Predictors of morbidity and mortality post emergency abdominal surgery: A national study

A risk prediction model based on machine learning algorithm for parastomal hernia after permanent colostomy

OBJECTIVE

To develop a machine learning-based risk prediction model for postoperative parastomal hernia (PSH) in colorectal cancer patients undergoing permanent colostomy, assisting nurses in identifying high-risk groups and devising preventive care strategies.

METHODS

A case-control study was conducted on 495 colorectal cancer patients who underwent permanent colostomy at the Second Affiliated Hospital of Anhui Medical University from June 2017 to June 2023, with a 1-year follow-up period. Patients were categorized into PSH and non-PSH groups based on PSH occurrence within 1-year post-operation. Data were split into training (70%) and testing (30%) sets. Variable selection was performed using Least Absolute Shrinkage and Selection Operator (LASSO) regression, and binary classification prediction models were established using Logistic Regression (LR), Support Vector Classification (SVC), K Nearest Neighbor (KNN), Random Forest (RF), Light Gradient Boosting Machine (LGBM), and Extreme Gradient Boosting (XgBoost). The binary classification label denoted 1 for PSH occurrence and 0 for no PSH occurrence. Parameters were optimized via 5-fold cross-validation. Model performance was evaluated using Area Under Curve (AUC), specificity, sensitivity, accuracy, positive predictive value, negative predictive value, and F1-score. Clinical utility was evaluated using decision curve analysis (DCA), model explanation was enhanced using shapley additive explanation (SHAP), and model visualization was achieved using a nomogram.

RESULTS

The incidence of PSH within 1 year was 29.1% (144 patients). Among the models tested, the RF model demonstrated the highest discrimination capability with an AUC of 0.888 (95% CI: 0.881-0.935), along with superior specificity, accuracy, sensitivity, and F1 score. It also showed the highest clinical net benefit on the DCA curve. SHAP analysis identified the top 10 influential variables associated with PSH risk: body mass index (BMI), operation duration, history and status of chronic obstructive pulmonary disease (COPD), prealbumin, tumor node metastasis (TNM) staging, stoma site, thickness of rectus abdominis muscle (TRAM), C-reactive protein CRP, american society of anesthesiologists physical status classification (ASA), and stoma diameter. These insights from SHAP plots illustrated how these factors influence individual PSH outcomes. The nomogram was used for model visualization.

CONCLUSION

The Random Forest model demonstrated robust predictive performance and clinical relevance in forecasting colonic PSH. This model aids in early identification of high-risk patients and guides preventive care.

Comparison of different scoring systems in predicting mortality and postoperative complications in acute care surgery patients at a Saudi Academic Centre

PURPOSE

Emergency surgery carries an increased risk of death and complications. Scoring systems can help identify patients at higher risk of mortality and complications. Scoring systems can also help benchmark acute care services. This study aims to compare different scoring systems in predicting outcomes among acute care surgery patients.

METHODS

Our study is a retrospective cohort study that included all adult emergency surgery admissions between 2017 and 2019. Data were obtained from patients' electronic health records. Same admission mortality and postoperative complications were collected. Data were recorded to calculate the American Society of Anesthesiologists Physical Status classification system (ASA-PS), Shock Index Score (SI), Age Shock Index Score (AgeSI), and the Emergency Surgery Score (ESS). The probability of death and complications was correlated with each scoring system and was assessed by calculating the c-statistic.

RESULTS

During the study period, 1606 patients fulfilled inclusion criteria. The mortality rate was 2.2%, complication rate was 18.7%. ESS predicted mortality with a c-statistic of 0.87 better than ASA-PS, AgeSI, and SI with a calculated c-statistic of 0.81, 0.74, and 0.57, respectively. ESS also predicted the occurrence of complications with a c-statistic of 0.83 better than ASA-PS, AgeSI, and SI with a calculated c-statistic of 0.72, 0.71, and 0.63, respectively.

CONCLUSION

ESS demonstrated a better prognostic accuracy for hospital mortality and postoperative complications than other prognostic scoring systems. Our findings suggest that a scoring system designed for the acute care surgical population may provide enhanced prognostic performance over other surgical prognostic scoring systems.