Blog - General

In a recent episode of the MS-Perspektive podcast, host Nele von Horsten speaks with neurologist Prof. Bernhard Hemmer about one of the most exciting questions in MS research: can multiple sclerosis be prevented?

Prof. Hemmer, who is involved in the WISDOM project, an international initiative focused on improving MS risk prediction and prevention, is a guest in episode #366 of the podcast. The interview is available via the MS-Perspektive website and podcast feed.

Some key highlights:

MS starts long before symptoms

• MS likely starts years before the first clinical symptoms appear
• By the time of diagnosis, MRI scans often already show earlier inflammatory activity
• This suggests MS has a long silent phase before it becomes clinically noticeable
• The disease process is therefore often well underway before the first relapse or symptoms occur

Moving toward early detection and prevention

Researchers are increasingly focusing on identifying people at higher risk earlier. Important risk factors include Epstein–Barr virus (EBV), vitamin D deficiency, smoking, obesity, and genetic predisposition. Biomarkers such as neurofilament light chain and early MRI findings may also help detect disease activity before symptoms occur.

EBV is a major focus of current research, as MS appears to be extremely rare in people who have never been infected. This has led to interest in vaccine-based prevention strategies, although these would require long-term studies to confirm effectiveness.

Who is at risk?

First-degree relatives of people with MS have a higher risk, but most will never develop the disease. Another important group is people with Radiologically Isolated Syndrome (RIS), where MRI scans show MS-like lesions without symptoms.

The role of WISDOM and future challenges

Despite progress, major challenges remain: prediction models are still imperfect, most high-risk individuals will never develop MS, and prevention studies require large, long-term international collaboration.

Initiatives like the WISDOM project, in which Prof. Hemmer participates, aim to improve risk prediction and support future prevention strategies.

Looking ahead

Over the next 5–10 years, researchers expect advances in blood-based diagnostics, MRI techniques, and large cohort studies of at-risk individuals. While true MS prevention is not yet possible, the field is steadily moving from treatment toward earlier intervention, and potentially prevention.

👉 You can listen to the full conversation with Prof. Hemmer here: https://ms-perspektive.de/366-prof-hemmer/

Legal and ethical frameworks for AI are often created at a distance from the environments where AI systems are actually developed. While these regulations aim to ensure fairness, transparency, and safety, developers frequently experience a gap between regulatory expectations and the practical realities of building AI models.

As part of WP1, discussions with AI development teams explore how legal and ethical requirements are experienced during the development process, particularly in healthcare and data-driven research.

One key theme is that developers generally understand the importance of regulation, especially regarding patient protection, fairness, and accountability, and requirements around explainability, documentation, and bias mitigation are to a large degree perceived as well aligned with scientific quality expectations.

Data-related requirements are among the biggest concerns. Ensuring data quality, completeness, representativeness, and security is critical for trustworthy AI, but real-world healthcare data is often incomplete, fragmented, or potentially biased. Developers therefore rely on mitigation strategies such as transparency about limitations, human oversight, and continuous monitoring.

Legal requirements also increasingly shape model design itself. Expectations regarding automatic logging, transparency, and human oversight are generally viewed as valuable safeguards, but they can also introduce technical complexity and slow development processes.

Questions about responsibility, acceptable risk, and fairness remain difficult to answer in practice. The discussions further highlight the importance of involving clinicians, patients, and other stakeholders in AI development. Including those who will ultimately use or be affected by AI systems can improve both ethical robustness and practical usability.

Overall, the conversations within WP1 demonstrate that ethical and legal frameworks are becoming an integral part of AI development. The challenge moving forward is to ensure that these frameworks not only protect individuals and society, but also remain realistic, understandable, and adaptable to the realities of innovation.