AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

MEDRAD® Stellant FLEX CT Injection System with Certegra Workstation: The MEDRAD® Stellant FLEX CT Injection System with Certegra Workstation, including Stellant FLEX CT Syringe Kits and Connector Tubing, is indicated for the specific purpose of injecting intravenous contrast media or saline into humans for diagnostic studies in computed tomography (CT) applications.
MEDRAD® Stellant FLEX Syringe Kits: The MEDRAD® Stellant FLEX CT Injection System with Certegra Workstation, including Stellant FLEX CT Syringe Kits and Connector Tubing, is indicated for the specific purpose of injecting intravenous contrast media or saline into humans for diagnostic studies in computed tomography (CT) applications.
MEDRAD® Stellant CT Injection System with Certegra Workstation: The MEDRAD® Stellant CT Injection System with Certegra Workstation is indicated for the specific purpose of injecting intravenous contrast media or saline into humans for diagnostic studies in computed tomography (CT) applications.
MEDRAD® Stellant Syringe Kits: The contents of this package are intended to be used in the delivery of contrast media or saline. They are indicated for single-use on one patient only with MEDRAD® Stellant Injectors.
MEDRAD® Stellant Connector Tubing: The contents of this package are intended to be used in the delivery of contrast media or saline. They are indicated for single-use on one patient only with MEDRAD® Stellant Injectors.
P3T Cardiac: P3T Cardiac is indicated for use with CT Angiography of the cardiac structures, coronary arteries, chambers of the heart, pulmonary vasculature, thoracic, and abdominal aorta.
P3T PA: P3T PA is indicated for use with CT Angiography of the cardiac structures, coronary arteries, chambers of the heart, pulmonary vasculature, thoracic, and abdominal aorta.
P3T Abdomen: P3T Abdomen is indicated for use with CT imaging of abdominal organs (i.e., liver, pancreas, kidneys).
ISI: The ISI module option is indicated for the specific purpose of allowing an injector to interface with a CT scanner.
Connect.CT: The Connect. CT application is indicated for the specific purpose of allowing the injector to interface with a CT scanner.

Device Description

MEDRAD Stellant FLEX CT Injection System with Certegra Workstation: The MEDRAD Stellant FLEX CT Injection System with Certegra Workstation is a software-controlled medical device used for the administration of intravenous CT contrast media and saline into the human vascular system for diagnostic studies in Computed Tomography (CT) procedures. Commonly referred to as an automated injection system, it is designed to allow a user to fill disposable syringes to perform an injection with a user-programmed volume, flow rate and/or duration.
MEDRAD Stellant CT Injection System with Certegra Workstation: The MEDRAD Stellant CT Injection System with Certegra Workstation is a software-controlled medical device used for the administration of intravenous CT contrast media and saline into the human vascular system for diagnostic studies in Computed Tomography (CT) procedures. Commonly referred to as an automated injection svstem, it is designed to allow a user to fill disposable svringes to perform an injection with a user-programmed volume, flow rate and/or duration.
Personalized Patient Protocol Technology (P3T): The Stellant P3T software accessories compute individual contrast injection protocols and scan timing, based on patient characteristics, scanner parameters and contrast concentration for individualized dosing, and for increasing the consistency of individualized injection protocols among clinicians.
Imaging System Interface (ISI): The ISI module options allow an injector to interface with a CT scanner.
Connect.CT: The Connect.CT application allows an injector to interface with a CT scanner.

AI/ML Overview

The provided document is a 510(k) premarket notification for a medical device: the MEDRAD Stellant FLEX CT Injection System with Certegra Workstation and associated components. This type of submission relies on demonstrating substantial equivalence to a legally marketed predicate device, rather than proving safety and effectiveness through extensive clinical trials as for a PMA. Therefore, the device performance is evaluated against established engineering specifications and verified through various forms of bench testing, rather than clinical efficacy measures.

Here's a breakdown of the requested information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not present acceptance criteria in a quantitative, pass/fail table format directly tied to an AI or algorithm's performance. Instead, it discusses the general performance requirements and outcomes of various engineering tests. The "reported device performance" is consistently stated as "All testing passed and the demonstrated product performance met all prior established acceptance criteria."

General categories of acceptance criteria (implicit from testing performed) and reported outcomes:

Category of Acceptance Criteria (Implicit)Reported Device Performance
Device performance (filling, protocol management, fluid delivery, flow rates, volumes, pressures)Passed, met all prior established acceptance criteria.
Environmental conditions (atmospheric, handling)Passed, met all prior established acceptance criteria.
Disposables mechanical functions (syringe, tubing, pressure capabilities per ISO 594)Passed, met all prior established acceptance criteria.
Disposables packaging (per ISO 11607-1)Passed, met all prior established acceptance criteria.
Biocompatibility (per ISO 10993-1:2009 for cytotoxicity, hemocompatibility, sensitization, irritation, acute systemic toxicity, materials mediated pyrogen)Passed, met the requirements.
Sterilization (per ISO 11137-1, -2, -3 to SAL of 10^-6)Passed, met all prior established acceptance criteria.
Safety and Compatibility (configurations, circuitry, IEC 60601-1, EMC, electrical safety, communication/control failure detection, programming keys, sensors, safe operation)Passed, met all prior established acceptance criteria.
Shelf-life and shipping (4-year aging for disposables, transit/storage for injector system per ISTA 2A)Passed, met all prior established acceptance criteria.
Reliability (sequential/repeated performance, no degradation with simultaneous processes)Passed, met all prior established acceptance criteria.
Simulated Use and Human Factors (clinical user needs, per EN 62366-1:2015 and FDA Guidance)Passed, demonstrated no new or different questions of safety or effectiveness.
Cleaning and disinfection (per FDA Guidance)Passed, systems meet requirements.

2. Sample Size Used for the Test Set and Data Provenance

The document describes various bench tests and simulated use tests rather than studies involving patient data or clinical test sets in the context of an AI/algorithm. Therefore, information regarding "sample size used for the test set" and "data provenance (e.g., country of origin of the data, retrospective or prospective)" is not applicable in the way it would be for AI/algorithm performance studies.

The testing involved:

  • Bench testing: Performed on design changes unique to the proposed devices and on shared elements, leveraging existing data from predicate devices. Specific sample sizes for mechanical tests (e.g., number of syringes tested for pressure) are not detailed but are implied to be sufficient for engineering verification.
  • Aged samples and samples subjected to shipping conditions were used for disposables performance testing.
  • Biocompatibility testing was done on the Kits and Tubing.

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

Given that this is a 510(k) submission for an injection system and accessories, relying on demonstrating substantial equivalence through engineering and simulated use testing, the concept of "ground truth" established by human experts (like radiologists for image analysis) is not directly applicable in the typical sense for AI/algorithm evaluation.

The "ground truth" for the performance tests would be the established engineering specifications and safety requirements, which are set by scientific and regulatory standards (e.g., ISO, IEC, ASTM) and internal design requirements. Human factors testing involved "simulated clinical environment" and validated "clinical user needs," implying input from clinical professionals, but specific numbers or qualifications are not provided.

4. Adjudication Method for the Test Set

Since there is no "test set" in the context of human interpretation of medical data, an "adjudication method" (like 2+1 or 3+1 for resolving disagreements) is not applicable.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No. The document explicitly states: "No clinical testing was required or performed to support this Traditional 510(k) Premarket Notification." Therefore, an MRMC comparative effectiveness study was not done. The device is not an AI/algorithm where human reader improvement with assistance would be measured.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

This device (an angiographic injector and its accessories) is a hardware and software system used with a human operator, not a standalone algorithm for diagnosis or image analysis. The "P3T software accessories compute individual contrast injection protocols and scan timing," which can be considered an algorithmic component, but its performance is verified as part of the overall system's functional design and accuracy in delivering specified parameters, not as a standalone diagnostic algorithm. The testing confirms that this software functions correctly within the system.

7. The Type of Ground Truth Used

The ground truth for this device's performance evaluation is based on:

  • Engineering specifications and design requirements: These define the expected performance parameters (e.g., flow rate range, volume range, pressure limits, sterilization level).
  • International standards and regulations: Such as ISO 594, ISO 11607-1, ISO 10993-1:2009, ISO 11137-1, IEC 60601-1, ASTM D4169, EN 62366-1:2015, and FDA Guidances. These standards establish acceptable performance thresholds for medical devices, particularly regarding safety, biocompatibility, and functionality.

8. The Sample Size for the Training Set

As this is a hardware medical device with supporting software for controlling injections, and not an AI/ML algorithm that requires a "training set" of data to learn from, this concept is not applicable.

9. How the Ground Truth for the Training Set Was Established

Since there is no training set in the context of AI/ML, the question of how its ground truth was established is not applicable. The device's "P3T software" calculates injection protocols based on "patient characteristics, scanner parameters and contrast concentration," which are pre-defined inputs and rules, not learned from a training set.

§ 870.1650 Angiographic injector and syringe.

(a)
Identification. An angiographic injector and syringe is a device that consists of a syringe and a high-pressure injector which are used to inject contrast material into the heart, great vessels, and coronary arteries to study the heart and vessels by x-ray photography.(b)
Classification. Class II (special controls). The device, when it is a non-patient contacting balloon inflation syringe intended only to inflate/deflate balloon catheters and monitor pressure within the balloon, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 870.9.