# Leveraging hand-crafted radiomics on multicenter FLAIR MRI for predicting disability worsening in people with multiple sclerosis

## TL;DR

This study uses machine learning and MRI scans to predict worsening disability in multiple sclerosis patients, showing potential for better tracking disease progression.

## Contribution

The novel use of hand-crafted radiomics features from FLAIR MRI with ML models to predict disability worsening in MS.

## Key findings

- The LGBM model with harmonized radiomics and clinical features outperformed clinical-only models in predicting disability worsening.
- Key predictive features included GLCM maximum probability in WML and GLDM dependence non-uniformity in NAWM.
- Short-term longitudinal changes showed limited predictive power compared to other features.

## Abstract

Multiple sclerosis (MS) is an autoimmune disease of the central nervous system, leading to varying degrees of functional impairment. Conventional tools, such as the Expanded Disability Status Scale (EDSS), lack sensitivity to subtle disease worsening. Radiomics provides a quantitative imaging approach to address this limitation. This study applied machine learning (ML) and radiomics features from T2-weighted Fluid-Attenuated Inversion Recovery (FLAIR) magnetic resonance imaging (MRI) to predict disability worsening in MS.

A retrospective analysis was performed on real-world data from 247 PwMS across two centers. Disability worsening was defined as a change in EDSS over two years. FLAIR MRIs underwent preprocessing and super-resolution reconstruction to enhance low-resolution images. White matter lesions (WML) were segmented using the Lesion Segmentation Toolbox (LST), and tissue segmentation was performed using sequence Adaptive Multimodal Segmentation. Radiomics features from WML and normal-appearing white matter (NAWM) were extracted using Pyradiomics, harmonized with Longitudinal ComBat, followed by recursive feature elimination for feature selection. Elastic Net, Balanced Random Forest (BRFC), and Light Gradient-Boosting Machine (LGBM) models were trained and evaluated.

The LGBM model with harmonized radiomics and clinical features outperformed the clinical-only model, achieving a test area under the precision-recall curve (PR AUC) of 0.20 and a receiver operating characteristic area under the curve (ROC AUC) of 0.64. Key predictive features, among others, included Gray-Level Co-Occurrence Matrix (GLCM) maximum probability (WML) and Gray-Level Dependence Matrix (GLDM) dependence non-uniformity (NAWM). However, short-term longitudinal changes showed limited predictive power (PR AUC = 0.11, ROC AUC = 0.69).

These findings highlight the potential of ML-driven radiomics in predicting disability worsening, warranting validation in larger, balanced datasets and exploration of advanced deep learning approaches.