ColoSense stool RNA test found 25 of 27 colorectal cancers

In FDA's review of ColoSense, the stool RNA test detected 92.6% of colorectal cancers and 41.3% of advanced precancerous lesions in 7,763 adults, with 85.6% specificity.

  • Not rated an organization

    Every participant also had a colonoscopy, so the test changed no screening decision in the study.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Intended benefit.
Evidence

foundstudiedreportedclaimed

An independent regulatory document supports the benefit.

Compared with

The FIT component of ColoSense alone, in the same adults. Measured.

Without the system
Cancer sensitivity 77.8%
With it
Cancer sensitivity 92.6%
The system’s part
FDA reviewers compare ColoSense with its own FIT component alone in the same adults, and the RNA model raised cancer sensitivity from 77.8% to 92.6%. The summary gives no specificity for FIT alone. It describes a model fitted with cross-validation and does not call it machine learning.
Limits
Not yet checked.
Costs and harms
Not yet checked.
Later
Not yet checked.

Download data Cite Suggest a correction

Benefit type
Improved Task Accuracy
System
ColoSense
Made by
Geneoscopy, Inc.
Used by
Geneoscopy (CRC-PREVENT study with participants from 48 US states)
Where
United States (48 contiguous states)
Stage
In a pilot
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Identifying Objects, Actions, and Events
Collections
Scrutiny and findings
Last revised
31 October 2026

Sources

  1. Regulatory document, by authors with no tie to the system.

    U.S. Food and Drug Administration, Center for Devices and Radiological Health. Summary of Safety and Effectiveness Data for ColoSense (P230001). Approved 2024-05-03.

    The ColoSense test had a CRC sensitivity of 92.6% (25/27, 2-sided 95% CI: 76-99%) and APL (AA/SPL) sensitivity of 41.3% (253/612). The AA sensitivity was 44.9% (231/514) and SPL sensitivity was 22.4% (22/98). The specificity in the non-NAPL or NEG group was 85.6% (2-sided 95% CI: 85%-86%).

Details

AI system

Workflow

Participants collected stool at home with the ColoSense Collection Kit and mailed it to a single laboratory. Laboratory technicians ran the test blinded to colonoscopy results.

Follow-up

Conditions for replication

The adult is 45 or older and at average risk for colorectal cancer. A positive result is followed by colonoscopy.

Entry details

Sector

Healthcare.

Purpose

Geneoscopy built ColoSense to screen adults aged 45 and over at average risk for colorectal cancer with a stool test that detects cancer and advanced precancerous lesions.

Not yet checked: model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). ColoSense stool RNA test found 25 of 27 colorectal cancers (AIBD-0814). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0814.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)

BibTeX Data Field definitions