Future Thoughts on Improving MS Trial Design, Calculations: Carrie Hersh, DO, MSc

WATCH TIME: 4 minutes

"I’m hoping we’ll be able to take this to the next steps where we’ll be able to continue this work and hopefully be able to create some sort of machine learning algorithm that might better identify individual treatments for the patient."

For relapsing multiple sclerosis (MS), there are several FDA-approved options to choose from; however, each medication differs in terms of mechanism of action, administration, and safety and efficacy profiles. Choosing the right medication can be a challenge for clinicians who treat patients with the condition, especially considering there are some therapeutics that are new to the market and some that may be on the way in the coming future. Understanding these heterogenous treatment effects (HTE) is something several within the space, including Carrie Hersh, DO, MSc, are heavily interested in.

At the 2022 European Committee for Treatment and Research in Multiple Sclerosis (ECTRIMS) Congress, October 26-28, in Amsterdam, the Netherlands, Hersh unveiled her research that established a proof of concept for 2-stage HTE models using real-world data from the MS PATHS research network. The analyses included patients with MS who were on either high, moderate, or low efficacy disease-modifying therapies. In the first stage, baseline relapse risk scores were derived by logistic LASSO regression with baseline covariates as inputs, while in the second stage, propensity score weighting using overlap weight was performed.

All told, the risk model achieved an area under the curve of 0.75 in the test set. In an interview with NeurologyLive^®, Hersh, an associate professor at Cleveland Clinic’s Lerner College of Medicine, provided comment on the changes needed to improve MS clinical trials and personalized medicine. Additionally, as more clinicians within the space aim to answer this question, Hersh discussed how she is able to navigate through which strategies may be more effective.

Click here for more coverage of ECTRIMS 2022.

REFERENCE:
1. Hersh CM, Sun Z, Grossman CI, Shen C, Pellegrini F, Campbell N. Proof-of-concept for 2-stage models of heterogenous treatment effects derived from the real-world MS PATHS research network. Presented at: 2022 ECTRIMS Congress; October 26-28; Amsterdam, Netherlands. P372