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

P.D. Access Device: Is intended for use when blood flow must be detected for percutaneous vessel cannulation. The vessel must be of a caliber which would normally be punctured with a needle and introducer of this size or larger. These additional probe/needle models are being incorporated to broaden the product line in order to accommodate both user preference and patient anatomies for all age groups.

P.D. Access Monitor: Is intended for use to audibly indicate the doppler response of blood flow within an artery or vein. It is intended for use only in conjunction with the P.D. Access Vascular Access Device.

Device Description

The P.D. Access™ device is intended to be used in conjunction with the P.D. Access Dual Frequency Monitor for general vascular use. The P.D. Access device is intended for general vascular use for audibly indicating the Doppler response to blood flow within an artery or vein. The indications and intended use for the P.D. Access device is the same as the predicate devices manufactured by CardioVascular Dynamics (i.e., P.D. Access/SmartNeedle). Product technology, performance characteristics, specifications, components and materials of the P.D. Access device are similar to those of predicate devices.

AI/ML Overview

The CardioVascular Dynamics, Inc. P.D. Access™ Vascular Access Device and P.D. Access™ Dual Frequency Monitor received 510(k) clearance based on substantial equivalence to predicate devices, rather than a study demonstrating meeting specific acceptance criteria with performance metrics. The submission focuses on comparing the new device's characteristics to already legally marketed devices.

Here's an analysis based on the provided documents:

1. Table of Acceptance Criteria and Reported Device Performance

The provided documents do not define specific quantitative acceptance criteria or present performance metrics in a manner typical for a study proving device efficacy or accuracy like sensitivity, specificity, or AUC. Instead, the acceptance is based on demonstrating substantial equivalence in design, materials, indications, and overall safety and effectiveness compared to predicate devices.

The "reported device performance" is described qualitatively as:

Acceptance Criteria Type (implied via substantial equivalence)Reported Device Performance
Dimensional, Strength, Ultrasonic Performance"These tests demonstrated that all of the items tested were within specification tolerances. There were no failures during these tests."
Biocompatibility"These tests demonstrated that all of the items tested were within specification tolerances. There were no failures during these tests."
Overall Safety and Effectiveness"Overall performance was safe and effective." (Based on similarity to predicate devices and aforementioned testing.)
Indications and Intended Use"The indications and intended use for the P.D. Access device is the same as the predicate devices manufactured by CardioVascular Dynamics (i.e., P.D. Access/SmartNeedle)." "The P.D. Access device is intended for use in the same manner. In particular, the P.D. Access device is equivalent in indications and intended use to devices manufactured by CardioVascular Dynamics, formerly manufactured by Advance Cardiovascular Systems (ACS)."
Product Technology, Performance Characteristics, Specs, Components, Materials"Product technology, performance characteristics, specifications, components and materials of the P.D. Access device are similar to those of predicate devices."

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

  • The documents do not mention a specific "test set" in the context of an accuracy or performance study involving patient data or clinical outcomes.
  • The testing described ("dimensional, strength, ultrasonic performance and biocompatibility testing") would have involved physical samples of the device components, not patient data.
  • No information on provenance (country of origin, retrospective/prospective) of data is provided, as no clinical study data is presented for performance evaluation against ground truth.

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

  • Not applicable. No clinical test set requiring expert ground truth establishment is described. The evaluation was primarily based on engineering and biocompatibility testing against predefined specifications, and a comparison to predicate devices, not an expert-adjudicated test set for diagnostic accuracy.

4. Adjudication Method for the Test Set

  • Not applicable. No clinical test set requiring adjudication is described.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

  • No, an MRMC comparative effectiveness study was not done. The submission solely focuses on demonstrating substantial equivalence to predicate devices, not on comparing performance with and without AI assistance or evaluating human reader improvement. This device is a diagnostic tool (Doppler monitor and access device), not an AI-powered image analysis system.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

  • No, a standalone performance study in the context of an algorithm or AI is not applicable. The P.D. Access device is a physical medical device (vascular access and Doppler monitor) that audibly indicates blood flow, designed for human clinical use, not a standalone algorithm. The "ultrasonic performance" testing would have verified its function, but this is distinct from AI algorithm performance.

7. Type of Ground Truth Used

  • The "ground truth" for the engineering and biocompatibility tests would be the established device specifications and regulatory standards for material properties, dimensions, ultrasonic output, and biocompatibility.
  • For the substantial equivalence claim, the "ground truth" is effectively the performance and safety profiles of the predicate devices, against which the new device was compared.

8. Sample Size for the Training Set

  • Not applicable. This device is not an AI/ML algorithm that requires a training set.

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

  • Not applicable. As the device does not involve AI/ML, there is no training set and therefore no ground truth establishment for one.

Summary based on the 510(k) submission:

The 510(k) cleared the P.D. Access™ Vascular Access Device and Dual Frequency Monitor based on its substantial equivalence to existing predicate devices. The evidence provided included:

  • Engineering and material testing (dimensional, strength, ultrasonic performance, biocompatibility) demonstrating the device met its own specifications and performed without failures.
  • A detailed comparison chart showing product technology, performance characteristics, specifications, components, and materials were "similar" to predicate devices.
  • An assertion that its indications for use and intended use were "the same" as predicate devices.

The FDA decision letter confirms this, stating the device is "substantially equivalent (for the indications for use stated in the enclosure) to devices marketed in interstate commerce prior to May 28, 1976... or to devices that have been reclassified." There were no clinical studies or performance accuracy studies against a "ground truth" as would be seen for new diagnostic algorithms or complex AI devices.

§ 892.1570 Diagnostic ultrasonic transducer.

(a)
Identification. A diagnostic ultrasonic transducer is a device made of a piezoelectric material that converts electrical signals into acoustic signals and acoustic signals into electrical signals and intended for use in diagnostic ultrasonic medical devices. Accessories of this generic type of device may include transmission media for acoustically coupling the transducer to the body surface, such as acoustic gel, paste, or a flexible fluid container.(b)
Classification. Class II.