Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Task-oriented virtual reality and brain functional plasticity in progressive multiple sclerosis: A randomized controlled trial on upper limb rehabilitation.

Multiple sclerosis (Houndmills, Basingstoke, England)·2026
Same author

The schema spectrum: Emergent structures and levels of abstraction in AI and the brain.

Neuron·2026
Same author

Live Attenuated Measles-Mumps-Rubella and Varicella Vaccinations and Multiple Sclerosis Activity.

JAMA network open·2026
Same author

Rethinking prognosis in multiple sclerosis: a multiaxial perspective.

Nature reviews. Neurology·2026
Same author

Uncoupling Relapse Reduction and Disability Progression: Evidence From Tolebrutinib Studies.

Neurology. Clinical practice·2026
Same author

Discovering Latent Graphs with GFlowNets for Diverse Conditional Image Generation.

Advances in neural information processing systems·2026

Related Experiment Video

Updated: Aug 27, 2025

Measuring Progressive Neurological Disability in a Mouse Model of Multiple Sclerosis
08:11

Measuring Progressive Neurological Disability in a Mouse Model of Multiple Sclerosis

Published on: November 14, 2016

11.1K

Estimating individual treatment effect on disability progression in multiple sclerosis using deep learning.

Jean-Pierre R Falet1,2,3, Joshua Durso-Finley4,5, Brennan Nichyporuk4,5

  • 1Montreal Neurological Institute, Department of Neurology and Neurosurgery, McGill University, Montreal, QC, Canada. jean-pierre.falet@mail.mcgill.ca.

Nature Communications
|September 26, 2022
PubMed
Summary
This summary is machine-generated.

Deep learning enhances multiple sclerosis clinical trials by predicting patient response to treatments. This predictive enrichment strategy improves statistical power, accelerating drug development for this challenging neurological disease.

More Related Videos

The Multiple Sclerosis Performance Test MSPT: An iPad-Based Disability Assessment Tool
11:35

The Multiple Sclerosis Performance Test MSPT: An iPad-Based Disability Assessment Tool

Published on: June 30, 2014

58.1K
Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models
14:14

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models

Published on: August 12, 2018

9.0K

Related Experiment Videos

Last Updated: Aug 27, 2025

Measuring Progressive Neurological Disability in a Mouse Model of Multiple Sclerosis
08:11

Measuring Progressive Neurological Disability in a Mouse Model of Multiple Sclerosis

Published on: November 14, 2016

11.1K
The Multiple Sclerosis Performance Test MSPT: An iPad-Based Disability Assessment Tool
11:35

The Multiple Sclerosis Performance Test MSPT: An iPad-Based Disability Assessment Tool

Published on: June 30, 2014

58.1K
Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models
14:14

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models

Published on: August 12, 2018

9.0K

Area of Science:

  • Neurology
  • Artificial Intelligence
  • Clinical Trials

Background:

  • Multiple sclerosis (MS) disability progression is difficult to treat.
  • Lack of predictive biomarkers hinders early-phase clinical trials for MS therapeutics.
  • Developing effective treatments for MS requires innovative trial designs.

Purpose of the Study:

  • To develop and validate a deep-learning predictive enrichment strategy for MS clinical trials.
  • To increase statistical power in short proof-of-concept trials.
  • To identify patients most likely to respond to specific MS therapies.

Main Methods:

  • A multi-headed multilayer perceptron model was developed to estimate conditional average treatment effects (CATE).
  • The model utilized baseline clinical and imaging features from MS patients.
  • Model pre-training on relapsing-remitting MS data, followed by fine-tuning on primary progressive MS (PPMS) data.
  • Patients predicted as most responsive were preferentially enrolled in simulated trials.

Main Results:

  • In a PPMS trial simulation, the model identified patient subgroups with significantly larger treatment effects for anti-CD20 therapies.
  • The top 50% and 30% predicted responders showed improved treatment effects (HR 0.492, p=0.0218 and HR 0.361, p=0.008, respectively).
  • The model successfully identified responders to laquinimod in a separate PPMS cohort, demonstrating generalizability.

Conclusions:

  • Deep learning-based predictive enrichment can significantly increase statistical power in MS clinical trials.
  • This strategy enables shorter, more efficient proof-of-concept trials.
  • The approach holds promise for accelerating the development of novel MS treatments.