Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K201302
    Device Name
    LiveOne
    Date Cleared
    2022-05-04

    (719 days)

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

    The LiveOne is intended to be used in patients who have a need for a noninvasive blood pressure and hemodynamic monitor.

    The LiveOne is intended to be used on subjects ≥ 27 years old and who have a palpable radial pulse. Software is used to provide data to qualified medical professionals for the purpose of assessing the patient's cardiac health via blood pressure readings in clinic setting by health care professional. LiveOne is intended only for measurement and display; it makes no diagnosis.

    Device Description

    The LiveOne is a non-invasive blood pressure monitor that utilizes a single patient use non-invasive pressure sensor placed on the wrist over the radial artery, and an electronic interface module. The device uses proprietary algorithms to analyze the radial artery pressure and display diastolic, systolic, and pulse rate and a pressure waveform. The device allows the healthcare provider to monitor blood pressure (based on visual waveform) in a clinical setting.

    AI/ML Overview

    Here's a breakdown of the acceptance criteria and the studies conducted for the LiveOne LM1P device, based on the provided text:

    1. Acceptance Criteria and Reported Device Performance

    ParameterAcceptance Criteria (ISO 81060-2:2018 Standard)Reported Performance (ICU Study)Reported Performance (General Population Study)
    Systolic BPMean bias and standard deviation within ISO 81060-2:2018 limitsMean bias: 0.7 ± 6.6 mmHgMean bias: -1.3 ± 7.2 mmHg
    Diastolic BPMean bias and standard deviation within ISO 81060-2:2018 limitsMean bias: 2.0 ± 5.5 mmHgMean bias: -0.4 ± 5.7 mmHg
    Heart RateRelative distance within ISO 81060-2:2018 limitsRelative distance: 2.9Relative distance: 1.36

    Note: The document explicitly states that the reported results are "within the acceptance criteria for the accuracy of blood pressure monitors" and "comply with the ISO standard requirements." However, the exact numerical acceptance criteria from ISO 81060-2:2018 are not detailed in the provided text. Typically, for ISO 81060-2, the mean difference (bias) for both systolic and diastolic measurements should be within ±5 mmHg, with a standard deviation no greater than 8 mmHg.

    2. Sample Sizes and Data Provenance

    ICU Accuracy Study:

    • Sample Size (Test Set): 26 subjects
    • Data Provenance: Not explicitly stated as retrospective or prospective, but described as a "multi-center, non-randomized, single arm study," which typically implies prospective data collection for a validation study. The country of origin is not specified.

    General Population Accuracy Study:

    • Sample Size (Test Set): 8 subjects
    • Data Provenance: Not explicitly stated as retrospective or prospective, but described as a "single-center, non-randomized, single arm study," typically implying prospective data collection. The country of origin is not specified. The subjects are described as "healthy subjects."

    3. Number of Experts and Qualifications for Ground Truth

    The document does not mention the use of experts to establish ground truth in the traditional sense of consensus reading for image-based diagnostics. For blood pressure measurement devices, the ground truth is typically established by a reference standard measurement.

    4. Adjudication Method

    Not applicable, as the studies are focused on direct comparison to a reference standard (arterial line) rather than expert adjudication of qualitative findings.

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

    No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not performed. This type of study is more common for diagnostic imaging AI algorithms where human readers interpret results, and the AI's impact on their performance is measured. The LiveOne LM1P is a non-invasive blood pressure monitor, not an AI for image interpretation.

    6. Standalone (Algorithm Only) Performance

    Yes, the studies conducted (ICU accuracy study and General population accuracy study) assessed the standalone performance of the LiveOne LM1P device. The device's measurements (systolic BP, diastolic BP, HR) were directly compared against the arterial line (A-line) measurements, which served as the gold standard. There is no mention of a human-in-the-loop interaction for the accuracy assessment itself, only that "Software is used to provide data to qualified medical professionals for the purpose of assessing the patient's cardiac health."

    7. Type of Ground Truth Used

    The ground truth used in both clinical studies was arterial line (A-line) measurements. This is a direct, invasive, and generally accepted gold standard for continuous blood pressure monitoring.

    8. Sample Size for the Training Set

    The document does not specify the sample size used for the training set of the LiveOne LM1P's proprietary algorithms. The clinical studies described are for validation/testing of the device's accuracy against a gold standard.

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

    The document does not describe how the ground truth for the training set was established. It only discusses the validation studies against arterial line measurements. Given that the device uses "proprietary algorithms to analyze the radial artery pressure," it is highly probable that some form of data (likely also compared to arterial line or other reference methods) was used for algorithm development and training, but this is not detailed in the provided text.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1