Individualized Therapy Optimization for Type 2 Diabetes

Background and AimsType 2 diabetes is a wide-spread chronic condition in which blood glucose and body weight management constitute essential therapeutic targets. Emerging technologies have the potential to aid complex therapeutic pharmacotherapy choices that are optimally tailored to individual needs. Here we propose an artificial intelligence combining guidelines with clinical features and continuous glucose monitoring (CGM) to optimize therapeutic decision-making. MethodsTherapeutic guidelines are first encoded using a rule-based model and trained on a neural network. Relying on real world evidence outcomes of a specialist outpatient clinic, transfer learning is used to optimize for glucose-lowering therapies that led to successful treatment outcomes defined as an absolute 0.3% reduction in glycated (HbA1c) over 6.5% without increasing body weight for a BMI over 28. Recommendations that deviate from guidelines are described with Shapley values and tested in digital twins for statistical significance. Four CGM-derived glucose-insulin response dynamic factors serve as additional biomarkers. ResultsDual glycemic & weight targets were achieved in actual clinical practice in 51% cases, increasing to 54% when clinical guidelines were followed. Selecting outcomes in the test set that follow individualized recommendations, this increases further to 56% when using only phenotypic markers and to 64% when adding CGM-derived dynamics factors. ConclusionsTested on the limited patient number available, our findings show that AI can outperform guidelines in complex type 2 diabetes cases by integrating multiple data sources, drawing on experiential clinical insights, and selecting treatments most effective for each patients glucose and weight control. One-linerA neural network is first trained on guidelines and subsequently on real-world evidence outcomes, performing dual glycaemic/weight optimization to improve the management of type 2 diabetes with/out gluco-dynamic parameters extracted from Continuous Glucose Monitoring.