Machine Learning and Cognitive Assessment in Multiple Sclerosis
In a study involving 222 individuals with multiple sclerosis (MS), cognitive impairment was identified in 62 participants (27.9%). The study compared published Italian MoCA cutoffs with a newly developed machine learning model, finding that the ML model provided better sensitivity and accuracy for assessing cognitive impairment (ROC-AUC = 0.787) compared to the traditional cutoffs, which had low sensitivity.
- Tags
- #MSResearch
- Most relevant to
- —
- Human efficacy
- Not established from this source
- Mechanism
- Not reported
- Evidence strength
- Not graded
- Outcome
- Not reported
Why it matters
This research is significant as it highlights the limitations of current cognitive screening methods (MoCA cutoffs) for MS patients, which may lead to underdiagnosis of cognitive impairment. The machine learning approach shows promise in improving diagnostic accuracy, potentially allowing for better patient management.
What this does not prove
The findings do not establish that the machine learning model is ready for clinical use, and further validation is needed. Additionally, the published Italian MoCA cutoffs have been shown to have insufficient sensitivity specifically for MS cognitive impairment, which could affect broader screening practices.
Next milestone
No next milestone was established from the available source.
Study facts
- Study design
- Not reported
- Participants / samples
- Not reported
- Randomised
- Not reported
- Controlled
- Not reported
- Primary endpoint met
- Not reported
- Relevant MS type
- Not reported
- Publication date
- 2026-10-06
- Evidence reviewed
- Abstract only
- Regulatory approval
- Not reported
- Research areas
- Not classified
- Biological target
- Not reported
- Pathway
- Not reported
- Population
- 222 people with MS
- Size of effect
- ROC-AUC = 0.787, sensitivity = 0.69, specificity = 0.72, balanced accuracy = 0.71
- Secondary endpoints
- Not reported
- MRI endpoints
- Not reported
- Biomarkers
- Not reported
- Safety
- Not reported
Original sources
- Primary evidenceA Feasible Machine Learning Approach to Improve Cognitive Screening in Multiple Sclerosis. ↗DOI: 10.3390/biomedicines14102262
Supporting passages (9)
publication datePublication date: 2026-10-06
interventionTitle: A Feasible Machine Learning Approach to Improve Cognitive Screening in Multiple Sclerosis.
comparatorConclusions: Published Italian MoCA cutoffs have insufficient sensitivity for screening MS-specific cognitive impairment.
primary endpointObjective: This study aimed to evaluate the diagnostic performance of published Italian MoCA cutoffs for MS-specific cognitive impairment and develop a machine learning (ML) pipeline to improve screening accuracy.
populationMethods: We prospectively enrolled 222 people with MS who underwent both MoCA and BICAMS assessment.
findingsResults: Cognitive impairment was identified in 62 (27.9%) participants.
limitationsConclusions: Published Italian MoCA cutoffs have insufficient sensitivity for screening MS-specific cognitive impairment.
effect sizeThe ML model achieved good discrimination (ROC-AUC = 0.787, 95% CI 0.717-0.852), with sensitivity = 0.69, specificity = 0.72, and balanced accuracy = 0.71.
peer reviewedPublication types: Journal Article
AI assessment, not yet reviewed by a person · version 1 · Community votes are separate from evidence review.