BACKGROUND & AIMS:Artificial intelligence-based computer-aided polyp detection (CADe) systems are intended to address the issue of missed polyps during colonoscopy. The effect of CADe during screening and surveillance colonoscopy has not previously been studied in a United States (U.S.) population.
METHODS:We conducted a prospective, multi-center, single-blind randomized tandem colonoscopy study to evaluate a deep-learning based CADe system (EndoScreener, Shanghai Wision AI, China). Patients were enrolled across 4 U.S. academic medical centers from 2019 through 2020. Patients presenting for colorectal cancer screening or surveillance were randomized to CADe colonoscopy first or high-definition white light (HDWL) colonoscopy first, followed immediately by the other procedure in tandem fashion by the same endoscopist. The primary outcome was adenoma miss rate (AMR), and secondary outcomes included sessile serrated lesion (SSL) miss rate and adenomas per colonoscopy (APC).
RESULTS:A total of 232 patients entered the study, with 116 patients randomized to the CADe colonoscopy first and 116 patients to HDWL colonoscopy first. After the exclusion of 9 patients, the study cohort included 223 patients. AMR was lower in the CADe-first group compared with the HDWL-first group (20.12% [34/169] vs 31.25% [45/144]; odds ratio [OR], 1.8048; 95% confidence interval [CI], 1.0780-3.0217; P [ .0247). SSL miss rate was lower in the CADe-first group (7.14% [1/14]) vs the HDWL-first group (42.11% [8/19]; P [ .0482). First-pass APC was higher in the CADe-first group (1.19 [standard deviation (SD), 2.03] vs 0.90 [SD, 1.55]; P [ .0323). First-pass ADR was 50.44% in the CADe-first group and 43.64 % in the HDWL-first group (P [ .3091).
CONCLUSION:In this U.S. multicenter tandem colonoscopy randomized controlled trial, we demonstrate a decrease in AMR and SSL miss rate and an increase in first-pass APC with the use of a CADesystem when compared with HDWL colonoscopy.
Alcohol use is a significant risk factor for colonic diverticulosis and may offer a partial explanation for the existing East-West paradox in disease prevalence and phenotype. Further studies are needed to investigate this association and its putative pathophysiological mechanisms.
Summary
Background
The proportions of patients with oesophageal adenocarcinoma (OAC) diagnosed by Barrett's oesophagus surveillance or with pre‐existing Barrett's oesophagus are unclear.
Aim
To estimate the prevalence of prior and concurrent Barrett's oesophagus diagnosis among patients with OAC or oesophagogastric junction adenocarcinomas (OGJAC).
Methods
We searched PubMed and Embase to identify studies published 1966‐1/8/2020 that examined the prevalence of prior (≥6 months) or concurrent Barrett's diagnosis (at cancer diagnosis) among OAC and OGJAC patients. Random effects models estimated overall and stratified pooled prevalence rates.
Results
A total of 69 studies, including 33 002 OAC patients (53 studies) and 2712 patients with OGJAC (28 studies) were included. The pooled prevalence of prior Barrett's oesophagus diagnosis in OAC was 11.8% (95% confidence interval [CI] 8.4%‐15.6%). The prevalence of prior Barrett's oesophagus diagnosis was higher in single‐centre resection studies (16.0%, 95% CI 8.7%‐24.9%) than population‐based cancer registry studies (8.4%, 95% CI 5.5%‐11.9%). The prevalence of concurrent Barrett's oesophagus in OAC was 56.6% (95% CI 48.5%‐64.6%). Studies with 100% early stage OAC had higher prevalence of concurrent Barrett's oesophagus (91.3%, 95% CI 82.4%‐97.6%) than studies with <50% early OAC (39.7%, 95% CI 33.7%‐45.9%). In OGJAC, the prevalence of prior and concurrent Barrett's oesophagus was 23.2% (95% CI 7.5%‐44.0%) and 26.3% (95% CI 17.8%‐35.7%), respectively.
Conclusions
Most patients with OAC have Barrett's oesophagus. Our meta‐analysis found ~12% of OAC patients had prior Barrett's diagnosis, but concurrent Barrett's oesophagus was found in ~57% at the time of OAC diagnosis. This represents a considerable missed opportunity for Barrett's oesophagus screening.
Esophageal adenocarcinoma (EAC) is a growing problem with a rapidly rising incidence. Risk factors include gastroesophageal reflux disease, central obesity, and smoking. The prognosis of EAC remains poor because it is usually diagnosed late, and many efforts have been made to improve prevention, early detection, and treatment. Acid suppression, nonsteroidal antiinflammatory drugs (NSAIDs), and statins may play a role in chemoprevention. Screening for Barrett's esophagus (BE), the only known precursor lesion of EAC, is indicated for individuals with increased risk. Endoscopic surveillance of patients with BE likely improves overall outcomes. Endoscopic ablation and resection is highly effective for treating dysplastic BE and early EAC, whereas esophagectomy is indicated for patients with locally advanced disease. This review covers epidemiology, staging, screening, and prevention of EAC as well as endoscopic and surgical management.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.