A Multimodal Stool Rna, Fit and Machine Learning Concept for Detection of Advanced Precancerous Lesions and Colorectal Cancer

Accurate and effective early detection of colorectal cancer (CRC) and advanced precancerous lesions (APLs) is still a challenge. The purpose of this study was to evaluate the clinical performance of a novel, non-invasive multimodal stool RNA test (mm-stRNA) that combines five human messenger RNA (mRNA) biomarkers and a fecal immunochemical test (FIT) in a machine learning (ML)-generated algorithm, for the sensitive detection of APLs and CRCs. For this purpose, stool samples from 265 subjects (34 CRCs, 68 APLs and 163 controls) were evaluated as part of the eAArly DETECT study, a US multi-site study with subjects suspected to have at least one APL or CRC, as well as average-risk individuals. FIT was evaluated with clinical positivity thresholds of 5 µg hemoglobin (Hb)/g of stool and 17 µg Hb/g. RNA was isolated from stabilized stool and analyzed for the expression levels of five mRNA biomarkers. Lab data were analyzed using a machine learning-generated algorithm that was developed in a stratified split-sample design and then applied as a locked model to the full 265-subject cohort. The mm-stRNA test achieved 97.1% sensitivity for CRC and 83.8% sensitivity for APLs, with 95.7% specificity. FIT sensitivity was 76.5 % vs. 70.6% for CRC and 45.6% vs. 36.8% for APL with a specificity of 84.0% vs. 90.8% when applying the cut-off levels 5 µg Hb/g vs. 17 µg Hb/g, respectively. The mm-stRNA approach appeared to have substantially improved performance compared to existing tests, but results need to be replicated in an independent prospective cohort.