Predicting disease activity in patients with multiple sclerosis: An explainable machine‐learning approach in the Mavenclad trials

Abstract

Multiple sclerosis (MS) is among the most common autoimmune disabling neurological conditions of young adults and affects more than 2.3 million people worldwide. Predicting future disease activity in patients with MS based on their pathophysiology and current treatment is pivotal to orientate future treatment. In this respect, we used machine learning to predict disease activity status in patients with MS and identify the most predictive covariates of this activity. The analysis is conducted on a pooled population of 1935 patients enrolled in three cladribine tablets clinical trials with different outcomes: relapsing–remitting MS (from CLARITY and CLARITY‐Extension trials) and patients experiencing a first demyelinating event (from the ORACLE‐MS trial). We applied gradient‐boosting (from XgBoost library) and Shapley Additive Explanations (SHAP) methods to identify patients' covariates that predict disease activity 3 and 6 months before their clinical observation, including patient baseline characteristics, longitudinal magnetic resonance imaging readouts, and neurological and laboratory measures. The most predictive covariates for early identification of disease activity in patients were found to be treatment duration, higher number of new combined unique active lesion count, higher number of new T1 hypointense black holes, and higher age‐related MS severity score. The outcome of this analysis improves our understanding of the mechanism of onset of disease activity in patients with MS by allowing their early identification in clinical settings and prompting preventive measures, therapeutic interventions, or more frequent patient monitoring.

Machine Learning in Modeling Disease Trajectory and Treatment Outcomes: An Emerging Enabler for Model‐Informed Precision Medicine

“…In a recent example from our research group, disease activity in patients with multiple sclerosis (MS) was predicted using supervised multivariable explainable ML models of longitudinal data in the phase III clinical trials of cladribine. 11 Using XGboost, the models combined patient baseline characteristics, longitudinal magnetic resonance imaging data, neurological assessments, and laboratory measures in 1,935 patients to predict disease activity 3 and 6 months before it was clinically observed. Several predictive factors for early disease activity were identified, including the duration of cladribine treatment, the number of new combined unique active lesions, the number of new T1 hypointense black holes, and the age-related MS severity score.…”

Artificial Intelligence for Quantitative Modeling in Drug Discovery and Development: An Innovation and Quality Consortium Perspective on Use Cases and Best Practices

“…For instance, Basu et al 60 used an explainable ML approach to predict future disease activity in patients with multiple sclerosis (MS) and identify the most predictive covariates. The analysis was conducted on a pooled population of 1,935 patients enrolled in 3 cladribine phase III clinical trials with different outcomes.…”

“…For instance, Basu et al 60 . used an explainable ML approach to predict future disease activity in patients with multiple sclerosis (MS) and identify the most predictive covariates.…”

An introduction to causal inference for pharmacometricians

“… 9 The use of DAGs for covariate selection in epidemiological studies of relevance to pharmacometrics, for example, for characterizing longitudinal progression toward end‐stage renal disease 10 or for characterizing overall survival in oncology in response to immune checkpoint inhibitors (CPIs). 11 , 12 The application of interpretable artificial intelligence/machine‐learning (AI/ML) algorithms (e.g., with interpretation assisted by Shapley values) to population pharmacokinetic modeling 13 and prediction of relapse and related disease activity in multiple sclerosis, 14 contemporaneous with an increased recognition of the interpretive value of formal causal frameworks in AI/ML research. 15 , 16 , 17 , 18 The advent of real‐world evidence (RWE) usage in pharmacometric analyses, 19 contemporaneous with a growing body of guidance for the use of RWE that advocates for the use of causal DAGs.…”

“…The application of interpretable artificial intelligence/machine‐learning (AI/ML) algorithms (e.g., with interpretation assisted by Shapley values) to population pharmacokinetic modeling 13 and prediction of relapse and related disease activity in multiple sclerosis, 14 contemporaneous with an increased recognition of the interpretive value of formal causal frameworks in AI/ML research. 15 , 16 , 17 , 18…”