Establishing a Proof Of Concept Model to Improve MS Treatment Optimization: Carrie Hersh, DO, MSc

Over the years, the treatment toolbox for patients with relapsing multiple sclerosis (MS) has grown immensely, with several different options and routes of administration to choose from. Finding the right therapy for an individual can be a challenge for clinicians, considering a lot of the available treatments differ in safety, efficacy, and tolerability profiles, as well as mechanisms of action. Several of those in the field, including Carrie Hersh, DO, MSc, are looking to find ways of understanding the heterogeneous treatment effects (HTE) in MS and how they can inform personalized medicine decisions.

At the 2022 European Committee for Treatment and Research in Multiple Sclerosis (ECTRIMS) Congress, October 26-28, in Amsterdam, the Netherlands, Hersh and her colleagues presented an analysis that aimed to establish proof-of-concept 2-stage HTE models derived from the real-world MS PATHS research network. The study featured 1600 patients with MS, had at least 1-year follow-up, and were on a disease-modifying therapy (DMT) that was either considered highly effective, moderate, or low. Patients were split into training (70%) and test (30%) sets stratified by treatment group.

In the first stage, baseline relapse risk scores were derived by logistic LASSO regression with baseline covariates as inputs. All told, the relapse risk model achieved an area under the curve of 0.75. Hersh, an associate professor at the Cleveland Clinic Lerner College of Medicine, sat down with NeurologyLive^® to provide an in-depth analysis of the newly developed 2-stage models. She detailed how she went about the analysis, the importance of incorporating all DMTs, and how the model could potentially improve personalized medicine going forward.