HipCheck

K230045

Stryker Corp. · cleared 2023-09-29 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.4)

“The software is provided to the user pre-installed on a mobile touchscreen tablet for which it has been tested for compatibility. Stryker conducted standalone performance testing on an object detection AI/ML model that is a part of the image processing pipeline.”

Algorithmobject detection AI/ML model and Alpha Angle algorithm using extraction of the region of interest, extended Gabor filtering, binary edge detection and classification, circular Hough transformation, feature point tracing, RANSAC circle matching, and target circle selection.

source quote (p.8)

“Stryker conducted standalone performance testing on an object detection AI/ML model that is a part of the image processing pipeline. Updating to HipCheck version 1.5.6's Alpha Angle algorithm has been done to enhance capabilities of the algorithm on uncommon image types (i.e., corner cases) while maintaining consistent capabilities on other image types. Extraction of the region of interest Extended Gabor filtering Binary edge detection and classification Circular Hough transformation Feature point tracing RANSAC circle matching Target circle selection”

Adaptive (vs locked)FDA source did not state this

PCCPNo

Cybersecurity addressedNo

Validation studies (2)

Bench

n=745 images

endpoints: Automatically detects the presence or absence of a hip; Finds the region of the image that contains the femur with high accuracy; Head center X coordinate is within +3.3%/-3.3; Head center Y coordinate is within +3.8%/-3.8%; Neck Angle relative to vertical is within +13.63°/-15.35°

Bench

sample size not stated

endpoints: segmentation accuracy and reliability; reliability of segmentation between Stryker personnel; reliability of the HipMap FAI Analysis by comparing clinical measurement outputs generated from the third-party segmentation (external rater vs internal rater), Stryker employee segmentations (inter-rater reliability), and iterations of segmentations performed by the same Stryker employee (intra-rater reliability).

Reported performance (3 observations)

accuracyas written: “Head center X coordinate accuracy”stated without valueCI within +3.3%/-3.3

source quote (p.11)

“Head center X coordinate is within +3.3%/-3.3”

accuracyas written: “Head center Y coordinate accuracy”stated without valueCI within +3.8%/-3.8%

source quote (p.11)

“Head center Y coordinate is within +3.8%/-3.8%”

accuracyas written: “Neck Angle relative to vertical accuracy”stated without valueCI within +13.63°/-15.35°

source quote (p.11)

“Neck Angle relative to vertical is within +13.63°/-15.35°”

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).