Controversy

Whether MGMT promoter methylation can be reliably predicted from routine MRI

Evidence grade: WEAK — Supported only by weak or preliminary evidence.

computed from the encoded evidence by the Atlas grading rule.

Position A

Multiple ML/DL models report AUCs 0.7-0.9 for MGMT prediction on multiparametric MRI

Position B

Well-designed studies conclude MRI cannot reliably predict MGMT; BraTS-MGMT-style tasks show near-chance external performance; positive results attributed to leakage/overfitting

Clinical stakes

MGMT governs temozolomide benefit; a false imaging surrogate could misdirect therapy or trial stratification

Open in the interactive atlas →

About this page

Curated and maintained by Resonant Labs. Reviewed by Claims are synthesized from the cited literature and graded per the Atlas methodology (about the Atlas). Last updated 2026-07-01.

This is an educational research resource from Resonant Labs, not clinical advice. Evidence grades and controversies are summarized from the literature and may change as the field evolves.