Generating Personalized Insulin Treatments Strategies with Deep Conditional Generative Time Series Models
This work addresses personalized treatment generation for diabetes patients, but it appears incremental as it builds on existing deep generative and decision theory methods without claiming major breakthroughs.
The paper tackles the problem of generating personalized insulin treatment strategies for hospitalized diabetes patients by combining deep generative time series models with decision theory, resulting in a framework that produces tailored treatment plans and blood glucose predictions.
We propose a novel framework that combines deep generative time series models with decision theory for generating personalized treatment strategies. It leverages historical patient trajectory data to jointly learn the generation of realistic personalized treatment and future outcome trajectories through deep generative time series models. In particular, our framework enables the generation of novel multivariate treatment strategies tailored to the personalized patient history and trained for optimal expected future outcomes based on conditional expected utility maximization. We demonstrate our framework by generating personalized insulin treatment strategies and blood glucose predictions for hospitalized diabetes patients, showcasing the potential of our approach for generating improved personalized treatment strategies. Keywords: deep generative model, probabilistic decision support, personalized treatment generation, insulin and blood glucose prediction