Sparse random projection plus multinomial logistic regression reaches 86% accuracy on 91-class CNS tumor classification from methylation data and 93% at family level, improving 4-5 points over prior reference on an independent 1,104-sample cohort.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Novel Machine Learning Approach for Central Nervous System Tumor Classification from DNA Methylation
Sparse random projection plus multinomial logistic regression reaches 86% accuracy on 91-class CNS tumor classification from methylation data and 93% at family level, improving 4-5 points over prior reference on an independent 1,104-sample cohort.