The value of machine learning approaches in the diagnosis of early gastric cancer: a systematic review and meta-analysis.

BACKGROUND: The application of machine learning (ML) for identifying early gastric cancer (EGC) has drawn increasing attention. However, there lacks evidence-based support for its specific diagnostic performance. Hence, this systematic review and meta-analysis was implemented to assess the performance of image-based ML in EGC diagnosis. METHODS: We performed a comprehensive electronic search in PubMed, Embase, Cochrane Library, and Web of Science up to September 25, 2022. QUADAS-2 was selected to judge the risk of bias of included articles. We did the meta-analysis using a bivariant mixed-effect model. Sensitivity analysis and heterogeneity test were performed. RESULTS: Twenty-one articles were enrolled. The sensitivity (SEN), specificity (SPE), and SROC of ML-based models were 0.91 (95% CI: 0.87-0.94), 0.85 (95% CI: 0.81-0.89), and 0.94 (95% CI: 0.39-1.00) in the training set and 0.90 (95% CI: 0.86-0.93), 0.90 (95% CI: 0.86-0.92), and 0.96 (95% CI: 0.19-1.00) in the validation set. The SEN, SPE, and SROC of EGC diagnosis by non-specialist clinicians were 0.64 (95% CI: 0.56-0.71), 0.84 (95% CI: 0.77-0.89), and 0.80 (95% CI: 0.29-0.97), and those by specialist clinicians were 0.80 (95% CI: 0.74-0.85), 0.88 (95% CI: 0.85-0.91), and 0.91 (95% CI: 0.37-0.99). With the assistance of ML models, the SEN of non-specialist physicians in the diagnosis of EGC was significantly improved (0.76 vs 0.64). CONCLUSION: ML-based diagnostic models have greater performance in the identification of EGC. The diagnostic accuracy of non-specialist clinicians can be improved to the level of the specialists with the assistance of ML models. The results suggest that ML models can better assist less experienced clinicians in diagnosing EGC under endoscopy and have broad clinical application value.

Construction and validation of a prognostic nomogram for predicting cancer-specific survival in patients with intermediate and advanced colon cancer after receiving surgery and chemotherapy.

BACKGROUND: Existing predictive models often focus solely on overall survival (OS), neglecting the bias that other causes of death might introduce into survival rate predictions. To date, there is no strict predictive model established for cancer-specific survival (CSS) in patients with intermediate and advanced colon cancer after receiving surgery and chemotherapy. METHODS: We extracted the data from the Surveillance, Epidemiology, and End Results (SEER) database on patients with stage-III and -IV colon cancer treated with surgery and chemotherapy between 2010 and 2015. The cancer-specific survival (CSS) was assessed using a competitive risk model, and the associated risk factors were identified via univariate and multivariate analyses. A nomogram predicting 1-, 3-, and 5-year CSS was constructed. The c-index, area under the curve (AUC), and calibration curve were adopted to assess the predictive performance of the model. Additionally, the model was externally validated. RESULTS: A total of 18 risk factors were identified by univariate and multivariate analyses for constructing the nomogram. The AUC values of the nomogram for the 1-, 3-, and 5-year CSS prediction were 0.831, 0.842, and 0.848 in the training set; 0.842, 0.853, and 0.849 in the internal validation set; and 0.815, 0.823, and 0.839 in the external validation set. The C-index were 0.826 (se: 0.001), 0.836 (se: 0.002) and 0.763 (se: 0.013), respectively. Moreover, the calibration curve showed great calibration. CONCLUSION: The model we have constructed is of great accuracy and reliability, and can help physicians develop treatment and follow-up strategies that are beneficial to the survival of the patients.