OsteoSight™ Hip (v1)

K251408

Naitive Technologies Ltd · cleared 2025-09-02 · product code SAO · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.6)
“OsteoSight is an AI-enabled software as a Medical Device (SaMD) that processes standard anteroposterior (AP) radiographs of the hip or pelvis in patients aged 50 years and older.”
AlgorithmAI-enabled algorithm pipeline, Supervised Machine Learning (ML)
source quote (p.6)
“OsteoSight applies an AI-enabled algorithm pipeline to estimate bone mineral density (BMD) at the femoral neck. If an estimated BMD is below the pre-specified threshold, OsteoSight generates a report indicating that the patient is at risk of having low BMD. This report is delivered to the interpreting physician via the host integration platform. OsteoSight does not provide a diagnosis or treatment recommendation. If the estimated BMD is above or equal to the pre-specified threshold, no report is generated. Supervised Machine Learning (ML)”
Adaptive (vs locked)FDA source did not state this
PCCPNo
Cybersecurity addressedNo

Validation studies (1)

Retrospective clinical

n=3,082 patients · 6 site(s)

endpoints: sensitivity; specificity

standards: ISO 14971, BS EN 62366, IEC 62304

Reported performance (5 observations)

sensitivity0.37CI 0.349-0.391
source quote (p.15)
“When calculated across the entire intended use population, including cases where no result was produced, sensitivity was 0.370 (95% CI 0.349-0.391)”
specificity0.951CI 0.936-0.963
source quote (p.15)
“specificity was 0.951 (95% CI 0.936-0.963)”
aurocas written: “AUC (subset)”0.837CI 0.821-0.853
source quote (p.15)
“Among patients in whom a result was generated, the area under the ROC curve (AUC) was 0.837 (95% CI 0.821-0.852).”
sensitivityas written: “Sensitivity (subset)”0.441CI 0.386-0.487
source quote (p.15)
“Sensitivity for detecting low BMD was 0.441 (95% CI 0.386-0.487)”
specificityas written: “Specificity (subset)”0.943CI 0.922-0.961
source quote (p.15)
“specificity was 0.943 (95% CI 0.922-0.961)”

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
0
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/K251408