Search Results

The intended use of the ECP Health System Model 2005 is for the treatment of patients with: (1). Stable or unstable angina pectoris. (2). Acute myocardial infarction (3). Cardiogenic shock (4). Congestive heart failure

ECP Health System Model 2005 is a positive and negative pressure integrated, non-invasive medical device for performing external sequential counterpulsation. It is a microprocessor-controlled system that inflates and deflates three parts of air cuffs which compress vascular beds in the calves, lower thighs, and upper thighs /buttocks to achieve the desired therapy.

This 510(k) premarket notification is for an External Counterpulsation Device (ECP Health System Model 2005). It does not involve an AI/ML component, therefore, many of the requested categories (acceptance criteria, study details, expert involvement, ground truth, training data, etc.) are not applicable in the context of an AI/ML device.

The submission focuses on establishing substantial equivalence to a predicate device (S-TCT Health External Counterpulsation Device, K030587), primarily by demonstrating similar technological characteristics and expanding the indications for use.

Here's a breakdown of the requested information based on the provided text, highlighting where the information is not applicable for a non-AI/ML device:

1. Table of acceptance criteria and the reported device performance

• Acceptance Criteria: Not explicitly defined in terms of quantitative performance metrics for a novel AI/ML algorithm. For this type of device, acceptance is based on demonstrating substantial equivalence to a legally marketed predicate device. This involves showing similar technological characteristics and safety/effectiveness.
• Reported Device Performance: Not reported in terms of specific performance metrics that would be applicable to an AI/ML device (e.g., sensitivity, specificity, AUC). The "performance" is implicitly demonstrated through the claim of substantial equivalence to the predicate device, which itself has established safety and effectiveness. The device's function is described as inflating and deflating three parts of air cuffs to achieve desired therapy.

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

• N/A. This is not an AI/ML device and therefore does not have a "test set" for algorithm evaluation in the traditional sense. The submission relies on a comparison to a predicate device already on the market.

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)

• N/A. This is not an AI/ML device and does not involve establishing ground truth for evaluating an algorithm's performance on a test set.

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

• N/A. This is not an AI/ML device.

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. This is not an AI/ML device, so no MRMC study comparing human readers with and without AI assistance was conducted.

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

• No. This is not an AI/ML device. It is a physical medical device (External Counterpulsation System) for therapy. Its operation does not involve a standalone algorithm performing diagnostic or predictive tasks.

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

• N/A. For this type of device, ground truth in the context of AI/ML evaluation is not relevant. The device's effectiveness is tied to its physiological mechanism and clinical outcomes (treatment of conditions like angina, MI, CHF), which would have been established for the predicate device through clinical trials. The current submission focuses on technological equivalence.

8. The sample size for the training set

• N/A. This is not an AI/ML device and does not have a "training set" in the context of machine learning.

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

• N/A. This is not an AI/ML device.

Summary regarding the study and acceptance:

The "study" in this context is the 510(k) premarket notification process itself, which aims to demonstrate that the ECP Health System Model 2005 is substantially equivalent to a predicate device (S-TCT Health External Counterpulsation Device, K030587).

• Basis for Acceptance: The FDA's acceptance (clearance) is based on the determination of substantial equivalence. This means the device has the same intended use, similar technological characteristics, and raises no new questions of safety or effectiveness as compared to the predicate device.
• Key Differences & Justification: The key differences noted for the ECP Health System Model 2005 are enlarged indications for use (adding Congestive Heart Failure and Unstable Angina Pectoris) and the addition of a finger pulse oximetry function. The submission explicitly states that "Technological and functional characteristics... are essentially the same as those of the predicate device." This assertion, combined with supporting documentation (not fully provided in the excerpt but implied by the 510(k) process), forms the basis for the FDA's "finding of substantial equivalence."
• No specific performance study in the AI/ML sense: The provided text does not describe a clinical study with performance metrics (like sensitivity, specificity, accuracy) that would be typical for an AI/ML device. Instead, the focus is on the device's design, intended use, and comparison to an already cleared device.

Ask a specific question about this device