Standalone sensitivity
0.9611 proportion
- EndpointImage-level fracture detection
- PopulationPediatric patients aged 2 years or older; all indicated study types and views, 3,016 radiographs
- Tested versionRayvolve (K240845)
FDA-cleared profile
AZmed SAS · X-ray/Radiography · FDA-cleared (510(k))
Authorized purpose: Assists radiologists and emergency physicians in detecting fractures on DICOM musculoskeletal radiographs for adults and children aged 2 years or older, limited to the FDA-listed anatomic areas and standard views (ankle, clavicle, elbow, forearm, hip, humerus, knee, pelvis, shoulder, tibia/fibula, wrist, hand, and foot); it is an aided-diagnosis device and does not operate autonomously.
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: Assists radiologists and emergency physicians in detecting fractures on DICOM musculoskeletal radiographs for adults and children aged 2 years or older, limited to the FDA-listed anatomic areas and standard views (ankle, clavicle, elbow, forearm, hip, humerus, knee, pelvis, shoulder, tibia/fibula, wrist, hand, and foot); it is an aided-diagnosis device and does not operate autonomously.
Evidence takeaway. Evidence from the reviewed source record: The exact FDA submission reports standalone pediatric performance on 3,016 radiographs across all indicated study types and views: sensitivity 0.9611, specificity 0.8597, and ROC-AUC 0.9399. The submission states that no new clinical study was conducted for K240845 and references the predicate Rayvolve clinical reader study separately.
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.
The 3,016-case results are standalone pediatric testing; do not merge them with predicate adult clinical-reader results.
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.
The 3,016-case results are standalone pediatric testing; do not merge them with predicate adult clinical-reader results.
Endpoint is image-level standalone sensitivity for the pediatric dataset; the structured metric records the paired specificity and AUC separately.
Endpoint is image-level standalone specificity for the pediatric dataset.
0.9611 proportion
0.8597 proportion
0.9399 ROC-AUC
K240845
The FDA packet states that no clinical study was conducted in support of K240845; this standalone assessment supported inclusion of the pediatric population.
K240845
Baseline ACR summary retained; FDA packet details above control endpoint and pediatric scope.
Safety and lifecycle
Recall and adverse-event records are shown only after product matching. Adverse-event reports do not establish incidence or causality.
No native submission-identifier match was found in the checked openFDA radiology recall snapshot. Product-name, manufacturer, and adverse-event searches remain necessary; this does not establish that no recall or safety report exists.
Price not public here; enter your quote
Not verified: Pricing information is recorded but not verified against a resolving source.
NICE HTG739 conditionally recommends Rayvolve for NHS use during a two-year evidence-generation period, subject to evidence-generation agreements and appropriate regulatory and DTAC approval; this is not a reimbursement determination.
NICE guidance for the NHS in England · England · Effective 2025-01-14NICE's exploratory model uses GBP 1 per scan and says actual software, implementation, and postmarket costs are uncertain. This is not a vendor quote or US coverage evidence.
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: DICOM radiographs from a DICOM Node or PACS, limited to the FDA-listed musculoskeletal study types and standard views: ankle, clavicle, elbow, forearm, hip, humerus, knee, pelvis, shoulder, tibia/fibula, wrist, hand, and foot.
Scope: Exact FDA submission.
Confirm scanner/model, protocol, series completeness and both software builds.
Field checked 2026-09-07 · FDA 510(k) K240845: Rayvolve
Source context, not route validation: The FDA packet describes current-edition DICOM interaction with existing DICOM Node servers such as PACS and clinical-grade viewers, with prediction output delivered as a processed DICOM image after the original.
Scope: Exact FDA submission. Specific interface versions, routing, viewer behavior, and local compatibility remain acceptance-test items.
Name gateways, destinations, transfer rules and failure visibility; a DICOM statement does not prove a route.
Field checked 2026-09-07 · FDA 510(k) K240845: Rayvolve
Source context, not route validation: On-premise or cloud platform connected to the radiology center local network and DICOM Node server.
Scope: Exact FDA submission. The FDA summary does not establish current hosting region, retention, security controls, uptime, or commercial configuration.
Confirm processing location, queue ownership, exclusions and exact AI build.
Field checked 2026-09-07 · FDA 510(k) K240845: Rayvolve
Source context, not route validation: Rayvolve outputs a prediction of potential fracture presence or absence and a processed image with bounding-box annotations localizing detected fractures; the initial image appears first and the processed image follows in the DICOM workflow, with annotations toggleable in the PACS/viewer.
Scope: Exact FDA submission.
Confirm object classes, units, references and whether findings, overlays or measurements reach their intended destination.
Field checked 2026-09-07 · FDA 510(k) K240845: Rayvolve
Unresolved route: Rayvolve outputs a prediction of potential fracture presence or absence and a processed image with bounding-box annotations localizing detected fractures; the initial image appears first and the processed image follows in the DICOM workflow, with annotations toggleable in the PACS/viewer.
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 2026-09-07 · FDA 510(k) K240845: Rayvolve
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.
The FDA summary does not establish current hosting region, retention, security controls, uptime, or commercial configuration.
Specific interface versions, routing, viewer behavior, and local compatibility remain acceptance-test items.
The exact FDA packet describes interaction with existing DICOM Node servers such as PACS and clinical-grade viewers, with the original image followed by the processed image containing fracture prediction and localization.
exact submission · checked 2026-09-07Test representative identifiers, routing, image ordering, annotation toggles, and failure handling locally.
The FDA packet describes on-premise and cloud operation connected to the radiology center local network and DICOM Node server.
exact submission · checked 2026-09-07Current hosting, PHI flow, retention, and service commitments are not established.
AZmed's current Rayvolve page describes local PACS/workflow integration in a radiology customer testimonial and presents Rayvolve as an AI second opinion for fracture detection.
product family · checked 2026-09-07Vendor page and testimonial; it does not establish a specific connector, PACS version, SLA, or local deployment result.
The NIHR/NICE early value assessment table describes Rayvolve in the assessed NHS context as using DICOM radiographs and integrating into existing hospital radiology workflows through Wellbeing's AI Connect gateway. That assessment lists Rayvolve as adult-only for its evaluated context, whereas the exact K240845 FDA indication includes pediatric patients aged 2 years or older.
product family · checked 2026-09-07Historical assessment context; do not use it to narrow or expand the exact FDA indication without the K240845 packet.
NICE HTG739 conditionally recommends Rayvolve for use in NHS urgent care while evidence is generated and calls for local disagreement protocols plus monitoring of accuracy, software failures, downstream referrals, treatment changes, implementation cost, subgroups, and postmarket surveillance.
product family · checked 2026-09-08English NHS health-technology guidance; not exact K240845 pricing, reimbursement, or US adoption evidence.
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.
Controlled anatomy normalization from the listed osteoarticular study types.
Research record
This audit distinguishes completed source review from fields that have not yet been researched.
The stored evidence-candidates metadata and identifier lists were screened in order. This was metadata screening, not a full paper or ClinicalTrials.gov record review; no candidate abstract or full text is promoted here. The current discovery snapshot contains 9 PubMed and 1 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, vendor product page, health technology assessment, literature index, trial registry, 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 current exact-product price or contract terms were established from the reviewed public sources. The NICE assessment used a notional cost input, not a vendor quote.
Bounded web search on 2026-10-26 (query: "AZmed Rayvolve reimbursement CPT"; top results reviewed) found no vendor or payer page stating coding, coverage or payment for this product. This records what was found, not that none exists; eligibility depends on payer, site of service and use case.
The FDA comparison table contains a privacy characteristic, but the reviewed sources do not establish the current commercial security architecture, retention, access controls, audit, or incident-response terms.
The FDA packet says instructions for use are transmitted and used to train users; current onboarding, competency, and support commitments were not established.
Local acceptance testing, production monitoring, drift review, update control, and incident escalation remain to be qualified.
10 sources - 3 history items
Scope: regulatoryIdentity, purpose, modality, anatomy
Scope: regulatoryIdentity, modalityContext
Scope: purpose, modality, intendedUsers, careSetting, output, reportedSensitivity, reportedSpecificity, evidenceSummary, integration, anatomy, evidenceStudies, implementationCapabilities
Scope: evidenceDiscovery
Scope: evidenceDiscovery, studyStatus
Scope: recallDiscovery, nativeSubmissionMatching
Scope: identity, clinicalUse, modality, anatomy, workflow, evidence, implementation
Scope: productFamily, clinicalWorkflow, PACS, implementationCapabilities
Scope: productFamily, implementationContext, populationContext
Scope: conditionalAdoption, economics, evidenceGaps, implementationCapabilities
Regulatory record
510(k)
Research record
human reviewed
Editorial review
Source-reviewed editorial overlay
Alternatives
Milvue
Authorized purpose: Aids clinicians and radiologists reviewing 2D X-ray radiographs by detecting, localizing, and characterizing fractures across the FDA-listed appendicular, hip/pelvis, clavicle, and thorax/rib examinations, and by detecting elbow joint effusion on lateral elbow or forearm views in children/adolescents and adults; results are not standalone clinical decisions.
Imagen Technologies, Inc.
Authorized purpose: Assists clinicians in detecting fractures during review of adult musculoskeletal radiographs.
Naitive Technologies Ltd
Authorized purpose: Opportunistically analyzes standard AP hip or pelvis radiographs in patients aged 50 years and older and issues a report when the estimated femoral-neck BMD is below a preset threshold to prompt clinical bone-health assessment; absence of a report does not rule out low BMD.
Velmeni, Inc.
Authorized purpose: Concurrent-read CADe to assist dentists in detecting specified tooth and jaw anatomy, bone-level landmarks, and root-canal-treated teeth in digital radiographs of permanent teeth in patients 15 years or older.
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