Radify Triage

K231871

Envisionit DeepAI Ltd · cleared 2024-01-17 · product code QFM · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.3)
RADIFY® Triage is a radiological computer-assisted triage and notification software that analyzes adult chest X-ray images for the presence of pre-specified suspected critical findings (pleural effusion and/or pneumothorax).
AlgorithmDeep Convolutional Neural Networks (DCNN)
source quote (p.5)
Artificial Intelligence Algorithm(s) – Deep Convolutional Neural Networks (DCNN)
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this

Validation studies (1)

Retrospective clinical

n=1,229 scans · 4 site(s)

endpoints: triaging of pneumothorax; triaging of pleural effusion

standards: FDA's Guidance for Industry and FDA Staff, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices."

Reported performance (10 observations)

sensitivity94.26CI 93.53, 94.99
source quote (p.13)
94.26 95% CI (93.53, 94.99)
specificity97.27CI 96.54, 98.00
source quote (p.13)
97.27 95% CI (96.54, 98.00)
aurocas written: “auc97.62CI 97.43 97.81
source quote (p.13)
97.62 95% CI (97.43 97.81)
aurocas written: “AUC (Pneumothorax)97.43CI 97.12, 97.74
source quote (p.10)
AUC: 97.43 (95% CI: [97.12, 97.74])
sensitivityas written: “Sensitivity (Pneumothorax)94.81CI 93.90, 95.73
source quote (p.10)
Sensitivity 94.81% (95% CI: [93.90, 95.73])
specificityas written: “Specificity (Pneumothorax)97.91CI 97.00, 98.83
source quote (p.10)
Specificity 97.91% (95% CI: [97.00, 98.83])
aurocas written: “AUC (Pleural Effusion)97.61CI 97.36, 97.86
source quote (p.10)
AUC: 97.61 (95% CI: [97.36, 97.86])
sensitivityas written: “Sensitivity (Pleural Effusion)94.39CI 93.26, 95.51
source quote (p.10)
Sensitivity 94.39% (95% CI: [93.26, 95.51])
specificityas written: “Specificity (Pleural Effusion)96.42CI 95.29, 98.00
source quote (p.10)
Specificity 96.42% (95% CI: [95.29, 98.00])
time_to_resultas written: “Average notification time3
source quote (p.12)
The performance time averaged at 3s.

Each value carries its own analysis unit and task — never compare or pool across devices. Source: 510(k) summary PDF.

Predicate network

Postmarket — what happened after clearance

0
recalls in product code, 24mo
0
MAUDE reports in code, 12mo
vs code's own 3-yr baseline
0
drift signals on this device

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device); a recall is shown as device-attributed only when the recall record itself lists this clearance number. Signals are descriptive observables with sources — never a judgment that the device is unsafe or drifting. Snapshot 2026-07-08.

Reimbursement — how devices like this got paid

Not yet tracked — no payment pathway indexed for this clearance (the reimbursement corpus is a growing seed set).

Applicable FDA guidance — what the submission is measured against

FDA guidance documents and guiding principles applicable to 510(k) AI/ML devices in the Radiology panel. A curated reference index, not legal or regulatory advice — each item states its own status, and a draft is never binding.

Applicability is derived from the device's FDA advisory panel and pathway — cross-cutting guidances apply to every AI/ML device; panel-specific ones are flagged. Titles, dates, and links verified against fda.gov as of July 2026.

Constat Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: constat.dev/precedent/device/K231871