FluChip-8G neural networks matched a cleared influenza test

In FDA's review of the FluChip-8G assay, sensitivity was 87.9% for influenza A and 100.0% for influenza B against a cleared molecular test, with specificities of 98.8% and 99.8%.

  • Not rated an organization

    The assay tested archived swabs against a cleared assay, and no diagnosis or treatment depended on its results.

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

An FDA-cleared influenza molecular assay on the same specimens. Measured.

The system’s part
Not isolated. The study compared the assay's calls with an FDA-cleared molecular assay. It did not compare testing with and without the neural networks.
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
FluChip-8G Influenza A+B Assay
Made by
InDevR, Inc.
Used by
InDevR (clinical study at three US testing sites on archived surveillance swabs)
Where
United States
Stage
Tested in a laboratory
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. 510(k) substantial equivalence determination decision summary for FluChip-8G Influenza A+B Assay (K182513). Cleared 2019-04-22.

    Table 20: FC8G Assay Performance Testing NS and NPS Specimens against the Comparator Assay – Prospective Clinical Study Virus Group (Analyte) Sensitivity Specificity TP/(TP+FN) % 95% CI TN/(TN+FP) % 95% CI Influenza A (Overall) 51/58 87.9% 77.1 – 94.0 915/926 98.8% 97.9 – 99.3
    Influenza B(Overall) 22/22 100.0% 85.1 – 100.0 960/962 99.8% 99.2 – 99.9

Details

AI system

Workflow

Influenza nucleic acids were extracted from the swabs, amplified and hybridized to the microarray. A deterministic decision tree combined the neural network outputs with control signals to give each result.

Follow-up

Conditions for replication

The specimen comes from a patient with signs and symptoms of respiratory infection. A non-seasonal influenza A result is confirmed with public health authorities.

Entry details

Sector

Healthcare.

Purpose

InDevR built the FluChip-8G Influenza A+B Assay to detect influenza A and B in respiratory swabs and to tell seasonal influenza A subtypes from non-seasonal ones.

Not yet checked: model, release, 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, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). FluChip-8G neural networks matched a cleared influenza test (AIBD-0806). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0806.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)

BibTeX Data Field definitions