Clinnova-MS: A Prospective Cohort Study of Patients With Multiple Sclerosis: A Trans-regional Digital Health Effort Unlocking the Potential of Artificial Intelligence and Data Science in Health Care

N/ANot Yet RecruitingNCT07280871

Luxembourg Institute of Health100 enrolled

Overview

The Clinnova-Multiple Sclerosis (MS) study is part of the Clinnova program (NCT06526364; NCT06235684 and NCT05733702), which seeks to advance precision medicine and the digitalization of healthcare through high-quality, interoperable health data. This program focuses on people with multiple sclerosis (MS) and aims to identify objective surrogate markers derived from clinical, epidemiological, imaging, and omics data that can predict disease activity, such as progression or relapses. By combining data science and artificial intelligence, the project seeks to improve patient stratification, support personalized therapeutic decisions, and provide insights into the mechanisms underlying treatment response and disease progression. Although many therapies are available for MS, it remains challenging to determine the most appropriate strategy for each patient and to prevent long-term disability. Current treatments mainly target relapses and inflammation, with limited effects on chronic progression. Clinnova-MS will collect and analyze real-world and research data to better understand variability in disease activity and treatment outcomes, enabling more precise, evidence-based care within the standard of care. This study represents the first step toward the broader Clinnova objective: developing sustainable, personalized, and preventive healthcare for people living with MS.

Multiple sclerosis (MS) treatments have advanced substantially, yet selecting the most effective therapy and preventing long-term progression remain challenging because of the disease's heterogeneity and variable treatment responses. Current drugs mainly target relapses and inflammation, while only partially protecting against neurodegeneration. Identifying predictive and prognostic biomarkers and improving monitoring are key to more personalized, evidence-based MS care. Clinnova-MS, part of the Clinnova program, is a prospective, observational cohort designed to explore objective markers of disease activity (progression or relapses) and treatment outcomes using clinical, imaging, molecular, digital, and patient-reported data. Artificial intelligence and data science will be applied to integrate information from sources such as MRI, deep molecular phenotyping, exposome data, Patient Reported Outcome Measures (PROMs)/Patient-Reported Experience Measures (PREMs), and connected devices. Up to 800 participants with early MS, transitioning to progressive disease, or undergoing treatment change will be enrolled in France, Switzerland, Germany, and Luxembourg (about 100 at Centre Hospitalier du Luxembourg (CHL)). Participants will provide clinical data, biological samples (blood mandatory; other specimens optional), imaging (as per standard care), and digital health information. They will be followed for up to five years, with visits at baseline, 6 months (optional), 12 months, annual follow-up, and unscheduled visits if new symptoms or relapses occur.

Interventions

CohortOTHER

Participants will provide data and samples for analysis. In the first year after inclusion, demographics, lifestyle, labs, and physical exams will be collected at baseline, 6, and 12 months. Patient-Reported Outcomes (PROs) and challenges will be gathered between visits via the dreaMS app. Biological samples (blood required; saliva, urine, stool, CSF, hair optional), tissue from endoscopic biopsy, and imaging (if done as standard care) will be taken at baseline, 6, and 12 months. One unscheduled visit may occur for flares or treatment changes. From month 12 to 4 years later, yearly medical data, PROs every 6 months, and continuous smartwatch data will be collected.

Eligibility

Sex: ALLMin age: 18 Years

Medical Language ↔ Plain English

Inclusion Criteria: 1. Signed informed consent form 2. ≥ 18 years of age 3. Willing and able to comply with the protocol for the duration of the study including data and samples collection as well as study visits and examinations. 4. Diagnosed with MS according to the revised McDonald criteria 2017 or revised McDonald criteria 2024, all clinical forms inclusive (CIS, RRMS, SPMS, PPMS) AND early disease stages (\< 3 years), OR presenting at hospital for evaluation of a change in therapy (flare) OR transitioning phase to progressive disease as evaluated based on EDSS. Exclusion Criteria: 1. Diagnosis uncertain (no fulfilment of inclusion criteria) 2. Any condition that could potentially hamper the compliance with the study protocol, including study procedures and study visits such as mental disability that makes it difficult or impossible to answer questionnaires. 3. Not fluent in any of the following languages: French, English or German. 4. Known pregnancy before the inclusion into the study

Outcomes

Primary Outcomes

Identification of Clinical, Imaging, and Omics Signatures for MS Subtype Stratification

Identify clinical, epidemiological, imaging and omics characteristics associated with changes of status for different subtypes of MS patients allowing the stratification of these patients according to similar patterns and disease courses.The primary endpoint will be the change of status of the patients' disease between the baseline and at Year 1. The status of the disease will be determined by using the No Evidence of Disease Activity (NEDA MS- 3).

Time frame: 1 year

Secondary Outcomes

Building Resources and Digital Tools to Advance Research and Healthcare in Multiple Sclerosis

* To identify clinical, imaging, epidemiological, omics and digital characteristics associated with MS disease activity triggering a treatment change. * To establish a sample and data bank to enable biomedical research. * To develop digital applications for improved interactions between patients and medical doctors, hence support improving healthcare. The secondary endpoints will be: 1. "Treatment change" (yes/no), a binary variable, defining if the current treatment has been changed at a time point/visit. The goal is to identify surrogate biomarkers for the clinician's decision to apply a treatment change. Treatment change is defined as either: * Change of drug dosage * Change of medication within the same treatment class * Change of treatment class 2. Change in participant reported outcomes and their evolution since baseline (improvement/worsening)