Search Results

The EPi-Ease™ Epicardial Access System is intended to access the epicardial surface of the heart via a subxiphoid approach.

EPi-Ease is composed of a radiopaque blunt distal tip, a distal suction port designed to draw pericardial tissue into the device, a hollow 22-gauge Tuohy needle that enables puncture of the pericardium internal to the device, and a lumen to allow for insertion of an endoscope to provide direct visualization during blunt dissection, needle puncture, and guidewire delivery. The distal suction port connects to the device handle and terminates in a standard luer connection. The needle connects to the handle and terminates in a needle actuator, which enables extension, and rotation of the encased needle a limited distance within the distal tip and provides a port for insertion of a commercially available guidewire. After puncture, the device allows passage of a standard, commercially available .014" guidewire. An additional flushing port is available using the 3-way stopcock.

The provided text describes the regulatory clearance of a medical device, the EPi-Ease™ Epicardial Access System (EAS), by the FDA. However, it does not contain information about a study involving an AI/Machine Learning algorithm or human readers. The document focuses on the mechanical and design verification and validation of a physical medical device (an epicardial access system) in comparison to a predicate device, as required for a 510(k) submission.

Therefore, I cannot provide the requested information regarding:

• A table of acceptance criteria and reported device performance related to an AI/ML study.
• Sample sizes, data provenance, number/qualifications of experts, or adjudication methods for an AI/ML test set.
• MRMC comparative effectiveness study, effect size, or standalone AI performance.
• Ground truth type, training set sample size, or how ground truth for the training set was established in the context of an AI/ML study.

The document lists "Performance Data" which refers to bench testing conducted on the physical device to ensure mechanical integrity, biocompatibility, shelf-life, etc., demonstrating substantial equivalence to a predicate device. This is a common requirement for physical medical devices and is distinct from studies required for AI/ML-driven devices.

Here's an interpretation of the "acceptance criteria" and "study" mentioned in the document for the physical device:

Acceptance Criteria and Study for the EPi-Ease™ Epicardial Access System (EAS)

The document states: "The EPi-Ease device met the predetermined acceptance criteria ensuring substantial equivalence to the predicate." The "study" here refers to the a series of bench tests, not an AI/ML performance study.

1. Table of Acceptance Criteria and Reported Device Performance (for the physical device):

2. Sample sized used for the test set and the data provenance:

• This information (specific sample sizes for each bench test) is not provided in the document.
• Data provenance: The testing was performed as part of the device's regulatory submission, likely at the manufacturer's facility or approved test labs. This is not "data provenance" in the sense of patient data for an AI/ML model.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• This is not applicable as the document describes bench testing of a physical device, not an AI/ML model requiring expert consensus for ground truth. The "ground truth" for these tests are objective measurements and established standards (e.g., ISO, ASTM).

4. Adjudication method for the test set:

• This is not applicable for the bench testing described. Test results are determined by meeting pre-specified engineering and performance specifications.

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 done. This device is a physical medical instrument, not an AI-assisted diagnostic tool.

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

• No, this is not applicable. The device is a physical instrument, not an algorithm.

7. The type of ground truth used:

• The ground truth for the bench tests are engineering specifications, material standards (e.g., ISO, ASTM), and functional performance criteria established for medical devices of this type, ensuring safety and effectiveness.

8. The sample size for the training set:

• This is not applicable. The document describes a physical device, not an AI/ML model that undergoes training.

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

• This is not applicable. There is no "training set" in the context of this device's development as described.

In summary, the provided document is a 510(k) clearance letter for a physical medical device, not an AI/Machine Learning product. Therefore, the specific questions related to AI/ML model testing and validation cannot be answered from the given text.

Ask a specific question about this device