Improving Surgical Risk Prediction Through Integrating Automated Body Composition Analysis: a Retrospective Trial on Colectomy Surgery

2025-06-13

AI Summary

Preoperative body composition assessment from CT remains underutilized for predicting long-term outcomes after colon surgery. Method: We developed a deep learning–based CT segmentation and quantification pipeline to automatically extract >300 muscle and adipose tissue features—including cross-sectional area, radiodensity (Hounsfield units), and visceral-to-subcutaneous fat ratio—at the L3 vertebral level. These imaging biomarkers were integrated with clinical variables and the ACS-NSQIP risk score to build Cox proportional hazards and logistic regression models for 1-year all-cause mortality and postoperative complications. Contribution/Results: This is the first systematic validation of automated, multi-feature body composition analysis for incremental prognostic value in colon surgery. L3 skeletal muscle radiodensity emerged as a significant independent predictor of mortality (HR = 0.62, p < 0.001). The combined model improved the C-index for 1-year mortality to 0.78 (+0.06 over NSQIP alone) and achieved an AUC of 0.82 for complication prediction. Findings demonstrate that quantitative CT-derived biomarkers substantially enhance conventional risk stratification.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Segmentation
• Search and Optimization: Evaluation and Analysis

Application Category

• Security and Privacy: Large-scale security measurements
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Objective: To evaluate whether preoperative body composition metrics automatically extracted from CT scans can predict postoperative outcomes after colectomy, either alone or combined with clinical variables or existing risk predictors. Main outcomes and measures: The primary outcome was the predictive performance for 1-year all-cause mortality following colectomy. A Cox proportional hazards model with 1-year follow-up was used, and performance was evaluated using the concordance index (C-index) and Integrated Brier Score (IBS). Secondary outcomes included postoperative complications, unplanned readmission, blood transfusion, and severe infection, assessed using AUC and Brier Score from logistic regression. Odds ratios (OR) described associations between individual CT-derived body composition metrics and outcomes. Over 300 features were extracted from preoperative CTs across multiple vertebral levels, including skeletal muscle area, density, fat areas, and inter-tissue metrics. NSQIP scores were available for all surgeries after 2012.

Problem

• Predict colectomy outcomes using automated CT body composition metrics
• Assess 1-year mortality prediction via Cox model and C-index
• Evaluate complications via AUC and body composition associations

Innovation

• Automated CT-based body composition analysis
• Integration with clinical risk predictors
• Multi-feature Cox and logistic regression models