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

Precision medicine for chronic diseases such as multiple sclerosis (MS) involves choosing a treatment which best balances efficacy and side effects/preferences for individual patients. Making this choice as early as possible is important, as delays in finding an effective therapy can lead to irreversible disability accrual. To this end, we present the first deep neural network model for individualized treatment decisions from baseline magnetic resonance imaging (MRI) (with clinical information if available) for MS patients. Our model (a) predicts future new and enlarging T2 weighted (NE-T2) lesion counts on follow-up MRI on multiple treatments and (b) estimates the conditional average treatment effect (CATE), as defined by the predicted future suppression of NE-T2 lesions, between different treatment options relative to placebo. Our model is validated on a proprietary federated dataset of 1817 multi-sequence MRIs acquired from MS patients during four multi-centre randomized clinical trials. Our framework achieves high average precision in the binarized regression of future NE-T2 lesions on five different treatments, identifies heterogeneous treatment effects, and provides a personalized treatment recommendation that accounts for treatment-associated risk (e.g. side effects, patient preference, administration difficulties).

According to the National Alliance on Mental Illness and the World Health Organization, depression affects 16 million Americans and 322 million people worldwide. Emerging evidence suggests that the COVID-19 pandemic is further exacerbating the prevalence of depression in the general population. With this trajectory, it is evident that more effective strategies are needed for therapeutics that address this critical public health issue. In a recent study, publishing in the June 9, 2021 online edition of Nature Translational Psychiatry, researchers at University of California San Diego School of Medicine used a combination of modalities, such as measuring brain function, cognition and lifestyle factors, to generate individualized predictions of depression. The machine learning and personalized approach took into account several factors related to an individual's subjective symptoms, such as sleep, exercise, diet, stress, cognitive performance and brain activity.