Machine learning-based risk predictive models for depression in patients with diabetes: A systematic review and meta-analysis - Takeaways - MDSpire

Machine learning-based risk predictive models for depression in patients with diabetes: A systematic review and meta-analysis

  • By

  • Cai, Xingxin

  • Guo, Guiying

  • Zhou, Jun

  • Han, Mengqi

  • Cui, Yuanyuan

  • Chen, Zhenglin

  • March 30, 2026

  • 0 min

Share

  • 1

    This systematic review evaluates machine learning models for predicting depression risk in diabetic patients.

  • 2

    A total of 14 studies with 64 distinct ML models were included, all assessed as high risk of bias.

  • 3

    The pooled AUC for the best-performing ML models was 0.822, indicating good predictive performance.

  • 4

    Logistic regression was the most frequently used ML method for developing depression risk prediction models.

  • 5

    Common predictors included age, sex, and BMI, which are easily accessible in clinical settings.

Original Source(s)

Machine learning-based risk predictive models for depression in patients with diabetes: A systematic review and meta-analysis

  • by Cai, Xingxin , Guo, Guiying , Zhou, Jun , Han, Mengqi , Cui, Yuanyuan , Chen, Zhenglin

  • March 30, 2026

Related Content

Late-life difficult-to-treat depression and dementia subtypes: a naturalistic cohort study using electronic health records

A review of risk factors and intervention measures for comorbidity of diabetes and mental disorders

Diabetes Self-Care Declines During Breast Cancer Treatment

Patients experience reduced monitoring, emotional distress, and gaps in coordinated care during adjuvant therapy