Predicting Metformin Efficacy in Improving Insulin Sensitivity Among Women With Polycystic Ovary Syndrome and Insulin Resistance: A Machine Learning Study
Authors' conclusion
The developed machine learning model could be applied to predict the efficacy of metformin in improving insulin sensitivity among women with PCOS and IR. The result could help doctors evaluate the efficacy of metformin in advance, optimize treatment plans, and thereby enhance overall clinical outcomes.
Study context
- Population
- Women with polycystic ovary syndrome (PCOS) and insulin resistance (IR) receiving metformin for 4 months; 27 baseline clinical variables
- Participants
- 114 women
- Comparison
- 5 machine learning models predicting metformin efficacy
- Primary endpoint
- Prediction of metformin efficacy in improving insulin sensitivity (AUC)
- Follow-up
- 4 months
Methodological detailsretrospective analysis of a multicentre RCT, multicenter, 4 feature selection methods compared to screen variables
- Retrospective analysis of a multicentre RCT
- Multicenter
- 4 feature selection methods compared to screen variables
Primary result
As reported in the abstract
Best-performing model AUC
| Group | AUC |
|---|---|
| Support Vector Machine | 0.781 (95% CI 0.772-0.791) |
Support Vector Machine
AUC0.781 (95% CI 0.772-0.791)
Further findings
- HOMA-IR, BMI and LDL-C were the key predictive variables
Original publication
Predicting Metformin Efficacy in Improving Insulin Sensitivity Among Women With Polycystic Ovary Syndrome and Insulin Resistance: A Machine Learning Study. Endocr Pract. Published 5 August 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →