Reproducibility and Generalizability of the Web-Based Tool to Predict Lamina Propria Fibrosis in Eosinophilic Esophagitis

Girish Hiremath*, Nicoleta C. Arva, Joshua B. Wechsler

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

We investigated reproducibility and generalizability of the recently developed web-based model to predict lamina propria fibrosis (LPF) in esophageal biopsies with inadequate lamina propria (LP) from patients with eosinophilic esophagitis (EoE) using an independent dataset (N = 183). For grade and stage scores of LPF, the area under the curve for predictive model was 0.77 (0.69-0.84) and 0.75 (0.67-0.82), and its accuracy was 78% and 72%, respectively. These model performance metrics were similar to that of the original model. A significant positive correlation was noted between the models' predictive probability and the grade and stage of LPF assessed by a pathologist (grade: r2= 0.48, P < 0.001; and stage: r2= 0.39, P < 0.001). These results support the reproducibility and generalizability of the web-based model to predict the presence of LPF in esophageal biopsies with inadequate LP in EoE. Additional studies are warranted to refine the web-based predictive models to provide predictive probability for sub-scores of LPF severity.

Original languageEnglish (US)
Pages (from-to)93-96
Number of pages4
JournalJournal of pediatric gastroenterology and nutrition
Volume77
Issue number1
DOIs
StatePublished - Jul 1 2023

Funding

G.H. is a consultant for Allakos, Bristol Myers Squibb, Regeneron, and has received speaker fees from Bristol Myer Squibb. J.B.W. is a consultant for Regeneron/Sanofi, InVea Therapeutics, and AstraZeneca, has received research funding from Allakos and Regeneron/Sanofi, and has received speaker fees from Regeneron/Sanofi. The remaining author reports no conflicts of interest. Sources of Funding: G.H. is supported by the NIH K23 (1K23DK13141-01) award. The work was independent of these funding sources. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.

Keywords

  • accuracy
  • area under the curve
  • eosinophilic esophagitis
  • lamina propria fibrosis
  • prediction model

ASJC Scopus subject areas

  • Pediatrics, Perinatology, and Child Health
  • Gastroenterology

Fingerprint

Dive into the research topics of 'Reproducibility and Generalizability of the Web-Based Tool to Predict Lamina Propria Fibrosis in Eosinophilic Esophagitis'. Together they form a unique fingerprint.

Cite this