Polyp Detection Rate Research Articles

Real-world effectiveness and safety of 1L polyethylene glycol and ascorbic acid for bowel preparation in patients aged 80 years or over

Background and study aim: Clinical trials and real-world studies show a 1L polyethene glycol and ascorbic acid solution (1L PEG-ASC) to be an effective and safe bowel preparation for colonoscopy in the general population. Here, the effectiveness and safety of 1L PEG-ASC were evaluated in patients aged 80 years or over in a real-world setting. Patients and methods: A post-hoc analysis of an observational, multicentre, retrospective study assessed the effectiveness and safety of 1L PEG-ASC on out-patients aged ≥80 years old undergoing a colonoscopy at 8 centres in Spain and Portugal. Cleansing quality was assessed using the Boston Bowel Preparation Scale, with overall scores ≥6 and all segmental scores ≥2 considered adequate colon cleansing, and overall scores ≥8 or 3 in the right colon considered high-quality cleansing. The caecal intubation rate, withdrawal time, polyp and adenoma detection rates, and adverse events (AEs) were also monitored. Results: Data were analysed from 423 patients aged ≥80 years; mean age 83.5 (±3.2) years and 49.2% males. The adequate colon cleansing success rate was 88.9%, with high-quality cleansing of the overall and right colon achieved in 54.1% and 46.1% of the patients, respectively. Colonoscopy was complete in 94.1% of cases, and the adenoma detection rate was 51.3%. At least one AE was experienced by 4.5% of participants, the most frequent being mild dehydration (2.8%) and nausea (1.2%). Conclusions: This post-hoc analysis confirms 1L PEG-ASC to be an effective and safe bowel cleansing preparation for patients aged 80 years or over in a real-world setting.

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.

British Society of Gastroenterology National Evaluation of Colonoscopy Quality: Findings from the National Endoscopy Database.

Analysis of national colonoscopy quality using automatically uploaded data from a national database, including exploring performance variation. Data on all colonoscopies performed in the UK 01/03/2019-29/02/2020 and recorded in the National Endoscopy Database were analysed. Unadjusted key performance indicators were calculated and proportions of endoscopists achieving national standards were determined. Regression models tested associations between case-mix (patient age, sex, indication) and colonoscopy quality. Endoscopist factors (specialty, annual procedure numbers, withdrawal times) were added to case-mix adjusted models, with results presented as adjusted odds ratios (aOR) with 95% confidence intervals. 592,764 colonoscopies were analysed. Rates of caecal intubation (93.5%, 95% CI 93.4-93.6), polyp detection (37.3%, 95% CI 37.2-37.4), and moderate/severe patient discomfort (4.8%, 95% CI 4.7-4.8) had all improved since the 2011 national audit (p<0.01 for all). 63.9% of endoscopists met all minimum standards for caecal intubation, polyp detection, and discomfort, but only 46.4% did so among those performing fewer than 100 colonoscopies annually. Overall, surgeons recorded lower caecal intubation and polyp detection rates than gastroenterologists (p<0.01); however, those performing over 100 annual colonoscopies achieved KPIs similar to gastroenterologists. Endoscopists with longer withdrawal times were almost twice as likely to identify polyps (aOR 1.9, 95% CI 1.7-2.2) and detected more large polyps (aOR 1.6, 95% CI 1.3-2.0). UK colonoscopy quality has improved, yet almost 40% of endoscopists still fell short of minimum standards. Variation in quality was strongly associated with endoscopist procedure volumes; mandating minimum annual procedures and emphasising longer withdrawal times could improve overall quality.

Efficacy of Second Forward-View Colonoscopy to Improve Adenoma Detection of Right-Side Colon: Systematic Review and Meta-Analysis

The second forward view (SFV) has been considered an effective method to improve the adenoma detection rate (ADR) in the right-side colon. On the other hand, there is insufficient evidence on how much the ADR is improved compared to standard one forward view (OFV) colonoscopy. A systematic review and meta-analysis were performed to determine the efficacy of improvement in the ADR by SFV colonoscopy. This study conducted a systematic literature search in Medline, Embase, and Cochrane Library until Sep 2024. Two independent investigators (HJK, JWL) conducted a database search, and studies regarding the SFV or retroflexion were selected. The primary outcomes were the ADR of the right-side colon, polyp detection rate, and withdrawal time. Statistical analyses were performed using STATA 18.0 Special edition. Ten studies with 5,886 patients were included in this review. The pooled ADR of SFV colonoscopy for the right colon was significantly higher than that of the OFV, with a risk ratio (RR) of 1.25 (95% CI, 1.13-1.38 I2=0.0%). This result was statistically significant in three non-randomized trials (RR 1.19, 95% CI 1.06-1.34, I2=0.0%) with low heterogeneity. The right-sided polyp detection rate (RR 1.19, 95% CI 1.06-1.34, I2=61.6%) and the ADR of the whole colon (RR 1.10, 95% CI 1.01-1.20, I2=0.0%) were also significantly higher than those of OFV colonoscopy. SFV colonoscopy is an effective method to improve the ADR of the right colon.

A clinical pilot trial of an artificial intelligence-driven smart phone application of bowel preparation for colonoscopy: a randomized clinical trial

Background High-quality bowel preparation is paramount for a successful colonoscopy. This study aimed to explore the effect of artificial intelligence-driven smartphone software on the quality of bowel preparation. Methods Firstly, we utilized 3305 valid liquid dung images collected via mobile phones as training data. the most effective model was employed on mobile phones to evaluate the quality of bowel preparation. Secondly, From May 2023 to September 2023, colonoscopy patients were randomly assigned to two groups – the AI group (n = 116) and the control group (n = 116) – using a randomized, controlled, endoscopist-blinded method. We compared the two groups in terms of Boston Bowel Preparation Scale (BBPS) scores, polyp detection rate, adverse reaction rate, and factors related to bowel preparation quality. The primary endpoint was the percentage of patients who achieved a BBPS ≥6 among those who effectively utilized the smartphone software. Results EfficientNetV2 exhibited the highest performance, with an accuracy of 87%, a sensitivity of 83%, and an AUC of 0.86. In the patient validation experiment, the AI group had higher BBPS scores than the control group (6.78 ± 1.41 vs. 5.35 ± 2.01, p = 0.001) and showed an improvement in the detection rate (71.55% vs. 56.90%, p = 0.020) for polyps. Multifactor logistic analysis indicated that compliance with enema solution usage rules (OR: 5.850, 95% confidence interval: 2.022–16.923), total water intake (OR: 1.001, 95% confidence interval: 1.001–1.002), and AI software reminders (OR: 2.316, 95% confidence interval: 1.096–4.893) were independently associated with BBPS scores ≥6. Conclusion Compared with traditional methods, the use of artificial intelligence combined with software to send reminders can lead to more accurate assessments of bowel preparation quality and an improved detection rate for polyps, thus demonstrating promising clinical value.

Optimized computer-assisted technique for increasing adenoma detection during colonoscopy: a randomized controlled trial.

Efforts to improve colonoscopy have recently focused on improving adenoma detection through individual interventions. We evaluated an optimized computer-assisted technique (CADopt) versus standard colonoscopy. A prospective randomized controlled trial was conducted enrolling adults (45-80 years) undergoing elective colonoscopy. Participants were randomized (1:1) to the intervention group (CADopt), and control group. In the CADopt group, endoscopists used a computer-aided polyp detection combined with linked color imaging, water exchange colonoscopy, and cecal retroflexion. In the control group, standard colonoscopy was performed. Primary outcome was Adenoma Detection Rate (ADR) in the intervention and control groups. Secondary outcomes included polyp detection rate (PDR), advanced ADR (AADR), sessile-serrated lesion detection rates (SDR), and Adenoma per colonoscopy (APC). A total of 467 patients were recruited and randomized (CADopt group 229 patients, 50.2% female vs 238 patients, 48.3% female in the control group). ADR was 49.3% (95% CI 42.7-56.0) for the CADopt group vs 38.2% (95% CI 32.0-44.7) for the control group (p = 0.016). PDR, AADR, SDR, and APC were 78.2% (95% CI 72.2-83.3), 13.1% (95% CI 9.0-18.2), 6.6% (95% CI 3.7-10.6), and 0.86 (95% CI 0.70-1.02) for the CADopt group versus 59.2% (95% CI 52.7-65.5), 8.0% (95% CI 4.9-12.2), 7.1% (95% CI 4.2-11.1), and 0.75 (95% CI 0.58-0.92) for the control group, respectively. Using an optimized computer-assisted technique led to significant improvements in ADR, PDR, and a trend towards AADR improvements.

Colon capsule endoscopy polyp detection rate vs colonoscopy polyp detection rate: Systematic review and meta-analysis

BACKGROUND Colon capsule endoscopy (CCE) is a modern, non-invasive method for large bowel visualization, offering a less invasive alternative to traditional colonoscopy (TC). While TC remains the gold standard for comprehensive large bowel assessment, including the detection and treatment of various conditions, the effectiveness of CCE in detecting polyps is less established. AIM To systematically review and compare the polyp detection rates (PDR) of CCE and TC. METHODS A systematic literature search was conducted using four scientific databases: CINAHL, MEDLINE via EBSCO, Cochrane Library, and MEDLINE/PubMed. A standardized search command was utilized to ensure consistency. Full papers were retrieved if they compared PDR between CCE and TC and involved patients over 18 years old. A meta-analysis was then conducted using the meta package in R software. RESULTS Initially, 339 articles were identified, with 128 duplicates and 15 non-English articles excluded, leaving 196 for screening. After further exclusions, 9 articles were included in the review. The meta-analysis revealed minimal differences in PDR between CCE and TC. The pooled PDR for TC was 0.61 (95%CI: 0.48–0.72), and for CCE, it was 0.61 (95%CI: 0.48–0.73). The overall comparison of the pooled PDR of both methods was 0.96 (95%CI: 0.90–1.02), indicating that CCE is non-inferior to TC. CONCLUSION CCE has emerged as a modern and safe diagnostic alternative to TC for polyp detection, demonstrating non-inferiority when compared to the conventional method.

The Effect of the Second Forward View on the Detection Rate of Sessile Serrated Lesions in the Proximal Colon: A Single-Center Prospective Randomized Controlled Study.

The detection rate of proximal sessile serrated lesion (PSSLDR) is linked to the incidence and mortality of colorectal cancer. However, research on second forward view (SFV) examinations for PSSLDR remains limited. This first randomized controlled trial assessed the impact of the proximal SFV on the PSSLDR. Patients were randomized into two groups during proximal colonoscopy: standard colonoscopy (SC) and SFV. The SC group underwent a standard examination, whereas the SFV group underwent a second examination of the proximal colon (cecum to splenic flexure). The primary outcome was PSSLDR, with secondary outcomes, including the proximal polyp detection rate (PPDR), proximal adenoma detection rate (PADR), and lesion miss rate, compared between the two groups. Among 246 patients (SC=124; SFV=122), SFV significantly improved the PSSLDR by 7.4% compared to SC (9.8% vs. 2.4%, P=0.017). SFV increased the PPDR by 20.2% (55.7% vs. 35.5%, P=0.002) and PADR by 12.7% (37.7% vs. 25%, P=0.039). Multivariate analysis revealed that sessile serrated lesions (SSLs) (OR=7.70, 95% CI [1.58, 37.59]), inflammatory polyps (OR=4.24, 95% CI [1.73, 10.39]), and lesion size (OR=0.76, 95% CI [0.60, 0.96]) were associated with proximal missed lesions. The overall polyp miss rate was 52.9%, with miss rates of 61.0% for polyps <5 mm, 80% for SSLs, and 42.2% for adenomas. Furthermore, 12.3% of patients experienced changes in surveillance intervals from SFV examination. SFV examination of the proximal colon significantly improved the PSSLDR by 7.4%, PPDR by 20.2%, PADR by 12.7%, while shortening the detection interval by 12.3%, making it a valuable and cost-effective addition to routine colonoscopy.

One-day low-residue diet is equally effective as the multiple-day low-residue diet in achieving adequate bowel cleansing: a meta-analysis of randomized controlled trials.

Colonoscopy is widely used as a diagnostic and preventive procedure for colorectal diseases. The most recent guidelines advocate the use of a low-residue diet (LRD) for bowel preparation before colonoscopy. LRD duration varies considerably, with recommended 1-day and multiple-day regimens in clinical practice. We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. We searched multiple databases for randomized controlled trials (RCTs) and analyzed the outcomes using a fixed-effects model. Six RCTs with 2,469 subjects were included in this study. The rates of adequate bowel preparation for 1-day and >1-day were 87.2% and 87.1%, respectively. No statistically significant differences were observed between the 1-day and >1-day LRD in adequate bowel preparation (odds ratio [OR], 1.03; 95% confidence interval [CI], 0.76-1.41; p=0.84; I2=0%), polyp detection rate (OR, 0.91; 95% CI, 0.76-1.09; p=0.29; I2=16%), adenoma detection rate (OR, 0.87; 95% CI, 0.71-1.08; p=0.21; I2=0%), and withdrawal time (mean difference, -0.01; 95% CI, -0.25 to 0.24; p=0.97; I2=63%). The efficacy of 1-day and multiple-day LRD is comparable in achieving satisfactory bowel preparation, highlighting their similar impact on the detection of polyps and adenomas during colonoscopy.

The Relationship Between Dietary and Supplemental omega-3 Highly Unsaturated Fatty Acid Intake, Blood and Tissue omega-3 Highly Unsaturated Fatty Acid Concentrations, and Colorectal Polyp Recurrence: A Secondary Analysis of the seAFOod Polyp Prevention Trial.

The seAFOod randomized controlled trial tested colorectal polyp prevention by the omega-3 (ω-3) highly unsaturated fatty acid (HUFA) eicosapentaenoic acid (EPA) and aspirin. Variable dietary intake of omega-3 HUFAs (also including docosahexaenoic acid [DHA]) and differential EPA capsule compliance could confound analysis of trial outcomes. The objective of this study was to investigate the relationship between total (diet and capsule) daily omega-3 HUFA intake, red blood cell (RBC), and rectal mucosa omega-3 HUFA concentrations, and colorectal polyp outcomes in a secondary analysis of the seAFOod trial. Individual-participant dietary omega-3 HUFA intake (mg/d) was derived from food frequency questionnaires using the European Prospective Investigation into Cancer and Nutrition-Norfolk fatty acid nutrient database. Capsule EPA intake (mg/d) was adjusted for compliance (capsule counting). Fatty acids were analyzed by liquid chromatography-tandem mass spectrometry (as % of total fatty acids). HUFA oxidation was measured using the HUFA/saturated fatty acid (SAT) ratio. The colorectal polyp detection rate (PDR; % with ≥1 polyps) and polyp number per participant were analyzed according to the change in RBC EPA concentrations during the trial (ΔEPA), irrespective of treatment allocation. There was a small degree of HUFA degradation over time in RBC samples stored at > -80oC at research sites (r = -0.36, P<0.001 for HUFA/SAT ratio over time), which did not affect analysis of omega-3 HUFA concentrations. Low baseline EPA concentration, as well as allocation to EPA and % compliance, were associated with a high ΔEPA. Individuals with a ΔEPA value >+0.5% points (ΔEPAhigh), irrespective of allocation to EPA or placebo, had a lower PDR than ΔEPAlow individuals (odds ratio: 0.63; 95% confidence interval [CI]: 0.40, 1.01) and reduced colorectal polyp number (incidence rate ratio: 0.74; 95% CI: 0.54, 1.02). Analysis of the seAFOod trial according to the change in EPA concentration, instead of treatment allocation, revealed a protective effect of EPA treatment on colorectal polyp recurrence (ISRCTN05926847).

Novel regimen for colonoscopy bowel preparation with oral lactulose: a prospective comparative study.

Polyethylene glycol (PEG) is considered the gold standard regimen for bowel preparation; however, due to the necessity of a large volume, patient tolerance is impaired. Therefore, lactulose is a novel alternative for colonoscopy preparation. This study aimed to investigate the efficacy and safety of lactulose-based bowel preparations in comparison with PEG for colonoscopy. This is a prospective, non-blinded, comparative study. Outpatients were randomly divided into two groups: group 1 (111 patients), PEG; and group 2 (111 patients), lactulose. The following clinical outcomes were assessed in each group: degree of bowel clearance using the Boston bowel preparation score, colorectal polyp detection rate, adenoma detection rate, tolerability, and side effects. The rate of inadequate bowel preparation was 8.1% and 1.8% for the PEG and lactulose groups, respectively (p=0.030). The Boston bowel preparation score for the entire colon was 7.34±1.17 and 8.36±1.09 for the PEG and lactulose groups, respectively (p<0.001). The satisfactory overall experience rates were 27.9% and 62.2% for the PEG and lactulose groups, respectively (p<0.001). The novel bowel preparation with oral lactulose was superior to that with PEG in terms of colon cleansing, adenoma detection rate, tolerance, and patient experience.

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

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

TSdetector: Temporal–Spatial self-correction collaborative learning for colonoscopy video detection

CNN-based object detection models that strike a balance between performance and speed have been gradually used in polyp detection tasks. Nevertheless, accurately locating polyps within complex colonoscopy video scenes remains challenging since existing methods ignore two key issues: intra-sequence distribution heterogeneity and precision-confidence discrepancy. To address these challenges, we propose a novel Temporal–Spatial self-correction detector (TSdetector), which first integrates temporal-level consistency learning and spatial-level reliability learning to detect objects continuously. Technically, we first propose a global temporal-aware convolution, assembling the preceding information to dynamically guide the current convolution kernel to focus on global features between sequences. In addition, we designed a hierarchical queue integration mechanism to combine multi-temporal features through a progressive accumulation manner, fully leveraging contextual consistency information together with retaining long-sequence-dependency features. Meanwhile, at the spatial level, we advance a position-aware clustering to explore the spatial relationships among candidate boxes for recalibrating prediction confidence adaptively, thus eliminating redundant bounding boxes efficiently. The experimental results on three publicly available polyp video dataset show that TSdetector achieves the highest polyp detection rate and outperforms other state-of-the-art methods. The code can be available at https://github.com/soleilssss/TSdetector.

Plain Computed Tomography for Differentiating Neoplastic and Non-neoplastic Pedunculated Gallbladder Polyps.

Objective Surgery is recommended for large pedunculated gallbladder polyps (PGPs), which measure 10 mm or more in size, because they tend to be neoplastic polyps (NPs), such as adenomas and adenocarcinomas. However, after resection, they are often found to be non-neoplastic polyps (non-NPs). This study aimed to evaluate the usefulness of plain computed tomography (CT) in distinguishing NPs from non-NPs. Methods Of the 80 patients who underwent cholecystectomy for PGPs ≥10 mm between January 2008 and February 2021, 46 who underwent plain and contrast-enhanced CT (CE-CT) before resection were included in this study. We retrospectively assessed the polyp detection rate (PDR) using CT and calculated the difference in the CT values between PGPs and the surrounding bile. Results Twenty-one patients had NPs (12 adenomas, 5 carcinomas in adenoma, and 4 adenocarcinomas). The others were non-NPs (24 cholesterol polyps and one hyperplastic polyp). The PDR using plain CT was significantly higher in the NP group than in the non-NP group (38% (8/21) vs. 0% (0/25), p <0.01). The sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy of NPs were 38%, 100%, 100%, 66%, and 72%, respectively. The difference in the CT values between PGPs and the surrounding bile was significantly larger in the NP group than in the non-NP group (14.12 ± 11.38 HU, 5.04 ± 6.15 HU, p <0.01). Conclusions PGPs detected using plain CT had a high probability of being NPs. Plain CT is therefore considered to be useful for differentiating NPs from non-NPs.

Clinical consequences of computer-aided colorectal polyp detection

Background and aimRandomised trials show improved polyp detection with computer-aided detection (CADe), mostly of small lesions. However, operator and selection bias may affect CADe’s true benefit. Clinical outcomes of increased...

Overview of a national endoscopy database: The Trans.IT database and its impact on data registration quality.

The Trans.IT database is a national gastrointestinal (GI) endoscopy database developed in 2012. It automatically collects anonymous data from GI endoscopy procedures in a centralized database. All endoscopists use a structured reporting tool for uniform data collection. In this study, we aim to provide an overview of the database and to evaluate its impact on data registration quality. We used all ERCPs, colonoscopies and colorectal cancer (CRC)-screening colonoscopies performed between 2016 and 2020. We excluded centers joining after 2016 and patients below age 18. Data registration quality for ERCPs included completeness of data for: intention of ERCP, Schutz score, ASA classification, papillary status (virgin or previous sphincterotomy), cannulation (success or failure to cannulate the desired duct) and procedural success. For colonoscopies: indication, ASA-classification, Boston Bowel Preparation Score (BBPS), cecal intubation, polyp detection rate (PDR). For CRC-screening colonoscopies, ASA-classification, BBPS, cecal intubation, PDR and adenoma detection rate (ADR). A total of 14,156 ERCPs, 150,962 colonoscopies and 37,199 colorectal cancer screening colonoscopies were included in our analysis. For ERCPs, registration of procedural intention, Schutz score, ASA classification, papillary status, cannulation and procedural success improved from 34.9%, 32.7%, 72.6%, 36.5%, 34.6%, 27.2% in 2016, to 86.4%, 84.6%, 97.4%, 86.4%, 82.1%, 84.0%, respectively, in 2020. For non-screening colonoscopies, registration of indication, ASA classification, BBPS, cecal intubation and PDR improved from 40.4%, 60.5%, 47.6%, 69.8% and 32.3% in 2016 to 90.3%, 88.9%, 59.8%, 79.1% and 39.1%, respectively, in 2020. For CRC-cancer screening colonoscopy registration equaled outcome, PDR and ADR changed from 74.7% to 63.6% in 2016 to 66.3% and 53.8% in 2020, respectively. The quality of endoscopy data registration has consistently improved over the years by using the Trans.IT database. This is most likely the result of feedback to performing endoscopists to review performance in real-time online and progressive awareness of quality of data registration.

Development and validation of the Open-Source Automatic Bowel Preparation Scale.

Insufficient bowel preparation accounts for up to 42% of missed adenomas in colonoscopy. However, major analysis programs found no correlation between adenoma detection rate and the human-rated Boston Bowel Preparation Scale (BBPS), indicating limitations of the scale. We therefore aimed to develop an open-source automatic bowel preparation scale (OSABPS) based on artificial intelligence that is correlated to the polyp detection rate (PDR). OSABPS was trained on 50,000 frames from 20 colonoscopies from three hospitals. It involved quantifying the presence of fecal matter within the colonoscopy frames, using an approach termed the fecal ratio - the proportion of pixels identified as feces (F) relative to those identified as mucosal tissue (M) (OSABPS = F/M) - thereby making 0 the optimal score indicating a perfect cleansing. Youden's J was used to set the threshold, as it determines the optimal balance between sensitivity and specificity. The algorithm was then tested on 1,405 colonoscopies from three hospitals (internal validation), and 5,525 frames from a public colonoscopy database (Nerthus, external validation). Internal validation: OSABPS correlated significantly with BBPS (Pearson's r = -.42, P<.001). A threshold of .09 OSABPS was determined using Youden's J. PDR was higher for colonoscopies below the threshold of Youden's J (Two proportion z-test, P<.001). External validation: OSABPS correlated significantly with BBPS (Pearson's r = -.70, P<.001). OSABPS can automatically, instantly and without human bias assess bowel preparation quality. Colonoscopies with an OSABPS > .09 should be considered for reexamination. OSABPS' open-source nature allows free implementation.

Sex Differences in Colonoscopy Indications and Findings: Results from a Large Multicenter Database.

Background: Sex-based differences are common among diseases. We aimed to investigate the differences in colonoscopy indications and its findings between males and females. Methods: A large, multi-center, cross-sectional, retrospective study included all colonoscopies performed between 2016 and 2021 in seven endoscopy departments. The indications and findings of the procedures were compared between males and females. Results: A total of 151,411 (52.6%) women and 136,519 (47.4%) men were included, aged 56.54 ± 12.9 years and 56.59 ± 12.7. Cecal intubation was similar (95.6% vs 95.5%, p = 0.251). More females had excellent or good bowel preparation compared to males (71.4% vs 65.6%). Colonoscopy due to abdominal pain, constipation, diarrhea, and anemia was higher in females compared to males (15% vs 9.9%, 3.9% vs 2.2%, and 7.6% vs 4.9%, p < 0.001, respectively), while positive FOBT, rectal bleeding and post-polypectomy surveillance and screening were more common indications among males (9.5% vs 7.8%, 10.7% vs 7.8%, and 10.8% vs 7.1%, respectively). On colonoscopy, males were found to have significantly higher colorectal cancer and polyps (0.5% vs 0.4% and 35.1% vs 24.6%). Polyp detection rates were lower in females across all indications, whereas diverticulosis rates were higher in males. However, a clinically significant difference regarding diverticulosis was observed only in patients with anemia as the indication. Conclusions: Notable differences exist between males and females in terms of the indications and findings on colonoscopy. This highlights the need for identifying the factors contributing to these differences and the developing sex-specific approaches for the diagnosis and management of gastrointestinal diseases.

Effect of an artificial intelligence-assisted recognition system on colonoscopy quality

Objective: To explore the value of the artificial intelligence (AI)-assisted recognition system in the detection quality of colonoscopy. Methods: From January 2023, the data on 700 patients who underwent colonoscopy in the Digestive Endoscopy Center of the First Affiliated Hospital of Zhejiang Chinese Medical University were collected prospectively. Based on a computerized number method, patients were divided into the AI assistance group and control group. The detection rate of adenomas (ADR) and polyps, number and size of adenomas, Boston bowel preparation scale (BBPS), intubation time, withdrawal time, and cecal intubation rate were compared between groups. Normally distributed data were analyzed with the t-test for independent samples. Non-normally distributed data were analyzed with the Rank sum test. Categorical data were analyzed with the Chi-square test. Results: In total, 691 patients were included in the analysis. According to the intention to treat (ITT) analysis and per-protocol (PP) analysis, the withdrawal time of the AI group was higher than that of the control group (ITT:436 (305, 620) vs 368 (265, 510) s, Z=-4.24, P<0.001;PP:439 (306, 618) vs 364 (262, 500) s,t=-4.50, P<0.001); however, there were no significant differences in the ADR (ITT:123(35.5%) vs 111(32.2%), χ2=0.88, P=0.349;PP:108(34.2%) vs 99(31.1%), χ2=0.67, P=0.414), the number of adenomas (ITT:0(0, 1) vs 0(0, 1),Z=-1.08, P=0.282;PP:0(0, 1) vs 0(0, 1),Z=-0.87, P=0.387), the polyp detection rate (ITT:85(24.6%) vs 85(24.6%),χ2=0.001, P=0.983;PP:79(25.0%) vs 77(24.2%),χ2=0.05, P=0.818), BBPS (ITT:6.5±0.9 vs 6.5±0.7,t=-0.59, P=0.555;PP:6.7±0.6 vs 6.6±0.6,t=-1.83, P=0.068), and cecal intubation rate (ITT:346(100.0%) vs 343(99.4%), χ2=0.50, P=0.478) between these two groups. After excluding inadequate bowel preparation and failed cecal intubation cases, the AI-assisted system was found to significantly improve the detection rate of small adenomas (≤5 mm) (PP:27.8%(88/316)vs 21.1%(67/318), χ2=3.94, P=0.047). Conclusions: The application of an AI-assisted system in colonoscopy can increase the withdrawal time and improve the detection rate of small adenomas.

Areas of improvement for colorectal cancer screening: Results of a screening initiative for 10,000 health care employees in Austria.

Background and study aims Participation in and quality of colorectal cancer (CRC) screening varies greatly and it is unclear how much of CRC screening guideline quality metrics reach patients. The aims of this prospective observational study were to provide data from everyday practice in Austria. Patients and methods All employees aged ≥ 50 years were invited and received a stool-based-test (FIT (cut-off 25 mcg Hb/g) and M2PK), which could be dropped off at the workplace. All individuals with positive tests were called and offered a colonoscopy near their workplace/home in ≤ 3 weeks performed by unselected endoscopists. Non-attendees received email and telephone reminders. Results Of 10,239 eligible employees (2706 males, 7533 females), 2390 (23%) (plus 673 < 50 years) median age 53 (interquartile range 50;56) participated in the stool-based screening (18% males, 25% females). Of 3063 tests, 747 (24%) were positive. The follow-up rate for 616 individuals who accepted or eventually underwent colonoscopy was 84% (n = 517). The adenoma detection rate (ADR) was 20.5% (31% in men, 17% in women) and varied substantially, ranging from 15% in hospitals (excluding the study center) to 18.5% among office-based endoscopists, and up to 36% in the study center. Most European Society of Gastrointestinal Endoscopy-recommended performance indicators were unmet, including the polyp detection rate (PDR), ADR, reporting of polyp characteristics, and bowel preparation adequacy. Conclusions There is a serious gap between recommended standards and real-world CRC screening colonoscopy quality. Implementation of CRC screening should not only be accompanied by strategies to increase participation rates but focus on implementation of rigorous, mandatory colonoscopy quality assurance programs.