EFAI Intelligent Cardiothoracic Ratio (iCTR) Assessment System

K212624

Ever Fortune. AI Co., Ltd. · cleared 2022-04-04 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.5)
“The iCTR is a non-invasive software medical device designed to be installed on the computer with specific system requirements. It is a radiological computer-assisted software system that automatically analyzes DICOM chest X-ray images in PA view and outputs the CTR through an artificial intelligence algorithm.”
Algorithmartificial intelligence algorithm that uses three quality control models and two annotation models to filter images and draw annotation lines for heart and thoracic cavity diameters.
source quote (p.5)
“The iCTR is designed to measure the maximal transverse diameter of heart and maximal inner transverse diameter of thoracic cavity and calculate the CTR of a chest X-ray image in posterior-anterior (PA) chest view using an artificial intelligence algorithm. The EFAI iCTR encompasses three quality control models and two annotation models. The quality control models are capable of filtering out non-chest X-ray images (Sensitivity 0.99, Accuracy 0.99), filtering out the non-PA view chest X-ray images(Sensitivity 0.99, Accuracy 0.97), and presenting with message for images with unclear boundary whose threshold is <0.5; the annotation models are able to draw two annotation lines, one indicating maximal transverse diameter of the heart (root-mean-square-error 8.81mm)and other indicating the maximal inner diameter of the thoracic cavity(root-mean-square-error 14.3mm).”
Adaptive (vs locked)No
source quote (p.10)
“Images and cases used for verification testing were carefully separated from training algorithms.”
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this

Validation studies (1)

Retrospective clinical

n=840 images · 3 site(s)

endpoints: accuracy

standards: IEC 62304, IEC 62366-1, IEC 62366-2, IMDRF/SaMD WG/N41FINAL:2017

Reported performance (4 observations)

sensitivity0.99
source quote (p.10)
“The quality control models are capable of filtering out non-chest X-ray images (Sensitivity 0.99, Accuracy 0.99), filtering out the non-PA view chest X-ray images(Sensitivity 0.99, Accuracy 0.97)”
accuracyas written: “Accuracy (non-chest X-ray images)”0.99
source quote (p.10)
“The quality control models are capable of filtering out non-chest X-ray images (Sensitivity 0.99, Accuracy 0.99)”
accuracyas written: “Accuracy (non-PA view chest X-ray images)”0.97
source quote (p.10)
“filtering out the non-PA view chest X-ray images(Sensitivity 0.99, Accuracy 0.97)”
accuracyas written: “Accuracy (EFAI iCTR system agreement with physician derived CTR)”0.95
source quote (p.10)
“The accuracy of EFAI iCTR system is 0.95.”

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

0
recalls in product code, 24mo
3
MAUDE reports in code, 12mo
—
vs code's own 3-yr baseline
0
drift signals on this device

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device); a recall is shown as device-attributed only when the recall record itself lists this clearance number. 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).

Applicable FDA guidance — what the submission is measured against

FDA guidance documents and guiding principles applicable to 510(k) AI/ML devices in the Radiology panel. A curated reference index, not legal or regulatory advice — each item states its own status, and a draft is never binding.

Applicability is derived from the device's FDA advisory panel and pathway — cross-cutting guidances apply to every AI/ML device; panel-specific ones are flagged. Titles, dates, and links verified against fda.gov as of July 2026.

Constat Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: constat.dev/precedent/device/K212624