Abstract 757: Integrating microbiome analysis and multi-modal data to identify high-risk population for esophageal adenocarcinoma

Abstract INTRODUCTION: Esophageal Adenocarcinoma (EAC) represents a pressing public health concern with a rising incidence and a staggering 5-year survival rate of less than 20%, emphasizing the critical need for early detection. Barrett's Esophagus (BE) serves as a well-established precursor to EAC, presenting an opportunity for proactive screening. The salivary microbiome provides a novel opportunity to identify a high-risk population with early-stage esophageal diseases. Here, we assessed whether the oral microbiome, in combination with lifestyle and clinical data, is associated with esophageal disease progression. METHODS: The study included n=23 esophageal adenocarcinoma patients, n=51 with Barrett's Esophagus, and n=32 healthy controls. Saliva samples were collected along with comprehensive lifestyle, dietary intake, and clinical data. Shotgun Metagenomics Sequencing was employed to investigate the microbiome composition of participants. Comprehensive microbiome analyses were performed to evaluate taxonomic profiles, including microbial abundance, microbiome diversity, and functional/metabolic insights. A multi-modal data integration strategy was used to incorporate data from the Diet Health Questionnaire (DHQ) and lifestyle and health records, aiming to utilize these multimodal features to predict esophageal disease formation and progression. RESULTS: A significant difference was observed in the salivary microbiome beta diversity between healthy controls and esophagus disease groups (p= 0. 03). Clustering by microbiome taxonomic composition using the Dirichlet Multinomial Mixtures (DMM) framework indicates that some microbial signatures are associated with esophageal diseases (p=0. 03). Healthy Eating Index Scores, total score (p=0. 01) ; vegetables (p=0. 003) ; greens, and beans score (p=0. 009) were significantly different between study groups. Microbial pathways associated with diet, microbial taxa linked to lifestyle and medications, and supervised classification results reveal group characteristics and diversity variations based on key covariates such as B12 and sugar uptakes. CONCLUSION: The study presents an innovative analytic approach to identify high-risk populations for esophageal diseases by integrating microbiome analysis and multi-modal data, providing insights into early detection and prevention. The potential of this research lies in its ability to revolutionize screening strategies, offering a non-invasive and cost-effective means to identify individuals at risk of EAC at earlier, more treatable stages. Citation Format: Duygu Altinok Dindar, Madeline Krieger, Amy Palma, John Cheney, Fouad Otaki, Jessica Yu, Stephanie Wood, Thomas J. Sharpton, James McGann, Lisa Karstens, Gurkan G. Yardimci, Zhenzhen Zhang. Integrating microbiome analysis and multi-modal data to identify high-risk population for esophageal adenocarcinoma abstract. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts) ; 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84 (6Suppl): Abstract nr 757.