Accurate pathological diagnosis is crucial for optimal management of patients with cancer. For the approximately 100 known tumour types of the central nervous system, standardization of the diagnostic process has been shown to be particularly challenging—with substantial inter-observer variability in the histopathological diagnosis of many tumour types. Here we present a comprehensive approach for the DNA methylation-based classification of central nervous system tumours across all entities and age groups, and demonstrate its application in a routine diagnostic setting. We show that the availability of this method may have a substantial impact on diagnostic precision compared to standard methods, resulting in a change of diagnosis in up to 12% of prospective cases. For broader accessibility, we have designed a free online classifier tool, the use of which does not require any additional onsite data processing. Our results provide a blueprint for the generation of machine-learning-based tumour classifiers across other cancer entities, with the potential to fundamentally transform tumour pathology.

The World Health Organization (WHO) classification and grading system attempts to predict the clinical course of meningiomas based on morphological parameters. However, because of high interobserver variation of some criteria, more reliable prognostic markers are required. Here, we assessed the TERT promoter for mutations in the hotspot regions C228T and C250T in meningioma samples from 252 patients. Mutations were detected in 16 samples (6.4% across the cohort, 1.7%, 5.7%, and 20.0% of WHO grade I, II, and III cases, respectively). Data were analyzed by t test, Fisher’s exact test, log-rank test, and Cox proportional hazard model. All statistical tests were two-sided. Within a mean follow-up time in surviving patients of 68.1 months, TERT promoter mutations were statistically significantly associated with shorter time to progression ( P < .001). Median time to progression among mutant cases was 10.1 months compared with 179.0 months among wild-type cases. Our results indicate that the inclusion of molecular data (ie, analysis of TERT promoter status) into a histologically and genetically integrated classification and grading system for meningiomas increases prognostic power. Consequently, we propose to incorporate the assessment of TERT promoter status in upcoming grading schemes for meningioma.