ABSTRACT
Limited studies have been reported about the function of low level of microsatellite instability (MSI-L) in cancer. The aim of our study is to unveil the prognostic role of MSI-L in gastric cancer (GC). One hundred nine patients with locally advanced GC (T3-4a, N+, M0) who underwent neoadjuvant chemotherapy plus gastrectomy with extended (D2) lymph node dissection were collected. Clinicopathological characteristics, tumour regression score, disease-free survival (DFS), and overall survival (OS) were analysed and correlated with the MSI status. The MSI status of 96 patients was identified (7 (7.3%) with MSI-H, 12 (12.5%) with MSI-L, and 77 (80.2%) with MSS). MSI-L was significantly correlated with perineural invasion (P = 0.009) and decreased MUC5AC expression (P = 0.042). Poor response to neoadjuvant chemotherapy in MSI-L patients (83.3% assessed as poor response) was observed (P = 0.501). Compared with patients with MSS tumours, patients with MSI-L tumours showed poor DFS (P = 0.018) with a hazard ratio (HR) of 2.839 (95% CI 1.131-7.124, P = 0.026) from multivariable cox regression analysis. However, this was not associated with OS (P = 0.063). MSI-L is an independent poor prognostic biomarker for the locally advanced gastric cancer treated with neoadjuvant chemotherapy. Further studies with larger sample sizes are needed for validation.
Subject(s)
Antineoplastic Combined Chemotherapy Protocols/therapeutic use , Biomarkers, Tumor/genetics , Capecitabine/therapeutic use , Gastrectomy , Lymph Node Excision , Microsatellite Instability , Neoadjuvant Therapy , Oxaloacetates/therapeutic use , Stomach Neoplasms/therapy , Adult , Aged , Antineoplastic Combined Chemotherapy Protocols/adverse effects , Capecitabine/adverse effects , Chemotherapy, Adjuvant , Disease-Free Survival , Female , Gastrectomy/adverse effects , Gastrectomy/mortality , Humans , Lymph Node Excision/adverse effects , Lymph Node Excision/mortality , Male , Middle Aged , Neoadjuvant Therapy/adverse effects , Neoadjuvant Therapy/mortality , Neoplasm Staging , Oxaloacetates/adverse effects , Prospective Studies , Risk Assessment , Risk Factors , Stomach Neoplasms/genetics , Stomach Neoplasms/mortality , Stomach Neoplasms/pathology , Time FactorsABSTRACT
Limited biomarkers have been identified as prognostic predictors for stage III colon cancer. To combat this shortfall, we developed a computer-aided approach which combing convolutional neural network with machine classifier to predict the prognosis of stage III colon cancer from routinely haematoxylin and eosin (H&E) stained tissue slides. We trained the model by using 101 cancers from West China Hospital (WCH). The predictive effectivity of the model was validated by using 67 cancers from WCH and 47 cancers from The Cancer Genome Atlas Colon Adenocarcinoma database. The selected model (Gradient Boosting-Colon) provided a hazard ratio (HR) for high- vs. low-risk recurrence of 8.976 (95% confidence interval (CI), 2.824-28.528; P, 0.000), and 10.273 (95% CI, 2.177-48.472; P, 0.003) in the two test groups, from the multivariate Cox proportional hazards analysis. It gave a HR value of 10.687(95% CI, 2.908-39.272; P, 0.001) and 5.033 (95% CI,1.792-14.132; P, 0.002) for the poor vs. good prognosis groups. Gradient Boosting-Colon is an independent machine prognostic predictor which allows stratification of stage III colon cancer into high- and low-risk recurrence groups, and poor and good prognosis groups directly from the H&E tissue slides. Our findings could provide crucial information to aid treatment planning during stage III colon cancer.