risk stratification in elderly GI cancer surgery patients; leaves open prospective validation before clinical adoption.
Frailty in the elderly population is associated with increased vulnerability to stressors, including surgical interventions. This study compared machine learning (ML) models with a clinical bedside tool, the Gastrointestinal Surgery Frailty Index (GiS-FI), for predicting mortality and morbidity in elderly patients undergoing gastrointestinal cancer surgery. In a multicenter analysis of 937 patients aged ≥65 years, the performance of various predictive models including Random Forest (RF), Least Absolute Shrinkage and Selection Operator (LASSO), Stepwise Regression, K-Nearest Neighbors, Neural Network, and Support Vector Machine algorithms were evaluated. The overall 30-day mortality and morbidity rates were 6.1% and 35.7%, respectively. For mortality prediction, the RF model demonstrated superior performance with an AUC of 0.822 (95% CI 0.714-0.931), outperforming the GiS-FI score (AUC = 0.772, 95% CI 0.675-0.868). For morbidity prediction, all models showed more modest discrimination, with stepwise regression and LASSO regression achieving the highest performance (AUCs of 0.652 and 0.647, respectively). Our findings suggest that ML approaches, particularly RF algorithm, offer enhanced predictive accuracy compared to traditional clinical scores for mortality risk assessment in elderly cancer patients undergoing gastrointestinal surgery. These advanced analytical tools could provide valuable decision support for surgical risk stratification in this vulnerable population.
No takes yet. Share an insight, caveat, or question.
Frezza et al. (2025) conducted an observational in Gastrointestinal cancer (n=937). Machine learning models (Random Forest) vs. Gastrointestinal Surgery Frailty Index (GiS-FI) was evaluated on 30-day mortality (AUC 0.822, 95% CI 0.714-0.931). A Random Forest machine learning model outperformed the clinical GiS-FI score in predicting 30-day mortality after gastrointestinal cancer surgery in the elderly (AUC 0.822, 95% CI 0.714-0.931).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: