Performance Of Endoscopy Research Articles

A novel endoscopic artificial intelligence system to assist in the diagnosis of autoimmune gastritis: a multicenter study.

Autoimmune gastritis (AIG), distinct from Helicobacter pylori-associated atrophic gastritis (HpAG), is underdiagnosed due to limited awareness. This multicenter study aims to develop a novel endoscopic artificial intelligence (AI) system assisting in AIG diagnosis. Patients diagnosed with AIG, as well as HpAG and non-atrophic gastritis (NAG), were retrospectively enrolled from six centers. Endoscopic images with relevant demographic and medical data, were collected for the development of AI-assisted system, SEER-SCOPE AI, based on multi-site feature fusion model. The diagnostic performance of SEER-SCOPE AI was evaluated in the internal and external datasets. Endoscopists' performance with and without AI support was tested and compared using Mann-Whitney U test. Heatmap analysis was performed to interpret SEER-SCOPE AI. 1 070 patients (294 AIG, 386 HpAG, 390 NAG) with 18 828 endoscopy images were collected. SEER-SCOPE AI achieved strong performance for identifying AIG, with 96.9% sensitivity, 92.2% specificity and an AUROC of 0.990 internally, and 90.3% sensitivity, 93.1% specificity and an AUROC of 0.973 externally. The performance of SEER-SCOPE AI (sensitivity 91.3%) was comparable to experts (87.3%) and significantly outperformed non-experts (70.0%). With AI support, the overall performance of endoscopists was improved (sensitivity: 90.3% [95% CI 86.0%-93.2%] vs. 78.7% [95% CI 73.6%-83.2%], p=0.008). Heatmap analysis revealed consistent focus of SEER-SCOPE AI on regions corresponding to atrophic areas. SEER-SCOPE AI demonstrated expert-level performance in identifying AIG, and enhanced the diagnostic ability of endoscopists. Its application holds promise as a potent endoscopy-assisted tool for guiding biopsy sampling and early detection of AIG.

A new artificial intelligence system for both stomach and small-bowel capsule endoscopy

Despite the benefits of artificial intelligence in small-bowel (SB) capsule endoscopy (CE) image reading, information on its application in the stomach and SB CE is lacking. In this multicenter, retrospective diagnostic study, gastric imaging data were added to the deep learning-based SmartScan (SS), which has been described previously. A total of 1069 magnetically controlled GI CE examinations (comprising 2,672,542 gastric images) were used in the training phase for recognizing gastric pathologies, producing a new artificial intelligence algorithm named SS Plus. A total of 342 fully automated, magnetically controlled CE examinations were included in the validation phase. The performance of both senior and junior endoscopists with both the SS Plus-assisted reading (SSP-AR) and conventional reading (CR) modes was assessed. SS Plus was designed to recognize 5 types of gastric lesions and 17 types of SB lesions. SS Plus reduced the number of CE images required for review to 873.90 (median, 1000; interquartile range [IQR], 814.50-1000) versus 44,322.73 (median, 42,393; IQR, 31,722.75-54,971.25) for CR. Furthermore, with SSP-AR, endoscopists took 9.54 minutes (median, 8.51; IQR, 6.05-13.13) to complete the CE video reading. In the 342 CE videos, SS Plus identified 411 gastric and 422 SB lesions, whereas 400 gastric and 368 intestinal lesions were detected with CR. Moreover, junior endoscopists remarkably improved their CE image reading ability with SSP-AR. Our study shows that the newly upgraded deep learning-based algorithm SS Plus can detect GI lesions and help improve the diagnostic performance of junior endoscopists in interpreting CE videos.

Optical diagnosis in still images of colorectal polyps: comparison between expert endoscopists and PolyDeep, a Computer-Aided Diagnosis system

BackgroundPolyDeep is a computer-aided detection and classification (CADe/x) system trained to detect and classify polyps. During colonoscopy, CADe/x systems help endoscopists to predict the histology of colonic lesions.ObjectiveTo compare the diagnostic performance of PolyDeep and expert endoscopists for the optical diagnosis of colorectal polyps on still images.MethodsPolyDeep Image Classification (PIC) is an in vitro diagnostic test study. The PIC database contains NBI images of 491 colorectal polyps with histological diagnosis. We evaluated the diagnostic performance of PolyDeep and four expert endoscopists for neoplasia (adenoma, sessile serrated lesion, traditional serrated adenoma) and adenoma characterization and compared them with the McNemar test. Receiver operating characteristic curves were constructed to assess the overall discriminatory ability, comparing the area under the curve of endoscopists and PolyDeep with the chi- square homogeneity areas test.ResultsThe diagnostic performance of the endoscopists and PolyDeep in the characterization of neoplasia is similar in terms of sensitivity (PolyDeep: 89.05%; E1: 91.23%, p=0.5; E2: 96.11%, p<0.001; E3: 86.65%, p=0.3; E4: 91.26% p=0.3) and specificity (PolyDeep: 35.53%; E1: 33.80%, p=0.8; E2: 34.72%, p=1; E3: 39.24%, p=0.8; E4: 46.84%, p=0.2). The overall discriminative ability also showed no statistically significant differences (PolyDeep: 0.623; E1: 0.625, p=0.8; E2: 0.654, p=0.2; E3: 0.629, p=0.9; E4: 0.690, p=0.09). In the optical diagnosis of adenomatous polyps, we found that PolyDeep had a significantly higher sensitivity and a significantly lower specificity. The overall discriminative ability of adenomatous lesions by expert endoscopists is significantly higher than PolyDeep (PolyDeep: 0.582; E1: 0.685, p < 0.001; E2: 0.677, p < 0.0001; E3: 0.658, p < 0.01; E4: 0.694, p < 0.0001).ConclusionPolyDeep and endoscopists have similar diagnostic performance in the optical diagnosis of neoplastic lesions. However, endoscopists have a better global discriminatory ability than PolyDeep in the optical diagnosis of adenomatous polyps.

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.

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. 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). 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. 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.

Influence of artificial intelligence on the diagnostic performance of endoscopists in the assessment of Barrett's esophagus: a tandem randomized and video trial.

This study evaluated the effect of an artificial intelligence (AI)-based clinical decision support system on the performance and diagnostic confidence of endoscopists in their assessment of Barrett's esophagus (BE). 96 standardized endoscopy videos were assessed by 22 endoscopists with varying degrees of BE experience from 12 centers. Assessment was randomized into two video sets: group A (review first without AI and second with AI) and group B (review first with AI and second without AI). Endoscopists were required to evaluate each video for the presence of Barrett's esophagus-related neoplasia (BERN) and then decide on a spot for a targeted biopsy. After the second assessment, they were allowed to change their clinical decision and confidence level. AI had a stand-alone sensitivity, specificity, and accuracy of 92.2%, 68.9%, and 81.3%, respectively. Without AI, BE experts had an overall sensitivity, specificity, and accuracy of 83.3%, 58.1%, and 71.5%, respectively. With AI, BE nonexperts showed a significant improvement in sensitivity and specificity when videos were assessed a second time with AI (sensitivity 69.8% [95%CI 65.2%-74.2%] to 78.0% [95%CI 74.0%-82.0%]; specificity 67.3% [95%CI 62.5%-72.2%] to 72.7% [95%CI 68.2%-77.3%]). In addition, the diagnostic confidence of BE nonexperts improved significantly with AI. BE nonexperts benefitted significantly from additional AI. BE experts and nonexperts remained significantly below the stand-alone performance of AI, suggesting that there may be other factors influencing endoscopists' decisions to follow or discard AI advice.

Prevalence and predictive factors of colorectal sessile serrated lesions in younger individuals.

Sessile serrated lesions (SSLs) are obscured lesions predominantly in the right-sided colon and associated with interval colorectal cancer; however, their prevalence and risk factors among younger individuals remain unclear. This retrospective study enrolled individuals who underwent index colonoscopy. The primary outcome was the SSL prevalence in the younger (<50 years) and older (≥50 years) age groups, while the secondary outcomes included clinically significant serrated polyps (CSSPs). Multivariable logistic regression was employed to identify predictors. Of the 9854 eligible individuals, 4712 (47.8%) were categorized into the younger age group. Individuals in the younger age group exhibited lower prevalences of adenomas (22.6% vs. 46.2%; P<0.001) and right-sided adenomas (11.2% vs. 27.2%; P<0.001) compared with their older counterparts. However, both groups exhibited a similar prevalence of SSLs (7.2% vs. 6.5%; P=0.16) and CSSPs (10.3% vs. 10.3%;P=0.96). Multivariable analysis revealed that age 40-49 years (odds ratio [OR] 1.81, 95%CI 1.01-3.23), longer withdrawal time (OR 1.17, 95%CI 1.14-1.20, per minute increment), and endoscopist performance (OR 3.35, 95%CI 2.44-4.58) were independent predictors of SSL detection in the younger age group. No significant correlation was observed between adenoma and SSL detection rates among endoscopists. SSLs are not uncommon among younger individuals. Moreover, diligent effort and expertise are of paramount importance in SSL detection. Future studies should explore the clinical significance of SSLs in individuals of younger age.

Artificial Intelligence-assisted colonoscopy and colorectal cancer screening: Where are we going?

Colorectal cancer is a significant global health concern, necessitating effective screening strategies to reduce its incidence and mortality rates. Colonoscopy plays a crucial role in the detection and removal of colorectal neoplastic precursors. However, there are limitations and variations in the performance of endoscopists, leading to missed lesions and suboptimal outcomes. The emergence of artificial intelligence (AI) in endoscopy offers promising opportunities to improve the quality and efficacy of screening colonoscopies. In particular, AI applications, including computer-aided detection (CADe) and computer-aided characterization (CADx), have demonstrated the potential to enhance adenoma detection and optical diagnosis accuracy. Additionally, AI-assisted quality control systems aim to standardize the endoscopic examination process. This narrative review provides an overview of AI principles and discusses the current knowledge on AI-assisted endoscopy in the context of screening colonoscopies. It highlights the significant role of AI in improving lesion detection, characterization, and quality assurance during colonoscopy. However, further well-designed studies are needed to validate the clinical impact and cost-effectiveness of AI-assisted colonoscopy before its widespread implementation.

Comparing sedation protocols for endoscopic retrograde cholangiopancreatography (ERCP): A retrospective study

BackgroundEndoscopic retrograde cholangiopancreatography (ERCP) is a widely used diagnostic and therapeutic procedure. Effective sedation is crucial to enhance patient comfort and optimize endoscopist performance. Various sedation protocols, including Propofol and Dexmedetomidine (Pro-Dex), Ketamine and Propofol (Keto-Fol), Propofol and Midazolam (Pro-Mid), and Propofol alone, have been utilized during ERCP. This retrospective study aims to compare the safety and efficacy of these four sedation protocols. MethodsA retrospective analysis was conducted on data from 600 patients who underwent ERCP between 2018 and 2021, with each patient receiving one of the four sedation protocols. Protocol assignment was based on the endoscopist's preference. Data on hemodynamic parameters, sedation level, recovery time, and procedure-related complications were collected. ResultsBaseline data showed no significant differences among the groups pre-procedure. The Pro-Dex group exhibited significantly lower mean total propofol dose, shorter recovery time, and faster achievement of Ramsay Sedation Scale (RSS) score 3–4 compared to the other groups. The Pro-group demonstrated significantly longer hospital stay than the other three groups (median, 4.19 ± 1.1 vs. 3.48 ± 1.2 days in the KP groups, p = 0.042). There were no significant variations in the incidence of respiratory depression, hypotension, or bradycardia among the four groups. Additionally, notable trends were found for hemodynamic measures, total propofol dosage, time to reach the desired level of sedation (as measured by the Ramsay Sedation Scale), and hospital stay based on BMI categories, indicating that higher BMI is linked to more serious outcomes. ConclusionOur retrospective study demonstrates that the Pro-Dex protocol offers superior sedation quality, faster recovery, and fewer complications compared to the other protocols during ERCP. However, the incidence of ERCP-related adverse events did not significantly differ among the four sedation protocols. These findings can aid clinicians in selecting the most appropriate sedation protocol for ERCP, considering patient and endoscopist preferences.

Artificial intelligence-assisted system for the assessment of Forrest classification of peptic ulcer bleeding: a multicenter diagnostic study.

Inaccurate Forrest classification may significantly affect clinical outcomes, especially in high risk patients. Therefore, this study aimed to develop a real-time deep convolutional neural network (DCNN) system to assess the Forrest classification of peptic ulcer bleeding (PUB). A training dataset (3868 endoscopic images) and an internal validation dataset (834 images) were retrospectively collected from the 900th Hospital, Fuzhou, China. In addition, 521 images collected from four other hospitals were used for external validation. Finally, 46 endoscopic videos were prospectively collected to assess the real-time diagnostic performance of the DCNN system, whose diagnostic performance was also prospectively compared with that of three senior and three junior endoscopists. The DCNN system had a satisfactory diagnostic performance in the assessment of Forrest classification, with an accuracy of 91.2% (95%CI 89.5%-92.6%) and a macro-average area under the receiver operating characteristic curve of 0.80 in the validation dataset. Moreover, the DCNN system could judge suspicious regions automatically using Forrest classification in real-time videos, with an accuracy of 92.0% (95%CI 80.8%-97.8%). The DCNN system showed more accurate and stable diagnostic performance than endoscopists in the prospective clinical comparison test. This system helped to slightly improve the diagnostic performance of senior endoscopists and considerably enhance that of junior endoscopists. The DCNN system for the assessment of the Forrest classification of PUB showed satisfactory diagnostic performance, which was slightly superior to that of senior endoscopists. It could therefore effectively assist junior endoscopists in making such diagnoses during gastroscopy.

The impact of endoscopist performance and patient factors on distal adenoma detection and colorectal cancer incidence

BackgroundHigh quality endoscopy is key for detecting and removing precursor lesions to colorectal cancer (CRC). Adenoma detection rates (ADRs) measure endoscopist performance. Improving other components of examinations could increase adenoma detection.AimsTo investigate how endoscopist performance at flexible sigmoidoscopy (FS) affects adenoma detection and CRC incidence.MethodsAmong 34,139 participants receiving FS screening by the main endoscopist at one of 13 centres in the UK FS Screening Trial, median follow-up was 17 years. Factors examined included family history of CRC, bowel preparation quality, insertion and withdrawal time, bowel segment reached, patient pain and ADR. Odds ratios (OR) for distal adenoma detection were estimated by logistic regression. Hazard ratios (HR) for distal CRC incidence were estimated by Cox regression.ResultsAt screening, 4,104 participants had distal adenomas detected and 168 participants developed distal CRC during follow-up. In multivariable models, a family history of CRC (yes vs. no: OR 1.40, 95%CI 1.21–1.62), good or adequate bowel preparation quality (vs. excellent: OR 0.84, 95%CI 0.74–0.95; OR 0.56, 95%CI 0.49–0.65, respectively) and longer insertion and withdrawal times (≥ 4.00 vs. < 2.00 min: OR 1.96, 95%CI 1.68–2.29; OR 32.79, 95%CI 28.22–38.11, respectively) were associated with adenoma detection. Being screened by endoscopists with low or intermediate ADRs, compared to high ADRs, was positively associated with CRC incidence (multivariable: HR 4.71, 95%CI 2.65–8.38; HR 2.16, 95%CI 1.22–3.81, respectively).ConclusionsBowel preparation quality and longer insertion and withdrawal time are key for improving distal adenoma detection. Higher ADRs were associated with a lower risk of distal CRC.

Endoscopic sleeve gastroplasty: stomach location and task classification for evaluation using artificial intelligence.

We have previously developed grading metrics to objectively measure endoscopist performance in endoscopic sleeve gastroplasty (ESG). One of our primary goals is to automate the process of measuring performance. To achieve this goal, the repeated task being performed (grasping or suturing) and the location of the endoscopic suturing device in the stomach (Incisura, Anterior Wall, Greater Curvature, or Posterior Wall) need to be accurately recorded. For this study, we populated our dataset using screenshots and video clips from experts carrying out the ESG procedure on ex vivo porcine specimens. Data augmentation was used to enlarge our dataset, and synthetic minority oversampling (SMOTE) to balance it. We performed stomach localization for parts of the stomach and task classification using deep learning for images and computer vision for videos. Classifying the stomach's location from the endoscope without SMOTE for images resulted in 89% and 84% testing and validation accuracy, respectively. For classifying the location of the stomach from the endoscope with SMOTE, the accuracies were 97% and 90% for images, while for videos, the accuracies were 99% and 98% for testing and validation, respectively. For task classification, the accuracies were 97% and 89% for images, while for videos, the accuracies were 100% for both testing and validation, respectively. We classified the four different stomach parts manipulated during the ESG procedure with 97% training accuracy and classified two repeated tasks with 99% training accuracy with images. We also classified the four parts of the stomach with a 99% training accuracy and two repeated tasks with a 100% training accuracy with video frames. This work will be essential in automating feedback mechanisms for learners in ESG.

Endoscopic ultrasound artificial intelligence-assisted for prediction of gastrointestinal stromal tumors diagnosis: A systematic review and meta-analysis.

Subepithelial lesions (SELs) are gastrointestinal tumors with heterogeneous malignant potential. Endoscopic ultrasonography (EUS) is the leading method for evaluation, but without histopathological analysis, precise differentiation of SEL risk is limited. Artificial intelligence (AI) is a promising aid for the diagnosis of gastrointestinal lesions in the absence of histopathology. To determine the diagnostic accuracy of AI-assisted EUS in diagnosing SELs, especially lesions originating from the muscularis propria layer. Electronic databases including PubMed, EMBASE, and Cochrane Library were searched. Patients of any sex and > 18 years, with SELs assessed by EUS AI-assisted, with previous histopathological diagnosis, and presented sufficient data values which were extracted to construct a 2 × 2 table. The reference standard was histopathology. The primary outcome was the accuracy of AI for gastrointestinal stromal tumor (GIST). Secondary outcomes were AI-assisted EUS diagnosis for GIST vs gastrointestinal leiomyoma (GIL), the diagnostic performance of experienced endoscopists for GIST, and GIST vs GIL. Pooled sensitivity, specificity, positive, and negative predictive values were calculated. The corresponding summary receiver operating characteristic curve and post-test probability were also analyzed. Eight retrospective studies with a total of 2355 patients and 44154 images were included in this meta-analysis. The AI-assisted EUS for GIST diagnosis showed a sensitivity of 92% [95% confidence interval (CI): 0.89-0.95; P < 0.01), specificity of 80% (95%CI: 0.75-0.85; P < 0.01), and area under the curve (AUC) of 0.949. For diagnosis of GIST vs GIL by AI-assisted EUS, specificity was 90% (95%CI: 0.88-0.95; P = 0.02) and AUC of 0.966. The experienced endoscopists' values were sensitivity of 72% (95%CI: 0.67-0.76; P < 0.01), specificity of 70% (95%CI: 0.64-0.76; P < 0.01), and AUC of 0.777 for GIST. Evaluating GIST vs GIL, the experts achieved a sensitivity of 73% (95%CI: 0.65-0.80; P < 0.01) and an AUC of 0.819. AI-assisted EUS has high diagnostic accuracy for fourth-layer SELs, especially for GIST, demonstrating superiority compared to experienced endoscopists' and improving their diagnostic performance in the absence of invasive procedures.

Development and initial validation of a video-based peroral endoscopic myotomy assessment tool

Video analysis has emerged as a potential strategy for performance assessment and improvement. We aimed to develop a video-based skill assessment tool for peroral endoscopic myotomy (POEM). POEM was deconstructed into basic procedural components through video analysis by an expert panel. A modified Delphi approach and 2 validation exercises were conducted to refine the POEM assessment tool (POEMAT). Twelve assessors used the final POEMAT version to grade 10 videos. Fully crossed generalizability (G) studies investigated the contributions of assessors, endoscopists' performance, and technical elements to reliability. G coefficients below .5 were considered unreliable, between .5 and .7 as modestly reliable, and above .7 as indicative of satisfactory reliability. After task deconstruction, discussions, and the modified Delphi process, the final POEMAT comprised 9 technical elements. G analysis showed low variance for endoscopist performance (.8%-24.9%) and high interrater variability (range, 63.2%-90.1%). The G score was moderately reliable (≥.60) for "submucosal tunneling" and "myotomy" and satisfactorily reliable (≥.70) for "active hemostasis" and "mucosal closure." We developed and established initial content and response process validity evidence for the POEMAT. Future steps include appraisal of the tool using a wider range of POEM videos to establish and improve the discriminative validity of this tool.

Variation in the rate of detection of minute and small early gastric cancers at diagnostic endoscopy may reflect the performance of individual endoscopists

ObjectiveThe documented variation in gastric cancer (GC) detection among endoscopists has often been dismissed as a coincidental artefact of the low incidence of gastric neoplasms; it is not considered associated...

Detection of duodenal villous atrophy on endoscopic images using a deep learning algorithm.

Celiac disease with its endoscopic manifestation of villous atrophy is underdiagnosed worldwide. The application of artificial intelligence (AI) for the macroscopic detection of villous atrophy at routine esophagogastroduodenoscopy may improve diagnostic performance. A dataset of 858 endoscopic images of 182 patients with villous atrophy and 846 images from 323 patients with normal duodenal mucosa was collected and used to train a ResNet 18 deep learning model to detect villous atrophy. An external data set was used to test the algorithm, in addition to six fellows and four board certified gastroenterologists. Fellows could consult the AI algorithm's result during the test. From their consultation distribution, a stratification of test images into "easy" and "difficult" was performed and used for classified performance measurement. External validation of the AI algorithm yielded values of 90 %, 76 %, and 84 % for sensitivity, specificity, and accuracy, respectively. Fellows scored values of 63 %, 72 % and 67 %, while the corresponding values in experts were 72 %, 69 % and 71 %, respectively. AI consultation significantly improved all trainee performance statistics. While fellows and experts showed significantly lower performance for "difficult" images, the performance of the AI algorithm was stable. In this study, an AI algorithm outperformed endoscopy fellows and experts in the detection of villous atrophy on endoscopic still images. AI decision support significantly improved the performance of non-expert endoscopists. The stable performance on "difficult" images suggests a further positive add-on effect in challenging cases.

Colonoscopy performance monitoring: do we need to adjust for case mix?

Introduction Overall caecum intubation rate(oCIR) and overall polyp detection rate(oPDR) have been proposed as performance indicators, but varying complexity in case mix among endoscopists may potentially affect validity. The study aims to explore the effect of adjusting for case mix on individual endoscopist performance by calculating case mix-adjusted performance estimates (cmCIR and cmPDR) and comparing them to overall performance estimates (oCIR and oPDR). The study also provides an R program for case mix analysis. Methods Logistic regression associated endoscopist, colonoscopy indication, patient age and patient gender with the binary outcomes of cecum intubation and polyp detection. Case mix-adjusted performance indicators were calculated for each endoscopist based on logistic regression and bootstraps. Endoscopists were ranked from best to worst by overall and case mix-adjusted performance estimates, and differences were evaluated using percentage points(pp) and rank changes. Results The dataset consisted of 7376 colonoscopies performed by 47 endoscopists. The maximum rank change for an endoscopist comparing oCIR and cmCIR was eight positions, interquartile range (IQR 1–3). The maximum change in CIR was 1.95 percentage point (pp) (IQR 0.27–0.86). The maximum rank change in the oPDR versus cmPDR analysis was 17 positions (IQR 1.5–8.5). The maximum change in PDR was 11.21 pp (IQR 2.05–6.70). Three endoscopists improved their performance from significantly inferior to within the 95% confidence interval (CI) range of performance targets using case mix-adjusted estimates. Conclusions The majority of endoscopists were unaffected by adjustment for case mix, but a few unfortunate endoscopists had an unfavourable case mix that could invite incorrect suspicion of inferior performance.

Assessment of the Role of Artificial Intelligence in the Association Between Time of Day and Colonoscopy Quality

Time of day was associated with a decline in adenoma detection during colonoscopy. Artificial intelligence (AI) systems are effective in improving the adenoma detection rate (ADR), but the performance of AI during different times of the day remains unknown. To validate whether the assistance of an AI system could overcome the time-related decline in ADR during colonoscopy. This cohort study is a secondary analysis of 2 prospective randomized controlled trials (RCT) from Renmin Hospital of Wuhan University. Consecutive patients undergoing colonoscopy were randomly assigned to either the AI-assisted group or unassisted group from June 18, 2019, to September 6, 2019, and July 1, 2020, to October 15, 2020. The ADR of early and late colonoscopy sessions per half day were compared before and after the intervention of the AI system. Data were analyzed from March to June 2022. Conventional colonoscopy or AI-assisted colonoscopy. Adenoma detection rate. A total of 1780 patients (mean [SD] age, 48.61 [13.35] years, 837 [47.02%] women) were enrolled. A total of 1041 procedures (58.48%) were performed in early sessions, with 357 randomized into the unassisted group (34.29%) and 684 into the AI group (65.71%). A total of 739 procedures (41.52%) were performed in late sessions, with 263 randomized into the unassisted group (35.59%) and 476 into the AI group (64.41%). In the unassisted group, the ADR in early sessions was significantly higher compared with that of late sessions (13.73% vs 5.70%; P = .005; OR, 2.42; 95% CI, 1.31-4.47). After the intervention of the AI system, as expected, no statistically significant difference was found (22.95% vs 22.06%, P = .78; OR, 0.96; 95% CI; 0.71-1.29). Furthermore, the AI systems showed better assistance ability on ADR in late sessions compared with early sessions (odds ratio, 3.81; 95% CI, 2.10-6.91 vs 1.60; 95% CI, 1.10-2.34). In this cohort study, AI systems showed higher assistance ability in late sessions per half day, which suggests the potential to maintain high quality and homogeneity of colonoscopies and further improve endoscopist performance in large screening programs and centers with high workloads.

The Saudi Gastroenterology Association guidelines for quality indicators in gastrointestinal endoscopic procedures.

The quality and safety of gastrointestinal endoscopy varies considerably across regions and facilities worldwide. In this field, quality management has traditionally focused on individual performance of endoscopists, with most indicators addressing process measures and limited evidence of improvement in health outcomes. Indicators of quality can be classified according to their nature and sequence. The various professional societies and organizations have proposed many systems of indicators, but a universal system is necessary so that healthcare professionals are not overburdened and confused with a variety of quality improvement approaches. In this paper, we propose guidelines by the Saudi Gastroenterology Association pertaining to quality in endoscopic procedures aiming to improve the awareness of endoscopy unit staff toward important quality indications to enhance and standardize quality of care provided to our patients.

Risk Factors Indicating Difficulty During Gastric Endoscopic Submucosal Dissection for Inexperienced Endoscopists: A Retrospective Study.

Factors that may make endoscopic submucosal dissection (ESD) difficult for operators have been evaluated according to results based on the performance of experienced endoscopists. This study aimed to verify the predictors of difficult gastric ESD for ESD beginners. From January 2015 to December 2021, 466 superficial gastric neoplasms were treated with ESD at Showa University Hospital. Excluding 103 lesions that performed ESD by experts who experienced more than 80 ESDs, a total of 363 lesions were included. The lesions were divided into two groups according to the ESD performance experience of the operator:ESD beginner (EB; ESD experience≤30 cases) and ESD intermediate (EI; ESD experience 31-80 cases) groups. Relationships between difficult ESD (having at least one of the following: procedure time>60 min, incomplete resection, change of operator, and occurrence of severe complications) and clinicopathological findings of the lesion were analyzed. The complete resection rates and the difficult ESD rates in the EB and EI groups were 99.3%, 94.8%, and 61.2%, 50.7%, respectively. In the EB group, univariate analysis showed that difficult ESD rate was significantly higher in the non-lower third lesions, the lesser curvature lesions, and cancerous lesions. In the EI group, univariate analysis showed that difficult ESD rate was significantly higher in lesion with ≥20 mm size, lesser curvature lesions, lesions with ulcers, and submucosal cancers. Multivariate analysis showed that the lesser curvature location and cancerous histology in the EB group and ≥20 mm lesion size, the lesser curvature location and submucosal invasion in the EI group were independent predictors of difficult ESD. The lesser curvature location is recognized as independent ESD difficulty factor for both beginners and intermediates.Cases with lesions located in the lesser curvature should not be selected for gastric ESD training by beginners.

Colonoscopy quality of GP endoscopists in three rural hospitals in Queensland, Australia.

Rural general practitioners (GPs) are responsible for delivering primary and secondary care to rural populations in Australia. There is limited literature investigating the performance of GP endoscopists. Theaim of this study was to investigate the colonoscopy performance of three GP endoscopists in rural Queensland against current Australian quality indicator (QI) standards. A cross sectional study investigated eligible colonoscopies between January 2018 and February 2021by three GP endoscopists in three rural hospitals inQueensland, Australia. A total of 1674 colonoscopies were investigated. The GP endoscopists demonstrated high QI performance, above the recommended benchmarks. Caecal intubation rate, adenoma detection rate, sessile serrated adenoma/polyp detection rate and clinically significant serrated polyp detection rate were 97.9%, 49.5%, 16% and 14.1% respectively. The major colonoscopy-related complications rate was 0.06%. Rural GP endoscopists potentially can deliver safe, high-quality colonoscopy services for rural communities and can have an integral part in facilitating colorectal cancer prevention and treatment in rural communities.