Search Results

The Foresight Intracardiac Echocardiography (ICE) System is indicated for intraluminal ultrasound visualization of cardiac and great vessel anatomy and physiology as well as visualization of other devices in the heart and great vessels of patients.

The Foresight ICE System is intended to be used for real-time, minimally-invasive guidance of several different intracardiac procedures including, but not limited to, atrial ablation procedures and transseptal punctures. The system will provide image information of cardiovascular anatomic features, spatial relationships of other devices within the heart and great vessels, physiological information of cardiovascular structures and features, and intra-procedure complications including pericardial effusions. The system will be comprised of catheter and a cart based console. The console includes the Acquisition and Display Module (ADM) for image display and manipulation as well as the Patient Interface Module (PIM) which the catheter connects to. The ADM will have two monitors to allow for ease of image view and review for both the technician and physician user. The technician user will be able to control the system software via an easy to use interface using multiple methods of input including a mouse, keyboard and/or a touch screen. Casters on the ADM will allow easy movement of the system throughout an EP Lab which can have a small footprint as well as small obstacles to cross. The catheter will be a 10.3F single use, sterile device, which will be able to perform intracardiac and intraluminal ultrasound imaging of adults. The catheter will be capable of real-time 2D side and forward viewing imaging with the ability to produce rapidly post processed 3D rendered images as well as ECG gated 3D images to reduce motion artifacts. The imaging system will be able to resolve and measure features such as the inferior and superior vena cava, ascending and descending aorta, left and right atria, left and right ventricle, fossa ovalis, aortic valve, mitral valve and tricuspid valves. It will display / measure flow velocities using Color and PW Doppler. The physician user will have easy steering maneuverability of the catheter via deflection and rotation, as well as having control over the position of the transducer to allow for multiple angles of images.

The provided document is a 510(k) premarket notification for a medical device (Foresight Intracardiac Echocardiography (ICE) System). It focuses on demonstrating substantial equivalence to predicate devices, rather than establishing acceptance criteria and proving performance against them in the way modern AI/ML device submissions might.

Therefore, many of the requested details, such as specific acceptance criteria for algorithm performance, performance metrics, sample sizes for test sets, data provenance, expert ground truth establishment, adjudication methods, MRMC studies, standalone performance, and training set details, are not present in this document.

The document primarily relies on non-clinical data (bench-top evaluations, animal testing, biological safety, electrical safety, acoustic output testing, packaging validation, and compliance with various IEC/ISO standards) to demonstrate substantial equivalence to previously cleared ICE systems. It explicitly states: "No clinical testing is included in the submission. Determination of substantial equivalence Performance is based on an assessment of non-clinical data."

However, I can extract and infer some information based on the type of submission and the data that is provided.

Acceptance Criteria and Study for Foresight Intracardiac Echocardiography (ICE) System

Based on the provided 510(k) summary (K162789), the device is a diagnostic ultrasound system (ICE) intended for visualization of cardiac and great vessel anatomy. The "acceptance criteria" in this context are not quantitative performance metrics for an AI algorithm, but rather the demonstration of substantial equivalence to predicate devices through engineering and non-clinical testing. The study supporting this is a series of non-clinical tests and comparisons.

1. Table of Acceptance Criteria and Reported Device Performance

As this is a 510(k) for an ultrasound imaging system without specific AI algorithms requiring performance metrics like sensitivity/specificity for disease detection, the "acceptance criteria" are related to product specifications, safety, and functionality, demonstrating equivalence to the predicate.

2. Sample Size for Test Set and Data Provenance:

• Test Set Sample Size: Not applicable in the context of typical AI/ML validation with a "test set" of patient data. The "test set" here refers to physical devices undergoing various engineering and safety tests. The document does not specify the number of devices or components tested, but implies standard engineering testing practices.
• Data Provenance: The data comes from non-clinical testing conducted by Conavi Medical Inc. (Canada-based). It is not patient data (retrospective or prospective), but rather lab, benchtop, and animal model data.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications of those Experts:

• Not applicable. This submission does not involve an AI algorithm where human experts establish ground truth from patient data. The "ground truth" for the device's functionality is established by engineering specifications, relevant IEC/ISO standards, and the performance of predicate devices.

4. Adjudication Method for the Test Set:

• Not applicable. There is no "adjudication" in the sense of resolving discrepancies in expert labeling of medical images. Testing involves objective measurements against engineering specifications and safety standards.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done:

• No. The document explicitly states: "No clinical testing is included in the submission." Therefore, no MRMC study was conducted comparing human readers with and without AI assistance, as there is no AI component being evaluated for diagnostic assistance.

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

• Not applicable. This device is an imaging system, not a standalone algorithm. Its performance is inherent to its ability to generate images, which are then interpreted by a human user.

7. The Type of Ground Truth Used:

• The "ground truth" is established by engineering specifications, international safety and performance standards (IEC, ISO, NEMA), and the established performance characteristics of the predicate devices. For example, the "ground truth" for acoustic output is derived from regulatory limits and safe operation ranges for diagnostic ultrasound. "Animal testing" contributes to safety and functional verification, but not to establishing a diagnostic "ground truth" on patient cases.

8. The Sample Size for the Training Set:

• Not applicable. This device does not use machine learning algorithms that require a "training set" of data.

9. How the Ground Truth for the Training Set was Established:

• Not applicable. See point 8.

Ask a specific question about this device