ESWL for large pancreatic calculi: Report of over 5000 patients.

INTRODUCTION: The primary aim of this study was to evaluate efficacy, safety and short-term pain relief after ESWL for large pancreatic calculi in over 5000 patients at a single center. METHODS: This is a retrospective analysis of prospectively collected data. Patients with painful calculi >5 mm, located in the head, neck and body region in the MPD, who were not amenable for extraction by the standard procedure of endoscopic pancreatic sphincterotomy were subjected to ESWL using a third generation dual focus lithotripter. Patients were followed up at 6 months for outcome evaluation. RESULTS: A total of 5124 patients (66% males) were subjected to ESWL. Majority of stones (79.2%) were radiopaque. Single calculi were seen in 3851 (75.1%).The majority of stones were located in head region of MPD in 2824 (55.1%) patients. 4386 (85.5%) patients required 3 or less sessions for fragmentation and complete stone clearance was achieved in 3722 (72.6%). EPS was performed in 5022 (98%) while PD stenting was required in 3536 (69%) patients. Of the 4280 patients followed up for 6 months, 3529 (82.6%) patients were pain free. Another 512 (11.9%) patients had significant reduction in VAS score. In 229 (5.3%) there was no decrease in pain intensity. Minor and self-limiting complications were reported in 1153 (22.5%). DISCUSSION: Our study confirms the safety and efficacy and short-term pain relief of ESWL for large calculi in the MPD. In properly selected patients, this should be offered as the first line of therapy for all large MPD calculi not amenable to the standard techniques of stone extraction.

Application of machine-learning model to optimize colonic adenoma detection in India.

AIMS: There is limited data on the prevalence and risk factors of colonic adenoma from the Indian sub-continent. We aimed at developing a machine-learning model to optimize colonic adenoma detection in a prospective cohort. METHODS: All consecutive adult patients undergoing diagnostic colonoscopy were enrolled between October 2020 and November 2022. Patients with a high risk of colonic adenoma were excluded. The predictive model was developed using the gradient-boosting machine (GBM)-learning method. The GBM model was optimized further by adjusting the learning rate and the number of trees and 10-fold cross-validation. RESULTS: Total 10,320 patients (mean age 45.18 ± 14.82 years; 69% men) were included in the study. In the overall population, 1152 (11.2%) patients had at least one adenoma. In patients with age > 50 years, hospital-based adenoma prevalence was 19.5% (808/4144). The area under the receiver operating curve (AUC) (SD) of the logistic regression model was 72.55% (4.91), while the AUCs for deep learning, decision tree, random forest and gradient-boosted tree model were 76.25% (4.22%), 65.95% (4.01%), 79.38% (4.91%) and 84.76% (2.86%), respectively. After model optimization and cross-validation, the AUC of the gradient-boosted tree model has increased to 92.2% (1.1%). CONCLUSIONS: Machine-learning models may predict colorectal adenoma more accurately than logistic regression. A machine-learning model may help optimize the use of colonoscopy to prevent colorectal cancers. TRIAL REGISTRATION: ClinicalTrials.gov (ID: NCT04512729).