Background: The role of retrospective analysis has been evolved greatly in cancer research. We undertook this meta-analysis to evaluate the diagnostic value of Neural networks (NNs) in Fine needle aspiration cytological (FNAC) image of cancer. Methods: We systematically retrieved 396 literatures on cytodiagnosis of NNs from Cochrane, PubMed, and EMBASE. After screening, only six studies were included in metaanalysis finally. Data was comprehensively analyzed by RevMan and meta-Disc software. Results: A total of 1165 cases were extracted from six articles. Among them, 593 cases were in the abnormal/positive group and 572 cases in the normal/negative group. The pooled estimates for the NNs cytology were Area under ROC curve (AUC): 0.

BackgroundGastric carcinoma (GC) is a highly aggressive malignancy and is associated with high morbidity and mortality rates around the world, the current tumor-node-metastasis (TNM) staging system is inadequate to predict overall survival (OS) in GC patients. therefore, potential forecasting methods for prognosis are important to investigate.MethodsDifferentially expressed genes (DEGs) were screened using gene expression data from The Cancer Genome Atlas (TCGA). We then construct a risk score signature model by univariate Cox proportional hazards regression (CPHR) analysis, the Kaplan-Meier method（KM）and multivariate CPHR analysis. Using TNM stage, we developed a signature-based nomogram. Finally, we utilize an independent Gene Expression Omnibus dataset (GSE62254) validate the prognostic value of risk score signature model and nomogram.ResultsWe identified five OS-related mRNAs among 1113 mRNAs that were differentially expressed between GC and normal samples in the TCGA dataset. We then constructed a five-mRNA signature model, which efficiently distinguished high-risk from low-risk patient in both cohort, and even viable in the TNM stage-III, gender(male, female) and age(＜65-year-old, ≥65-year-old) subgroups (P<0.05). Utilizing TNM stage, we developed a signature-based nomogram, which performed better than use the TNM stage or five-mRNA signature alone for prognostic prediction in the TCGA and GSE62254 dataset.ConclusionsThese results suggest that both risk signature and nomogram were effective prognostic indicators for patients with GCs, and could potentially be used for individualized management of such patients.