Quality indicators for colonoscopy and the risk of interval cancer

Current status of artificial intelligence colonoscopy on improving adenoma detection rate based on systematic review of multiple metanalysis

BACKGROUND

Colorectal cancer (CRC) can be prevented by screening and early detection. Colonoscopy is used for screening, and adenoma detection rate (ADR) is used as a key quality indicator of sufficient colonoscopy. However, ADR can vary significantly among endoscopists, leading to missed polyps or cancer. Artificial intelligence (AI) has shown promise in improving ADR by assisting in real-time polyp identification or diagnosis. While multiple randomized controlled trials (RCTs) and metanalyses highlight the benefits of AI in increasing detection rates and reducing missed polyps, concerns remain about its real-world applicability, impact on procedure time, and cost-effectiveness.

AIM

To explore the current status of AI assistance colonoscopy in adenoma detection and improving quality of colonoscopy.

METHODS

This systematic review followed PRISMA guidelines, both PubMed and Web of Science databases were used for articles search. Metanalyses and systematic reviews that assessed AI's role during colonoscopy. English article only published between January 2000 and January 2025 were included. Articles related to non-adenoma indications were excluded. Data extraction was independently performed by two researchers for accuracy and consistency.

RESULTS

22 articles met the inclusion criteria, with significant heterogeneity (I² = 28%-91%) observed in multiple studies. The number of studies per metanalysis ranged from 5 to 33, with higher heterogeneity in analyses involving more than 18 RCTs. AI demonstrated improvement in ADR, with an approximate 20% increase across multiple studies. However, its effectiveness in detecting flat or serrated adenomas remains unproven. Endoscopists with low ADR benefit more from AI-colonoscopies, while expert endoscopists outperformed AI in ADR, adenoma miss rate, and the identification of advanced lesions. No significant change in withdrawal time was observed when comparing AI-assisted colonoscopy to conventional endoscopy.

CONCLUSION

While AI-assisted colonoscopy has been shown to improve procedural quality, particularly for junior endoscopists and those with lower ADR, its performance decreases when compared to expert endoscopists in real-time clinical practice. This is especially evident in non-randomized studies, where AI demonstrates limited real-world benefits despite its benefit in controlled settings. Furthermore, no meta-analyses have specifically examined AI's impact on the learning experience of fellows and residents. Some experts caution that reliance on AI may prevent trainees from developing essential observational skills, potentially leading to less thorough examinations. Further research is needed to determine the actual benefits of AI-colonoscopy, particularly its role in cancer prevention. As technology advances, improved outcomes are expected, especially in detecting small, flat, and lesions at difficult anatomical locations.

Photodocumentation of Large Colorectal Polyps: An Audit of Image Quality

BACKGROUND

Numerous guidelines recommend photodocumentation (PD) of large colorectal polyps ≥10 mm (LP) preresection relative to an open snare or forceps, and suggests postresection PD of the clear resection base. However, no quality metrics have been proposed. We recently reported that preresection and postresection PD occurred in 82% and 52% of 1693 resected LPs, respectively; however, the quality of PD was not ascertained.

AIMS

To assess the quality of preresection and postresection PD of LPs based on consensus definitions.

METHODS

Images of LPs resected between 2016 and 2021 were reviewed by 3 gastroenterologists and 1 fellow for assessment of (1) high-quality preresection PD (enough polyp visualized to estimate size), (2) presence of a tool relative to the LP, (3) estimated polyp size, and (4) high-quality postresection PD (clean base without visible polyp tissue). Confidence levels in PD quality assessment and estimated size were provided. Agreement on size was assessed using free-marginal kappa.

RESULTS

One hundred ninety-nine LPs with both preresection and postresection images were included. Reviewers' assessment of high-quality preresection PD ranged from 49% to 82% and 51% to 70% for high-quality postresection PD. One percent of preresection images demonstrated an open snare or forceps relative to the LP. Only 74% to 89% of polyps were estimated by reviewers to be ≥10 mm [Kappa=0.66 (95% CI: 0.48-0.64)]. High-level confidence in PD quality and size assessment was lowest in the fellow compared with established gastroenterologists.

CONCLUSIONS

Although guidelines recommend PD of LPs preresection and postresection, the quality of PD appears suboptimal. Quality standards in LP PD should be considered and the impact of high-quality PD on patient outcomes should be studied.

Profile of colorectal polyps in young patients: A retrospective study

There is an increased incidence of colorectal cancer in young patients, however, the relationship between polyp characteristics and histology is not clearly understood. This study aimed to investigate the prevalence of different histological types of polyps in young patients and risk factors associated with advanced histology. Young patients (aged <45) who underwent polypectomy at Sir Run Run Shaw Hospital (2015-2017, Zhejiang, China) and West China Xiamen Hospital (2023-2024, Xiamen, China) were included. A database of endoscopes was accessed to classify polyps according to endoscopic features. The distribution of polyps and the risk factors associated with advanced histology were reported. The detection rate of polyps among the young adults was 20%, with 47.6% of adenoma. Hyperplastic polyps were second only to tubular adenomas in frequency. Of the 2776 polyps, nearly 85% were sessile, 29.4% were located in the sigmoid colon, and 25.4% were located in the rectum. Among polyps, 87.3% were <10 mm in diameter. Histological features of advanced adenoma were found in 5.3% of patients. Of these, 30.4% occurred in polyps <10 mm. Furthermore, 69.6% were distributed in the distal colorectum. Multivariate logistic regression analysis demonstrated that polyp size and morphology were independent predictors of advanced adenomas. In young patients, polyps are mainly located in the distal colorectum, with tubular adenoma being the predominant type. Large size and pedunculated morphology were independent predictors of advanced polyp histology in young patients. Nearly one-third of the advanced histology cases were associated with small polyps. It is recommended that endoscopists resect all neoplastic polyps found during colonoscopy, especially pedunculated polyps, and submit them for histology.

Akita Japan population-based colonoscopy screening trial: report of initial colonoscopy

OBJECTIVE

To assess the safety and quality of baseline screening colonoscopy in a randomised controlled trial (RCT).

METHODS

A population-based RCT with an explanatory design is ongoing to evaluate the efficacy of colonoscopy screening in 9751 men and women aged 40-74 years at average risk of colorectal cancer (CRC) in Japan. Screening colonoscopies for the intervention group were performed from June 2009 to June 2017.

RESULTS

Of the 4861 participants in the intervention group, 4495 (92.5%) underwent screening colonoscopy. The quality of bowel preparation was excellent (34.8%) or good (45.6%) in 80.4% of cases. The caecal intubation rate was 99.7% (4483/4495), and the mean (±SD) withdrawal time was 9.7 (±5.3) min. The adenoma detection rate (ADR) was 39.4% (1770/4495). A total of 27 participants (0.6%) were diagnosed with CRC, and 266 (5.9%) were diagnosed with advanced neoplasia (AN). In women, adenomas were more frequently detected in the proximal colon than in the distal colon (proximal: 18.9% vs distal: 16.4%, p=0.024), and a similar trend was observed for AN (proximal: 2.4% vs distal: 1.5%, p=0.045). No serious adverse events related to screening colonoscopy were reported, and minor adverse events were observed in two participants (0.04%).

CONCLUSIONS

Adequate performance in compliance, ADR, and safety was confirmed in the intervention arm of the RCT evaluating the efficacy of screening colonoscopy. The high quality of screening colonoscopy observed in the trial suggests its feasibility as a population-based screening approach.

TRIAL REGISTRATION NUMBER

UMIN000001980.

The potential of CT colonography for colorectal cancer screening in Japan

Colorectal cancer remains a leading cause of mortality worldwide, and early detection is essential for improving outcomes. CT colonography (CTC) has emerged as a promising alternative to optical colonoscopy for colorectal cancer screening. This article explores the potential of CTC in Japan, focusing on quality control, patient acceptability, complications, and its role in screening programs. CTC has demonstrated high sensitivity and specificity for detecting colorectal polyps, with its diagnostic performance comparable to colonoscopy for lesions ≥ 10 mm. Techniques such as fecal tagging and dual-position imaging significantly enhance diagnostic accuracy. However, the variability in diagnostic outcomes underscores the need for rigorous interpretation training and quality control. The American College of Radiology recommends training with at least 50 cases verified by colonoscopy. Despite its advantages, the adoption of CTC in Japan remains limited due to low awareness among medical professionals, a shortage of trained radiologists, and the absence of specific guidelines endorsing its use. Patient acceptability for CTC is high due to its non-invasive nature, shorter examination time, and reduced bowel preparation requirements compared to colonoscopy. Nonetheless, complications such as bowel perforation, albeit rare, necessitate careful risk assessment. While CTC has been recognized in the U.S. and Europe for screening and diagnostic follow-up, its integration into Japan's colorectal cancer screening guidelines is crucial to expand its utilization. To maximize the benefits of CTC, efforts must focus on standardizing methodologies, establishing quality indicators, and generating robust evidence on mortality reduction and cost-effectiveness.

Case-mix-adjusted mean number of polyps per 100 procedures: a new candidate gold standard colonoscopy key performance indicator

OBJECTIVE

Adenoma detection rate (ADR) has been criticised as a colonoscopy key performance indicator (KPI), for excluding serrated polyps, requiring histological data and fostering a 'one-and-done' attitude. We hypothesised that a case-mix-adjusted mean number of polyps (aMNP) would address these criticisms and provide a better measure of colonoscopy quality. We aimed to develop an aMNP using the National Endoscopy Database (NED) and assess its relationship with quality metrics.

METHODS

We extracted colonoscopy data from NED for 1 January 2019-4 April 2019. Multiple negative binomial regression was undertaken to estimate effects of patient variables on MNP and generate aMNP. Associations between aMNP and polyp detection rate (PDR), proximal polypectomy rate (PPR), postcolonoscopy colorectal cancer (PCCRC) rate and Joint Advisory Group for GI endoscopy (JAG) Global Rating Scale (GRS) were explored.

RESULTS

92 892 colonoscopies were analysed. Patient age, sex and procedure indication were significantly associated with MNP and used to create aMNP. At endoscopist level, aMNP strongly correlated with PDR (Spearman rho=0.834, p<0.001) and PPR (rho=0.709, p<0.001). Median aMNP was significantly lower in Trusts with higher versus lower PCCRC rates (73.9 vs 67.0 polyps per 100 procedures, p=0.047) and higher in units with GRS A/B versus C/D (aMNP 63.5 vs 55.2, p<0.001).

CONCLUSIONS

We demonstrate a method to compute a novel case-mix-adjusted KPI, aMNP, which is significantly associated with PDR, PPR, PCCRC and JAG GRS. Histological data were unavailable. aMNP addresses many limitations of ADR, adjusts for warranted variation in detection, and hence may improve audit and feedback engagement. We propose it as a candidate gold standard KPI for reporting endoscopy quality.

A Novel Natural Language Processing Tool Improves Colonoscopy Auditing of Adenoma and Serrated Polyp Detection Rates

BACKGROUND AND STUDY AIMS

Determining adenoma detection rate (ADR) and serrated polyp detection rate (SDR) can be challenging as they usually involve manual matching of colonoscopy and histology reports. This study aimed to validate a Natural Language Processing (NLP) code that enables rapid and efficient data extraction to calculate ADR and SDR.

DESIGN

A NLP code was developed to automatically extract colonoscopy quality indicators from colonoscopy and histology reports at a tertiary health service. These reports were manually reviewed to verify the concordance of ADR and SDR between the two methods. This process was applied in the initial training phase, repeated following modification of the code, and again with a validation cohort.

RESULTS

Included in the training and test phases were 5911 colonoscopies, with 2022 in the validation phase. The NLP code extracted patient names with 99.9% concordance and had a 98.9% accuracy in ADR and SDR in the training phase. Search terms were subsequently modified to take into consideration spelling variations and overlapping terminologies. Using data from the same cohort, accuracy of the NLP improved to 100%, excluding four colonoscopies that had missing histology reports in the test phase. Using a validated cohort, NLP had a 99.9% accuracy in ADR and SDR. The total time taken for auditing using NLP in the validation phase was less than 1 h.

CONCLUSIONS

An automatic NLP code had an accuracy of almost 100% in determining ADR and SDR in a tertiary colonoscopy service. Wider adoption of NLP enables significant improvements in colonoscopy audits that is accurate and time efficient.

Exploring intraprocedural performance in colonoscopy: Insights from a tertiary care center in Saudi Arabia

BACKGROUND

Colonoscopy is essential for diagnosing and managing colorectal conditions, and is recognized as the gold standard for early cancer detection and removal of precancerous lesions. The American Society for Gastrointestinal Endoscopy and the American College of Gastroenterology have established benchmark indicators to minimize the risk of interval colorectal cancer. Despite their importance, research on these metrics in Saudi Arabia is limited. This study analyzes key intraprocedural indicators of colonoscopies at a tertiary care center to evaluate adherence to care standards.

METHODS

This retrospective study examined 3763 colonoscopies conducted by adult gastroenterologists at Johns Hopkins Aramco Healthcare from January 2021 to December 2022. Procedures were categorized as screening and non-screening, with demographic data collected alongside withdrawal time (WT), cecal intubation rate (CIR), polyp detection rate (PDR), adenoma detection rate (ADR), Boston Bowel Preparation Scale (BBPS), polyp retrieval rate, rectal retroflexion, and adverse events.

RESULTS

The mean age of participants was 54.13 years, with 81.56% of them Saudis and 44.6% female. The average WT was 10 min. The overall CIR was 93.6% (94.78% for screening), with a PDR of 33.9% and a retrieval rate of 96.6%. ADR for screening participants was 25.63%, and 88.94% of participants achieved a BBPS score of 6 or more. The adverse event rate was at 0.2%, primarily due to bleeding.

CONCLUSIONS

The study indicates that colonoscopy procedures adhere to care standards, with ADR among male screening patients approaching 30%. Further research is necessary to evaluate pre- and post-procedural indicators.

Dynamic adenoma detection rate influences the risk of metachronous advanced neoplasia after removal of low-risk findings in screening colonoscopy

BACKGROUND

Endoscopists' adenoma detection rate (ADR) may change over time and dynamic ADR has been identified as a predictor for post-screening colorectal cancer. However, whether low-risk findings removed by an endoscopist with a lower dynamic ADR benefit from a shorter duration of follow-up requires further research.

METHODS

We conducted a two-center retrospective study of individuals who had low-risk findings removed and underwent subsequent surveillance colonoscopy. Endoscopists' dynamic ADR was the ADR of the previous 100 screening colonoscopies performed by the same endoscopist. A Cox-regression model and Kaplan-Meier survival analysis were used to explore the relationship between dynamic ADR and metachronous advanced colorectal neoplasia (ACRN).

RESULTS

Totally, 3471 individuals who had low-risk findings removed in baseline colonoscopy were included in analysis. Decreasing endoscopists' dynamic ADR was independently associated with metachronous ACRN. A 3.97-, 2.21-, and 2.67-fold increased risk for metachronous ACRN was observed in individuals of which baseline colonoscopy was performed by an endoscopist with a dynamic ADR of < 15%, 15-19%, and 20-24%, respectively, compared with those with the highest dynamic ADR (≥ 25%). The cumulative incidence of metachronous ACRN reached the 5% threshold at 4.5 years, 7.3 years, and 6.2 years in the dynamic ADR < 15%, 15-19%, and 20-24% group, respectively.

CONCLUSION

Endoscopists' dynamic ADR influences the risk of metachronous ACRN after removal of low-risk findings in screening colonoscopy. Individuals undergoing removal of low-risk findings in screening colonoscopy by an endoscopist with a dynamic ADR < 25% may benefit from a shorter duration of follow-up interval.

A national survey on gastroenterology and hepatology training reveals dissimilar perceptions between trainees and trainers and an important need for improvement in training programs

OBJECTIVE

We aimed to collect data on gastroenterology and hepatology training from the viewpoint of trainees and trainers.

METHODS

A national online survey was distributed among trainees and specialists at certified training institutions between February and May 2024.

RESULTS

Overall, 226 respondents - 98 trainees, 78 trainers, 50 program directors, and department heads responded, with a national coverage of 70% of trainees and 85% of specialty-department heads. A training curriculum was reported by 56% of trainees and 84% of curriculum organizers, regular feedback and training progress meetings by 11% of trainees (57% if considered without assessment of training progress), but 88% of curriculum organizers. Training was rated as very good or good by 65% of trainees, 79% of trainers, and 100% of department heads. Quality of functional diagnostics, endoscopy, and ultrasound training was rated as very good or good by trainees in 16, 61, and 54%, by trainers in 27, 79, and 58%, and by department heads in 74, 89, and 85%. Much agreement was found concerning the wish for external rotations (trainees 65%, trainers 70%, and department heads 89%) and a new postcertification advanced-endoscopy training and accreditation.

CONCLUSION

Department heads seem to overestimate the quality of their training programs. Consequently, we found large discrepancies in the perception of specialty training that should stimulate efforts to standardize training and boost necessary train-the-trainer programs. Diagnosis of functional gastrointestinal disorders and abdominal ultrasound skills are areas with the largest room for improvement. Increased flexibility of hospital providers will be crucial for significant improvement of external training possibilities.

Improvement in Adenoma Detection Rate with Distal Attachment Device Endo-Wing™-Assisted Colonoscopy: A Randomized Control Trial

Aim: Endo-Wing™ is a soft silicone device with six wing-like projections attached at the end of the colonoscope that provides superior visualization by flattening the colonic fold and helps to maintain a central view of the colonoscope during withdrawal. This study aims to compare the adenoma detection rate (ADR) between standard colonoscopy and Endo-Wing™-assisted colonoscopy. Methods: This is a single-center, single-blind, parallel-group, randomized, actively controlled, exploratory clinical trial conducted between July 2019 and April 2020. Participants aged 45 and above who were symptomatic of colorectal cancer (CRC) or with a history of adenoma and under active surveillance were included. Exclusion criteria included colonic strictures, tumors, active colitis, a previous history of polyposis syndrome, colostomy/ileostomy, or a BPPS score of 0. Participants were subsequently randomized to receive standard colonoscopy (n = 96) or Endo-Wing™-assisted colonoscopy (n = 96) at a 1:1 ratio using a central block randomization method with varying block sizes. The primary endpoint was the ADR, and the differences between the two groups were evaluated using univariable statistical methods. Results: The ADR, the number of adenomas, and the size of adenomas in the Endo-Wing™-assisted colonoscopy group were significantly higher compared to standard colonoscopy (p = 0.005, 0.035, and 0.035, respectively). Cecal intubation rates were similar in both groups (p > 0.999). The proportions of colonoscopy requiring increased sedation and standard sedation were similar in both groups (p = 0.613). No adverse effects of bleeding, perforation, and device dislodgement were reported in both groups. Conclusions: This study concludes that Endo-Wing™-assisted colonoscopy improves the ADR compared to standard colonoscopy.

Impact of Bowel Cleansing on Polyp and Adenoma Detection Rate: Post-Hoc Analysis of a Randomized Clinical Trial

OBJECTIVES

To assess the impact of bowel cleansing quality on polyp detection rate (PDR) and adenoma detection rate (ADR) and explore predictors of lesion detection rate in patients undergoing colonoscopy.

METHODS

This is a post-hoc analysis of a multicenter randomized controlled trial (RCT) comparing 1L polyethylene glycol plus ascorbate (1L PEG+ASC) vs. 4L PEG as bowel preparation for colonoscopy.

RESULTS

PDR was significantly higher (35.6% vs. 18.5%, p = 0.013), and ADR was higher even if not significantly (25.6% vs. 16.7%, p = 0.153) in patients with Boston Bowel Preparation Scale (BBPS) ≥6 over BBPS <6. Comparing patients with BBPS = 9 over BBPS = 7-8, no significant differences were found in PDR (34.5% vs. 38.4%, p = 0.483) nor ADR (24.1% vs. 27.2%, p = 0.553). At multivariable regression analysis, older age (OR = 1.042, 95%CI = 1.021-1.063; p < 0.001), shorter intubation time (OR = 0.891, 95%CI = 0.816-0.972; p = 0.010), higher withdrawal time (OR = 1.171, 95%CI = 1.094-1.253; p < 0.001) and full consumption of the first dose (OR = 8.368, 95%CI = 1.025-68.331; p = 0.047) were independently associated with ADR.

CONCLUSIONS

This post-hoc analysis of a RCT showed that excellent cleansing (BBPS = 9) over high-quality cleansing (BBPS = 7-8) does not significantly improve PDR or ADR. Neither cleansing success nor preparation types were independently associated with ADR. Compliance with bowel preparation, timing of colonoscopy and withdrawal time are key elements for adequate ADR with potential implications for reducing interval colorectal cancer.

Adenoma Detection Rates Calculated Using All Examinations Are Associated With Lower Risk for Postcolonoscopy Colorectal Cancer: Data From the New Hampshire Colonoscopy Registry

INTRODUCTION

We used New Hampshire Colonoscopy Registry data to examine the association between postcolonoscopy colorectal cancer (PCCRC) risk and an adenoma detection rate (ADR) which was calculated using examinations with all indications, as compared with ADR restricted to only screening examinations.

METHODS

Our cohort study included New Hampshire Colonoscopy Registry patients with an index examination and at least 1 follow-up event, either a colonoscopy or a CRC diagnosis. Our outcome, PCCRC, was any CRC diagnosed ≥6 months after an index examination. The exposure variable was endoscopist-specific all-examination ADR (ADR-A), calculated for all indications, divided into quintiles. We also compared the ADR-A with a screening ADR (ADR-S). Cox regression was used to model the hazard of PCCRC on ADR, controlling for age, sex, and other covariates.

RESULTS

In 32,535 patients, a lower hazard for PCCRC (n = 178) was observed for ADR-A's ≥ 23%, as compared with ADR-A's <23% (reference) (23% to <29%: hazard ratio (HR) = 0.56, 95% CI: 0.36-0.87; 29% to <34%: HR = 0.60, 95% CI: 0.38-0.94; 34% to <44%: HR = 0.43, 95% CI: 0.29-0.65; and ≥44%: HR = 0.32, 95% CI: 0.16-0.63). The highest quartile of ADR-A (42%+) (HR = 0.41, 95% CI: 0.23-0.75) had a similar protection from PCCRC as the highest quartile of ADR-S (35%+) (HR = 0.38, 95% CI: 0.21-0.70). We observed 95% CIs for ADR's were 28% narrower (median = 0.72; interquartile range (IQR): 0.10) for endoscopists when using ADR-A vs ADR-S.

DISCUSSION

Our data demonstrating lower PCCRC risk in examinations performed by endoscopists with higher ADR's calculated with all examinations help to validate ADR-A as a quality measure. ADR-A may also increase precision of the calculated ADR. Endoscopists should strive for a higher ADR-A with 44% as an aspirational target.

Lower adenoma detection rate in anesthesia assisted colonoscopy: a retrospective study

Objectives

As anesthesia assisted (AA) colonoscopy becomes increasingly popular, there has been concern about its impact on the quality of colonoscopy examinations. We aimed to clarify the impact of anesthesia assistance on the adenoma detection rate (ADR) and non-adenomatous polyp detection rate (PDR) of colonoscopy.

Methods

We collected data from patients undergoing colonoscopy throughout the year 2023 at our institution, with a total of 16,465 cases identified for potential analysis. After using propensity score matching (PSM) to minimize the influence of other variables on the study outcomes, there were 6,094 cases remaining for analysis in both the AA group and non-AA group, respectively. Then, we compared the ADR and PDR between the two groups and analyzed the colon location and size of adenomas or polyps found in different groups.

Results

The ADR in the non-AA group (36.94%) was significantly higher than that in the AA group (26.40%) (p<0.0001), while there was no statistically significant difference in the PDR between the two groups. AA could also affect the probability of discovering adenomas or polyps in some colon segments, but had no significant effect on the size of the discovered adenomas or polyps. In addition, there were more significant advantages of ADR in the non-AA group among the more experienced endoscopists' cohort.

Conclusions

Non-AA colonoscopy had a higher ADR, suggesting that while AA may potentially reduce patient stress responses to some extent, it confers few benefits in terms of adenoma detection.

Clinical Trial Registration

https://www.chictr.org.cn/showproj.html?proj=232248.

Differences in colonoscopy performance among four endoscopy centers in Western Norway: Influence of case-mix

Background and study aims

Unmodifiable patient factors such as age, sex, and indication (case-mix) may influence colonoscopy performance. In this study, we explored how case-mix affected polyp detection, cecal intubation, and pain on a center level.

Methods

A cross-sectional study was performed on data from four centers in Western Norway registered in the national endoscopy quality registry, Gastronet, in 2020 and 2021. We extracted demographics, indication, and the performance measures cecal intubation rate (CIR), proportion of at least one polyp ≥ 5 mm in size per colonoscopy (PDR-5), and pain. We also analyzed the explanatory variables bowel preparation, withdrawal time, and sedation/analgesia.

Results

First colonoscopies in 14,765 patients were included. Median age was 60 years (interquartile range 46-71) and 54% were women. Case-mix differed between centers and significantly influenced performance measures. Increased PDR-5 was associated with higher age and male sex (odds ratio [OR] 1.27, 95% confidence interval [CI] 1.18-1.37). The indication surveillance had the highest PDR-5 (44.9%, 95% CI 42.6-47.1) and inflammatory bowel disease the lowest (14.6%, 95% CI 12.3-16.8). CIR decreased with increasing age. Men had less pain (OR 0.33, 95% CI 0.27-0.39). Among indications, surveillance and IBD had higher CIRs and less pain. Performance measures differed among centers, even after adjustment for case-mix and other known explanatory variables such as sedation/analgesia and bowel preparation.

Conclusions

Case-mix influenced performance measures. Although we showed center differences in performance, other factors, such as individual endoscopist skills, probably influence performance measures. Our study demonstrates the importance of considering case-mix when assessing colonoscopy performance.

Eye movement patterns associated with colorectal adenoma detection: Post hoc analysis of randomized controlled trial

Background and study aims

The adenoma detection rate is higher among endoscopists who spend more time observing screen edges during colonoscopies. Nonetheless, eye movement parameters related to lesion detection remain unknown. This study aimed to determine the specific eye movement parameters related to colorectal adenoma detection, including the gaze rate in a particular area and eye movement speed.

Patients and methods

This study was a post hoc analysis of a randomized controlled trial investigating the effect of modifying eye movements of endoscopists on colorectal adenoma detection. Gaze rate at a specific area and eye movement speed were calculated based on endoscopist gaze coordinates in each examination. Time required for observation and treatment of polyps was excluded. The lower peripheral area was defined as the bottom row when the screen was divided into 6×6 sections. These parameters were compared between patients with and without adenomas.

Results

Five physicians performed 158 colonoscopies. The adenoma detection group exhibited a lower peripheral gaze rate (13.7% vs. 9.5%, P = 0.004) and smaller average eye movement distance (29.9 pixels/30 ms vs. 33.3 pixels/30 ms, P = 0.022). Logistic regression analysis showed that a lower peripheral gaze rate > 13.0% and an average eye movement distance <30 pixels/30 ms were increased independent predictors of adenoma detection ( P = 0.024, odds ratio [OR] 2.53, 95% confidence interval [CI] 1.71-3.28; P = 0.045, OR 4.57, 95% CI 1.03-20.2), whereas age, sex, and withdrawal time were not.

Conclusions

Lower peripheral gaze rate and slow eye movement are associated with colorectal adenoma detection.

Efficacy and safety of oral sulfate solution versus polyethylene glycol for colonoscopy: A systematic review and meta-analysis of randomized controlled trials

Background

Colonoscopy is the gold standard for early detection and monitoring of colorectal cancer. Procedural effectiveness is dependent on optimal bowel preparation. Traditional polyethylene glycol (PEG) solutions are difficult to tolerate, whereas newer low-volume alternatives, including PEG with ascorbic acid and oral sulfate solutions (OSS), offer improved efficacy and tolerability. The meta-analysis was performed to evaluate the efficacy and safety of OSS compared to PEG for bowel preparation in colonoscopy.

Methods

Studies were identified by searching PubMed, Embase, Cochrane CENTRAL, and clinicaltrials.gov from inception until June 2024. Only randomized controlled trials comparing OSS with PEG were included. Data was analyzed using R version 4.4.0 using a random effects model to calculate risk ratios (RRs) and mean differences (MDs) with 95% confidence intervals (CIs).

Results

Twenty-one studies with 6346 participants met the inclusion criteria. OSS significantly improved adenoma detection (RR, 1.13; 95% CI, 1.04-1.22; p-value <0.01; I2 = 0%) and polyp detection rates (RR, 1.16; 95% CI, 1.06-1.26; p-value <0.01; I2 = 0%), and had a higher Boston Bowel Preparation Scale (BBPS) score (MD, 0.31; 95% CI, 0.13-0.50; p-value <0.01; I2 = 81%). PEG was associated with more sleep disturbances (RR, 0.45; 95% CI, 0.25-0.82; p-value = 0.03; I2 = 0%). However, other adverse effects were similar between both solutions.

Conclusion

OSS demonstrated superior adenoma and polyp detection rates. When compared to PEG, patients utilizing OSS achieved higher BBPS scores. Data gleaned support enhanced cleansing efficacy and safety of OSS as a bowel preparation regimen.

Role of Artificial Intelligence for Colon Polyp Detection and Diagnosis and Colon Cancer

The broad use of artificial intelligence (AI) and its various applications have already shown significant impact in medicine and in everyday life. In gastroenterology, the most studied AI tools at present are computer-aided detection (CADe) and computer-aided diagnosis (CADx). These tools have been mainly assessed during colonoscopy for the detection of polyps and for the prediction of their histology based on their appearance. Their use aims to improve colonoscopy quality, standardize procedures, and potentially reduce costs. Data on CADe demonstrate clear benefits that are applicable to clinical practice. While CADx shows good diagnostic performance, its additional benefits in assisting endoscopists remain unclear.

Risk Factors of Missed Adenoma Detected by Colonoscopic Polypectomy and Its Impact of the Endoscopic System

BACKGROUND

The adenoma detection rate is a key colonoscopy quality indicator, but the adenoma miss rate (AMR) is more strongly linked to post-colonoscopy colorectal cancer risk. While studies examined high-definition colonoscopy and AMR, no studies have assessed its impact on consecutive polypectomy.

AIM

This study aimed to identify adenomas missed in screening or surveillance colonoscopy and determine if the endoscopic system affects the miss rate.

METHODS

This retrospective study analyzed patients referred to Dong-A University Hospital for polypectomy after polyps were detected during screening or surveillance colonoscopy at 24 healthcare institutions. Endoscopic systems used in these colonoscopies were classified as FHD (FHD) or non-FHD. Consecutive polypectomies were performed by a single expert between March 2020 and February 2022 using the FHD system. The AMR was compared and analyzed for screening or surveillance colonoscopies performed using FHD endoscopic systems and those using non-FHD endoscopic systems.

RESULTS

Of 542 polyps, 186 were missed (miss rate: 25.22%). Miss rates for adenoma and advanced neoplasia were 27.34% and 14.69%. Univariate analysis identified age, adenoma count, and endoscopic system as significant factors. However, only the endoscopic system remained significant in the multivariate analysis. In screening or surveillance colonoscopy, the use of FHD endoscopic systems demonstrated a lower AMR compared to non-FHD systems (21.86% vs. 31.41%, P = 0.014).

CONCLUSION

The use of FHD endoscopic systems reduced AMR compared to non-FHD systems.

AGA Living Clinical Practice Guideline on Computer-Aided Detection-Assisted Colonoscopy

BACKGROUND & AIMS

This American Gastroenterological Association (AGA) guideline is intended to provide an overview of the evidence and support endoscopists and patients on the use of computer-aided detection (CADe) systems for the detection of colorectal polyps during colonoscopy.

METHODS

A multidisciplinary panel of content experts and guideline methodologists used the Grading of Recommendations Assessment, Development and Evaluation framework and relied on the following sources of evidence: (1) a systematic review examining the desirable and undesirable effects (ie, benefits and harms) of CADe-assisted colonoscopy, (2) a microsimulation study estimating the effects of CADe on longer-term patient-important outcomes, (3) a systematic search of evidence evaluating the values and preferences of patients undergoing colonoscopy, and (4) a systematic review of studies evaluating health care providers' trust in artificial intelligence technology in gastroenterology.

RESULTS

The panel reached the conclusion that no recommendation could be made for or against the use of CADe-assisted colonoscopy in light of very low certainty of evidence for the critical outcomes, desirable and undesirable (11 fewer colorectal cancers per 10,000 individuals and 2 fewer colorectal cancer deaths per 10,000 individuals), increased burden of more intensive surveillance colonoscopies (635 more per 10,000 individuals), and cost and resource implications. The panel acknowledged the 8% (95% CI, 6%-10%) increase in adenoma detection rate and 2% (95% CI, 0%-4%) increase in advanced adenoma and/or sessile serrated lesion detection rate.

CONCLUSIONS

This guideline highlights the close tradeoff between desirable and undesirable effects and the limitations in the current evidence to support a recommendation. The panel acknowledged the potential for CADe to continually improve as an iterative artificial intelligence application. Ongoing publications providing evidence for critical outcomes will help inform a future recommendation.

Impact of advanced endoscopy training on colonoscopy quality and efficiency

Objectives

Few reports have detailed improvements in the quality of colonoscopies with continuous training post-fellowship completion. We examined the changes in colonoscopy performance among trainees during our advanced endoscopy training program.

Methods

Screening or surveillance colonoscopies performed by 11 trainees who participated in our 3-year advanced endoscopy training program between April 2015 and March 2020 were retrospectively analyzed. Quality and efficiency metrics of colonoscopies were evaluated annually.

Results

Altogether, 297, 385, and 438 colonoscopies were enrolled in the first, second, and third training years, respectively. The mean insertion times were 8.6, 7.6, and 6.9 min in the first, second, and third training years, respectively, with significant improvement from the first to second year (p = 0.03) and from the first to third year (p < 0.01). The adenoma detection rate, proximal adenoma detection rate, and mean number of adenomas per patient exhibited a tendency to improve annually; however, the difference was not significant. Polypectomy efficiency was 10.5%, 11.2%, and 13.0%, with significant improvements from the first to third year (p < 0.01) and from the second to third year (p = 0.02). Insertion time and polypectomy efficiency showed significant improvements, especially among trainees experienced with <500 colonoscopies.

Conclusions

Through our advanced endoscopy training program, there has been an improvement in the quality and efficiency of colonoscopy for trainees who have completed their fellowships, particularly those with <500 colonoscopies.

Gender Differences in Quality of Bowel Preparation for Colonoscopy: Post Hoc Analysis of a Randomized Controlled Trial

OBJECTIVE

Bowel cleansing is a key element for a quality colonoscopy. Despite recent advances, not all predictors of successful cleansing are fully known. This post hoc analysis of an RCT aims to explore gender differences in bowel cleansing quality.

METHODS

The "OVER" trial was a multicenter phase-4 RCT including 478 patients randomized 1:1 to receive split-dose 1L polyethylene glycol plus ascorbate (PEG+ASC) or 4L-PEG. In this post hoc analysis, multivariable logistic regression models were designed to assess predictors of cleansing success (CS) and adenoma detection rate (ADR) by gender.

RESULTS

Of the 478 randomized patients, 50.2% were males and 49.8% females.Overall, CS was comparable between females and males (87.1% vs 88.4, P = 0 .6), whereas CS in the right (95.7% vs 90.9, P = 0.049) and transverse colon (98.6% vs 93.9, P =0.011) was significantly higher in females.At multivariable regression analysis for CS outpatient setting (OR = 5.558) and higher withdrawal time (OR = 1.294) were independently associated with CS in females, whereas screening/surveillance indication (OR = 6.776) was independently associated with CS in males.At multivariable regression analysis for ADR, running time <5 hours (OR = 3.014) and higher withdrawal time (OR = 1.250) were independently associated with ADR in females, whereas older age (OR = 1.040) and higher withdrawal time (OR = 1.093) were independently associated with ADR in males.

CONCLUSIONS

This study showed different results in bowel preparation quality and different predictors of CS and ADR by gender. These findings suggest the need for further research to explore gender-specific approaches for bowel preparation.

Efficacy of texture and color enhancement imaging for the visibility and diagnostic accuracy of non-polypoid colorectal lesions

Objective

A newly launched endoscopy system (EVIS X1, CV-1500; Olympus) is equipped with texture and color enhancement imaging (TXI). We aimed to investigate the efficacy of TXI for the visibility and diagnostic accuracy of non-polypoid colorectal lesions.

Methods

We examined 100 non-polypoid lesions in 42 patients from the same position, angle, and distance of the view in three modes: white light imaging (WLI), narrow-band imaging (NBI), and TXI. The primary outcome was to compare polyp visibility in the three modes using subjective polyp visibility score and objective color difference values. The secondary outcome was to compare the diagnostic accuracy without magnification.

Results

Overall, the visibility score of TXI was significantly higher than that of WLI (3.7 ± 1.1 vs. 3.6 ± 1.1; p = 0.008) and lower than that of NBI (3.7 ± 1.1 vs. 3.8 ± 1.1; p = 0.013). Color difference values of TXI were higher than those of WLI (11.5 ± 6.9 vs. 9.1 ± 5.4; p < 0.001) and lower than those of NBI (11.5 ± 6.9 vs. 13.1 ± 7.7; p = 0.002). No significant differences in TXI and NBI (visibility score: 3.7 ± 1.0 vs. 3.8 ± 1.1; p = 0.833, color difference values: 11.6 ± 7.1 vs. 12.9 ± 8.3; p = 0.099) were observed for neoplastic lesions. Moreover, the diagnostic accuracy of TXI was significantly higher than that of NBI (65.5% vs. 57.6%, p = 0.012) for neoplastic lesions.

Conclusions

TXI demonstrated higher visibility than that of WLI and lower than that of NBI. Further investigations are warranted to validate the performance of the TXI mode comprehensively.

A comparative study benchmarking colon polyp with computer-aided detection (CADe) software

Background and aims

Computer-aided detection software (CADe) has shown promising results in real-time polyp detection, but a limited head-to-head comparison of the available CADe systems has been performed. Moreover, such systems have not been compared to endoscopists using standardized videos. This study aims to compare the performance of three CADe systems in detecting polyps, employing a novel standardized methodology.

Methods

Videos from 300 colonoscopies conducted at Oslo University Hospital were analyzed. Short video clips (20-45 s) presenting normal mucosa or polyps were randomly selected. These videos were then streamed through each CADe system from Medtronic, Olympus, and Augere Medical. Each system featured diverse configurations, resulting in a total of six software settings. Sensitivity and false positivity (FP) were assessed by comparing the CADe systems to both the mean of the systems and pairwise between them. Furthermore, the systems' performance was compared to the performance of five endoscopists.

Results

CADe systems' sensitivity ranged between 84.9% and 98.7%, with statistically significant differences observed between the systems, both in comparison to the mean and to each other. FP rates ranged between 1.2% and 5.6%, also differing statistically significantly between the systems. The CADe systems achieving the highest sensitivity also exhibited the highest FP. Statistically significant differences in the alert delay were observed between different CADe systems and endoscopists.

Conclusions

This study highlights significant differences between commercially available CADe software regarding sensitivity and FP, but a superior performance compared to endoscopists. The software with the highest sensitivity also exhibited the highest FP, highlighting the need for further refinement.

The Efficacy of Texture and Color Enhancement Imaging Observation in the Detection of Colorectal Lesions: A Multicenter, Randomized Controlled Trial (deTXIon Study)

BACKGROUND & AIMS

Colonoscopy is the gold standard for detecting and resecting adenomas and early-stage cancers to reduce colorectal cancer (CRC) incidence and mortality rates. This study aimed to confirm the superiority of texture and color enhancement imaging (TXI) over white light imaging (WLI) in detecting colorectal lesions.

METHODS

This randomized controlled trial was conducted at 8 Japanese institutions between March 2023 and October 2023. Participants aged 40 to 80 years old scheduled for CRC screening and nonscreening purposes, such as postpolypectomy surveillance, positive fecal occult blood test results, and abdominal symptoms, were included. We used only the latest model colonoscopes and performed observations in each arm of the TXI model and WLI. The primary end point was the mean number of adenomas detected per procedure. Secondary end points included the adenoma detection rate, polyp detection rate, flat polyp detection rate, and adverse events.

RESULTS

A total of 956 patients were enrolled and randomized. After patients who did not meet the eligibility criteria were excluded, 451 and 445 patients were included in the TXI and WLI arms, respectively. The mean number of adenomas detected per procedure was 1.4 and 1.5 and the adenoma detection rate was 57.2% and 56.0% in TXI and WLI, respectively, and there were no statistically significant differences between 2 arms. The polyp detection rate and flat polyp detection rate were significantly higher in TXI than in WLI, which were 82.5% vs 74.4% (P = .003), and 76.5% vs 70.3% (P = .036), respectively.

CONCLUSIONS

This study did not demonstrate the superiority of TXI over WLI in detecting neoplastic lesions. However, TXI may be effective in detecting flat polyps.

CLINICAL TRIAL REGISTRATION

jRCT1032230089.

One in three adenomas could be missed by white-light colonoscopy - findings from a systematic review and meta-analysis

BACKGROUND

White light (conventional) colonoscopy (WLC) is widely used for colorectal cancer screening, diagnosis and surveillance but endoscopists may fail to detect adenomas. Our goal was to assess and synthesize overall and subgroup-specific adenoma miss rates (AMR) of WLC in daily practice.

METHODS

We conducted a systematic review in MEDLINE, EMBASE, Cochrane Library, and grey literature on studies evaluating diagnostic WLC accuracy in tandem studies with novel-colonoscopic technologies (NCT) in subjects undergoing screening, diagnostic or surveillance colonoscopy. Information on study design, AMR overall and specific for adenoma size, histology, location, morphology and further outcomes were extracted and reported in standardized evidence tables. Study quality was assessed using the QUADAS-2 tool. Random-effects meta-analyses and meta-regression were performed to estimate pooled estimates for AMR with 95% confidence intervals (95% CI) and to explain heterogeneity.

RESULTS

Out of 5,963 identified studies, we included sixteen studies with 4,101 individuals in our meta-analysis. One in three adenomas (34%; 95% CI: 30-38%) was missed by WLC in daily practice individuals. Subgroup analyses showed significant AMR differences by size (36%, adenomas 1-5 mm; 27%, adenomas 6-9 mm; 12%, adenomas ≥ 10 mm), histology (non-advanced: 42%, advanced: 21%), morphology (flat: 50%, polypoid: 27%), but not by location (distal: 36%, proximal: 36%).

CONCLUSIONS

Based on our meta-analysis, one in three adenomas could be missed by WLC. This may significantly contribute to interval cancers. Our results should be considered in health technology assessment when interpreting sensitivity of fecal occult blood or other screening tests derived from studies using WLC as "gold standard".

Colon Cancer Screening, Surveillance, and Treatment: Novel Artificial Intelligence Driving Strategies in the Management of Colon Lesions

Colonoscopy, a crucial procedure for detecting and removing colorectal polyps, has seen transformative advancements through the integration of artificial intelligence, specifically in computer-aided detection (CADe) and diagnosis (CADx). These tools enhance real-time detection and characterization of lesions, potentially reducing human error, and standardizing the quality of colonoscopy across endoscopists. CADe has proven effective in increasing adenoma detection rate, potentially reducing long-term colorectal cancer incidence. However, CADe's benefits are accompanied by challenges, such as potentially longer procedure times, increased non-neoplastic polyp resections, and a higher surveillance burden. CADx, although promising in differentiating neoplastic and non-neoplastic diminutive polyps, encounters limitations in accuracy, particularly in the proximal colon. Real-world data also revealed gaps between trial efficacy and practical outcomes, emphasizing the need for further research in uncontrolled settings. Moreover, CADx limited specificity and binary output underscore the necessity for explainable artificial intelligence to gain endoscopists' trust. This review aimed to explore the benefits, harms, and limitations of artificial intelligence for colon cancer screening, surveillance, and treatment focusing on CADe and CADx systems for lesion detection and characterization, respectively, while addressing challenges in integrating these technologies into clinical practice.

Accuracy of Computer-aided Diagnosis in Colonoscopy Varies According to Polyp Location: A Systematic Review and Meta-analysis

BACKGROUND & AIMS

Computer-aided diagnosis (CADx) assists endoscopists in differentiating between neoplastic and non-neoplastic polyps during colonoscopy. This study aimed to evaluate the impact of polyp location (proximal vs. distal colon) on the diagnostic performance of CADx for ≤5 mm polyps.

METHODS

We searched for studies evaluating the performance of real-time CADx alone (ie, independently of endoscopist judgement) for predicting the histology of colorectal polyps ≤5 mm. The primary endpoints were CADx sensitivity and specificity in the proximal and distal colon. Secondary outcomes were the negative predictive value (NPV), positive predictive value (PPV), and the accuracy of the CADx alone. Distal colon was limited to the rectum and sigmoid.

RESULTS

We included 11 studies for analysis with a total of 7782 polyps ≤5 mm. CADx specificity was significantly lower in the proximal colon compared with the distal colon (62% vs 85%; risk ratio (RR), 0.74; 95% confidence interval [CI], 0.72-0.84). Conversely, sensitivity was similar (89% vs 87%); RR, 1.00; 95% CI, 0.97-1.03). The NPV (64% vs 93%; RR, 0.71; 95% CI, 0.64-0.79) and accuracy (81% vs 86%; RR, 0.95; 95% CI, 0.91-0.99) were significantly lower in the proximal than distal colon, whereas PPV was higher in the proximal colon (87% vs 76%; RR, 1.11; 95% CI, 1.06-1.17).

CONCLUSION

The diagnostic performance of CADx for polyps in the proximal colon is inadequate, exhibiting significantly lower specificity compared with its performance for distal polyps. Although current CADx systems are suitable for use in the distal colon, they should not be employed for proximal polyps until more performant systems are developed specifically for these lesions.

The Effect of Computer-Aided Device on Adenoma Detection Rate in Different Implement Scenarios: A Real-World Study

BACKGROUND

Several recent studies have found that the efficacy of computer-aided polyp detection (CADe) on the adenoma detection rate (ADR) diminished in real-world settings. The role of unmeasured factors in AI-human interaction, such as monitor approaches, remains unknown. This study aimed to validate the effectiveness of CADe in the real world and assess the impact of monitor approaches.

METHODS

A retrospective propensity score-matched cohort study was conducted using routine data from a tertiary endoscopy center in China before and after the implementation of CADe. Four propensity score-matched cohorts were established: Cohort 1: pre-CADe matched with dual-monitor CADe-assisted group; Cohort 2: dual-monitor CADe-assisted with single-monitor CADe-assisted group; Cohort 3: pre-CADe with single-monitor CADe-assisted group; and Cohort 4: pre-CADe with CADe period. ADR was set as the primary outcome.

RESULTS

There were 5390, 6083, and 6131 eligible patients in the pre-CADe group, dual-monitor group, and single-monitor group, respectively. In the matched analysis, results indicated that regardless of the monitor setup, CADe-assisted groups showed a trend of increased ADR compared with the pre-CADe period (CADe period: OR 1.141, 95% CI 1.047-1.243; p = 0.003; dual-monitor: OR 1.178, 95% CI 1.069-1.299, p = 0.001; single-monitor: OR 1.094, 95% CI 0.998-1.200, p = 0.056). Moreover, no significant difference between different monitor approaches was observed, although dual-monitor setup showed an increasing tendency on ADR compared with single-monitor setup (OR 1.069, 95% CI 0.985-1.161, p = 0.109).

CONCLUSION

CADe shows great potential to improve ADR during colonoscopy in the real world. Meanwhile, changes in monitor setup do not significantly impact the assistance capability of CADe. Further research dedicated to evaluating the unmeasured elements in the AI-clinician hybrid for better implementation of CADe would be beneficial.

Optimal visual gaze pattern of endoscopists for improving adenoma detection during colonoscopy (with video)

BACKGROUND AND AIMS

Visual gaze pattern (VGP) analysis quantifies endoscopists' specific eye movements. VGP during colonoscopy may be associated with polyp detection. However, the optimal VGP to maximize detection performance remains unclear. This study evaluated the optimal endoscopic VGP that enabled the highest colorectal adenoma detection rate.

METHODS

This randomized controlled trial was conducted between July and December 2023. We developed an eye-tracking and feedback (ETF) system that instructed endoscopists to correct their gaze toward the periphery of an endoscope screen with an audible alert. Patients who underwent colonoscopy were randomly assigned to 4 groups: 3 intervention groups, in which the endoscopist's gaze was instructed to a different level of the peripheral screen area using the ETF system (the periphery of 4 × 4, 5 × 5, and 6 × 6 divisions of the screen), and a control group in which the endoscopist did not receive instructions. The primary outcome was the number of adenomas detected per colonoscopy (APC).

RESULTS

In total, 189 patients were enrolled. The APC and adenoma detection rate were significantly higher in the 6 × 6 group than in the control group (1.82 ± 2.41 vs 0.59 ± 1.17, P = .002; 68.9% vs 30.8%, P = .002). The APC and the number of screen divisions were positively correlated (R = 0.985, P = .0152). The rate at which the endoscopist gazed at the periphery of the screen was positively correlated with the number of divisions (R = 0.964, P = .0363).

CONCLUSIONS

Colorectal adenoma detection was improved by correcting the endoscopist's gaze to the periphery of the screen, especially by dividing the screen into 6 × 6 segments.

AI and Polyp Detection During Colonoscopy

Colorectal cancer (CRC) prevention depends on effective colonoscopy; yet variability in adenoma detection rates (ADRs) and missed lesions remain significant hurdles. Artificial intelligence-powered computer-aided detection (CADe) systems offer promising advancements in enhancing polyp detection. This review examines the role of CADe in improving ADR and reducing adenoma miss rates (AMRs) while addressing its broader clinical implications. CADe has demonstrated consistent improvements in ADRs and AMRs; largely by detecting diminutive polyps, but shows limited efficacy in identifying advanced adenomas or sessile serrated lesions. Challenges such as operator deskilling and the need for enhanced algorithms persist. Combining CADe with adjunctive techniques has shown potential for further optimizing performance. While CADe has standardized detection quality; its long-term impact on CRC incidence and mortality remains inconclusive. Future research should focus on refining CADe technology and assessing its effectiveness in reducing the global burden of CRC.

Sustained success in endoscopic performance demonstrated by the Irish National Endoscopy Quality Improvement Programme

Background and study aims

The National Gastrointestinal Endoscopy Quality Improvement (NEQI) Programme captures over 94% of endoscopic activity in the Republic of Ireland (ROI), accounting for > 120,000 colonoscopies per annum. The aim of this study was to assess temporal changes in colonoscopy Key Quality Indicators (KQIs) at a national level over a 5-year period among low-, intermediate-, and high-volume endoscopists.

Methods

A retrospective analysis of all NEQI colonoscopy episodes occurring between 2016 and 2022, collating colonoscopy KQIs (cecal intubation rate [CIR], comfort score [CS], polyp detection rate [PDR] and sedation use). Endoscopists with 5 consecutive years of activity were defined as low, intermediate, or high activity according to annual procedural volumes.

Results

Over 658,000 colonoscopies were completed by 1240 endoscopists. Workload is disproportionate, with 36% of endoscopists completing 66% of national colonoscopy volume. Low-, intermediate-, and high-activity endoscopists all demonstrated sustained improvements in KQI targets over the study period. Comparing experts (≥ 300 colonoscopies/year) vs non-experts, KQI plateaus were demonstrated for PDR at < 150 colonoscopies per year (34.2% vs 29.6%, P = 0.002), CS at < 200 procedures per year (97.5% vs 94.9%, P < 0.001), and CIR at < 250 colonoscopies per year (94.5% vs 93.4%, P = 0.048).

Conclusions

This study represents the first published endoscopist-level NEQI data demonstrating ongoing KQI improvements for endoscopists at all activity levels. Sustaining this improvement and continuing to capture national endoscopic performance will remain a core role of the Irish NEQI program. Workforce imbalances and minimum annual volumes continue to represent challenges for national endoscopy programs.

ARE QUALITY INDICATORS IMPORTANT IN COLONOSCOPIES? ANALYSIS OF 3,076 EXAMS IN A PRIVATE TERTIARY SERVICE IN SOUTHEASTERN BRAZIL

BACKGROUND

The carcinogenesis of colorectal cancer is well understood. Adenomas are the precursor lesions in about 70% of cases, highlighting the importance of screening programs.

AIMS

The aim of this study was to analyze the effectiveness of colonoscopy examinations performed in a private tertiary service by calculating the polyp detection rate (PDR) and adenoma detection rate (ADR) and comparing these rates with literature data.

METHODS

This retrospective observational study evaluated colonoscopies performed at Hospital Centro Médico de Campinas between 2018 and 2020. It assessed the indications and complications of colonoscopy, sex, age group, bowel preparation, cecal intubation rate, ADR, PDR, and advanced adenoma detection rate (AADR).

RESULTS

During the period, 3,686 colonoscopies were performed, and 3,076 were included in the analysis. The mean patient age was 57.2 years, and most patients were female (53.5%). Complications occurred in 39 colonoscopies (1.3%), with bleeding in six cases and perforation in one case. Tubular adenoma was the most prevalent histological subtype found in 20% of tests and in 62.7% of those with positive findings. The PDR was 23% and significantly increased with advancing age (p<0.01). The ADR was 20% and also significantly increased with age (p<0.001). This rate was higher in men (27%). The AADR was 4%.

CONCLUSIONS

Colonoscopy is an effective polyp detection method, and the PDR was higher in men and significantly increased with age. The ADR and AADR were comparable to the literature data.

Right-Sided Versus Left-Sided Colon Cancer-A 5-Year Single-Center Observational Study

Background: Global colorectal cancer (CRC) incidence is significant, constituting 15% of all cancer cases with 1.4 million new diagnoses annually. Recent research suggests categorizing CRC into three clinical groups: right colon cancer (RCC), left colon cancer (LCC), and rectal cancer, each with distinct embryological and molecular characteristics. Methods: A retrospective analysis of 189 patients (103 men, 86 women) undergoing surgery for RCC and LCC from January 2018 to December 2023 was performed. Results: LCC was a more common localization (98, 51.85%) than RCC (91, 48.15%). Patients with RCC were older than patients with LCC (70 (36-92, IQR 11) vs. 68 (38-84, IQR 12.5) years; p = 0.02). The duration of surgical procedure was comparable in both groups (225 (120-420, IQR 80) vs. 210 (105-505, IQR 85) minutes; p = 0.16). Complications occurred in 16 (17.58%) patients with RCC and in 15 (15.31%) patients with LCC (p = 0.72). One-year overall survival was 92.76% (SE 2.16%) (91.57% (SE 3.43%) in the RCC group and 93.99% (SE 2.61%) in the LCC group; p = 0.79). Conclusions: Colon cancer incidence is increasing globally due to economic and lifestyle factors. Our study reflects this trend, noting a rise in cases from 2018 to 2023. Despite several differences, overall survival rates do not significantly differ between RCC and LCC patients. Understanding clinical disparities is crucial for optimizing patient outcomes.

Adenoma Detection Rates by Physicians and Subsequent Colorectal Cancer Risk

Importance

Patients of physicians with higher adenoma detection rates (ADRs) during colonoscopy have lower colorectal cancer (CRC) risk after screening colonoscopy (ie, postcolonoscopy CRC). Among physicians with an ADR above the recommended threshold, it is unknown whether improving ADR is associated with a lower incidence of CRC in their patients.

Objective

To determine the association of improved ADR in physicians with a range of ADR values at baseline with CRC incidence among their patients.

Design, Setting, and Participants

A total of 789 physicians in the Polish Colonoscopy Screening Program were studied between 2000 and 2017, with final follow-up on December 31, 2022. Joinpoint regression analyses were used to identify trends between changes in ADR and postcolonoscopy CRC incidence. Rates of CRC after colonoscopy were compared between physicians whose ADR improved and those without improvement. ADR improvement was defined as either an improvement by at least 1 ADR sextile category or remaining in the highest category.

Exposure

Physician ADR.

Main Outcomes and Measures

Association of improved ADR with postcolonoscopy CRC incidence.

Results

Of 485 615 patients (mean [SD] age, 57 [5.41] years; 60% female), 1873 CRC diagnoses and 474 CRC-related deaths occurred during a median follow-up of 10.2 years. Among individual physicians at baseline, median (IQR) ADR was 21.8% (15.9%-28.2%) and maximum ADR was 63.0%. Joinpoint regression showed a change in CRC incidence trends at an ADR level of 26%, corresponding to a CRC incidence of 27.1 per 100 000 person-years. Patients of physicians whose ADR was less than 26% at baseline and improved during follow-up had a postcolonoscopy CRC incidence of 31.8 (95% CI, 29.5-34.3) per 100 000 person-years, compared with 40.7 (95% CI, 37.8-43.8) per 100 000 person-years for patients of physicians with an ADR of less than 26% at baseline who did not improve during follow-up (difference, 8.9/100 000 person-years [95% CI, 5.06-12.74]; P < .001). Patients of physicians whose ADR was above 26% at baseline and improved during follow-up had a postcolonoscopy CRC incidence of 23.4 (95% CI, 18.4-29.8) per 100 000 person-years, compared with 22.5 (95% CI, 18.3-27.6) for patients of physicians whose ADR was above 26% at baseline and did not improve during follow-up (difference, 0.9/100 000 person-years [95% CI, -6.46 to 8.26]; P = .80).

Conclusions and Relevance

In this observational study, improved ADR over time was statistically significantly associated with lower CRC risk in patients who underwent colonoscopy compared with absence of ADR improvement, but only among patients whose physician had a baseline ADR of less than 26%.

Improving colonoscopy quality in the national VA healthcare system

BACKGROUND

Colorectal cancer (CRC) prevention is a Veterans Affairs (VA) priority. Colonoscopy quality, especially adenoma detection rate (ADR), is critical for effective screening. Our research indicates considerable variation in ADR among VA providers. Even a slight increase in ADR can reduce fatal CRC rates, and audit and feedback strategies have improved ADR in other settings. A recent report identified deficiencies in VA colonoscopy quality, highlighting the need for standardized documentation and reporting. To address this, we developed the VA Endoscopy Quality Improvement Program (VA-EQuIP), which aims to improve colonoscopy quality through benchmarking and collaborative learning, aligning with VA's modernization priorities and HSR&D and QUERI goals of accelerating evidence-based implementation.

METHODS

We will conduct a stepped wedge cluster randomized trial to evaluate whether VA-EQuIP improves provider ADR compared to usual care, the implementation of VA-EQuIP, site-level factors associated with colonoscopy quality improvement, and components of provider behavior change. Using mixed methods our study will measure outcomes like reach, implementation, adoption, maintenance of VA-EQuIP, and provider behavior change. The analysis will include primary and secondary outcomes, such as overall and screening ADR, cecal intubation rate, and bowel preparation quality, using mixed effects generalized linear models and interrupted time-series analyses. Adoption and implementation will be evaluated through usage statistics, surveys, and qualitative interviews to identify factors influencing success.

DISCUSSION

This study will assess the impact of VA-EQuIP on colonoscopy quality metrics and factors associated with effective implementation. VA-EQuIP infrastructure allows for national-scale implementation and evaluation of quality reporting with minimal manual labor, guiding future quality improvement efforts to ensure optimal patient care.

Practical utility of linked color imaging in colonoscopy: Updated literature review

The remarkable recent developments in image-enhanced endoscopy (IEE) have significantly contributed to the advancement of diagnostic techniques. Linked color imaging (LCI) is an IEE technique in which color differences are expanded by processing image data to enhance short-wavelength narrow-band light. This feature of LCI causes reddish areas to appear redder and whitish areas to appear whiter. Because most colorectal lesions, such as neoplastic and inflammatory lesions, have a reddish tone, LCI is an effective tool for identifying colorectal lesions by clarifying the redder areas and distinguishing them from the surrounding normal mucosa. To date, eight randomized controlled trials have been conducted to evaluate the effectiveness of LCI in identifying colorectal adenomatous lesions. The results of a meta-analysis integrating these studies demonstrated that LCI was superior to white-light endoscopy for detecting colorectal adenomatous lesions. LCI also improves the detection of serrated lesions by enhancing their whiteness. Furthermore, accumulating evidence suggests that LCI is superior to white-light endoscopy for the diagnosis of the colonic mucosa in patients with ulcerative colitis. In this review, based on a comprehensive search of the current literature since the implementation of LCI, the utility of LCI in the detection and diagnosis of colorectal lesions is discussed. Additionally, the latest data, including attempts to combine artificial intelligence and LCI, are presented.

A deep neural network improves endoscopic detection of laterally spreading tumors

BACKGROUND

Colorectal cancer (CRC) is the malignant tumor of the digestive system with the highest incidence and mortality rate worldwide. Laterally spreading tumors (LSTs) of the large intestine have unique morphological characteristics, special growth patterns and higher malignant potential. Therefore, LSTs are a precancerous lesion of CRC that could be easily missed.

OBJECTIVE

The purpose of this study was to establish an LSTs lesion detection algorithm based on the YOLOv7 model and to evaluate the detection performance of the algorithm on LSTs.

METHOD

A total of 7985 LSTs images and 93,197 non-LSTs images were included in this study, and the training set, validation set, and 80% of the data in the dataset is used for training, 10% for validation, and 10% for testing. In detail, a total of 6261 LSTs images and 74,798 non-LSTs images were used as the training set to train the LSTs lesion detection algorithm to identify LSTs. A total of 743 LSTs images and 9486 non-LSTs images were used as validation set to evaluate the learning ability of the LSTs lesion detection algorithm. A total of 981 LSTs images and 8913 non-LSTs images were used as test set to evaluate the generalization ability of the LSTs lesion detection algorithm. To evaluate the diagnostic ability of the LSTs lesion detection algorithm for LSTs, we selected 3636 images (562 LSTs, 3074 non-LSTs) images from the test set as the subtest set. Finally, we compared the performance of the AI algorithm with endoscopist in the diagnosis of LSTs.

RESULT

The accuracy of LSTs lesion detection algorithm in identifying LSTs is 99.34%, sensitivity is 96.88%, specificity is 99.8%, positive predictive value is 98.94%, and negative predictive value is 99.41%.

CONCLUSION

Our model based on the YOLOv7 achieved high diagnostic accuracy in LSTs lesion, significantly better than that of novice and senior doctors, and reaching the same level as expert endoscopists.

Artificial Intelligence for Adenoma and Polyp Detection During Screening and Surveillance Colonoscopy: A Randomized-Controlled Trial

Background: Colorectal cancer (CRC) is the second leading cause of cancer death in Kuwait. The effectiveness of colonoscopy in preventing CRC is dependent on a high adenoma detection rate (ADR). Computer-aided detection can identify (CADe) and characterize polyps in real time and differentiate benign from neoplastic polyps, but its role remains unclear in screening colonoscopy. Methods: This was a randomized-controlled trial (RCT) enrolling patients 45 years of age or older presenting for outpatient screening or surveillance colonoscopy (Kuwait clinical trial registration number 2047/2022). Patients with a history of inflammatory bowel disease, alarm symptoms, familial polyposis syndrome, colon resection, or poor bowel preparation were excluded. Patients were randomly assigned to either high-definition white-light (HD-WL) colonoscopy (standard of care) or HD-WL colonoscopy with the CADe system. The primary outcome was ADR. The secondary outcomes included polyp detection rate (PDR), adenoma per colonoscopy (APC), polyp per colonoscopy (PPC), and accuracy of polyp characterization. Results: From 1 September 2022 to 1 March 2023, 102 patients were included and allocated to either the HD-WL colonoscopy group (n = 51) or CADe group (n = 51). The mean age was 52.8 years (SD 8.2), and males represented 50% of the cohort. Screening for CRC accounted for 94.1% of all examinations, while the remaining patients underwent surveillance colonoscopy. A total of 121 polyps were detected with an average size of 4.18 mm (SD 5.1), the majority being tubular adenomas with low-grade dysplasia (47.1%) and hyperplastic polyps (46.3%). There was no difference in the overall bowel preparation, insertion and withdrawal times, and adverse events between the two arms. ADR (primary outcome) was non-significantly higher in the CADe group compared to the HD colonoscopy group (47.1% vs. 37.3%, p = 0.3). Among the secondary outcomes, PDR (78.4% vs. 56.8%, p = 0.02) and PPC (1.35 vs. 0.96, p = 0.04) were significantly higher in the CADe group, but APC was not (0.75 vs. 0.51, p = 0.09). Accuracy in characterizing polyp histology was similar in both groups. Conclusions: In this RCT, the artificial intelligence system showed a non-significant trend towards improving ADR among Kuwaiti patients undergoing screening or surveillance colonoscopy compared to HD-WL colonoscopy alone, while it significantly improved the detection of diminutive polyps. A larger multicenter study is required to detect the true effect of CADe on the detection of adenomas.

Comparison of Colon Adenoma Detection Rate Using Transparent Cap-Assisted and Conventional Colonoscopy: Result from an International Trial in Asia

INTRODUCTION

Controversy remains regarding transparent cap-assisted technique improves adenoma detection rate (ADR) in colonoscopy. We aimed to investigate the effect of transparent cap-assisted colonoscopy (CAC) on ADR and other colonoscopy performance.

METHODS

We performed subanalysis of an international, multicenter, open-label database containing colonoscopy data from 11 centers in 4 Asian countries/regions on patients who underwent colonoscopy. The patient characteristics, procedure-related characteristics, and pathological findings of all detected lesions were prospectively recorded. The patients were divided into 2 groups as receiving colonoscopy with or without transparent cap attachment. The ADR and procedure time were compared between the 2 groups. Other procedural factors related to ADR were also investigated.

RESULTS

Between November 2020 and January 2022, 3,029 who underwent colonoscopy (transparent CAC, n = 1,796; standard colonoscopy, n = 1,233) were enrolled in this study. The transparent CAC group ADR was significantly higher than the conventional colonoscopy (55.1% vs. 50.0%, p < 0.01). Transparent CAC detected a higher proportion of patients with adenoma (odd ratio [OR]: 1.59, 95% CI: 1.13-2.24, p < 0.01) and any polypoid lesion (OR: 1.49, 95% CI: 1.04-2.16, p = 0.03). Transparent CAC also reduced cecal intubation time (mean difference: -0.35 min) and total colonoscopy time (mean difference -3.4 min). In the other procedural factors, using linked-color imaging (OR: 1.75, 95% CI: 1.49-2.06, p < 0.01), patient body rotation (OR: 1.54, 95% CI: 1.12-2.13, p < 0.01), longer withdrawal time (OR: 1.12, 95% CI: 1.09-1.15, p < 0.01) were also significantly associated to adenoma detection.

CONCLUSION

In real-world practice, transparent CAC is a safe and inexpensive technology that could improve adenoma and polyp detection.

Benefits, burden, and harms of computer aided polyp detection with artificial intelligence in colorectal cancer screening: microsimulation modelling study

ABSTRACT

Objective

To estimate the benefits, burden, and harms of implementing computer aided detection (CADe) of polyps in colonoscopy of population based screening programmes for colorectal cancer.

Design

Microsimulation modelling study.

Setting

Cost effectiveness working package in the OperA (optimising colorectal cancer prevention through personalised treatment with artificial intelligence) project. A parallel guideline committee panel (BMJ Rapid recommendation) was consulted in defining the screening interventions and selection of outcome measures.

Population

Four cohorts of 100 000 European individuals aged 60-69 years.

Intervention

The intervention was one screening of colonoscopy and a screening of colonoscopy after faecal immunochemical test every other year with CADe. The comparison group had the same screening every other year without CADe.

Main outcome measures

Benefits (colorectal cancer incidence and death), burden (surveillance colonoscopies), and harms (colonoscopy related adverse events) over 10 years were measured. The certainty in each outcome was assessed by use of the GRADE (Grading of Recommendations Assessment, Development, and Evaluation) approach.

Results

For 100 000 individuals participating in colonoscopy screening, 824 (0.82%) were diagnosed with colorectal cancer within 10 years without CADe versus 713 (0.71%) with CADe (risk difference -0.11% (95% CI -0.43% to 0.21%)). For faecal immunochemical test screening colonoscopy, the risk was 5.82% (n=5820) without CADe versus 5.77% (n=5770) with CADe (difference -0.05% (-0.33% to 0.15%)). The risk of surveillance colonoscopy increased from 26.45% (n=26 453) to 32.82% (n=32 819) (difference 6.37% (5.8% to 6.9%)) for colonoscopy screening and from 52.26% (n=52 263) to 53.08% (n=53 082) (difference 0.82% (0.38% to 1.26%)) for faecal immunochemical test screening colonoscopy. No significant differences were noted in adverse events related to the colonoscopy between CADe and no CADe. The model estimates were sensitive to the assumed effects of screening on colorectal cancer risk and of CADe on adenoma detection rates. All outcomes were graded as low certainty.

Conclusion

With low certainty of evidence, adoption of CADe in population based screening provides small and uncertain clinical meaningful benefit, no incremental harms, and increased surveillance burden after screening.

Post-colonoscopy cancer rates in Scotland from 2012 to 2018: A population-based cohort study

AIM

The aim of this work was to quantify post-colonoscopy colorectal cancer (PCCRC) rates in National Health Service (NHS) Scotland using World Endoscopy Association guidelines, compare incidence between health boards and referral streams and explore comparisons in results with published data from other healthcare systems.

METHOD

This is a population-based cohort study using NHS Scotland data between 2012 and 2018. All people undergoing colonoscopy between 2012 and 2018 and subsequently diagnosed as having bowel cancer up to 3 years after their investigation were included. The main outcome measures are national trends in the PCCRC rate at 3 years (PCCRC-3yr). with comparison between bowel screening and non-screening referral routes, board of referral and analysis of factors associated with occurrence.

RESULTS

The overall unadjusted PCCRC-3yr was 7.9% (7.4%-8.3%). There was no change in the annual rate over the 7-year study period. The PCCRC rate was lower for the Scottish Bowel Cancer Screening Programme (6.7% vs. 8.3%), but compared unfavourably with rates reported by the NHS England Bowel Cancer Screening Programme from an earlier time period. There was wide variation in rates between health boards of similar population size. Rates were higher in women, with increasing age and in patients with a history of inflammatory bowel disease or diverticular disease.

CONCLUSION

Despite advances in technology, there has been no improvement in the PCCRC rate in Scotland between 2012 and 2018. Rates in bowel screening colonoscopy are better than in nonscreening colonoscopy but compare unfavourably with NHS England, possibly as a result of less robust endoscopist selection and training. Quality improvement is required in colonoscopy in order to improve patient outcomes nationally, and to allow equitable access to higher-quality colonoscopy in different regions of the country.

Effectiveness of artificial intelligence assisted colonoscopy on adenoma and polyp miss rate: A meta-analysis of tandem RCTs

BACKGROUND AND AIMS

One-fourth of colorectal neoplasia is missed at screening colonoscopy, representing the leading cause of interval colorectal cancer (I-CRC). This systematic review and meta-analysis summarizes the efficacy of computer-aided colonoscopy (CAC) compared to white-light colonoscopy (WLC) in reducing lesion miss rates.

METHODS

Major databases were systematically searched through May 2024 for tandem-design RCTs comparing lesion miss rates in CAC-first followed by WLC vs WLC-first followed by CAC. The primary outcomes were adenoma miss rate (AMR) and polyp miss rate (PMR). The secondary outcomes were advanced AMR (aAMR) and sessile serrated lesion miss rate (SMR).

RESULTS

Six RCTs (1718 patients) were included. AMR was significantly lower for CAC compared to WLC (RR = 0.46; 95 %CI [0.38-0.55]; P < 0.001). PMR was also lower for CAC compared to WLC (RR = 0.44; 95 %CI [0.33-0.60]; P < 0.001). No significant difference in aAMR (RR = 1.28; 95 %CI [0.34-4.83]; P = 0.71) and SMR (RR = 0.44; 95 %CI [0.15-1.28]; P = 0.13) were observed. Sensitivity analysis including only RCTs performed in CRC screening and surveillance setting confirmed lower AMR (RR = 0.48; 95 %CI [0.39-0.58]; P < 0.001) and PMR (RR = 0.50; 95 %CI [0.37-0.66]; P < 0.001), also showing significantly lower SMR (RR = 0.28; 95 %CI [0.11-0.70]; P = 0.007) for CAC compared to WLC.

CONCLUSIONS

CAC results in significantly lower AMR and PMR compared to WLC overall, and significantly lower AMR, PMR and SMR in the screening/surveillance setting, potentially reducing the incidence of I-CRC.

Use of artificial intelligence improves colonoscopy performance in adenoma detection: a systematic review and meta-analysis

BACKGROUND AND AIMS

Artificial intelligence (AI) is increasingly used to improve adenoma detection during colonoscopy. This meta-analysis aimed to provide an updated evaluation of computer-aided detection (CADe) systems and their impact on key colonoscopy quality indicators.

METHODS

We searched the EMBASE, PubMed, and MEDLINE databases from inception until February 15, 2024, for randomized control trials (RCTs) comparing the performance of CADe systems with routine unassisted colonoscopy in the detection of colorectal adenomas.

RESULTS

Twenty-eight RCTs were selected for inclusion involving 23,861 participants. Random-effects meta-analysis demonstrated a 20% increase in adenoma detection rate (risk ratio [RR], 1.20; 95% confidence interval [CI], 1.14-1.27; P < .01) and 55% decrease in adenoma miss rate (RR, 0.45; 95% CI, 0.37-0.54; P < .01) with AI-assisted colonoscopy. Subgroup analyses involving only expert endoscopists demonstrated a similar effect size (RR, 1.19; 95% CI, 1.11-1.27; P < .001), with similar findings seen in analysis of differing CADe systems and healthcare settings. CADe use also significantly increased adenomas per colonoscopy (weighted mean difference, 0.21; 95% CI, 0.14-0.29; P < .01), primarily because of increased diminutive lesion detection, with no significant difference seen in detection of advanced adenomas. Sessile serrated lesion detection (RR, 1.10; 95% CI, 0.93-1.30; P = .27) and miss rates (RR, 0.44; 95% CI, 0.16-1.19; P = .11) were similar. There was an average 0.15-minute prolongation of withdrawal time with AI-assisted colonoscopy (weighted mean difference, 0.15; 95% CI, 0.04-0.25; P = .01) and a 39% increase in the rate of non-neoplastic resection (RR, 1.39; 95% CI, 1.23-1.57; P < .001).

CONCLUSIONS

AI-assisted colonoscopy significantly improved adenoma detection but not sessile serrated lesion detection irrespective of endoscopist experience, system type, or healthcare setting.

Current Status of Artificial Intelligence Use in Colonoscopy

BACKGROUND

Artificial intelligence (AI) has significantly impacted medical imaging, particularly in gastrointestinal endoscopy. Computer-aided detection and diagnosis systems (CADe and CADx) are thought to enhance the quality of colonoscopy procedures.

SUMMARY

Colonoscopy is essential for colorectal cancer screening but often misses a significant percentage of adenomas. AI-assisted systems employing deep learning offer improved detection and differentiation of colorectal polyps, potentially increasing adenoma detection rates by 8%-10%. The main benefit of CADe is in detecting small adenomas, whereas it has a limited impact on advanced neoplasm detection. Recent advancements include real-time CADe systems and CADx for histopathological predictions, aiding in the differentiation of neoplastic and nonneoplastic lesions. Biases such as the Hawthorne effect and potential overdiagnosis necessitate large-scale clinical trials to validate the long-term benefits of AI. Additionally, novel concepts such as computer-aided quality improvement systems are emerging to address limitations facing current CADe systems.

KEY MESSAGES

Despite the potential of AI for enhancing colonoscopy outcomes, its effectiveness in reducing colorectal cancer incidence and mortality remains unproven. Further prospective studies are essential to establish the overall utility and clinical benefits of AI in colonoscopy.

Validation of Artificial Intelligence Computer-Aided Detection of Colonic Neoplasm in Colonoscopy

BACKGROUND/OBJECTIVES

Controlling colonoscopic quality is important in the detection of colon polyps during colonoscopy as it reduces the overall long-term colorectal cancer risk. Artificial intelligence has recently been introduced in various medical fields. In this study, we aimed to validate a previously developed artificial intelligence (AI) computer-aided detection (CADe) algorithm called ALPHAON® and compare outcomes with previous studies that showed that AI outperformed and assisted endoscopists of diverse levels of expertise in detecting colon polyps.

METHODS

We used the retrospective data of 500 still images, including 100 polyp images and 400 healthy colon images. In addition, we validated the CADe algorithm and compared its diagnostic performance with that of two expert endoscopists and six trainees from Gachon University Gil Medical Center. After a washing-out period of over 2 weeks, endoscopists performed polyp detection on the same dataset with the assistance of ALPHAON®.

RESULTS

The CADe algorithm presented a high capability in detecting colon polyps, with an accuracy of 0.97 (95% CI: 0.96 to 0.99), sensitivity of 0.91 (95% CI: 0.85 to 0.97), specificity of 0.99 (95% CI: 0.97 to 0.99), and AUC of 0.967. When evaluating and comparing the polyp detection ability of ALPHAON® with that of endoscopists with different levels of expertise (regarding years of endoscopic experience), it was found that ALPHAON® outperformed the experts in accuracy (0.97, 95% CI: 0.96 to 0.99), sensitivity (0.91, 95% CI: 0.85 to 0.97), and specificity (0.99, 95% CI: 0.97 to 0.99). After a washing-out period of over 2 weeks, the overall capability significantly improved for both experts and trainees with the assistance of ALPHAON®.

CONCLUSIONS

The high performance of the CADe algorithm system in colon polyp detection during colonoscopy was verified. The sensitivity of ALPHAON® led to it outperforming the experts, and it demonstrated the ability to enhance the polyp detection ability of both experts and trainees, which suggests a significant possibility of ALPHAON® being able to provide endoscopic assistance.

13-Year colorectal cancer risk after lower-quality, higher-quality and no screening colonoscopy: a cohort study

OBJECTIVES

A lower-quality colonoscopy has been shown to be less effective in reducing colorectal cancer (CRC) incidence than a higher-quality colonoscopy, but the comparison with no-screening colonoscopy (noSC) is lacking. We aimed to compare the 13-year risk of developing CRC between persons with I) a higher-quality screening colonoscopy (higherQualSC), II) a lower-quality screening colonoscopy (lowerQualSC), and III) without a screening colonoscopy.

STUDY DESIGN AND SETTING

A health-care database (∼20% of the German population) was used to emulate a target trial with three arms: higherQualSC vs lowerQualSC vs noSC at baseline. The quality of screening colonoscopy was categorized based on the polyp detection rate of the examining physician (cut-off: 21.8%). We included persons aged 55-69 years at average CRC risk and CRC screening naïve at baseline. We estimated adjusted cumulative CRC incidence over 13 years of follow-up.

RESULTS

The higherQualSC arm comprised 142,960 persons, the lowerQualSC arm 62,338 persons, and the noSC arm 124,040 persons. The adjusted 13-year CRC risk was 1.77% in the higherQualSC arm, 2.09% in the lowerQualSC arm, and 2.74% in the noSC arm. Compared to the noSC arm, the adjusted relative risk was 0.76 (95% CI: 0.70-0.84) in the lowerQualSC arm and 0.65 (95% CI: 0.60-0.69) in the higherQualSC arm.

CONCLUSION

Our study shows that a lowerQualSC is also effective in reducing CRC incidence compared to noSC. However, the effect is about one-third less than that of a higherQualSC.

Colorectal Neoplasia Detection Rates in Lynch Syndrome

BACKGROUND

The expected and optimal adenoma detection rate (ADR) is not well characterized in Lynch syndrome (LS). The aim of this study is to determine the ADR, the overall colorectal neoplasia detection rate (CNDR), proximal serrated detection rate (PSDR), and CRC detection rate (CRCDR) in an LS cohort.

METHODS

A retrospective study was performed of individuals with LS who were evaluated at a single tertiary care center from May 2001 to September 2023 (n = 542). Data from procedure and pathology reports were collected along with relevant demographic, clinical history, and family history data. Fisher's exact test and the Kruskal-Wallis test were used to assess factors associated with colorectal neoplasia.

RESULTS

Amongst 542 individuals with LS, 352 met the inclusion criteria, and their 1296 colonoscopies/sigmoidoscopies were used for analysis. The cohort was primarily female (64.5%), white (87.5%), and privately insured (76.1%), with a near even distribution across genotypes. CNDR was 27.9%, ADR was 21.4%, PSDR was 7.7%, and CRCDR was 1.5%. Advanced age, Medicare insurance, prior colonic resection, and prior history of non-CRC were significantly associated with an increased CNDR and ADR (p < 0.05). PSDR remained constant with age. There was no association with genotype, biological sex, race, smoking, BMI, aspirin use, nor family history.

CONCLUSIONS

Despite frequent colonoscopies/sigmoidoscopies, individuals with LS maintain a high rate of colorectal neoplasia, primarily driven by increased detection of adenomas with advancing age. Neoplasia rates may serve as helpful "ballpark rates" for endoscopists performing colonoscopies/sigmoidoscopies in LS. However, further studies need to determine whether neoplasia rates are predictive of CRC risk and outcomes in LS.

Terminal ileal intubation is not necessary in routine colonoscopy: data from a large-scale retrospective study

BACKGROUND

Terminal ileal intubation (TII) demonstrates a complete colonoscopy, but whether it should be performed in routine colonoscopies remains uncertain. We aimed to explore the diagnostic yield of TII in routine colonoscopy and investigate the association of TII and the detection of lesion.

METHODS

We conducted a retrospective study included patients who underwent colonoscopy with cecal intubation at our endoscopic center between November 1 2022 and July 31 2023. Macroscopic and histologic findings of terminal ileum were recorded. We used propensity score matching to adjust for differences between groups and further analyzed the difference of polyp detection rate (PDR), adenoma detection rate (ADR), sessile serrated lesion detection rate (SSDR) and lesion detection rate of right-sided colon, cecum and ascending colon between patients underwent TII or not.

RESULTS

There were 13,372 patients with cecal intubation colonoscopy, including 7599 (56.8%) with TII and 5773 (43.2%) without TII. Abnormal endoscopic findings were observed in 150 of 7599 unselected individuals and only 7 of these cases were regarded as pathologically significant. Likewise, abnormal endoscopic findings were found in 62 of 3502 asymptomatic individuals with 54 nonspecific ileitis determined by histopathology. After PSM, there were no significant differences in PDR (52.0% vs. 52.3%, P = 0.761), ADR (30.9% vs. 32.2%, P = 0.208), SSDR (1.6% vs. 1.5%, P = 0.541), right-sided lesion detection rate (16.9% vs. 16.8%, P = 0.908), lesion detection rate of cecum (4.9% vs. 4.7%, P = 0.613) and ascending colon (13.5% vs. 13.2%, P = 0.656) between the two groups.

CONCLUSION

TII was not necessary in routine colonoscopy, owing to the limited diagnostic value and lack of superiority on lesion detection.

Costs and benefits of a formal quality framework for colonoscopy: Economic evaluation

Background and study aims Reduction of colorectal cancer morbidity and mortality is one of the primary objectives of colonoscopy. Post-colonoscopy colorectal cancers (PCCRCs) are critical outcome parameters. Analysis of PCCRC rates can validate quality assurance measures in colonoscopy. We assessed the effectiveness of implementing a gastroenterologist-led quality framework that monitors key procedure quality indicators (i.e., bowel preparation quality, adenoma detection rates, or patient satisfaction) by comparing the PCCRC rate before and after implementation. Patients and methods Individuals who had a colonoscopy between 2010 and 2017 at a single tertiary center in Queensland, Australia, were included and divided into two groups: baseline (2010-2014) and redesign phase (2015-2017). Data linkage of the state-wide cancer registry and hospital records enabled identification of subjects who developed colorectal cancers within 5 years of a negative colonoscopy. Costs associated with quality improvement were assessed for effectiveness. Results A total of 19,383 individuals had a colonoscopy during the study period. Seventeen PCCRCs were detected. The PCCRC rate was 0.376 per 1,000 person-years and the average 5-year PCCRC risk ranged from 0.165% to 0.051%. The rate of PCCRCs was higher at the beginning (0.166%; 95% confidence interval [CI] 0.15%-0.17%) compared with the later period with full implementation of quality control measures (0.027%; 95% CI 0.023%-0.03%). The quality process determined an incremental cost-effectiveness ratio of -$5,670.53 per PCCRC avoided. Conclusions This large cohort study demonstrated that a formal gastroenterologist-led quality assurance framework embedded into the routine operations of a clinical department not only reduces interval cancers but is also cost-effective regarding life years gained and quality-adjusted life years.