Stacked classifiers for individualized prediction of glycemic control following initiation of metformin therapy in type 2 diabetes

Abstract

Objective: Metformin is the preferred first-line medication for management of type 2 diabetes and prediabetes. However, over a third of patients experience primary or secondary therapeutic failure. We developed machine learning models to predict which patients initially prescribed metformin will achieve and maintain control of their blood glucose after one year of therapy. Materials and Methods: We performed a retrospective analysis of administrative claims data for 12,147 commercially-insured adults and Medicare Advantage beneficiaries with prediabetes or diabetes. Several machine learning models were trained using variables available at the time of metformin initiation to predict achievement and maintenance of hemoglobin A1c (HbA1c) <7.0% after one year of therapy. Results: AUC performances based on five-fold cross-validation ranged from 0.58 to 0.75. The most influential variables driving the predictions were baseline HbA1c, starting metformin dosage, and presence of diabetes with complications. Conclusions: Machine learning models can effectively predict primary or secondary metformin treatment failure within one year. This information can help identify effective individualized treatment strategies. Most of the implemented models outperformed traditional logistic regression, highlighting the potential for applying machine learning to problems in medicine.

Machine Learning Approaches to Predict Risks of Diabetic Complications and Poor Glycemic Control in Nonadherent Type 2 Diabetes

“…Dennis H Murphree et al built several ML models to predict good HbA1c control (<7.0%) among T2D patients, which showed the potential for applying ML to solve problems in medical fields ( Tsao et al, 2018 ). Consistent with prior research studies ( Murphree et al, 2018 ; Tsao et al, 2018 ; Zarkogianni et al, 2018 ; Aminian et al, 2020 ), the findings of this study showed high AUCs.…”

Glycemic Control Comparative of Metformin and Glimepiride in Monotherapy of Type 2 Diabetes Mellitus Patient at Islamic Jemursari Hospital Surabaya in 2018

“…While many patients need to start metformin at a lower dose and gradually increase it so as to minimize gastrointestinal side effects. 9 In conclusion, the results of the present study show that the efficacy of high-dose metformin is dose-dependent in Japanese patients with type 2 diabetes and the efficacy and safety of metformin were similar when taken either twice daily or three times daily. 10 There were 82 type 2 diabetes mellitus patients with prescribed 500 mg metformin twice daily.…”

Application of Machine Learning in Translational Medicine: Current Status and Future Opportunities

“…ML models can provide valuable insights into the importance of dosage in the real-world use of drugs in the context of a multitude of demographic and clinical factors. For example, the critical importance of attaining target metformin dosage for optimal glycemic control could be demonstrated in a large reverse translational ML analysis of administrative claims data for 12,147 commercially insured adults and Medicare Advantage beneficiaries with prediabetes or diabetes in the context of 58 demographic, laboratory, and co-morbidity-related patient-specific factors ( 78 ). This analysis used an ensemble model incorporating diverse methods (e.g., RF, gradient boosting, regression splines, discriminant analysis) to allow patient-specific prediction of 1-year glycemic control for adult patients with either diabetes or prediabetes who are newly prescribed metformin.…”