Risk Prediction of Barrett’s Esophagus in a Taiwanese Health Examination Center Based on Regression Models

Determining the target population for the screening of Barrett’s esophagus (BE), a precancerous condition of esophageal adenocarcinoma, remains a challenge in Asia. The aim of our study was to develop risk prediction models for BE using logistic regression (LR) and artificial neural network (ANN) methods. Their predictive performances were compared. We retrospectively analyzed 9646 adults aged ≥20 years undergoing upper gastrointestinal endoscopy at a health examinations center in Taiwan. Evaluated by using 10-fold cross-validation, both models exhibited good discriminative power, with comparable area under curve (AUC) for the LR and ANN models (Both AUC were 0.702). Our risk prediction models for BE were developed from individuals with or without clinical indications of upper gastrointestinal endoscopy. The models have the potential to serve as a practical tool for identifying high-risk individuals of BE among the general population for endoscopic screening.

Download Full-text

LOW PREVALENCE OF BARRETT’S ESOPHAGUS IN A RISK AREA FOR ESOPHAGEAL CANCER IN SOUTH OF BRAZIL

Arquivos de Gastroenterologia ◽

10.1590/s0004-2803.201700000-45 ◽

2017 ◽

Vol 54 (4) ◽

pp. 305-307 ◽

Cited By ~ 1

Author(s):

Diego Michelon DE CARLI ◽

Amanda Faria de ARAUJO ◽

Renato Borges FAGUNDES

Keyword(s):

Barrett’S Esophagus ◽

Esophageal Adenocarcinoma ◽

Odds Ratio ◽

Barrett's Esophagus ◽

Gastrointestinal Endoscopy ◽

Upper Gastrointestinal Endoscopy ◽

Columnar Lined Esophagus ◽

Low Prevalence ◽

Gerd Symptoms ◽

Upper Gastrointestinal

ABSTRACT BACKGROUND: Barrett’s esophagus a complication of gastroesophageal reflux disease (GERD) is a precursor of esophageal adenocarcinoma. The incidence of esophageal adenocarcinoma has been increasing in most Western countries. Rio Grande do Sul (RS), the Southernmost state of Brazil has the highest rates of esophageal cancer with low prevalence of esophageal adenocarcinoma. OBJECTIVE: To investigate the prevalence of Barrett’s esophagus among patients underwent to upper gastrointestinal endoscopy in the last 5 years. METHODS: The records of patients underwent upper gastrointestinal endoscopy between 2011 and 2015 were analyzed. Demographic data, GERD symptoms, endoscopic findings, extension and histological diagnosis of columnar epithelia of the esophagus were recorded. Significance among the variables was accessed by chi-square test and Fisher’s exact test with 95% CI. RESULTS: A total of 5996 patients underwent to upper gastrointestinal endoscopy in the period were included. A total of 1769 (30%) patients with GERD symptoms or esophagitis and 107 (1.8%) with columnar lined esophagus were identified. Except for eight patients, the others with columnar lined esophagus had GERD symptoms or esophagitis. Barrett’s esophagus defined by the presence of intestinal metaplasia occurred in 47 patients; 20 (43%) with segments over 3 cm and 27 (57%) with segments shorter than 3 cm. The global prevalence of Barrett’s esophagus was 0.7% and in GERD patients 2.7%. The odds ratio for the occurrence of columnar lined esophagus in patients with GERD was 30 (95%CI=15.37-63.34). The odds ratio for the presence of intestinal metaplasia in long segments was 8 (95%CI=2.83-23.21). CONCLUSION: GERD patients had a risk 30-folds greater to present columnar lined esophagus than patients without GERD symptoms. Long segments of columnar lined esophagus, had a risk eight-folds higher to have Barrett’s esophagus than short segments. Barrett’s esophagus overall prevalence was 0.7%. In GERD patients, the prevalence was 2.7%. Long Barrett’s esophagus represented globally 0.3% and 1.1% in GERD patients.

Download Full-text

The burden of upper gastrointestinal endoscopy in patients with Barrett’s esophagus

Endoscopy ◽

10.1055/s-2006-944613 ◽

2006 ◽

Vol 38 (9) ◽

pp. 873-878 ◽

Cited By ~ 36

Author(s):

M. Kruijshaar ◽

M. Kerkhof ◽

P. Siersema ◽

E. Steyerberg ◽

M. Homs ◽

...

Keyword(s):

Barrett’S Esophagus ◽

Barrett's Esophagus ◽

Gastrointestinal Endoscopy ◽

Upper Gastrointestinal Endoscopy ◽

Upper Gastrointestinal

Download Full-text

Barrett’s Esophagus in Patients with Gastroesophageal Reflux Disease

Journal of Nepal Health Research Council ◽

10.3126/jnhrc.v16i2.20300 ◽

2018 ◽

Vol 16 (2) ◽

pp. 144-148 ◽

Cited By ~ 1

Author(s):

Khus Raj Dewan ◽

Bhanumati Saikia Patowary ◽

Subash Bhattarai ◽

Gaurav Shrestha

Keyword(s):

Barrett’S Esophagus ◽

Reflux Disease ◽

Barrett's Esophagus ◽

Gastrointestinal Endoscopy ◽

Asian Population ◽

Upper Gastrointestinal Endoscopy ◽

Suspected Case ◽

Squamous Cells ◽

Four Quadrant ◽

Upper Gastrointestinal

Background: Barrett’s esophagus a is metaplasia of normal squamous cells that line the lower part of the esophagus and carries a major risk for adenocarcinoma of esophagus. In Asian population, the prevalence of Barrett’s esophagus and adenocarcinoma are less common than in Western countries but has been increasing.Methods: This is a hospital based descriptive study comprising of 120 consecutive patients with symptoms of gastroesophagial reflux disease belonging to both sexes of any age group. The diagnosis of gastroesophagial reflux disease was based on the symptoms like heart burn and regurgitation. Upper gastrointestinal endoscopy was done in all the patients. Four quadrant biopsies were taken from the esophagogastric junction in suspected case of Barrett’s esophagus. The diagnosis of Barrett’s esophagus was confirmed histopathologically.Results: There were 44.2% males and 55.8% females, age ranging from 22 to 85 years mean being 44.33+13.37. Of them, gastroesophagial reflux disease was mild in 54.16%, moderate in 21.16% and severe in 16.66%. Upper Gastrointestinal endoscopy revealed non erosive gastroesophagial reflux disease in 50%, erosive in 45%, hiatal hernias in 5% and Barrett’s esophagus in 1.6%. Both patients with Barrett’s esophagus were elderly and had short segment (<3cm) involvement with no evidence of dysplasia or adenocarcinoma histopathologically.Conclusions: Endoscopic surveillance with detailed inspection and systematic biopsies is recommended for most patients with Barrett’s esophagus. Esophageal carcinoma if detected should be treated at the earliest.

Download Full-text

Risk Prediction Models for Barrett’s Esophagus Discriminate Well and Are Generalizable in an External Validation Study

Digestive Diseases and Sciences ◽

10.1007/s10620-019-06018-2 ◽

2020 ◽

Vol 65 (10) ◽

pp. 2992-2999 ◽

Cited By ~ 1

Author(s):

Colin J. Ireland ◽

Aaron P. Thrift ◽

Adrian Esterman

Keyword(s):

Barrett’S Esophagus ◽

Risk Prediction ◽

Validation Study ◽

Barrett's Esophagus ◽

Prediction Models ◽

External Validation ◽

Risk Prediction Models ◽

External Validation Study

Download Full-text

Risk Prediction for Early Chronic Kidney Disease: Results from an Adult Health Examination Program of 19,270 Individuals

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph17144973 ◽

2020 ◽

Vol 17 (14) ◽

pp. 4973 ◽

Cited By ~ 1

Author(s):

Chin-Chuan Shih ◽

Chi-Jie Lu ◽

Gin-Den Chen ◽

Chi-Chang Chang

Keyword(s):

Chronic Kidney Disease ◽

Kidney Disease ◽

Decision Tree ◽

Risk Prediction ◽

Prediction Models ◽

Health Examination ◽

Adult Health ◽

Risk Prediction Models ◽

Linear Discriminant ◽

C4.5 Decision Tree

Developing effective risk prediction models is a cost-effective approach to predicting complications of chronic kidney disease (CKD) and mortality rates; however, there is inadequate evidence to support screening for CKD. In this study, four data mining algorithms, including a classification and regression tree, a C4.5 decision tree, a linear discriminant analysis, and an extreme learning machine, are used to predict early CKD. The study includes datasets from 19,270 patients, provided by an adult health examination program from 32 chain clinics and three special physical examination centers, between 2015 and 2019. There were 11 independent variables, and the glomerular filtration rate (GFR) was used as the predictive variable. The C4.5 decision tree algorithm outperformed the three comparison models for predicting early CKD based on accuracy, sensitivity, specificity, and area under the curve metrics. It is, therefore, a promising method for early CKD prediction. The experimental results showed that Urine protein and creatinine ratio (UPCR), Proteinuria (PRO), Red blood cells (RBC), Glucose Fasting (GLU), Triglycerides (TG), Total Cholesterol (T-CHO), age, and gender are important risk factors. CKD care is closely related to primary care level and is recognized as a healthcare priority in national strategy. The proposed risk prediction models can support the important influence of personality and health examination representations in predicting early CKD.

Download Full-text