Leveraging Natural Language Processing to Accurately Identify Histologically Confirmed Esophageal and Gastric Premalignant and Malignant Conditions Using a Large-Scale Health-Record Linked Genomic Biobank.

ABSTRACT:

Background and aims

Our understanding of the epidemiology and natural history of gastroesophageal precancerous conditions is limited by a lack of robust analyses using large-scale individual-level data. We aimed to develop and validate a natural language processing (NLP) algorithm to identify and phenotype esophageal and gastric precancerous conditions and cancer and apply this to the Million Veteran Program (MVP), a uniquely powerful nationwide genomic biobank linked to individual-level electronic health record data.

Methods

We identified 121,808 individuals in MVP who underwent upper endoscopy with biopsies. From these, 426 pathology notes from 426 individuals were used to develop and manually validate an NLP rule-based algorithm identifying intestinal metaplasia, dysplasi

SUBMITTER: Giera A 

PROVIDER: S-EPMC12546855 | biostudies-literature | 2026

REPOSITORIES: biostudies-literature