Machine learning models in predicting viability after testicular torsion: a proof of concept study.

PURPOSE: Decision-making for orchiectomy following testicular torsion often relies on subjective clinical evaluations. This study investigates the efficacy of machine learning (ML) models in objectively predicting post-torsion testicular viability, aiming to maintain a parenchymal ratio over 80% compared to the contralateral testicle, irrespective of initial appearance and surgical timing.

METHODS

A prospective database from a single surgeon (2020-2024) covering all patients who underwent detorsion and subsequent bilateral orchidopexy was utilized. Follow-up ultrasounds were conducted at 6 to 12 months post-procedure. Variables included patient age (neonatal, prepubertal, post-pubertal), time from presentation to surgery, and history of torsion-detorsion events. Various ML models-logistic regression, k-nearest neighbors (k-NN), and decision trees-were assessed for precision and recall.

RESULTS

The decision tree model demonstrated the highest accuracy at 90.5%, followed by the regression model at 82.7%, and the k-NN model at 81.4%. The area under the curve (AUC) for the regression model indicated adequate predictability for testicular viability. A crucial finding was the impact of the timing of surgical intervention; surgeries conducted within six hours showed a 100% viability rate (p = 0.001). The patient's age also significantly affected outcomes, with post-pubertal patients showing a highest viability rate of 57.1% (p = 0.041). Detailed performance metrics, such as precision, recall, and F1-scores for each model, further validate the predictive capacity of these ML models.

CONCLUSION

Preliminary results suggest that ML models are viable tools for predicting testicular viability post-torsion, significantly enhancing clinical decision-making by providing an objective basis for potentially preserving testicles. Further studies with larger datasets are necessary to confirm and refine these predictions.