Long-term impact of artificial intelligence on colorectal adenoma detection in high-risk colonoscopy

BACKGROUND Improved adenoma detection rate(ADR)has been demonstrated with artificial intelligence(AI)-assisted colonoscopy.However,data on the real-world appli-cation of AI and its effect on colorectal cancer(CRC)screening outcomes is limited.AIM To analyze the long-term impact of AI on a diverse at-risk patient population undergoing diagnostic colonoscopy for positive CRC screening tests or sympt-oms.METHODS AI software(GI Genius,Medtronic)was implemented into the standard proced-ure protocol in November 2022.Data was collected on patient demographics,procedure indication,polyp size,location,and pathology.CRC screening outcomes were evaluated before and at different intervals after AI introduction with one year of follow-up.RESULTS We evaluated 1008 colonoscopies(278 pre-AI,255 early post-AI,285 established post-AI,and 190 late post-AI).The ADR was 38.1%pre-AI,42.0%early post-AI(P=0.77),40.0%established post-AI(P=0.44),and 39.5%late post-AI(P=0.77).There were no significant differences in polyp detection rate(PDR,baseline 59.7%),advanced ADR(baseline 16.2%),and non-neoplastic PDR(baseline 30.0%)before and after AI introduction.CONCLUSION In patients with an increased pre-test probability of having an abnormal colonoscopy,the current generation of AI did not yield enhanced CRC screening metrics over high-quality colonoscopy.Although the potential of AI in colonoscopy is undisputed,current AI technology may not universally elevate screening metrics across all situations and patient populations.Future studies that analyze different AI systems across various patient populations are needed to determine the most effective role of AI in optimizing CRC screening in clinical practice.

Evaluating the risk of adverse events with interventional endoscopic retrograde cholangiopancreatography and endoscopic ultrasound procedures in cirrhotic patients

BACKGROUND Hepatic cirrhosis is associated with greater adverse event rates following surgical procedures and is thought to have a higher risk of complications with interventional procedures in general.However,these same patients often require interventional gastrointestinal procedures such as endoscopic retrograde cholangiopancreatography(ERCP)and endoscopic ultrasound(EUS).While studies examining this scenario exist,the overall body of evidence for adverse event rates associated with ERCP/EUS procedures is more limited.We sought add to the literature by examining the incidence of adverse events after ERCP/EUS procedures in our safety-net hospital population with the hypothesis that severity of cirrhosis correlates with higher adverse event rates.AIM To examine whether increasing severity of cirrhosis is associated with greater incidence of adverse events after interventional ERCP/EUS procedures.METHODS We performed a retrospective study of patients diagnosed with hepatic cirrhosis who underwent ERCP and/or EUS-guided fine needle aspirations/fine needle biopsies from January 1,2016 to March 14,2019 at our safety net hospital.We recorded Child-Pugh and Model for End-stage Liver Disease(MELD-Na)scores at time of procedure,interventions completed,and 30-day post-procedural adverse events.Statistical analyses were done to assess whether Child-Pugh class and MELD-Na score were associated with greater adverse event rates and whether advanced techniques(single-operator cholangioscopy,electrohydraulic lithotripsy/laser lithotripsy,or needle-knife techniques)were associated with higher complication rates.RESULTS 77 procedures performed on 36 patients were included.The study population consisted primarily of middle-aged Hispanic males.30-d procedure-related adverse events included gastrointestinal bleeding(7.8%),infection(6.5%),and bile leak(2%).The effect of Child-Pugh class C vs class A and B significantly predicted adverse events(β=0.55,P<0.01).MELD-Na scores also significantly predicted adverse events(β=0.037,P<0.01).Presence of advanced techniques was not associated with higher adverse events(P>0.05).When MELD-Na scores were added as predictors with the effect of Child-Pugh class C,logistic regression showed MELD-Na scores were a significant predictor of adverse events(P<0.01).The findings held after controlling for age,gender,ethnicity and repeat cases.CONCLUSION Increasing cirrhosis severity predicted adverse events while the presence of advanced techniques did not.MELD-Na score may be more useful in predicting adverse events than Child-Pugh class.