Development and validation of an individual weight-loss model for patients with diabetes treated with metformin
Authors' conclusion
The developed machine learning model can be used to predict the individual weight loss responses to metformin and provide new insights for clinical practice regarding weight management in Chinese patients with diabetes.
Study context
- Population
- Chinese patients with newly diagnosed T2D on metformin monotherapy, from three Chinese randomized controlled trials (RCTs)
- Participants
- 1,325 patients3 RCTs
- Outcome
- Prediction of weight loss at end of treatment (categorical weight loss at 3% or 5%)
- Follow-up
- End of treatment
Methodological detailsmachine learning, pooled data from three RCTs, Online web-based tool constructed based on the prediction model
- Machine learning
- Pooled data from three RCTs
- Online web-based tool constructed based on the prediction model
Performance
As reported in the abstract
Prediction of categorical weight loss (3% or 5%), test set
All AUC values in the test set exceeded
0.71
Maximum AUC in the test set
0.83
Original publication
Development and validation of an individual weight-loss model for patients with diabetes treated with metformin. Diabetes Res Clin Pract. Published 27 February 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →