Careverse CoronaryDoc (Careverse CoronaryDoc)

K251656

Careverse Technology Pte. Ltd. · cleared 2025-09-04 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.4)

“Careverse CoronaryDoc is a web-based software application”

AlgorithmThe software automatically extracts the coronary region, detects suspected stenosis lesions, performs automatic plaque analysis, and detects stents and bridges.

source quote (p.6)

“Based on the axial image data of coronary computed tomography angiography (CCTA), Careverse CoronaryDoc automatically extracts the coronary region, detects suspected stenosis lesions in this area, and further performs automatic plaque analysis. At the same time, the software can also automatically detect stents and bridges.”

Adaptive (vs locked)FDA source did not state this

PCCPNo

Cybersecurity addressedYes

source quote (p.10)

“Guiding Principles for Cybersecurity Registration Review of Medical Devices (2022)”

Validation studies (1)

Reader study (MRMC)

n=1,116 other

endpoints: segmentation performance (Dice Coefficient and 95% Hausdorff Distance); labeling performance (accuracy on case level and accuracy on vessel level); stenosis performance (agreement percentage); plaque performance (Pearson Correlation Coefficient and Bland-Altman Agreement)

standards: ISO 14971:2019, ISO/TR 24971:2020, ISO 13485:2016, IEC 62304:2015, GB/T 25000.51-2016, General Principles of Software Validation; Final Guidance for Industry and FDA Staff, CDRH and FDA, Jan. 11, 2012, Guiding Principles for Cybersecurity Registration Review of Medical Devices (2022), Guidelines for On-site Inspection of Independent Software in Good Manufacturing Practice for Medical Devices (2020)

Reported performance (3 observations)

diceas written: “Dice Coefficient”0.899

source quote (p.9)

“The value of Dice Coefficient is 0.899”

accuracyas written: “Labeling accuracy (case level)”93.1

source quote (p.9)

“the accuracy on case level is 93.10%”

accuracyas written: “Labeling accuracy (vessel level)”98.21

source quote (p.9)

“the accuracy on vessel level is 98.21%”

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

recalls in product code, 24mo

MAUDE reports in code, 12mo

—

vs code's own 3-yr baseline

drift signals on this device

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device). 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).