(79 days)
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.
§ 870.2100 Cardiovascular blood flowmeter.
(a)
Identification. A cardiovascular blood flowmeter is a device that is connected to a flow transducer that energizes the transducer and processes and displays the blood flow signal.(b)
Classification. Class II (performance standards).