Generating Personalized Insulin Treatments Strategies with Deep Conditional Generative Time Series Models

TL;DR

This paper introduces a deep generative time series framework that creates personalized insulin treatment strategies for diabetic patients by modeling patient data and optimizing for better health outcomes.

Contribution

It presents a novel combination of deep generative models with decision theory to generate personalized, outcome-optimized treatment strategies from patient data.

Findings

Generated personalized insulin treatment strategies for diabetic patients.

Accurately predicted blood glucose trajectories using the model.

Demonstrated potential for improved personalized treatment planning.

Abstract

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