Development and Validation of Machine Learning Models for Predicting 13 or More Sections in Mohs Micrographic Surgery

Development and validation of a SHAP-interpretable GBM model for predicting postoperative recurrence of anal Fistula

This study aimed to develop and interpret a machine learning model for predicting postoperative recurrence of anal fistula using routine laboratory indicators and inflammation-related indices. A total of 2,214 patients who underwent fistulectomy were included. Patients from wards 5, 11, 12, 13 and 14 ( n  = 1,772) were divided by stratified random sampling according to recurrence status into training ( n  = 1,242) and testing ( n  = 530) cohorts. Patients from wards 15 and 16 ( n  = 442), which were managed by separate clinical teams, were reserved as a ward-based internal validation cohort. Univariate and multiple fistula tracts. analyses were performed to identify recurrence-associated factors, and LASSO regression was used for feature selection. Multiple machine learning models were developed and compared, including logistic regression, support vector machine, GBM, neural network, XGBoost, AdaBoost, LightGBM, and CatBoost. Model performance was assessed using ROC curves, calibration curves, decision curve analysis, and classification metrics. SHAP analysis was applied for model interpretation. Multivariate logistic regression analysis showed that WBC, RBC, hs-CRP, and NCR were independent predictors of recurrence. LASSO regression selected 11 variables for model development. Among the candidate models, GBM demonstrated the most balanced predictive performance and was therefore selected as the final model. The AUCs of GBM in the training, testing, and validation sets were 0.777, 0.784, and 0.712, respectively. Calibration curves showed acceptable agreement between predicted and observed risks, while decision curve analysis indicated potential clinical benefit within low-to-moderate threshold probability ranges. SHAP analysis identified age, WBC, RBC, NCR, and hs-CRP as the main contributors to model prediction. Restricted cubic spline analysis revealed a significant nonlinear association between NCR and recurrence risk. WBC, RBC, hs-CRP, and NCR were independently associated with postoperative recurrence of anal fistula. The LASSO-based GBM model demonstrated stable predictive performance and acceptable clinical utility. Routine hematological parameters and inflammation-related indices, particularly NCR, may support individualized recurrence risk stratification and postoperative follow-up.

The Usefulness of Machine Learning Models to Predict Patient‐Reported Outcome Measures in Chronic Rhinosinusitis With Nasal Polyps

ABSTRACT Background and Objective The treatment available for chronic rhinosinusitis with nasal polyps (CRSwNP) has remained unsatisfactory. Patient‐reported outcome measures (PROMs), capturing patient‐perceived health status and well‐being, are vehicles for measuring and improving the efficacy of care. This study aimed to establish machine learning (ML) models to predict PROMs in CRSwNP patients using minimally invasive and easily acquired clinical data. Methods We collected commonly available clinical predictive data from 437 patients and established four separate ML models in the training set: a least absolute shrinkage and selection operator (LASSO)‐based Logistic regression, a random forest (RF) regression, a gradient‐boosted decision tree (GBDT), and a deep neural network (DNN). In the test and independent external validation sets, the predictive performance of these models was measured by calculating C statistics, expected prediction results, and decision curves. A feature‐ranking analysis was performed using the ML algorithm. We then developed a predictive nomogram using LASSO‐based Logistic regression. Results The models performed well on an independent external validation set, with no statistically significant differences in generalization ability metrics between groups. LASSO regression identified key features of the predictive PROMs. A nomogram was created based on multivariate Logistic regression with LASSO regularization. Conclusions All four ML models demonstrated similar performance in predicting PROMs in CRSwNP patients from which a clinical nomogram was developed. Early prediction of the subjective treatment response is crucial, as it influences clinician decisions and facilitates effective doctor‐patient communication preoperatively; this could lead to more precise and personalized treatment for CRSwNP patients.

Construction and internal validation of a machine learning model for predicting 30-day readmission after hip surgery

To develop and internally validate a machine learning (ML)-based model for predicting 30-day postoperative readmission after hip surgery using multidimensional perioperative data, and to evaluate its potential clinical utility. This single-center retrospective cohort study included 720 patients who underwent hip-related surgery at Guangxi Zhuang Autonomous Region People’s Hospital between 2022 and 2025. Patients were randomly divided into training and test sets at a 7:3 ratio. Demographic characteristics, comorbidities, laboratory variables, anesthesia and temperature-management variables, surgical characteristics, and transfusion-related variables were extracted. Candidate predictors were first selected in the training set using the Boruta algorithm. Eleven base models and one stacking ensemble model were then developed using the selected features. Hyperparameters were optimized using 5-fold cross-validation combined with grid search. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC) and the area under the precision-recall curve (PRAUC), while decision curve analysis (DCA) and SHapley Additive exPlanations (SHAP) were used to assess clinical net benefit and model interpretability. The overall 30-day readmission rate was 4.3%. In the test set, the XGBoost model achieved an AUC of 0.88 and a PRAUC of 0.53. Across commonly used threshold probabilities, XGBoost provided a higher net benefit than treat-all or treat-none strategies. SHAP analysis identified preoperative albumin, post-anesthesia care unit (PACU) temperature, warming duration, age, and heart failure as the leading predictors of readmission risk. The XGBoost-based ML model showed potential for predicting 30-day readmission after hip surgery and may provide supportive information for perioperative risk stratification and modifiable management strategies, particularly nutritional optimization and temperature management.

Machine learning-based model to predict liposuction outcomes in unilateral breast cancer-related lymphedema

Background Breast cancer-related lymphedema (BCRL) is a common and disabling complication after breast cancer surgery, with substantial effects on limb function and quality of life. Liposuction is an established option for selected patients with chronic BCRL. However, postoperative response is heterogeneous. This study aimed to develop a machine learning model to predict liposuction efficacy in patients with unilateral BCRL. Methods We analyzed 623 unilateral BCRL cases undergoing liposuction at Beijing Shijitan Hospital, randomly splitting them 7:3 into training (n=437) and validation (n=186) cohorts. Least absolute shrinkage and selection operator (LASSO) regression with cross-validation guided feature selection. Seven algorithms—logistic regression (LR), support vector machines (SVM), decision trees (DT), artificial neural networks (ANN), LightGBM, XGBoost, and random forests (RF)—were trained and benchmarked. Performance via AUC, calibration, DCA, and Brier score identified SVM as optimal. SHAP interpretation facilitated deployment of a web-based calculator. Results The overall rate of favorable outcomes following liposuction was 64.7%. Cross-validated Lasso analysis, factoring in clinical validity and predictive importance, yielded four key predictors: history of erysipelas, preoperative affected-to-unaffected limb volume difference (Preoperative_difference), extracellular water ratio of the affected limb (r-ECW%), and body fat percentage. Among the seven models evaluated, the SVM exhibited the most balanced overall performance, achieving an accuracy of 77.42%, precision of 75.00%, specificity of 90.00%, F1-score of 0.632, Brier score of 0.163, and an AUC of 0.818 (95% CI: 0.757–0.876). Although not possessing the highest AUC, the SVM demonstrated exceptional resistance to overfitting, evidenced by a minimal AUC decrement of merely 0.0298 from the training to the validation set. Both calibration and decision curve analyses corroborated its robust generalizability, underscoring its tangible clinical utility. Conclusions An SVM model predicting surgical outcomes in BCRL was created and integrated into a user-friendly online tool. This calculator guides surgical choices based on predictive outputs, offering a valuable reference for refining patient management and treatment plans.

An explainable machine learning model for type B aortic dissection identification: development and internal evaluation

Purpose Type B aortic dissection (TBAD) is a life-threatening cardiovascular emergency that requires timely recognition. This study aimed to develop and internally evaluate an explainable machine learning model for identifying existing TBAD using routinely available clinical history and admission laboratory data. Methods This single-center retrospective case-control study included 1,640 participants, comprising 854 patients with CTA-confirmed TBAD and 786 hospitalized controls who underwent whole-aorta CTA and were confirmed not to have aortic dissection. Demographic characteristics, medical history, and admission laboratory test results were collected as 38 initial candidate features. Least absolute shrinkage and selection operator (LASSO) regression was applied to identify key discriminative variables. Machine-learning models based on eight algorithms were then developed and compared: support vector machine (SVM), gradient boosting machine (GBM), neural network, extreme gradient boosting (XGBoost), k-nearest neighbors (KNN), adaptive boosting (AdaBoost), light gradient boosting machine (LightGBM), and categorical boosting (CatBoost). Hyperparameters were tuned in the training set using grid search and repeated 10-fold cross-validation with five repeats. Model discrimination was evaluated in the held-out internal test set using the area under the receiver operating characteristic curve (AUC). The final representative model was selected for exploratory interpretation using SHapley Additive exPlanations (SHAP). Results LASSO regression identified five predictors: hypertension, white blood cell count, lymphocyte percentage, basophil percentage, and monocyte count. Several models showed comparable discrimination in the held-out internal test set. The neural network model achieved an AUC of 0.883 in the training set and 0.852 in the held-out internal test set, with 95% confidence intervals of 0.864–0.902 and 0.819–0.885, respectively. Based on the ROC curve analysis, the neural network model showed relatively favorable discrimination and was therefore selected as the final representative model for exploratory SHAP-based interpretation. SHAP analysis indicated that lymphocyte percentage, hypertension, monocyte count, white blood cell count, and basophil percentage were the major contributors to the predictions of the final model, with lymphocyte percentage showing the highest mean absolute SHAP value. Conclusion This study developed and internally evaluated an explainable machine-learning model for identifying existing TBAD in a single-center CTA-confirmed retrospective case-control cohort. Given the lack of external validation, this study should be regarded as exploratory. External validation in clinically relevant acute symptomatic populations is required before clinical implementation.

Machine learning-based prediction of perioperative complications in spine surgery: a large-scale model development and validation study.