Integrated biomarker profiling for predicting the response of type 2 diabetes to metformin
Authors' conclusion
The IBP composed of nine biomarkers can be used to predict the response of T2D patients to metformin, enabling clinicians to start a combined medication strategy as soon as possible if T2D patients do not respond to metformin.
Study context
- Population
- T2D patients treated with metformin
- Participants
- 73 vs 63
- Comparison
- Metformin responders vs non-responders
- Respondersn = 73
- Non-respondersn = 63reference
- Outcome
- Prediction of response of T2D patients to metformin by integrated biomarker profiling (IBP)
Methodological detailsserum metabolomic analysis, verification in insulin-resistant mice, five machine learning methods compared, Naïve Bayes classifier
- Serum metabolomic analysis
- Verification in insulin-resistant mice
- Five machine learning methods compared
- Naïve Bayes classifier
Main finding
As reported in the abstract
IBP of 9 biomarkers (Naïve Bayes) predicting metformin response
Accuracy of integrated biomarker profiling (IBP)
89.70%
Differential serum metabolites identified
88
Candidate biomarkers after verification in mice
19
Biomarkers confirmed after metformin regulation
9
Original publication
Integrated biomarker profiling for predicting the response of type 2 diabetes to metformin. Diabetes Obes Metab. Published 3 June 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →