DeepXray

K223621

Alpha Intelligence Manifolds, Inc. · cleared 2023-09-08 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.4)
“DeepXray is a standalone software device that utilizes artificial intelligence (AI) and computer vision algorithms to assist clinical professionals in analyzing and measuring radiographic abnormalities of knee osteoarthritis (OA) during review of posterior-anterior or anterior-posterior knee radiographs.”
Algorithmartificial intelligence (AI) and computer vision algorithms trained on medical images
source quote (p.5)
“DeepXray and predicate devices all utilize computer vision (CV) as well as artificial intelligence (AI) algorithms trained on medical images to perform automated image processing tasks such as knee detection, landmark detection, and joint space detection.”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this

Validation studies (1)

Retrospective clinical

n=1,121 patients · 1 site(s)

endpoints: Sensitivity (KL Grade ","2); Specificity (KL Grade ","2); Sensitivity (OARSI Grade ","1); Specificity (OARSI Grade ","1); Sensitivity (Presence/Absence); Specificity (Presence/Absence); Slope; Intercept

Reported performance (8 observations)

sensitivity0.87CI 0.86/0.88
source quote (p.8)
“0.87 (0.86/0.88)”
specificity0.84CI 0.83/0.85
source quote (p.8)
“0.84 (0.83/0.85)”
sensitivityas written: “Sensitivity (OARSI Grade ","1) for Joint Space Narrowing”0.88CI 0.87/0.89
source quote (p.8)
“0.88 (0.87/0.89)”
specificityas written: “Specificity (OARSI Grade ","1) for Joint Space Narrowing”0.82CI 0.81/0.83
source quote (p.8)
“0.82 (0.81/0.83)”
sensitivityas written: “Sensitivity (OARSI Grade ","1) for Osteophyte”0.86CI 0.85/0.87
source quote (p.8)
“0.86 (0.85/0.87)”
specificityas written: “Specificity (OARSI Grade ","1) for Osteophyte”0.8CI 0.79/0.81
source quote (p.8)
“0.80 (0.79/0.81)”
sensitivityas written: “Sensitivity (Presence/Absence) for Sclerosis”0.84CI 0.83/0.85
source quote (p.8)
“0.84 (0.83/0.85)”
specificityas written: “Specificity (Presence/Absence) for Sclerosis”0.88CI 0.87/0.89
source quote (p.8)
“0.88 (0.87/0.89)”

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/K223621