Logo
Daily Brief
Following Why
AI Cracks the Multiple Sclerosis Code

AI Cracks the Multiple Sclerosis Code

Machine learning uncovers hidden disease subtypes, pointing toward personalized treatment

Overview

Scientists at UCL used AI to identify two biologically distinct subtypes of multiple sclerosis—early sNfL and late sNfL—based on when nerve damage shows up in blood tests and brain scans. The discovery, published in Nature Medicine in December 2025, means doctors can finally match 2.9 million MS patients worldwide to treatments that actually fit their disease progression pattern.

This isn't incremental progress. For decades, MS treatment has been one-size-fits-all: wait for symptoms, prescribe drugs, hope they work. The AI model called SuStaIn analyzed data from 600 patients and found that some develop aggressive lesions early with corpus callosum damage, while others show slow brain shrinkage in the limbic cortex first. Patients with early sNfL could now get high-efficacy drugs immediately instead of after they've already lost function. The stakes are whether MS care joins the precision medicine revolution—or stays stuck in trial-and-error mode.

Key Indicators

2
New MS subtypes identified
Early sNfL and late sNfL subtypes based on timing of nerve damage biomarkers
2.9M
People with MS worldwide
Global patient population who could benefit from personalized treatment
600
Patients in UCL study
Dataset size for AI model training combining blood tests and brain scans
84%
AI accuracy in related MS research
Similar AI approaches correctly predict disease patterns in validation studies

People Involved

Dr. Arman Eshaghi
Dr. Arman Eshaghi
Senior Research Fellow, Queen Square MS Centre (Lead researcher developing MS-PINPOINT AI tools for personalized MS treatment)
Prof. Frederik Barkhof
Prof. Frederik Barkhof
Professor of Neuroradiology, UCL (Senior advisor on imaging biomarkers for MS research)
Dr. Alexandra Young
Dr. Alexandra Young
Principal Research Fellow, UCL Hawkes Institute (Co-developer of SuStaIn algorithm)
Dr. Neil Oxtoby
Dr. Neil Oxtoby
Principal Research Fellow, UCL Hawkes Institute (Leading clinical translation of SuStaIn algorithm)

Organizations Involved

QU
Queen Square Analytics
UCL Spinout Company
Status: Commercializing AI algorithms for neurological disease analysis

UCL spinout developing breakthrough imaging analysis technology for clinical trials and patient care in neurological diseases.

UCL Queen Square Institute of Neurology
UCL Queen Square Institute of Neurology
Academic Research Institute
Status: World-leading neurology research center

Premier neurological research institute developing AI tools for understanding brain disease progression and treatment.

Timeline

  1. AI Identifies Two New Biological Subtypes of Multiple Sclerosis

    Research

    UCL and Queen Square Analytics publish Nature Medicine study identifying early sNfL and late sNfL subtypes using blood biomarker analysis combined with brain imaging, enabling personalized treatment strategies.

  2. MS-PINPOINT Project Funded

    Funding

    Arman Eshaghi receives NIHR Advanced Fellowship to develop AI tools predicting individual MS patient outcomes and treatment responses.

  3. First AI-Identified MS Subtypes Discovered

    Research

    UCL team uses SuStaIn to identify three MS subtypes from 6,322 MRI brain scans, demonstrating AI's potential for disease classification.

  4. Queen Square Analytics Founded

    Commercial

    UCL spinout launched to commercialize SuStaIn algorithm and bring AI-driven neurological disease analysis to clinical practice.

  5. SuStaIn Algorithm Debuts in Nature Communications

    Research

    UCL researchers publish machine learning technique that identifies disease subtypes and progression stages from cross-sectional data, initially applied to Alzheimer's disease.

Scenarios

1

AI-Guided Treatment Becomes Standard MS Care Within 5 Years

Discussed by: UCL researchers, precision medicine analysts, medical AI journals including Nature Medicine and The Lancet Digital Health

The sNfL blood test combined with SuStaIn analysis gets adopted into standard MS diagnostic protocols. Neurologists routinely subtype patients at diagnosis, prescribing alemtuzumab or ocrelizumab immediately to early sNfL patients while reserving neuroprotective therapies for late sNfL cases. Clinical trials report 40-50% reductions in disability progression compared to traditional escalation approaches. Insurance companies cover the biomarker test after cost-benefit analyses show savings from preventing hospitalizations and disability. The model expands to other autoimmune and neurodegenerative diseases, making precision neurology mainstream.

2

Adoption Stalls on Reimbursement and Validation Gaps

Discussed by: Health economics researchers, insurance industry analysts, neurology practice management journals

Despite promising research, widespread adoption hits roadblocks. Insurance companies balk at covering sNfL testing without multi-year outcome data proving cost-effectiveness. Smaller hospitals lack access to the imaging analysis infrastructure Queen Square Analytics provides. Regulatory agencies demand larger validation studies across diverse populations before endorsing subtype-specific treatment guidelines. Academic medical centers use the approach, but community neurologists—who treat most MS patients—stick with familiar escalation protocols. The technology remains available but reaches only 15-20% of patients who could benefit.

3

Discovery Accelerates Broader AI Diagnostics Revolution

Discussed by: Medical AI researchers, pharmaceutical companies, FDA regulatory experts, tech industry health divisions

The MS breakthrough validates pattern-recognition AI across complex diseases. Within three years, similar algorithms identify subtypes for lupus, rheumatoid arthritis, Crohn's disease, and major depression using biomarker-imaging combinations. The FDA creates a fast-track pathway for AI diagnostic tools that use clinically validated algorithms like SuStaIn. Pharma companies redesign clinical trials around AI-identified patient subtypes, leading to higher drug approval rates and more effective therapies. Queen Square Analytics and competitors build a multi-billion dollar industry in precision diagnostics, fundamentally changing how medicine categorizes and treats disease.

Historical Context

AlphaFold Cracks Protein Structure Problem

2020-2024

What Happened

DeepMind's AlphaFold 2 solved the 50-year protein structure prediction challenge in 2020, achieving 90%+ accuracy on protein shapes. By 2022, AlphaFold predicted structures for 200 million proteins—a thousand-fold increase over experimental data. Over 3 million researchers in 190 countries adopted the tool for drug discovery, vaccine development, and understanding disease mechanisms.

Outcome

Short Term

Academic labs and pharma companies immediately integrated AlphaFold into research pipelines, accelerating drug discovery timelines by months to years.

Long Term

Established AI as credible for solving fundamental biological problems, attracting billions in biotech AI investment and enabling the current wave of disease-subtyping algorithms.

Why It's Relevant Today

AlphaFold proved AI could handle biological complexity that defeated traditional methods. The MS subtyping breakthrough follows the same playbook: using pattern recognition on complex data to reveal hidden structure that changes how we approach treatment.

IBM Watson for Oncology Failure

2011-2022

What Happened

After winning Jeopardy in 2011, IBM positioned Watson as cancer care's future. But Watson for Oncology was trained on hypothetical cases from one hospital, not real patient data. It gave unsafe treatment recommendations, performed worse than human oncologists in trials, and failed to demonstrate patient benefit despite partnerships with 50+ hospitals. IBM sold off Watson Health assets in 2022 after a $4 billion loss.

Outcome

Short Term

Hospitals abandoned Watson implementations; oncologists lost trust in AI diagnostic claims; investors became skeptical of overhyped medical AI.

Long Term

The failure taught medical AI developers that training data quality, clinical validation, and narrow problem definition matter more than general intelligence or marketing hype.

Why It's Relevant Today

The UCL approach learned Watson's lessons. SuStaIn uses real patient data from 600+ MS cases, focuses narrowly on subtype identification rather than treatment recommendation, and publishes peer-reviewed validation before commercializing. Success requires rigorous science, not just powerful algorithms.

First MS Disease-Modifying Therapy Approved

1993-2010

What Happened

In 1993, interferon beta-1b became the first drug proven to alter MS's natural course, reducing relapses in relapsing-remitting MS by about 30%. This was revolutionary after a century of MS being untreatable. By 2010, several more disease-modifying therapies emerged (glatiramer acetate, natalizumab, fingolimod), but all followed an escalation approach: start with moderate drugs, switch to high-efficacy therapies only after disease worsens.

Outcome

Short Term

MS transformed from progressive disability sentence to manageable chronic condition for many patients; neurologists gained treatment options beyond symptom management.

Long Term

The escalation paradigm became entrenched despite evidence that early aggressive treatment prevents irreversible damage better than waiting for progression.

Why It's Relevant Today

For 30+ years, MS treatment has been one-size-fits-all escalation. The AI subtyping breakthrough challenges this orthodoxy by enabling personalized treatment from day one—early sNfL patients get high-efficacy drugs immediately, potentially preventing damage the escalation approach allows to accumulate.

10 Sources:
+4
Nature Medicine Euronews UCL News Clinical and Translational Science Google DeepMind Henrico Dolfing SingleCare eBioMedicine Nature Communications Journal of Neurology