Search Results

CT Injector: Administration of contrast and flushing media in conjunction with computed tomography (CT) scanning of the body.
EDA: The Extravasation Detection Accessory is indicated for the detection of extravasations of contrast media during CT using a power injector.

The EmpowerCTA Injector System is an injection system that uses one or two consumable syringe(s) to displace contrast media and flushing media to the patient. A motor driven linear actuator controls displacement of the syringe piston. This method of contrast injection is consistent with predicate devices from E-Z-EM for over 12 years. This new version of the EmpowerCT Injector family addresses the addition of a second syringe for the device for purposes of displacing flushing media.

This document is a 510(k) premarket notification for the E-Z-EM EmpowerCTA Injector System with Optional EDA. It demonstrates substantial equivalence to a predicate device, the E-Z-EM EmpowerCT Injector System (K011160). It is not a study report for an AI/ML device evaluating acceptance criteria through a clinical trial with human readers or AI standalone performance. Therefore, most of the requested information regarding acceptance criteria, study design, and AI performance metrics is not applicable.

However, I can extract information related to the device's technical specifications and how its performance is compared to the predicate device to establish substantial equivalence.

1. Table of Acceptance Criteria and Reported Device Performance

Since this is a 510(k) for a device modification and not an AI/ML device with clinical performance endpoints, "acceptance criteria" here refers to the performance specifications demonstrating substantial equivalence to the predicate device. The document explicitly outlines the performance characteristics of the proposed device and compares them to the predicate.

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

This information is not applicable as this is a 510(k) submission for a medical device injector system, not an AI/ML diagnostic or prognostic device that typically relies on clinical test sets with patient data. The "testing" referred to here is primarily engineering verification and validation against technical specifications and predicate device performance, not a clinical study on a patient population.

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)

This is not applicable. Ground truth, in the context of clinical expert consensus for image interpretation or diagnosis, is not relevant for this device's 510(k) submission. The device performs automated contrast injection and extravasation detection, not diagnostic interpretation.

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

This is not applicable for the reasons stated above.

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

This is not applicable. This document describes an automated medical device (contrast injector), not an AI-assisted diagnostic or treatment planning tool that would involve human readers.

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

This concept is not applicable in the AI/ML sense. The device itself operates "standalone" in its function of injecting contrast and detecting extravasation, but it is not an algorithm making diagnostic decisions. It performs physical and electronic functions. Performance is confirmed through engineering tests, not a "standalone algorithm" evaluation against ground truth in a clinical dataset.

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

For this device, "ground truth" would relate to the accurate measurement of physical parameters like flow rate, volume, pressure, and bio-impedance, as well as the reliable detection of simulated extravasation events in a laboratory setting. This would be established by controlled experimental setups and validated measurement equipment, rather than clinical expert consensus or pathology. The document implies that the device's performance characteristics match those of the predicate, which would have undergone similar engineering validation.

8. The sample size for the training set

This is not applicable. The device is not an AI/ML model that undergoes "training" on a dataset in the traditional sense. It is a control system with specific algorithms for injection and detection, likely developed through engineering design, mathematical modeling, and empirical testing.

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

This is not applicable as there is no "training set" in the context of AI/ML for this device.

Ask a specific question about this device