Input or output interoperability
DICOM is explicitly referenced in the described input, output, or workflow.
exact submission · checked 2026-09-01The model card does not establish every supported DICOM object, transfer method, or local interface.
FDA-cleared profile
Saige-Q
DeepHealth, Inc.
Authorized purpose: Provides passive worklist prioritization for compatible FFDM and DBT screening mammograms.
Evidence status: each field states its source quality, applicability, and review date. Research pending, information not established, and vendor documentation pending remain distinct outcomes.
Product overview
Start with the essentials
Authorized purpose: Provides passive worklist prioritization for compatible FFDM and DBT screening mammograms.
Overview status: Source-reviewed overview
- What does this software do? Authorized purpose: Provides passive worklist prioritization for compatible FFDM and DBT screening mammograms.
- Which images or clinical context are in scope? Modality: Mammography/DBT Anatomy or clinical context: Breast Input: DICOM files from one FFDM or DBT screening study, compatible with specified Hologic mammography equipment.
- Who uses it? Intended users: Interpreting radiologists.
- What does the software produce? Output: A Saige-Q suspicion code to PACS, EPR, RIS, or workstation; suspicious studies also receive an informational compressed preview.
- What is its most important limitation? Key limitation: Passive notification only, with no diagnostic information beyond triage; not a replacement for image review or standalone decision-making and cases remain on the worklist.
Clinical takeaway
Clinical role: Provides passive worklist prioritization for compatible FFDM and DBT screening mammograms.
Evidence takeaway
Evidence from the reviewed source record: Retrospective blinded multicenter FFDM study of 501 malignant and 832 normal cases and DBT study of 517 malignant and 1,011 normal cases reported AUC 0.966 and 0.985 respectively; no one global accuracy applies.
Clinical details
What this tool is for
Start with the authorized purpose, then verify how it fits your service line and reading workflow.
- Exact purpose
- Provides passive worklist prioritization for compatible FFDM and DBT screening mammograms.
Clinical-use display mirrors the exact FDA-supported purpose reconciled in this remediation finding.
- Intended users
- Interpreting radiologists.
FDA packet intended-user statement.
- Care setting and population
- The screening population described in the FDA intended use; the institutional care setting requires local confirmation.
Conservative normalization of explicit wording in an exact-submission source.
- Workflow role
- Triage or notification support
Conservative normalization of explicit wording in an exact-submission source.
- Required input
- DICOM files from one FFDM or DBT screening study, compatible with specified Hologic mammography equipment.
FDA packet input and system scope.
- Output and human action
- A Saige-Q suspicion code to PACS, EPR, RIS, or workstation; suspicious studies also receive an informational compressed preview.
FDA packet output scope.
- Limitations
- Passive notification only, with no diagnostic information beyond triage; not a replacement for image review or standalone decision-making and cases remain on the worklist.
Exact FDA limitation boundary.
Regulatory identity
FDA record and catalog context
The FDA listing establishes the regulatory identity. It does not by itself establish local workflow fit, pricing, security, or performance in your environment.
Implementation
Questions for IT, informatics, and operations
Use these fields to structure a vendor demo, security review, and implementation estimate.
- Integration
- The exact-submission ACR model card explicitly references DICOM, PACS, and RIS in the described input, output, or workflow; exact interfaces, versions, and local compatibility require confirmation.
Interoperability terms explicitly reported in the exact-submission ACR model card; interface versions and local compatibility still require confirmation.
- Deployment and data flow
- Both
Deployment category preserved from the prior exact-submission review; hosting region, data flow, and current commercial configuration still require vendor confirmation.
- Security and privacy
- Vendor documentation pending
Exact-release security controls, data retention, hosting boundaries, and scoped assurance documentation require vendor confirmation.
- Training and support
- Vendor documentation pending
Current training prerequisites, competency checks, and support commitments for the exact configuration require vendor confirmation.
- Monitoring and change control
- Vendor documentation pending
Current drift, quality, uptime, alert, escalation, and incident-response commitments for the exact configuration require vendor confirmation.
Result destination
PACS and workstation are explicitly referenced as a result destination.
exact submission · checked 2026-09-01Confirm supported products, versions, routing behavior, and display requirements during local evaluation.
Supported acquisition environment
Scanner manufacturers: All
exact submission · checked 2026-09-01Confirm currently supported software versions, protocols, and site-specific acquisition configurations.
ACR exact-submission catalog context
ACR AI Central provides an exact-submission model card for Saige-Q; FDA labeling remains controlling for clinical use, limitations, and performance.
exact submission · checked 2026-09-09Evidence
Performance 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.
- Evidence summary
- Retrospective blinded multicenter FFDM study of 501 malignant and 832 normal cases and DBT study of 517 malignant and 1,011 normal cases reported AUC 0.966 and 0.985 respectively; no one global accuracy applies.
Submission-reported performance results.
- Reported sensitivity
- 89.40%
Model sensitivity reported by ACR AI Central. Review endpoint, threshold, study population, and tested version before comparison.
- Reported specificity
- 86.90%
Model specificity reported by ACR AI Central. Review endpoint, threshold, study population, and tested version before comparison.
No contextualized exact-version metric has completed evidence review. Regulatory-document values, when available, are shown above with their limitations.
Saige-Q regulatory performance study summary
- DesignStand-Alone Performance
- PopulationPopulation described in the exact-submission ACR model card
- Scopeexact submission
- Tested versionExact product version not reported; regulatory study summarized for FDA submission K203517
- Samplen=2861
- Sites14
- IndependenceIndependence not established
K203517
ACR AI Central summarizes the regulatory study; consult the exact FDA materials before comparative use.
Costs and setup
Budget and ongoing governance
These are common procurement questions; unknown values remain visible until a source supports them.
- Pricing and total cost
- Vendor documentation pending
No public price or quote for the exact K203517 configuration was established in this review.
- Reimbursement and coding
- Not established in reviewed sources
No exact-product payer policy, coding instruction, or payment determination was established; eligibility must be evaluated by payer, site of service, and use case.
Safety and lifecycle
Postmarket record
Recall and adverse-event records are shown only after product matching. Adverse-event reports do not establish incidence or causality.
- Postmarket safety review
- The exact-identifier FDA recall query returned no native recall record for K203517. This limited result does not establish absence of recalls or other safety information and does not cover later versions, family records, MAUDE reports, corrections, or field notices.
Buyer worksheet
Open questions to take to the vendor
- Verify security and privacy controls: Exact-release security controls, data retention, hosting boundaries, and scoped assurance documentation require vendor confirmation.
- Verify training: Current training prerequisites, competency checks, and support commitments for the exact configuration require vendor confirmation.
- Verify pricing and total cost: No public price or quote for the exact K203517 configuration was established in this review.
- Verify reimbursement and coding relevance: No exact-product payer policy, coding instruction, or payment determination was established; eligibility must be evaluated by payer, site of service, and use case.
- Verify local validation and lifecycle monitoring: Current drift, quality, uptime, alert, escalation, and incident-response commitments for the exact configuration require vendor confirmation.
Research record
What has been checked
This audit distinguishes completed source review from fields that have not yet been researched.
Exact FDA record reviewedStatus
2026-09-20Last searched
28Fields reviewed
10Source classes checked
0Screened PubMed leads
0Screened trial leads
0Unreviewed FDA recall leads
The refreshed discovery snapshot contains no PubMed or ClinicalTrials.gov candidates; no external evidence was promoted. The current discovery snapshot contains 0 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 device recall, literature index, trial registry, fda decision summary packet, pubmed, clinical trials, openfda device recall
Sources & history
How this profile was documented
Open the ledger for source dates, scope, and research-record updates.
View source ledger and history
Source ledger
-
FDA K203517: Saige-Q
Scope: identity, clinicalUse, modality, anatomy, workflow, evidence, implementation, purpose, intendedUsers, input, output, limitations, evidenceSummary
-
Artificial Intelligence-Enabled Medical Devices
Scope: regulatoryIdentity, modalityContext
-
Saige-Q model card (K203517)
Scope: intendedUsers, output, limitations, reportedSensitivity, reportedSpecificity, evidenceSummary, integration, anatomy, evidenceStudies, implementationCapabilities
-
PubMed biomedical literature index
Scope: evidenceDiscovery
-
ClinicalTrials.gov study registry
Scope: evidenceDiscovery, studyStatus
-
openFDA Device Recall API
Scope: recallDiscovery, nativeSubmissionMatching
-
openFDA exact recall query for K203517
Scope: postmarketSafety
Research history
-
K203517 FDA decision
Regulatory record
510(k)
-
Source-review record updated
Research record
fda record reviewed
-
Reader overview source-reviewed
Editorial review
Source-reviewed editorial overlay
Alternatives
Related tools to compare
FDA-cleared K252954
MammoSightAI
Neurocareai, Inc. (Dba Savelife.Ai)
Tags screening cases as suspicious or blank to aid worklist prioritization; radiologists must review every examination and it does not mark original images.
- Modality
- Mammography/DBT
- Anatomy
- Breast
- Decision
- 2026-05-04
FDA-cleared K252482
CogNet AI-MT+
Medcognetics, Inc.
Prioritizes suspicious screening DBT examinations for MQSA interpreting physicians; every examination remains subject to full physician review.
- Modality
- Mammography/DBT
- Anatomy
- Breast
- Decision
- 2025-12-11
FDA-cleared K233108
VinDr-Mammo
VinBigData Joint Stock Company
The VinDr-Mammo is a passive notification for prioritization-only, a parallel- workflow software tool used by MQSA qualified interpreting physicians to prioritize patients with...
- Modality
- Mammography/DBT
- Anatomy
- Breast
- Decision
- 2024-05-23
FDA-cleared K220080
CogNet QmTRIAGE
MedCognetics, Inc.
Passive exam-level notification and prioritization of suspicious findings in screening mammograms.
- Modality
- Mammography/DBT
- Anatomy
- Breast
- Decision
- 2022-09-29