Kellgren-Lawrence grade sensitivity
0.87 proportion
- EndpointSensitivity for KL grade >= 2
- Population11,775 knees from 6,114 DICOM studies and 1,121 subjects
- Tested versionDeepXray configuration described in K223621
FDA-cleared profile
Alpha Intelligence Manifolds, Inc. · X-ray/Radiography · FDA-cleared (510(k))
Authorized purpose: DeepXray is a fully automated CR or DX radiographic image-processing device intended to aid trained medical professionals in measuring minimum joint-space width, assessing sclerosis, joint-space narrowing, and osteophytes under OARSI criteria, and assessing radiographic knee osteoarthritis under Kellgren-Lawrence grading of standing fixed-flexion knee radiographs. It must not replace full patient evaluation or be relied on alone for diagnosis.
Overview status: Source-reviewed overview
Workflow role has not yet been reviewed for this navigation pilot.
A tag identifies a documented role; it does not establish compatibility or local acceptance. Methods and sources
Clinical takeaway. Clinical role: DeepXray is a fully automated CR or DX radiographic image-processing device intended to aid trained medical professionals in measuring minimum joint-space width, assessing sclerosis, joint-space narrowing, and osteophytes under OARSI criteria, and assessing radiographic knee osteoarthritis under Kellgren-Lawrence grading of standing fixed-flexion knee radiographs. It must not replace full patient evaluation or be relied on alone for diagnosis.
Evidence takeaway. Evidence from the reviewed source record: The exact FDA document reports clinical performance validation on an independent test dataset from one OAI clinical site: 6,125 knee radiographs from 1,121 individuals, with ground truth established by multiple physicians following adjudication. For KL Grade ≥2, sensitivity was 0.87 (95% C.I. 0.86/0.88) and specificity 0.84 (0.83/0.85); sensitivity and specificity were also reported for joint space narrowing, osteophyte and sclerosis. Orthogonal regression slopes against OAI reference measurements were 1.02 (medial mJSW), 0.98 (lateral mJSW) and 0.97 (femoral-tibial angle). Results are as reported in the FDA submission, not independent validation.
Evidence context not reviewed for this FDA record.
Label constraints have not been reviewed for this exact FDA record. Unknown is not all ages or evidence of unsuitability.
Public-label constraints, not patient-level eligibility or a medical recommendation. Training and evaluation populations are separate. Read the original labeling and confirm the exact release and protocol.
Packet wording: "DeepXray’s clinical performance validation was performed on an independent test dataset using data from one of the five clinical sites of the Osteoarthritis Initiative (OAI), a multicenter longitudinal study. This test dataset comprised of 6,125 knee radiographs, representing 1,121 individuals," … "ground truth labeling of Kellgren-Lawrence grades as well as osteophyte, sclerosis, and joint space narrowing grades according to the OARSI criteria, and measurements of the minimum joint space width and femoral-tibial angle were established in the OAI study by multiple physicians following adjudication procedures". Read from the exact FDA decision document on 2026-11-14.
Evidence
Metrics are shown only when they are tied to a source, endpoint, population, and tested product version. Candidate literature without exact product and version linkage is not shown as product evidence.
Packet wording: "DeepXray’s clinical performance validation was performed on an independent test dataset using data from one of the five clinical sites of the Osteoarthritis Initiative (OAI), a multicenter longitudinal study. This test dataset comprised of 6,125 knee radiographs, representing 1,121 individuals," … "ground truth labeling of Kellgren-Lawrence grades as well as osteophyte, sclerosis, and joint space narrowing grades according to the OARSI criteria, and measurements of the minimum joint space width and femoral-tibial angle were established in the OAI study by multiple physicians following adjudication procedures". Read from the exact FDA decision document on 2026-11-14.
Packet wording: "DeepXray Result Sample Number Performance Metric Output (95% C.I.) Sensitivity Kellgren- 11775 knees/ 0.87 (0.86/0.88) (KL Grade ≥2) Lawrence 6114 DICOM/ Grade 1121 subjects" … "Sensitivity 11775 knees/ 0.88 (0.87/0.89) Joint Space (OARSI Grade ≥1) 6114 DICOM/ Narrowing". Read from the exact FDA decision document on 2026-11-14; this is the submission-reported standalone result, not independent validation.
Packet wording: "DeepXray Result Sample Number Performance Metric Output (95% C.I.) Sensitivity Kellgren- 11775 knees/ 0.87 (0.86/0.88) (KL Grade ≥2) Lawrence 6114 DICOM/ Grade 1121 subjects Specificity 0.84 (0.83/0.85) (KL Grade ≥2)" … "Joint Space (OARSI Grade ≥1) 6114 DICOM/ Narrowing Specificity 1121 subjects 0.82 (0.81/0.83) (OARSI Grade ≥1)". Read from the exact FDA decision document on 2026-11-14; this is the submission-reported standalone result, not independent validation.
0.87 proportion
0.84 proportion
0.88 proportion
0.82 proportion
K223621
The FDA summary also reports osteophyte and sclerosis metrics and measurement regressions; four status metrics are promoted here to keep the dossier concise. The source states that automated quality control blocked 0.3% of test samples.
Safety and lifecycle
Recall and adverse-event records are shown only after product matching. Adverse-event reports do not establish incidence or causality.
Exact-identifier review does not prove absence of all product-family safety signals.
Price not public here; enter your quote
Not publicly available: Reviewed sources do not publish an exact-product procurement price with a stated offer scope.
No separate named-product payment identified in reviewed public material
Centers for Medicare & Medicaid Services · United StatesThis is not a product-specific reimbursement determination. Build a local total-cost and value model and verify payer, site-of-service, coding, and coverage assumptions independently.
Match the AI release, system build, configuration and region. Source documentation does not establish acceptance of an installed system.
No specific system/version pairing has completed review for this FDA record. A broad DICOM or product-family statement does not establish a named viewer build's support.
Public source context, not tested interoperability. Each hop needs its own release/configuration evidence. Missing or unavailable routes are not documented incompatibility. All local tests are planned, not passed; no installed-system acceptance is recorded.
Acquisition/source → routing → AI processing → returned objects → viewer/worklist/report → support owner
No specific route context has been source-reviewed for this record. Obtain both endpoint builds and documents; this is not a finding of incompatibility.
Source context, not route validation: Computed or directly digital standing, fixed-flexion knee radiographs in CR or DX format.
Scope: Exact FDA submission.
Confirm scanner/model, protocol, series completeness and both software builds.
Field checked 2026-09-04 · FDA 510(k) K223621: DeepXray
Source context, not route validation: The FDA package describes CR or DX radiograph input, DICOM viewing beside the original radiograph, a browser-based editable report, quality warnings, markup images, and saved or output reports.
Scope: Exact FDA submission. This is the interface boundary described in the exact FDA package; current local compatibility, routing, identity, archive, and downtime behavior still require acceptance testing.
Name gateways, destinations, transfer rules and failure visibility; a DICOM statement does not prove a route.
Field checked 2026-09-04 · FDA 510(k) K223621: DeepXray
Source context, not route validation: The FDA package describes operation in Docker containers on a Linux server with a web-browser report; current hosting, security, service, availability, and local deployment remain unverified.
Scope: Exact FDA submission. This is the release-level boundary described in the exact FDA package; current hosting, contracts, security, availability, upgrade path, and site configuration remain separate evidence.
Confirm processing location, queue ownership, exclusions and exact AI build.
Field checked 2026-09-04 · FDA 510(k) K223621: DeepXray
Source context, not route validation: Minimum joint-space width, femoral-tibial angle, Kellgren-Lawrence grade, OARSI feature assessments, quality warnings, and an editable web report.
Scope: Exact FDA submission.
Confirm object classes, units, references and whether findings, overlays or measurements reach their intended destination.
Field checked 2026-09-04 · FDA 510(k) K223621: DeepXray
Unresolved route: Minimum joint-space width, femoral-tibial angle, Kellgren-Lawrence grade, OARSI feature assessments, quality warnings, and an editable web report.
Scope: Exact FDA submission.
Confirm the named viewer/worklist/report build, display behavior and report transfer. Output support alone does not establish this endpoint. The displayed source describes output, not validated end-to-end delivery.
Field checked 2026-09-04 · FDA 510(k) K223621: DeepXray
Unresolved route: Not established for the exact route.
Scope: Scope not established.
Name the local, platform and AI supplier support owners and escalation path.
No tests below have been performed or accepted.
Agree the evidence and acceptance owner with your team and suppliers. Checkmarks apply to this page only and are not acceptance receipts.
This is the release-level boundary described in the exact FDA package; current hosting, contracts, security, availability, upgrade path, and site configuration remain separate evidence.
This is the interface boundary described in the exact FDA package; current local compatibility, routing, identity, archive, and downtime behavior still require acceptance testing.
This is buyer-facing monitoring guidance derived from the exact cleared or authorized scope; it is not a claim that the FDA package provides a live monitoring service.
Map installed model, build, options, population, anatomy, inputs, outputs, and enabled functions to K223621 before acceptance.
exact submission · checked 2026-09-04Later product-family features are not evidence that this cleared or authorized release includes them.
The FDA package describes operation in Docker containers on a Linux server with a web-browser report; current hosting, security, service, availability, and local deployment remain unverified.
exact submission · checked 2026-09-04FDA-described deployment boundaries do not establish current hosting contracts, security controls, uptime, or local qualification.
The FDA package describes CR or DX radiograph input, DICOM viewing beside the original radiograph, a browser-based editable report, quality warnings, markup images, and saved or output reports.
exact submission · checked 2026-09-04Test representative identifiers, orientation, geometry, measurements, units, routing, failure handling, and round trips locally.
Use a signed local test set for the supported population and workflow. Include common and difficult cases, exclusions, acquisition variation, failed or low-quality inputs, reviewer overrides, and downstream effects. The software must not replace full patient evaluation or be relied on alone for diagnosis; quality control may withhold results and professional review remains required.
exact submission · checked 2026-09-04Define stop-use, escalation, rollback, and revalidation triggers before production use.
Model capital and recurring cost against net staff time after review, throughput, repeat imaging or rework, room time, consumables, infrastructure, training, service, downtime, upgrade, and replacement costs.
product family · checked 2026-09-04No exact-product price was found in the reviewed public material; productivity or value claims require local evidence.
Monitor K223621 by exact hardware, software, model, and algorithm version; patient population; anatomy; protocol; operator; input quality; output edits or overrides; failed studies; repeat acquisition or rework; downstream impact; downtime; incidents; recalls; and updates. Track these product-specific limits: The software must not replace full patient evaluation or be relied on alone for diagnosis; quality control may withhold results and professional review remains required.
exact submission · checked 2026-09-04Revalidate after material software, hardware, model, protocol, interface, or clinical-policy changes. knee radiograph osteoarthritis analysis software limits remain submission-specific.
Regulatory identity
The FDA listing establishes the regulatory identity. It does not by itself establish local workflow fit, pricing, security, or performance in your environment.
Research record
This audit distinguishes completed source review from fields that have not yet been researched.
Five PubMed records were screened. Two concern the different DeepXray Spina bone-density product and three are unrelated legacy uses of the phrase deep X-ray; none evaluates the K223621 knee-osteoarthritis product and version, so all five are quarantined. The current discovery snapshot contains 5 PubMed and 0 ClinicalTrials.gov candidate records; its dated, count-matched human screening remains current. Unlinked candidates remain quarantined. Native FDA recall identifiers produced 0 postmarket candidate records; 0 have been reviewed (0 published, 0 rejected) and 0 remain unreviewed.
Candidate leads were screened against the exact product and tested version. Unlinked records remain quarantined.
Source classes: fda ai list, fda decision summary, acr ai central product, fda decision material, fda pma record, peer reviewed literature, clinical trial registry, reimbursement policy, fda device recall, pubmed, clinical trials, openfda device recall
Recorded state, verification date, notes and sources for fields without a publishable value. Conflicting records stay explicitly unsettled here; no plain settled value is shown for them.
No public list price for the exact cleared or authorized configuration was found. Obtain a written quote separating hardware or license basis, implementation, interfaces, infrastructure, training, service, upgrades, renewal, consumables, and exit costs.
Public materials reviewed for this exact release do not establish the complete security posture. Request data-flow, identity, audit, encryption, retention, remote-access, vulnerability-management, backup, and incident-response evidence.
7 sources - 3 history items
Scope: identity, purpose, clinicalUse, modality, anatomy, intendedUsers, careSetting, workflowRole, input, output, limitations, evidenceSummary
Scope: regulatoryIdentity, modalityContext
Scope: intendedUsers, output, limitations, reportedSensitivity, reportedSpecificity, evidenceSummary, integration, anatomy, evidenceStudies, implementationCapabilities
Scope: evidenceDiscovery
Scope: evidenceDiscovery, studyStatus
Scope: coverage, codingContext
Scope: recallDiscovery, nativeSubmissionMatching
Regulatory record
510(k)
Research record
human reviewed
Editorial review
Source-reviewed editorial overlay
Alternatives
Crescom Co., Ltd.
Authorized purpose: Assist trained professionals in assessing radiographic knee osteoarthritis and its sclerosis, joint-space-narrowing, and osteophyte features on standing fixed-flexion knee radiographs.
Overjet, Inc.
Authorized purpose: Overjet Iris is a web-based dental PACS for storing, viewing, and supporting image-quality review of two-dimensional intraoral radiographs, panoramic images, and color photographs.
Pearl, Inc.
Authorized purpose: Second Opinion Panoramic is an automated image-processing aid that identifies and marks regions of interest for caries, periapical radiolucency, and impacted third molars on panoramic radiographs of permanent teeth in patients aged 16 years and older.
VideaHealth Inc.
Authorized purpose: Analyzes bitewing, periapical, and panoramic intraoral radiographs from patients aged 3 years and older to identify and localize specified suspected dental findings, historical treatments, and normal anatomy; diagnostic use remains with trained dental professionals.
Copy this public context and add the field, proposed wording and original source before sending. Nothing here is submitted automatically. Form-specific prefill has not been verified.
Open existing correction destinationPermission to display a submission is not evidence verification. A submission enters editorial review; it does not approve a public change. Form availability, data entry, receipt, review and publication are separate steps. Data entry and receipt remain unverified.
No entry has been added to this scoped change history for this record. This is not proof that the record never changed.
Correction policy and limits · Public repository change history