Search Results

INTENDED USE: P3TTM Cardiac is intended for use with CT Angiography. P3TTM Cardiac computes individual contrast injection protocols and scan timing, based on patient characteristics, scanner parameters and contrast concentration. The user will be required to confirm/change the suggested protocol before beginning an injection.

INDICATIONS FOR USE: P3T™ Cardiac is indicated for use with CT Angiography of the cardiac structures, coronary arteries, chambers of the heart, pulmonary vasculature, and thoracic and abdominal aorta.

The MEDRAD Stellant CT Injector System with P3T™ Cardiac is a syringe-based fluid delivery system indicated for delivery of contrast media during computed tomography procedures. The MEDRAD Stellant CT Injector System is intended for the specific purpose of injecting intravenous contrast media into humans for diagnostic studies in computed tomography (CT) applications.

MEDRAD Stellant CT Injector System operating software includes P3T™ Cardiac, an optional, password-enabled software accessory. The injector system, when used with P3T™ Cardiac, maintains the same intended use, same operational parameters, and same labeling (with the addition of the P3T™ Cardiac operation manual), and is used in the same manner as the injector system without the software accessory.

The P3T™ Cardiac software accessory provides the convenience of generating patientspecific contrast injection protocols, and increases the consistency of individualized injection protocols among technologists.

The provided document is a 510(k) summary for the MEDRAD Stellant CT Injector System with P3TTM Cardiac. This document describes an injector system with a software accessory (P3TTM Cardiac) that computes contrast injection protocols and scan timing for CT Angiography.

Based on the content, this is not a study of an AI/ML diagnostic or prognostic device that would have specific performance metrics like sensitivity, specificity, or AUC against a ground truth dataset. Instead, it's a submission for an imaging accessory that aids in optimizing injection protocols. The submission focuses on substantial equivalence to a predicate device (MEDRAD Stellant CT Injector System with P3TTM CardiacFlow (K072886)) rather than presenting a performance study against specific acceptance criteria for diagnostic accuracy.

Therefore, many of the requested elements for a performance study (like test set size, expert ground truth, MRMC study, standalone performance, training set details) are not applicable or not present in this type of submission, as the device's function is to generate protocols, not to interpret images or diagnose conditions.

Here's a breakdown based on the provided text, highlighting what is available and what is not:

1. Table of Acceptance Criteria and Reported Device Performance:

The document does not present a table of specific quantitative "acceptance criteria" and "reported device performance" in the way one would for a diagnostic algorithm (e.g., sensitivity, specificity, accuracy thresholds). Instead, the "acceptance" for this type of device is regulatory clearance based on substantial equivalence to a predicate device. The performance is indirectly supported by the device's functionalities being comparable or expanded from the predicate, and its ability to generate injection protocols as intended.

Key "performance" aspects discussed are functional equivalence to its predicate:

Summary of "Acceptance": The device was deemed "substantially equivalent" to the predicate device (K072886) by the FDA, based on the comparison of features and intended use. The extension of indications to include pulmonary vasculature and abdominal aorta (beyond gated ECG acquisition) for the P3T™ Cardiac, while maintaining the same core functionality and safety features, was accepted.

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

• Not applicable / Not provided. This document does not describe a clinical performance study using a test set of patient data for a diagnostic outcome. The P3T™ Cardiac software is an accessory that computes injection protocols, not interprets images.

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

• Not applicable / Not provided. As there is no test set for diagnostic performance, there is no need for experts to establish ground truth in this context. The "ground truth" for the device would be the accuracy of its computed injection protocols in practice, which is generally assessed through engineering validation and clinical use rather than a formal ground-truth-labeled dataset.

4. Adjudication method for the test set:

• Not applicable / Not provided.

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 a diagnostic AI device. An MRMC study is not relevant here. The device assists technologists in generating protocols, but not in image interpretation or diagnosis.

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

• Not applicable / Not provided in this context. While the P3T™ Cardiac software operates standalone to compute the protocol, it's explicitly stated that "The user will be required to confirm/change the suggested protocol before beginning an injection." This indicates a human-in-the-loop for final decision-making, which is part of its intended safe use. The submission focuses on the safety and functional equivalence of the injector system with the software rather than a standalone AI performance evaluation for diagnostic output.

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

• Not applicable / Not provided. The "ground truth" for an injection protocol computation device would involve whether the computed protocols lead to optimal image quality and patient outcomes, which is generally assured through engineering validation, simulated environments, and clinical experience/studies (not usually detailed in a 510(k) summary focused on substantial equivalence).

8. The sample size for the training set:

• Not applicable / Not provided. The P3T™ Cardiac software computes protocols based on patient characteristics and scanner parameters using presumably pre-programmed algorithms or models, not a machine learning "training set" in the sense of image recognition or diagnostic AI.

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

• Not applicable / Not provided.

Ask a specific question about this device

The MEDRAD Stellant CT Injector System is intended for the specific purpose of injecting intravenous contrast media into humans for diagnostic studies in computed tomography (CT) applications.

The Stellant P3T CardiacFlow software accessory is intended for use in CT angiography of cardiac structures, including coronary arteries, chambers of the heart, and thoracic and abdominal aorta during gated ECG acquisition.

The Stellant P3T CardiacFlow software accessory computes individual contrast injection protocols and scan timing, based on patient characteristics, scanner parameters and contrast concentration. The user will be required to confirm/change the suggested protocol before beginning an injection.

MEDRAD Stellant CT Injector System operating software has been modified to include the P3T CardiacFlow accessory. P3T CardiacFlow is an optional, password-enabled accessory. The injector system, when used with P3T CardiacFlow, maintains the same intended use, same operational parameters, and same labeling (with the addition of a P3T CardiacFlow operations manual). This device is also used in the same manner as the predicate devices.

The MEDRAD Stellant CT Injector System with P3T CardiacFlow is a syringe-based fluid delivery system indicated for delivery of contrast media during computed tomography procedures. The MEDRAD Stellant CT Injector System is intended for the specific purpose of injecting intravenous contrast media into humans for diagnostic studies in computed tomography (CT) applications.

MEDRAD Stellant CT Injector System operating software has been modified to include the P3T CardiacFlow accessory. MEDRAD Stellant CT Injector System with P3T CardiacFlow maintains the same intended use, operational parameters, and labeling as the MEDRAD Stellant CT Injector System, with the addition of P3T CardiacFlow Instructions For Use. The P3T CardiacFlow accessory provides the convenience of generating patient-specific contrast injection protocols, and increases the consistency of individualized injection protocols among technologists. Stellant CT Injector System with P3T CardiacFlow is used in the same manner as the predicate device (Stellant CT Injector System without P3T CardiacFlow).

The provided document, K072886, describes the MEDRAD Stellant CT Injector System with P3T CardiacFlow software accessory. This is a premarket notification (510(k)) and primarily focuses on establishing substantial equivalence to predicate devices, rather than an independent clinical study demonstrating specific performance metrics against defined acceptance criteria. Therefore, the details requested for a clinical study proving acceptance criteria compliance are not fully available in this document.

However, based on the information provided, we can infer the acceptance criteria and some aspects of performance. The substantial equivalence argument itself serves as the "study" in this context for regulatory clearance.

1. Table of Acceptance Criteria and Reported Device Performance

Given that this is a 510(k) for substantial equivalence, the "acceptance criteria" are implicitly met by demonstrating that the proposed device is as safe and effective as the predicate devices. The performance is reported in terms of feature comparison.

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

The document does not describe a clinical study with a "test set" in the traditional sense of patient data used to evaluate AI performance. The evaluation is based on a comparison of device features, intended use, and operational parameters against existing legally marketed predicate devices. The provenance of any underlying data that informed the development of the P3T CardiacFlow algorithm (e.g., patient characteristics, scanner parameters, contrast concentration relationships) is not specified. It is likely based on engineering principles, scientific literature, and potentially in-house data/simulations rather than a distinct, prospectively collected, and adjudicated clinical "test set" for regulatory submission.

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

Not applicable, as this device's regulatory review is based on substantial equivalence to existing devices and its operational safety and effectiveness, rather than a diagnostic AI algorithm requiring ground truth established by experts on a test set. The efficacy of the P3T CardiacFlow algorithm itself (meaning its ability to accurately compute protocols for optimal cardiac CT angiography) would presumably be verified through internal engineering and potentially pre-clinical or limited clinical testing, but these details are not provided in the 510(k) summary.

4. Adjudication Method for the Test Set

Not applicable for the reasons stated in point 3.

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

Not applicable. This device is an injector system with software to assist in protocol generation, not an AI diagnostic algorithm meant to be read by human readers. Therefore, an MRMC study is not relevant to its regulatory submission in this context. The benefit of the P3T CardiacFlow is stated as "increases the consistency of individualized injection protocols among technologists" (page 1).

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

The P3T CardiacFlow is not a standalone algorithm that operates without human intervention. The document explicitly states: "The user will be required to confirm/change the suggested protocol before beginning an injection." and "every injection protocol must be approved and locked by the practitioner. The practitioner always has the option of modifying or deleting the P3T CardiacFlow suggested protocol." (Page 1-2). This indicates a human-in-the-loop design where the algorithm provides suggestions but requires final human approval and can be overridden.

7. The Type of Ground Truth Used (Expert Consensus, Pathology, Outcomes Data, etc.)

Since this is not a diagnostic device establishing a "ground truth" for a medical condition, the concept of ground truth as typically applied to diagnostic AI is not directly applicable. For the P3T CardiacFlow software, the "ground truth" for its function would be whether the computed protocols are appropriate and effective for the intended CT angiography procedures, leading to diagnostic quality images while ensuring patient safety. This "truth" would likely be established through:

• Engineering validation: Demonstrating that the algorithm correctly applies the defined logic based on input parameters.
• Physical modeling, simulations, and phantom studies: Verifying that the proposed injection protocols achieve desired contrast enhancement profiles.
• Possibly limited clinical evaluation or literature review: Confirming that the principles underlying the algorithm lead to clinically acceptable results in practice, as informed by medical expertise in CT angiography.
  However, specific details of such validation are not provided in this 510(k) summary.

8. The Sample Size for the Training Set

Not applicable. The document does not describe a machine learning model that requires a distinct "training set" of data for learning patterns, as might be the case for image recognition algorithms. The P3T CardiacFlow computes protocols based on predefined patient characteristics, scanner parameters, and contrast concentration, likely using a programmed algorithm based on scientific principles and clinical knowledge, rather than a learned model from a large dataset.

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

Not applicable for the reasons stated in point 8.

Ask a specific question about this device