Premarket evidence — what FDA accepted

Device typesamd

source quote (p.5)

“The SMART Bun-Yo-Matic CT device is an automatic software tool that segments foot and ankle bones from computed tomography (CT) images and provides a case report showing images of a 3D model of the segmented structures with pre-operative and post-correction measurements. The correction is for hallux valgus through a Lapidus Arthrodesis procedure. The case report also provides parameters of an orthopedic surgical instrument and an example of an implant construct for the procedure. The device includes machine learning derived outputs.”

Algorithmmachine learning

source quote (p.5)

“The device includes machine learning derived outputs. The AI algorithm for bone identification was developed using 145 CT image studies and metal identification was developed using 130 CT image studies.”

Adaptive (vs locked)FDA source did not state this

PCCPFDA source did not state this

Cybersecurity addressedFDA source did not state this

Validation studies (3)

Retrospective clinical

n=82 images

Bench

sample size not stated

endpoints: 95% model conformance within 1.0mm distance to reference model and 2.0 degrees standard deviation for angular measurements; estimated correction +1 degree for angular measurements and ext{SMART Bun-Yo-Matic CT software provides: Visualization report of the three-dimensional mathematical models of the anatomical structures of foot and ankle and three-dimensional models of orthopaedic fixation devices, Measurement templates containing radiographic measures of foot and ankle, Surgical planning application for visualization of foot and ankle anatomical three-dimensional structures, radiographic measures, and surgical instrument parameters.

Bench

sample size not stated

Reported performance (2 observations)

sensitivity100

source quote (p.5)

“The existence of metal was identified correctly for 98.8% of the images (specificity 98%, sensitivity 100%).”

specificity98

source quote (p.5)

“The existence of metal was identified correctly for 98.8% of the images (specificity 98%, sensitivity 100%).”

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

1

drift signals on this device

re_clearance
The FDA AI/ML device list shows a newer 510(k) K240736 (decision 2024-07-02) from Disior Ltd for a matching device line ("SMART Bun-Yo-Matic X-Ray") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K240736

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).