Key result
Machine learning algorithms, including XGBoost (AUC 0.88), demonstrated equivalent predictive performance to classical logistic regression (AUC 0.83) for assessing 30-day complication risk after hemorrhoidal surgery.
Why the study?
Machine learning algorithms are emerging as an alternative to traditional regression analysis, but their role compared to classical logistic regression for preoperative risk assessment in proctological surgery needed investigation.
Do machine learning algorithms improve preoperative risk prediction for 30-day complications compared to logistic regression in patients undergoing proctological surgery?
Observational (n=1,510)
Yes
Do machine learning algorithms improve preoperative risk prediction for 30-day complications compared to logistic regression in patients undergoing proctological surgery?
Machine learning and classical logistic regression models demonstrated equivalent predictive performance for 30-day complications following elective surgery for grade III hemorrhoidal disease.
Clinical risk prediction models are ubiquitous in many surgical domains. The traditional approach to develop these models involves the use of regression analysis. Machine learning algorithms are gaining in popularity as an alternative approach for prediction and classification problems. They can detect non-linear relationships between independent and dependent variables and incorporate many of them. In our work, we aimed to investigate the potential role of machine learning versus classical logistic regression for the preoperative risk assessment in proctological surgery. We used clinical data from a nationwide audit: the database consisted of 1510 patients affected by Goligher's grade III hemorrhoidal disease who underwent elective surgery. We collected anthropometric, clinical, and surgical data and we considered ten predictors to evaluate model-predictive performance. The clinical outcome was the complication rate evaluated at 30-day follow-up. Logistic regression and three machine learning techniques (Decision Tree, Support Vector Machine, Extreme Gradient Boosting) were compared in terms of area under the curve, balanced accuracy, sensitivity, and specificity. In our setting, machine learning and logistic regression models reached an equivalent predictive performance. Regarding the relative importance of the input features, all models agreed in identifying the most important factor. Combining and comparing statistical analysis and machine learning approaches in clinical field should be a common ambition, focused on improving and expanding interdisciplinary cooperation.
No takes yet. Share an insight, caveat, or question.
Romano et al. (2025) conducted an observational in Goligher's grade III hemorrhoidal disease (n=1,510). Machine learning models (Decision Tree, Support Vector Machine, XGBoost) vs. Logistic regression was evaluated on Predictive performance for 30-day complication rate (Area Under the Curve). Machine learning algorithms, including XGBoost (AUC 0.88), demonstrated equivalent predictive performance to classical logistic regression (AUC 0.83) for assessing 30-day complication risk after hemorrhoidal surgery.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: