Iyer, Prasad G.

INTRODUCTION: Screening for Barrett's esophagus (BE) is suggested in those with risk factors, but remains underutilized. BE/esophageal adenocarcinoma (EAC) risk prediction tools integrating multiple risk factors have been described. However, accuracy remains modest (area under the receiver-operating curve [AUROC] ≤0.7), and clinical implementation has been challenging. We aimed to develop machine learning (ML) BE/EAC risk prediction models from an electronic health record (EHR) database. METHODS: The Clinical Data Analytics Platform, a deidentified EHR database of 6 million Mayo Clinic patients, was used to predict BE and EAC risk. BE and EAC cases and controls were identified using International Classification of Diseases codes and augmented curation (natural language processing) techniques applied to clinical, endoscopy, laboratory, and pathology notes. Cases were propensity score matched to 5 independent randomly selected control groups. An ensemble transformer-based ML model architecture was used to develop predictive models. RESULTS: We identified 8,476 BE cases, 1,539 EAC cases, and 252,276 controls. The BE ML transformer model had an overall sensitivity, specificity, and AUROC of 76%, 76%, and 0.84, respectively. The EAC ML transformer model had an overall sensitivity, specificity, and AUROC of 84%, 70%, and 0.84, respectively. Predictors of BE and EAC included conventional risk factors and additional novel factors, such as coronary artery disease, serum triglycerides, and electrolytes. DISCUSSION: ML models developed on an EHR database can predict incident BE and EAC risk with improved accuracy compared with conventional risk factor-based risk scores. Such a model may enable effective implementation of a minimally invasive screening technology.

Background Methods: The question prompt list content was derived through a modified Delphi process consisting of 3 rounds. In round 1, experts provided 5 answers to the prompts “What general questions should patients ask when given a new diagnosis of Barrett’s esophagus” and “What questions do I not hear patients asking, but given my expertise, I believe they should be asking?” Questions were reviewed and categorized into themes. In round 2, experts rated questions on a 5-point Likert scale. In round 3, experts rerated questions modified or reduced after the previous rounds. Only questions rated as “essential” or “important” were included in Barrett’s esophagus question prompt list (BE-QPL). To improve usability, questions were reduced to minimize redundancy and simplified to use language at an eighth-grade level (Fig. 1). Results: Twenty-one esophageal medical and surgical experts participated in both rounds (91% males; median age 52 years). The expert panel comprised of 33% esophagologists, 24% foregut surgeons, and 24% advanced endoscopists, with a median of 15 years in clinical practice. Most (81%), worked in an academic tertiary referral hospital. In this 3-round Delphi technique, 220 questions were proposed in round 1, 122 (55.5%) were accepted into the BE-QPL and reduced down to 76 questions (round 2), and 67 questions (round 3). These 67 questions reached a Flesch Reading Ease of 68.8, interpreted as easily understood by 13 to 15 years olds. Conclusions: With multidisciplinary input, we have developed a physician-derived BE-QPL to optimize patient-physician communication. Future directions will seek patient feedback to distill the questions further to a smaller number and then assess their usability.

Abstract Endoscopic eradication therapy (EET) has become a standard of care for treatment of dysplastic Barrett’s esophagus (BE) and early Barrett’s neoplasia. EET mainly consists of removal of any visible lesions via endoscopic resection and eradication of all remaining Barrett’s mucosa using endoscopic ablation. Endoscopic mucosal resection and endoscopic submucosal dissection are the two available resection techniques. After complete resection of all visible lesions, it is crucial to perform endoscopic ablation to ensure complete eradication of the remaining Barrett’s segment. Endoscopic ablation can be done either with thermal techniques, including radiofrequency ablation and argon plasma coagulation, or cryotherapy techniques. The primary end point of EET is achieving complete remission of intestinal metaplasia (CRIM) to decrease the risk of dysplastic recurrence after successful EET. After CRIM is achieved, a standardized endoscopic surveillance protocol needs to be implemented for early detection of BE recurrence.

Abstract Purpose: Current endoscopy-based screening and surveillance programs have not been proven effective at decreasing esophageal adenocarcinoma (EAC) mortality, creating an unmet need for effective molecular tests for early detection of this highly lethal cancer. We conducted a genome-wide methylation screen to identify novel methylation markers that distinguish EAC and high-grade dysplasia (HGD) from normal squamous epithelium (SQ) or nondysplastic Barrett's esophagus (NDBE). Experimental Design: DNA methylation profiling of samples from SQ, NDBE, HGD, and EAC was performed using HM450 methylation arrays (Illumina) and reduced-representation bisulfate sequencing. Ultrasensitive methylation-specific droplet digital PCR and next-generation sequencing (NGS)-based bisulfite-sequencing assays were developed to detect the methylation level of candidate CpGs in independent esophageal biopsy and endoscopic brushing samples. Results: Five candidate methylation markers were significantly hypermethylated in HGD/EAC samples compared with SQ or NDBE (P < 0.01) in both esophageal biopsy and endoscopic brushing samples. In an independent set of brushing samples used to construct biomarker panels, a four-marker panel (model 1) demonstrated sensitivity of 85.0% and 90.8% for HGD and EACs respectively, with 84.2% and 97.9% specificity for NDBE and SQ respectively. In a validation set of brushing samples, the panel achieved sensitivity of 80% and 82.5% for HGD and EAC respectively, at specificity of 67.6% and 96.3% for NDBE and SQ samples. Conclusions: A novel DNA methylation marker panel differentiates HGD/EAC from SQ/NDBE. DNA-methylation–based molecular assays hold promise for the detection of HGD/EAC using esophageal brushing samples.

Abstract Background: Over 20 susceptibility single-nucleotide polymorphisms (SNP) have been identified for esophageal adenocarcinoma (EAC) and its precursor, Barrett esophagus (BE), explaining a small portion of heritability. Methods: Using genetic data from 4,323 BE and 4,116 EAC patients aggregated by international consortia including the Barrett's and Esophageal Adenocarcinoma Consortium (BEACON), we conducted a comprehensive transcriptome-wide association study (TWAS) for BE/EAC, leveraging Genotype Tissue Expression (GTEx) gene-expression data from six tissue types of plausible relevance to EAC etiology: mucosa and muscularis from the esophagus, gastroesophageal (GE) junction, stomach, whole blood, and visceral adipose. Two analytical approaches were taken: standard TWAS using the predicted gene expression from local expression quantitative trait loci (eQTL), and set-based SKAT association using selected eQTLs that predict the gene expression. Results: Although the standard approach did not identify significant signals, the eQTL set–based approach identified eight novel associations, three of which were validated in independent external data (eQTL SNP sets for EXOC3, ZNF641, and HSP90AA1). Conclusions: This study identified novel genetic susceptibility loci for EAC and BE using an eQTL set–based genetic association approach. Impact: This study expanded the pool of genetic susceptibility loci for EAC and BE, suggesting the potential of the eQTL set–based genetic association approach as an alternative method for TWAS analysis.

Abstract Background and study aims Radiofrequency ablation (RFA) for dysplastic Barrett’s esophagus (BE) has resulted in a paradigm shift in the management of BE. Despite widespread adoption of RFA, the optimal surveillance interval of the ablated zone is unclear. Methods A patient-level discrete time cycle Markov model was developed to model clinical surveillance strategies post-RFA for BE. Three surveillance strategies were examined: the American College of Gastroenterology (ACG) strategy based on ACG guidelines for post-RFA surveillance, the Cotton strategy based on data from the USA and UK RFA registries, and the UK strategy in line with surveillance strategies in UK centers. Monte-Carlo deterministic and probabilistic analyses were performed over 10,000 iterations (i. e., representing 10,000 patient journeys) and sensitivity analyses were carried out on the variables used in the model. Results On base-case analysis, the ACG strategy was the most cost-effective strategy, at a mean cost of £ 11,733 ($ 16,396) (standard deviation (SD) 1520.15) and a mean effectiveness of 12.86 (SD 0.07) QALYs. Probabilistic sensitivity analysis demonstrated that the ACG model was the most cost-effective strategy with a net monetary benefit (NMB) of £ 5,136 ($ 7177) (SD 241) compared to the UK strategy and a NMB of £ 7017 ($ 9,806) (SD 379) compared to the Cotton strategy. At a willingness to pay (WTP) threshold of £ 20,000 ($ 27,949), the ACG model was superior to the other strategies as the most cost-effective strategy. Conclusions A post-RFA surveillance strategy based on the ACG guidelines seems to be the most cost-effective surveillance option.

Barrett's esophagus (BE) is a common condition associated with chronic gastroesophageal reflux disease. BE is the only known precursor to esophageal adenocarcinoma, a highly lethal cancer with an increasing incidence over the last 5 decades. These revised guidelines implement Grading of Recommendations, Assessment, Development, and Evaluation methodology to propose recommendations for the definition and diagnosis of BE, screening for BE and esophageal adenocarcinoma, surveillance of patients with known BE, and the medical and endoscopic treatment of BE and its associated early neoplasia. Important changes since the previous iteration of this guideline include a broadening of acceptable screening modalities for BE to include nonendoscopic methods, liberalized intervals for surveillance of short-segment BE, and volume criteria for endoscopic therapy centers for BE. We recommend endoscopic eradication therapy for patients with BE and high-grade dysplasia and those with BE and low-grade dysplasia. We propose structured surveillance intervals for patients with dysplastic BE after successful ablation based on the baseline degree of dysplasia. We could not make recommendations regarding chemoprevention or use of biomarkers in routine practice due to insufficient data.