K Number
K981702
Date Cleared
1999-03-05

(295 days)

Product Code
Regulation Number
870.1130
Panel
CV
Reference & Predicate Devices
Predicate For
N/A
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The WS-300 system is intended for the noninvasive measurement of systolic and diastolic blood pressure and determination of heart rate in adult patients. The product is recommended for use by patients with labile blood pressure or known hypertension in a home care environment as an adjunct to medical management.

Device Description

The WS-300 system is an automatic sphygmomanometer intended for measurement of blood pressure at the wrist using the oscillometric method. The entire system, including the cuff, is a single wrist-mounted unit. The system is microprocessor controlled and includes an air pump, an electromagnetic valve to regulate deflation rate, circuitry to detect and process minute pressure oscillations, an LCD display of systolic and diastolic pressure readings followed by heart rate, and pushbutton controls. A memory circuit stores the seven most recent measurements for comparison.

Operation: The WS-300 system employs a pressurement algorithm designed to detect, filter, process, and store pressure readings. The algorithm has been evaluated for the ability to detect and compensate for artifacts and to vield reliable readings in the presence of cardiac arrhythmias. The electromagnetic deflation control valve maintains the deflation rate at a constant 4 mmHg/sec irrespective of differences in wrist size which would otherwise cause variation in the deflation rate.

Power: The unit is powered by two AA-size batteries and contains an indicator to alert the operator when battery charge is weak.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study information for the Model WS-300 Automatic Digital Electronic Wrist Blood Pressure Monitor, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

Acceptance CriterionReported Device Performance
Measurement Accuracy"The results of performance tests showed the WS-300 to comply with measurement accuracy... requirements as stated in ANSI/AAMI Standard SP10-1992." (Note: The specific numerical accuracy limits of ANSI/AAMI SP10-1992 are not provided in this document, but compliance with the standard indicates they were met.)
Cuff Deflation Requirements"The results of performance tests showed the WS-300 to comply with... cuff deflation requirements as stated in ANSI/AAMI Standard SP10-1992." Additionally, "The electromagnetic deflation control valve maintains the deflation rate at a constant 4 mmHg/sec irrespective of differences in wrist size."
Artifact Detection & Compensation"The algorithm has been evaluated for the ability to detect and compensate for artifacts..." (No specific quantitative performance metrics are given, but evaluation was conducted.)
Reliable Readings in Presence of Cardiac Arrhythmias"...and to yield reliable readings in the presence of cardiac arrhythmias." (No specific quantitative performance metrics are given, but evaluation was conducted.)
Maximum Cuff Pressure"Safety testing including maximum cuff pressure... has been conducted, resulting in the determination that the subject device complies with all relevant safety standards."
Stability (Operating & Storage)"Safety testing including... stability under various operating and storage conditions... has been conducted, resulting in the determination that the subject device complies with all relevant safety standards."
Vibration and Shock"Safety testing including... vibration and shock... has been conducted, resulting in the determination that the subject device complies with all relevant safety standards."
Electromagnetic Compatibility (EMC)"Safety testing including... electromagnetic compatibility has been conducted, resulting in the determination that the subject device complies with all relevant safety standards."
Software Validation"Software validation testing was performed and reported in accordance with applicable FDA guidance."

2. Sample Size for the Test Set and Data Provenance

The document mentions "injecting identical pulse wave data" to compare the WS-300 with the predicate device (WS-200). This suggests a simulated or benchtop test, rather than a clinical human subject test with a specific sample size of individuals. The data provenance is not explicitly stated as originating from a specific country or as retrospective/prospective in a clinical sense. Given the method, it's likely lab-generated data.

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

Not applicable. The "ground truth" for the performance evaluation appears to be established by comparison to a predicate device and adherence to a recognized standard (ANSI/AAMI SP10-1992), rather than expert consensus on clinical cases. The comparison involved "injecting identical pulse wave data" and evaluating output, which doesn't directly involve human experts establishing ground truth for individual cases.

4. Adjudication Method for the Test Set

Not applicable. There is no mention of an adjudication method as the evaluation was based on a direct comparison of outputs from synthesized pulse wave data and compliance with a standard, rather than subjective interpretation of results requiring adjudication.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study Was Done

No, an MRMC comparative effectiveness study was not explicitly done. The document describes a comparison of the WS-300 with the predicate device WS-200 by "injecting identical pulse wave data." This is a technical comparison for performance, not a study evaluating human reader improvement with AI assistance.

6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) Was Done

Yes, the performance testing described is a standalone evaluation. The device (algorithm) was tested by "injecting identical pulse wave data" – this assesses the algorithm's performance without human interaction or interpretation as part of the measurement process itself. The intended use is for home measurement, where the device operates automatically.

7. The Type of Ground Truth Used

The ground truth appears to be based on:

  • Comparison to a Predicate Device: "excellent agreement between results calculated by the subject device and the predicate device were demonstrated."
  • Compliance with a Recognized Standard: "The results of performance tests showed the WS-300 to comply with measurement accuracy and cuff deflation requirements as stated in ANSI/AAMI Standard SP10-1992."
  • Engineered Performance: The "electromagnetic deflation control valve maintains the deflation rate at a constant 4 mmHg/sec," which is a design specification that contributes to accurate measurement.

8. The Sample Size for the Training Set

The document does not provide any information regarding a training set sample size. This type of device's algorithm development might not involve a distinct "training set" in the sense of machine learning models that require labeled data to learn. The algorithm for oscillometric blood pressure measurement is typically based on physiological principles and signal processing, which may be developed and refined through engineering and testing, rather than traditional machine learning training.

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

As no "training set" is mentioned or implied for an AI/machine learning model, this information is not provided in the document. The algorithm's development and validation would likely rely on established physiological models of blood pressure, signal processing techniques, and testing against reference measurements (e.g., from an invasive arterial line or a professional mercury sphygmomanometer in a controlled setting, though this is not explicitly detailed in the provided text for the training phase).

§ 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).