Prediction of success of slings in female stress incontinence, statistical and AI modeling

Studies on predicting the outcome of sling surgery are limited. Most depend on analysis of multiple confounding factors using regression models. However, their prediction results are limited. In this study, we tested a statistical regression model and an AI model for the prediction of the outcome of mid-urethral sling. Data were collected from 151 patients who underwent MUS surgery in our center from 2002 to 2022 and confounding factors that affect the outcome of the surgery at a minimum of one year. The study was divided into two phases. Phase I included the construction of a prediction model using binomial logistic regression. In phase II, we applied AI techniques (Artificial neural network (ANN) and Support Vector Machines (SVM) trying to obtain better predictions. Phase I: The logistic regression model predicted the outcome of surgery with overall accuracy of 90.7% and positive predictive value of 61.5% [X² (11) = 46.24, P < 0.001]. Phase II: The data of the patients were entered as 10 features; 9 were predictors and the 10^th was the output. The output comprised 18 cases designated as 'failure' and 133 as 'success' output. The best model performance-wise was the (SVM) with 92% accuracy and 96% F1-score, which meets the industrial standards for predictive models. However, ANN produced 90% accuracy and 94% F1-score. However, our sample size is small. Prediction of the outcome of MUS surgery was achieved using different modalities with the best prediction of the outcome obtained by SVM method. This is helpful in future counseling of women undergoing sling surgery, whatever its type as to what to expect after surgery.