The paths of MS – data-driven personalized prediction of multiple sclerosis risk and disease-modifying treatment outcomes

Multiple sclerosis (MS), a chronic inflammatory and neurodegenerative condition, is a major driver of disability and healthcare costs among young to middle-aged adults.

Access to disease-modifying treatments (DMTs) early in the disease course is thought to have improved prognosis, but outcomes vary greatly between patients.

Major knowledge gaps remain on prognostic markers and on the benefit-risk balance of specific DMTs strategies in real world populations, with little evidence to guide the choice of DMT for individual patients.

This prompted us to establish Combat-MS: a nationwide study following 3500 participants to answer which initial or secondary DMT strategy that, at the group level, best preserves quality of life and neurological functions.

This unique cohort combined prospective serum samples and clinical evaluations with rich data from national registers, resulting in a series of influential publications.

With this proposal, the cohort will be expanded further with promising biomarkers, imaging and electronic medical record data, covering patients’ trajectories from first healthcare contacts to long-term treatment outcomes.

Analyzing this rich data with state-of-the art biostatistics and machine learning, my team will build a framework for a precision medicine approach to MS, providing individualized risk predictions at different clinical stages and evaluating the benefit-risk of distinct DMT strategies across diverse MS populations.