Skip to Main Content (Press Enter)

Logo UNISR
  • ×
  • Home
  • Persone
  • Pubblicazioni
  • Facoltà
  • Ambiti Di Ricerca
  • Attrezzature

UNIFIND
Logo UNISR

|

UNIFIND

unisr.it
  • ×
  • Home
  • Persone
  • Pubblicazioni
  • Facoltà
  • Ambiti Di Ricerca
  • Attrezzature
  1. Pubblicazioni

Machine learning for multiple sclerosis classification and disability prediction using clinical and MRI data

Articolo
Data di Pubblicazione:
2026
Citazione:
Machine learning for multiple sclerosis classification and disability prediction using clinical and MRI data / Valsasina, P., Storelli, L., Tedone, N., Pantano, P., Piervincenzi, C., Tommasin, S., Gallo, A., Altieri, M., Maggi, G., De Stefano, N., Bianchi, A., Battaglini, M., Mazzetti, G., Pagani, E., Rocca, M.A., Filippi, M.. - In: FRONTIERS IN ARTIFICIAL INTELLIGENCE. - ISSN 2624-8212. - 9:(2026). [10.3389/frai.2026.1792870]
Abstract:
Introduction Multiple sclerosis (MS) is a complex disease characterized by diverse clinical presentations and progression patterns. Accurate classification and prediction of disease severity are crucial for personalized treatment. We applied machine learning (ML) to demographic, clinical and MRI data to distinguish MS patients from healthy controls (HC), classify MS phenotypes and predict disability using the Expanded Disability Status Scale (EDSS) score.Methods We included 1,554 MS patients and 520 HC from the Italian Neuroimaging Network Initiative repository, all with neurological assessment and brain T2-/3D T1-weighted MRI. Derived MRI features included total and regional T2 lesion volumes (LV), and normalized tissue volumes from cortical and subcortical grey matter (GM), white matter, cerebellum and brainstem. ML models, including support vector machines, multi-layer perceptron networks, Random Forest and Gradient Boosting were trained for classification and prediction tasks. SHAP analysis ranked the most influential variables.Results ML models achieved 89-96% accuracy in distinguishing MS patients from HC, driven mainly by T2 LV and brainstem/cerebellar GM volumes. Relapsing vs progressive MS was classified with 92% accuracy, with EDSS, age, thalamic and cortical GM volumes as key predictors. EDSS prediction achieved an intra-class correlation of 0.56-0.76; most relevant contributors were T2 LV, sex, cortical/cerebellar GM and thalamic volumes.Discussion ML models demonstrated high accuracy in detecting MS, differentiating phenotypes, and predicting disability. Integrating demographic, clinical and MRI measures emerges as an effective strategy for patients' classification and disease severity assessment.
Tipologia CRIS:
1.1 Articolo in rivista
Elenco autori:
Valsasina, Paola; Storelli, Loredana; Tedone, Nicolò; Pantano, Patrizia; Piervincenzi, Claudia; Tommasin, Silvia; Gallo, Antonio; Altieri, Manuela; Maggi, Gianpaolo; De Stefano, Nicola; Bianchi, Alessia; Battaglini, Marco; Mazzetti, Giulia; Pagani, Elisabetta; Rocca, Maria A.; Filippi, Massimo
Autori di Ateneo:
FILIPPI MASSIMO
ROCCA MARIA ASSUNTA
Link alla scheda completa:
https://iris.unisr.it/handle/20.500.11768/201858
Link al Full Text:
https://iris.unisr.it//retrieve/handle/20.500.11768/201858/355398/Front%20Artif%20Intell%209_1792870.pdf
Pubblicato in:
FRONTIERS IN ARTIFICIAL INTELLIGENCE
Journal
  • Utilizzo dei cookie

Realizzato con VIVO | Designed by Cineca | 26.11.1.0