Identification of prognostic long intergenic non-coding RNAs as competing endogenous RNAs with KRAS mutations in colorectal cancer.

Colorectal cancer (CRC) is recognized as a common type of human cancer, and KRAS mutations are correlated with poor CRC survival outcomes. The evaluation and prediction of CRC results remain challenging. In the present study, RNA sequencing and clinical data from The Cancer Genome Atlas were used to identify KRAS mutation-related prognostic long intergenic non-coding RNAs (lincRNAs) in CRC. Significantly dysregulated lincRNAs and independent prognostic lincRNAs with KRAS mutations in CRC were identified. Two lincRNAs with KRAS mutations, LINC00265 and AL390719.2, were selected as key prognostic lincRNAs for both 10- and 5-year survival rates. In addition, competing endogenous (ce)RNA models were constructed to comprehensively assess the oncogenic performance of the two key lincRNAs. The ceRNA models suggested that LINC00265 and AL390719.2 are critical for the cell cycle and cancer pathways. Finally, reverse transcription-quantitative PCR was used to validate the ceRNA models in 12 pairs of CRC tissue samples. These prognostic lincRNAs may provide novel biomarkers for the prognostic prediction of CRC. The ceRNA model may also demonstrate the underlying mechanism of these lincRNAs in CRC.

Evaluation of the effects of an artificial intelligence system on endoscopy quality and preliminary testing of its performance in detecting early gastric cancer: a randomized controlled trial.

BACKGROUND: Esophagogastroduodenoscopy (EGD) is a prerequisite for detecting upper gastrointestinal lesions especially early gastric cancer (EGC). An artificial intelligence system has been shown to monitor blind spots during EGD. In this study, we updated the system (ENDOANGEL), verified its effectiveness in improving endoscopy quality, and pretested its performance in detecting EGC in a multicenter randomized controlled trial. METHODS: ENDOANGEL was developed using deep convolutional neural networks and deep reinforcement learning. Patients undergoing EGD in five hospitals were randomly assigned to the ENDOANGEL-assisted group or to a control group without use of ENDOANGEL. The primary outcome was the number of blind spots. Secondary outcomes included performance of ENDOANGEL in predicting EGC in a clinical setting. RESULTS: 1050 patients were randomized, and 498 and 504 patients in the ENDOANGEL and control groups, respectively, were analyzed. Compared with the control group, the ENDOANGEL group had fewer blind spots (mean 5.38 [standard deviation (SD) 4.32] vs. 9.82 [SD 4.98]; P < 0.001) and longer inspection time (5.40 [SD 3.82] vs. 4.38 [SD 3.91] minutes; P < 0.001). In the ENDOANGEL group, 196 gastric lesions with pathological results were identified. ENDOANGEL correctly predicted all three EGCs (one mucosal carcinoma and two high grade neoplasias) and two advanced gastric cancers, with a per-lesion accuracy of 84.7 %, sensitivity of 100 %, and specificity of 84.3 % for detecting gastric cancer. CONCLUSIONS: In this multicenter study, ENDOANGEL was an effective and robust system to improve the quality of EGD and has the potential to detect EGC in real time.