Skip to main content
Fig. 3 | Acta Neuropathologica Communications

Fig. 3

From: MGMT methylation pattern of long-term and short-term survivors of glioblastoma reveals CpGs of the enhancer region to be of high prognostic value

Fig. 3

Random Forest analysis of all CpGs. Random Forest analysis demonstrates that CpG 86 has the highest predictive value of all tested CpGs. A Analysis of the raw data highlights CpGs 58, 73–79, 84–88 and 94–96 to be correlated with overall survival. Here, CpG 86 (bp + 154) demonstrate by far the most prominent value, followed by CpG 88 (bp + 180). B For additional inclusion of other predictive factors, such as temozolomide treatment, age at diagnosis, affected lobe and hemisphere, missing values had to be imputed to perform Conditional Random Forest analysis. Conditional Random Forest valued temozolomide administration and age of the patient as the strongest predictor of outcome followed by two clusters CpG 73–79 and CpG 84–88, which were similar to those with the raw data A. Also within the analysis with imputed data the methylation state of CpG 86 (bp + 154) resulted in the highest predictive value among all analyzed CpGs of MGMT

Back to article page

Acta Neuropathologica Communications

ISSN: 2051-5960

Contact us