A Tissue Systems Pathology Assay for High-Risk Barrett's Esophagus

Abstract

Background: Better methods are needed to predict risk of progression for Barrett's esophagus. We aimed to determine whether a tissue systems pathology approach could predict progression in patients with nondysplastic Barrett's esophagus, indefinite for dysplasia, or low-grade dysplasia.

Methods: We performed a nested case-control study to develop and validate a test that predicts progression of Barrett's esophagus to high-grade dysplasia (HGD) or esophageal adenocarcinoma (EAC), based upon quantification of epithelial and stromal variables in baseline biopsies. Data were collected from Barrett's esophagus patients at four institutions. Patients who progressed to HGD or EAC in ≥1 year (n = 79) were matched with patients who did not progress (n = 287). Biopsies were assigned randomly to training or validation sets. Immunofluorescence analyses were performed for 14 biomarkers and quantitative biomarker and morphometric features were analyzed. Prognostic features were selected in the training set and combined into classifiers. The top-performing classifier was assessed in the validation set.

Results: A 3-tier, 15-feature classifier was selected in the training set and tested in the validation set. The classifier stratified patients into low-, intermediate-, and high-risk classes [HR, 9.42; 95% confidence interval, 4.6-19.24 (high-risk vs. low-risk); P < 0.0001]. It also provided independent prognostic information that outperformed predictions based on pathology analysis, segment length, age, sex, or p53 overexpression.

Conclusion: We developed a tissue systems pathology test that better predicts risk of progression in Barrett's esophagus than clinicopathologic variables.

Impact: The test has the potential to improve upon histologic analysis as an objective method to risk stratify Barrett's esophagus patients. Cancer Epidemiol Biomarkers Prev; 25(6); 958-68. ©2016 AACR.

Figure 1. Development and Performance of 15-Feature Risk Score in Training Set of BE Patients

A ROC curve for 15-feature risk score in training set of incident progressor and nonprogressor patients. B, C and D: KM analysis of probability of progression to HGD/EAC in patients scored low-, intermediate- and high-risk by the 15-feature risk classifier from all four institutions, the three US institutions and AMC, respectively. E: Univariate HRs and ORs with 95% C.I. for comparisons between risk groups.

Figure 2. Detection of High Risk Features that Precede Morphologic Changes in BE

Endoscopy, H&E and multiplexed fluorescence biomarker images are shown for an incident progressor (IP) (panels A-C) and a non-progressor (NP) (panels D-F) with GI subspecialist diagnosis of BE ND. The IP patient progressed to HGD 6.3 years later and was scored high-risk by the 15-feature classifier. The NP patient had 7.8 years of endoscopic surveillance showing no progression to HGD/EAC and was scored low-risk. A: Endoscopy image from IP showing BE without visible lesions; B: H&E-stained biopsy from IP showing ND; C: Biomarker patterns in ND biopsy from IP (upper-left fragment: p53-yellow, p16-green, AMACR-red, upper-right: HER2/neu-green, K20-red, lower-left: CD68-green, COX-2-red, lower-right: HIF-1α-green, CD45RO-red; D: Endoscopy image from NP showing BE without visible lesions; E: H&E-stained biopsy from NP showing ND; F: Biomarker patterns in ND biopsy from NP showing absence of high-risk changes (upper-left: p53-yellow, p16-green, AMACR-red, upper-right: HER2/neu-green, K20-red, lower-left: CD68-green, COX-2-red, lower-right: HIF-1α-green, CD45RO-red. Hoechst labeling shown in blue in panels C and F.

Figure 3. Validation of 15-Feature Risk Classifier in Separate Set of BE Patients

A ROC curve for 15-feature risk classifier in validation set. B, C and D: KM analysis of probability of progression to HGD/EAC in validation set patients scored low-, intermediate- and high-risk by the 15-feature risk classifier in patients from all four institutions, US institutions and AMC, respectively. E: HRs and ORs (95% C.I.) for comparisons between risk groups. F: 5-year progression rate as a continuous function of the risk score.