Performance of Computer-Aided Detection and Quality of Bowel Preparation: A Comprehensive Analysis of Colonoscopy Outcomes.

BACKGROUND: Artificial intelligence (AI) has emerged as a promising tool for detecting and characterizing colorectal polyps during colonoscopy, offering potential enhancements in traditional colonoscopy procedures to improve outcomes in patients with inadequate bowel preparation. AIMS: This study aimed to assess the impact of an AI tool on computer-aided detection (CADe) assistance during colonoscopy in this population. METHODS: This case-control study utilized propensity score matching (PSM) for age, sex, race, and colonoscopy indication to analyze a database of patients who underwent colonoscopy at a single tertiary referral center between 2017 and 2023. Patients were excluded if the procedure was incomplete or aborted owing to poor preparation. The patients were categorized based on the use of AI during colonoscopy. Data on patient demographics and colonoscopy performance metrics were collected. Univariate and multivariate logistic regression models were used to compare the groups. RESULTS: After PSM patients with adequately prepped colonoscopies (n = 1466), the likelihood of detecting hyperplastic polyps (OR = 2.0, 95%CI 1.7-2.5, p < 0.001), adenomas (OR = 1.47, 95%CI 1.19-1.81, p < 0.001), and sessile serrated polyps (OR = 1.90, 95%CI 1.20-3.03, p = 0.007) significantly increased with the inclusion of CADe. In inadequately prepped patients (n = 160), CADe exhibited a more pronounced impact on the polyp detection rate (OR = 4.34, 95%CI 1.6-6.16, p = 0.049) and adenomas (OR = 2.9, 95%CI 2.20-8.57, p < 0.001), with a marginal increase in withdrawal and procedure times. CONCLUSION: This study highlights the significant improvement in detecting diminutive polyps (< 5 mm) and sessile polyps using CADe, although notably, this benefit was only seen in patients with adequate bowel preparation. In conclusion, the integration of AI in colonoscopy, driven by artificial intelligence, promises to significantly enhance lesion detection and diagnosis, revolutionize the procedure's effectiveness, and improve patient outcomes.

Artificial Intelligence for Real-Time Prediction of the Histology of Colorectal Polyps by General Endoscopists.

BACKGROUND: Real-time prediction of histologic features of small colorectal polyps may prevent resection and/or pathologic evaluation and therefore decrease colonoscopy costs. Previous studies showed that computer-aided diagnosis (CADx) was highly accurate, though it did not outperform expert endoscopists. OBJECTIVE: To assess the diagnostic performance of histologic predictions by general endoscopists before and after assistance from CADx in a real-life setting. DESIGN: Prospective, multicenter, single-group study. (ClinicalTrials.gov: NCT04437615). SETTING: 6 centers across the United States. PARTICIPANTS: 1252 consecutive patients undergoing colonoscopy and 49 general endoscopists with variable experience in real-time prediction of polyp histologic features. INTERVENTION: Real-time use of CADx during routine colonoscopy. MEASUREMENTS: The primary end points were the sensitivity and specificity of CADx-unassisted and CADx-assisted histologic predictions for adenomas measuring 5 mm or less. For clinical purposes, additional estimates according to location and confidence level were provided. RESULTS: The CADx device made a diagnosis for 2695 polyps measuring 5 mm or less (96%) in 1252 patients. There was no difference in sensitivity between the unassisted and assisted groups (90.7% vs. 90.8%; P = 0.52). Specificity was higher in the CADx-assisted group (59.5% vs. 64.7%; P < 0.001). Among all 2695 polyps measuring 5 mm or less, 88.2% and 86.1% (P < 0.001) in the CADx-assisted and unassisted groups, respectively, could be resected and discarded without pathologic evaluation. Among 743 rectosigmoid polyps measuring 5 mm or less, 49.5% and 47.9% (P < 0.001) in the CADx-assisted and unassisted groups, respectively, could be left in situ without resection. LIMITATION: Decision making based on CADx might differ outside a clinical trial. CONCLUSION: CADx assistance did not result in increased sensitivity of optical diagnosis. Despite a slight increase, the specificity of CADx-assisted diagnosis remained suboptimal. PRIMARY FUNDING SOURCE: Olympus America Corporation served as the clinical study sponsor.

Optical diagnosis of colorectal polyps using novel blue light imaging classification among trainee endoscopists.

BACKGROUND: Blue light imaging (BLI) has been shown to improve the characterization of colorectal polyps among the endoscopy experts. We aimed to determine if this technology could be taught to endoscopy trainees while maintaining high accuracy and interobserver agreement. METHODS: Twenty-one gastroenterology trainees (fellows) from two academic institutions participated in this prospective study. Each trainee completed a web-based learning comprising four modules: pre-test, didactic videos explaining the BLI Adenoma Serrated International Classification (BASIC), interactive examples, and post-test assessment. The pre- and post-test modules consisted of reviewing video images of colon polyps in high definition white light imaging and BLI and then applying the BASIC classification to determine if the polyps were likely to be adenomatous. Confidence in adenoma identification (rated '1' to '5'), accuracy in polyp (adenoma vs. non-adenoma) identification, and agreement in characterization per BASIC criteria were derived. RESULTS: Trainee accuracy in the adenoma diagnosis improved from 74.7% (pre-test) to 85.4% (post-test) (P < 0.01). There was a trend towards higher accuracy in polyp characterization with subsequent years of training (1st year fellows 77.4%, 2nd year 88.5%, and final year 94.0%) with consistent improvements after the e-learning across years of trainees. Overall, trainees were able to identify adenoma with a high sensitivity of 86.9%, specificity 83.9%, positive predictive value of 84.4%, and negative predictive value of 86.5%. However, their interobserver agreement in adenoma diagnosis was moderate (k = 0.52). CONCLUSION: The novel BLI classification can be easily taught to gastroenterology trainees using an online module and accuracy improves with years of training reaching >90% for colorectal polyp characterization.

Risk prediction rule for advanced neoplasia on screening colonoscopy for average-risk individuals.

BACKGROUND: In resource-limited countries, risk stratification can be used to optimize colorectal cancer screening. Few prospective risk prediction models exist for advanced neoplasia (AN) in true average-risk individuals. AIM: To create and internally validate a risk prediction model for detection of AN in average-risk individuals. METHODS: Prospective study of asymptomatic individuals undergoing first screening colonoscopy. Detailed characteristics including diet, exercise and medications were collected. Multivariate logistic regression was used to elucidate risk factors for AN (adenoma ≥1 cm, villous histology, high-grade dysplasia or carcinoma). The model was validated through bootstrapping, and discrimination and calibration of the model were assessed. RESULTS: 980 consecutive individuals (51% F; 49% M) were enrolled. Adenoma and AN detection rates were 36.6% (F 29%: M 45%; P < 0.001) and 5.1% (F 3.8%; M 6.5%) respectively. On multivariate analysis, predictors of AN [OR (95%CI)] were age [1.036 (1.00-1.07); P = 0.048], BMI [overweight 2.21 (0.98-5.00); obese 3.54 (1.48-8.50); P = 0.018], smoking [< 40 pack-years 2.01 (1.01-4.01); ≥ 40 pack-years 3.96 (1.86-8.42); P = 0.002], and daily red meat consumption [2.02 (0.92-4.42) P = 0.079]. Nomograms of AN risk were developed in terms of risk factors and age separately for normal, overweight and obese individuals. The model had good discrimination and calibration. CONCLUSION: The prevalence of adenoma and AN in average-risk Lebanese individuals is similar to the West. Age, smoking, and BMI are important predictors of AN, with obesity being particularly powerful. Though external validation is needed, this model provides an important platform for improved risk-stratification for screening programs in regions where universal screening is not currently employed.

The Natural History of Incidental Colonic Diverticulosis on Screening Colonoscopy.

Background: The natural history of colonic diverticulosis is unclear. Methods: Patients with incidental diverticulosis identified in a previous prospective cross-sectional screening colonoscopy study were evaluated retrospectively for clinic or hospital visit(s) for diverticular disease (DD= acute diverticulitis or diverticular bleeding) using review of electronic health records and patient phone interview. Results: 826 patients were included in the screening colonoscopy study. Three were excluded for prior DD. In all, 224 patients (27.2%; mean age 62.3 ± 8.2) had incidental diverticulosis distributed in the left colon (67.4%), right colon (5.8%), or both (22.8%). Up-to-date information was available on 194 patients. Of those, 144 (74.2%) could be reached for detailed interview and constituted the study population. Over a mean follow-up of 7.0 ± 1.7 years, DD developed in 6 out of 144 patients (4.2%) (4 acute cases of diverticulitis, 1 probable case of diverticular bleeding, and 1 acute case of diverticulitis and diverticular bleeding). Two patients were hospitalized, and none required surgery. The time to event was 5.1 ± 1.6 years and the incidence rate was 5.9 per 1000 patient-years. On multivariate analysis, none of the variables collected at baseline colonoscopy including age, gender, obesity, exercise, fiber intake, alcohol use, constipation, or use of NSAIDs were associated with DD. Conclusion: The natural history of incidental diverticulosis on screening colonoscopy was highly favorable in this well-defined prospectively identified cohort. The common scenario of incidental diverticulosis at screening colonoscopy makes this information clinically relevant and valuable to physicians and patients alike.

Effect of Diet Liberalization on Bowel Preparation.

OBJECTIVES: Precolonoscopy dietary regimens often are restricted to clear liquids; however, the superiority of a clear liquid diet (CLD) for bowel preparation quality is ambiguous. We performed a meta-analysis of randomized trials comparing bowel preparation outcomes between a low-residue diet (LRD) or regular diet (RD) compared with a CLD. METHODS: MEDLINE, clinicaltrials.gov, Cochrane Central Register, Scopus, Embase, Cumulative Index to Nursing and Allied Health Literature, and the Web of Science databases were used to conduct a search for randomized controlled trials from 1976 to March 2015. Of 122 relevant references, 12 studies met our inclusion criteria, 7 studies of which were classified as being of high quality. Pooled estimates of bowel preparation quality were defined as adequate versus inadequate. Secondary outcomes included tolerability, willingness to repeat bowel preparation, adverse events, and adenoma detection rate. Pooled estimates of relative risk (RR) were used for dichotomous variables and standardized mean difference for continuous variables. RESULTS: In the high-quality studies, there were no differences in bowel preparation quality among the LRD/RD and CLD groups (RR 0.98; 95% confidence interval [CI] 0.93-1.04). Analysis of secondary outcomes included all of the studies. Tolerability (RR 1.04, 95% CI 1.01-1.08) and willingness to repeat favored the liberalized diet arm (RR 1.08, 95% CI 1.01-1.16). There was no significant difference in the adenoma detection rate, whereas hunger was more common in the CLD group. CONCLUSIONS: An LRD/RD provided no difference in bowel preparation quality as compared with a CLD. As such, it may be reasonable for patients without risk factors for poor preparation to undergo an LRD until lunch the day before their colonoscopy given that bowel preparation tolerability and willingness to repeat were greater among groups with a liberalized diet.

A Customized Mobile Application in Colonoscopy Preparation: A Randomized Controlled Trial.

OBJECTIVES: Adherence with diet and prescribed purgative is essential for proper cleansing with low-volume bowel preparations. The aim of this work was to assess the effect of a customized mobile application (App) on adherence and quality of bowel preparation. METHODS: One hundred and sixty (160) eligible patients scheduled for elective colonoscopy were randomly assigned to paper (control) or App-based instructions. The preparation consisted of low-fiber diet for 2 days, clear fluids for one day and split-dose sodium picosulfate/magnesium citrate (SPS). Before colonoscopy, information was collected regarding adherence with, and utility of the provided instructions. The colonoscopists, blinded to assignment, graded bowel preparation using the Aronchick, Ottawa, and Chicago preparation scales. The primary endpoint was adherence with instructions. Quality of preparation was a secondary endpoint. RESULTS: No difference in overall adherence or bowel cleanliness was observed between the study arms. Adherence was reported in 82.4% of App vs. 73.4% of controls (P=0.40). An adequate bowel preparation on the Aronchick scale was noted in 77.2 vs. 82.5%, respectively (P=0.68). Mean scores on the Ottawa and Chicago scales were also similar. Gender, age, time of colonoscopy, and BMI did not influence preparation or adherence. Compliance with the clear fluid diet component was noted in 94% of patients with BMI<30 vs. 77% with BMI≥30 (P<0.01). SPS was well tolerated by 81.9% of patients. The App was user-friendly and received higher overall rating in this respect than paper instructions (P<0.01). CONCLUSIONS: SPS is well tolerated and effective for bowel cleansing regardless of instruction method. Customized smartphone applications are effective, well-accepted and could replace standard paper instructions for bowel preparation.ClinicalTrials.gov: NCT02410720.

The burden of bowel preparations in patients undergoing elective colonoscopy.

BACKGROUND: An adequate bowel preparation is an important quality measure for optimal colonoscopy. AIMS: The aim of this article is to study the burden of bowel preparations by examining seven specific variables (hunger, taste, volume, sleep, social, work, and adverse events (AEs)). METHODS: Ambulatory patients undergoing elective colonoscopy completed a questionnaire regarding their experience with the prescribed preparation. The seven study variables were graded using a numerical scale of 0-10 (best to worst). A score >6 was considered to indicate a significant impact and used as primary outcome. Patients were also asked to grade in descending order what they perceived as the worst aspect of the preparation. RESULTS: A total of 216 patients completed the survey. Preparations consisted of split-dose sodium picosulfate (SPS) (n = 49), split-dose 4 l PEG ± menthol (n = 49), full-dose PEG (n = 68), and 2 l split-dose PEG + ascorbic acid (n = 50). Except for work and AEs, all variables were considered to have a negative impact by >20% of patients (range 20.4-34.2). SPS was superior to PEG regimens in taste (4.1% vs. 35.9%) and volume (0% vs. 44.9%) (p < 0.05 for both) but inferior for hunger (30.6% vs. 19.2%; p = 0.09). The addition of menthol to PEG significantly improved taste (22.4% vs. 41.5%; p = 0.02). Sleep disturbances were most common with SPS and least with split-dose PEG (30.6% vs. 17.4%; p < 0.05). Overall, patients ranked volume, taste, and hunger as most burdensome. CONCLUSIONS: The burden of bowel preparation is substantial. An informed personalized choice of preparation may improve adherence, tolerability and colon cleansing.

Body mass index and quality of bowel preparation: Real life vs. clinical trials.

BACKGROUND AND STUDY AIMS: Obesity is a recognised risk factor for poor bowel preparation in retrospective studies whilst corresponding data in prospective trials are marginally reported. Aims are to evaluate the relation between body mass index (BMI) and preparation quality in retrospective and interventional prospective settings and within a single centre. PATIENTS AND METHODS: Data from a recent colorectal cancer screening registry were retrospectively analysed for the relation between BMI and adequacy of preparation. Patients were categorised as underweight (BMI<20kg/m(2)), normal (20-25kg/m(2)), overweight (25-30kg/m(2)), and obese (>30kg/m(2)). Data from a recent prospective colon preparation trial were similarly analysed. RESULTS: 541 registry patients were included. Multivariate analysis showed BMI to be an independent risk factor for inadequate preparation. Obesity was associated with odds ratio (OR) of 5.3 [95% confidence interval (CI) 1.4-19.8; p=0.01] compared to normal BMI. A significant difference was also noted in underweight but otherwise healthy individuals (OR=11.1, 95% CI 2-60; p=0.005). In the prospective study of 195 patients, obese patients had comparable rates of inadequate preparation to normal-weight individuals (OR=0.7, 95% CI 1.1-3.96; p=0.68). Underweight patients had a significantly worse preparation compared to normal BMI individuals (OR=8, 95% CI 1.1-58; p=0.04). CONCLUSIONS: In real life, bowel preparations in obese individuals have a lower quality in comparison to normal individuals. This finding is not replicated in clinical trials. This discrepancy is likely the result of focused patient education suggesting that this is primarily a dietary compliance phenomenon. Underweight individuals appear to have worse quality of preparation independent of study design or setting.

Low Prevalence of Hypomagnesemia in Long-term Recipients of Proton Pump Inhibitors in a Managed Care Cohort.

BACKGROUND & AIMS: Chronic intake of proton pump inhibitors (PPI) has been associated with hypomagnesemia, but prevalence of PPI-associated hypomagnesemia is not known. METHODS: We examined the prevalence of hypomagnesemia among long-term PPI recipients by using a large health maintenance organization database. We collected data on 10,167 participants eligible for chronic drug prescriptions from 2008 through 2013. Adult subjects receiving continuous PPI therapy for ≥ 6 months between 2008 and 2013 and ≥ 1 serum magnesium determination(s) were identified. Patients with any magnesium levels less than 1.6 mg/dL were selected for analysis; those with recognizable causes of altered magnesium homeostasis were excluded. RESULTS: Five hundred ninety participants received long-term PPIs, and 414 (70.2%) met the inclusion criteria for a total exposure of 2293 PPI-years (average, 5.7 years/subject). Of these patients, 57 (13.8%) had ≥ 1 low serum magnesium; 5 were no longer on PPIs, and 44 had other recognizable causes for hypomagnesemia (25 receiving diuretics, 8 with chronic diarrhea, 8 with chronic kidney disease, and 3 with malignancies). Of the 8 remaining patients (7 female; mean age, 71.2 ± 13.4 years; mean daily medications, 5.4 ± 1.1), mild hypomagnesemia (range, 1.2-1.5 mg/dL) was noted in 13.9% of 289 measurements. All 8 patients had normal serum levels of magnesium at their final measurement. CONCLUSIONS: In the absence of known precipitating factors, chronic PPI use does not appear to be associated with hypomagnesemia.

Efficacy of reduced-dose regimen of a capsule containing bismuth subcitrate, metronidazole, and tetracycline given with amoxicillin and esomeprazole in the treatment of Helicobacter Pylori infection.

It is well known that triple therapy for Helicobacter pylori is losing efficacy worldwide. A regimen containing proton pump inhibitor and multiple-dose capsules of bismuth, metronidazole, and tetracycline has proven efficacy. In addition, a literature review on dosage of previous regimens shows that half-dose clarithromycin-based regimens are equally effective to full-dose regimens. However, the applicability of dose reduction to bismuth-based therapy is unknown. This communication shows that a reduced-dose bismuth-based regimen fails to achieve acceptable eradication rates.

Split-dose menthol-enhanced PEG vs PEG-ascorbic acid for colonoscopy preparation.

AIM: To compare the efficacy and palatability of 4 L polyethylene glycol electrolyte (PEG) plus sugar-free menthol candy (PEG + M) vs reduced-volume 2 L ascorbic acid-supplemented PEG (AscPEG). METHODS: In a randomized controlled trial setting, ambulatory patients scheduled for elective colonoscopy were prospectively enrolled. Patients were randomized to receive either PEG + M or AscPEG, both split-dosed with minimal dietary restriction. Palatability was assessed on a linear scale of 1 to 5 (1 = disgusting; 5 = tasty). Quality of preparation was scored by assignment-blinded endoscopists using the modified Aronchick and Ottawa scales. The main outcomes were the palatability and efficacy of the preparation. Secondary outcomes included patient willingness to retake the same preparation again in the future and completion of the prescribed preparation. RESULTS: Overall, 200 patients were enrolled (100 patients per arm). PEG + M was more palatable than AscPEG (76% vs 62%, P = 0.03). Completing the preparation was not different between study groups (91% PEG + M vs 86% AscPEG, P = 0.38) but more patients were willing to retake PEG + M (54% vs 40% respectively, P = 0.047). There was no significant difference between PEG + M vs AscPEG in adequate cleansing on both the modified Aronchick (82% vs 77%, P = 0.31) and the Ottawa scale (85% vs 74%, P = 0.054). However, PEG + M was superior in the left colon on the Ottawa subsegmental score (score 0-2: 94% for PEG + M vs 81% for AscPEG, P = 0.005) and received significantly more excellent ratings than AscPEG on the modified Aronchick scale (61% vs 43%, P = 0.009). Both preparations performed less well in afternoon vs morning examinations (inadequate: 29% vs 15.2%, P = 0.02). CONCLUSION: 4 L PEG plus menthol has better palatability and acceptability than 2 L ascorbic acid- PEG and is associated with a higher rate of excellent preparations; Clinicaltrial.gov identifier: NCT01788709.

Challenging the dogma: a randomized trial of standard vs. half-dose concomitant nonbismuth quadruple therapy for Helicobacter pylori infection.

BACKGROUND: Current treatment of Helicobacter pylori consists of three or four drugs for 7-14 days with important associated cost and adverse events. AIMS: This study compared efficacy and safety of standard dose vs. half-dose concomitant nonbismuth quadruple therapy (NBQT) for 7 days. The standard dose consisted of twice daily rabeprazole 20 mg, amoxicillin 1 g, metronidazole 500 mg, and clarithromycin 500 mg. METHODS: This was a prospective randomized trial. (14)C-urea breath test was performed ≥4 weeks after treatment and ≥2 weeks off acid suppressive therapy. Compliance and adverse events were monitored during treatment. RESULTS: A total of 200 consecutive treatment-naïve patients were enrolled. Baseline characteristics were similar between groups, with 15.5% of subjects reporting prior macrolide use. Eradication occurred in 78% (95% CI 68.6-85.7%) in both groups on intention-to-treat analysis. Per-protocol rates were 82.1 vs. 83.9% for standard-dose patients vs. half-dose patients, respectively (p = NS). Adverse events (only mild) were reported in 57 vs. 41% of standard-dose patients vs. half-dose patients (p = 0.024), with metallic taste and nausea notably less frequent in the latter (36 vs. 12% and 18 vs. 7%, respectively; p < 0.05 for both). Overall, eradication failed in 38.7% of prior macrolide users vs. 18.9% without such exposure (p = 0.019). On multivariate logistic regression, prior macrolide exposure was the only factor associated with failed eradication (OR 2.60, 95% CI 1.06-6.39; p = 0.038). Treatment was cheaper with the half-dose regimen. INTERPRETATION: A 50% reduction in antibiotic dosage does not diminish efficacy of concomitant nonbismuth quadruple therapy but leads to significant reduction in cost and adverse events. Seven-day concomitant NBQT is suboptimal for H. pylori independent of prior macrolide exposure.

Sugar-free menthol candy drops improve the palatability and bowel cleansing effect of polyethylene glycol electrolyte solution.

BACKGROUND: Colon preparations are generally poorly tolerated. OBJECTIVE: To study the efficacy of sugar-free candy drops in improving palatability and tolerability of polyethylene glycol electrolyte solution (PEG-E). DESIGN: Single-blind, randomized, controlled trial. SETTING: University medical center. PATIENTS: Ambulatory patients scheduled for elective colonoscopy. INTERVENTION: Menthol candy drops. Patients were randomly assigned to split-dose, 4-L, PEG-E ± cough drops. Palatability was assessed on a linear scale of 1 to 5 (1 = disgusting; 5 = tasty). Quality of preparation, remaining unconsumed volume, and side effects were secondary outcomes. MAIN OUTCOME MEASUREMENTS: Palatability and tolerability of PEG-E. RESULTS: A total of 99 patients were enrolled (50 control group, 49 candy drops-added group). The mean (± standard deviation) palatability score was significantly better in candy drop users versus controls (3.9 ± 0.7 vs 2.8 ± 1.2, respectively; P < .001) as were the preparations scored as excellent (63.3% vs 34% of controls; P = .004). Side effects were similar except for nausea (24.5% candy drops vs 44% controls; P = .04). The amount of unconsumed PEG-E was not different between candy drop and control groups (128 [± 361 mL] versus 69 [± 194 mL], respectively; P = .32) but was significantly lower in excellent grade preparations versus other grades (31 [± 103 mL] versus 162 [± 384 mL], respectively; P = .024). On multivariate logistic regression, an excellent preparation was associated with candy drops (odds ratio [OR] 3.3, 95% confidence interval [CI], 1.4-7.8; P = .006) and smaller unconsumed volume of same-day PEG-E [OR 0.996, 95% CI, 0.992-1.000; P = .044). LIMITATIONS: Single-center study. CONCLUSION: Sugar-free menthol candy drops are a safe and effective addition to split-dose PEG-E, resulting in improved tolerability and patient compliance, which appears to translate into improved bowel cleansing. ( CLINICAL TRIAL REGISTRATION NUMBER: NCT01541683.).