Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K190982

    Validate with FDA (Live)

    Date Cleared
    2020-05-29

    (410 days)

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

    Automatic Digital Blood Pressure Monitor is intended to measure the systolic and diastolic blood pressure as well as the pulse rate of adult person via non-invasive oscillometric technique in which an inflatable cuff is wrapped around the wrist or the upper arm. It can be used at medical facilities or at home. The intended wrist circumference is 12.520 cm and the intended arm circumference has several models: 2333 cm, 2535 cm, 2242 cm, 33~43 cm.

    Device Description

    Automatic Digital Blood Pressure Monitor is a non-invasive blood pressure measurement system intended to measure the diastolic and systolic blood pressures and pulse rate of an adult individual via non-invasive Oscillometric technique in which an inflatable cuff is wrapped around the wrist or the upper arm.It can be used at medical facilities or at home. The Automatic Digital Blood Pressure Monitor main units have the operating elements of ON/OFF knob, SET key which can be user-friendly controlled. Arm type Blood Pressure Monitor is equipped with inflatable cuff, while The wrist type Blood Pressure Monitor`s cuff is attached to the device body itself.

    AI/ML Overview

    This document is a 510(k) summary for an Automatic Digital Blood Pressure Monitor. It describes the device's characteristics, intended use, and comparison to predicate devices to demonstrate substantial equivalence.

    Here's a breakdown of the requested information based on the provided document:

    1. Table of Acceptance Criteria and Reported Device Performance

    The acceptance criteria for the blood pressure monitor's accuracy are based on ISO 81060-2:2013 Non-invasive sphygmomanometers - Part 2: Clinical validation of automated measurement type.

    Acceptance Criteria (from ISO 81060-2)Reported Device Performance
    Accuracy within acceptable scope specified in ISO 81060-2:2013"The results showed the accuracy of the blood pressure monitor is within acceptable scope specified in ISO 81060-2."
    Pressure accuracy: ±3 mmHgPressure: ±3 mmHg
    Pulse accuracy: ±5%Pulse: ±5%

    Note: The document explicitly states the device meets the ISO 81060-2 standard but doesn't provide granular numerical data beyond the +/- tolerance levels. It confirms the device's accuracy specifications align with the standard.

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

    • Sample Size (Test Set):
      • Arm Sphygmomanometer: 90 patients (divided by cuff size: 23-33cm: 49 males and 41 females; 25-35cm: 38 males and 52 females; 22-42cm: 48 males and 42 females; 33-43cm: 38 males and 52 females).
      • Wrist Sphygmomanometer: 90 patients (43 males and 47 females).
      • Total Patients: 180 (90 arm + 90 wrist).
    • Data Provenance: The document does not explicitly state the country of origin. It indicates the clinical study was conducted, and "All the subjects were volunteer to take part in the clinical study." The study is described as a clinical investigation, implying a prospective study.

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

    The document does not specify the number of experts or their qualifications. However, for blood pressure measurements, the "ground truth" is typically established by trained medical professionals (e.g., physicians, nurses) using a reference device.

    4. Adjudication Method for the Test Set

    The document states: "The manual Mercury Sphygmomanometer was used as a reference device." This implies a comparison method where the device's readings are compared against the gold standard (manual mercury sphygmomanometer readings). It does not describe an adjudication method with multiple readers deciding on a "ground truth" where there might be inter-reader variability, as would be common in diagnostic imaging studies. The reference device is the ground truth.

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

    No, an MRMC comparative effectiveness study was not done. This type of study is typically performed for AI-assisted diagnostic devices to assess how AI impacts human reader performance. This device is a direct measurement device (automatic blood pressure monitor), not an AI-enabled diagnostic tool in the sense that an algorithm assists human interpretation of images. The study focused on the device's accuracy compared to a reference standard.

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

    Yes, in a sense, the primary test conducted was a "standalone" performance test of the device. The clinical study evaluated the direct output of the Automatic Digital Blood Pressure Monitor against a manual mercury sphygmomanometer, without human interpretation of the device's output being a variable. The device itself performs the measurement and provides readings.

    7. The Type of Ground Truth Used

    The ground truth used was measurements from a manual Mercury Sphygmomanometer. This is considered a highly reliable and commonly accepted gold standard for blood pressure measurement.

    8. The Sample Size for the Training Set

    The document does not provide information about a separate "training set" or its sample size. This is typical for medical devices that perform a direct physical measurement (like a blood pressure monitor) and are validated against a known standard. The "training" for such a device is typically part of its engineering and algorithm development, not a discrete data set for a machine learning model submitted for regulatory review in the same way as AI software.

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

    As no specific training set is mentioned in the regulatory document (likely because the device's function is a direct measurement and not an AI/ML model requiring a separate training data ground truth for submission), this information is not provided. The device's underlying algorithm is likely developed and refined through engineering and calibration processes based on known physiological principles of oscillometric measurement, rather than learning from a 'labeled training dataset' in the context of AI.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1