Related Experiment Video
Updated: Mar 6, 2026
A Method of Trigonometric Modelling of Seasonal Variation Demonstrated with Multiple Sclerosis Relapse Data
Published on: December 9, 2015
Predictors of short-term, relapse-independent progression in multiple sclerosis: A machine learning approach based on
Antonio Ianniello1, Elena Barbuti2, Maria Francesca Capobianco3
1Department of Human Neurosciences, Sapienza University of Rome, Italy; Multiple Sclerosis Center, San Pietro Fatebenetratelli, Rome, Italy.
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.
Insights
Machine learning models can predict progression independent of relapse activity (PIRA) in multiple sclerosis (MS) using clinical and MRI data. Incorporating longitudinal imaging improves prediction accuracy for earlier treatment strategies.
Area of Science:
- Neurology
- Radiology
- Artificial Intelligence
Background:
- Progression independent of relapse activity (PIRA) is a significant contributor to long-term disability in multiple sclerosis (MS), even in early disease stages.
- Predicting short-term PIRA in routine clinical practice remains challenging, hindering timely intervention.
- Conventional clinical and MRI metrics alone are insufficient for accurate short-term PIRA prediction.
Purpose of the Study:
- To develop and evaluate machine learning (ML) models for predicting PIRA in relapsing MS.
- Utilize routinely available clinical and conventional MRI-derived features for PIRA prediction.
- Assess the utility of longitudinal imaging data in enhancing PIRA prediction accuracy.
Main Methods:
- Developed two ML models (Naïve Bayes classifier) to predict PIRA at 24 and 36 months in relapsing MS patients.
- Employed baseline and longitudinal clinical data, including brain and spine lesion burden, atrophy, and change in structural connectivity (ChaCo) scores.
- Utilized feature selection and class balancing with Synthetic Minority Over-sampling Technique (SMOTE) for model training.
Main Results:
- The 24-month PIRA prediction model achieved moderate discriminative performance (AUC = 0.73), primarily driven by baseline features.
- The 36-month PIRA prediction model, incorporating longitudinal data, demonstrated improved accuracy (AUC = 0.83).
- Key predictors for the 36-month model included baseline disability, brain volume changes, new cervical cord lesions, and baseline ChaCo features.
Conclusions:
- Machine learning models integrating clinical and conventional MRI features can predict short-term PIRA with moderate to high accuracy.
- The inclusion of longitudinal imaging changes significantly enhances prediction performance.
- These ML models may facilitate earlier, individualized treatment strategies for MS patients to mitigate disability progression.
Related Concept Videos
01:18Steps in Outbreak Investigation
01:25Multiple Regression
Farmers can use multiple regression to determine the crop yield based on more than one factor, such as water availability, fertilizer, soil properties, etc. Here, the crop yield is the response or dependent variable as it depends on the other independent variables. The analysis requires the construction of a scatter plot...