Defining a Multi-Omic, AI-Enabled Stool Screening Paradigm for Colorectal Cancer: A Consensus Framework for Clinical Translation

TL;DR

This paper proposes a new stool screening method for colorectal cancer that combines DNA methylation and gut microbiome data using AI to improve detection of precancerous lesions.

Contribution

The novel contribution is a multi-omic framework integrating host DNA methylation and microbiome signals with AI to enhance detection of advanced precancerous lesions.

Findings

Combining DNA methylation and microbiome data improves detection of advanced precancerous lesions.

Microbiome-based models are sensitive to batch effects, requiring standardized pre-analytics and validation strategies.

Scenario modeling suggests a multi-omic approach could detect 13–23 more precancerous lesions per 1000 individuals screened.

Abstract

Most colorectal cancers can be prevented when advanced precancerous lesions are found and removed, yet many people do not undergo colonoscopy. Home stool-based tests help improve access, but current stool DNA tests still miss many advanced precancerous lesions (advanced adenomas and serrated precursors). This review explains why combining two complementary signals from the same stool sample may help: host DNA methylation markers shed from the colon lining and patterns in the gut microbiome. Artificial intelligence (AI) can fuse these signals into a single score and provide clinician-friendly explanations. Because microbiome data are sensitive to collection and laboratory differences, practical steps are outlined to standardize pre-analytics and reduce batch effects. A stepwise evidence-generation roadmap aligned with modern reporting standards is also presented to support real-world clinical translation.

Colorectal cancer (CRC) develops through both conventional adenoma–carcinoma and serrated neoplasia pathways, yet noninvasive screening still under-detects the advanced precursor lesions that enable true cancer prevention. Stool-based screening reduces CRC mortality, but its preventive impact remains constrained by limited detection of advanced precancerous lesions (APLs), including advanced adenomas and sessile serrated lesions. Next-generation multitarget stool DNA assays (mt-sDNA; e.g., Cologuard Plus) have established high sensitivity for CRC and specificity approaching 94%, leaving improved APL detection as the principal opportunity for innovation. This review presents a consensus framework for a multi-omic stool screening paradigm that integrates host epigenetic markers (DNA methylation) with gut microbiome features using artificial intelligence (AI). Multi-omics capture complementary layers of early tumor biology: epithelial shedding and field effects reflected in host methylation signals together with luminal ecological and inflammatory changes represented by microbial features. Evidence from cross-cohort microbiome studies indicates that microbial signatures provide an additive—rather than standalone—axis of information for CRC and its precursor lesions. Because microbiome-based models are highly susceptible to batch effects arising from collection devices, extraction chemistry, sequencing platforms, and bioinformatic pipelines, practical mitigation strategies are outlined, including harmonized pre-analytics, batch-aware study design, leakage-resistant validation, and computational harmonization. A translational roadmap linking analytical validity, locked-model development, and prospective colonoscopy-verified clinical validation is proposed, aligned with TRIPOD + AI, STARD, PROBAST-AI, SPIRIT-AI, CONSORT-AI, and DECIDE-AI reporting standards. Scenario modeling using BLUE-C prevalence estimates suggests that improving APL sensitivity from approximately 43% to 55–65% at ~94% specificity could translate to detecting roughly 13–23 additional advanced precancerous lesions per 1000 individuals screened, highlighting the potential prevention impact of a multi-omic approach. This framework aims to guide developers and clinical investigators toward next-generation stool tests capable of materially improving precursor-lesion detection while maintaining clinically acceptable specificity.

Figures