Search

Summary Background Screening for Barrett's oesophagus relies on endoscopy, which is invasive and few who undergo the procedure are found to have the condition. We aimed to use machine learning techniques to develop and externally validate a simple risk prediction panel to screen individuals for Barrett's oesophagus. Methods In this prospective study, machine learning risk prediction in Barrett's oesophagus (MARK-BE), we used data from two case-control studies, BEST2 and BOOST, to compile training and validation datasets. From the BEST2 study, we analysed questionnaires from 1299 patients, of whom 880 (67·7%) had Barrett's oesophagus, including 40 with invasive oesophageal adenocarcinoma, and 419 (32·3%) were controls. We randomly split (6:4) the cohort using a computer algorithm into a training dataset of 776 patients and a testing dataset of 523 patients. We compiled an external validation cohort from the BOOST study, which included 398 patients, comprising 198 patients with Barrett's oesophagus (23 with oesophageal adenocarcinoma) and 200 controls. We identified independently important diagnostic features of Barrett's oesophagus using the machine learning techniques information gain and correlation-based feature selection. We assessed multiple classification tools to create a multivariable risk prediction model. Internal validation of the model using the BEST2 testing dataset was followed by external validation using the BOOST external validation dataset. From these data we created a prediction panel to identify at-risk individuals. Findings The BEST2 study included 40 diagnostic features. Of these, 19 added information gain but after correlation-based feature selection only eight showed independent diagnostic value including age, sex, cigarette smoking, waist circumference, frequency of stomach pain, duration of heartburn and acidic taste, and taking antireflux medication, of which all were associated with increased risk of Barrett's oesophagus, except frequency of stomach pain, with was inversely associated in a case-control population. Logistic regression offered the highest prediction quality with an area under the receiver-operator curve (AUC) of 0·87 (95% CI 0·84–0·90; sensitivity set at 90%; specificity of 68%). In the testing dataset, AUC was 0·86 (0·83–0·89; sensitivity set at 90%; specificity of 65%). In the external validation dataset, the AUC was 0·81 (0·74–0·84; sensitivity set at 90%; specificity of 58%). Interpretation Our diagnostic model offers valid predictions of diagnosis of Barrett's oesophagus in patients with symptomatic gastro-oesophageal reflux disease, assisting in identifying who should go forward to invasive confirmatory testing. Our predictive panel suggests that overweight men who have been taking antireflux medication for a long time might merit particular consideration for further testing. Our risk prediction panel is quick and simple to administer but will need further calibration and validation in a prospective study in primary care. Funding Charles Wolfson Charitable Trust and Guts UK.

BACKGROUND: Radiofrequency ablation (RFA) is currently recommended for dysplastic Barrett's oesophagus (BO); however, there are limited data on treatment response when stratified by baseline histology. OBJECTIVE: The objective of this article is to evaluate RFA outcomes and durability for BO with different baseline histology. METHODS: Patients treated with RFA between 2007 and 2017 at a single institution were retrospectively included. Outcome measures were: (a) complete remission of dysplasia (CRD) and intestinal metaplasia (CRIM) at 18 months, (b) complication rate and (c) durability of CRD and CRIM. RESULTS: A total of 148 patients underwent RFA, of whom 113 completed the treatment protocol (21 low-grade dysplasia (LGD), 46 high-grade dysplasia (HGD) and 46 intramucosal carcinoma (IMC)). CRD and CRIM were achieved in 94.7% and 78.8% of patients, respectively. When stratified by baseline histology, there was no significant difference in CRD between groups (LGD, 95.2%; HGD, 95.7%; and IMC, 93.5%; p = 0.89). Similarly, there was no significant difference in CRIM between groups (LGD, 71.4%; HGD, 76.1% and IMC, 87.0%; p = 0.39). CRD and CRIM durability at 24 months for LGD, HGD and IMC were 100%, 97.7% and 100% (log rank p = 0.31), and 100%, 89.0% and 95.5%, respectively (log rank p = 0.62). CONCLUSION: Baseline histology is not a predictor of RFA response. Once CRD and CRIM are achieved, these effects are durable over time.

BACKGROUND: Proton-pump inhibitors (PPIs) are the mainstay of gastroesophageal reflux disease (GERD) treatment, however, up to 30% of patients have a poor symptomatic response. PH-impedance is the gold standard to assess whether this is due to persistent acid reflux. We aimed to characterize clinical predictors of persistent esophageal acid reflux on PPIs including gastric pH measured during endoscopy. METHODS: We prospectively recruited patients with GERD and/or Barrett’s esophagus (BE) on PPIs. All patients completed a symptom questionnaire (RDQ) and underwent gastroscopy with gastric pH analysis, immediately followed by ambulatory 24-hour pH-impedance. We used a modified cut-off of 1.3% for pathological esophageal acid exposure time (AET). Multiple linear regression model was used to analyze the correlation between AET and predictive variables. RESULTS: We recruited 122 patients, of which 92 (75.4%) were included in the final analysis [44 male (47.8%), median age 53 years (IQR: 43–66)]. Forty-four patients (47.8%) had persistent acid reflux with a median total AET of 2.2 (IQR1.2-5.0), as compared to 0.1 (IQR 0.0-0.2) in patients without persistent reflux (n=48; P

Supplemental material, UEG880362 Supplemental Material for Endoscopic measurement of gastric pH is associated with persistent acid reflux in patients treated with proton pump inhibitors for gastroesophageal reflux disease by Wladyslaw Januszewicz, James Hartley, William Waldock, Geoffrey Roberts, Bincy Alias, Anthony Hobson, Lorenz Wernisch and Massimiliano di Pietro in United European Gastroenterology Journal

Introduction The CytospongeTM device offers a less invasive way to test for Barrett’s oesophagus and early oesophageal cancer in patients with acid reflux symptoms. Due to the low cost compared with endoscopy, the device could have a direct impact on NHS spend. The procedure is safe, less time consuming, and should be straightforward for nurses to administer in a primary care setting. The BEST3 trial is a UK-wide randomised trial of CytospongeTM compared with usual care, which provides an ideal opportunity to determine the feasibility and roll out of the device for administration by Practice Nurses and Clinical Research Network Nurses. Methods A training module has been designed to ensure that nurses have background knowledge of Barrett’s and the clinical follow-up plan if a patient is given a positive diagnosis. Risks and benefits of having the procedure are explained and Standard Operating Procedures (SOPs) discussed to deal with any adverse events. Training is delivered in two stages: i) Centralised training where nurses attend in groups of between 2–10 individuals using a combination of videos, PowerPoint presentations and live clinical procedures. ii) Nurses observe at least one procedure and are then supervised until they feel confident. All nurses are then assessed by a trainer in their technique of safe delivery and withdrawal of the device. Once signed off they are able to carry out clinics independently with ongoing monitoring by the Trials Unit. Results 15 CRN Nurses and 8 GP Practice Nurses from 30 surgeries have been trained during the BEST3 trial. Following the training programme, the CRN nurses were generally deemed competent after 3 clinic sessions, whereas the Practice Nurses required 2 clinic sessions as they were more used to delivering clinical interventions. The nurses found that having the intense training close to the time of starting the clinics, and the extended supervision, enabled them to feel confident quickly. During the training phase, more patients required a second attempt to swallow the device before it was successful. Specifically, 9% of the patients received 2 CytospongesTM before the device was successfully swallowed and 4% (12 out of 331) were unable to swallow after two attempts. In comparison, 99% of patients received a successfully delivered device when administered by a Trainer. Conclusion The CytospongeTM device is suitable for delivery by nurses in the primary care setting. The feedback received on the training module was positive and therefore CytospongeTM training would be suitable to wider implementation in the NHS setting, with the added benefit of a potential cost reduction when compared with endoscopy.