Annual colonoscopy volume and maintenance of competency for surgeons

Assessment of colonoscopy skill using machine learning to measure quality: Proof-of-concept and initial validation

Background and study aims Low-quality colonoscopy increases cancer risk but measuring quality remains challenging. We developed an automated, interactive assessment of colonoscopy quality (AI-CQ) using machine learning (ML). Methods Based on quality guidelines, metrics selected for AI development included insertion time (IT), withdrawal time (WT), polyp detection rate (PDR), and polyps per colonoscopy (PPC). Two novel metrics were also developed: HQ-WT (time during withdrawal with clear image) and WT-PT (withdrawal time subtracting polypectomy time). The model was pre-trained using a self-supervised vision transformer on unlabeled colonoscopy images and then finetuned for multi-label classification on another mutually exclusive colonoscopy image dataset. A timeline of video predictions and metric calculations were presented to clinicians in addition to the raw video using a web-based application. The model was externally validated using 50 colonoscopies at a second hospital. Results The AI-CQ accuracy to identify cecal intubation was 88%. IT ( P = 0.99) and WT ( P = 0.99) were highly correlated between manual and AI-CQ measurements with a median difference of 1.5 seconds and 4.5 seconds, respectively. AI-CQ PDR did not significantly differ from manual PDR (47.6% versus 45.5%, P = 0.66). Retroflexion was correctly identified in 95.2% and number of right colon evaluations in 100% of colonoscopies. HQ-WT was 45.9% of, and significantly correlated with ( P = 0.85) WT time. Conclusions An interactive AI assessment of colonoscopy skill can automatically assess quality. We propose that this tool can be utilized to rapidly identify and train providers in need of remediation.

Pediatric Endoscopy Quality Improvement Network Quality Standards and Indicators for Pediatric Endoscopists and Endoscopists in Training: A Joint NASPGHAN/ESPGHAN Guideline

INTRODUCTION

High-quality pediatric endoscopy requires reliable performance of procedures by competent individual providers who consistently uphold all standards determined to assure optimal patient outcomes. Establishing consensus expectations for ongoing monitoring and assessment of individual pediatric endoscopists is a method for confirming the highest possible quality of care for such procedures worldwide. We aim to provide guidance to define and measure quality of endoscopic care for children.

METHODS

With support from the North American and European Societies of Pediatric Gastroenterology Hepatology and Nutrition (NASPGHAN and ESPGHAN), an international working group of the Pediatric Endoscopy Quality Improvement Network (PEnQuIN) used the methodological strategy of the Appraisal of Guidelines for REsearch and Evaluation (AGREE) II instrument to develop standards and indicators relevant for assessing the quality of endoscopists. Consensus was sought via an iterative online Delphi process and finalized at an in-person conference. The quality of evidence and strength of recommendations were rated according to the GRADE (Grading of Recommendation Assessment, Development, and Evaluation) approach.

RESULTS

The PEnQuIN working group achieved consensus on 6 standards that all providers who perform pediatric endoscopy should uphold and 2 standards for pediatric endoscopists in training, with 7 corresponding indicators that can be used to identify high-quality endoscopists. Additionally, these can inform continuous quality improvement at the provider level. Minimum targets for defining high-quality pediatric ileocolonoscopy were set for 2 key indicators: cecal intubation rate (≥90%) and terminal ileal intubation rate (≥85%).

DISCUSSION

It is recommended that all individual providers performing or training to perform pediatric endoscopy initiate and engage with these international endoscopist-related standards and indicators developed by PEnQuIN.

Trends in spatial access to colonoscopy in South Carolina, 2000-2014

BACKGROUND

Colonoscopy use has increased since Medicare began covering screening for average-risk persons. Our objective was to describe changes in spatial access to colonoscopy in South Carolina (SC) between 2000 and 2014.

METHODS

Using data from the SC Ambulatory Surgery Database, we created annual ZIP Code Tabulation Area (ZCTA) spatial accessibility scores. We assessed changes in accessibility, colonoscopy supply, and potential demand, overall and by metropolitan designation. Spatial clustering was also explored.

RESULTS

Spatial accessibility decreased across both small rural and metropolitan ZCTAs but was significantly higher in metropolitan areas during the first part of the study period . The proportion of persons with no access to colonoscopy within 30 min increased over time but was consistently higher in small rural areas. Clusters of low accessibility grew over time.

CONCLUSIONS

The supply of colonoscopy facilities decreased relative to the potential demand, and clusters of low access increased, indicating a contraction of services.

Assessment of quality benchmarks in adenoma detection in Mexico

Background and study aims  Several Latin American countries, including Mexico, have reported an increase in colorectal cancer (CRC) mortality. The effectiveness of a colonoscopy in preventing CRC depends on the quality of the procedure, for which the adenoma detection rate (ADR) is one of the most trusted indicators. Awareness of ADR can improve the quality of colonoscopies through proper feedback and training of the specialists. The goal of this study was to estimate the ADR among Mexican endoscopists with experience in CRC screening and to compare it with previously reported data from this country. Methods  We carried out a retrospective study to analyze ADR data in Mexico. The information was obtained from a group of certified endoscopists and compared with the former published data from Mexico. Results  We found a current ADR of 24.6 % (95 %CI, 22.4 %-26.8 %) from 1,478 colonoscopies performed by eight endoscopists in two third-level private hospitals. The average ADR reported in previous publications was 15.2 % (95 %CI, 13.3 %-17.1 %). Statistical analysis showed differences between our results and those from previous studies (24.6 % vs. 15.2 %, P  < 0.001). Conclusions  The actual ADR in Mexico is higher than previously reported. Previous low ADR values could be explained by poorly performed colonoscopies rather than by low adenoma and CRC incidence in our country.

Rural Standards and the Quality Equation

The article describes the barriers rural surgeons face when attempting to measure, analyze, and benchmark the quality and value of the care they provide for their patients. Examples of suboptimal care are presented as well as special geographic and resource-related circumstances for many of these disparities of care. The article includes in-depth descriptions of the American College of Surgeons (ACS) Optimal Resources for Surgical Quality and Safety Program and the ACS Rural Hospital Surgical Verification and Quality Improvement Program. The article concludes by discussing several documented clinical, economic, and social advantages of keeping surgical care local.

Effect of an educational intervention on colonoscopy quality outcomes

BACKGROUND

We aimed to assess the effect of a colonoscopy skills improvement (CSI) course on quality indicators at our institution.

METHODS

This retrospective cohort study included ten surgeons and nine gastroenterologists practicing in a tertiary referral center who had undergone CSI training between 2014 and 2015. Procedural data for 50 colonoscopies by each physician was collected immediately before and after CSI training, and again 8 months after training. The primary outcome was adenoma detection rate (ADR) and secondary outcomes included colonoscopy completion rate (CCR), and withdrawal time (WT). Univariate analysis followed by stepwise multivariable logistic regression was performed to assess for predictors of these outcomes. These variables included patient age, gender, indication for colonoscopy, quality of bowel preparation, and CSI training.

RESULTS

2533 colonoscopies were included. There was no improvement in ADR for the entire group immediately after training and at 8 months (31.8% vs. 33.6% vs. 35.3%, p = 0.319). In subgroup analysis, the ADR of surgeons improved non-significantly immediately after completing the course and increased further at 8 months (30.9% vs. 31.6% vs. 37.6%, p = 0.065). The same changes were not observed for the gastroenterology subgroup (32.9% vs. 36.0% vs. 32.8%, p = 0.550). No change was noted in CCR or WT. In multivariate analysis of the surgical subgroup, increased patient age, male gender, and the 8-month time point following CSI training were associated with higher ADR.

CONCLUSION

CSI training is associated with an improvement in ADR for surgeons at our institution.

Colonoscopy education for surgical residents in Korea: a national survey of Korean Surgical Skill Study Group

Purpose

A standardized colonoscopy training program surgical residents is still unestablished. The aim of this study was to assess the current status of colonoscopy training for surgical residents and collect the opinions on the direction for future colonoscopy education.

Methods

A questionnaire survey containing 24 items was conducted by sending an email to 310 colorectal surgeons in 84 training hospitals across the country.

Results

One hundred fifteen staff surgeons (115 of 310, 37%) of 84 institutions returned fully completed questionnaires. Most surgeons were working at tertiary hospitals with more than 5 years of clinical experience. About half of the responding surgeons answered that they perform colonoscopy in clinical practice and the main purpose of colonoscopy was follow-up after colorectal resection. Only 9 of 84 hospitals (10.7%) had a regular program on colonoscopy training for surgical residents. Most of colonoscopy education was conducted irregularly in a form of staff lecture, conferences or hands-on workshops. According to the future directions, 72 of 115 surgeons (62.6%) answered judging competency in colonoscopy should be needed for professional qualification of the surgeon. About 50 cases of colonoscopy seem appropriate during the 4-year-training of surgical residency, especially during the third- and fourth-year.

Conclusion

This survey shows colonoscopy education for surgical residents is still insufficient in Korea and that most surgeons feel that regular colonoscopy training is needed during the surgical residency period. There needs to be efforts to standardize the education program as well as various institutional and academic societal supports to achieve this goal.

Proximal Sessile Serrated Adenomas Are More Prevalent in Caucasians, and Gastroenterologists Are Better Than Nongastroenterologists at Their Detection

BACKGROUND AND AIM

Proximal sessile serrated adenomas (PSSA) leading to colorectal cancer (CRC) represent an alternate pathway for CRC development. In this study, we aim to determine the prevalence of PSSAs and the impact of patient, colonoscopy, and endoscopist-related factors on PSSA detection.

METHODS

Patients ≥ 50 years of age undergoing a screening colonoscopy between 2012 and 2014 were included. Detection rates based on patient gender, race, colonoscopy timing, fellow participation, bowel preparation quality, and specialty of the endoscopist were calculated. t-tests were used to compare detection rates and a multivariate-adjusted analysis was performed.

RESULTS

140 PSSAs were detected from 4151 colonoscopies, with a prevalence of 3.4%. Detection rate was higher in Caucasians compared to African-Americans (AA) (3.7 ± 4.1 versus 0.96 ± 3.5; p < 0.001). Gastroenterologists detected more PSSAs compared to nongastroenterologists (3.9 ± 3.5 versus 2.2 ± 3.0; p = 0.028). These findings were still significant after adjusted multivariate analysis. The rest of the factors did not make significant difference in PSSA detection rate.

CONCLUSIONS

PSSAs are more prevalent in Caucasians compared to AAs. Racial difference in prevalence of PSSAs is intriguing and warrants further investigation. Gastroenterologists have a significantly higher PSSADR compared to nongastroenterologists. Educational measures should be implemented in nongastroenterologists to improve their PSSA detection rates.