Sonix Health

K240645

Ontact Health Co., Ltd · cleared 2024-11-27 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.6)
Sonix Health will be offered as SW only, to be installed directly on customer PC hardware. Sonix Health is DICOM compliant and is used within a local network.
Algorithmtwo-step algorithm; single identification model for view identification; deep learning algorithm for B-mode, M-mode, and Doppler algorithms for the second step; main algorithm identifies view and segments anatomy
source quote (p.6)
Sonix Health utilizes a two-step algorithm. A single identification model identifies a view in the first step. The second step performs the deep learning algorithm according to the view. The deep learning algorithms for the second step are categorized as B-mode, M-mode, and Doppler algorithms. The main algorithm of Sonix Health is to identify the view and segment the anatomy in the image.
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedYes
source quote (p.9)
Throughout the verification and validation process, traceability was maintained, encompassing risk management (including Cyber Security and Usability).

Validation studies (1)

Retrospective clinical

n=335 patients · 2 site(s)

endpoints: average accuracy of 96.25% for the additional views in the ‘View Recognition' software; average correlation coefficient of 0.918 for 'Auto Measure'; average correlation coefficient of 0.88 for LVGLS values and LARS and LACts for 'Auto Strain'; correlation coefficient 0.69 of RV Free wall strain; RMSE of 2.16% for average GLS; RMSE was 6.32% for Segmental Longitudinal Strain

standards: Digital Imaging and Communications in Medicine (DICOM) Set (Ps3.1 - .20), IEC 62304:2006, Medical Device Software - Software Life Cycle Processes., ISO 14971 Second edition 2007-03-01, Medical devices - Application of risk management to medical devices., IEC 62366-1 Edition 1.1 2020-06, Medical devices-Part 1 Application of usability engineering to medical devices.

Reported performance (1 observation)

accuracyas written: “average accuracy for 'View Recognition' software96.25
source quote (p.9)
it achieved an average accuracy of 96.25% for the additional views in the ‘View Recognition' software (exceeding the acceptable threshold of 84%)

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
3
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). 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).

RIGOR™ Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: radar.healthai.com/precedent/device/K240645