Nomogram to predict the presence of EGFR activating mutation in lung adenocarcinoma

摘要: Epidermal growth factor receptor (EGFR) tumour genotyping is crucial to guide treatment decisions regarding the use of EGFR tyrosine kinase inhibitors in nonsmall cell lung cancer (NSCLC). However, some patients may not be able obtain testing, either because tissue limited and/or tests are routinely offered. Here, we aimed build a model-based nomogram allow for prediction presence mutations NSCLC. We retrospectively collected clinical and pathological data on 3,006 with NSCLC who had their tumours genotyped at five institutions worldwide. Variables interest were integrated multivariate logistic regression model. In 2,392 non-Asian adenocarcinomas, most important predictors harbouring mutation were: lower tobacco smoking exposure (OR 0.41, 95% CI 0.37-0.46), longer time interval between cessation diagnosis 2.19, 1.71-2.80), advanced stage 1.58, 1.18-2.13), papillary 4.57, 3.14-6.66) or bronchioloalveolar 2.84, 1.98-4.06) histologically predominant subtype. A was established showed excellent discriminating accuracy: concordance index an independent validation dataset 0.84. As practices transition incorporating as part routine care, this could highly useful predict adenocarcinoma when mutational profiling available possible.