Predictive factors for inadequate bowel preparation using low-volume polyethylene glycol (PEG) plus ascorbic acid for an outpatient colonoscopy

Applying machine learning to predict bowel preparation adequacy in elderly patients for colonoscopy: development and validation of a web-based prediction tool

BACKGROUND

Adequate bowel preparation is crucial for effective colonoscopy, especially in elderly patients who face a high risk of inadequate preparation. This study develops and validates a machine learning model to predict bowel preparation adequacy in elderly patients before colonoscopy.

METHODS

The study adhered to the TRIPOD AI guidelines. Clinical data from 471 elderly patients collected between February and December 2023 were utilized for developing and internally validating the model, while 221 patients' data from March to June 2024 were used for external validation. The Boruta algorithm was applied for feature selection. Models including logistic regression, light gradient boosting machines, support vector machines (SVM), decision trees, random forests, and extreme gradient boosting were evaluated using metrics such as AUC, accuracy, sensitivity, and specificity. The SHAP algorithm helped rank feature importance. A web-based application was developed using the Streamlit framework to enhance clinical usability.

RESULTS

The Boruta algorithm identified 7 key features. The SVM model excelled with an AUC of 0.895 (95% CI: 0.822-0.969), and high accuracy, sensitivity, and specificity. In external validation, the SVM model maintained robust performance with an AUC of 0.889. The SHAP algorithm further explained the contribution of each feature to model predictions.

CONCLUSION

The study developed an interpretable and practical machine learning model for predicting bowel preparation adequacy in elderly patients, facilitating early interventions to improve outcomes and reduce resource wastage.

Effectiveness of a Mobile Health Application for Educating Outpatients about Bowel Preparation

Colonoscopy is an essential method for diagnosing and treating colorectal cancer, relying on effective bowel preparation to thoroughly examine the large intestinal mucosa. Traditional education involves printed instructions and verbal explanations but does not guarantee clear patient understanding. Poor bowel preparation can obscure mucosal visibility, delaying cancer diagnosis and treatment. A mobile medical model using Android devices for bowel preparation education was tested in a single-blind, randomized trial. This trial enrolled outpatients undergoing colonoscopy at the Endoscopy Center for Diagnostic and Treatment between 27 October 2021 and 31 December 2022. This study introduced the ColonClean app alongside traditional methods. After examination, endoscopists rated the preparation quality using the Aronchick scale. A data analysis was conducted using SPSS 25.0 to determine if there was a significant improvement in bowel preparation quality between the control group (traditional method) and the experimental group (traditional method plus the ColonClean app). Forty patients were recruited in each group. In the experimental group, all ratings were "fair", with 75% receiving an "excellent" or "good" rating, showing statistical significance (p = 0.016). The ColonClean app improves bowel preparation quality more effectively than traditional care instructions.

Comparison of Objectively Assessed Versus Patient-Reported Clarity of Last Rectal Effluent for the Prediction of Quality of Bowel Preparation for Colonoscopy: A Prospective, Case-Control Study

INTRODUCTION

Colonoscopy is a crucial procedure for various clinical purposes, including screening for colorectal cancer. Adequate bowel preparation is essential for its success. Poor bowel preparation can lead to bad outcomes. An objective assessment of bowel preparation quality is typically only possible after the colonoscope is inserted. This study aimed to objectively correlate the clarity of last rectal effluent, directly collected in a transparent container, with the quality of bowel preparation, and compare it with patient-reported descriptions.

METHODS

This prospective, single-centre, case-control study obtained ethical clearance and included patients aged >18 years undergoing colonoscopies. Cases included patients who collected the last rectal effluent and took photographs, while controls relied on verbal descriptions. Data collected included demographics, clinical information, bowel preparation quality, and lastly, stool clarity. A statistical analysis was performed to identify correlations and associations.

RESULTS

Of the 70 included patients, 45 were male. The mean age was 35.8 ± 14.3 years. Cases had a higher mean age (37.8 ± 14.6). A higher number of cases had comorbidities (11, 68.8%). Photographic recording of the last rectal effluent was not associated with the adequacy of bowel preparation. Thin yellow fluid was the most common last-rectal effluent clarity (33, 47.1%). Thin, clear fluid was significantly associated with adequate bowel preparation.

CONCLUSION

Objective assessment of last rectal effluent clarity correlates with the quality of bowel preparation. This can improve the quality of bowel preparation for colonoscopies and potentially reduce the need for repeat procedures, contributing to better patient outcomes and cost savings in healthcare systems.

Split dose bowel preparation before colonoscopy of PEG (Nulytely) in comparison to routine single dose bowel preparation

BACKGROUND

The aim of this study was to compare the efficacy and tolerability of polyethylene glycol (PEG) in single- or split-dose regimens for colonoscopy bowel preparation.

METHODS

This is a prospective, randomized, endoscopist blinded, single-center study, that included adult patients who underwent colonoscopy during the period from December 2017 to October 2018. Two groups were enrolled in the same period: One group used 4 L of PEG (Nulytely) in a single-dose preparation, administered a day before the procedure, and the other group received a split-dose regimen of 2 L PEG (Nulytely), given a day before the procedure and 2 L on the day of the procedure in the early morning. The Boston Bowel Preparation Scale (BBPS) was used for bowel preparation adequacy; scales 0 and 1 were considered inadequate, and scales 2 and 3 were considered adequate preparation.

RESULTS

Two hundred and forty patients were enrolled, 120 (50%) using the split-dose regimen and 120 (50%) using the single-dose regimen, for bowel preparation. Males constituted 51.6% of the study cohort. In the single-dose group, 62.5% achieved adequate bowel preparation compared to 89.2% in the split-dose group (p< 0.001). In addition, polyp detection in the split-dose group was 23.3% in comparison to 10.8% in the single-dose group (P = 0.016). We also found hypertension and diabetes as significant predictors of bowel preparation inadequacy, while sex and age were not related to bowel preparation adequacy.

CONCLUSIONS

Split-dose bowel preparation for colonoscopy with PEG (Nulytely) is better than routine single-dose, in terms of adequate bowel preparation and polyp detection.

Bowel-cleansing efficacy of the 1L polyethylene glycol-based bowel preparation NER1006 (PLENVU) in patient subgroups in two phase III trials

BACKGROUND

Adequate bowel preparation prior to colonoscopy is essential for visualization of the colonic mucosa to maximize adenoma and polyp detection. The risk of inadequate bowel cleansing is heightened if the patient is older, male, overweight, and has comorbidities, such as diabetes. This post hoc analysis of the combined MORA and NOCT clinical trials explores the efficacy of evening/morning split-dose regimens of NER1006 (PLENVU^®, Norgine Ltd), a 1-liter polyethylene glycol (PEG) bowel preparation, to evaluate its bowel-cleansing efficacy in patients at risk for inadequate cleansing.

METHODS

Patients requiring colonoscopy were randomized to receive evening/morning split-dosing of either NER1006, 2-liter (2L) PEG and ascorbate, or oral sulfate solution (OSS). Bowel-cleansing efficacy was assessed by treatment-blinded central readers using the validated Harefield Cleansing Scale (HCS).

RESULTS

Split-dose NER1006 was associated with high levels of cleansing, ranging between 87.0% and 94.0% across all patient subtypes (n = 551), including patients with obesity or diabetes. However, patients aged >65 years and <45 years showed significantly greater rates of successful cleansing than patients aged 45-65 years (94.0% versus 94.2% versus 87.0%, p = 0.002). The high-risk patient subgroup, which included obese males aged ⩾60 years, had significantly improved overall and high-quality bowel-cleansing success rates of 100% (33/33) and 72.7% (27/33) on the HCS with NER1006, compared with 86.7% (26/30) and 50% (15/30) with the comparator solutions (p = 0.015 and p = 0.033, respectively). In this high-risk subgroup, adenoma detection was greater per patient receiving NER1006 versus the comparator group (1.82 versus 0.93, p = 0.041). NER1006 was the only treatment that enabled the detection of patients with ⩾5 adenomas [9.1% (3/33) versus 0/30, p = 0.047].

CONCLUSION

NER1006 effectively cleansed a broad range of patients and offered superior bowel cleansing versus 2LPEG/OSS in patients at increased risk of colorectal cancer. Future research should establish whether more effective cleansing also enables improved adenoma detection.

PLAIN LANGUAGE SUMMARY

A low-volume bowel preparation solution to better detect lesions associated with colorectal cancer during colonoscopyColorectal cancer (CRC) is the fourth most commonly diagnosed cancer in the world. Obese men over the age of 65 years are at particularly increased risk of developing CRC. If the changes in their large intestine (colon) could be seen more clearly during a colonoscopy (where a small camera is inserted via the anus to examine the bowels from the inside), patients who need treatment would be diagnosed earlier, thus improving their chances of survival. In this paper we discuss the use of a bowel preparation solution that is more convenient for patients (less to drink) but also cleans bowels more effectively, meaning more lesions are detected than when other solutions are used. This improved cleansing, and thus better visualization, occurred in a range of patients, including those at higher risk of CRC, such as older, overweight men.

Impact of Prepackaged Low-Residue Diet on Bowel Preparation for Colonoscopy: A Meta-analysis

This meta-analysis aimed to evaluate the impact of prepackaged low-residue diet (PLRD) on bowel preparation for colonoscopy. We searched PubMed, Web of Science, EMBASE, and Cochrane Library databases from inception to August 2020. Randomized controlled trials (RCTs) comparing PLRD with clear liquid diet (CLD) or self-prepared LRD were considered for inclusion. The analysis calculated the odds ratio (OR) for the rate of adequate bowel preparation, patient tolerance, willingness to repeat bowel preparation, tolerability of bowel preparation, and overall adverse effects. Five RCTs published between 2006 and 2019 (N = 561) were included in our meta-analysis. Compared with the traditional CLD or self-prepared LRD, PLRD showed significantly higher rates of adequate bowel preparation (OR, 2.16; 95% confidence interval [CI], 1.18-3.98; p = .01), patient tolerance (OR, 1.99; 95% CI, 1.30-3.07; p = .002), and willingness to repeat the bowel preparation (OR, 1.68; 95% CI, 1.05-2.70; p = .03), with no differences in adverse events (OR, 0.93; 95% CI, 0.59-1.46; p = .75). Prepackaged low-residue diet improved bowel preparation quality, patient tolerance, and willingness to repeat bowel preparations. Importantly, PLRD does not increase the incidence of adverse events. This suggests that it is effective and safe to use PLRD for bowel preparation before colonoscopy.

Recent Advances in Colonic Preparation for an Accurate Colonoscopy - How to Improve Our Practice to Meet the Quality Criteria

Colorectal cancer (CRC) remains a major problem of global health. Screening colonoscopy is the gold standard in detection of CRC. A quality colonoscopy needs good indication, adequate bowel preparation, adequate examination time (30 to 45 minutes), a minimum 6 minutes time for mucosal examination during colonoscopy descent, a good centre adenoma detection rate. In 28-33% of the colonoscopies, the bowel preparation is unsatisfactory which leads to several hidden costs including the rise of preventable and treatable death rate regarding colorectal carcinoma. The ESGE (European Society of Gastrointestinal Endoscopy) recommends a maximum of 10% poor preparations, threshold that is diffi cult to reach in many centres. Newer low-volume laxative regimens for bowel cleansing are better in the fi elds of compliance and tolerability than the classic 4L PEG with 2L PEG-CS (Clensia ®) being one of the new promising low-volume formulas. The low fi bre diet is now preferred due to better compliance and tolerability.