(59 days)
The device as a noninvasive blood pressure measurement system intended to measure the systolic and diastolic blood pressures and pulse rate or an adult individual, over age 18, at home by using a non-invasive technique in which an inflatable cuff is wrapped around the wrist. The cuff circumference is limited to 5.25"-7.75".
APM BP108A uses the Oscillomeric method to measure the blood pressure. The Oscillometric method is adopted clinically to measure the blood pressure recently. It is not needed to use the stethoscope, as in the traditional measuring method, to monitor the Korotkov sound when deciding the systolic or diastolic pressure. The Oscillometric method senses the vibrating signal via the closed air pipe system and utilizes the microcomputer to automatically sense the characteristics of the pulse Through simple calculation, clinically proven, the reading can reflect the signal. accurate real blood pressure, and the systolic pressure is defined as the pressure when the cuff pressure oscillating amplitude begins to increase and the diastolic pressure as the pressure when the cuff pressure oscillating amplitude stops decreasing.
The provided document is a 510(k) summary for the APM Blood Pressure Monitor, BP108A. While it mentions performance testing against standards, it does not detail specific acceptance criteria or provide a study report proving the device meets those criteria.
Here's an analysis based on the available information regarding your requested points:
1. A table of acceptance criteria and the reported device performance
The document mentions compliance with the ANSI/AAMI SP10-1992 standard for Electronic or Automated Sphygmomanometers. This standard outlines accuracy requirements for blood pressure monitors. However, the document does not provide a table with specific acceptance criteria from this standard and the device's reported performance against them. It simply states that performance testing was conducted against this standard.
The ANSI/AAMI SP10-1992 standard typically has requirements related to accuracy (mean difference and standard deviation between the device and a reference measurement), usually for systolic and diastolic blood pressure. For example, a common requirement is that the mean difference should be within ±5 mmHg with a standard deviation of no more than 8 mmHg. However, these specific values are not provided in the document for the APM Blood Pressure Monitor, BP108A.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
The document does not specify the sample size used for performance testing related to the ANSI/AAMI SP10-1992 standard. It also does not mention the country of origin of the data or whether the study was retrospective or prospective.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
When evaluating blood pressure monitors against a reference standard like ANSI/AAMI SP10, the "ground truth" for blood pressure measurements is typically established by comparing the device's readings to those obtained by trained observers using a auscultatory method (manual sphygmomanometry with a stethoscope) or a validated reference device. Such studies usually involve multiple trained observers (often two, sometimes a third for adjudication) who are proficient in taking manual blood pressure measurements according to specific protocols.
However, the provided document does not specify the number or qualifications of experts used to establish the ground truth for the performance testing.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
The document does not mention any adjudication method used for the test set. In performance testing for blood pressure monitors, if multiple observers are used for the reference measurements, methods like averaging their readings or involving an adjudicator for discrepancies are common.
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
This device is a non-invasive blood pressure monitor, not an AI-powered diagnostic tool for image interpretation or similar. Therefore, a multi-reader multi-case (MRMC) comparative effectiveness study involving human readers and AI assistance is not applicable to this type of device and was not mentioned as being performed.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The device itself is a standalone blood pressure monitor (algorithm only for measurement without human intervention beyond placing the cuff and initiating the measurement). The performance testing against ANSI/AAMI SP10-1992 would inherently be a standalone performance evaluation of the device's accuracy in measuring blood pressure compared to a reference standard. The document doesn't explicitly label it as "standalone study" but the nature of the device and the standard implies this.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
For blood pressure monitors, the "ground truth" is typically established by concurrent measurements performed by trained observers using a validated reference method (e.g., auscultatory method with a mercury sphygmomanometer or a validated electronic device). This is a form of expert measurement consensus/comparison rather than pathology or outcomes data. The document does not explicitly state how the ground truth was established beyond referencing the ANSI/AAMI SP10 standard, which implicitly requires this type of comparison.
8. The sample size for the training set
The document does not mention a training set because this type of device (traditional non-invasive blood pressure monitor) doesn't typically utilize machine learning in a way that requires a "training set" in the context of AI/ML models. Its algorithm for oscillometric measurement is based on established physiological principles and signal processing, not on iterative learning from a labeled dataset in the typical AI sense.
9. How the ground truth for the training set was established
As there is no mention of a "training set" in the context of an AI/ML model for this device, this question is not applicable.
§ 870.1130 Noninvasive blood pressure measurement system.
(a)
Identification. A noninvasive blood pressure measurement system is a device that provides a signal from which systolic, diastolic, mean, or any combination of the three pressures can be derived through the use of tranducers placed on the surface of the body.(b)
Classification. Class II (performance standards).