ABSTRACT
Acute lower gastrointestinal bleeding (LGIB) is a common reason for hospitalization in the United States and is associated with significant utilization of hospital resources, as well as considerable morbidity and mortality. These revised guidelines implement the Grading of Recommendations, Assessment, Development, and Evaluation methodology to propose recommendations for the use of risk stratification tools, thresholds for red blood cell transfusion, reversal agents for patients on anticoagulants, diagnostic testing including colonoscopy and computed tomography angiography (CTA), endoscopic therapeutic options, and management of antithrombotic medications after hospital discharge. Important changes since the previous iteration of this guideline include recommendations for the use of risk stratification tools to identify patients with LGIB at low risk of a hospital-based intervention, the role for reversal agents in patients with life-threatening LGIB on vitamin K antagonists and direct oral anticoagulants, the increasing role for CTA in patients with severe LGIB, and the management of patients who have a positive CTA. We recommend that most patients requiring inpatient colonoscopy undergo a nonurgent colonoscopy because performing an urgent colonoscopy within 24 hours of presentation has not been shown to improve important clinical outcomes such as rebleeding. Finally, we provide updated recommendations regarding resumption of antiplatelet and anticoagulant medications after cessation of LGIB.
Subject(s)
Gastrointestinal Hemorrhage , Hospitalization , Humans , Gastrointestinal Hemorrhage/diagnosis , Gastrointestinal Hemorrhage/etiology , Gastrointestinal Hemorrhage/therapy , Anticoagulants/therapeutic use , Acute Disease , Inpatients , Colonoscopy/adverse effectsABSTRACT
INTRODUCTION: Cold snare polypectomy (CSP) is strongly recommended as the optimal technique for the complete removal of small polyps. Though significant variability in polypectomy technique and quality has been established, the learning curve and impact of targeted training on CSP are unknown. Video feedback has shown promise as an effective pedagogy to improve performance among surgical trainees. We aimed to compare CSP performance between trainees who received video-based feedback and those who received conventional apprentice-based concurrent feedback. We hypothesized that video-based feedback would accelerate competence. METHODS: We conducted a single-blinded, randomized controlled trial on competence for CSP of polyps <1 cm, comparing video-based feedback with conventional feedback. We randomly assigned deidentified consecutively recorded CSP videos to blinded raters to assess using the CSP Assessment Tool. We shared cumulative sum learning curves every 25 CSP with each trainee. The video feedback trainees also received biweekly individualized terminal feedback. Control trainees received conventional feedback during colonoscopy. The primary outcome was CSP competence. We also assessed competence across domains and change over polypectomy volume. RESULTS: We enrolled and randomized 22 trainees, 12 to video-based feedback and 10 to conventional feedback, and evaluated 2,339 CSP. The learning curve was long; 2 trainees (16.7%) in the video feedback achieved competence, after a mean of 135 polyps, and no one in the control ( P = 0.481) achieved competence. Overall and in all steps of CSP, a higher percentage of the video feedback group met competence, increasing 3% every 20 CSP ( P = 0.0004). DISCUSSION: Video feedback aided trainees to competence in CSP. However, the learning curve was long. Our findings strongly suggest that current training methods are not sufficient to support trainees to competency by the completion of their fellowship programs. The impact of new training methods, such as simulation-based mastery learning, should be assessed to determine whether such methods can result in achievement of competence at a faster rate; ClinicalTrials.gov : NCT03115008.
Subject(s)
Colonic Polyps , Colonoscopy , Humans , Colonoscopy/methods , Colonic Polyps/surgery , MicrosurgeryABSTRACT
BACKGROUND AND AIMS: Patients with inflammatory bowel disease (IBD) are at risk of developing dysplasia. According to the Surveillance for Colorectal Endoscopic Neoplasia Detection and Management in Inflammatory Bowel Disease Patients: International Consensus Recommendations, "After complete removal of endoscopically resectable nonpolypoid dysplastic lesions, surveillance colonoscopy is suggested rather than colectomy." We sought to add data to the literature and hypothesized that the endoscopic resection of nonpolypoid colorectal dysplasia (NP-CRD) is safe and effective. METHODS: We conducted a retrospective study of a large cohort of patients with IBD at 2 medical centers who underwent colonoscopy between 2007 and 2018. Patients with at least 1 nonpolypoid lesion ≥10 mm were identified. We measured the feasibility of endoscopic resection, incidence of local recurrence, incidence of cancer, need for surgery, and frequency of adverse events. RESULTS: We studied 326 patients who underwent a mean ± standard deviation of 3.6 ± 3.0 (range, 1-16) colonoscopies during a total follow-up of 1208 patient-years. In 36 patients, 161 lesions ≥10 mm were identified, 63 of which were nonpolypoid (mean size, 17.8 ± 8.9 mm; range, 10-45 mm) (prevalence, 7.7%). The majority of nonpolypoid lesions (96.8% [61 of 63]) were managed endoscopically. Four lesions (mean index lesion size, 32.5 ±11.0 mm) had small local recurrences that were successfully retreated with endoscopy. There were no severe adverse events related to IBD or colorectal cancer observed in the follow-up period. CONCLUSIONS: In this IBD cohort, surveillance colonoscopy rather than colectomy was found to be safe and effective in patients with NP-CRD after undergoing endoscopic resection. After complete removal of endoscopically resectable NP-CRD, surveillance colonoscopy should be considered a safe and effective first-line strategy rather than colectomy.
Subject(s)
Carcinoma in Situ , Colorectal Neoplasms , Inflammatory Bowel Diseases , Humans , Retrospective Studies , Colonoscopy , Colorectal Neoplasms/surgery , Colorectal Neoplasms/pathology , Colectomy , Hyperplasia , Inflammatory Bowel Diseases/complications , Inflammatory Bowel Diseases/surgery , Inflammatory Bowel Diseases/pathology , Carcinoma in Situ/surgeryABSTRACT
This clinical practice guideline from the American Society for Gastrointestinal Endoscopy provides an evidence-based approach to strategies to prevent endoscopy-related injury (ERI) in GI endoscopists. It is accompanied by the article subtitled "Methodology and Review of Evidence," which provides a detailed account of the methodology used for the evidence review. This document was developed using the Grading of Recommendations Assessment, Development and Evaluation framework. The guideline estimates the rates, sites, and predictors of ERI. Additionally, it addresses the role of ergonomics training, microbreaks and macrobreaks, monitor and table positions, antifatigue mats, and use of ancillary devices in decreasing the risk of ERI. We recommend formal ergonomics education and neutral posture during the performance of endoscopy, achieved through adjustable monitor and optimal procedure table position, to reduce the risk of ERI. We suggest taking microbreaks and scheduled macrobreaks and using antifatigue mats during procedures to prevent ERI. We suggest the use of ancillary devices in those with risk factors predisposing them to ERI.
Subject(s)
Endoscopy, Gastrointestinal , Ergonomics , Humans , Posture , Risk FactorsABSTRACT
Endoscopy staff suffer work-related musculoskeletal disorders at a rate greater than or comparable to nurses and technicians in other subspecialities, which may be attributable to the widespread use of manual pressure and repositioning during colonoscopy. In addition to negatively impacting staff health and job performance, colonoscopy-related musculoskeletal disorder injuries may also signal potential risks to patient safety. To assess the prevalence of staff injury and perceived patient harm relating to the use of manual pressure and repositioning techniques during colonoscopy, 185 attendees of a recent national meeting of the Society of Gastroenterology Nurses and Associates were asked to recall experiencing injuries to themselves or observing injuries to other staff or patients during colonoscopy. A majority of respondents (84.9%, n = 157) reported either experiencing or observing staff injury, whereas 25.9% ( n = 48) reported observing patient complications. Among respondents who perform manual repositioning and apply manual pressure during colonoscopy (57.3%, n = 106), 85.8% ( n = 91) reported experiencing musculoskeletal disorders from performing these tasks; 81.1% ( n = 150) reported no awareness of colonoscopy-specific ergonomics policies at their facility. Results highlight the relationship between the physical job requirements of endoscopy nurses and technicians, staff musculoskeletal disorders, and patient complications, and suggest that implementation of staff safety protocols may benefit patients as well as endoscopy staff.
Subject(s)
Musculoskeletal Diseases , Nursing Staff, Hospital , Humans , Colonoscopy/adverse effects , Endoscopy, Gastrointestinal , Musculoskeletal Diseases/diagnosis , Musculoskeletal Diseases/epidemiology , Musculoskeletal Diseases/etiologyABSTRACT
BACKGROUND & AIMS: Adenoma detection rate (ADR) is a key measure of colonoscopy quality. However, efficient measurement of ADR can be challenging because many colonoscopies are performed for non-screening purposes. Measuring ADR without being restricted to screening indication may likely facilitate more widespread implementation of quality monitoring. We hypothesized that the ADR for all colonoscopies, irrespective of the indication, would be equivalent to the ADR for screening colonoscopies. METHODS: We reviewed consecutive colonoscopies at two Veterans Affairs centers performed by 21 endoscopists over 6 months in 2015. We calculated the ADR for screening exams, non-screening (surveillance and diagnostic) exams, and all exams (irrespective of indication), correcting for within-endoscopist correlation. We then performed simulation modeling to calculate the ADRs under 16 hypothetical scenarios of various indication distributions. We simulated 100,000 trials with 3,000 participants, randomly assigned indication (screening, surveillance, diagnostic, and FIT+) from a multinomial distribution, randomly drew adenoma using the observed ADRs per indication, and calculated 95% confidence intervals of the mean differences in ADR of screening and non-screening indications. RESULTS: Among 2628 colonoscopies performed by 21 gastroenterologists, the indication was screening in 28.9%, surveillance in 48.2% and diagnostic in 22.9%. There was no significant difference in the ADR, 50% (95%CI: 45-56%) for all colonoscopies vs 49% (95%CI: 43-56%) for screening exams (p=.55). ADRs were 56% for surveillance and 38% for diagnostic exams. In our simulation modeling, only one out of 16 scenarios (screening 10%, surveillance 70%, diagnostic 10% and FIT+ 10%) resulted in a significant difference between the calculated ADRs for screening and non-screening indications. CONCLUSIONS: In our study, the overall ADR computed from all colonoscopies was not significantly different than the conventional ADR based on screening colonoscopies. Assessing ADR for colonoscopy irrespective of indication may be adequate for quality monitoring, and could facilitate the implementation of quality measurement and reporting. Future prospective studies should evaluate the validity of using overall ADR for quality reporting in other jurisdictions before adopting this method in clinical practice.
Subject(s)
Adenoma , Colorectal Neoplasms , Adenoma/diagnosis , Colonoscopy , Colorectal Neoplasms/diagnosis , Early Detection of Cancer , Humans , Mass Screening , Prospective StudiesABSTRACT
BACKGROUND AND AIMS: Endoscopists experience upper extremity musculoskeletal injuries. The primary aim of this study was to compare distal upper extremity biomechanical risk factors during colonoscopy with established risk thresholds. Secondary aims were to determine which subtasks during colonoscopy are associated with the greatest risk and to evaluate an intervention to reduce risks. METHODS: Twelve endoscopists performed 2 to 4 colonoscopies while thumb pinch force and forearm muscle loads of extensor carpi radialis (ECR) and flexor digitorum superficialis (FDS) muscles were collected. Peak exertion values were analyzed using amplitude probability distribution functions. An endoscope support device was evaluated during simulated colonoscopy (n = 8). RESULTS: Mean endoscopist age was 42.3 years; 67% were men. Peak thumb pinch force exceeded risk thresholds for pinch force (10 N) and percent of time spent in forceful pinch for all colonoscopy subtasks. Peak ECR and FDS muscle activity exceeded the action limit (10% maximum voluntary contraction [MVC]) in both forearms. Peak left FDS, left ECR, and right ECR activity exceeded the threshold limit value (>30% MVC). Peak left FDS and ECR activity were significantly greater during insertion than during withdrawal (P < .05). Peak right FDS and ECR activity were significantly greater during right colon insertion compared with withdrawal (P < .05). The endoscope support device reduced left ECR muscle activity (P = .02). CONCLUSIONS: Thumb pinch forces and time spent in forceful pinch indicate high-risk exposures during colonoscopy. Left wrist extensor muscle activity exceeded established thresholds with the greatest risk occurring during insertion. An endoscope support device reduced loads to the left wrist extensors.
Subject(s)
Forearm , Musculoskeletal Diseases , Adult , Colonoscopy , Electromyography , Female , Humans , Male , Musculoskeletal Diseases/etiology , Risk FactorsABSTRACT
GOAL: We sought to quantify the independent effects of age, sex, and race/ethnicity on risk of colorectal cancer (CRC) and advanced neoplasia (AN) in Veterans. STUDY: We conducted a retrospective, cross-sectional study of Veterans aged 40 to 80 years who had diagnostic or screening colonoscopy between 2002 and 2009 from 1 of 14 Veterans Affairs Medical Centers. Natural language processing identified the most advanced finding and location (proximal, distal). Logistic regression was used to examine the adjusted, independent effects of age, sex, and race, both overall and in screening and diagnostic subgroups. RESULTS: Among 90,598 Veterans [mean (SD) age 61.7 (9.4) y, 5.2% (n=4673) were women], CRC and AN prevalence was 1.3% (n=1171) and 8.9% (n=8081), respectively. Adjusted CRC risk was higher for diagnostic versus screening colonoscopy [odds ratio (OR)=3.79; 95% confidence interval (CI), 3.19-4.50], increased with age, was numerically (but not statistically) higher for men overall (OR=1.53; 95% CI, 0.97-2.39) and in the screening subgroup (OR=2.24; 95% CI, 0.71-7.05), and was higher overall for Blacks and Hispanics, but not in screening. AN prevalence increased with age, and was present in 9.2% of men and 3.9% of women [adjusted OR=1.90; 95% CI, 1.60-2.25]. AN risk was 11% higher in Blacks than in Whites overall (OR=1.11; 95% CI, 1.04-1.20), was no different in screening, and was lower in Hispanics (OR=0.74; 95% CI, 0.55-0.98). Women had more proximal CRC (63% vs. 39% for men; P=0.03), but there was no difference in proximal AN (38.3% for both genders). CONCLUSIONS: Age and race were associated with AN and CRC prevalence. Blacks had a higher overall prevalence of both CRC and AN, but not among screenings. Men had increased risk for AN, while women had a higher proportion of proximal CRC. These findings may be used to tailor when and how Veterans are screened for CRC.
Subject(s)
Colorectal Neoplasms , Veterans , Colorectal Neoplasms/diagnosis , Colorectal Neoplasms/epidemiology , Cross-Sectional Studies , Ethnicity , Female , Humans , Male , Middle Aged , Prevalence , Retrospective Studies , Risk FactorsABSTRACT
BACKGROUND AND AIMS: Gastroenterology fellowships need to ensure that trainees achieve competence in upper endoscopy (EGD) and colonoscopy. Because the impact of structured feedback remains unknown in endoscopy training, this study compared the effect of structured feedback with standard feedback on trainee learning curves for EGD and colonoscopy. METHODS: In this multicenter, cluster, randomized controlled trial, trainees received either individualized quarterly learning curves or feedback standard to their fellowship. Assessment was performed in all trainees using the Assessment of Competency in Endoscopy tool on 5 consecutive procedures after every 25 EGDs and colonoscopies. Individual learning curves were created using cumulative sum (CUSUM) analysis. The primary outcome was the mean CUSUM score in overall technical and overall cognitive skills. RESULTS: In all, 13 programs including 132 trainees participated. The intervention arm (6 programs, 51 trainees) contributed 558 EGD and 600 colonoscopy assessments. The control arm (7 programs, 81 trainees) provided 305 EGD and 468 colonoscopy assessments. For EGD, the intervention arm (-.7 [standard deviation {SD}, 1.3]) had a superior mean CUSUM score in overall cognitive skills compared with the control arm (1.6 [SD, .8], P = .03) but not in overall technical skills (intervention, -.26 [SD, 1.4]; control, 1.76 [SD, .7]; P = .06). For colonoscopy, no differences were found between the 2 arms in overall cognitive skills (intervention, -.7 [SD, 1.3]; control, .7 [SD, 1.3]; P = .95) or overall technical skills (intervention, .1 [SD, 1.5]; control, -.1 [SD, 1.5]; P = .77). CONCLUSIONS: Quarterly feedback in the form of individualized learning curves did not affect learning curves for EGD and colonoscopy in a clinically meaningful manner. (Clinical trial registration number: NCT02891304.).
Subject(s)
Learning Curve , Clinical Competence , Colonoscopy , Feedback , Gastroenterology/education , HumansABSTRACT
The current endoscope design is not ergonomic. There is a high prevalence of endoscopy-related injury reported in the literature, and studies have demonstrated high-risk biomechanical exposures during the performance of routine colonoscopy. Endoscopy ergonomics focuses on understanding the endoscopist's interaction with the endoscope and the endoscopy unit and re-designing these tasks to minimize the risk of endoscopy-related injury. The discussion to date has focused on what the endoscopist can do to minimize his or her risk of injury. It is imperative that we re-frame that discussion because the implication that physicians are responsible for implementing personal or workplace interventions places an undue burden on physicians and will be the least effective exposure control method. Endoscope companies need to consider the endoscopist in their design process. As a profession, we need to collectively advocate for endoscopist safety. We offer a perspective on how ergonomic endoscopy can become a realistic and achievable goal.
Subject(s)
Endoscopy , Ergonomics , Musculoskeletal Diseases/prevention & control , Occupational Diseases/prevention & control , Humans , Musculoskeletal Diseases/etiology , Occupational Diseases/etiology , PostureABSTRACT
BACKGROUND AND AIMS: Polyps <1 cm are the most commonly found polyps during colonoscopy. Cold snare removal is preferred given the significantly higher rate of incomplete resection associated with piecemeal biopsy forceps resection. There are currently no standardized tools to assess competence in cold snare polypectomy. This study aimed to develop and validate a cold snare polypectomy assessment tool (CSPAT). METHODS: Experts in cold snare polypectomy used a Delphi method to develop the CSPAT. Metrics with a greater than 85% agreement as being "important" or "very important" were included in the CSPAT. The tool included evaluation of polyp inspection, positioning, appropriate ensnarement of tissue to ensure a rim of normal tissue, tissue retrieval, and postpolypectomy site inspection. Experts in cold snare polypectomy used the CSPAT to evaluate preselected videos that were previously evaluated using the Direct Observation of Polypectomy Skills (DOPyS) tool. Interobserver agreement was evaluated. CSPAT scores were compared with DOPyS scores to assess content validity. RESULTS: Sixteen experts developed the 12-item CSPAT, and 13 experts reviewed 55 videos. There was a moderate degree of agreement in 10 metrics (κ = .52-.59) and a substantial degree of agreement (κ = .61-.63) in the other 2. There was a strong correlation between the mean of individual metrics 1 to 12 compared with the global competence assessment (ρ = .88, P < .001). There was a moderate correlation between the average overall DOPyS score and the overall CSPAT competence score (ρ = .56, P < .001). CONCLUSIONS: We have developed and validated a customized CSPAT that can be easily applied to video-based assessments to assess competence in training and among practicing endoscopists.
Subject(s)
Colonic Polyps/surgery , Colonoscopy/standards , Quality Assurance, Health Care/methods , Clinical Competence , Delphi Technique , Humans , Video RecordingSubject(s)
Endoscopy, Gastrointestinal , Ergonomics , Humans , Faculty , Fellowships and ScholarshipsABSTRACT
BACKGROUND AND AIMS: Balancing the risks for thromboembolism and postpolypectomy bleeding in patients requiring anticoagulation and antiplatelet agents is challenging. We investigated the incidence and risk factors for postpolypectomy bleeding on anticoagulation, including heparin bridge and other antithrombotic therapy. METHODS: We performed a retrospective cohort and case control study at 2 tertiary-care medical centers from 2004 to 2012. Cases included male patients on antithrombotics with hematochezia after polypectomy. Nonbleeding controls were matched to cases 3 to 1 by antithrombotic type, study site, polypectomy technique, and year of procedure. Our outcomes were the incidence and risk factors for postpolypectomy bleeding. RESULTS: There were 59 cases and 174 matched controls. Postpolypectomy bleeding occurred in 14.9% on bridge anticoagulation. This was significantly higher than the overall incidence of bleeding on antithrombotics at 1.19% (95% confidence interval, 0.91%-1.54%) (59/4923). We identified similarly low rates of bleeding in patients taking warfarin (0.66%), clopidogrel (0.84%), and aspirin (0.92%). Patients who bled tended to have larger polyps (13.9 vs 7.3 mm; P < .001) and more polyps ≥2 cm (41% vs 10%; P < .001). Bleeding risk was increased with restarting antithrombotics within 1 week postpolypectomy (odds ratio [OR] 4.50; P < .001), having polyps ≥2 cm (OR 5.94; P < .001), performing right-sided cautery (OR 2.61; P = .004), and having multiple large polyps (OR 2.92; P = .001). Among patients on warfarin, the presence of bridge anticoagulation was an independent risk factor for postpolypectomy bleeding (OR 12.27; P = .0001). CONCLUSION: We conclude that bridge anticoagulation is associated with a high incidence of postpolypectomy bleeding and is an independent risk factor for hemorrhage compared with patients taking warfarin alone. A higher threshold to use bridge anticoagulation should be considered in patients with an elevated bleeding risk.
Subject(s)
Colonic Polyps/surgery , Colorectal Neoplasms/surgery , Gastrointestinal Hemorrhage/epidemiology , Platelet Aggregation Inhibitors/therapeutic use , Postoperative Hemorrhage/epidemiology , Aged , Anticoagulants/therapeutic use , Aspirin/therapeutic use , Case-Control Studies , Clopidogrel , Colonic Polyps/pathology , Colonoscopy , Colorectal Neoplasms/pathology , Female , Gastrointestinal Hemorrhage/etiology , Heparin, Low-Molecular-Weight/therapeutic use , Humans , Incidence , Male , Middle Aged , Postoperative Hemorrhage/etiology , Retrospective Studies , Risk Factors , Thromboembolism/prevention & control , Ticlopidine/analogs & derivatives , Ticlopidine/therapeutic use , Time Factors , Warfarin/therapeutic useABSTRACT
BACKGROUND AND AIMS: Since 1985, the American Society for Gastrointestinal Endoscopy (ASGE) has awarded grants for endoscopic-related research. The goals of this study were to examine trends in ASGE grant funding and to assess productivity of previous recipients of the ASGE grant awards. METHODS: This was a retrospective cohort analysis of all research grants awarded by the ASGE through 2009. Measures of academic productivity and self-assessment of the ASGE awards' impact on the recipients' careers were defined by using publicly available resources (eg, National Library of Medicine-PubMed) and administration of an electronic survey to award recipients. RESULTS: The ASGE awarded 304 grants totaling $12.5 million to 214 unique awardees. Funding increased 7.5-fold between 1985 and 1989 (mean $102,000/year) and between 2005 and 2009 (mean $771,000/year). The majority of awardees were men (83%), were at or below the level of assistant professor (82%), with a median of 3 years of postfellowship experience at the time of the award, and derived from a broad spectrum of institutions as measured by National Institutes of Health funding rank (median 26, interquartile range [IQR] 12-64). Nineteen percent had a master's degree in a research-related field. Awardees' median publications per year increased from 3.5 (IQR 1.2-9.0) before funding to 5.7 (IQR 1.8-9.5) since funding; P = .04, and median h-index scores increased from 3 (IQR 1-8) to 17 (IQR 8-26); P < .001. Multivariate analysis found that the presence of a second advanced degree (eg, masters or doctorate) was independently predictive of high productivity (odds ratio [OR] 2.92; 95% confidence interval [CI], 1.09-7.81). Among 212 unique grant recipients, 82 (40%) completed the online survey. Of the respondents, median peer-reviewed publications per year increased from 3.4 (IQR 1.9-5.5) to 4.5 (IQR 2.0-9.5); P = .17. Ninety-one percent reported that the ASGE grant had a positive or very positive impact on their careers, and 85% of respondents are currently practicing in an academic environment. Most of the grants resulted in at least 1 peer-reviewed publication (67% per Internet-based search and 81% per survey). CONCLUSIONS: The ASGE research program has grown considerably since 1985, with the majority of grants resulting in at least 1 grant-related publication. Overall academic productivity increased after the award, and the majority of awardees report a positive or very positive impact of the award on their careers. Medical professional societies are an important sponsor of clinical research.
Subject(s)
Biomedical Research , Gastroenterology , Research Support as Topic , Cohort Studies , Efficiency , Endoscopy, Gastrointestinal , Female , Humans , Male , National Institutes of Health (U.S.) , Publishing , Research Personnel , Retrospective Studies , Societies, Medical , United StatesSubject(s)
Coronavirus Infections/prevention & control , Equipment Reuse , Infectious Disease Transmission, Patient-to-Professional/prevention & control , Pandemics/prevention & control , Pneumonia, Viral/prevention & control , Respiratory Protective Devices , Smoke , Betacoronavirus , COVID-19 , Cholangiopancreatography, Endoscopic Retrograde , Choledocholithiasis/surgery , Coronavirus Infections/transmission , Humans , Particle Size , Pneumonia, Viral/transmission , SARS-CoV-2 , Smell , Sphincterotomy, EndoscopicABSTRACT
BACKGROUND: An accurate system for tracking of colonoscopy quality and surveillance intervals could improve the effectiveness and cost-effectiveness of colorectal cancer (CRC) screening and surveillance. The purpose of this study was to create and test such a system across multiple institutions utilizing natural language processing (NLP). METHODS: From 42,569 colonoscopies with pathology records from 13 centers, we randomly sampled 750 paired reports. We trained (n=250) and tested (n=500) an NLP-based program with 19 measurements that encompass colonoscopy quality measures and surveillance interval determination, using blinded, paired, annotated expert manual review as the reference standard. The remaining 41,819 nonannotated documents were processed through the NLP system without manual review to assess performance consistency. The primary outcome was system accuracy across the 19 measures. RESULTS: A total of 176 (23.5%) documents with 252 (1.8%) discrepant content points resulted from paired annotation. Error rate within the 500 test documents was 31.2% for NLP and 25.4% for the paired annotators (P=0.001). At the content point level within the test set, the error rate was 3.5% for NLP and 1.9% for the paired annotators (P=0.04). When eight vaguely worded documents were removed, 125 of 492 (25.4%) were incorrect by NLP and 104 of 492 (21.1%) by the initial annotator (P=0.07). Rates of pathologic findings calculated from NLP were similar to those calculated by annotation for the majority of measurements. Test set accuracy was 99.6% for CRC, 95% for advanced adenoma, 94.6% for nonadvanced adenoma, 99.8% for advanced sessile serrated polyps, 99.2% for nonadvanced sessile serrated polyps, 96.8% for large hyperplastic polyps, and 96.0% for small hyperplastic polyps. Lesion location showed high accuracy (87.0-99.8%). Accuracy for number of adenomas was 92%. CONCLUSIONS: NLP can accurately report adenoma detection rate and the components for determining guideline-adherent colonoscopy surveillance intervals across multiple sites that utilize different methods for reporting colonoscopy findings.