Show abstract - Show schedule - Proceedings - PDF - Reviews

Precision medicine for chronic diseases such as multiple sclerosis (MS) involves choosing a treatment that best balances efficacy and side effects for the individual patients. Making this choice as early as possible would be important, as delays in finding an effective therapy can lead to irreversible disability accrual. To this end, we present the first multi-head, deep neural network model for individualized treatment decisions from baseline magnetic resonance imaging (MRI) (with clinical information if available) for MS patients which (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 large, 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, can reliably identify heterogeneous treatment effects, and provides a personalized treatment recommendation that accounts for treatment-associated risk.
Hide abstract

Friday 8th July
Poster Session 3.2 - onsite 11:00 - 12:00, virtual 15:20 - 16:20 (UTC+2)
Hide schedule