| Title: |
Predictors of short-term, relapse-independent progression in multiple sclerosis: A machine learning approach based on clinical data and conventional MRI-derived features |
| Authors: |
Ianniello A.; Barbuti E.; Capobianco M. F.; Tranfa M.; Miele C.; Ruggieri S.; Pontillo G.; Cocozza S.; Pantano P.; Pozzilli C.; Cuocolo R.; Petracca M. |
| Contributors: |
Ianniello, A.; Barbuti, E.; Capobianco, M. F.; Tranfa, M.; Miele, C.; Ruggieri, S.; Pontillo, G.; Cocozza, S.; Pantano, P.; Pozzilli, C.; Cuocolo, R.; Petracca, M. |
| Publication Year: |
2026 |
| Subject Terms: |
Brain atrophy; Conventional MRI biomarker; Machine learning; Multiple sclerosi; Progression independent of relapse activity; Spinal cord atrophy |
| Description: |
Background: Progression independent of relapse activity (PIRA) contributes to long-term disability in multiple sclerosis (MS), even in early stages. However, predicting short-term PIRA in routine clinical settings remains a challenge. Objectives: To develop and evaluate machine learning (ML) models to predict PIRA in relapsing MS using routinely available clinical and conventional MRI-derived features. Methods: We developed two ML models to predict PIRA at 24 and 36 months in relapsing MS using baseline and longitudinal clinical and conventional MRI-derived data including brain and spine lesion burden, atrophy, and change in structural connectivity (ChaCo) scores. A Naïve Bayes classifier was trained after feature selection and class balancing with Synthetic Minority Over-sampling Technique (SMOTE). Results: Among 186 patients, 12.4% experienced PIRA at 24 months. In a longitudinal subset (n = 81), 19.7% developed PIRA at 36 months. The 24-month model, achieved moderate discriminative performance (AUC = 0.73), mainly driven by baseline features. The 36-month model, including baseline disability, brain volume and volume change over time, new cervical cord lesions and baseline ChaCo features, showed improved accuracy (AUC = 0.83). Conclusions: ML models using clinical and conventional MRI features can predict short-term PIRA with moderate-to-high accuracy. Incorporating imaging changes over time enhances prediction and may support earlier individualized treatment strategies. |
| Document Type: |
article in journal/newspaper |
| Language: |
English |
| Relation: |
info:eu-repo/semantics/altIdentifier/pmid/41780422; info:eu-repo/semantics/altIdentifier/wos/WOS:001709956500001; volume:483; firstpage:1; lastpage:6; numberofpages:6; journal:JOURNAL OF THE NEUROLOGICAL SCIENCES; https://hdl.handle.net/11386/4939163 |
| DOI: |
10.1016/j.jns.2026.125846 |
| Availability: |
https://hdl.handle.net/11386/4939163; https://doi.org/10.1016/j.jns.2026.125846 |
| Accession Number: |
edsbas.360F9B85 |
| Database: |
BASE |