Search Results

The Falcon/Xpress is intended for use in the noninvasive evaluation of peripheral vascular pathology in patients. The Falcon/Xpress is not intended to replace other means of evaluating vital patient physiological processes, is not intended to be used in fetal applications, and is not intended to be used inside the sterile field. The Falcon/Xpress is to be used only by trained medical personnel in hospitals, clinics and physicians' offices by prescription or doctor's orders

The Falcon/Xpress is intended for use in the noninvasive evaluation of peripheral vascular pathology in patients . The Falcon/Xpress is a new model that is added to the cleared Falcon product family (K111416), which already includes the Falcon/Pro, Falcon/Quad and Falcon/ABI+ models. The Falcon/Xpress is similar to the other Falcon models in terms of technology, operation, software, intended use, applications, and accessories. The main differences are that the Falcon/Xpress supports 2 independent pressure channels (compared to 10 for the Pro and 4 for the Falcon/Quad and Falcon/ABI+), 2 PPG sensors (compared to 5 for the Pro and 4 for the Quad and ABI+), 2 Doppler ports (compared to 3 for the Pro and Quad and 0 for the ABI+), and no temperature sensor (compared to 1 for the Pro, Quad and ABI+). In addition, the Falcon/Xpress supports operation with an external battery and supports an 8-channel pressure selector (not available with the other Falcon models). The Falcon/Xpress supports an optional tablet, and can be mounted on a cart or within a dedicated bag. The Falcon/Xpress system is smaller in size, with dimensions of roughly 27x20x5.5 cm, compared to the Falcon legacy models with dimensions of 34x31x9.5 cm. In addition, the Falcon/Xpress system weighs roughly 2 kg, compared to roughly 4 kg for the Falcon legacy models. Similar to the other Falcon models, the Falcon/Xpress is based on pneumatic technology to measure systolic blood pressures and Pulse Volume Recording waveforms (PVR) at various peripheral limb sites. Similarly, the Falcon/Xpress includes the same Continuous Wave (CW) Doppler technology as the other Falcon models to allow measurements of blood flow velocities in peripheral blood vessels. The Falcon/Xpress also supports the same Photo-Plethysmography technology (PPG) as the other cleared Falcon models. The above-mentioned technologies allow the Falcon/Xpress to perform peripheral vascular diagnosis measurements in a similar manner to the cleared Falcon models (K111416), including the measurements of segmental systolic blood pressures, the Ankle-Brachial pressure index, PVR measurement, PPG measurements, and blood flow velocity measurements. The measurements support dedicated specialty test protocols such as measurements under various stress conditions, thoracic outlet syndrome, raynaud's syndrome, pulse wave velocity, penile function, venous reflux, venous capacitance and outflow, palmar arch test, arterio-venous fistula, and similar. All of the specialty tests simply use the measurements according to dedicated protocols and display for the evaluation of specific medical conditions. The pressure cuffs are connected to the air tubes via "Bayonet" connectors or Viasonix Vfit connectors. Both of these options are designed to avoid potential misconnections by being incompatible with standard Luer connectors or other connectors used for nonvascular applications.

The provided text is an FDA 510(k) summary for the Falcon/Xpress device. It focuses on demonstrating substantial equivalence to a predicate device rather than presenting a detailed clinical study for assessing performance against specific acceptance criteria for AI integration.

Therefore, many of the requested details, particularly regarding acceptance criteria for AI performance, sample sizes for test sets, expert ground truth establishment, MRMC studies, standalone AI performance, and AI-specific training/ground truth, are not available in this document. The document explicitly states "No clinical study was conducted to support this application."

However, I can extract information related to the device's characteristics and the non-clinical testing performed to show its equivalence to the predicate device.

Here's an attempt to answer your questions based on the provided text, while acknowledging the limitations:

1. A table of acceptance criteria and the reported device performance

The document does not specify quantitative acceptance criteria in terms of AI model performance (e.g., AUC, sensitivity, specificity) because it's not a study of AI performance, but rather a submission for substantial equivalence based on device characteristics. Instead, the "acceptance criteria" are implied by the claim of substantial equivalence to the predicate device and compliance with relevant standards. The reported performance is an assertion of equivalency of the new model to the predicate device through non-clinical testing.

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

• Sample Size: Not applicable/not stated. The submission relies on non-clinical bench testing and substantial equivalence to a predicate device, not a clinical study with a specific test set of patient data for performance evaluation.
• Data Provenance: Not applicable, as there was no clinical data test set.

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

• Not applicable. No clinical test set with expert ground truth was used for this 510(k) submission.

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

• Not applicable. No clinical test set.

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. The document explicitly states: "No clinical study was conducted to support this application." This device is not an AI-assisted diagnostic tool in the sense of image interpretation for which an MRMC study would typically be performed.

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

• Not applicable. This is not an AI algorithm submitting standalone performance data. The device itself is a diagnostic instrument, not solely an AI algorithm. Its performance is evaluated through its physical and software functionality as a whole unit, which is compared to its predicate.

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

• For the non-clinical testing, the "ground truth" would be established by validated test methods, reference standards, and specifications against which the device's components and integrated system are measured. For example:
  • Pressure measurements: Calibration against known pressure standards.
  • Doppler frequencies: Measurement against known frequency sources.
  • Software functionality: Verification and validation against software requirements and design specifications.
  • Safety/EMC: Compliance with international standards (IEC 60601 series).

8. The sample size for the training set

• Not applicable. This document does not describe the development or performance of an AI model that would require a "training set" in the machine learning sense. It's a medical device.

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

• Not applicable, as there was no AI training set as described in the context of this submission.

Ask a specific question about this device