Influence of artificial intelligence on the diagnostic performance of endoscopists in the assessment of Barrett's esophagus: a tandem randomized and video trial.

BACKGROUND: This study evaluated the effect of an artificial intelligence (AI)-based clinical decision support system on the performance and diagnostic confidence of endoscopists in their assessment of Barrett's esophagus (BE). METHODS: 96 standardized endoscopy videos were assessed by 22 endoscopists with varying degrees of BE experience from 12 centers. Assessment was randomized into two video sets: group A (review first without AI and second with AI) and group B (review first with AI and second without AI). Endoscopists were required to evaluate each video for the presence of Barrett's esophagus-related neoplasia (BERN) and then decide on a spot for a targeted biopsy. After the second assessment, they were allowed to change their clinical decision and confidence level. RESULTS: AI had a stand-alone sensitivity, specificity, and accuracy of 92.2%, 68.9%, and 81.3%, respectively. Without AI, BE experts had an overall sensitivity, specificity, and accuracy of 83.3%, 58.1%, and 71.5%, respectively. With AI, BE nonexperts showed a significant improvement in sensitivity and specificity when videos were assessed a second time with AI (sensitivity 69.8% [95%CI 65.2%-74.2%] to 78.0% [95%CI 74.0%-82.0%]; specificity 67.3% [95%CI 62.5%-72.2%] to 72.7% [95%CI 68.2%-77.3%]). In addition, the diagnostic confidence of BE nonexperts improved significantly with AI. CONCLUSION: BE nonexperts benefitted significantly from additional AI. BE experts and nonexperts remained significantly below the stand-alone performance of AI, suggesting that there may be other factors influencing endoscopists' decisions to follow or discard AI advice.

Detection of duodenal villous atrophy on endoscopic images using a deep learning algorithm.

BACKGROUND AND AIMS: Celiac disease with its endoscopic manifestation of villous atrophy (VA) is underdiagnosed worldwide. The application of artificial intelligence (AI) for the macroscopic detection of VA at routine EGD may improve diagnostic performance. METHODS: A dataset of 858 endoscopic images of 182 patients with VA and 846 images from 323 patients with normal duodenal mucosa was collected and used to train a ResNet18 deep learning model to detect VA. An external dataset was used to test the algorithm, in addition to 6 fellows and 4 board-certified gastroenterologists. Fellows could consult the AI algorithm's result during the test. From their consultation distribution, a stratification of test images into "easy" and "difficult" was performed and used for classified performance measurement. RESULTS: External validation of the AI algorithm yielded values of 90%, 76%, and 84% for sensitivity, specificity, and accuracy, respectively. Fellows scored corresponding values of 63%, 72%, and 67% and experts scored 72%, 69%, and 71%, respectively. AI consultation significantly improved all trainee performance statistics. Although fellows and experts showed significantly lower performance for difficult images, the performance of the AI algorithm was stable. CONCLUSIONS: In this study, an AI algorithm outperformed endoscopy fellows and experts in the detection of VA on endoscopic still images. AI decision support significantly improved the performance of nonexpert endoscopists. The stable performance on difficult images suggests a further positive add-on effect in challenging cases.

Texture and color enhancement imaging versus high definition white-light endoscopy for detection of colorectal neoplasia: a randomized trial.

BACKGROUND: Texture and color enhancement imaging (TXI) was recently proposed as a substitute for standard high definition white-light imaging (WLI) to increase lesion detection during colonoscopy. This international, multicenter randomized trial assessed the efficacy of TXI in detection of colorectal neoplasia. METHODS: Consecutive patients aged ≥ 40 years undergoing screening, surveillance, or diagnostic colonoscopies at five centers (Italy, Germany, Japan) between September 2021 and May 2022 were enrolled. Patients were randomly assigned (1:1) to TXI or WLI. Primary outcome was adenoma detection rate (ADR). Secondary outcomes were adenomas per colonoscopy (APC) and withdrawal time. Relative risks (RRs) adjusted for age, sex, and colonoscopy indication were calculated. RESULTS: We enrolled 747 patients (mean age 62.3 [SD 9.5] years, 50.2 % male). ADR was significantly higher with TXI (221/375, 58.9 %) vs. WLI (159/372, 42.7 %; adjusted RR 1.38 [95 %CI 1.20-1.59]). This was significant for ≤ 5 mm (RR 1.42 [1.16-1.73]) and 6-9 mm (RR 1.36 [1.01-1.83]) adenomas. A higher proportion of polypoid (151/375 [40.3 %] vs. 104/372 [28.0 %]; RR 1.43 [1.17-1.75]) and nonpolypoid (136/375 [36.3 %] vs. 102/372 [27.4 %]; RR 1.30 [1.05-1.61]) adenomas, and proximal (143/375 [38.1 %] vs. 111/372 [29.8 %]; RR 1.28 [1.05-1.57]) and distal (144/375 [38.4 %] vs. 98/372 [26.3 %]; RR 1.46 [1.18-1.80]) lesions were found with TXI. APC was higher with TXI (1.36 [SD 1.79] vs. 0.89 [SD 1.35]; incident rate ratio 1.53 [1.25-1.88]). CONCLUSIONS: TXI increased ADR and APC among patients undergoing colonoscopy for various indications. TXI increased detection of polyps < 10 mm, both in the proximal and distal colon, and may help to improve colonoscopy quality indicators.

Role of artificial intelligence in diagnosing Barrett's esophagus-related neoplasia.

Barrett's esophagus is associated with an increased risk of adenocarcinoma. Thorough screening during endoscopic surveillance is crucial to improve patient prognosis. Detecting and characterizing dysplastic or neoplastic Barrett's esophagus during routine endoscopy are challenging, even for expert endoscopists. Artificial intelligence-based clinical decision support systems have been developed to provide additional assistance to physicians performing diagnostic and therapeutic gastrointestinal endoscopy. In this article, we review the current role of artificial intelligence in the management of Barrett's esophagus and elaborate on potential artificial intelligence in the future.