Wei JH, et al. - Researchers undertook this retrospective analysis and multicentre validation study, to develop a classifier based on single-nucleotide polymorphisms (SNPs) to enhance the predictive accuracy for renal cell carcinoma recurrence. In addition, they determined if intratumour heterogeneity affected the precision of the classifier. A six-SNP-based classifier was developed using LASSO Cox regression, based on the association between SNP status and patients' recurrence-free survival. They validated the six-SNP-based classifier in the internal testing set (n=226), the independent validation set (Chinese multicentre study; 428 patients treated between Jan 1, 2004 and Dec 31, 2012, at three hospitals in China), and The Cancer Genome Atlas (TCGA) set (441 retrospectively identified patients who underwent resection between 1998 and 2010 for localised clear cell renal cell carcinoma in the USA). Findings suggest a practical and reliable predictive value of this six-SNP-based classifier that can complement the existing staging system for predicting localized renal cell carcinoma recurrence after surgery. This may help physicians to make more informed treatment decisions about adjuvant therapy. The accuracy of the six-SNP-based classifier as a reliable predictor of recurrence was not affected by the intratumor heterogeneity. For patients at differing risks of recurrence, treatment decisions could be made with the help of the classifier.