LogoFDA 510(k) Search
K Number
K101419
Device Name
ENSITE VELOCITY SYSTEM, MODEL EE3000
Manufacturer
ST. JUDE MEDICAL
Date Cleared
2010-06-11

(22 days)

Product Code
DQK
Regulation Number
870.1425
Type
Special
Panel
CV
Reference & Predicate Devices
K093942
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The EnSite Velocity™ Cardiac Mapping System is a suggested diagnostic tool in patients for whom electrophysiology studies are indicated.

  • When used with the EnSite Array™ Catheter, the EnSite System is intended to be used in the right atrium of patients with complex arrhythmias that may be difficult to identify using conventional mapping systems alone.
  • OR
  • When used with the EnSite NavX Surface Electrode Kit, the EnSite System is intended to display the position of conventional electrophysiology (EP) catheters in the heart.
Device Description

The EnSite Velocity System consists of the following:

  • Display Workstation
  • Amplifier
AI/ML Overview

The provided text is a 510(k) Summary for the EnSite Velocity System. It details the device's regulatory information, intended use, and comparison to a predicate device. However, it does not contain information about the acceptance criteria or a study proving the device meets those criteria, as typically understood in the context of AI/ML performance evaluation.

The "Summary of Non-Clinical Testing" section states, "Bench testing was performed to confirm that the changes met design requirements and did not affect the safety or effectiveness of the product." The "Summary of Clinical Testing" section states, "Cross-vendor interoperability testing sessions were conducted between EnSite Courier and 15 different PACS models/versions, seven vendors. This clinical test report can be found in Appendix S."

This submission appears to be for an update to an existing system (EnSite Velocity v.1.3 (K093942)) to include "EnSite Courier™" which is a networking software feature. The testing described is focused on interoperability and verifying that changes did not negatively impact safety or effectiveness compared to the predicate device, rather than establishing performance metrics against a defined acceptance criterion for a novel diagnostic accuracy claim.

Therefore, many of the requested items cannot be answered from the provided text.

Here's a breakdown of what can be inferred or confirmed:

  1. A table of acceptance criteria and the reported device performance:

    • Cannot be provided. The document does not specify quantitative acceptance criteria (e.g., sensitivity, specificity, accuracy) for a diagnostic performance study, nor does it report such metrics. The non-clinical testing focused on "meeting design requirements" and not affecting safety/effectiveness. The clinical testing focused on "interoperability."

  2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):

    • For the "Cross-vendor interoperability testing sessions," the "test set" consisted of "15 different PACS models/versions, seven vendors." No patient data sample size, provenance, or retrospectivity/prospectivity is mentioned as the testing was on interoperability, not clinical diagnostic performance.

  3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience):

    • Not applicable. This information is relevant for studies evaluating diagnostic accuracy against expert ground truth. The described testing was for interoperability and non-inferiority via bench testing.

  4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

    • Not applicable. See point 3.

  5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

    • No. An MRMC study was not described. The device is an electrophysiology mapping system, and the update involves networking software. This type of study is not relevant to the described testing.

  6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

    • The device is a "Cardiac Mapping System" and the update is for "EnSite Courier™" networking software. It is not an "algorithm only" device in the AI/ML sense. The testing described (bench testing and interoperability) is a form of standalone testing for the specific aspects evaluated (design requirements and data exchange).

  7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):

    • For the non-clinical bench testing, the "ground truth" would be the engineering design requirements.
    • For the clinical interoperability testing, the "ground truth" would be successful data exchange with various PACS systems. No medical ground truth (pathology, expert consensus, outcomes) was established as this was not a diagnostic accuracy study.

  8. The sample size for the training set:

    • Not applicable. This device and its update (networking software) are not described as using an AI/ML algorithm that would require a "training set" in the context of machine learning model development.

  9. How the ground truth for the training set was established:

    • Not applicable. See point 8.

§ 870.1425 Programmable diagnostic computer.

(a)
Identification. A programmable diagnostic computer is a device that can be programmed to compute various physiologic or blood flow parameters based on the output from one or more electrodes, transducers, or measuring devices; this device includes any associated commercially supplied programs.(b)
Classification. Class II (performance standards).