FDA-cleared profile
Caption Health
Caption Interpretation Automated Ejection Fraction Software processes previously acquired adult transthoracic cardiac ultrasound images, stores and manipulates images, and measures them using an ultrasound device, personal computer, or compatible DICOM-compliant PACS to provide an automated estimate of left-ventricular ejection fraction that may assist a clinician in cardiac evaluation.
Clinical fit
Start with the authorized purpose, then verify how it fits your service line and reading workflow.
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.
Implementation
Use these fields to structure a vendor demo, security review, and implementation estimate.
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 the release-level boundary described in the exact FDA package; current hosting, contracts, security, availability, upgrade path, and site configuration remain separate evidence.
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.
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 K200621 before acceptance.
exact submission · checked 2026-09-04Later product-family features are not evidence that this cleared or authorized release includes them.
The FDA labeling describes deployment on an ultrasound device, personal computer, or compatible DICOM-compliant PACS; current site topology, hosting responsibility, availability, security, and service 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 use on an ultrasound device, personal computer, or compatible DICOM-compliant PACS and output of an ejection-fraction estimate with confidence information for clinician viewing.
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. Use is limited to adult transthoracic cardiac ultrasound and supported views; clinicians must review clips and accept or reject automated estimates before clinical use.
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 K200621 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: Use is limited to adult transthoracic cardiac ultrasound and supported views; clinicians must review clips and accept or reject automated estimates before clinical use.
exact submission · checked 2026-09-04Revalidate after material software, hardware, model, protocol, interface, or clinical-policy changes. automated echocardiography ejection-fraction software limits remain submission-specific.
Evidence
Metrics are shown only when they are tied to a source, endpoint, population, and tested product version.
Values reported in the exact-submission materials. Consult the linked source for endpoint, threshold, population, and confidence interval before comparison.
Specificity is not promoted as a product-wide endpoint. Compare only an exact endpoint, threshold, population, version, study design, and source if separately verified.
Observed PPV point estimate across imaging modes and views in Clip Annotator study compared with expert readers.
Tested version: Caption Interpretation Automated Ejection Fraction Software configuration described in K200621Observed sensitivity point estimate across imaging modes and views in Clip Annotator study compared with expert readers.
Tested version: Caption Interpretation Automated Ejection Fraction Software configuration described in K200621FDA 510(k) Clip Annotator study and pivotal clinical investigation comparing AutoEF to conventional ejection-fraction calculation methods. · Heart; left ventricle; adult cardiac evaluation
exact submission · Tested version: Caption Interpretation Automated Ejection Fraction Software configuration described in K200621 · Sponsor or vendor studyK200621
The FDA summary reports thresholded PPV and sensitivity point estimates and qualitative statements about RMSD acceptance criteria, but does not expose all study counts in the public decision material.
Economics and lifecycle
These are common procurement questions; unknown values remain visible until a source supports 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.
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.
Safety and lifecycle
Recall and adverse-event records are shown only after product matching. Adverse-event reports do not establish incidence or causality.
Each published event was manually matched to the exact FDA submission and affected product or version; a recall does not establish an AI-algorithm defect or current site exposure unless the event states that scope.
Terminated
2021-05-19Exact version match to Caption AI 1.2.0. This was a software-output issue involving AutoEF and IQS estimates.
Buyer worksheet
Research record
This audit distinguishes completed source review from fields that have not yet been researched.
The locked snapshot contains no PubMed or ClinicalTrials.gov candidates for K200621; no evidence was promoted or quarantined. 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. 1 FDA recall candidate was manually reviewed: 1 published and 0 rejected as a neighboring or otherwise inapplicable version. Native FDA recall identifiers produced 1 postmarket candidate record; 1 has been reviewed (1 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
Sources
Sources accessed through 2026-09-04.
Alternatives
Exo Imaging
Provides AI-assisted cardiac, lung and abdominal quality feedback and measurements; users remain responsible for scan quality and diagnosis and must not rely solely on the...
Ultrasight, Ltd.
PVAD IQ supports qualified-physician clinical decision support by identifying the aortic annulus and PVAD inlet, calculating their mean distance, and identifying clips acceptable...
Diagnoly
FETOLY analyzes fetal ultrasound images and sequences to detect labeled fetal brain and heart views, assess image completeness or quality, and provide fetal biometric measurements...
GE Medical Systems Ultrasound and Primary care Diagnostics
Voluson Performance 16 and 18 are general-purpose diagnostic ultrasound systems for imaging, measurement, display, and analysis of the human body and fluid across the labeled...