Combining Clinical and Genetic Data to Predict Response to Fingolimod Treatment in Relapsing Remitting Multiple Sclerosis Patients: A Precision Medicine Approach

Abstract

A personalized approach is strongly advocated for treatment selection in Multiple Sclerosis patients due to the high number of available drugs. Machine learning methods proved to be valuable tools in the context of precision medicine. In the present work, we applied machine learning methods to identify a combined clinical and genetic signature of response to fingolimod that could support the prediction of drug response. Two cohorts of fingolimod-treated patients from Italy and France were enrolled and divided into training, validation, and test set. Random forest training and robust feature selection were performed in the first two sets respectively, and the independent test set was used to evaluate model performance. A genetic-only model and a combined clinical–genetic model were obtained. Overall, 381 patients were classified according to the NEDA-3 criterion at 2 years; we identified a genetic model, including 123 SNPs, that was able to predict fingolimod response with an AUROC= 0.65 in the independent test set. When combining clinical data, the model accuracy increased to an AUROC= 0.71. Integrating clinical and genetic data by means of machine learning methods can help in the prediction of response to fingolimod, even though further studies are required to definitely extend this approach to clinical applications

A two-years real-word study with fingolimod: early predictors of efficacy and an association between EBNA-1 IgG titers and multiple sclerosis progression

“…Patients recruited for this multicenter study showed a lower proportion of NEDA-3 condition compared to most of the studies performed in real-world: 56.6% ( 28 ), 44% ( 29 ), 48.3% ( 8 ), 44% ( 30 ), but similar to other real-world studies, 22% ( 31 ), and post-hoc analyses of randomized clinical trials, 29.5% ( 32 ), and 31.0% ( 33 ). The variability in NEDA-3 proportion could be explained by the heterogeneity of MS patients included in the different real-world studies.…”

“…With this aim, we performed a retrospective study analyzing different clinical, radiological, genetic and environmental factors as possible early predictors of response in MS patients treated with fingolimod along 24 months. Some clinical factors have been previously related to fingolimod response as early predictors ( 8 , 9 ). Regarding genetic factors, they have been searched before in relation to the response to the different DMTs in MS. Pharmacogenomic studies have shown that the human leukocyte antigen (HLA) could help to better identify appropriated candidates to each treatment ( 10 , 11 ), although in other occasions not ( 12 , 13 ).…”

Personalized Treatment for Multiple Sclerosis: The Role of Precision Medicine

“…The etiology and pathogenesis of MS are complex and multifactorial, with a combination of genetic and environmental factors implicated in its development and progression (1). Despite significant advancements in MS research, the underlying mechanisms of the disease remain poorly understood, and there is currently no cure for MS (2). Precision medicine is an emerging approach to healthcare that aims to optimize medical treatment by tailoring it to the specific characteristics of each patient.…”

Vision Impairment prediction for patients diagnosed with Multiple Sclerosis: Cosmos based machine learning model training and evaluation

“…14 However, their analysis included features commonly not available within de-identified structured EHR datasets, such as the EDSS and functional sub-scores. Other work focused on predicting vision impairment using genetic markers 15,16 and imaging data. 17,18 EHRs are widely available, and the rapid development of predictive models is facilitated by the use of structured data collected and readily available within the EHR.…”