Sign in Subscribe
Cancer research

Machine Learning Predictive Models for Survival in Uterine Cancer Patients With Type 2 Diabetes: A Territory-Wide Cohort Study

Strategic Insights

— 1 min read

Researchers at the Chinese University of Hong Kong have developed predictive models using machine learning to identify key survival predictors and develop a clinically interpretable risk scoring system for uterine cancer patients with type 2 diabetes. The study aimed to identify risk factors associated with survival in uterine cancer patients with type 2 diabetes and estimate their survival probabilities.

Key Takeaways:

  • The study utilized Cox proportional hazards regression, survival tree, LASSO Cox regression, boosting, and random survival forest (RSF) to develop predictive models for survival in uterine cancer patients with type 2 diabetes.
  • The RSF model demonstrated the strongest predictive performance, achieving a time-dependent area under the curve (AUC) of 0.823 and a C-index of 0.90.
  • A risk scoring system was created based on seven criteria: age at cancer diagnosis, duration of type 2 diabetes, creatinine levels, serum potassium level, low-density lipoprotein cholesterol level (LDL-C) level, body mass index (BMI), and triglycerides level.
  • The scoring system classified 31.4% of patients as high-risk, resulting in a 5-year survival probability of 43.5%, about 1.7 times lower than that of the low-risk group.
  • The study found that key predictors, including age at cancer diagnosis, duration of type 2 diabetes, creatinine levels, serum potassium levels, LDL-C levels, BMI, and triglycerides levels, effectively stratified survival risk.
  • The research concluded that these findings demonstrate the potential of data-driven models to enhance individualized prediction and inform targeted clinical management.

Statistics:

  • 2047 uterine cancer patients with type 2 diabetes were included in the cohort study.
  • The average survival time was 100.82 (standard deviation: 72.75) months.
  • 31.4% of patients were classified as high-risk, resulting in a 5-year survival probability of 43.5%.
  • The RSF model achieved a time-dependent area under the curve (AUC) of 0.823 and a C-index of 0.90.

Sources:

  • Huang, J., et al. (2025). Machine Learning-Predictive Models for Survival in Uterine Cancer Patients With Type 2 Diabetes: A Territory-Wide Cohort Study. Journal of Obstetrics and Gynaecology Research, 51(10), 1111-1447-0756. Wiley. https://onlinelibrary.wiley.com/journal/10.1111/(ISSN)1447-0756
  • NewsRx. (2025, October 13). Reports Outline Type 2 Diabetes Study Findings from Chinese University of Hong Kong (Machine Learning-Predictive Models for Survival in Uterine Cancer Patients With Type 2 Diabetes: A Territory-Wide Cohort Study). Clinical Trials Week, p 399.

Read more