Background: Adjuvant chemotherapy after surgery improves survival of patients with stage II–III, resectable gastric cancer. However, the overall survival benefit observed after adjuvant chemotherapy is moderate, suggesting that not all patients with resectable gastric cancer treated with adjuvant chemotherapy benefit from it. We aimed to develop and validate a predictive test for adjuvant chemotherapy response in patients with resectable, stage II–III gastric cancer. Methods: In this multi-cohort, retrospective study, we developed through a multi-step strategy a predictive test consisting of two rule-based classifier algorithms with predictive value for adjuvant chemotherapy response and prognosis. Exploratory bioinformatics analyses identified biologically relevant candidate genes in gastric cancer transcriptome datasets. In the discovery analysis, a four-gene, real-time RT-PCR assay was developed and analytically validated in formalin-fixed, paraffin-embedded (FFPE) tumour tissues from an internal cohort of 307 patients with stage II–III gastric cancer treated at the Yonsei Cancer Center with D2 gastrectomy plus adjuvant fluorouracil-based chemotherapy (n=193) or surgery alone (n=114). The same internal cohort was used to evaluate the prognostic and chemotherapy response predictive value of the single patient classifier genes using associations with 5-year overall survival. The results were validated with a subset (n=625) of FFPE tumour samples from an independent cohort of patients treated in the CLASSIC trial (NCT00411229), who received D2 gastrectomy plus capecitabine and oxaliplatin chemotherapy (n=323) or surgery alone (n=302). The primary endpoint was 5-year overall survival. Findings: We identified four classifier genes related to relevant gastric cancer features (GZMB, WARS, SFRP4, and CDX1) that formed the single patient classifier assay. In the validation cohort, the prognostic single patient classifier (based on the expression of GZMB, WARS, and SFRP4) identified 79 (13%) of 625 patients as low risk, 296 (47%) as intermediate risk, and 250 (40%) as high risk, and 5-year overall survival for these groups was 83·2% (95% CI 75·2–92·0), 74·8% (69·9–80·1), and 66·0% (60·1–72·4), respectively (p=0·012). The predictive single patient classifier (based on the expression of GZMB, WARS, and CDX1) assigned 281 (45%) of 625 patients in the validation cohort to the chemotherapy-benefit group and 344 (55%) to the no-benefit group. In the predicted chemotherapy-benefit group, 5-year overall survival was significantly improved in those patients who had received adjuvant chemotherapy after surgery compared with those who received surgery only (80% [95% CI 73·5–87·1] vs 64·5% [56·8–73·3]; univariate hazard ratio 0·47 [95% CI 0·30–0·75], p=0·0015), whereas no such improvement in 5-year overall survival was observed in the no-benefit group (72·9% [66·5–79·9] in patients who received chemotherapy plus surgery vs 72·5% [65·8–79·9] in patients who only had surgery; 0·93 [0·62–1·38], p=0·71). The predictive single patient classifier groups (chemotherapy benefit vs no-benefit) could predict adjuvant chemotherapy benefit in terms of 5-year overall survival in the validation cohort (p interaction =0·036 in univariate analysis). Similar results were obtained in the internal evaluation cohort. Interpretation: The single patient classifiers validated in this study provide clinically important prognostic information independent of standard risk-stratification methods and predicted chemotherapy response after surgery in two independent cohorts of patients with resectable, stage II–III gastric cancer. The single patient classifiers could complement TNM staging to optimise decision making in patients with resectable gastric cancer who are eligible for adjuvant chemotherapy after surgery. Further validation of these results in prospective studies is warranted. Funding: Ministry of ICT and Future Planning; Ministry of Trade, Industry, and Energy; and Ministry of Health and Welfare.
Bibliographical noteFunding Information:
This study was supported by the Bio & Medical Technology Development Program of the National Research Foundation funded by the Ministry of ICT and Future Planning ( NRF-2015M3A9D7029834 ); the Technology Innovation Program funded by the Ministry of Trade, Industry, and Energy ( 10041653 ); the National R&D Program for Cancer Control funded by the Ministry of Health and Welfare ( 1020390 and 1320360 ); and the Korea Health Technology R&D Project through the Korea Health Industry Development Institute funded by the Ministry of Health and Welfare (HI14C1324). We thank Soonmyung Paik (Severance Biomedical Science Institute, Yonsei University College of Medicine, Seoul, South Korea) for his invaluable comments and advice.
All Science Journal Classification (ASJC) codes