TaqMan low-density arrays and analysis by artificial neuronal networks predict response to neoadjuvant chemoradiation
Ute Warnecke-Eberz1, Ralf Metzger, Elfriede Bollschweiler
1Center for Integrated Oncology (CIO), University Hospital of Cologne, Kerpener Strasse 62, 50937 Köln, Germany. ute.warnecke-eberz@uk-koeln.de
Aims:
Neoadjuvant radiochemotherapy of locally advanced esophageal cancer is only effective for patients with major histopathological response. A total of 17 genes were selected to predict histopathologic tumor response to chemoradiation (cisplatin, 5-fluorouracil, 36 Gy).
Materials & Methods:
For gene-expression analysis quantitative TaqMan low-density arrays were applied. Expression levels in pretreatment biopsies of 41 patients (cT2-4, Nx, M0) were compared with the degree of histopathologic regression in resected specimens applying univariate, multivariate and artificial neuronal network analyses.
Results:
Dihydropyrimidine dehydrogenase was identified as an independent predictor associated with major response (p < 0.002). Multivariate analysis of the marker combination provided response prediction with 75.0% sensitivity, 81.0% specificity and 78.1% accuracy. Artificial neuronal network analysis was the best predictive model for major histopathologic response (80% sensitivity, 90.5% specificity and 85.4% accuracy), representing a clinically practical system.
Conclusion:
Low-density-array RT-PCR analyzed by artificial neuronal network predicts histopathologic response to neoadjuvant chemoradiation in our patient collective, and could be used to further individualize treatment strategies in esophageal cancer.
