Reusing a prepaid health plan's fecal immunochemical tests for microbiome associations with colorectal adenoma

Abstract

An altered colonic microbiota probably increases colorectal adenoma (CRA) and cancer (CRC) risk, but large, unbiased fecal collections are needed to examine the relationship of gut microbiota diversity and composition to colorectal carcinogenesis. This study assessed whether fecal immunochemical tests (FITs) from CRA/CRC screening may fulfill this requirement. Using FIT, self-collected by members of Kaiser Permanente Hawaii (KPH), as well as interspersed quality control (QC) specimens, DNA was extracted and amplified to generate 16S rRNA microbiome profiles rarified at 10,000 reads. CRA/CRC were diagnosed by colonoscopy and histopathology. Covariates were from electronic KPH records. Of 921 participants' FIT devices, 538 (58%) yielded at least 10,000 rRNA reads and 1016 species-level variants mapped to 46 genera. Of the 538 evaluable participants, 63 (11.7%) were FIT-negative per protocol, and they were considered negative for CRA/CRC. Of the 475 FIT + participants, colonoscopy and pathologic review revealed that 8 (1.7%) had CRC, 71 (14.9%) had high-risk CRA, 107 (22.5%) had low-risk CRA, and 289 (60.8%) did not have CRA/CRC. Men were 2.27-fold [95% confidence interval (CI) 1.32-3.91] more likely than women to be FIT+ . Men also had 1.96-fold (CI 1.24-3.07) higher odds of low-risk CRA, with similar trends for high-risk CRA and CRC. CRA/CRC were not associated with overweight, obesity, diabetes, or antibiotic prescriptions in this study. QC analysis across 24 batches of FIT devices revealed QC outliers in four batches. With or without exclusion of the four QC-outlier batches, as well as lenient (1000-read) rarefaction, CRA/CRC had no consistent, statistically significant associations with fecal microbiome alpha diversity, beta diversity or genera relative abundance. CRA/CRC had expected associations with male sex but not with microbiome metrics. Fecal microbiome profiling using DNA extracted from at-home collected, re-used FIT devices is feasible, albeit with substantial challenges. Using FITs for prospective microbiome studies of CRA/CRC risk should consider the impact of the current findings on statistical power and requisite sample sizes.

Figure 1

Flow chart of specimens, colorectal adenoma (CRA), colorectal carcinoma (CRC), and fecal immunochemistry test (FIT) status of Kaiser Permanente Hawaii participants. High-risk CRA had diameter ≥ 1 cm or villous histology.

Figure 2

Principal coordinate plots of microbiome communities across FIT, CRA, and CRC groups.

Figure 3

Bar plots of estimated coefficients for individual genera relative abundance by diagnosis status. Red bars indicate a nominal significant result at p-value < 0.05 level in unadjusted linear regression.

Figure 4

Estimated richness (Observed Species) and three estimates of alpha diversity (Chao1, Shannon, and PD.whole.tree) are presented across all 24 batches of the 72 quality control (QC) samples. For each box, the central line indicates the mean value, the box is the interquartile range (IQR, 25th to 75th percentile), the whiskers are the largest (or smallest) value within 1.5-times the IQR), and outlier values are dots. Box colors are arbitrary and have no particular meaning.