TriVerity sorted emergency patients by infection type and severity

In FDA's review of TriVerity, 80.4% of bacterial results fell in actionable bands. Severe illness within seven days followed in 58.1% of patients with Very High results and 2.7% with Very Low.

  • Not rated an organization

    Results were not used in care, so no gain in diagnosis or treatment is reported for any hospital.

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

Prevalence of severe illness across the 1,120 patients. Measured.

Without the system
10.9%
With it
58.1% in the Very High band and 2.7% in the Very Low band
The system’s part
Not isolated. The study compared the test's bands with physician adjudication and later outcomes. It did not compare care with and without the test. The summary refers to the training of the classifier but does not describe it.
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
TriVerity
Made by
Inflammatix, Inc.
Used by
Inflammatix (non-interventional SEPSIS-SHIELD study at 22 emergency departments and academic hospitals in the United States and Europe)
Where
22 sites in the United States and Europe
Stage
Tested in a laboratory
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Analyzing Data or Information, 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. 510(k) substantial equivalence determination decision summary for TriVerity (K241676). Cleared 2025-01-10.

    For the forced adjudicated population, 80.4% of the results fell into the clinically actionable Very High, High, Low or Very Low interpretation bands (40.8% Very High and High, 39.6% Very Low and Low interpretation bands); only 19.6% of results were found in the moderate interpretation band which had a LR of 0.9.

Details

AI system

Reported configuration

IMX-BVN-4 and IMX-SEV-4 classifiers

Workflow

Blood was drawn into a PAXgene Blood RNA tube and run on the Myrna instrument. Cut-offs between the interpretation bands were set before the clinical trial on 399 samples from independent sites.

Follow-up

Conditions for replication

The patient is an adult in the emergency department with suspected acute infection or suspected sepsis. Clinicians use the result with clinical assessments and other laboratory findings.

Entry details

Sector

Healthcare.

Purpose

Inflammatix built TriVerity to help emergency clinicians tell bacterial from viral infection and judge the risk of severe illness in adults with suspected acute infection or sepsis.

References

Other identifiers

Clinicaltrials_gov: NCT04094818.

Not yet checked: model, provider, role, configuration, inputs and outputs, autonomy, human oversight, AI contribution, 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, category mappings.

Cite this record

Peter H. Vartanian. (2026). TriVerity sorted emergency patients by infection type and severity (AIBD-0802). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0802.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)

BibTeX Data Field definitions