MiRNA expression patterns predict survival in glioblastoma

Background: In order to define new prognostic subgroups in patients with glioblastoma a miRNA screen (> 1000 miRNAs) from paraffin tissues followed by a bio-mathematical analysis was performed. Methods: 35 glioblastoma patients treated between 7/2005 - 8/2008 at a single institution with surgery and postoperative radio(chemo) therapy were included in this retrospective analysis. For microarray analysis the febit biochip "Geniom (R) Biochip MPEA homo-sapiens" was used. Total RNA was isolated from FFPE tissue sections and 1100 different miRNAs were analyzed. Results: It was possible to define a distinct miRNA expression pattern allowing for a separation of distinct prognostic subgroups. The defined miRNA pattern was significantly associated with early death versus long-term survival (split at 450 days) (p = 0.01). The pattern and the prognostic power were both independent of the MGMT status. Conclusions: At present, this is the first dataset defining a prognostic role of miRNA expression patterns in patients with glioblastoma. Having defined such a pattern, a prospective validation of this observation is required.