CINA

K200855

AVICENNA.AI · cleared 2020-06-24 · product code QAS · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.5)
“CINA is a radiological computer-assisted triage and notification software device.”
Algorithmartificial intelligence algorithm, deep learning AI algorithms
source quote (p.5)
“CINA uses an artificial intelligence algorithm to analyze images and highlight cases with detected (1) ICH or (2) LVO on a standalone Web application in parallel to the ongoing standard of care image interpretation. All devices are software packages with similar technological characteristics and principles of operation, and incorporate deep learning AI algorithms that process images, and software to send notifications and to display unannotated preview images.”
Adaptive (vs locked)FDA source did not state this
PCCPNo
Cybersecurity addressedNo

Validation studies (1)

Retrospective clinical

n=1,290 cases · 3 site(s)

endpoints: sensitivity; specificity; time-to-notification; overall agreement; Positive predictive value; negative predictive value

standards: Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices

Reported performance (12 observations)

sensitivity0.914CI 95% CI: 87.2% – 94.5%
source quote (p.7)
“Sensitivity and specificity for the “ICH” prioritization and triage application were observed to be 91.4% (95% CI: 87.2% – 94.5%) and 97.5% (95% CI: 95.8% – 98.6%), respectively.”
specificity0.975CI 95% CI: 95.8% – 98.6%
source quote (p.7)
“Sensitivity and specificity for the “ICH” prioritization and triage application were observed to be 91.4% (95% CI: 87.2% – 94.5%) and 97.5% (95% CI: 95.8% – 98.6%), respectively.”
aurocas written: “auc”0.94
source quote (p.7)
“ROC curve showed an AUC of 0.94.”
sensitivityas written: “Sensitivity (LVO)”0.979CI 95% CI: 94.6% – 99.4%
source quote (p.7)
“Regarding the “LVO” prioritization and triage application, Sensitivity and specificity of 97.9% (95% CI: 94.6% – 99.4%) and 97.6% (95% CI: 95.1% – 99%), respectively were observed.”
specificityas written: “Specificity (LVO)”0.976CI 95% CI: 95.1% – 99%
source quote (p.7)
“Regarding the “LVO” prioritization and triage application, Sensitivity and specificity of 97.9% (95% CI: 94.6% – 99.4%) and 97.6% (95% CI: 95.1% – 99%), respectively were observed.”
aurocas written: “AUC (LVO)”0.98
source quote (p.7)
“ROC curve showed an AUC of 0.98.”
time_to_resultas written: “Time-to-notification (ICH) Mean”21.6CI ± 4.4
source quote (p.8)
“Table 2: Time-to-notification for ICH and LVO image processing applications CINA - ICH 21.6 ± 4.4 (seconds)”
time_to_resultas written: “Time-to-notification (LVO) Mean”34.7CI ± 10.7
source quote (p.8)
“Table 2: Time-to-notification for ICH and LVO image processing applications CINA - LVO 34.7 ± 10.7 (seconds)”
ppvas written: “PPV (ICH) at 25% prevalence”0.924
source quote (p.8)
“Table 1: PPV and NVP values for ICH and LVO image processing applications Prevalence 25% PPV (%) 92.4”
npvas written: “NPV (ICH) at 25% prevalence”0.971
source quote (p.8)
“Table 1: PPV and NVP values for ICH and LVO image processing applications Prevalence 25% NPV (%) 97.1”
ppvas written: “PPV (LVO) at 25% prevalence”0.931
source quote (p.8)
“Table 1: PPV and NVP values for ICH and LVO image processing applications Prevalence 25% PPV (%) 93.1”
npvas written: “NPV (LVO) at 25% prevalence”0.993
source quote (p.8)
“Table 1: PPV and NVP values for ICH and LVO image processing applications Prevalence 25% NPV (%) 99.3”

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
6
drift signals on this device
  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K240942 (decision 2024-09-12) from Avicenna.AI for a matching device line ("CINA-CSpine") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K240942

  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K240612 (decision 2024-05-31) from Avicenna.AI for a matching device line ("CINA-VCF") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K240612

  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K233342 (decision 2024-03-15) from Avicenna.AI for a matching device line ("CINA-ASPECTS") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K233342

  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K233968 (decision 2024-03-13) from Avicenna.AI for a matching device line ("CINA-iPE") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K233968

  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K221716 (decision 2022-11-22) from AVICENNA.AI for a matching device line ("CINA") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K221716

  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K210237 (decision 2021-05-19) from Avicenna.AI for a matching device line ("CINA CHEST") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K210237

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/K200855