Adenoma detection rate and risk of colorectal cancer and death

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.

Artificial Intelligence in Gastrointestinal Endoscopy

Recent advancements in artificial intelligence (AI) have significantly impacted the field of gastrointestinal (GI) endoscopy, with applications spanning a wide range of clinical indications. The central goals for AI in GI endoscopy are to improve endoscopic procedural performance and quality assessment, optimize patient outcomes, and reduce administrative burden. Despite early progress, such as Food and Drug Administration approval of the first computer-aided polyp detection system in 2021, there are numerous important challenges to be faced on the path toward broader adoption of AI algorithms in clinical endoscopic practice.

Simulation-Based Learning as a Strategy to Optimizing Efficiency of Upper Endoscopy and Colonoscopy

Gastrointestinal diseases impose a significant morbidity, mortality, and health care cost burden, affecting millions annually in the United States alone. Endoscopy plays a crucial role in managing these conditions. Despite technological advancements in endoscopy, ensuring efficient, high-quality care remains challenging. A critical need to standardize high-quality endoscopy is for education reform in the training of endoscopists. Traditional apprenticeship-based training methods are dependent on the trainer as well as the patient case mix. Simulation-based mastery learning (SBML) emerges as a promising strategy to improve endoscopy training. This review discusses the current state of SBML for optimizing upper endoscopy and colonoscopy efficiency.

Colonoscopic surveillance in Lynch syndrome: guidelines in perspective

Lynch syndrome predisposes to a high risk of colorectal cancer and colonoscopy remains the primary preventive strategy. The prevention of colorectal cancer through colonoscopy relies on identifying and removing adenomas, the main precursor lesion. Nevertheless, colonoscopy is not an optimal strategy since post-colonoscopy colorectal cancer remains an important issue. In continuation of a 2021 journal review, the present article seeks to offer an updated perspective by examining relevant articles from the past 3 years. We place recent findings in the context of existing guidelines, with a specific focus on colonoscopy surveillance. Key aspects explored include colonoscopy quality standards, timing of initiation, and surveillance intervals. Our review provides a comprehensive analysis of adenoma-related insights in Lynch syndrome, delving into emerging technologies like virtual chromoendoscopy and artificial intelligence-assisted endoscopy. This review aims to contribute valuable insights into the topic of colonoscopy surveillance in Lynch syndrome.

Efficacy of colonoscopic re-examination across the entire colon: a randomized controlled trial

BACKGROUND

In standard colonoscopic examinations, some polyps may be missed during the withdrawal phase. Re-examination of the right colon can improve the adenoma detection rate (ADR). However, the effectiveness of applying this re-examination strategy to the entire colon remains unknown. We investigated whether re-examination could increase the detection rate of polyps and adenomas throughout the colon.

METHODS

A randomized, controlled, single-center trial (NCT03268200) was conducted in a university hospital. Patients aged 45-75 years were randomly assigned to either the study or control group. For patients in the control group, observation and polypectomy were performed once using the standard colonoscopy method. For patients in the study group, polypectomy was repeated twice during the withdrawal phase after the initial insertion of the colonoscope. These examinations were performed in the right transverse and left colons. The primary endpoints were the polyp detection rate (PDR) and ADR, defined as the proportion of patients with ≥ 1 polyp and ≥ 1 adenoma, respectively.

RESULTS

Overall, 406 patients were enrolled (study group, n = 210; control group, n = 196) and analyzed. Generally, PDRs and ADRs were similar between the study (withdrawal 1 + 2) and control groups (withdrawal 1), except for the right colon. However, the second withdrawal review increased number of polyps and adenomas in the overall, right, mid, and left colon, respectively.

CONCLUSION

The results of this trial indicated that re-examination of the entire colon during colonoscopy could be beneficial for detecting concealed polyps in patients at risk of interval cancer.

The Efficacy of Real-time Computer-aided Detection of Colonic Neoplasia in Community Practice: A Pragmatic Randomized Controlled Trial

BACKGROUND & AIMS

The use of computer-aided detection (CADe) has increased the adenoma detection rates (ADRs) during colorectal cancer (CRC) screening/surveillance in randomized controlled trials (RCTs) but has not shown benefit in real-world implementation studies. We performed a single-center pragmatic RCT to evaluate the impact of real-time CADe on ADRs in colonoscopy performed by community gastroenterologists.

METHODS

We enrolled 1100 patients undergoing colonoscopy for CRC screening, surveillance, positive fecal-immunohistochemical tests, and diagnostic indications at one community-based center from September 2022 to March 2023. Patients were randomly assigned (1:1) to traditional colonoscopy or real-time CADe. Blinded pathologists analyzed histopathologic findings. The primary outcome was ADR (the percentage of patients with at least 1 histologically proven adenoma or carcinoma). Secondary outcomes were adenomas detected per colonoscopy (APC), sessile-serrated lesion detection rate, and non-neoplastic resection rate.

RESULTS

The median age was 55.5 years (interquartile range, 50-62 years), 61% were female, 72.7% were of Hispanic ethnicity, and 9.1% had inadequate bowel preparation. The ADR for the CADe group was significantly higher than the traditional colonoscopy group (42.5% vs 34.4%; P = .005). The mean APC was significantly higher in the CADe group compared with the traditional colonoscopy group (0.89 ± 1.46 vs 0.60 ± 1.12; P < .001). The improvement in adenoma detection was driven by increased detection of <5 mm adenomas. CADe had a higher sessile-serrated lesion detection rate than traditional colonoscopy (4.7% vs 2.0%; P = .01). The improvement in ADR with CADe was significantly higher in the first half of the study (47.2% vs 33.7%; P = .002) compared with the second half (38.7% vs 34.9%; P = .33).

CONCLUSIONS

In a single-center pragmatic RCT, real-time CADe modestly improved ADR and APC in average-detector community endoscopists. (ClinicalTrials.gov number, NCT05963724).

Association of Endoscopist Colonoscopy Quality Measures With Follow-Up Colonoscopy Outcomes After Positive Stool Tests (Multitarget Stool DNA or Fecal Immunochemical Test): Retrospective Cross-Sectional Analysis of Data From the New Hampshire Colonoscopy Registry

INTRODUCTION

Negative colonoscopies following positive stool tests could result from stool test characteristics or from the quality of endoscopist performance. We used New Hampshire Colonoscopy Registry data to examine the association between endoscopist detection rates and polyp yield in colonoscopies performed for positive fecal immunochemical test (FIT) or multitarget stool DNA (mt-sDNA) test to evaluate the degree to which positive stool tests followed by negative colonoscopy ("false positives") vary with endoscopist quality. In addition, we investigated the frequency of significant polyps in the subgroup of highest quality colonoscopies following positive stool tests.

METHODS

We compared the frequencies of negative colonoscopies and of specific polyps following positive stool tests across quartiles of endoscopist adenoma detection rate (ADR) and clinically significant serrated polyp detection rate (CSSDR).

RESULTS

Our sample included 864 mt-sDNA+ and 497 FIT+ patients. We found a significantly lower frequency of negative colonoscopies following positive stool tests among endoscopists with higher ADR and CSSDR, particularly in the 2 highest quartiles. In addition, detection of any adenoma after a positive stool test for endoscopists in the fourth ADR quartile was 63.3% (FIT+) and 62.8% (mt-sDNA+). Among endoscopists in the fourth CSSDR quartile, sessile serrated lesions were found in 29.2% of examinations following a positive mt-sDNA and in 13.5% following FIT+ examinations.

DISCUSSION

The frequency of negative colonoscopies after positive stool tests was significantly higher in examinations performed by endoscopists with low ADR and CSSDR. Our results also suggest a benchmark target of at least 40% for ADR in patients with mt-sDNA+ or FIT+ tests and 20% for sessile serrated lesions in mt-sDNA+ patients.

A computer-aided detection system in the everyday setting of diagnostic, screening, and surveillance colonoscopy: an international, randomized trial

BACKGROUND

 Computer-aided detection (CADe) has been developed to improve detection during colonoscopy. After initial reports of high efficacy, there has been an increasing recognition of variability in the effectiveness of CADe systems. The aim of this study was to evaluate a CADe system in a varied colonoscopy population.

METHODS

 A multicenter, randomized trial was conducted at seven hospitals (both university and non-university) in Europe and Canada. Participants referred for diagnostic, non-immunochemical fecal occult blood test (iFOBT) screening, or surveillance colonoscopy were randomized (1:1) to undergo CADe-assisted or conventional colonoscopy by experienced endoscopists. Participants with insufficient bowel preparation were excluded from the analysis. The primary outcome was adenoma detection rate (ADR). Secondary outcomes included adenomas per colonoscopy (APC) and sessile serrated lesions (SSLs) per colonoscopy.

RESULTS

 581 participants were enrolled, of whom 497 were included in the final analysis: 250 in the CADe arm and 247 in the conventional colonoscopy arm. The indication was surveillance in 202/497 colonoscopies (40.6 %), diagnostic in 199/497 (40.0 %), and non-iFOBT screening in 96/497 (19.3 %). Overall, ADR (38.4 % vs. 37.7 %; P = 0.43) and APC (0.66 vs. 0.66; P = 0.97) were similar between CADe and conventional colonoscopy. SSLs per colonoscopy was increased (0.30 vs. 0.19; P = 0.049) in the CADe arm vs. the conventional colonoscopy arm.

CONCLUSIONS

 In this study conducted by experienced endoscopists, CADe did not result in a statistically significant increase in ADR. However, the ADR of our control group substantially surpassed our sample size assumptions, increasing the risk of an underpowered trial.

Improved Adenoma Detection Rate Using a Novel Colonoscopic Distal Attachment: A Multicenter Randomized Controlled Trial

INTRODUCTION

To evaluate the effect of Embrella, a novel-designed colonoscopic distal attachment, on adenoma detection rate (ADR) and adenoma per colonoscopy (APC), compared with standard colonoscopy in routine practice.

METHODS

All consecutive participants who underwent routine colonoscopic examinations at 3 endoscopy centers in China were enrolled. Participants were randomly assigned in a 1:1 ratio to the Embrella-assisted colonoscopy (EAC) or standard colonoscopy (SC) groups. ADR, APC, inspection time, pain scores, and adverse events were recorded.

RESULTS

Overall, 1,179 participants were randomized into the EAC (n = 593) and SC groups (n = 586). EAC increased the overall ADR from 24.6% to 34.2% ( P < 0.001) and improved APC from 0.44 to 0.64 ( P = 0.002). Subgroup analyses indicated that EAC significantly improved ADR for adenomas < 10 mm (13.8% vs 8.5%, P = 0.004 for 5-9 mm and 27.0% vs 17.2%, P < 0.001 for < 5 mm), nonpedunculated adenomas (26.6% vs 18.8%, P < 0.001), and adenomas in the transverse (10.8% vs 6.1%, P = 0.004) and left colon (21.6% vs 13.7%, P < 0.001). APC in the subgroup analyses was consistent with ADR. The mean inspection time was shorter with EAC (6.52 vs 6.68 minutes, P = 0.046), with no significant impact on participants' pain scores ( P = 0.377). Moreover, no EAC-related adverse events occurred.

DISCUSSION

EAC significantly increased ADR and APC compared with SC, particularly for adenomas <10 mm, nonpedunculated adenomas, and adenomas in the transverse and left colon.

Precision therapy for cancer prevention by targeting carcinogenesis

Cancer represents a major global public health burden, with new cases estimated to increase from 14 million in 2012 to 24 million by 2035. Primary prevention is an effective strategy to reduce the costs associated with cancer burden. For example, measures to ban tobacco consumption have dramatically decreased lung cancer incidence and vaccination against human papillomavirus can prevent cervical cancer development. Unfortunately, the etiological factors of many cancer types are not completely clear or are difficult to actively control; therefore, the primary prevention of such cancers is not practical. In this review, we update the progress on precision therapy by targeting the whole carcinogenesis process, especially for three high-risk groups: (1) those with chronic inflammation, (2) those with inherited germline mutations, and (3) those with precancerous lesions like polyps, gastritis, actinic keratosis or dysplasia. We believe that attenuating chronic inflammation, treating precancerous lesions, and removing high-risk tissues harboring germline mutations are precision methods for cancer prevention.

Specialty-Based Ambulatory Quality Improvement Program: A Specialty-Specific Ambulatory Metric Project

BACKGROUND AND OBJECTIVES

Healthcare is increasingly being delivered in the outpatient setting, but robust quality improvement programs and performance metrics are lacking in ambulatory care, particularly specialty-based ambulatory care.

METHODS

To promote quality improvement in ambulatory care, we developed an infrastructure to create specialty-specific quality measures and dashboards that could be used to display providers' performance across relevant measures to individual providers and institutional leaders.

RESULTS

The products of this program include a governance and infrastructure for specialty-specific ambulatory quality metrics as well as two distinct dashboards for data display. One dashboard is provider-facing, displaying provider's performance on specialty-specific measures as compared to institutional standards. The second dashboard is a leadership dashboard that provides overall and provider-level information on performance across measures.

CONCLUSIONS

The Specialty-based Ambulatory Quality program reflects a systematic, institutionally-supported quality improvement framework that can be applied across diverse ambulatory specialties. As next steps, we plan to evaluate the program's impact on provider performance across measures and expand this program to other specialties practicing in the outpatient setting.

[Colon polyp detection based on multi-scale and multi-level feature fusion and lightweight convolutional neural network]

Early diagnosis and treatment of colorectal polyps are crucial for preventing colorectal cancer. This paper proposes a lightweight convolutional neural network for the automatic detection and auxiliary diagnosis of colorectal polyps. Initially, a 53-layer convolutional backbone network is used, incorporating a spatial pyramid pooling module to achieve feature extraction with different receptive field sizes. Subsequently, a feature pyramid network is employed to perform cross-scale fusion of feature maps from the backbone network. A spatial attention module is utilized to enhance the perception of polyp image boundaries and details. Further, a positional pattern attention module is used to automatically mine and integrate key features across different levels of feature maps, achieving rapid, efficient, and accurate automatic detection of colorectal polyps. The proposed model is evaluated on a clinical dataset, achieving an accuracy of 0.9982, recall of 0.9988, F1 score of 0.9984, and mean average precision (mAP) of 0.9953 at an intersection over union (IOU) threshold of 0.5, with a frame rate of 74 frames per second and a parameter count of 9.08 M. Compared to existing mainstream methods, the proposed method is lightweight, has low operating configuration requirements, high detection speed, and high accuracy, making it a feasible technical method and important tool for the early detection and diagnosis of colorectal cancer.

Patient Perceptions on the Follow-Up of Abnormal Cancer Screening Test Results

BACKGROUND

Timely follow-up after an abnormal cancer screening test result is needed to maximize the benefits of screening, but is frequently not achieved. Little is known about patient experiences with the process of following up abnormal screening results.

OBJECTIVE

Assess patient experiences and perceptions regarding the process of a diagnostic workup following abnormal breast, cervical, or colorectal cancer screening results.

DESIGN

Survey of participating patients between April 2021 and June 2022 after reaching the primary outcome time point in a randomized controlled trial to improve follow-up of overdue abnormal screening results.

PARTICIPANTS

Patients from 44 participating practices in three primary care practice networks.

MAIN MEASURES

Self-reported ease of scheduling follow-up, perceived barriers or concerns, provider trust, and satisfaction with communication and care received for the follow-up of abnormal screening results.

RESULTS

Overall, 241 (25.0%) patients completed the survey including 66 (32.8%) with breast, 79 (25.3%) with cervical, and 96 (21.3%) with colorectal screening test; median age 55 years, 79.7% women, 80.5% non-Hispanic white, and 51.0% did not complete recommended follow-up. Most patients were worried that the test would find cancer (63.1%), but fewer worried about discomfort or side effects (34.4%), and neither were associated with completing follow-up. However, 17% of patients did not think they needed follow-up tests or appointments and were less likely to complete follow-up (10.5% vs. 24.0%, respectively, p-value 0.009). Most patients were very satisfied with their overall care (71.0%), but only 50.2% strongly agreed that they trusted their provider to put their medical needs above all else when making recommendations.

CONCLUSIONS

Patients with overdue abnormal breast, cervical, and colorectal cancer screening test results reported important deficiencies in the management of recommended follow-up. Addressing patient concerns about fear of cancer and effectively communicating the need for follow-up procedures may improve timely follow-up after an abnormal cancer screening result.

TRIAL REGISTRATION

ClinicalTrials.gov NCT03979495.

Association of Antibody Responses to Helicobacter pylori Proteins with Colorectal Adenoma and Colorectal Cancer

Helicobacter pylori (H. pylori) has been implicated in colorectal carcinogenesis. Here, the association of immune responses to bacterial exposure with advancing stages of colorectal neoplasia was assessed by multiplex serology. Immunoglobulin (Ig) A and G antibody responses to thirteen proteins of H. pylori were measured by a Luminex-based multiplex assay in plasma from patients with colorectal cancer (CRC, n = 25), advanced adenoma (n = 82), or small polyps (n = 85) and controls (n = 100). Multivariable logistic regression was used to assess the association of bacterial seropositivity with colorectal neoplasia. The threshold for overall seropositivity required subjects to be positive for at least 4 out of the 13 tested antigens. In a cohort subset with matched data (n = 34), H. pylori seropositivity was correlated with bacterial abundance in both neoplastic and matched normal tissue. While no association was found between H. pylori seropositivity and the presence of CRC, IgA seropositivity to CagA was associated with a decreased risk of advanced adenoma (odds ratio, OR = 0.48, 95% confidence intervals, CIs: 0.24-0.96). Regarding IgG, higher antibody responses to HpaA was associated with advanced adenoma occurrence (OR = 2.46, 95% CI: 1.00-6.01), while responses to HP0395, CagA and Catalase were associated with polyp development (OR = 2.65, 95%, CI: 1.31-5.36, OR = 1.83, 95% CI: 1.01-3.32, and OR = 2.16, CI: 1.09-4.29, respectively). Positive correlations were found between H. pylori abundance in the normal mucosa and levels of both the IgA and IgG antibody response to Catalase and VacA antigens (r = 0.48, p < 0.01; r = 0.37, p = 0.04; r = 0.51, p < 0.01; and r = 0.71, p = 0.04, respectively). Conversely, H. pylori abundance was negatively correlated with levels of IgA antibody response to HpaA and with IgG antibody response to HP0231 in the diseased tissue (r = -0.34, p = 0.04 and r = -0.41, p = 0.01, respectively). The association between levels of H. pylori antigens and colorectal neoplasia risk gradually decreased with the adenoma progression, implicating the early activation of the immune response at the polyp stage. Thus, the evaluation of antibody response to certain bacterial antigens may indicate the presence of early-stage colorectal neoplasia. Further studies are needed to clarify the role H. pylori or the immune response to its antigens may have in colorectal carcinogenesis stages.

Application of Artificial Intelligence in the diagnosis and treatment of colorectal cancer: a bibliometric analysis, 2004-2023

Background

An increasing number of studies have turned their lens to the application of Artificial Intelligence (AI) in the diagnosis and treatment of colorectal cancer (CRC).

Objective

To clarify and visualize the basic situation, research hotspots, and development trends of AI in the diagnosis and treatment of CRC, and provide clues for research in the future.

Methods

On January 31, 2024, the Web of Science Core Collection (WoSCC) database was searched to screen and export the relevant research published during 2004-2023, and Cite Space, VoSviewer, Bibliometrix were used to visualize the number of publications, countries (regions), institutions, journals, authors, citations, keywords, etc.

Results

A total of 2715 pieces of literature were included. The number of publications grew slowly until the end of 2016, but rapidly after 2017, till to the peak of 798 in 2023. A total of 92 countries, 3997 organizations, and 15,667 authors were involved in this research. Chinese scholars released the highest number of publications, and the U.S. contributed the highest number of total citations. As to authors, MORI, YUICHI had the highest number of publications, and WANG, PU had the highest number of total citations. According to the analysis of citations and keywords, the current research hotspots are mainly related to "Colonoscopy", "Polyp Segmentation", "Digital Pathology", "Radiomics", "prognosis".

Conclusion

Research on the application of AI in the diagnosis and treatment of CRC has made significant progress and is flourishing across the world. Current research hotspots include AI-assisted early screening and diagnosis, pathology, and staging, and prognosis assessment, and future research is predicted to put weight on multimodal data fusion, personalized treatment, and drug development.

A lighter hybrid feature fusion framework for polyp segmentation

Colonoscopy is widely recognized as the most effective method for the detection of colon polyps, which is crucial for early screening of colorectal cancer. Polyp identification and segmentation in colonoscopy images require specialized medical knowledge and are often labor-intensive and expensive. Deep learning provides an intelligent and efficient approach for polyp segmentation. However, the variability in polyp size and the heterogeneity of polyp boundaries and interiors pose challenges for accurate segmentation. Currently, Transformer-based methods have become a mainstream trend for polyp segmentation. However, these methods tend to overlook local details due to the inherent characteristics of Transformer, leading to inferior results. Moreover, the computational burden brought by self-attention mechanisms hinders the practical application of these models. To address these issues, we propose a novel CNN-Transformer hybrid model for polyp segmentation (CTHP). CTHP combines the strengths of CNN, which excels at modeling local information, and Transformer, which excels at modeling global semantics, to enhance segmentation accuracy. We transform the self-attention computation over the entire feature map into the width and height directions, significantly improving computational efficiency. Additionally, we design a new information propagation module and introduce additional positional bias coefficients during the attention computation process, which reduces the dispersal of information introduced by deep and mixed feature fusion in the Transformer. Extensive experimental results demonstrate that our proposed model achieves state-of-the-art performance on multiple benchmark datasets for polyp segmentation. Furthermore, cross-domain generalization experiments show that our model exhibits excellent generalization performance.

Transmesenteric internal hernia: an unexpected adverse event induced by colonoscopy

Transmesenteric internal hernia is an uncommon cause of small bowel obstruction that occurs when small bowel loops protrude through a mesenteric defect into the abdominal cavity. Herein, we present an unexpected case of colonoscopy-induced transmesenteric internal hernia. An 81-year-old male patient presenting with intermittent hematochezia and constipation had undergone a laparoscopic left nephrectomy for ureteral cancer. A colonoscopy was performed to identify the etiology of his symptoms. He complained of severe abdominal pain 2 h after the examination despite uneventful endoscopic procedures, including cold snare polypectomy. Contrast-enhanced computed tomography revealed a strangulated small bowel obstruction with a closed-loop formation outside the descending colon. The small bowel loop was incarcerated into the left retroperitoneal space. Emergency laparotomy detected small bowel loops that prolapsed into the nephrectomy pedicle via a descending mesenteric defect, developed during the laparoscopic left nephrectomy. The incarcerated small bowel was detached from the hernia and returned to its normal position, and the mesenteric defect was closed. He demonstrated an uneventful postoperative course, with no internal hernia recurrence after discharge. This case indicates the risk of transmesenteric internal hernia through inadvertently created mesenteric defects should be borne in mind, especially when performing colonoscopies in patients who underwent laparoscopic nephrectomies.

Computer-aided diagnosis system for optical diagnosis of colorectal polyps under white light imaging

OBJECTIVES

This study presents a novel computer-aided diagnosis (CADx) designed for optically diagnosing colorectal polyps using white light imaging (WLI).We aimed to evaluate the effectiveness of the CADx and its auxiliary role among endoscopists with different levels of expertise.

METHODS

We collected 2,324 neoplastic and 3,735 nonneoplastic polyp WLI images for model training, and 838 colorectal polyp images from 740 patients for model validation. We compared the diagnostic accuracy of the CADx with that of 15 endoscopists under WLI and narrow band imaging (NBI). The auxiliary benefits of CADx for endoscopists of different experience levels and for identifying different types of colorectal polyps was also evaluated.

RESULTS

The CADx demonstrated an optical diagnostic accuracy of 84.49%, showing considerable superiority over all endoscopists, irrespective of whether WLI or NBI was used (P < 0.001). Assistance from the CADx significantly improved the diagnostic accuracy of the endoscopists from 68.84% to 77.49% (P = 0.001), with the most significant impact observed among novice endoscopists. Notably, novices using CADx-assisted WLI outperform junior and expert endoscopists without such assistance.

CONCLUSIONS

The CADx demonstrated a crucial role in substantially enhancing the precision of optical diagnosis for colorectal polyps under WLI and showed the greatest auxiliary benefits for novice endoscopists.

Colorectal adenoma detection rate using texture and color enhancement imaging versus white light imaging with chromoendoscopy: a propensity score matching study

BACKGROUND AND AIM

Few studies have evaluated the adenoma detection rate (ADR) of colonoscopy with texture and color enhancement imaging (TXI), a novel image-enhancing technology. This study compares the detection of colorectal polyps using TXI to that using white light imaging (WLI).

METHODS

This single-center retrospective study used propensity-matched scoring based on the patients' baseline characteristics (age, sex, indication, bowel preparation, endoscopist, colonoscope type, and withdrawal time) to compare the results of patients who underwent chromoendoscopy using WLI or TXI at the Toyoshima Endoscopy Clinic. The differences in polyp detection rates and the mean number of detected polyps per colonoscopy were determined between the TXI and WLI groups.

RESULTS

After propensity score matching, 1970 patients were enrolled into each imaging modality group. The mean patient age was 57.2 ± 12.5 years, and 44.5% of the cohort were men. The ADR was higher in the TXI group than in the WLI group (55.0% vs 49.4%, odds ratio: 1.25). High-risk ADR were more common in the TXI group than in the WLI group (17.6% vs 12.8%; OR: 1.45). The mean number of adenomas per colonoscopy (APC) was higher in the TXI group than in the WLI group (1.187 vs 0.943, OR: 1.12). APC with a flat morphology (1.093 vs 0.848, OR: 1.14) and APC of <6 mm (0.992 vs 0.757, OR: 1.16) were higher in the TXI group than in the WLI group.

CONCLUSION

Compared to WLI, TXI improved the ADR in patients who underwent chromoendoscopy based on actual clinical data.

Polyp detection with colonoscopy assisted by the GI Genius artificial intelligence endoscopy module compared with standard colonoscopy in routine colonoscopy practice (COLO-DETECT): a multicentre, open-label, parallel-arm, pragmatic randomised controlled trial

BACKGROUND

Increased polyp detection during colonoscopy is associated with decreased post-colonoscopy colorectal cancer incidence and mortality. The COLO-DETECT trial aimed to assess the clinical effectiveness of the GI Genius intelligent endoscopy module for polyp detection, comparing colonoscopy assisted by GI Genius (computer-aided detection [CADe]-assisted colonoscopy) with standard colonoscopy in routine practice.

METHODS

We did a multicentre, open-label, parallel-arm, pragmatic randomised controlled trial in 12 National Health Service (NHS) hospitals (ten NHS Trusts) in England, among adults (aged ≥18 years) undergoing planned colonoscopy for gastrointestinal symptoms or for surveillance due to personal or family history (ie, symptomatic indications), or colorectal cancer screening. Randomisation (1:1) to CADe-assisted colonoscopy or standard colonoscopy was done with a web-based dynamic adaptive algorithm, immediately before colonoscopy, with stratification by age group, sex, colonoscopy indication (screening or symptomatic), and NHS Trust. Recruiting staff, participants, and colonoscopists were unmasked to trial allocation; histopathologists, co-chief investigators, and trial statisticians were masked. CADe-assisted colonoscopy consisted of standard colonoscopy plus the GI Genius module active for at least the entire inspection phase of colonoscope withdrawal. The primary outcome was mean adenomas per procedure (total number of adenomas detected divided by total number of procedures); the key secondary outcome was adenoma detection rate (proportion of colonoscopies with at least one adenoma). Analysis was by intention to treat (ITT), with outcomes compared between groups by mixed-effects regression modelling, in which effect estimates were adjusted for randomisation stratification variables. Data were imputed for outcome measures with more than 5% missing values. All participants who underwent colonoscopy were assessed for safety. The trial is registered on ISRCTN (ISRCTN10451355) and ClinicalTrials.gov (NCT04723758), and is complete.

FINDINGS

Between March 29, 2021, and April 6, 2023, 2032 participants (1132 [55·7%] male, 900 [44·3%] female; mean age 62·4 years [SD 10·8]) were recruited and randomly assigned: 1015 to CADe-assisted colonoscopy and 1017 to standard colonoscopy. 1231 (60·6%) participants were undergoing screening and 801 (39·4%) had symptomatic indications. Mean adenomas per procedure was 1·56 (SD 2·82; n=1001 participants with available data) in the CADe-assisted colonoscopy group versus 1·21 (1·91; n=1009) in the standard colonoscopy group, representing an adjusted mean difference of 0·36 (95% CI 0·14-0·57; adjusted incidence rate ratio 1·30 [95% CI 1·15-1·47], p<0·0001). Adenomas were detected in 555 (56·6%) of 980 participants in the CADe-assisted colonoscopy group versus 477 (48·4%) of 986 in the standard colonoscopy group, representing a proportion difference of 8·3% (95% CI 3·9-12·7; adjusted odds ratio 1·47 [95% CI 1·21-1·78], p<0·0001). Numbers of adverse events were similar between the CADe-assisted colonoscopy and standard colonoscopy groups (adverse events: 25 vs 19; serious adverse events: four vs six), and no adverse events in the CADe-assisted colonoscopy group were deemed to be related to GI Genius use on independent review.

INTERPRETATION

Results of the COLO-DETECT trial support the use of GI Genius to increase detection of premalignant colorectal polyps in routine colonoscopy practice.

FUNDING

Medtronic.

Impact of Bowel Preparation Quality on Colonoscopy Findings and Colorectal Cancer Deaths in a Nation-Wide Colorectal Cancer Screening Program

INTRODUCTION

Adequate bowel preparation is paramount for a high-quality screening colonoscopy. Despite the importance of adequate bowel preparation, there is a lack of large studies that associated the degree of bowel preparation with long-term colorectal cancer outcomes in screening patients.

METHODS

In a large population-based screening program database in Austria, quality of bowel preparation was estimated according to the Aronchick Scale by the endoscopist (excellent, good, fair, poor, and inadequate bowel preparation). We used logistic regression to assess the influence of bowel preparation on the detection of different polyp types and the interphysician variation in bowel preparation scoring. Time-to-event analyses were performed to investigate the association of bowel preparation with postcolonoscopy colorectal cancer (PCCRC) death.

RESULTS

A total of 335,466 colonoscopies between January 2012 and follow-up until December 2022 were eligible for the analyses. As compared with excellent bowel preparation, adenoma detection was not significantly lower for good bowel preparation (odds ratio 1.01, 95% confidence interval [CI] 0.9971-1.0329, P = 0.1023); however, adenoma detection was significantly lower in fair bowel preparation (odds ratio 0.97, 95% CI 0.9408-0.9939, P = 0.0166). Individuals who had fair or lower bowel preparation at screening colonoscopy had significantly higher hazards for PCCRC death (hazard ratio for fair bowel preparation 2.56, 95% CI 1.67-3.94, P < 0.001).

DISCUSSION

Fair bowel preparation on the Aronchick Scale was not only associated with a lower adenoma detection probability but also with increased risk of PCCRC death. Efforts should be made to increase bowel cleansing above fair scores.

Impact of linked color imaging on the proximal adenoma miss rate: a multicenter tandem randomized controlled trial (the COCORICO trial)

BACKGROUND

Missed lesions are common during standard colonoscopy and are correlated with post-colonoscopy colorectal cancer. Contrast-enhanced technologies have recently been developed to improve polyp detection. We aimed to evaluate the impact of linked color imaging (LCI) on the proximal adenoma miss rate in routine colonoscopy.

METHODS

This national, multicenter, tandem, randomized trial compared the outcomes of colonoscopy with white-light imaging (WLI) versus LCI for polyp detection in the right colon. Two consecutive examinations of the right colon (upstream of the hepatic flexure) were made with WLI and LCI by the same operator. First-pass examination by WLI or LCI was randomized 1:1 after cecal intubation. According to statistical calculations, 10 endoscopy units had to include approximately 700 patients. The primary outcome was proximal adenoma miss rate. Secondary outcomes were the proximal miss rates for sessile serrated lesions (SSL), advanced adenomas, and polyps.

RESULTS

764 patients were included from 1 January 2020 to 22 December 2022, and 686 patients were randomized (345 WLI first vs. 341 LCI first). Both groups were comparable in terms of demographics and indications. The proximal adenoma miss rate was not significantly higher in the WLI-first group (36.7%) vs. the LCI-first group (31.8%) (estimated mean absolute difference: 4.9% [95%CI -5.2% to 15.0%], P = 0.34). There was also no significant difference in miss rates for SSLs, advanced adenomas, and polyps in the proximal colon.

CONCLUSIONS

In contrast to previous data, this study does not support the benefit of LCI to the proximal adenoma miss rate in routine colonoscopy.

Artificial Intelligence in Coloproctology: A Review of Emerging Technologies and Clinical Applications

Artificial intelligence (AI) has emerged as a transformative tool across several specialties, namely gastroenterology, where it has the potential to optimize both diagnosis and treatment as well as enhance patient care. Coloproctology, due to its highly prevalent pathologies and tremendous potential to cause significant mortality and morbidity, has drawn a lot of attention regarding AI applications. In fact, its application has yielded impressive outcomes in various domains, colonoscopy being one prominent example, where it aids in the detection of polyps and early signs of colorectal cancer with high accuracy and efficiency. With a less explored path but equivalent promise, AI-powered capsule endoscopy ensures accurate and time-efficient video readings, already detecting a wide spectrum of anomalies. High-resolution anoscopy is an area that has been growing in interest in recent years, with efforts being made to integrate AI. There are other areas, such as functional studies, that are currently in the early stages, but evidence is expected to emerge soon. According to the current state of research, AI is anticipated to empower gastroenterologists in the decision-making process, paving the way for a more precise approach to diagnosing and treating patients. This review aims to provide the state-of-the-art use of AI in coloproctology while also reflecting on future directions and perspectives.

Effect of a novel artificial intelligence-based cecum recognition system on adenoma detection metrics in a screening colonoscopy setting

BACKGROUND AND AIMS

Cecal intubation in colonoscopy relies on self-reporting. We developed an artificial intelligence-based cecum recognition system (AI-CRS) for post-hoc verification of cecal intubation and explored its impact on adenoma metrics.

METHODS

Quality metrics, including cecal intubation rate (CIR), adenoma detection rate (ADR), and other ADR-related metrics, were compared both before (2015-2018) and after (2019-2022) the implementation of the AI-CRS.

RESULTS

Although the CIR did not change significantly after the implementation of the AI-CRS, the ADR and advanced ADR significantly increased. Although the ADR significantly increased in all segments, the most significant increase in advanced ADR was observed in the proximal colon. Implementation of the AI-CRS was associated with a higher likelihood of detecting adenoma (adjusted odds ratio, 1.35; 95% confidence interval, 1.26-1.45) and advanced adenoma (adjusted odds ratio, 1.23; 95% confidence interval, 1.07-1.41), respectively.

CONCLUSIONS

Implementation of a post-hoc verification of cecal intubation using an AI-CRS significantly improved various adenoma metrics in screening colonoscopy.

Evaluation of the efficacy of polyethylene glycol in combination with different doses of linaclotide in a fractionated bowel preparation for colonoscopy: a prospective randomized controlled study

BACKGROUND AND AIM

The ideal bowel cleansing program still needs to be explored. The aim was to compare the bowel cleansing effect and patient tolerance of low-dose polyethylene glycol (PEG) combined with different doses of linaclotide in fractionated bowel preparation.

METHODS

The subjects were randomly assigned to the 3LPEG group, 2LPEG + 2L group, or 2LPEG + L group. The primary outcome was to use the Ottawa Bowel Preparation Scale (OBPS) to evaluate the efficacy of bowel cleansing, and the secondary outcomes were the detection rate of adenomas and polyps, adverse reactions, tolerance, and defecation dynamics; subsets of patients with chronic constipation and irritable bowel syndrome were also analyzed.

RESULTS

A total of 753 patients were randomly assigned. In ITT analysis, the success of preparation of the 2LPEG + 2L group was better than that of the 2LPEG + L group or the 3LPEG group (92.0% vs. 82.3% vs. 82.1%; P = 0.002). Compared with the 3LPEG group, the 2LPEG + L group showed similar but non-inferior results (82.3% vs. 82.1%, P > 0.05). The 2LPEG + 2L group was similar to the 2LPEG + L group in terms of adverse reaction, tolerance, willingness to reuse, and sleep quality, but both were superior to the 3LPEG group. In a subgroup analysis of chronic constipation, the 2LPEG + 2L group had the best cleansing effect on the right colon and mid colon, while in the subgroup analysis of irritable bowel syndrome, the tolerance was better in the 2LPEG + 2L group and the 2LPEG + L group than the 3LPEG group.

CONCLUSIONS

2LPEG + 2L is a feasible bowel preparation regimen.

Usefulness and safety of new ultrasmall-diameter colonoscope for cases with difficult insertion: a retrospective study

Colonoscopies are widely available, but there are cases where insertion can be difficult, even for experienced endoscopists. EC-760XP/L, a new ultrasmall-diameter long scope, may be useful in such cases. This single-center retrospective study included 39 cases where colonoscope insertion was difficult even when previously conducted by an experienced endoscopist. The primary outcome was the cecal intubation time using EC-760XP/L compared to the time used in a previous examination with a standard scope. The secondary outcomes were the cecum intubation rate, intestinal cleanliness level, adenoma detection rate, polyp detection rate, sedative use rate, occurrence of adverse events, and pain experience. A comparison of cecal intubation times between EC-760XP/L and the standard scope showed that insertion times were significantly lower with EC-760XP/L (9.5 min) compared to the standard scope (19 min) (p < 0.01). The standard scope achieved cecal intubation in 30 cases (76.9%), whereas EC-760XP/L reached the cecum in all cases (p < 0.01). Pain was observed in 3 cases (8.3%) with the EC-760XP/L, which was significantly lower than the 22 cases (56.4%) with the standard scope (p < 0.01). In conclusion, EC-760XP/L proved to be useful in cases where colonoscope insertion was difficult.

Adenoma Detection Rate and Polyp Detection Rate among Gastroenterology Fellows and Consultants in a Tertiary Hospital in the Philippines: A Cross-sectional Study

Background and Objective

Colorectal cancer (CRC) is the third most commonly diagnosed cancer and the fourth leading cause of cancer mortality worldwide. Likewise in the Philippines, the prevalence of CRC has shown to be increasing. Colonoscopy, a screening procedure for CRC, has parameters to gauge quality of detection. One of which is the Adenoma Detection Rate (ADR). Higher ADR has been linked to improved cancer detection. This study aimed to determine the ADR and Polyp Detection Rate (PDR) among Gastroenterology practitioners in a tertiary government university hospital in the Philippines, estimate ADR from PDR, and identify factors associated with ADR.

Methods

An analytical, cross-sectional study among patients who underwent colonoscopy for the years 2021 and the first half of 2022 at the Central Endoscopy Unit (CENDU) of the Philippine General Hospital. Demographic data of fellows and consultants were collected through an online form, while those from patients were obtained from electronic records. Colonoscopy details and histopathology results were accessed through the hospital's Open Medical Record System (MRS). ADR, PDR, and estimated ADR were computed using established formulas. To evaluate the strength of the relationship between the estimated and actual ADR, Pearson's correlation coefficient was used. Chi-square analysis, Mann-Whitney U test, and Kruskal-Wallis H test were performed to identify the factors that might influence the ADR. A cut-off of p <0.05 was considered statistically significant.

Results

The total computed ADR of consultants and fellows combined is 22%. The difference between the ADRs of Gastroenterology consultants and Fellows-in-Training is statistically significant at 31.6% and 18.7%, respectively (p= 0.017). The total Polyp Detection Rate is 57.6% while the weighted group average Adenoma to Polyp Detection Rate Quotient (APDRQ) is 0.4085 or 40.85%. The estimated ADR has a moderate degree of correlation with the actual ADR when an outlier was excluded (r=0.521 (95% CI, 0.072-0.795, p=0.0266). Significant factors related to ADR include endoscopists' years of practice (p=0.020), number of colonoscopies done (p=0.031), and patient tobacco use (p=0.014).

Conclusion

The overall ADR among consultants and fellows is at par with the standard guidelines. A moderate degree of correlation exists between actual and estimated ADR when an outlier is excluded; however, more studies are needed to determine the APDRQ in the wider local setting. Longer years in practice, total number of colonoscopies performed, and patient tobacco use are associated with increased ADR.

Adenoma detection rate by colonoscopy in real-world population-based studies: a systematic review and meta-analysis

BACKGROUND

Adenoma detection rate (ADR) is a quality indicator set at a minimum of 25% in unselected populations by the European Society of Gastrointestinal Endoscopy (ESGE). Nevertheless, a lack of pooled observational data resembling real-world practice limits support for this threshold. We aimed to perform a systematic review with meta-analysis to evaluate the pooled rates for conventional adenoma detection, polyp detection (PDR), cecal intubation, bowel preparation, and complications in population-based studies.

METHODS

The PubMed, Scopus, and Web of Science databases were searched until May 2023 for populational-based studies reporting overall ADR in unselected individuals. A random-effects model was used for meta-analysis.

RESULTS

31 studies were included, comprising 3 644 561 subjects. A high quality of procedures was noticeable, with a high cecal intubation rate and low complication rate. The overall pooled ADR, PDR, and rate of cancer detection were 26.5% (95%CI 23.3% to 29.7%), 38.3% (95%CI 32.5% to 44.1%), and 2.7% (95%CI 1.5% to 3.9%), respectively. ADR varied according to indication: screening 33.3% (95%CI 24.5% to 42.2%), surveillance 42.9% (95%CI 36.9% to 49.0%), and diagnostic 24.7% (95%CI 19.5% to 29.9%), with subgroup analysis revealing rates of 34.4% (95%CI 22.0% to 40.5%) for post-fecal occult blood test and 26.6% (95%CI 22.6% to 30.5%) for primary colonoscopy screening. Diminutive conventional adenomas yielded a pooled rate of 59.9% (95%CI 43.4% to 76.3%). The pooled rate for overall serrated lesion detection was 12.4% (95%CI 8.8% to 16.0%). Male sex and higher age were significantly associated with an ADR above the benchmark.

CONCLUSION

This first meta-analysis relying on real-world observational studies supports the ESGE benchmark for ADR, while suggesting that different benchmarks might be used according to indication, sex, and age.

Automatic assessment of bowel preparation by an artificial intelligence model and its clinical applicability

BACKGROUND AND AIM

Reliable bowel preparation assessment is important in colonoscopy. However, current scoring systems are limited by laborious and time-consuming tasks and interobserver variability. We aimed to develop an artificial intelligence (AI) model to assess bowel cleanliness and evaluate its clinical applicability.

METHODS

A still image-driven AI model to assess the Boston Bowel Preparation Scale (BBPS) was developed and validated using 2361 colonoscopy images. For evaluating real-world applicability, the model was validated using 113 10-s colonoscopy video clips and 30 full colonoscopy videos to identify "adequate (BBPS 2-3)" or "inadequate (BBPS 0-1)" preparation. The model was tested with an external dataset of 29 colonoscopy videos. The clinical applicability of the model was evaluated using 225 consecutive colonoscopies. Inter-rater variability was analyzed between the AI model and endoscopists.

RESULTS

The AI model achieved an accuracy of 94.0% and an area under the receiver operating characteristic curve of 0.939 with the still images. Model testing with an external dataset showed an accuracy of 95.3%, an area under the receiver operating characteristic curve of 0.976, and a sensitivity of 100% for the detection of inadequate preparations. The clinical applicability study showed an overall agreement rate of 85.3% between endoscopists and the AI model, with Fleiss' kappa of 0.686. The agreement rate was lower for the right colon compared with the transverse and left colon, with Fleiss' kappa of 0.563, 0.575, and 0.789, respectively.

CONCLUSIONS

The AI model demonstrated accurate bowel preparation assessment and substantial agreement with endoscopists. Further refinement of the AI model is warranted for effective monitoring of qualified colonoscopy in large-scale screening programs.

Effect of computer aided detection device on the adenoma detection rate and serrated detection rate among trainee fellows

Background and Aims

The utilization of artificial intelligence (AI) with computer-aided detection (CADe) has the potential to increase the adenoma detection rate (ADR) by up to 30% in expert settings and specialized centers. The impact of CADe on serrated polyp detection rates (SDR) and academic trainees ADR & SDR remains underexplored. We aim to investigate the effect of CADe on ADR and SDR at an academic center with various levels of providers' experience.

Methods

A single-center retrospective analysis was conducted on asymptomatic patients between the ages of 45 and 75 who underwent screening colonoscopy. Colonoscopy reports were reviewed for 3 months prior to the introduction of GI Genius™ (Medtronic, USA) and 3 months after its implementation. The primary outcome was ADR and SDR with and without CADe.

Results

Totally 658 colonoscopies were eligible for analysis. CADe resulted in statistically significant improvement in SDR from 8.92% to 14.1% (P = 0.037). The (ADR + SDR) with CADe and without CADe was 58% and 55.1%, respectively (P = 0.46). Average colonoscopy (CSC) withdrawal time was 17.33 min (SD 10) with the device compared with 17.35 min (SD 9) without the device (P = 0.98).

Conclusion

In this study, GI Genius™ was associated with a statistically significant increase in SDR alone, but not in ADR or (ADR + SDR), likely secondary to the more elusive nature of serrated polyps compared to adenomatous polyps. The use of CADe did not affect withdrawal time.

Nationally Automated Colonoscopy Performance Feedback Increases Polyp Detection: The NED APRIQOT Randomized Controlled Trial

BACKGROUND & AIMS

Postcolonoscopy colorectal cancer incidence and mortality rates are higher for endoscopists with low polyp detection rates. Using the UK's National Endoscopy Database (NED), which automatically captures real-time data, we assessed if providing feedback of case-mix-adjusted mean number of polyps (aMNP), as a key performance indicator, improved endoscopists' performance. Feedback was delivered via a theory-informed, evidence-based audit and feedback intervention.

METHODS

This multicenter, prospective, NED Automated Performance Reports to Improve Quality Outcomes Trial randomized National Health Service endoscopy centers to intervention or control. Intervention-arm endoscopists were e-mailed tailored monthly reports automatically generated within NED, informed by qualitative interviews and behavior change theory. The primary outcome was endoscopists' aMNP during the 9-month intervention.

RESULTS

From November 2020 to July 2021, 541 endoscopists across 36 centers (19 intervention; 17 control) performed 54,770 procedures during the intervention, and 15,960 procedures during the 3-month postintervention period. Comparing the intervention arm with the control arm, endoscopists during the intervention period: aMNP was nonsignificantly higher (7%; 95% CI, -1% to 14%; P = .08). The unadjusted MNP (10%; 95% CI, 1%-20%) and polyp detection rate (10%; 95% CI, 4%-16%) were significantly higher. Differences were not maintained in the postintervention period. In the intervention arm, endoscopists accessing NED Automated Performance Reports to Improve Quality Outcomes Trial webpages had a higher aMNP than those who did not (aMNP, 118 vs 102; P = .03).

CONCLUSIONS

Although our automated feedback intervention did not increase aMNP significantly in the intervention period, MNP and polyp detection rate did improve significantly. Engaged endoscopists benefited most and improvements were not maintained postintervention; future work should address engagement in feedback and consider the effectiveness of continuous feedback.

CLINICAL TRIALS REGISTRY

 www.isrctn.org ISRCTN11126923 .

White spots around colorectal tumors are cancer-related findings and may aid endoscopic diagnosis: a prospective study in Japan

BACKGROUND/AIMS

During endoscopy, white spots (WS) are sometimes observed around benign or malignant colorectal tumors; however, few reports have investigated WS, and their significance remains unknown. Therefore, we investigated the significance of WS from clinical and pathological viewpoints and evaluated its usefulness in endoscopic diagnosis.

METHODS

Clinical data of patients with lesions diagnosed as epithelial tumors from January 1, 2019, to December 31, 2020, were analyzed (n=3,869). We also performed a clinicopathological analysis of adenomas or carcinomas treated with endoscopic resection (n=759). Subsequently, detailed pathological observations of the WS were performed.

RESULTS

The positivity rates for WS were 9.3% (3,869 lesions including advanced cancer and non-adenoma/carcinoma) and 25% (759 lesions limited to adenoma and early carcinoma). Analysis of 759 lesions showed that the WS-positive lesion group had a higher proportion of cancer cases and larger tumor diameters than the WS-negative group. Multiple logistic analysis revealed the following three statistically significant risk factors for carcinogenesis: positive WS, flat lesions, and tumor diameter ≥5 mm. Pathological analysis revealed that WS were macrophages that phagocytosed fat and mucus and were white primarily because of fat.

CONCLUSIONS

WS are cancer-related findings and can become a new criterion for endoscopic resection in the future.

Effect of different working periods on missed diagnosis of colorectal polyps in colonoscopy

BACKGROUND

To investigate the effect of different working periods on missed diagnoses in patients with colorectal polyps in colonoscopy.

METHODS

We conducted a retrospective analysis of patients who were diagnosed with colorectal polyps during colonoscopy in an outpatient department between July and December 2022. These patients were subsequently hospitalized for resection during this period. Patients with missed diagnoses were those who had newly discovered polyps in a second colonoscopy. The working periods were categorized as work, near the end of work, and delayed work, respectively, in the morning and afternoon.

RESULTS

A total of 482 patients were included, and the miss rate of diagnosis was 48.1% (232/482), mainly in the transverse colon (25%), and the ascending colon (23%). Patient age was a risk factor for the miss rate of diagnosis (OR = 1.025, 95%CI: 1.009-1.042, P = 0.003) and was also associated with the number of polyps detected for the first colonoscopy (χ2 = 18.196, P = 0.001). The different working periods had no statistical effect on the missed rate of diagnosis (χ2 = 1.998, P = 0.849). However, there was an increasing trend in miss rates towards the end of work and delayed work periods, both in the morning and afternoon. The highest miss rate (60.0%) was observed during delayed work in the afternoon. Additionally, poor bowel preparation was significantly more common during delayed work in the afternoon.

CONCLUSIONS

The increasing trend in miss rates towards the end of work and delayed work periods deserves clinical attention. Endoscopists cannot always stay in good condition under heavy workloads.

Will artificial intelligence reach any limit in gastroenterology?

Endoscopy is the cornerstone in the management of digestive diseases. Over the last few decades, technology has played an important role in the development of this field, helping endoscopists in better detecting and characterizing luminal lesions. However, despite ongoing advancements in endoscopic technology, the incidence of missed pre-neoplastic and neoplastic lesions remains high due to the operator-dependent nature of endoscopy and the challenging learning curve associated with new technologies. Artificial intelligence (AI), an operator-independent field, could be an invaluable solution. AI can serve as a “second observer”, enhancing the performance of endoscopists in detecting and characterizing luminal lesions. By utilizing deep learning (DL), an innovation within machine learning, AI automatically extracts input features from targeted endoscopic images. DL encompasses both computer-aided detection and computer-aided diagnosis, assisting endoscopists in reducing missed detection rates and predicting the histology of luminal digestive lesions. AI applications in clinical gastrointestinal diseases are continuously expanding and evolving the entire digestive tract. In all published studies, real-time AI assists endoscopists in improving the performance of non-expert gastroenterologists, bringing it to a level comparable to that of experts. The development of DL may be affected by selection biases. Studies have utilized different AI-assisted models, which are heterogeneous. In the future, algorithms need validation through large, randomized trials. Theoretically, AI has no limit to assist endoscopists in increasing the accuracy and the quality of endoscopic exams. However, practically, we still have a long way to go before standardizing our AI models to be accepted and applied by all gastroenterologists.

Effect of artificial intelligence implementation to the latest generation 4K colonoscopy

<b>Indroduction:</b> Colonoscopy is an acclaimed screening test to detect colorectal cancer (CRC). The most important quality indicators for colonoscopy are adenoma detection rate (ADR), cecal intubation rate (CIR), withdrawal time (WT), and bowel preparation (Boston Bowel Preparation Scale; BBPS). In modern endoscopy practice, the human eye is enhanced by highdefinition white-light visualization and advanced imaging technology. The main limitation of this procedure is the detection rate of suspicious lesions. The next generation of endoscopes with 4K resolution and computer-aided detection (CADe) based on artificial intelligence (AI) may be the next step to improve the quality of tests performed.<b>Aim:</b> The aim was to assess the effect of CADe implementation in the environment of the latest generation of endoscopes and 4K visualization in retrospective analysis.<b>Methods:</b> The study included 2,000 patients over 18 years old who underwent colonoscopy for various indications. Olympus Endo-Aid CADe AI system was used, together with the latest X1 series endoscope set using LED lighting and 4K ultra high-resolution technology. Group I consisted of 1,000 consecutive tests performed using Endo-Aid CADe, and group II the first 1,000 consecutive tests without the CADe system. ADR, Advanced adenoma detection rate (AADR), polyp detection rate (PDR), and mean polyp per patient score (MPP) were assessed in each group<b>Results:</b> A total of 2,000 participants were included in the analysis, divided into two groups regarding CADe implementation. The overall PDR was similar in the analyzed groups (AI: 46.7% <i>vs.</i> non-AI: 44.9%, P = 0.419). Both ADR (29.7 <i>vs.</i> 28.9%, P = 0.694) and AADR (6.9 <i>vs.</i> 7.1%, P = 0.861) changed unremarkably. However, a significant elevation in MPP was noted. The MPP rose from 0.85 in the non-AI group to 1.26 in the AI group (P<0.001). The comparative analysis conducted separately for each segment of the bowel revealed that PDR remarkably increased in the left colon (29.3 <i>vs.</i> 18.0%, P<0.001), with no difference for other segments and other parameters. Investigating the MPP separately in each segment showed a significant difference for the right colon (0.33 <i>vs.</i> 0.23, P = 0.032) and the left colon (0.47 <i>vs.</i> 0.28, P<0.001). When adjusted to bowel preparation the PDR and MPP were constantly higher in the AI group (29.3 <i>vs.</i> 19.0%, P<0.001, and 0.48 <i>vs.</i> 0.30, P<0.001, respectively). In addition, the significant impact of AI implementation on MPP faded in the right colon (0.33 <i>vs.</i> 0.24, P = 0.051) when compared with the overall analysis.<b>Conclusions:</b> Although recently published evidence is optimistic regarding AI efficiency in improving the quality of colonoscopy, the provided results widen the overall perspective. Prospective randomized controlled trials (RCTs) including procedures performed with newest generation scopes should elucidate the role of AI in high-resolution colonoscopy.

Computer-aided quality assessment of endoscopist competence during colonoscopy: a systematic review

BACKGROUND AND AIMS

Endoscopists' competence can vary widely, as shown in the variation in the adenoma detection rate (ADR). Computer-aided quality assessment (CAQ) can automatically assess performance during individual procedures. In this review we identified and described different CAQ systems for colonoscopy.

METHODS

A systematic review of the literature was done using MEDLINE, EMBASE, and Scopus based on 3 blocks of terms according to the inclusion criteria: colonoscopy, competence assessment, and automatic evaluation. Articles were systematically reviewed by 2 reviewers, first by abstract and then in full text. The methodological quality was assessed using the Medical Education Research Study Quality Instrument (MERSQI).

RESULTS

Of 12,575 identified studies, 6831 remained after removal of duplicates and 6806 did not pass the eligibility criteria and were excluded, leaving 25 studies, of which 13 studies were included in the final analysis. Five categories of CAQ systems were identified: withdrawal speedometer (7 studies), endoscope movement analysis (3 studies), effective withdrawal time (1 study), fold examination quality (1 study), and visual gaze pattern (1 study). The withdrawal speedometer was the only CAQ system that tested its feedback by examining changes in ADR. Three studies observed an improvement in ADR, and 2 studies did not. The methodological quality of the studies was high (mean MERSQI, 15.2 points; maximum, 18 points).

CONCLUSIONS

Thirteen studies developed or tested CAQ systems, most frequently by correlating it to the ADR. Only 5 studies tested feedback by implementing the CAQ system. A meta-analysis was impossible because of the heterogeneous study designs, and more studies are warranted.

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

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

An Accurate and Automated Method for Adenoma Detection Rate and Report Card Generation Utilizing Common Electronic Health Records

GOALS

To develop an automated method for Adenoma Detection Rate (ADR) calculation and report card generation using common electronic health records (EHRs).

BACKGROUND

ADR is the most widely accepted colonoscopy quality indicator and is inversely associated with interval colorectal cancer incidence and mortality. However, ADR is difficult to efficiently measure and disseminate, due to need for data integration from distinct electronic databases.

METHODS

We migrated data from an endoscopy reporting software (Endosoft) to Epic Reporting Servers where it was combined with anatomic pathology data (Beaker Lab Information System, EPIC Systems). A natural language processing expression was developed to search Beaker pathology reports for accurate identification of adenomatous polyps. A blinded physician manually validated a final cohort of 200 random procedures. ADR report cards were automatically generated utilizing the Crystal Reports feature within EPIC.

RESULTS

Validation of the natural language processing algorithm for ADR showed a sensitivity, specificity, and accuracy of 100%. ADR was automatically calculated for 12 endoscopists over a calendar year. Two thousand two hundred seventy-six screening colonoscopies were performed with 775 procedures having a least one adenoma detected, for a total ADR of 34%. Report cards were successfully generated within the EPIC EHR and distributed to endoscopists by secure e-mail.

CONCLUSION

We describe an accurate, automated and scalable process for ADR calculation and reporting utilizing commonly adopted EHRs and data integration methods. By integrating the process of ADR collection and streamlining dissemination of reports, this methodology is poised to enhance colonoscopy quality care across health care networks that use it.

G-EYE Improves Polyp, Adenoma, and Serrated Polyp Detection Rates in Colonoscopy: A Systematic Review and Meta-analysis

BACKGROUND

Colonoscopy is the gold-standard test to decrease mortality from colorectal cancer (CRC). G-EYE is an inflated balloon on the bending section of the scope with the ability to flatten the folds to improve the adenoma detection rate (ADR). We performed this meta-analysis to evaluate the efficacy of G-EYE in improving ADR and other quality indicators of colonoscopy.

METHODS

A literature search was performed through March 21, 2023, on databases including Embase, Medline, Cochrane Central Register of Controlled Trials, Web of Science Core Collection, KCI-Korean Journal Index, and Global Index Medicus. Core concepts of G-EYE, colonoscopy, ADR, polyp detection rate (PDR), serrated polyp detection rate (SPDR), and withdrawal time were searched. Statistical analysis was performed with OpenMeta[Analyst]. The odds ratio (OR) for the proportional variable and mean difference for the continuous variable along with 95% CI was used with a P-value <0.05 considered statistically significant. We used the DerSimonian-Laird method and random effects model for pooling data.

RESULTS

The search strategy yielded a total of 143 articles. Three studies with 3868 total colonoscopies were finalized. The pooled ADR, PDR, and SPDR showed statistical improvement with G-EYE (OR: 1.744, 95% CI: 1.534-1.984, P<0.001; OR: 1.766, 95% CI: 1.547-2.015, P<0.001; and OR: 1.603, 95% CI: 1.176-2.185, P=0.003). The withdrawal time was also noted to be higher in the G-EYE group (mean difference: 0.114, CI: 0.041-0.186, P=0.002).

CONCLUSIONS

This meta-analysis suggests that G-EYE can improve ADR, PDR, and SPDR. Further studies are needed to evaluate the effect of G-EYE on interval CRC and mortality rate.

SimCol3D - 3D reconstruction during colonoscopy challenge

Colorectal cancer is one of the most common cancers in the world. While colonoscopy is an effective screening technique, navigating an endoscope through the colon to detect polyps is challenging. A 3D map of the observed surfaces could enhance the identification of unscreened colon tissue and serve as a training platform. However, reconstructing the colon from video footage remains difficult. Learning-based approaches hold promise as robust alternatives, but necessitate extensive datasets. Establishing a benchmark dataset, the 2022 EndoVis sub-challenge SimCol3D aimed to facilitate data-driven depth and pose prediction during colonoscopy. The challenge was hosted as part of MICCAI 2022 in Singapore. Six teams from around the world and representatives from academia and industry participated in the three sub-challenges: synthetic depth prediction, synthetic pose prediction, and real pose prediction. This paper describes the challenge, the submitted methods, and their results. We show that depth prediction from synthetic colonoscopy images is robustly solvable, while pose estimation remains an open research question.

Choosing Your Endoscopist: A Retrospective Single-Centre Cohort Study

Background Colorectal cancer is one of the most common internal malignancies affecting Australians, and colonoscopy is widely accepted as a part of comprehensive large bowel assessment. Different specialties perform colonoscopies, most commonly general surgeons and gastroenterologists. Analysing performance outcomes against benchmarks allows insight into inter-specialty differences and enables the improvement of overall service provision and quality. Methods We performed a retrospective single-centre cohort study on 2086 patients undergoing colonoscopies by seven surgeons (S) and nine gastroenterologists (G) between July 2021 and June 2023. Primary outcomes were comparative caecal intubation rates (CIR), photo documentation rates (PDR), documented withdrawal rates (DWR), withdrawal times (WT), and adenoma detection rates (ADR). Secondary outcomes characterised adenoma frequency, optimal WT, and indications for colonoscopies. Results We found significant differences in CIR (S: 94.9%, 990/1043; G: 99%, 1033/1043, P<0.01), PDR (S: 95.9%, 949/990; G: 99.1%, 1024/1033, P<0.01), DWR (S: 17.4%, 181/1043; G: 87.3%, 911/1043, P<0.01), WT >6 minutes (S: 82.3%, 149/181; G: 97.8%, 891/911, P<0.01), and ADR (S: 37.9%, 193/509; G: 59.7%, 421/705, P<0.01). Subgroup analysis revealed adenoma frequency peaked at 50-70 years old and optimal WT was ≥9 minutes. We demonstrated surgeons mainly perform colonoscopies for diverticulitis surveillance, abnormal imaging, post-cancer resections, and rectal bleeding, but gastroenterologists predominantly investigate bowel symptoms, polyp surveillance, positive faecal occult blood test, and anaemia. Conclusion Despite both specialties surpassing national standards in CIR and ADR, there were significant differences in performance indicators. We believe ADR differences could be explained by different indications specialties perform colonoscopies for. Increasing WT ≥9 minutes could improve ADR, and education on the usage of withdrawal timer on endoscopes will improve DWR.

Adenomas and Sessile Serrated Lesions in 45- to 49-Year-Old Individuals Undergoing Colonoscopy: A Systematic Review and Meta-Analysis

INTRODUCTION

Colorectal cancer (CRC) screening is now recommended at the age of 45 years in the United States. However, information regarding the adenomas detection rate (ADR) and sessile serrated lesions (SSLs) in 45- to 49-year-old individuals is limited. In addition, the impact of lowering the screening age to 45 years on the ADR and the detection rate of SSLs is not well elucidated. This systematic review and meta-analysis aims to report the overall ADR and SSL detection rate in 45- to 49-year-old individuals undergoing colonoscopy.

METHODS

We searched MEDLINE, EMBASE, SCOPUS, Web of Science, ClinicalTrials.gov , and the Cochrane database from inception through October 2022 to identify studies reporting on ADR and SSL detection rates in 45- to 49-year-old individuals undergoing colonoscopies for all indications. This approach acknowledges the possibility of including individuals undergoing diagnostic colonoscopies or those with increased risk factors for CRC. We also conducted a separate analysis examining ADR in average-risk individuals undergoing screening colonoscopy. The pooled rates with their corresponding 95% confidence intervals (CIs) were generated using the fixed-effects model. I2 was used to adjudicate heterogeneity.

RESULTS

Sixteen studies met the inclusion criteria. All studies were retrospective except one; 3 had data from national/local registries. There were 41,709 adenomas detected across 150,436 colonoscopies. The pooled overall ADR was 23.1% (95% CI 19.7%-27.0%, I2 = 98.6%). The pooled ADR in individuals with average risk of CRC from 7 studies was 28.2% (95% CI 24.6%-32.0%, I2 = 96.5%). The pooled overall SSL detection rate from 6 studies was 6.3% (95% CI 3.8%-10.5%, I2 = 97%). The included studies were heterogeneous because of differences in the inclusion and exclusion criteria and patient population.

DISCUSSION

In 45- to 49-year-old individuals undergoing a colonoscopy for any indication, the ADR and SSL detection rates were 23.1% and 6.3%, respectively. We conclude that these outcomes in 45- to 49-year-olds are comparable with individuals aged 50-54 years.

Predicting Risk of Colorectal Cancer After Adenoma Removal in a Large Community-Based Setting

INTRODUCTION

Colonoscopy surveillance guidelines categorize individuals as high or low risk for future colorectal cancer (CRC) based primarily on their prior polyp characteristics, but this approach is imprecise, and consideration of other risk factors may improve postpolypectomy risk stratification.

METHODS

Among patients who underwent a baseline colonoscopy with removal of a conventional adenoma in 2004-2016, we compared the performance for postpolypectomy CRC risk prediction (through 2020) of a comprehensive model featuring patient age, diabetes diagnosis, and baseline colonoscopy indication and prior polyp findings (i.e., adenoma with advanced histology, polyp size ≥10 mm, and sessile serrated adenoma or traditional serrated adenoma) with a polyp model featuring only polyp findings. Models were developed using Cox regression. Performance was assessed using area under the receiver operating characteristic curve (AUC) and calibration by the Hosmer-Lemeshow goodness-of-fit test.

RESULTS

Among 95,001 patients randomly divided 70:30 into model development (n = 66,500) and internal validation cohorts (n = 28,501), 495 CRC were subsequently diagnosed; 354 in the development cohort and 141 in the validation cohort. Models demonstrated adequate calibration, and the comprehensive model demonstrated superior predictive performance to the polyp model in the development cohort (AUC 0.71, 95% confidence interval [CI] 0.68-0.74 vs AUC 0.61, 95% CI 0.58-0.64, respectively) and validation cohort (AUC 0.70, 95% CI 0.65-0.75 vs AUC 0.62, 95% CI 0.57-0.67, respectively).

DISCUSSION

A comprehensive CRC risk prediction model featuring patient age, diabetes diagnosis, and baseline colonoscopy indication and polyp findings was more accurate at predicting postpolypectomy CRC diagnosis than a model based on polyp findings alone.