A Decision Support Tool for the Discontinuation of Disease Modifying Therapies in Multiple Sclerosis

点击翻译按钮获取中文摘要

Project summary The treatment of multiple sclerosis (MS) has been transformed with the introduction of disease-modifying therapies (DMTs), but these medications DMTs have known risks and are a significant financial burden for many people with MS and for the healthcare system as a whole. Nationally, prescription drugs account for 10- 15% of total healthcare spending, but, for people with MS, prescription drugs account for more than two-thirds of their total healthcare expenditures. The benefits of DMTs are clear early in the disease course, where they have been shown to prevent relapses and the accumulation of lesions in the central nervous system. Later in the disease course, the combination of immunosenscence and a shift from widespread neuroinflammation to neurodegeneration results in diminished biological benefits of DMTs and a shift in the risk/benefit ratio in people with MS. The most common risks associated with DMTs are infections, which have been reported to be as high as 19.7 per 1000 person-years. Studies have also shown that infectious complications tend to increase with both age and increased years of DMT exposure. For these biological, financial, and risk reasons discontinuation of DMT in certain individuals should be considered. There is a growing body of observational research supporting the notion that there is a safe time to discontinue DMTs with a low risk of recurrent disease activity. These studies all suggest that older patients who have been on a DMT for several years without active disease (no relapses, no new MRI lesions) have a low likelihood of recurrent disease activity after discontinuing DMT. Despite the growing evidence to support DMT discontinuation there is a lack of consensus from neurological societies and there is no standardized approach to this clinical decision. This study seeks to develop and validation a machine learning based point of care decision support tool to standardize the approach to MS DMT discontinuation. This study will develop the machine learning algorithm in a large retrospective clinical cohort and externally validate the tool in the “Discontinuation of disease modifying therapies in multiple sclerosis” (DISCOMS; NCT 03073603) randomized, controlled, single-blinded, clinical trial dataset during the R21 phase. In the R33 phase the validated point of care tool will be implemented through a pragmatic randomized clinical trial to assess the adoption and impact on clinical outcomes over 24 months. The overarching goal of this proposal is to create a decision support tool that will provide a standardized approach to DMT discontinuation resulting in a reduction in risk exposure and financial burden to people with MS.