Learning Insulin-Glucose Dynamics in the Wild
This work addresses blood glucose forecasting for type 1 diabetics, representing an incremental improvement by combining biomedical and machine learning approaches.
The authors tackled the problem of forecasting blood glucose in type 1 diabetics by developing a new model that augments an existing biomedical model with time-varying dynamics from a machine learning sequence model, resulting in improved forecasting up to six hours with physiologically plausible forecasts.
We develop a new model of insulin-glucose dynamics for forecasting blood glucose in type 1 diabetics. We augment an existing biomedical model by introducing time-varying dynamics driven by a machine learning sequence model. Our model maintains a physiologically plausible inductive bias and clinically interpretable parameters -- e.g., insulin sensitivity -- while inheriting the flexibility of modern pattern recognition algorithms. Critical to modeling success are the flexible, but structured representations of subject variability with a sequence model. In contrast, less constrained models like the LSTM fail to provide reliable or physiologically plausible forecasts. We conduct an extensive empirical study. We show that allowing biomedical model dynamics to vary in time improves forecasting at long time horizons, up to six hours, and produces forecasts consistent with the physiological effects of insulin and carbohydrates.