A recent study demonstrated that machine learning models can effectively predict the progression of patients with multiple sclerosis (MS), raising new hope for improved management of the disease. The study, led by Edward De Brouwer of the Catholic University of Leuven in Belgium, was published this week in PLOS Digital Health.
Multiple sclerosis is a chronic progressive disease in which the immune system attacks the protective sheath around the nerves, worsening disability over time. Over the past decade, the global prevalence of MS has increased by more than 30%, making it increasingly important to predict its progression. Accurate predictions can help patients better plan their lives and help doctors tailor treatment more effectively.
The study analyzed data from 15,240 adults with at least a three-year history of MS. These patients were treated at 146 MS centers across 40 countries, providing a comprehensive dataset that researchers used to train advanced machine learning models that predicted the likelihood of disease progression over the coming months and years.
The results were promising. The model demonstrated an average prediction accuracy score of 0.71 out of 1. This score, known as the area under the receiver operating characteristic curve (ROC-AUC), reflects how accurately the model can predict future disability progression. Higher scores indicate better performance. Importantly, the study found that a patient's past disability progression was a stronger predictor of future progression than their treatment history or relapse history.
Edward de Brouwer highlighted the importance of this study, saying: “Using the clinical histories of more than 15,000 patients with multiple sclerosis, we have trained a machine learning model that can reliably predict the likelihood of disability progression over the next two years. This model is broadly applicable as it only uses routinely collected clinical variables.”
These findings suggest that machine learning models have the potential to significantly improve how MS is managed. By providing accurate predictions, these models can help doctors make better treatment decisions and assist patients in planning for the future. Because the models use standard clinical data, they can be easily integrated into routine clinical practice.
The researchers believe that this model has the potential to significantly improve the quality of life for people with multiple sclerosis. They recommend further studies to test the model's effectiveness in real-world situations. Advances in machine learning represent a major step forward in understanding and managing complex diseases like multiple sclerosis.
The study highlights how technology can provide valuable insights, support better medical decision-making and offer new hope to patients suffering from chronic and progressive conditions.
