Recommendations For Colonoscopy Research Articles

ChatGPT4 Outperforms Endoscopists for Determination of Postcolonoscopy Rescreening and Surveillance Recommendations

Large language models including Chat Generative Pretrained Transformers version 4 (ChatGPT4) improve access to artificial intelligence, but their impact on the clinical practice of gastroenterology is undefined. This study compared the accuracy, concordance, and reliability of ChatGPT4 colonoscopy recommendations for colorectal cancer rescreening and surveillance with contemporary guidelines and real-world gastroenterology practice. History of present illness, colonoscopy data, and pathology reports from patients undergoing procedures at 2 large academic centers were entered into ChatGPT4 and it was queried for the next recommended colonoscopy follow-up interval. Using the McNemar test and inter-rater reliability, we compared the recommendations made by ChatGPT4 with the actual surveillance interval provided in the endoscopist's procedure report (gastroenterology practice) and the appropriate US Multisociety Task Force (USMSTF) guidance. The latter was generated for each case by an expert panel using the clinical information and guideline documents as reference. Text input of de-identified data into ChatGPT4 from 505 consecutive patients undergoing colonoscopy between January 1 and April 30, 2023, elicited a successful follow-up recommendation in 99.2% of the queries. ChatGPT4 recommendations were in closer agreement with the USMSTF Panel (85.7%) than gastroenterology practice recommendations with the USMSTF Panel (75.4%) (P < .001). Of the 14.3% discordant recommendations between ChatGPT4 and the USMSTF Panel, recommendations were for later screening in 26 (5.1%) and for earlier screening in 44 (8.7%) cases. The inter-rater reliability was good for ChatGPT4 vs USMSTF Panel (Fleiss κ, 0.786; 95% CI, 0.734-0.838; P < .001). Initial real-world results suggest that ChatGPT4 can define routine colonoscopy screening intervals accurately based on verbatim input of clinical data. Large language models have potential for clinical applications, but further training is needed for broad use.

Closing the Gap: A Critical Examination of Adherence, Inconsistency, and Improvements in Colonoscopy Reporting Practices

Introduction: Comprehensive and standardized colonoscopy reports are crucial in colorectal cancer prevention, monitoring, and research. This study investigates adherence to national and international guidelines by analyzing reporting practices among 21 endoscopists in 7 German centers, with a focus on polyp reporting. Methods: We identified and assessed German, European, American, and World Health Organization-provided statements to identify key elements in colonoscopy reporting. Board-certified gastroenterologists rated the relevance of each element and estimated their reporting frequency. Adherence to the identified report elements was evaluated for 874 polyps from 351 colonoscopy reports ranging from March 2021 to March 2022. Results: We identified numerous recommendations for colonoscopy reporting. We categorized the reasoning behind those recommendations into clinical relevance, justification, and quality control and research. Although all elements were considered relevant by the surveyed gastroenterologists, discrepancies were observed in the evaluated reports. Particularly diminutive polyps or attributes which are rarely abnormal (e.g., surface integrity) respectively rarely performed (e.g., injection) were sparsely documented. Furthermore, the white light morphology of polyps was inconsistently documented using either the Paris classification or free text. In summary, the analysis of 874 reported polyps revealed heterogeneous adherence to the recommendations, with reporting frequencies ranging from 3% to 89%. Conclusion: The inhomogeneous report practices may result from implicit reporting practices and recommendations with varying clinical relevance. Future recommendations should clearly differentiate between clinical relevance and research and quality control or explanatory purposes. Additionally, the role of computer-assisted documentation should be further evaluated to increase report frequencies of non-pathological findings and diminutive polyps.

Projected Colorectal Cancer Incidence and Mortality Based on Observed Adherence to Colonoscopy and Sequential Stool-Based Screening.

Modeling supporting recommendations for colonoscopy and stool-based colorectal cancer (CRC) screening tests assumes 100% sequential participant adherence. The impact of observed adherence on the long-term effectiveness of screening is unknown. We evaluated the effectiveness of a program of screening colonoscopy every 10 years vs annual high-sensitivity guaiac-based fecal occult blood testing (HSgFOBT) using observed sequential adherence data. The MIcrosimulation SCreening ANalysis (MISCAN) model used observed sequential screening adherence, HSgFOBT positivity, and diagnostic colonoscopy adherence in HSgFOBT-positive individuals from the National Colonoscopy Study (single-screening colonoscopy vs ≥4 HSgFOBT sequential rounds). We compared CRC incidence and mortality over 15 years with no screening or 10 yearly screening colonoscopy vs annual HSgFOBT with 100% and differential observed adherence from the trial. Without screening, simulated incidence and mortality over 15 years were 20.9 (95% probability interval 15.8-26.9) and 6.9 (5.0-9.2) per 1,000 participants, respectively. In the case of 100% adherence, only screening colonoscopy was predicted to result in lower incidence; however, both tests lowered simulated mortality to a similar level (2.1 [1.6-2.9] for screening colonoscopy and 2.5 [1.8-3.4] for HSgFOBT). Observed adherence for screening colonoscopy (83.6%) was higher than observed sequential HSgFOBT adherence (73.1% first round; 49.1% by round 4), resulting in lower simulated incidence and mortality for screening colonoscopy (14.4 [10.8-18.5] and 2.9 [2.1-3.9], respectively) than HSgFOBT (20.8 [15.8-28.1] and 3.9 [2.9-5.4], respectively), despite a 91% adherence to diagnostic colonoscopy with FOBT positivity. The relative risk of CRC mortality for screening colonoscopy vs HSgFOBT was 0.75 (95% probability interval 0.68-0.80). Findings were similar in sensitivity analyses with alternative assumptions for repeat colonoscopy, test performance, risk, age, and projection horizon. Where sequential adherence to stool-based screening is suboptimal and colonoscopy is accessible and acceptable-as observed in the national colonoscopy study, microsimulation, comparative effectiveness, screening recommendations.

Fecal methylated syndecan-2 (SDC2) testing for early screening of colorectal cancerous and precancerous lesions: A real-world retrospective study in China

BackgroundColorectal cancer (CRC) is a major public health concern and the second leading cause of cancer-related deaths worldwide. However, challenges remain in deploying effective screening strategies for early-stage CRC. This study aimed to evaluate the effectiveness of a fecal-based syndecan-2 (SDC2) methylation test for the detection of colorectal lesions and CRC. MethodsWe retrospectively collected data on participants who underwent fecal SDC2 methylation testing from January 1, 2019, to May 30, 2023. Patients with positive results were recommended to undergo colonoscopy. Performance indicators associated with certain clinical characteristics, including positive rate (PR), positive predictive value (PPV), and colonoscopy compliance rate (CCR), were subjected to statistical analysis. ResultsWe analyzed data from 113,209 participants, of whom 11,841 (10.4% PR) had positive fecal SDC2 methylation test results. A total of 4315 participants with positive results adhered to the colonoscopy recommendations, and the CCR was 36.4%. Finally, 3169 colorectal lesions were detected, including 1134 polyps, 875 non-advanced adenomas (NAAs), 770 advanced adenomas (AAs), and 390 CRCs, with PPV values of 26.3% (1134/4315), 20.3% (875/4315), 17.8% (770/4315), and 9.0% (390/4315), respectively. Notably, the PPV for CRC increased significantly with age (χ2 = 164.40, P < 0.0001). In addition, as the cycle threshold (CT) values increased, the PPVs of AAs and CRCs generally decreased, whereas those of NAAs and polyps significantly increased. Moreover, the clinical patient group had the highest incidence of late-stage CRC (stage II and higher), whereas asymptomatic populations from the staff physical examination group and rural town-based screening programs had the highest number of stage 0 and I CRCs detected (P = 0.0107). ConclusionsThis study indicates that fecal SDC2 methylation testing combined with colonoscopy may be an effective screening method for colorectal lesions and CRC.

Prevalence of neoplasia at colonoscopy among testicular cancer survivors treated with platinum-based chemotherapy.

Testicular cancer survivors (TCS) treated with platinum-based chemotherapy have an increased risk of colorectal cancer (CRC). We determined the yield of colonoscopy in TCS to assess its potential in reducing CRC incidence and mortality. We conducted a colonoscopy screening study among TCS in four Dutch hospitals to assess the yield of colorectal neoplasia. Neoplasia was defined as adenomas, serrated polyps (SPs), advanced adenomas (AAs: ≥10 mm diameter, high-grade dysplasia or ≥25% villous component), advanced serrated polyps (ASPs: ≥10 mm diameter or dysplasia) or CRC. Advanced neoplasia (AN) was defined as AA, ASP or CRC. Colonoscopy yield was compared to average-risk American males who underwent screening colonoscopy (n = 24,193) using a propensity score matched analysis, adjusted for age, smoking status, alcohol consumption and body mass index. A total of 137 TCS underwent colonoscopy. Median age was 50 years among TCS (IQR 43-57) vs 55 years (IQR 51-62) among American controls. A total of 126 TCS were matched to 602 controls. The prevalence of AN was higher in TCS than in controls (8.7% vs 1.7%; P = .0002). Nonadvanced adenomas and SPs were detected in 45.2% of TCS vs 5.5% of controls (P < .0001). No lesions were detected in 46.0% of TCS vs 92.9% of controls (P < .0001). TCS treated with platinum-based chemotherapy have a higher prevalence of neoplasia and AN than matched controls. These results support our hypothesis that platinum-based chemotherapy increases the risk of colorectal neoplasia in TCS. Cost-effectiveness studies are warranted to ascertain the threshold of AN prevalence that justifies the recommendation of colonoscopy for TCS.

SIED-GISCOR recommendations for colonoscopy in screening programs: Part I – Diagnostic

The implementation of FIT programs reduces incidence and mortality from CRC in the screened subjects. The ultimate efficacy for CRC morbidity and mortality prevention in a FIT program depends on the colonoscopy in FIT+ subjects that has the task of detecting and removing these advanced lesions. Recently, there has been growing evidence on factors that influence the quality of colonoscopy specifically withing organized FIT programs, prompting to dedicated interventions in order to maximize the benefit/harm ratio of post-FIT colonoscopy. This document focuses on the diagnostic phase of colonoscopy, providing indications on how to standardise colonoscopy in FIT+ subjects, regarding timing of examination, management of antithrombotic therapy, bowel preparation, competence and sedation.

Evaluation of a questionnaire to assess the indication for screening colonoscopy for asymptomatic patients.

Colorectal cancer is the second most common cause of cancer death worldwide. Screening colonoscopy is a very effective measure to prevent colorectal cancer and can reduce mortality at the population level. However, the participation rates of screening programs are low.To provide easily accessible information on screening colonoscopy and to increase the participation rates of screening programs, we developed a questionnaire for asymptomatic patients based on the German guidelines to assess the indication for screening colonoscopy. We evaluated the questionnaire with reference to the indications given by specialists in gastroenterology. Patients who visited a specialist in gastroenterology in an outpatient clinic of a tertiary hospital for other reasons than a colonoscopy were eligible for the study. A maximum of seven questions to assess the indication for screening colonoscopy were answered by the patients. Afterward, the indication for screening colonoscopy was given or not by a specialist in gastroenterology. The accuracy of the questionnaire was measured in terms of sensitivity, specificity, and predictive values. In total, 335 patients were included in the analyses, of whom 50 and 285 patients were given and were not given an indication for screening colonoscopy by the specialists, respectively. In 0/50 patients, the questionnaire was false negative and in 8/285 patients false positive. Thus, the questionnaire had a sensitivity of 100% (95% confidence interval: 93-100%), a specificity of 97% (95-99%), a negative predictive value of 100% (99-100%), and a positive predictive value of 86% (75-94%).A subgroup analysis including patients who had never had a colonoscopy (n=109) showed comparable results: sensitivity of 100% (92-100%), specificity of 92% (83-97%), negative predictive value of 100% (94-100%), and positive predictive value of 90% (87-97%). The self-assessment questionnaire for asymptomatic individuals to assess the recommendation for screening colonoscopy is very sensitive and specific compared to a specialist in gastroenterology.The questionnaire can be found at: https://www.interdisziplinaere-endoskopie.mri.tum.de/de/infos-patienten/index.php.

Knowledge and Attitude of Inflammatory Bowel Disease Patients Toward Colorectal Cancer Risk, Its Management, and the Role of Healthcare Providers: A Cross-Sectional Study in the UK.

Inflammatory bowel disease (IBD) increases the risk for colorectal cancer (CRC). Limited literature exists on patients' knowledge of CRC risk and management. Attitude toward doctor-recommended management and the role of healthcare providers (HCPs) in CRC risk awareness remain unexplored. This study aimed to fill the gap in knowledge about CRC risk awareness and management in IBD patients in the UK. This cross-sectional internet-based study was conducted in April-July 2019. Adult (>18 years) IBD patients with a confirmed diagnosis for 2 years and adequate command of English language were invited from non-Natinal Health Services sources. A self-designed and piloted questionnaire with open- and closed-ended questions was used. Closed-ended data were analyzed using descriptive statistics and open-ended responses were analyzed using content analysis. Ninety-two participants (52.5% Crohn's disease and 67.5% females) responded. Around 88% knew that IBD increased CRC risk. Only 20.7% were aware of colonoscopy as the best screening tool; 88% were unaware of screening initiation time. Almost 90% would agree to a doctor's recommendation of colonoscopy. For dysplasia with 10% risk of CRC, 46.7% would not agree with colectomy. Some 48% reported to have never had a discussion about the risk of CRC in IBD with their HCPs, while 58% were not informed of the role of screening and surveillance in managing CRC risk. IBD patients were poorly aware of CRC risk management and had mixed willingness to comply with a doctor's recommendation. HCP's role in cancer knowledge dissemination was suboptimal and patients desired more information.

Practice Patterns of Colorectal Polypectomy in Pediatric Endoscopic Specialists in South Korea: A Nationwide Survey Study

Total colonoscopy is recommended if colorectal polyps are clinically suspected. This study aimed to investigate the performance status of pediatric colonoscopic polypectomy in Korea. We surveyed pediatric endoscopic specialists who perform colonoscopic polypectomy in Korea using a questionnaire of 13 questions on pediatric colonoscopic polypectomy performance status. The survey was conducted at 45 institutions, and 32 specialists (71.1%) responded. Among the respondents, 31.2% (10/32) said colonoscopy was performed in all age groups, while 12.5% (4/32) said sigmoidoscopy was performed in all age groups. Meanwhile, 56.2% (18/32) said that sigmoidoscopy was performed in young children, while colonoscopy was performed in older children. Among them, 38.9% (7/18) believe that 4-6 years were young, and 44.5% (8/18) believe that 7-9 years were young. Regarding surveillance examinations, 21.9% (7/32) said they would perform a surveillance colonoscopy or sigmoidoscopy in the future if less than five juvenile polyps were found in the colon. Meanwhile, if less than five adenomatous polyps were found in the colon, 93.8% (30/32) said they would perform surveillance colonoscopy or sigmoidoscopy in the future. More than half of the pediatric endoscopic specialists in Korea choose between a colonoscopy and sigmoidoscopy depending on the patient's age, contrary to the generally accepted recommendation of total colonoscopy if colorectal polyps are suspected in children and adolescents. In this survey, most pediatric endoscopists used the age range of 4-9 years as the reference age.

S307 Artificial Intelligence Identifies High Risk Patients Lost to Colon Cancer Screening Follow-Up During COVID-19 Pandemic

Introduction: The COVID-19 pandemic resulted in the complete stoppage of many colon cancer screening programs. During this time, many patients were at risk of being lost to follow up for their colorectal cancer (CRC) screening and surveillance. Here, we describe use of an artificial intelligence driven recall system to surface high risk patients potentially overdue for repeat colonoscopy and interrogate the reasons for missed recall. Methods: We conducted a retrospective study at a tertiary care academic medical center in continuous patients who underwent an initial colonoscopy between August to October 2019 and had a follow-up recommendation for a repeat colonoscopy within 2 years of the index procedure. A natural language understanding workflow was developed by Halo Solutions LLC in which: 1) procedure reports from gGastro (Modernizing Medicine, Florida) were converted to text files using OCR, and 2) these reports were evaluated alongside linked electronic healthcare record (EHR) data to determine the timing and indication of the recall procedure. Data was then manually reviewed to assess the reasons for missing the surveillance colonoscopy. Cases were randomly checked for accuracy, reaching an accuracy rate of 96%. Results: 4663 colonoscopies were performed, of which 14% (n=677) had a recall recommendation for surveillance colonoscopy within 2 years of the index colonoscopy. Of those cases, 24% (n=162/677) were flagged as potentially overdue. Of the 162 cases, 48 were found to have missing colonoscopy orders, 31 were not contacted by scheduling, and 32 were lost to follow up despite at least 1 attempted outreach. The remaining 51 were also lost to follow up but upon further review, deemed not overdue following manual review of the full record (e.g., outside records documented colonoscopy, patient expired, etc.). Conclusion: Missed CRC surveillance for patients with higher risk findings or disease processes increases the risk of patient harm from missed polyps and cancers. Nearly one in six patients who were advised to have a colonoscopy within two years of their index procedure were lost to follow up. In most EHR systems, once these patients are lost to follow up, there is no safety net to identify who these patients are. Integrating artificial intelligence into the EHR and clinical practice enables rapid identification of patients at risk of loss to follow up and allows for optimizing patient care and safety.

S278 Assessing Adherence to Recommending 10-Year Intervals After Normal Screening Colonoscopy in Average-Risk Individuals Based on Specialty and Practice Status

Introduction: After a normal average-risk CRC screening colonoscopy, endoscopists should recommend repeat screening in 10 years. Target is 90% adherence per guidelines, and this has been a priority quality indicator for CMS Medical Incentive Payment System and the ACPs Choosing Wisely Program. Our 2017 quality improvement (QI) project showed poor adherence (less than 40%) among private gastroenterologists and academic surgeons. Prior to commencing a new QI initiative, this project assessed frequency of adherence in 2021 at a single site. Methods: Inclusion criteria: To minimize confounders, patients were limited to: (a) average-risk, 50-82 year old; (b) colonoscopy performed in 2021; (c) sole indication of CRC screening; (d) no biopsy, polypectomy, or reference to abnormal findings on procedure report. Study Setting: Hospital-based “open” endoscopy suite (i.e., utilized by academic/private gastroenterologists and academic surgeons) at an academic tertiary care center. Primary Outcome: Adherence to guideline intervals defined as repeat colonoscopy in 10 years, discontinuation of CRC screening due to patient’s age when bowel preparation is adequate or repeat colonoscopy within 1 year if bowel preparation is poor/inadequate. Adherence rates stratified by specialty and type of practice: academic gastroenterologist (n = 7), academic surgeon (n = 3), or private gastroenterologist (n = 6). Differences in adherence between groups assessed using chi-square analysis. Results: Among 465 eligible patients, mean age was 60.1 +/- 8.2 years, 38.5% male, and 76.8% African American. Adherence surpassed target of 90% adherence for academic gastroenterologists (total=96.0%) with (96.9%) or without GI fellows (88.9%) and was superior to adherence by private gastroenterologists or academic general surgeons (p < 0.001). The latter two groups were adherent in 32.4% and 42.3%, respectively (Figure). Adherence was significantly better with good/excellent bowel preps (71.8%) compared to other bowel prep categories (p< 0.001), and patients with poor, fair, or no documentation of prep were adherent in 42.1% (Table). Conclusion: In this project, adherence among academic gastroenterologist met guideline-specified target of 90% when a gastroenterology fellow participated in the procedure. In all other groups, adherence did not meet the recommended threshold. These data are similar to our 2017 QI project and identify an excellent opportunity for a quality intervention educational and monitoring project to improve performance.Figure 1.: Adherence to Guidelines per Endoscopic Specialty Table 1. - Adherence to Recommended Intervals stratified by Bowel Preparation Bowel Preparation Adherence to Recommended Intervals* P-value No Documentation 42.9% (9/21) < 0.001 Poor/Inadequate 62.2% (28/45) Fair 19.5% (8/41) Good/Excellent 71.8% (257/358) *Adherence to recommended intervals by guidelines defined as a 10-year repeat colonoscopy recommendation if colonoscopy was normal in an average-risk individual, < 1 year was recommended if the bowel preparation was inadequate, or repeat colonoscopy not recommended if patient was ≥66 years at time of normal colonoscopy.

Colorectal adenomas and MAFLD: a cross-sectional study in a hispanic screening cohort

Aims: Prior evidence demonstrates an association between non-alcoholic fatty liver disease (NAFLD) and colorectal adenomas (CRA) risk. However, information using the new definition of the disease [i.e., metabolic dysfunction-associated fatty liver disease (MAFLD)] is scarce. We aimed to assess the relationship between MAFLD and CRA risk. Methods: We conducted a cross-sectional study including patients from three university centers in Chile who underwent a colonoscopy for colorectal cancer screening and abdominal imaging study. We obtained sociodemographic and clinical data, and we performed univariate and multivariable regression analyses. Results: In total, 895 patients were included; 42% were male, the mean age was 59.9 ± 9.3 years, and 37.8% (338) had CRA. Patients harboring polyps were predominantly males (48.2% vs. 38.2%, P = 0.002), older (61.6 ± 8.7 years vs. 58.9 ± 9.5 years, P &lt; 0.001), and exhibited a higher body weight than controls [75 (66-88) kg vs. 72 (63-82.3) kg, P = 0.002]. Fifty-six percent of patients showed hepatic steatosis in imaging studies and 54.4% met MAFLD diagnostic criteria. The adenoma detection rate was higher in the MAFLD group compared to controls (46.4% vs. 27.5%, P &lt; 0.001). In the multivariable analysis, MAFLD was significantly associated with the presence of CRA (odds ratio = 2.32; 95%CI: 1.68-3.19, P &lt; 0.0001). There were no statistically significant differences of histopathological characteristics of the adenomas according to the presence of MAFLD. Conclusion: The present study shows that, in Chilean Hispanic subjects, MAFLD is associated with an increased risk of CRA. This information may be useful to design specific screening colonoscopy recommendations in MAFLD patients.

Colonoscopy utilization and outcomes in older adults: Data from the New Hampshire Colonoscopy Registry.

Colonoscopy is frequently performed in older adults, yet data on current use, and clinical outcomes of and follow-up recommendations after colonoscopy in older adults are lacking. This was an observational study using the New Hampshire Colonoscopy Registry of adults age ≥65 years undergoing colonoscopy for screening, surveillance of prior polyps, or evaluation of symptoms. The main outcomes were clinical findings of polyps and colorectal cancer and recommendations for future colonoscopy by age. Between 2009 and 2019, there were 42,611 colonoscopies, of which 17,527 (41%) were screening, 19,025 (45%) surveillance, and 6059 (14%) for the evaluation of symptoms. Mean age was 71.1 years (SD 5.0), and 49.3% were male. The finding of colorectal cancer was rare (0.71%), with the highest incidence among diagnostic examinations (2.4%). The incidence of advanced polyps increased with patient age from 65-69 to ≥85 years for screening (7.1% to 13.6%; p= 0.05) and surveillance (9.4% to 12.0%; p< 0.001). Recommendations for future colonoscopy decreased with age and varied by findings at current colonoscopy. In patients without any significant findings, 85% aged 70-74 years, 61.9% aged 75-79 years, 39.1% aged 80-84 years, and 27.4% aged ≥85 years (p< 0.001) were told to continue colonoscopy. Among patients with advanced polyps, 97.2% aged 70-74 years, 89.6% aged 75-79 years, 78.4% aged 80-84 years, and 66.7% aged ≥85 years were told to continue colonoscopy (p< 0.001). Within this comprehensive statewide registry, clinical findings during colonoscopy varied by indication and increased with age. Overall rates of finding advanced polyps and colorectal cancer are low. Older adults are frequently recommended to continue colonoscopy despite advanced age and insignificant clinical findings on current examination. These data inform the potential benefits of ongoing colonoscopy, which must be weighed with the low but known potential immediate and long-term harms of colonoscopy, including cost, psychological distress, and long lag time to benefit exceeding life expectancy.

Recommendations for follow-up interval after colonoscopy with inadequate bowel preparation in a national colonoscopy quality registry

Endoscopist recommendations regarding a repeat colonoscopy after inadequate bowel cleanliness have not been fully described. Our aim was to evaluate the timing of recommendations for repeat colonoscopy after inadequate bowel preparation using a large, national colonoscopy registry. We performed a cross-sectional analysis of all outpatient screening and surveillance colonoscopies among adults ages 50 to 75 reported in the GI Quality Improvement Consortium from 2011 to 2018. The primary outcome was a recommendation to repeat colonoscopy within 1 year. Secondary outcomes were recommendations based on indication of colonoscopy and colonoscopy findings and predictors of a recommendation to follow-up within 1 year. There were 260,314 colonoscopies with inadequate bowel preparation performed at 672 different sites by 4001 endoscopists. Of these, 31.9% contained a recommendation for follow-up within 1 year. This did not differ meaningfully by examination indication. The severity of colonoscopy findings influenced the recommendations for follow-up (within 1 year in 84.0% of cases with adenocarcinoma, 51.8% with any advanced lesion, and 23.2% with 1-2 small adenomas). Younger age, more severe pathology, location in the Northeast, and performance by an endoscopist with an adenoma detection rate≥25% were associated with recommendations for follow-up within 1 year. Only some colonoscopies with inadequate bowel preparation are recommended to be repeated within 1 year, which may have implications for potential missed lesions. Further understanding of reasons driving recommendations is an important next step to improving guideline-concordant colonoscopy practice.

A Multilocus Blood-Based Assay Targeting Circulating Tumor DNA Methylation Enables Early Detection and Early Relapse Prediction of Colorectal Cancer

Colorectal cancer (CRC) is one of the most common and deadliest cancers worldwide. Patient survival can be greatly improved if cancerous lesions are detected early. 1 Siegel R.L. et al. CA Cancer J Clin. 2020; 70: 7-30 Crossref PubMed Scopus (10742) Google Scholar Despite a strong recommendation of colonoscopy for CRC screening, patients prefer noninvasive tests, and 83% favor blood-based tests. 2 Adler A. et al. BMC Gastroenterol. 2014; 14: 183 Crossref PubMed Scopus (109) Google Scholar Blood tests that rely on a single DNA methylation biomarker have been approved 3 deVos T. et al. Clin Chem. 2009; 55: 1337-13346 Crossref PubMed Scopus (391) Google Scholar ; however, they are not recommended due to the low sensitivity for detecting early-stage CRC. 4 US Preventive Services Task Force et al. JAMA. 2016; 315: 2564-2575 Crossref PubMed Scopus (1196) Google Scholar

Updates in artificial intelligence in gastroenterology endoscopy in 2020.

Artificial intelligence is becoming rapidly integrated into modern technology including medicine. Artificial intelligence has a wide range of potential in gastroenterology, particularly with endoscopy, given the required analysis of large datasets of images. The aim of this review is to summarize the advances of artificial intelligence in gastroenterology (GI) endoscopy over the past year. Computer-aided detection (CADe) systems during real-time colonoscopy have resulted in increased adenoma detection rate with no significant increase in procedure times. Deep learning techniques have been utilized to accurately assess bowel preparation quality, which would impact surveillance colonoscopy recommendations. For the upper GI tract, CADe systems have been developed to aid in improving the diagnosis of Barrett's neoplasia during real-time endoscopy. Artificial intelligence-assisted real-time endoscopy has been shown to reduce blind spots during EGD. The application of artificial intelligence in gastroenterology endoscopy remains promising. Advances over the past year include improved detection of GI neoplasia during endoscopy and characterization of lesions. Further research including randomized, multicenter trials are needed to further evaluate the use of artificial intelligence for real-time endoscopy.

913 An Audit of Colonoscopy Compliance Within A Screening Programme for Patients with A Family History of Colorectal Cancer (CRC)

Abstract Introduction Guidelines on the management of hereditary CRC were updated in 2019 and have led to more stringent use of surveillance colonoscopies. Patients with ‘family history’ (FH) CRC Surveillance programme at York Hospitals Trust were studied to assess compliance with colonoscopy recommendations. Method Current BSG/ACPGBI guidelines recommend biennial, quinquennial, one-off or no colonoscopy surveillance for patients with Lynch syndrome, and those deemed to have high, moderate, and average risks of developing hereditary cancer, respectively. Examination of electronic records and clinical notes were performed to determine if they were Lynch positive and/or if they could be assigned a risk category. Results Database of 227 patients, of which 14 were high, 61 moderate and 45 were low risk. 47 had Lynch syndrome. Compliance of colonoscopy was poor for patients with average and moderate FH risk (both 0%). Compliance was higher for patients with high risk of FH (50%) and those with Lynch syndrome (57%) Risk was indeterminate in 24 patients due to inadequate data therefore compliance could not be assessed. Conclusions A large proportion of patients with low to moderate ‘FH’ risk within our current surveillance programme had unnecessary colonoscopies. Stratification of patients into the appropriate risk categories optimizes the benefit from surveillance programmes.

Are the current colonoscopy recommendations for interval surveillance in patients with polyps enough? Machine learning-augmented propensity score cohort analysis of 1840 patients.

Colonoscopy remains the gold standard for screening and surveillance of colorectal neoplasms, and is associated with a lower risk of colorectal cancer (CRC)-related mortality. The current interval surveillance recommendations in patients with previous adenomas lack sufficient evidence. The prevalence of subsequent adenomas, and especially high-risk adenomas, during surveillance is not well known. The primary outcome of this study was to determine the prevalence of polyps upon surveillance colonoscopy in patients who have a history of adenomas on initial average-risk-screening colonoscopy, but then have a normal initial surveillance (second) colonoscopy between 2003 and 2017. This is the first known retrospective cohort study of adenoma detection rate (ADR) with sub-group analysis of patients with serial surveillance colonoscopies by abnormal and high-risk surveillance findings separately by prior abnormal colonoscopies and correct surveillance strategies based on the recent March 2020 updated guidelines. After ADR calculation, machine learning-augmented propensity score adjusted multivariable regression with augmented inverse-probability weighting propensity (AIPW) score analysis was used to assess the relationship between guideline adherence, as well as abnormal and high-risk surveillance findings. A total of 1840 patients with pathologically confirmed adenomas or cancer on an initial average-risk-screening (first) colonoscopy met study criteria. 837 (45.5%) had confirmed adenomas on second colonoscopy, and 1003 (54.5%) had normal findings. Of 837 patients with polyps on both first and second colonoscopy, 423 (50.5%) had adenomas on third colonoscopy. Of the 1003 patients without polyps on second colonoscopy, 406 (40.5%) had confirmed adenomas on third colonoscopy. Guideline adherence was low at 9.18%, though was associated in propensity score adjusted multivariable regression with increased odds of an abnormal third (but not high-risk) colonoscopy, with comparable AIPW results. This 14-year study demonstrates the ADR to be > 40% on the third colonoscopy for patients with adenomas on initial screening colonoscopy, who then have a normal second colonoscopy. Through advanced machine learning and propensity score analysis, we showed that correct adherence is associated with higher odds of abnormal, but not high-risk abnormal 3rd colonoscopy, with evidence that high-risk surveillance findings are reduced by providers shortening the time between surveillance colonoscopies in contrast to the guidelines for those for whom there is presumed greater clinical suspicion of eventual cancer. Larger prospective trials are needed to guide optimal surveillance for these patients.

Interval colonoscopy following acute diverticulitis should not be discouraged yet: results from a retrospective cohort.

Although included in some guidelines, the recommendation of interval colonoscopy after an acute diverticulitis (AD) episode has recently been questioned. In this study, we evaluated the incidence of colon cancer during the follow-up of an episode of AD. A retrospective review was carried out of patients with conservatively treated AD at our Institution (January 2011 to December 2018) with or without endoscopic study. Patients who had no colonoscopy performed were followed for two years. The demographic, clinical, radiological, follow-up and anatomopathological records were analysed. We determined CT scan validity for the differential diagnosis of CC and AD; sensibility, specificity, predictive values and likelihood ratios were calculated. Patients lost to follow-up and patients who had had colonoscopy in the previous three years were excluded. This study included 285 patients with a mean age of 59 years. A total of 225 interval colonoscopies were performed and 60 patients without colonoscopy were followed up. There were 19 CC (6.7%) diagnosed, 14 with interval colonoscopy and 5 during follow-up; 8 (42.1%) happened in patients who had had an episode of uncomplicated AD. Although CT scan accuracy is high, 87.7%, positive and negative likelihood ratios were low, 4.67 and 0.64, respectively. Interval colonoscopy should still be advisable after an episode of AD. The rationale for this statement is based on a non-negligible rate of hidden CC and an important uncertainty in the differential diagnosis.

Uptake and predictors of colonoscopy use in family members not participating in cascade genetic testing for Lynch syndrome

Cascade genetic testing provides a method to appropriately focus colonoscopy use in families with Lynch syndrome (LS). However, research suggests that up to two-thirds at risk to inherit LS don’t participate. Within the United States, no studies have assessed colonoscopy use within this elusive and high-risk subset. We set forth to (1) document colonoscopy use within those not undergoing genetic testing (NGT) and (2) identify factors associated with completing colonoscopy. Data came from a cross sectional survey of families with molecularly confirmed LS. One hundred seventy-six (176) adults participated; 47 of unknown variant status and 129 with variant status known (59 carriers/70 non-carriers). Despite a high level of awareness of LS (85%) and identical recommendations for colonoscopy, NGT reported significantly lower use of colonoscopy than carriers (47% vs. 73%; p = 0.003). Our results show that perceived risk to develop colon cancer (AOR = 1.99, p < 0.05) and physician recommendations (AOR = 7.64, p < 0.01) are significant predictors of colonoscopy use across all family members controlling for carrier status. Given these findings, health care providers, should assess patients’ perceived risk to develop cancer, assist them in adjusting risk perceptions and discuss recommendations for colonoscopy with all members in families with LS.Trial Registration Clinical Trials.gov Identifier: NCT00004210.