CCRA: A colon cleanliness rating algorithm based on colonoscopy video analysis

Objective

A Colon Cleanliness Rating Algorithm (CCRA) based on colonoscopy image analysis is proposed in this paper, in order to solve the problem that the results of Colon Cleanliness (or Bowel Preparation Quality) rating caused by manual inspection are inconsistent.

Methods

Firstly, CCRA intercepts images from the colonoscopy video. Secondly, each colonoscopy image's stool area is segmented by U-Net to obtain the 2-classification segmentation results. Finally, the colon cleanliness is obtained by comparing the average area of the stool area with the standard proportion.

Results

After testing, the pixel accuracy of the U-Net model is 97.02 %, IoU is 83.67 %, accuracy is 92.17 %, recall is 90.21 %, F1-Score is 90.95 %. The accuracy of CCRA is 92.45 %-99.275.

Conclusion

The experimental results show that the CCRA proposed in this paper can quickly and accurately output the colon cleanliness rating of patients without manpower.

Effect of acuity level and patient characteristics on bowel preparation quality: a retrospective cohort study of inpatient colonoscopies

BACKGROUND AND AIMS

Colonoscopy is the primary method to detect mucosal abnormalities in the colon, rectum, and terminal ileum. Inadequate bowel preparation is a common problem and can impede successful visualization during colonoscopy. Although studies identified hospitalization as a predictor of inadequate bowel preparation, acuity of care vary greatly within this patient population. The current study aims to examine the effect of patient characteristics and care level predictors on inadequate bowel preparation quality within the inpatient setting.

METHODS

This retrospective study was conducted in a single urban level 1 trauma medical center and included adult patients undergoing diagnostic colonoscopy while admitted in the hospital from January 1, 2015 to June 30, 2020. We examined the level of inpatient care between the General Medical Floor (GMF), Intensive Care Units (ICU) and Telemetry Unit (TU) and assessed this association with bowel preparation quality, adjusting for known and unknown predictors.

RESULTS

Of 538 patients undergoing colonoscopy, 47.4% were admitted into TU, 43.7% into GMF and 8.9% into ICU. For the entire sample, 72.7% of patients achieved good or excellent preparation and quality of bowel preparation differed by care level (P = 0.01). Patients from the critical care units were less likely to achieve adequate bowel preparation when compared to GMF (Odds Ratio [OR] 0.36; 95% Confidence Interval [CI] 0.17,0.77), after adjusting for patient characteristics, medications, physical status, and preparation regimen. No significant difference in Bowel Preparation Quality (BPQ) was identified between patients from GMF and TU (OR 0.96; 95%CI 0.61, 1.52). Furthermore, adequate BPQ was associated with withdrawal time and cecal intubation, but not higher adenoma detection rates.

CONCLUSIONS

Results suggest the ICU setting is an independent predictor for inadequate bowel preparation and patients with prior opioid and laxative use may be more likely to have inadequate bowel preparation in the hospital. Future interventions should prioritize preprocedural clinician meetings for critical care unit patients, including a more detailed readiness assessment and thorough medication history.

Quality of colonoscopy performed by medical or surgical specialists and trainees in five Australian hospitals

BACKGROUND

Ensuring colonoscopy procedure quality is vital to the success of screening and surveillance programmes for bowel cancer in Australia. However, the data on the performance of quality metrics, through adequate adenoma detection, bowel preparation, and procedure completion rates, in the Australian public sector is limited. Understanding these can inform quality improvement to further strengthen our capacity for prevention and early detection of colorectal cancer.

AIM

To determine the quality of colonoscopy in Australian teaching hospitals and their association with proceduralist specialty, trainee involvement, and location.

METHODS

We retrospectively evaluated 2443 consecutive colonoscopy procedure reports from 1 January to 1 April, 2018 from five public teaching tertiary hospitals in Australia (median 60 years old, 49% male). Data for bowel preparation quality, procedure completion rates, and detection rates of clinically significant adenomas, conventional adenomas, and serrated lesions was collected and compared to national criteria for quality in colonoscopy. Participating hospital, proceduralist specialty, and trainee involvement indicators were used for stratification. Data was analysed using Chi-squared tests of independence, Mann-Whitney U, One-way ANOVA, and multivariate binary logistic regression.

RESULTS

Fifty-two point two percent (n = 1276) and 43.3% (n = 1057) were performed by medical and surgical proceduralists respectively, whilst 29.8% (n = 728) involved a trainee. Inadequate bowel preparation affected 7.3% of all procedures. The procedure completion rate was 95.1%, which increased to 97.5% after adjustment for bowel preparation quality. The pooled cancer, adenoma, and serrated lesion detection rates for all five hospitals were 3.5%, 40%, and 5.9% respectively. Assessed hospitals varied significantly by patient age (P < 0.001), work-force composition (P < 0.001), adequacy of bowel preparation (P < 0.001), and adenoma detection rate (P < 0.001). Two hospitals (40%) did not meet all national criteria for quality, due to a procedure completion rate of 94.5% or serrated lesion detection rate of 2.6%. Although lower than the other hospitals, the difference was not significant. Compared with surgical specialists, procedures performed by medical specialists involved older patients [65 years (inter-quartile range, IQR 58-73) vs 64 years (IQR 56-71); P = 0.04] and were associated with a higher adenoma detection rate [odds ratio (OR) 1.53; confidence interval: 1.21-1.94; P < 0.001]. Procedures involving trainee proceduralists were not associated with differences in the detection of cancer, adenoma, or serrated lesions, compared with specialists, or according to their medical or surgical background. On multivariate analysis, cancer detection was positively associated with patient age (OR 1.04; P < 0.001) and negatively associated with medical compared to surgical proceduralists (OR 0.54; P = 0.04). Conventional adenoma detection rates were independently associated with increasing patient age (OR 1.04; P < 0.001), positively associated with medical compared to surgical proceduralists (OR 1.41; P = 0.002) and negatively associated with male gender (OR 0.53; P < 0.001).

CONCLUSION

Significant differences in the quality of colonoscopy in Australia exist, even when national benchmarks are achieved. The role of possible contributing factors, like procedural specialty and patient gender need further evaluation.

Endoscopic Disease Activity and Biologic Therapy Are Independent Predictors of Suboptimal Bowel Preparation in Patients with Inflammatory Bowel Disease Undergoing Colonoscopy

BACKGROUND AND AIMS

Optimal bowel preparation (BP) is critical for endoscopic assessment of inflammation and dysplasia in patients with inflammatory bowel disease (IBD). Comorbidities and patient-related factors have been associated with suboptimal BP (SOBP) in the general population. We sought to identify disease-specific characteristics that may impact the quality of BP in patients with IBD.

METHODS

We conducted a retrospective analysis of adult IBD patients who underwent outpatient colonoscopies between January 2014 and September 2020 at a large academic medical center. Quality of BP was documented using the Boston Bowel Preparation Scale (BBPS) or the Aronchick scale and dichotomized into "suboptimal" (BBPS 0-5 or Aronchick "fair," "poor," unsatisfactory") and "optimal" (BBPS 6-9 or Aronchick "excellent," "good"). IBD-specific and other factors associated with SOBP were evaluated using logistic regression analyses.

RESULTS

Among a total of 395 IBD patients [54% males, mean age 40 years, 63% with Crohn's disease (CD), 35% with ulcerative colitis (UC)], 24.8% had SOBP. On multivariable analysis, moderate-to-severe endoscopic disease vs mild or inactive disease was associated with a higher odds of SOBP [adjusted OR 2.7(95% CI 1.52-4.94)], whereas baseline biologic use was associated with a lower odds of SOBP [aOR 0.24(0.09-0.65)] among the overall IBD cohort. Additionally, age > 65 years [aOR 2.99(1.19-7.54)] and single-dose vs split-dose BP [aOR 2.37(1.43-3.95)] were predictors of SOBP. In the subgroup analysis by IBD type, moderate-to-severe endoscopic disease predicted SOBP among both CD and UC cohorts.

CONCLUSION

Endoscopic disease activity was predictive of SOBP, and biologic therapy was protective against SOBP among IBD patients.

Comparative Effectiveness of Commercial Bowel Preparations in Ambulatory Patients Presenting for Screening or Surveillance Colonoscopy

BACKGROUND

Inadequate bowel preparation (IBP) is associated with reduced adenoma detection. However, limited research has examined the impact of different commercial bowel preparations (CBPs) on IBP and adenoma detection. We aim to determine whether type of CBP used is associated with IBP or adenoma detection.

METHODS

We retrospectively evaluated outpatient, screening or surveillance colonoscopies performed in the Cleveland Clinic health system between January 2011 and June 2017. IBP was defined by the Aronchick scale. Multilevel mixed-effects logistic regression was performed to assess the association between CBP type and IBP and adenoma detection. Fixed effects were defined as demographics, comorbidities, medication use, and colonoscopy factors. Random effect of individual endoscopist was considered.

RESULTS

Of 153,639 colonoscopies, 75,874 records met inclusion criteria. Median age was 54; 50% were female; 17.7% had IBP, and adenoma detection rate was 32.6%. In adjusted analyses, compared to GoLYTELY, only NuLYTELY [OR 0.66 (95% CI 0.60, 0.72)] and SuPREP [OR 0.53 (95% CI 0.40, 0.69)] were associated with reduced IBP. Adenoma detection did not vary based on the type of bowel preparation used.

CONCLUSIONS

Among patients referred for screening or surveillance colonoscopy, choice of CBP was not associated with adenoma detection. Decisions about CBP should be based on other factors, such as tolerability, cost, or safety.

Does It work in Clinical Practice? A Comparison of Colonoscopy Cleansing Effectiveness in Clinical Practice Versus Efficacy from Selected Prospective Trials

Background

Adequate bowel preparation is essential for a high-quality colonoscopy. Many randomized controlled trials (RCTs) have investigated bowel preparation protocols, including split-dose and low-volume regimens. However, RCTs are conducted in an ideal, controlled setting, and translation of trial results to clinical practice is challenging. In this study, we compared the quality of bowel preparations of real-world patients from clinical practice with those enrolled in several prospective trials.

Methods

Bowel preparation quality, defined by the Ottawa Bowel Preparation Scale (OBPS), from four RCTs and one prospective trial were compared with two observational diary studies. Bowel preparations were polyethylene glycol preparation (PEG) or sodium picosulfate plus magnesium citrate (P/MC) taken via traditional or split-dose timing regimen. Age, sex, average number of bowel movements per day, comorbidities, colonoscopy indication and colonoscopy completion rates were also collected.

Results

Patients enrolled in prospective trials had a better OBPS by one point when compared with those in observational clinical practice studies (P<0.049), after controlling for age, sex, colonoscopy indication and type of bowel preparation used. We also found that each 10-year increase in age was associated with a 0.2 point increase in OBPS (P=0.008), and men were associated with a 0.5 increase in OBPS when compared with women P=0.014).

Conclusion

Patients from clinical practice have higher OBPS than prospective trial patients. Increased age and male sex were also associated with increased OBPS. We believe increased patient motivation and education around bowel preparation regimen plays an important role in the success of bowel preparations.

Withdrawal time in excellent or very poor bowel preparation qualities

AIM: To evaluate association(s) between withdrawal time and polyp detection in various bowel preparation qualities.

METHODS: Retrospective cohort analysis of screening colonoscopies performed between January 2005 and June 2011 for patients with average risk of colorectal cancer. Exclusion criteria included patients with a personal history of adenomatous polyps or colon cancer, prior colonic resection, significant family history of colorectal cancer, screening colonoscopy after other abnormal screening tests such as flexible sigmoidoscopy or barium enema, and screening colonoscopies during in-patient care. All procedures were performed or directly supervised by gastroenterologists. Main measurements were number of colonic segments with polyps and total number of colonic polyps.

RESULTS: Multivariate analysis of 8331 colonoscopies showed longer withdrawal time was associated with more colonic segments with polyps in good (adjusted OR = 1.16; 95%CI: 1.13-1.19), fair (OR = 1.13; 95%CI: 1.10-1.17), and poor (OR = 1.18; 95%CI: 1.11-1.26) bowel preparation qualities. A higher number of total polyps was associated with longer withdrawal time in good (OR = 1.15; 95%CI: 1.13-1.18), fair (OR = 1.13; 95%CI: 1.10-1.16), and poor (OR = 1.20; 95%CI: 1.13-1.29) bowel preparation qualities. Longer withdrawal time was not associated with more colonic segments with polyps or greater number of colonic polyps in bowel preparations with excellent (OR = 1.07, 95%CI: 0.99-1.26; OR = 1.11, 95%CI: 0.99-1.24, respectively) and very poor (OR = 1.02, 95%CI: 0.99-1.12; OR = 1.05, 95%CI: 0.99-1.10, respectively) qualities.

CONCLUSION: Longer withdrawal time is not associated with higher polyp number detected in colonoscopies with excellent or very poor bowel preparation quality.