RESUMO
OBJECTIVE: Artificial intelligence (AI) may reduce underdiagnosed or overlooked upper GI (UGI) neoplastic and preneoplastic conditions, due to subtle appearance and low disease prevalence. Only disease-specific AI performances have been reported, generating uncertainty on its clinical value. DESIGN: We searched PubMed, Embase and Scopus until July 2020, for studies on the diagnostic performance of AI in detection and characterisation of UGI lesions. Primary outcomes were pooled diagnostic accuracy, sensitivity and specificity of AI. Secondary outcomes were pooled positive (PPV) and negative (NPV) predictive values. We calculated pooled proportion rates (%), designed summary receiving operating characteristic curves with respective area under the curves (AUCs) and performed metaregression and sensitivity analysis. RESULTS: Overall, 19 studies on detection of oesophageal squamous cell neoplasia (ESCN) or Barrett's esophagus-related neoplasia (BERN) or gastric adenocarcinoma (GCA) were included with 218, 445, 453 patients and 7976, 2340, 13 562 images, respectively. AI-sensitivity/specificity/PPV/NPV/positive likelihood ratio/negative likelihood ratio for UGI neoplasia detection were 90% (CI 85% to 94%)/89% (CI 85% to 92%)/87% (CI 83% to 91%)/91% (CI 87% to 94%)/8.2 (CI 5.7 to 11.7)/0.111 (CI 0.071 to 0.175), respectively, with an overall AUC of 0.95 (CI 0.93 to 0.97). No difference in AI performance across ESCN, BERN and GCA was found, AUC being 0.94 (CI 0.52 to 0.99), 0.96 (CI 0.95 to 0.98), 0.93 (CI 0.83 to 0.99), respectively. Overall, study quality was low, with high risk of selection bias. No significant publication bias was found. CONCLUSION: We found a high overall AI accuracy for the diagnosis of any neoplastic lesion of the UGI tract that was independent of the underlying condition. This may be expected to substantially reduce the miss rate of precancerous lesions and early cancer when implemented in clinical practice.
RESUMO
OBJECTIVE: Cyclooxygenases (COX) are important enzymes not only in the maintenance of mucosal integrity but also in pathological processes, namely in inflammation and tumor development in the gastrointestinal tract. Our goal was to understand whether there is a clear role for COX polymorphisms in gastric and colorectal carcinogenesis. METHODS: A systematic review was conducted on observational studies assessing the involvement of COX polymorphisms at the onset of gastric or colorectal lesions, retrieved through a MEDLINE database search by May 2008. The dominant genetic model was assumed for each polymorphism and a random-effect model was used for pooling results. RESULTS: Twenty-two studies were retrieved reporting a total of 26 COX polymorphisms (nine in COX1 and 17 in COX2 genes). Carriers of -1329A, -899C alleles, and *429TT genotype revealed increased risk for gastric cancer [odds ratio (OR)=1.83; 95% confidence interval (CI): 1.07-3.10, OR=2.02; 95% CI: 1.00-4.10 and OR=1.34; 95% CI: 1.06-1.71, respectively). For colorectal lesions, the -899G>C and -1329G>A polymorphisms also showed an increased risk for cancer (OR=1.35; 95% CI: 1.01-1.81 and OR=1.36; 95% CI: 1.11-1.66, respectively). Furthermore, C allele carriers of V102V single nucleotide polymorphisms presented a decreased risk for colorectal adenoma onset (OR=0.77; 95% CI: 0.58-1.03). CONCLUSION: Although further studies, namely cohorts and/or adequately matched case-control studies, are required to unravel the impact of most COX polymorphisms, clearly there are evidences that support the involvement of -899G>C and -1329G>A COX2 polymorphisms in either gastric or colorectal carcinogenesis. These markers could be used to optimize management strategies (follow-up and/or chemoprevention).