Caption Interpretation Automated Ejection Fraction Software

K200621

Caption Health · cleared 2020-07-22 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.4)

“The Caption Interpretation Automated Ejection Fraction Software applies machine learning algorithms to process echocardiography images in order to calculate left ventricular ejection fraction. The Caption Interpretation Automated Ejection Fraction software is used to process previously acquired transthoracic cardiac ultrasound images, to store images, and to manipulate and make measurements on images using an ultrasound device, personal computer, or a compatible DICOM-compliant PACS system in order to provide automated estimation of left ventricular ejection fraction.”

Algorithmmachine learning algorithms

source quote (p.4)

“The Caption Interpretation Automated Ejection Fraction Software applies machine learning algorithms to process echocardiography images in order to calculate left ventricular ejection fraction.”

Adaptive (vs locked)FDA source did not state this

PCCPFDA source did not state this

Cybersecurity addressedFDA source did not state this

Validation studies (2)

Reader study (MRMC)

sample size not stated

endpoints: PPV point estimates for the Clip Annotator for identification of the imaging mode and the view; sensitivity point estimates across views and imaging mode

Retrospective clinical

sample size not stated

endpoints: relationship (RMSD) between AutoEF derived values based on the best available view combination and the reference method; EF estimation based on two or more views of AP2, AP4 or PLAX; Single-view EF estimation based on the AP4 view; AP2 and PLAX views observed results; AP2-only and PLAX-only RMSD

Reported performance (2 observations)

sensitivity0.9

source quote (p.6)

“observed sensitivity point estimates were greater than 90% across views and imaging mode.”

ppvas written: “PPV”0.97

source quote (p.6)

“observed PPV point estimates for the Clip Annotator were greater than 97% for identification of the imaging mode and the view.”

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

recalls in product code, 24mo

MAUDE reports in code, 12mo

—

vs code's own 3-yr baseline

drift signals on this device

re_clearance
The FDA AI/ML device list shows a newer 510(k) K210747 (decision 2022-01-19) from Caption Health for a matching device line ("Caption Interpretation Automated Ejection Fraction Software") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K210747

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device). 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).