Search Results

The FlowMet is a non-invasive probe that is affixed to the fingers or toes and intended to quantify tissue blood flow rate.

The FlowMet™ is a non-invasive probe that is affixed to the fingers or toes and intended to quantify tissue blood flow rate. The FlowMet™ probe is affixed to the digit (finger or toe) using a medical tape that is wrapped around the digit. Light source (laser diode) and detector (CMOS camera) secured in ABS/PC housings which are affixed to the digit using medical tape. Light source and detector are oriented to allow transillumination of digit.

The provided text describes the FlowMet device and its equivalence to a predicate device (FlowMet-R). However, it does not contain information about the acceptance criteria or a study proving the device meets those criteria, as typically found in a clinical performance study for an AI-enabled device. The document primarily focuses on demonstrating substantial equivalence to a predicate non-AI device based on technological characteristics and non-clinical performance data (bench testing).

Therefore, I cannot fulfill your request for the detailed information about acceptance criteria and a study proving an AI device meets them, as this information is not present in the provided document. The FlowMet is a "Cardiovascular blood flowmeter" using "Laser Speckle Imaging" and is described as a non-invasive probe measuring tissue blood flow rate, without any mention of AI or machine learning components.

Specifically, the document states:

• No clinical testing was performed. This is a key indicator that a clinical study with detailed acceptance criteria and human expert evaluation, as often required for AI/ML devices, was not conducted.
• The performance data provided is from a bench test comparing the FlowMet to its predicate (FlowMet-R) under known flow rate conditions using a tissue analog, not actual human data.
• The comparison focuses on technological characteristics (e.g., laser safety, measurement site, sterility, affixing method) and non-clinical performance data (linearity, coefficient of variation, correlation coefficient in a bench setting).

Without information regarding AI/ML components or a clinical performance study, I cannot provide the requested details about acceptance criteria, test set characteristics (sample size, provenance, ground truth establishment), expert qualifications, adjudication methods, MRMC studies, or standalone performance.

Ask a specific question about this device

The FlowMet-R is a non-invasive probe that is affixed to the fingers or toes and intended to quantify tissue blood flow rate.

The FlowMet-R™ is a non-invasive probe that is affixed to the fingers or toes and intended to quantify tissue blood flow rate. The FlowMet-R™ is a miniaturized clip-on probe, designed to be affixed to the fingers or toes. The FlowMet-R™'s clamshell housing blocks the laser output when not in use or when applied to a digit.

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the provided text:

The document does not explicitly state "acceptance criteria" for performance metrics in a table format. However, it presents performance tests and their outcomes, implying that successful completion of these tests demonstrates the device meets the necessary performance standards for substantial equivalence.

1. Table of Acceptance Criteria and Reported Device Performance

Based on the performance data section, here's a reconstructed table of implied acceptance criteria and reported performance:

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

• Benchtop Test (FlowMet-R™ vs. PeriCam PSI): No specific sample size in terms of test runs or repeated measurements is provided, but it states "flow rates were varied from 2-20ml/min" and "data was collected concurrently from both systems for a specified length of time (30 seconds) at each flow rate." The data provenance is controlled laboratory conditions using a "tissue analog."
• Benchtop Test (Impact of Skin Coloration): No specific sample size is provided beyond "FlowMet-R™ data was collected under known flow rate conditions using a tissue analog." Skin colors were "simulated by creating silicone-based skin analogs with varying optical absorption." The data provenance is controlled laboratory conditions using "tissue analogs."
• Clinical Test (FlowMet-R™ vs. Laser Doppler):
  • Sample Size: 10 patients (5 male, 5 female).
  • Data Provenance: Not explicitly stated, but it is a prospective clinical test on human subjects ("Data was collected from 10 patients before, during, and after vascular disruption induced via brachial artery occlusion.").
• Clinical Test (Impact of Skin Color):
  • Sample Size: 91 patients (181 total limbs, 84 from females, 97 from males). Grouped by ethnicity/skin color: White/Caucasian (N=144), Hispanic/Latino (N=23), Asian (N=11), and African American (N=3).
  • Data Provenance: Not explicitly stated, but implies prospective collection from human subjects ("FlowMet-R™ blood flow and sensor intensity data was collected from 91 patients").

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

The document does not describe the use of experts to establish ground truth in the context of adjudication for the test set.

• For the benchtop tests, the "ground truth" was established by known volumetric flow rates or controlled optical properties of tissue analogs.
• For the clinical tests, the "ground truth" was established by:
  • The expected physiological response to vascular occlusion.
  • Comparison to a legally marketed predicate device (Laser Doppler flowmeter, K974285, specifically PeriFlux System 5000), which itself serves as a clinical reference.

4. Adjudication Method for the Test Set

No adjudication method involving experts is mentioned for any of the described tests. The comparisons are against physical ground truths (known flow rates, simulated skin colors) or against established medical devices (predicate PeriCam PSI, PeriFlux System 5000 Laser Doppler).

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

No MRMC comparative effectiveness study involving human readers and AI assistance is reported. This device is a measurement tool, not an AI for image interpretation that would typically involve human-in-the-loop performance studies.

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

The described performance tests are all standalone (algorithm only) performance studies, as the device directly measures and quantifies tissue blood flow rate. There is no human intervention in the interpretation of the raw data that the device outputs; the output itself is the measurement. The studies compare the device's measurements against known physical parameters or another established device, not against human judgment.

7. The Type of Ground Truth Used

• Benchtop Test (FlowMet-R™ vs. PeriCam PSI): Ground truth was based on a known, controlled volumetric flow rate using a pump system and tissue analog.
• Benchtop Test (Impact of Skin Coloration): Ground truth was based on known, controlled optical absorption (simulating skin color) in tissue analogs.
• Clinical Test (FlowMet-R™ vs. Laser Doppler): Ground truth was established by:
  • Physiological changes (expected decrease in flow during occlusion).
  • Comparison to measurements from a legally marketed predicate device (Laser Doppler flowmeter), which serves as a clinical reference standard.
• Clinical Test (Impact of Skin Color): Ground truth was based on statistical analysis of measured flow values across self-reported or observed ethnicity/skin color groups, to determine if significant differences existed.

8. The Sample Size for the Training Set

The document describes performance testing (validation) of the device. It does not provide information about a "training set" because this device is not presented as an AI/machine learning device that requires a training set in the conventional sense. The device uses "Laser Speckle Imaging" principles, implying fixed algorithms based on physics rather than learned patterns from data.

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

As no training set is mentioned or implied for this type of device, this question is not applicable.

Ask a specific question about this device