EUVIMEDEUVIMED entdecken
Crossref

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

Mith Lewis Concio, Tuba Nur Aydin, Jessica Ming, Jin Kyu Kim, Armando Lorenzo, Mandy Rickard, Pippi Salle, Rodrigo Romao, Joana Dos Santos, Michael Chua

Pediatric Surgery International · 14.01.2026 · 42 (1)

DOI: 10.1007/s00383-025-06282-6 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pediatric Surgery International, online erschienen am 14.01.2026. Verfasst von Mith Lewis Concio und 9 weiteren Autor:innen. Beteiligte Einrichtung: University of Toronto, Toronto, ON, Canada. mithlewis.concio@mail.utoronto.ca. Hauptthemen laut MEDLINE: Spermatic Cord Torsion, Machine Learning, Orchiectomy, Testis. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 11 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Spermatic Cord TorsionMachine LearningOrchiectomyTestisTissue SurvivalHumansMalePredictive Learning ModelsProspective StudiesProof of Concept StudyChild, PreschoolChildInfantOrchiopexy

Stichwörter der Autor:innen

Clinical decision supportMachine learningPediatric urologyTesticular torsionTesticular viability

Autor:innen und Institutionen

  • University of Toronto, Toronto, ON, Canada. mithlewis.concio@mail.utoronto.ca.
  • The Hospital for Sick Children, Toronto, ON, Canada.
  • University of New Mexico, Albuquerque, NM, USA.
  • Riley Hospital for Children, Indianapolis, IN, USA.

Zitieren

APA

Concio, M. L., Aydin, T. N., Ming, J., Kim, J. K., Lorenzo, A., Rickard, M., Salle, P., Romao, R., Dos Santos, J., & Chua, M. (2026). Machine learning models in predicting viability after testicular torsion: a proof of concept study. Pediatric Surgery International, 42(1). https://doi.org/10.1007/s00383-025-06282-6

Vancouver

Concio ML, Aydin TN, Ming J, Kim JK, Lorenzo A, Rickard M, et al. Machine learning models in predicting viability after testicular torsion: a proof of concept study. Pediatric Surgery International. 2026;42(1). doi:10.1007/s00383-025-06282-6

BibTeX
@article{Concio2026,
  author = {Concio, Mith Lewis and Aydin, Tuba Nur and Ming, Jessica and Kim, Jin Kyu and Lorenzo, Armando and Rickard, Mandy and Salle, Pippi and Romao, Rodrigo and Dos Santos, Joana and Chua, Michael},
  title = {Machine learning models in predicting viability after testicular torsion: a proof of concept study},
  journal = {Pediatric Surgery International},
  year = {2026},
  volume = {42},
  number = {1},
  doi = {10.1007/s00383-025-06282-6}
}
Kostenlos starten →