Dennis H Murphree1, Elaheh Arabmakki2, Che Ngufor2, Curtis B Storlie2, Rozalina G McCoy3. 1. Division of Biomedical Statistics and Informatics, Department of Health Sciences Research, Mayo Clinic, Rochester, MN 55905, USA. Electronic address: murphree.dennis@mayo.edu. 2. Division of Biomedical Statistics and Informatics, Department of Health Sciences Research, Mayo Clinic, Rochester, MN 55905, USA. 3. Division of Community Internal Medicine, Department of Medicine, Mayo Clinic, Rochester, MN, 55905, USA; Division of Health Care Policy & Research, Department of Health Sciences Research, Mayo Clinic, Rochester, MN, 55905, USA; Mayo Clinic Robert D. and Patricia E. Kern Center for the Science of Health Care Delivery, Mayo Clinic, Rochester, MN 55905, USA.
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.
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.
Authors: Silvio E Inzucchi; Richard M Bergenstal; John B Buse; Michaela Diamant; Ele Ferrannini; Michael Nauck; Anne L Peters; Apostolos Tsapas; Richard Wender; David R Matthews Journal: Diabetes Care Date: 2015-01 Impact factor: 19.112
Authors: Jemal Abawajy; Andrei Kelarev; Morshed Chowdhury; Andrew Stranieri; Herbert F Jelinek Journal: Comput Biol Med Date: 2013-07-12 Impact factor: 4.589