Disease phenotype prediction in multiple sclerosis

Progressive multiple sclerosis (PMS) is currently diagnosed retrospectively. Here, we work toward a set of biomarkers that could assist in early diagnosis of PMS. A selection of cerebrospinal fluid metabolites (n = 15) was shown to differentiate between PMS and its preceding phenotype in an independent cohort (AUC = 0.93). Complementing the classifier with conformal prediction showed that highly confident predictions could be made, and that three out of eight patients devel-oping PMS within three years of sample collection were predicted as PMS at that time point. Finally, this methodology was applied to PMS patients as part of a clin-ical trial for intrathecal treatment with rituximab. The methodology showed that 68% of the patients decreased their similarity to the PMS phenotype one year af-ter treatment. In conclusion, the inclusion of confidence predictors contributes with more information compared to traditional machine learning, and this infor-mation is relevant for disease monitoring.

Automated summary

Currently, there is a need for biomarkers to assist in early diagnosis of progressive multiple sclerosis (PMS). Research has shown that a selection of cerebrospinal fluid metabolites can differentiate between PMS and its preceding phenotype. By using predictive methods, highly confident predictions can be made for patients who will develop PMS within three years. In a clinical trial, the methodology was applied to PMS patients receiving intrathecal treatment, and it was found that 68% of the patients decreased their similarity to the PMS phenotype after one year of treatment.