A Novel Machine Learning Approach for Central Nervous System Tumor Classification from DNA Methylation

2026-07-01

AI Summary

This study addresses the poor cross-cohort generalizability, methodological shortcomings, and unstable multi-class evaluation commonly observed in DNA methylation–based classification of central nervous system tumors. To overcome these limitations, we propose a streamlined machine learning pipeline integrating sparse random projection for dimensionality reduction with multinomial logistic regression, coupled with stratified cross-validation and a rigorous evaluation protocol. The approach achieves high generalization performance while maintaining model simplicity and clinical interpretability. Evaluated on a reference cohort of 2,801 samples, the method attains an average accuracy of 96%. In an independent clinical cohort of 1,104 cases, it yields 86% accuracy at the 91-class level and 93% at the family level—representing a 4–5 percentage point improvement over existing methods—and demonstrates strong practical utility for clinical deployment.

Abstract

NA methylation profiling has become a powerful approach for central nervous system (CNS) tumor classification, yet important challenges remain regarding cross-cohort transferability, methodological correctness, and robust multiclass evaluation. In this work, we propose a novel and methodologically rigorous machine-learning approach for methylation-based CNS tumor classification that combines Sparse Random Projection for dimensionality reduction with multinomial logistic regression for classification. We evaluate the proposed approach in the same general experimental setting established by a widely used reference classifier. On the 2,801-sample reference cohort, our method achieves a mean accuracy of 96\% under stratified 3-fold cross-validation. On the independent 1,104-sample clinical evaluation cohort, it reaches 86\% accuracy at the 91-class level and 93\% when predictions are evaluated at the methylation class family level. These results improve upon the corresponding state-of-the-art reference figures of 82\% class-level concordance and 88\% family-level concordance, yielding absolute gains of approximately 4 and 5 percentage points, respectively. This improvement is clinically relevant: in a diagnostic setting, a 5-point increase in correct tumor classification can directly affect cancer subtype assignment and, in turn, influence treatment selection and downstream clinical decision-making. Our results show that the proposed model, grounded in stronger methodological practice in machine learning, consistently outperforms the previous state of the art across evaluation settings and can materially improve the reliability of CNS tumor classification.

Problem

• CNS tumor classification
• DNA methylation
• cross-cohort transferability
• multiclass evaluation
• methodological correctness

Innovation

• Sparse Random Projection
• multinomial logistic regression
• DNA methylation profiling
• CNS tumor classification
• cross-cohort generalization