K Number
K193627
Date Cleared
2020-07-12

(199 days)

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

Automatic Upper Arm Blood Pressure Monitor is intended for use by medical professionals or at home to monitor and display diastolic, systolic blood pressure and pulse rate on adult each time, with an air cuff buckled around one's arm according to the instruction in the user's guide manual.

Device Description

Automatic Upper Arm Blood Pressure Monitor is designed to measure the systolic, diastolic and pulse rate of an individual by using a non-invasive technique which an inflatable cuff is wrapped around upper arm. Our method to define systolic and diastolic pressures is similar to the auscultatory method but using an electronic capacitive pressure sensor rather than stethoscope and mercury manometer. The sensor converts tiny alteration in cuff pressure to electrical signals; by analyzing those signals to define the systolic, diastolic and calculating pulse rate is a well-known technique in the market so called "oscillometric method". The device also has low voltage indication, which will be triggered when the battery is low.

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:

Device: Automatic Upper Arm Blood Pressure Monitor (Models: BA-801X, BA-802X, BA-803X, BA-805X, BA-806X, BA-811X, BA-812X, BA-813X, BA-821X, BA-822X, BA-823X, BA-826X, BA-818, BA-819)

1. Table of Acceptance Criteria and Reported Device Performance:

Acceptance Criteria (Standard from AAMI / ANSI / ISO 81060-2)Reported Device Performance
Pressure Measurement Accuracy: ± 3 mmHgPressure: ± 3mmHg
Pulse Measurement Accuracy: ± 5%Pulse: ±5%

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

The provided document states: "The whole product and manufacturing used for the Automatic Upper Arm Blood Pressure Monitor are identical to those of the predicate device, which were demonstrated to conform with the following standards: ... AAMI / ANSI / ISO 81060-2 Second Edition, Non-Invasive Sphygmomanometers Part 2: Clinical Validation of Automated Measurement Type. (Cardiovascular)."

However, the document does not directly provide the sample size or data provenance (e.g., country of origin, retrospective/prospective) for the clinical validation of the subject device itself. Instead, it refers to prior validation of the predicate devices. To get this information, one would need to consult the 510(k) submissions for predicate devices K153552 and K172895, as the subject device is deemed "substantially equivalent" to them based on these prior validations.

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

The document refers to the AAMI / ANSI / ISO 81060-2 standard for clinical validation. This standard typically involves trained observers (often medical professionals) to perform auscultatory blood pressure measurements, which serve as the ground truth.

However, the specific number of experts and their qualifications for the predicate device studies (which this device relies upon) are not explicitly stated in this 510(k) summary. The standard implicitly dictates the methodology for such experts to ensure accuracy.

4. Adjudication Method for the Test Set:

The document refers to the AAMI / ANSI / ISO 81060-2 standard. This standard specifies a rigorous methodology for obtaining reference blood pressure measurements, often including:

  • Utilizing trained observers.
  • Taking multiple consecutive measurements.
  • Calculating the average of these measurements as the reference.
  • Potentially discarding outlying measurements.

However, the specific adjudication method (e.g., 2+1, 3+1, none) used in the predicate device studies is not detailed in this 510(k) summary. One would need to refer to the original validation reports for the predicate devices.

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:

This device is an Automatic Upper Arm Blood Pressure Monitor and does not involve AI assistance for human readers. Therefore, an MRMC comparative effectiveness study involving AI assistance is not applicable and was not performed. The device takes direct measurements.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done:

Yes, the device is an "Automatic Upper Arm Blood Pressure Monitor," indicating it operates in a standalone manner to measure blood pressure and pulse rate without continuous human interpretation or input during the measurement process. The clinical validation, by referring to AAMI / ANSI / ISO 81060-2, assesses the device's accuracy in autonomously taking these measurements against a reference standard.

7. The Type of Ground Truth Used:

The ground truth for blood pressure measurement, as stipulated by standards like AAMI / ANSI / ISO 81060-2, is typically established by trained observers using a validated reference method, such as auscultatory blood pressure measurement performed by healthcare professionals. This involves a mercury sphygmomanometer or an equivalent calibrated non-invasive device, with readings taken by at least two independent observers.

8. The Sample Size for the Training Set:

The document states: "All hardware and software of the subject device are based on that of the predicate device K153552 and K172895 since no new testing is presented in the submission." This implies that no new training set was explicitly created or used for the subject device beyond what was used for the predicate devices.

The text does not provide details on the training set or its size for the development of the oscillometric algorithm in either the subject device or its predicates. Blood pressure monitors using the oscillometric method are typically developed and calibrated by engineering teams using various physiological data and signal processing techniques. The "training" here refers more to the engineering development and calibration process rather than a machine learning training set with annotated data.

9. How the Ground Truth for the Training Set was Established:

As mentioned above, the development of an oscillometric blood pressure monitor involves engineering development and calibration. The "ground truth" during this development phase would typically involve:

  • Reference blood pressure measurements: Using highly accurate, invasive (e.g., intra-arterial) or highly precise non-invasive (e.g., mercury sphygmomanometer with trained observers) methods during the development and calibration of the oscillometric algorithm.
  • Physiological models and simulations: To refine the algorithm's ability to interpret oscillometric waveforms.
  • Extensive testing against a range of patient populations: To ensure the algorithm performs robustly across different physiological conditions.

However, specific details on the ground truth establishment for the training set (developmental calibration) are not provided in this 510(k) summary. Such details would typically be part of the manufacturer's internal design and development files. The 510(k) summary primarily focuses on the clinical validation against established standards for regulatory approval.

§ 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).