Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K223873
    Manufacturer
    Date Cleared
    2023-09-29

    (280 days)

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

    The Boppli Infant Blood Pressure Monitor is indicated for use by medically trained personnel in clinical settings, such as the NICU, PICU, CVICU, and emergency or operating room, to continuously monitor diastolic, systolic, and mean arterial blood pressures of neonates and infants, under 5 kilograms in weight, who have a palpable pulse.

    Device Description

    The Boppli Infant Blood Pressure Monitor, or Boppli Device, is a non-invasive blood pressure monitor that utilizes a reusable mobile tablet electronic interface (Boppli Bedside) with a single-use non-invasive sensor band (Boppli Band) that is placed on the arm or leg of an infant over a palpable pulse point, such as the radial or dorsalis pedis artery, respectively. The device uses proprietary algorithms to derive the arterial pressure and display systolic (SBP) and diastolic blood pressure (DBP), mean arterial pressure (MAP), pulse rate (PR), and a continuous pressure waveform. The device allows healthcare providers to monitor a neonate's blood pressure in clinical settings.

    AI/ML Overview

    Here's a breakdown of the acceptance criteria and the study proving the Boppli Infant Blood Pressure Monitor meets them, based on the provided text:

    1. Table of Acceptance Criteria and Reported Device Performance

    ParameterAcceptance CriteriaReported Device Performance (Method A: ISO 81060-2)Reported Device Performance (Method B: ANSI/AAMI SP10)
    Primary Endpoint GoalMAE <= +/- 5 mmHg and SD <= 8 mmHg for SBP, DBP, and MAPMAE <= +/- 5 mmHg and SD <= 8 mmHg for SBP, DBP, and MAP
    MAP AccuracyMAE <= +/- 5 mmHg1.0 mmHg0.7 mmHg
    MAP PrecisionSD <= 8 mmHg7.5 mmHg5.3 mmHg
    SBP AccuracyMAE <= +/- 5 mmHg-0.8 mmHg-0.8 mmHg
    SBP PrecisionSD <= 8 mmHg10.5 mmHg (Missed)7.7 mmHg
    DBP AccuracyMAE <= +/- 5 mmHg2.1 mmHg1.4 mmHg
    DBP PrecisionSD <= 8 mmHg6.6 mmHg4.7 mmHg
    Pulse Rate ErrorWithin 5% of actual bpmMet the accuracy requirementMet the accuracy requirement

    Note on SBP Performance: The device "missed the primary endpoint for the systolic blood pressure" with a standard deviation (SD) of 10.5 mmHg for Method A. However, for Method B, the SBP SD was 7.7 mmHg, which meets the criteria. The document states that "Given the intended use population, the high-acuity environment, and conjunction with SpO2 monitoring, the higher standard deviation was determined to be acceptable."

    2. Sample Size and Data Provenance

    • Test Set Sample Size: 79 subjects (neonates and infants under 5 kg in weight who required invasive blood pressure monitoring). The clinical study also collected 735 data points for Method A and 741 data points for the Band Error Calculation.
    • Data Provenance: The study was described as a "prospective, multi-center clinical study." The country of origin of the data is not explicitly stated, but clinical studies for FDA submissions are typically conducted in the US or in countries with comparable regulatory and medical standards, using a diverse patient population if possible. Given the focus on neonates and infants, it's likely specialized clinical settings were utilized.

    3. Number of Experts and Qualifications for Ground Truth

    The document does not explicitly state the number of experts used to establish ground truth or their qualifications. The ground truth method used was a comparison against an "invasive arterial reference" (intra-arterial line, IAL), which is considered the gold standard for blood pressure measurement. The interpretation of this data would typically be performed by trained medical personnel, but the specific number and qualifications of individuals performing the IAL measurements or data review are not detailed as "experts establishing ground truth."

    4. Adjudication Method for the Test Set

    The document does not describe an adjudication method for the test set. Given that the ground truth was an objective measurement from an invasive arterial line, human adjudication of "ground truth" (e.g., as in image classification) would not be applicable here. The comparison was directly between device measurements and IAL measurements.

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

    No. This was a direct comparison of a device's measurements against an industry-standard invasive measurement (IAL), not a study involving human readers or AI assistance in interpretation/diagnosis. Therefore, an MRMC study and effect size for human improvement are not applicable.

    6. Standalone (Algorithm Only) Performance

    Yes, the study primarily assessed the standalone performance of the Boppli Infant Blood Pressure Monitor. The device uses "proprietary algorithms to derive the arterial pressure," and the study directly compared the outputs of these algorithms (via the device measurement) to the invasive arterial reference. While "medically trained personnel" are indicated for its use, the accuracy assessment itself is of the device's measurements.

    7. Type of Ground Truth Used

    The type of ground truth used was outcomes data / objective measurement: comparison against an "invasive arterial reference" (intra-arterial line, IAL). This is considered the clinical gold standard for continuous blood pressure monitoring.

    8. Sample Size for the Training Set

    The document does not provide information on the sample size used for the training set of the device's algorithms. The text focuses only on the clinical validation (test set).

    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. It only mentions that the device uses "proprietary algorithms." Typically, ground truth for training medical device algorithms often involves large datasets with concurrently acquired reference standard measurements (e.g., IAL data, as used in this clinical study, or other validated methods).

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1