Introduction

Acute variceal bleeding is a life-threatening decompensating event in the natural history of cirrhosis. Endoscopic variceal ligation (EVL) along with non-selective beta blockers or carvedilol are current standard of care for patients with acute esophageal variceal bleeding. Use of proton pump inhibitors (PPI) in post EVL period is more of a personal choice as various society guidelines do not recommend continuation of PPI after EVL owing to low quality of evidence to support their use. The literature regarding the benefits of PPI in post EVL re-bleeding and mortality is heterogeneous without any clear answer particularly for mortality.

Aims & Methods

We conducted a single centre, outcome assessor blinded prospective randomized control trial where patients of liver cirrhosis with suspected or documented acute variceal bleeding were screened and those who underwent EVL were randomized into PPI or No-PPI group. Patients in the PPI group received Tab esomeprazole 40 mg once a day in addition to standard of care for all the patients. Both groups were followed up at 2 weeks post index EVL after randomization for occurrence of rebleeding and a repeat upper gastrointestinal endoscopy (UGIE) to document presence or absence of post EVL ulcers, their number and size. All patients were again followed up at 3 months for development of recurrent bleeding, mortality and adverse effect like pain and dysphagia post EVL. Primary outcome was to compare the rate of recurrent bleeding after EVL between the 2 groups. Secondary outcomes were to assess the difference in mortality, number and size of post EVL ulcers and adverse effects in the form of pain and dysphagia post EVL. Association between categorical outcomes was assessed by cross tabulation and comparison of percentages. Chi square test was used to test statistical significance. The association between quantitative variables was assessed by independent sample t-test to assess statistical significance. A p value of <0.05 was considered significant.

Results

A total of 246 patients were screened from June 2023 to April 2024 and 170 patients were randomized to both the groups. Baseline parameters were comparable between the groups. In the primary outcome, number of patients who developed recurrent bleeding episode were 23 (28.05%) in the no-PPI group, which were significantly more in comparison to 9 (11.54%) in the PPI group (p=0.009). Among the secondary outcomes, incidence of mortality was higher in the no-PPI group [16 (19.51%) vs 13 (16.67%) respectively], although statistically non-significant (p=0.640). All 16 (100%) deaths in the no-PPI group were related to rebleeding episode in comparison to only 5 (38.46%) deaths in the PPI group (p=0.035). Incidence of post EVL ulcers was significantly more in the no-PPI group [65 (86.67%) vs 22 (30.99%) respectively; p<0.001]. Median post EVL ulcer number and size were also significantly higher in the no-PPI group [1 (IQR 1,2) vs 0 (IQR 0,1) (p=<0.001); 6 mm (IQR 5,8) vs 5 mm (IQR 5,6) (p=0.0061) respectively]. At 2 weeks, chest pain was reported by 7 (9.33%) patients in the no PPI group vs 2 (2.82%) patients in the PPI group (p=0.167). No patient reported dysphagia at 2 weeks. No patient reported chest pain or dysphagia at 3 months.

Conclusion

Prescription of PPI after EVL in patients of liver cirrhosis with acute esophageal variceal bleeding is beneficial as it significantly decreases the recurrent bleeding episodes as well as mortality in such patients.

Introduction

Bowel preparation quality is a key determinant of colonoscopy effectiveness and adenoma detection^1,2. Manual evaluation of free-text colonoscopy reports is labor-intensive and limits quality monitoring³. Developing a natural language processing (NLP) application for measuring colonoscopy quality demonstrates the potential to automate this process by extracting key quality indicators⁴.

Aims & Methods

We aimed to develop and validate a NLP approach to automatically classify bowel cleanliness and to comprehensively structure colonoscopy reports by extracting procedural and pathological variables. A total of 11,374 reports from our institutional endoscopy unit were analyzed. An annotated dataset of 1,018 reports labeled as “good,” “intermediate,” or “poor” preparation was used to train a TF-IDF–based logistic regression classifier. Cross-validation and test performance were evaluated using accuracy, precision, recall, and F1-scores, and the model was applied to the full dataset. Additional variables (cecal intubation, polyp presence, number, size, localization, polypectomy method, and hemostasis application) were extracted using rule-based NLP heuristics. Adenoma detection rate (ADR) was calculated in a predefined subset (January 2023–July 2025) with complete pathology data, and multivariable logistic regression identified independent predictors.

Results

The NLP classifier achieved a cross-validated accuracy of 92%. Precision and recall were highest for “good” preparation (0.98 and 0.99) and acceptable for “intermediate” (0.85 and 0.82) and “poor” (0.85 and 0.87). Application to the full cohort yielded 5,787 (50.9%) good, 2,176 (19.1%) intermediate, and 3,411 (30.0%) poor preparations. Leveraging these structured data, ADR analysis in the subset of 5,420 patients showed an overall rate of 20.4%. Multivariable analysis demonstrated that ADR was independently associated with older age (OR 1.05 per year, 95% CI 1.05–1.06, p<0.001), male sex (OR 1.74, 95% CI 1.51–2.01, p<0.001), adequate bowel preparation (OR 1.46, 95% CI 1.21–1.75, p<0.001), cecal intubation (OR 1.76, 95% CI 1.43–2.16, p<0.001), and procedures performed by specialists compared with trainees (24.0% vs 20.3%; OR 1.25, 95% CI 1.05–1.47, p=0.010).

Conclusion

This large-scale real-world analysis demonstrates the feasibility of NLP-based automated classification of bowel preparation quality and its direct utility in generating structured colonoscopy datasets for quality monitoring. By integrating bowel cleanliness with other performance indicators (age, sex, cecal intubation, operator expertise), our framework not only achieved high classification accuracy but also provided clinically relevant benchmarks for ADR, supporting targeted quality improvement in endoscopy units.

References

1. Clark BT, Protiva P, Nagar A, et al. Quantification of Adequate Bowel Preparation for Screening or Surveillance Colonoscopy in Men. Gastroenterology. 2016;150(2):396-e15. doi:10.1053/j.gastro.2015.09.041
2. Clark BT, Rustagi T, Laine L. What level of bowel prep quality requires early repeat colonoscopy: systematic review and meta-analysis of the impact of preparation quality on adenoma detection rate. Am J Gastroenterol. 2014;109(11):1714-1724. doi:10.1038/ajg.2014.232
3. Raju GS, Lum PJ, Slack RS, et al. Natural language processing as an alternative to manual reporting of colonoscopy quality metrics. Gastrointest Endosc. 2015;82(3):512-519. doi:10.1016/j.gie.2015.01.049
4. Harkema H, Chapman WW, Saul M, Dellon ES, Schoen RE, Mehrotra A. Developing a natural language processing application for measuring the quality of colonoscopy procedures. J Am Med Inform Assoc. 2011;18 Suppl 1(Suppl 1):i150-i156. doi:10.1136/amiajnl-2011-000431