EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Leveraging machine learning methods to predict post-transplant diabetes in solid organ transplant recipients

Rhea Varghese iD, Yingji Sun, Saba Maleki iD, Mamatha Bhat iD

Journal of the Endocrine Society · 02.11.2026 · 10 (12)

DOI: 10.1210/jendso/bvag236 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the Endocrine Society, online erschienen am 15.10.2026. Verfasst von Rhea Varghese und 3 weiteren Autor:innen. Beteiligte Einrichtung: Ajmera Transplant Centre, University Health Network, Toronto, ON M5G 2N2, Canada. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University Health Network.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Post-transplant diabetes mellitus (PTDM) is a common complication following solid organ transplantation and is associated with increased morbidity and mortality. This study aimed to identify both generalizable and solid organ-specific predictors of PTDM with machine learning methods. Materials & Methods In this study, we used 2002-2023 data from the Scientific Registry of Transplant Recipients (SRTR) to examine the risk of PTDM development across the liver (n = 128 016), kidney (n = 360 562), heart (n = 45 505), and lung (n = 36 260) transplant recipients. We examined various features at baseline using logistic regression and random forest models. Performance was evaluated using area under the receiver operating characteristic curve (AUROC), Brier scores, sensitivity, and specificity. Shapley Additive exPlanations were used for model interpretation and to identify key relevant features.

Results

The incidence of PTDM ranged from 15.0% in kidney to 20.2% in lung recipients. Compared to logistic regression, random forest demonstrated modestly improved discrimination (AUROC: 0.62-0.63) and calibration (Brier: 0.124-0.156). It was found across all models that age and BMI were consistent predictors. Prednisone and cyclosporine maintenance were often found to be associated with higher PTDM risk while mycophenolate mofetil was seen as protective. SHAP analysis demonstrated complex, nonlinear interactions and supported known risk patterns such as increased age and male sex.

Conclusion

Our machine learning model identified risk factors common to post-transplant diabetes across organ transplant recipients, guiding more optimal patient survival post-transplant.

Schlagwörter

Stichwörter der Autor:innen

logistic regressionmachine learningpost-transplant diabetesrandom forestsolid organ transplant

Autor:innen und Institutionen

  • Ajmera Transplant Centre, University Health Network, Toronto, ON M5G 2N2, Canada.
  • Temerty Faculty of Medicine, University of Toronto, Toronto, ON M5S 3H2, Canada.
  • Division of Gastroenterology & Hepatology, Department of Medicine, University of Toronto, Toronto, ON M5S 3H2, Canada.

ORCID-Profile: Rhea Varghese, Saba Maleki, Mamatha Bhat

Förderung

  • University Health Network

Zitieren

APA

Varghese, R., Sun, Y., Maleki, S., & Bhat, M. (2026). Leveraging machine learning methods to predict post-transplant diabetes in solid organ transplant recipients. Journal of the Endocrine Society, 10(12). https://doi.org/10.1210/jendso/bvag236

Vancouver

Varghese R, Sun Y, Maleki S, Bhat M. Leveraging machine learning methods to predict post-transplant diabetes in solid organ transplant recipients. Journal of the Endocrine Society. 2026;10(12). doi:10.1210/jendso/bvag236

BibTeX
@article{Varghese2026,
  author = {Varghese, Rhea and Sun, Yingji and Maleki, Saba and Bhat, Mamatha},
  title = {Leveraging machine learning methods to predict post-transplant diabetes in solid organ transplant recipients},
  journal = {Journal of the Endocrine Society},
  year = {2026},
  volume = {10},
  number = {12},
  doi = {10.1210/jendso/bvag236}
}
Kostenlos starten →