K-numberK250886
Device nameEPIQ Series Diagnostic Ultrasound Systems; Affiniti Series Diagnostic Ultrasound Systems
ApplicantPhilips Ultrasound, LLC
Product codeIYN
Device classClass II
Decision dateJun 18, 2025
DecisionSubstantially Equivalent
Regulation892.1550
AI Summary extracted from FDA summary PDF · never regenerated
Intended use

The EPIQ and Affiniti Series Diagnostic Ultrasound Systems with Smart View Select (SVS) v2 software are ultrasound diagnostic imaging devices that perform fluid flow analysis of the human body. SVS v2 is an automated software feature that uses artificial intelligence to classify and select optimal images for left ventricular analysis in adult cardiac transthoracic examinations, assisting users in image selection without manual review.

Technological characteristics

The subject devices use a deep learning neural network for view identification and optimal triplet (A4C, A2C, A3C) selection, with a revised heuristic logic step that preferentially selects triplets of shallower scan depths (12–20 cm restriction for proposed device vs. predicate's 10 cm minimum with 1 cm variation constraint). The classification engine is AI-based while the selection algorithm is non-AI. No hardware changes were made; existing cleared Philips transducers are used.

Test standards cited

IEC 62304 (Medical device software – Software life cycle processes, 2006 + A 2015), IEC 62366-1 (Usability engineering to medical devices, Edition 1.1 2020-06), ISO 14971 (Risk management for medical devices, 2019), and FDA Guidance for Industry and FDA Staff – Marketing Clearance of Diagnostic Ultrasound Systems and Transducers (February 2023).

Substantial equivalence argument

The proposed devices are substantially equivalent because: (1) indications for use, user environment, and regulatory classification are identical to predicate K240850; (2) performance testing via retrospective analysis demonstrated strong correlation between SVS-selected clips and manually selected clips for ejection fraction (r=0.891, 95% CI 0.851–0.920) and global longitudinal strain (r=0.906, 95% CI 0.871–0.931), both exceeding the predefined acceptance criterion of >0.8; and (3) the revision to the depth-selection heuristic does not raise new safety or effectiveness questions, as the algorithm remains functionally similar and produces clinically equivalent results.

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 →