Machine learning-based prediction of adverse events following colorectal resection to guide optimal surgeon-hospital selection

BACKGROUND: Post-colectomy adverse events occur in up to one third of patients. We used machine learning (ML) models to predict complications and inform optimal surgeon–hospital assignment.

STUDY DESIGN: Adults ≥18 undergoing colon or rectal resection in an academic system from 2018 to 2024 were included. Multiple ML algorithms trained on patient and provider features predicted postoperative complications. Model performance was compared by the scaled Brier score. Patients were simulated to their optimal surgeon-hospital dyad to estimate risk reduction.

RESULTS: Among 4689 cases, 1562 (33.3%) experienced ≥1 adverse event. LightGBM outperformed alternate ML models (p < 0.05). LightGBM achieved a scaled Brier score of 0.11 (95% CI 0.08–0.16). Top predictors included pre-operative diagnosis, surgeon identifier, and ostomy. Simulations suggested a 4.6% (CI 4.2-4.9%) net absolute complication risk reduction and 6.9% (CI 6.5-7.3%) reduction with reassignment to an optimal surgeon–hospital dyad.

CONCLUSIONS: ML models could enable a proactive referral strategy to promote optimal surgical outcomes.

• Machine learning models predicted post-colectomy adverse events using preoperative data.
• Simulations suggested these tools could reduce complication risk by up to 6.9%.
• Machine learning models can provide surgeon-hospital assignments optimized on patient outcomes.

Drew W Goldberg, Charles C Horn, Isaac J Perron, J Walker Rosenthal, Gary E Weissman, Rachel R Kelz