K-numberK250670
Device nameEchoConfidence (USA)
ApplicantMycardium AI Limited
Product codeQIH
Device classClass II
Decision dateJun 30, 2025
DecisionSubstantially Equivalent
Regulation892.2050
AI Summary extracted from FDA summary PDF · never regenerated
Intended use

EchoConfidence is software that displays and analyzes transthoracic echocardiogram images to assist physicians in reviewing cardiac images, making measurements, and generating reports. It provides automatic view classification, cardiac structure segmentation (ventricles, atria, chamber walls, great vessels), functional measurements, and Doppler assessments for patients aged 18 years and older with known or suspected cardiac disease.

Technological characteristics

Both EchoConfidence and its predicates use artificial intelligence to segment and analyze echocardiographic images for structural and functional cardiac measurements. EchoConfidence offers additional capabilities including manual editing of contours, automatic view classification, and a broader range of outputs (over 100 measurements) compared to the predicate devices, though these enhancements are independent of output variable accuracy.

Test standards cited

EN ISO 14971 (risk management), IEC 62304 (software lifecycle), IEC 62366-1 and IEC 62366-2 (usability engineering). Testing also referenced FDA guidance documents on software cybersecurity in medical devices.

Substantial equivalence argument

Both devices target the same patient population and intended users, employing AI to segment and quantify structural and functional cardiac measures from echocardiographic images. The validation study demonstrated that EchoConfidence's mean absolute error compared to three human expert readers was equivalent to or better than the experts' agreement with each other, with the upper 95% confidence interval well below the +25% acceptance criterion. The additional features (manual editing, view classification, expanded outputs) do not impact the accuracy of the core measurements, preserving equivalence in safety and effectiveness for the stated indications.

Extracted by AI from the official FDA summary PDF →
Source

View the full FDA submission: accessdata.fda.gov

Researching this as a predicate?
Want a transparent AI-ranking score, AI-discovered related predicates, ongoing safety and warning-letter monitoring, full predicate chain lineage, and a drafted SE rationale — all saved to your own project? That's what an account adds.
Start free trial →

Everything you need for a 510(k) submission. Nothing you don't.

14-day free trial. No setup. Cancel anytime.

Start free trial →
Building an AI or ML-enabled device? Predicate search, PCCP tracking, and AI-specific FDA intelligence — built exclusively for AI/ML devices. Try AIFDA Intel →