Ultrasound Workspace (UWS 6.0)

K241659

Philips Ultrasound LLC · cleared 2025-02-10 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.5)
“Ultrasound Workspace is a clinical software package designed for review, quantification and reporting of structures and function based on multi-dimensional digital medical data acquired with different modalities.”
Algorithmmachine learning algorithms; artificial intelligence for model based segmentation; semi-automated quantitative imaging algorithm
source quote (p.5)
“It performs border detection and tracking to identify each of the LV segments, provides segmental wall motion scores for each segments of the LV by using machine learning algorithms and calculates an overall wall motion score index (WMSI) as the average of the segmental scores. 3D Auto TV software enables semi-automated quantification of the tricuspid valve during transesophageal echocardiography (TEE) and transthoracic echocardiography (TTE) examinations. It applies artificial intelligence for model based segmentation. The SWM software is a semi-automated quantitative imaging algorithm, as users are generally expected to review and concur with the initialization and generated results.”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedYes
source quote (p.19)
“Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions (2023)”

Validation studies (3)

Retrospective clinical

sample size not stated

endpoints: Pearson's correlation coefficient to be >0.8 for each endpoint

Reader study (MRMC)

sample size not stated

endpoints: high agreement of the 3D Auto TV software with the 4D Cardio-View software; Confidence intervals for the limits of agreement were within the acceptance criteria ± 46% and ± 52% for annulus size and annulus shape; Bias was also evaluated for automation performance, where relative bias based on inter-observer variability was met, specifically within +/- 17.37% for distance (size) and +/- 23.68% for circumference (shape); accuracy and precision of the underlying measurement primitives were also evaluated through use of in silico phantoms with known dimensions. Mean relative error of the measurement primitives on the in-silico phantoms were within +/- 1%, with limits of agreement within acceptance criteria of +/- 5%

Retrospective clinical

sample size not stated

endpoints: limits of agreement (LoA) of -49.29 (lower LoA) and 25.09 (upper LoA) and associated confidence intervals: lower end of 95% LoA (-58.37,-40.20) and upper end of 95% LoA (16.01,34.18); acceptance criteria set for the study was defined as maximum allowable difference (Δ) of 61.6 ml; bias was assessed where the acceptance criteria for mean difference (bias) within +/- 19.2ml was met; peak regurgitant flow output from 3D Auto CFQ was also validated against 2D PISA methodology on the same subjects. For both fully-automated and semi-automated 3D Auto CFQ, the upper and lower bounds of the 95% confidence interval for Pearson's correlation exceeded the acceptance criteria of > 0.8 when compared to 2D PISA.

Reported performance (1 observation)

f1as written: “Mean relative error of measurement primitives on in-silico phantoms”stated without valueCI within +/- 1%
source quote (p.20)
“Mean relative error of the measurement primitives on the in-silico phantoms were within +/- 1%, with limits of agreement within acceptance criteria of +/- 5%.”

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); 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/K241659