Aims: The aim of this study was to analyze the current trend in the use of antidiabetes as well as other drugs for comorbidities along the duration of diabetes. The study also aimed to analyze the direct drug cost to patients. Settings and Design: Retrospective cross-sectional study. Subjects and Methods: Data captured in clinic electronic medical records of an endocrine practice was analyzed. Statistical Analysis Used: Data was analyzed descriptively using machine learning codes on python platform. Results: Records of 489 people who attended the clinic during the 6-month period were retrieved. Data of 403 people with diabetes were analyzed after exclusion of incomplete data. Use of antidiabetic drug increased from 1.44 (0.78) [mean (standard deviation)] in people with a duration of diabetes <5 years to 3.18 (1.05) in people with 20+ years of diabetes. The mean number of antidiabetic drug usage seems to plateau at 15 years of diabetes. About 46% of people with 20+ years of diabetes required insulin therapy. Prescription patterns involving a combination of different drug classes in patients were also analyzed. The cost of diabetes therapy increases linearly along the duration of diabetes. Conclusion: This study provides valuable insights on temporal prescription patterns of antidiabetic drugs from an endocrine practice. Metformin remains the most preferred drug across the entire duration of diabetes. Dipeptidyl peptidase-4 inhibitors seem to be fast catching up with sulfonylureas as a second-line treatment after metformin. After 20 years or more of diabetes duration, 46% people would require insulin for glycemic control.

No abstract

Background and Objectives: Application of artificial intelligence/machine learning (AI/ML) for automation of diabetes management can enhance equitable access to care and ensure delivery of minimum standards of care. Objective of the current study was to create a clinical decision support system using machine learning approach for diabetes drug management in people living with Type 2 diabetes. Methodology: Study was conducted at an Endocrinology clinic and data collected from the electronic clinic management system. 15485 diabetes prescriptions of 4974 patients were accessed. A data subset of 1671 diabetes prescriptions of 940 patients with information on diabetes drugs, demographics (age, gender, body mass index), biochemical parameters (HbA1c, fasting blood glucose, creatinine) and patient clinical parameters (diabetes duration, compliance to diet/exercise/medications, hypoglycemia, contraindication to any drug, summary of patient self monitoring of blood glucose data, diabetes complications) was used in analysis. An input of patient variables were used to predict all diabetes drug classes to be prescribed. Random forest algorithms were used to create decision trees for all diabetes drugs. Results and Conclusion: Accuracy for predicting use of each individual drug class varied from 85% to 99.4%. Multi-drug accuracy, indicating that all drug predictions in a prescription are correct, stands at 72%. Multi drug class accuracy in clinical application may be higher than this result, as in a lot of clinical scenarios, two or more diabetes drugs may be used interchangeably. This report presents a first positive step in developing a robust clinical decision support system to transform access and quality of diabetes care.