Diagnosis and Management of Eosinophilic Esophagitis

Clinical presentation and endoscopic findings in adult patients with eosinophilic esophagitis

Background/Aim: The frequency of eosinophilic esophagitis has been rising over the last decades. It is diagnosed primarily based on symptoms and endoscopic and histopathological examination findings. Although eosinophilic esophagitis is not associated with malignancy, it remains an important condition affecting both children and adults, as it is associated with morbidity such as dysphagia, food impaction, and esophageal strictures. This study aimed to define clinical and endoscopic characteristics of adult patients diagnosed with eosinophilic esophagitis based on recently recommended histopathological criteria. Methods: This retrospective cross-sectional descriptive study included 54 adult patients (mean age: 33.6 yr, range: 16–61 yr) who underwent upper gastrointestinal system endoscopy for dyspeptic complaints (epigastric pain, reflux, dysphagia, or food impaction) and diagnosed with eosinophilic esophagitis based on the latest histopathological criteria (≥15 eosinophils per high-power field). Patients with a history of malignancy were excluded. Patients’ clinical, endoscopic, and histopathological data were examined. Results: In patients diagnosed with eosinophilic esophagitis, the most common presenting complaint was dysphagia (61.1%), followed by dyspepsia (24.0%), regurgitation (16.6%), chest pain (16.6%), epigastric pain (12.9%), food impaction (11.1%), and halitosis (3.7%), without any age predilection for the complaints. White papules and linear furrow were the most frequent findings on endoscopic examination (35.1% each), followed by circular rings (24.0%), paleness (22.2%), normal endoscopic finding (20.3%), and small-caliber esophagus (11.1%). Conclusion: The diagnosis of eosinophilic esophagitis remains challenging due to considerable variations in definitions and in the relative frequencies of endoscopic findings. Therefore, we recommend combining clinical, endoscopic, and histologic criteria to establish diagnosis. The identification of standards for diagnosis in future studies is warranted.

Advancing Eosinophilic Esophagitis Diagnosis and Phenotype Assessment with Deep Learning Computer Vision

Eosinophilic Esophagitis (EoE) is an inflammatory esophageal disease which is increasing in prevalence. The diagnostic gold-standard involves manual review of a patient's biopsy tissue sample by a clinical pathologist for the presence of 15 or greater eosinophils within a single high-power field (400× magnification). Diagnosing EoE can be a cumbersome process with added difficulty for assessing the severity and progression of disease. We propose an automated approach for quantifying eosinophils using deep image segmentation. A U-Net model and post-processing system are applied to generate eosinophil-based statistics that can diagnose EoE as well as describe disease severity and progression. These statistics are captured in biopsies at the initial EoE diagnosis and are then compared with patient metadata: clinical and treatment phenotypes. The goal is to find linkages that could potentially guide treatment plans for new patients at their initial disease diagnosis. A deep image classification model is further applied to discover features other than eosinophils that can be used to diagnose EoE. This is the first study to utilize a deep learning computer vision approach for EoE diagnosis and to provide an automated process for tracking disease severity and progression.

The Role of Food Allergy in Eosinophilic Esophagitis

Food allergy is often understood as an IgE-mediated hypersensitivity, characterized by allergic symptoms which occur “immediately” after the ingestion of a relevant food allergen. Increasingly, however, other food-related immune-mediated disorders are recognized in which symptoms can have a delayed onset and IgE does not play a central role. One of the described examples of the latter is eosinophilic esophagitis (EoE) – a disease defined pathologically by local eosinophilic inflammation in the esophagus in the setting of symptoms of esophageal dysfunction. The evidence that EoE is a food-mediated allergic disease includes i) almost all patients respond to an elemental diet and many respond to a diet in which dairy, wheat, eggs and/or soy are eliminated, ii) the presence of food-specific IgE and Th2 cells are consistent with a loss of tolerance to trigger foods and iii) many EoE patients have concomitant IgE-mediated food allergy and other allergic co-morbidities. This narrative review focuses on the hypothesis that EoE is a form of chronic food allergy. The goal is to describe similarities and differences in EoE and IgE-mediated food allergy, and to consider ways that these two increasingly common forms of food allergy are related to each other.