Longitudinal machine learning modeling of MS patient trajectories improves predictions of disability progression

• Temporal neural networks allow to significantly improve the prediction of disability progression in MS patients. • Disability progression can be predicted in a 2-year horizon can be predicted with an AUC-ROC of 0.85. • Longitudinal clinical history of the patients ranks amongst the most predictive variables for disability progression. Research in Multiple Sclerosis (MS) has recently focused on extracting knowledge from real-world clinical data...