(77 days)
The Cheetah Integrated Vascular Diagnostic System (I.V.D.S.) is a non-invasive tool intended to detect blood wave front (BWF) delay.
The Cheetah I.V.D.S. is a portable, non-invasive, 4-Channel Cheetah - Blood Wave Front (BWF) detector, with an additional Time Marker channel. The Cheetah channel is intended to measure the time lag between the start of the blood wave front in the peripheral vascular system and the peak of the R-wave on the time marker signal.
The Cheetah I.V.D.S. consists of 2 finger probes, 2 toe probes and time marker leads placed on the subject's wrists and legs. The probes are connected to a computer that analyses and presents a print out of the pulse wave as it reaches the periphery.
In addition, the Cheetah I.V.D.S. comprises standard Laptop computer connected to conventional analog-to-digital converter, which is used for the analysis and presentation of the acquired data.
The Cheetah I.V.D.S. is a device intended to detect blood wave front (BWF) delay. The provided text outlines its intended use, design, and a clinical study conducted for substantial equivalence.
Here's an analysis of the acceptance criteria and the study, with a focus on the requested information:
1. Table of Acceptance Criteria and Reported Device Performance
The provided text does not explicitly state quantitative performance acceptance criteria (e.g., specific accuracy thresholds) for the Cheetah I.V.D.S. in terms of BWF delay detection. Instead, the performance evaluation primarily focuses on demonstrating substantial equivalence to a predicate device, the Autocorr® Plus (#3404) Pulse Oximeter/ECG Monitor.
The key performance criterion for the Cheetah I.V.D.S. in the context of the clinical study was:
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| No statistically significant difference in automatically calculated time lag measurements between the Cheetah I.V.D.S. and the predicate Autocorr device, when using the same Time markers. | "Study results showed that using the same Time markers, there is no statistically significant difference between the automatically calculated time lag measurements of the Cheetah I.V.D.S. and the output of the Autocorr device." |
2. Sample Size Used for the Test Set and Data Provenance
The document does not specify the sample size of subjects or data points used in the clinical study that compared the Cheetah I.V.D.S. to the Autocorr device.
The data provenance (country of origin, retrospective/prospective) is also not explicitly stated for this clinical study.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
The document does not describe the use of experts to establish a "ground truth" for the test set in the conventional sense of expert consensus on a diagnosis or measurement. Instead, the comparison was made against a legally marketed predicate device, the Autocorr Time Marker. The "ground truth" in this context is the output of the predicate device.
4. Adjudication Method for the Test Set
No adjudication method is described for the test set. Given that the comparison was between the Cheetah I.V.D.S. and a predicate device's output, it's unlikely that expert adjudication as typically applied to image or diagnostic interpretation was used.
5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs. Without AI Assistance
No Multi Reader Multi Case (MRMC) comparative effectiveness study was done. The Cheetah I.V.D.S. is not presented as an AI-assisted device for human readers; it is a non-invasive diagnostic tool that measures BWF delay. Therefore, there's no mention of human reader improvement with or without AI assistance.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
The clinical study described appears to be a standalone performance evaluation in the sense that the Cheetah I.V.D.S. itself, without human interpretation adding to its direct output, was compared to the predicate device. The device "analyses and presents a print out of the pulse wave" and "calculates and compares the time lags." The comparison was specifically on the "automatically calculated time lag measurements."
7. The Type of Ground Truth Used
The ground truth used for the comparative clinical study was the output of a legally marketed predicate device, the Autocorr® Plus Pulse Oximeter/ECG Monitor (specifically its time marker functionality). This falls under a form of reference standard comparison against an established and accepted device.
8. The Sample Size for the Training Set
The document does not mention a "training set" in the context of machine learning or AI development. The device is described as utilizing "currently available technology," and the software verification and validation are mentioned as ensuring performance according to specifications, but no explicit training data or its size is provided.
9. How the Ground Truth for the Training Set Was Established
As no training set is described for machine learning or AI, the method for establishing ground truth for a training set is not applicable or provided in this document. The device's functionality is based on established physiological measurements rather than learned patterns from a large training dataset.
§ 870.1425 Programmable diagnostic computer.
(a)
Identification. A programmable diagnostic computer is a device that can be programmed to compute various physiologic or blood flow parameters based on the output from one or more electrodes, transducers, or measuring devices; this device includes any associated commercially supplied programs.(b)
Classification. Class II (performance standards).