K Number
K163679
Date Cleared
2017-06-07

(162 days)

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

The upper arm blood pressure monitor is used to carry out non-invasive measurement and monitoring of the arterial blood pressure values in adults. This allows you to quickly and easily measure your blood pressure, save the measured values and display the development and average values of the measured values taken.

Device Description

Digital Automatic Blood Pressure Monitor MD3600 (Subject Device) are non-invasive blood pressure measurement systems for use by medical professional or at home. It is designed to measure the systolic and diastolic blood pressure, and pulse rate of an individual in each measurement and then display the readings on a digital panel.

The Subject Device utilize the oscillometric methodology, in which an inflatable cuff is wrapped around the upper arm of an individual, for blood pressure measurement. This means the monitor detects your blood's movement through your brachial artery and converts the movement into a digital reading.

The Subject Device equipped with Bluetooth transmission, which enable user to transfer the measurement record from the device to a mobile platform through Bluetooth. User can manage the measurement record by using the mobile application.

AI/ML Overview

Acceptance Cryiteria and Study Data for Digital Automatic Blood Pressure Monitor MD3600

1. Table of Acceptance Criteria and Reported Device Performance

The provided document describes the predicate device's acceptance criteria, which are identical to the subject device's criteria given the statement "All of the clinical and non-clinical testing performed on the Subject Device are same as the Predicate Device. Therefore, no bench test is conducted to show the performance of the Subject Device are equivalent to the Predicate Device." The key performance criteria for a non-invasive blood pressure measurement system are accuracy and range.

Acceptance CriteriaReported Device Performance (Subject Device MD3600)
Blood Pressure Accuracy± 3 mmHg
Pulse Rate Accuracy± 5 % of the reading
BP Measurement RangeCuff Pressure: 0 - 300 mmHg
Systolic Pressure: 50 - 250 mmHg
Diastolic Pressure: 30 - 200 mmHg
Resolution of MeasurementBlood Pressure: 1 mmHg, Pulse Rate: 1 beat/min
Pulse Rate Measurement Range40 - 180 beats/min

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

  • Sample Size for Test Set: 100 patients (49 males and 51 females).
  • Data Provenance: The document does not explicitly state the country of origin for the clinical study data or if it was retrospective or prospective. However, based on the submission being from "GRANDWAY TECHNOLOGY (SHENZHEN) LIMITED" in "Shenzhen, People's Republic of China," and the clinical study being conducted to support FDA clearance, it is likely a prospective study. The location of the study subjects (e.g., country) is not specified.

3. Number of Experts Used to Establish Ground Truth and Qualifications

  • The document implies that the ground truth for the test set was established using a "Standard auscultation method" by a medical professional or professionals.
  • Number of Experts: Not explicitly stated, but typically, auscultation involves at least one trained observer.
  • Qualifications of Experts: Not explicitly stated, but the "Standard auscultation method" implies a trained medical professional (e.g., a physician, nurse, or technician with appropriate training in blood pressure measurement).

4. Adjudication Method for the Test Set

The adjudication method appears to be a direct comparison against the "Standard auscultation method." Measurements were "repeated alternatively with the device and auscultation in the same arm according to the sequence in ISO 81060-2." This suggests a comparative, side-by-side measurement rather than an adjudication process between multiple expert readings of the device outputs.

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

  • No, a MRMC comparative effectiveness study was not done. The study described focuses on the standalone performance of the device against a reference standard (auscultation), not on how human readers' performance improves with or without AI assistance. The device is an automatic blood pressure monitor, not an AI-assisted diagnostic tool that would typically involve human-in-the-loop performance measurement.

6. Standalone Performance Study

  • Yes, a standalone study was done. The clinical test described focuses on the device's ability to accurately measure blood pressure and pulse rate independently, comparing its readings directly against the "Standard auscultation method." This is a standalone performance evaluation of the algorithm/device.

7. Type of Ground Truth Used

  • Expert Consensus (Auscultation): The ground truth used was established by a "Standard auscultation method," which relies on a trained human observer using a stethoscope and sphygmomanometer as the reference standard for blood pressure measurement. This is a form of expert-derived ground truth.

8. Sample Size for the Training Set

  • The document does not provide information on the sample size used for the training set. Blood pressure monitors like this typically use algorithms developed and validated over many years, often using large, proprietary datasets, which are not usually detailed in 510(k) summaries unless they are novel AI/ML algorithms. The 510(k) summary focuses on the validation of the final device rather than the underlying algorithm development.

9. How Ground Truth for the Training Set Was Established

  • The document does not provide information on how the ground truth for the training set was established. Similar to point 8, this information is typically part of the device's research and development and not always explicitly detailed in a 510(k) summary for a well-established device type like a blood pressure monitor. The assumption would be that the training data, if any specific to the algorithm, would have been established through clinically validated reference methods, likely auscultation, similar to the test set ground truth.

§ 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).