Predicting sperm retrieval success in salvage testicular sperm extraction: a machine learning perspective

Creative Commons License

Hazir B., Sahin A., GÜLTEKİN M. H., ÖZER C., Kayra M. V., Hasirci E., ...Daha Fazla

INTERNATIONAL JOURNAL OF IMPOTENCE RESEARCH, 2026 (SCI-Expanded, Scopus)

Özet

This multicenter retrospective observational study aimed to identify predictive factors for successful secondary testicular spermextraction (TESE) using advanced machine learning (ML) models. Data from 503 infertile men who underwent secondary TESEbetween 2021 and 2024 after a previous unsuccessful attempt were analyzed. Preoperative characteristics and laboratoryfindingswere assessed using ten ML algorithms, including Xtreme Gradient Boosting, Random Forest, Gradient Boosting, Decision Tree,AdaBoost, Logistic Regression, Multi-Layer Perceptron, Support Vector Machine, K-Nearest Neighbors, and Naive Bayes. Modelperformance was evaluated using accuracy, sensitivity, specificity, predictive values, F1 score, Youden Index, and area under theROC curve. Sperm retrieval succeeded in 211 patients (41.9%) and failed in 292 (58.1%). Mean infertility duration was 7.25 years.Xtreme Gradient Boosting consistently outperformed other algorithms across all performance metrics. Key predictors of successfulsecondary TESE included preoperative body mass index, TESE location, luteinizing hormone level, and semen volume. Testicularvolumes and infertility duration also contributed significantly to prediction accuracy. Incorporating multiple clinical and laboratoryparameters into ML-based predictive models can improve surgical planning and preoperative counseling. For men undergoingsecondary TESE, these models may identify those with a very low chance of success, reducing unnecessary repeat surgicalinterventions.