K-numberK243884
Device nameTAVIPILOT
ApplicantCaranx Medical
Product codeOWB
Device classClass II
Decision dateJul 7, 2025
DecisionSubstantially Equivalent
Regulation892.1650
AI Summary extracted from FDA summary PDF · never regenerated
Intended use

TAVIPILOT is intra-operative software that uses real-time fluoroscopy to detect, track, and mark the non-coronary cusp and prosthetic valve during transcatheter aortic valve implantation/replacement (TAVI/TAVR) procedures. It provides visual guidance overlaid on 2D X-ray images to help position the prosthetic valve according to the pre-procedure plan, but does not replace the surgeon's or cardiologist's clinical judgment.

Technological characteristics

The key technological difference from the predicate (Philips HeartNavigator 2.0) is that TAVIPILOT uses trained AI/ML models to detect and track the non-coronary cusp and transcatheter aortic valve directly from live fluoroscopic images, whereas the predicate uses previously acquired CT scan data converted to 2D projections. Both systems display 2D landmarks overlaid on live X-ray images and require compatible FDA-cleared C-arm X-ray devices, Windows operating systems, and specified computing hardware.

Test standards cited

TAVIPILOT was developed and validated according to IEC 62304:2006+A1:2015 (medical device software lifecycle), IEC 62366-1:2015+AMD1:2020 (usability engineering), ISO 14971:2029 (risk management), CR34971:2022 (AI/ML risk guidance), and TIR57:2016 (medical device security). Interoperability was tested with FDA-cleared C-arm systems from GE, Philips, and Siemens.

Substantial equivalence argument

TAVIPILOT is substantially equivalent because it achieves the same intended purpose—real-time guidance for TAVI valve positioning—using comparable workflow steps and user interface methods as the predicate. Although the technological mechanism differs (AI/ML detection versus CT-based registration), validation testing demonstrated TAVIPILOT has equivalent or better accuracy (NCC ≤2 mm, TAV ≤1 mm with 100% statistical significance in both contrasted and non-contrasted images) compared to the predicate. Both systems maintain the original fluoroscopic stream separately and overlay 2D guidance; both require trained healthcare professionals; and both are used in the same clinical environment. The difference in underlying technology does not raise new safety or effectiveness concerns.

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 →