A Machine Learning Pipeline for Multiple Sclerosis Biomarker Discovery: Comparing explainable AI and Traditional Statistical Approaches

2025-09-26

AI Summary

This study addresses the limited reliability and interpretability of biomarker discovery in multiple sclerosis (MS) using peripheral blood mononuclear cells (PBMCs). We propose a novel integrative framework combining explainable AI—specifically SHAP (Shapley Additive Explanations)—with conventional differential expression analysis. The method integrates eight publicly available microarray datasets, employs an XGBoost classifier optimized via Bayesian hyperparameter tuning, implements multi-dataset harmonized preprocessing, and incorporates gene set enrichment analysis. Results demonstrate complementary feature selection between SHAP and traditional methods, with their integration substantially deepening biological mechanistic insight. Key pathogenic genes linked to sphingolipid signaling, Th cell differentiation, and Epstein–Barr virus response were identified; several SHAP-prioritized genes were independently validated functionally. This framework enhances both the robustness and interpretability of MS biomarker discovery and advances understanding of MS immunopathogenesis, yielding novel candidate therapeutic targets for translational research.

Technology Category

• Machine Learning: Transparent, Interpretable, Explainable ML
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

We present a machine learning pipeline for biomarker discovery in Multiple Sclerosis (MS), integrating eight publicly available microarray datasets from Peripheral Blood Mononuclear Cells (PBMC). After robust preprocessing we trained an XGBoost classifier optimized via Bayesian search. SHapley Additive exPlanations (SHAP) were used to identify key features for model prediction, indicating thus possible biomarkers. These were compared with genes identified through classical Differential Expression Analysis (DEA). Our comparison revealed both overlapping and unique biomarkers between SHAP and DEA, suggesting complementary strengths. Enrichment analysis confirmed the biological relevance of SHAP-selected genes, linking them to pathways such as sphingolipid signaling, Th1/Th2/Th17 cell differentiation, and Epstein-Barr virus infection all known to be associated with MS. This study highlights the value of combining explainable AI (xAI) with traditional statistical methods to gain deeper insights into disease mechanism.

Problem

• Comparing explainable AI with traditional statistical methods for biomarker discovery
• Identifying Multiple Sclerosis biomarkers using machine learning on PBMC datasets
• Discovering complementary biomarkers through SHAP analysis and differential expression

Innovation

• Machine learning pipeline integrates multiple microarray datasets
• XGBoost classifier optimized via Bayesian search for biomarker discovery
• SHAP explanations compared with traditional differential expression analysis