K Number
K240832
Date Cleared
2024-06-07

(73 days)

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

This Blood Pressure Monitor is a digital monitor intended for use in measuring blood pressure and pulse rate with arm circumference ranging from 22cm to 32cm (about 8¾ -12½´) or 22cm to 42cm (about 834"-161/2"). It is intended for adult indoor use only.

Device Description

Blood Pressure Monitor BBZ32-AA01 is designed to measure systolic pressure, diastolic pressure and pulse rate of adult by a non-invasive technique, with an inflatable cuff wrapped around the upper arm. The method to define systolic and diastolic pressure is similar to auscultatory method, though it uses an electronic pressure sensor rather than a stethoscope and mercury manometer. The sensor converts tiny alternations of cuff pressure into electrical signals. Based on analysis of these signals, the systolic and diastolic blood pressure is defined, and the pulse rate is calculated. This is an extensively used technique applied in blood pressure monitors, also known as "oscillometric method". The main components of the Blood Pressure Monitor include main unit and cuff. For the outer housing of the main unit, it's made of HIPS material. As for accompanying cuffs, two types of cuffs have been clinically validated to be matched with the device, suitable for adults with arm circumference from 22cm~42cm. The cuff is consisted of fabric and an inflatable bladder inside. For critical electronic components, there is PCB, thermistor, pressure pump, motor, release valve and pressure sensor. The device also enjoys a function of detecting irregular pulse rate. When measurements were performed, the monitor will record all pulse intervals and calculate the average. If two or more pulse intervals were recorded, and the difference between each interval and the average is larger than ±25% of the average; or if four or more pulse intervals were recorded, and the difference between each interval and the average is larger than ±15% of the average, the irregular pulse symbol will be displayed along with measurement results. An embedded Bluetooth wireless connection module in the device allows it to connect with matching receiving ends. When a measurement is done, the results will be displayed on LCD, and the measured data will be transferred to the APP via Bluetooth.

AI/ML Overview

The Guangdong Transtek Medical Electronics Co., Ltd. Blood Pressure Monitor (BBZ32-AA01) underwent a clinical study to demonstrate its performance against established acceptance criteria.

1. Table of Acceptance Criteria and Reported Device Performance

The device's performance was evaluated against the criteria outlined in ISO 81060-2:2018/Amd.1:2020 for non-invasive sphygmomanometers. The document does not explicitly present these as a table of "acceptance criteria," but rather as two validation criteria (Criterion 1 and Criterion 2) that the device must fulfill. The reported device performance is indicated as having fulfilled both these criteria.

CriterionAcceptance Criteria (Implicit from ISO 81060-2:2018/Amd.1:2020)Reported Device Performance (Mean Difference +/- Standard Deviation)
Impulse Test (e.g., Blood Pressure Accuracy)(Criterion 1) Mean difference and standard deviation of differences between reference blood pressure and device readingsSystolic BP: 0.17 ± 2.57 mmHg; Diastolic BP: 0.79 ± 2.09 mmHg
Impulse Test (e.g., Blood Pressure Accuracy)(Criterion 2) Mean difference and standard deviation of differences between reference blood pressure and device readingsSystolic BP: 0.17 ± 1.99 mmHg; Diastolic BP: 0.79 ± 1.68 mmHg

Note: The exact numerical thresholds for acceptance for Criterion 1 and 2 from ISO 81060-2:2018/Amd.1:2020 are not explicitly stated in this document but are implied to have been met by the reported performance.

2. Sample Size and Data Provenance

  • Test Set Sample Size: 86 qualified subjects.
  • Data Provenance: The document does not explicitly state the country of origin but mentions the manufacturer is "Guangdong Transtek Medical Electronics Co., Ltd." in China. It is a prospective clinical study, as indicated by "The clinical study was performed on the device..."

3. Number of Experts and Qualifications

The document does not provide information on the number of experts used to establish the ground truth or their specific qualifications (e.g., radiologist with 10 years of experience). It only refers to "reference BPs" for comparison.

4. Adjudication Method

The document does not specify an adjudication method like 2+1 or 3+1 for establishing ground truth. The "reference BPs" suggest a gold standard measurement was used, but the process for ensuring its accuracy is not detailed.

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

No multi-reader multi-case (MRMC) comparative effectiveness study was done to assess human readers' improvement with or without AI assistance. This device is a standalone blood pressure monitor, not an AI-assisted diagnostic tool.

6. Standalone Performance

Yes, a standalone performance study was done. The clinical study described evaluates the algorithmic (device) performance in measuring blood pressure and pulse rate without human-in-the-loop assistance for interpretation or adjudication of results.

7. Type of Ground Truth Used

The ground truth used was "reference BPs." This implies that the device readings were compared against highly accurate and established blood pressure measurements, likely obtained by a validated manual method (e.g., auscultatory method by trained professionals) or another highly accurate reference device.

8. Sample Size for the Training Set

The document does not mention a training set sample size. This suggests the blood pressure monitor is likely based on an established oscillometric algorithm rather than a machine learning model that requires a dedicated training set.

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

Since no training set is mentioned (implying a rule-based or conventional algorithm rather than a machine learning model), the method for establishing ground truth for a training set is not applicable or detailed in this document.

§ 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).