Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K173123
    Device Name
    Pulse Oximeter
    Date Cleared
    2018-08-13

    (318 days)

    Product Code
    Regulation Number
    870.2700
    Reference & Predicate Devices
    Why did this record match?
    Reference Devices :

    K153021

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    Fingertip Pulse Oximeter C101H1 is a non-invasive device intended for spot checking of function of arterial hemoglobin (SpO2) and pulse rate (PR). This portable device is indicated for use in adult patients in hospitals.

    Device Description

    SpO2 is based on the absorption of pulse blood oxygen to red and infrared light by means of finger sensor and SpO2 measuring unit. The light-electronic transducer in finger sensor converts the pulse red and infrared light modulated by pulse blood oxygen into electrical signal is processed by hardware and software of the unit. The PLETH curve and numeral value of SpO2 will be obtained.

    The pulse oximeter, C101H1, is designed for spot checking of the pulse oxygen saturation and pulse rate for adults in a clinic environment. This medical device can be reused. Not for continuously monitoring. The device is not for life-supporting or life-sustaining, not for implant.

    The device is not provided sterile and is NOT a reprocessed single-use device.

    The device is a spot-check pulse oximeter and does not include alarms.

    The device does not support the measurement in the condition of low perfusion.

    The device is not intended for life-supporting or life-sustaining.

    The device is reusable and does not need sterilization.

    AI/ML Overview

    Here's an analysis of the provided information, describing the acceptance criteria and the study that proves the device meets them:

    1. Table of Acceptance Criteria and Reported Device Performance

    Performance MetricAcceptance Criteria (Predicate Device)Reported Device Performance (C101H1)
    SpO2 Measuring Range0%-100%0%-100%
    SpO2 Resolution1%1%
    SpO2 Accuracy (70-100%)±3%A_rms = 2.12% (within 70-100% range)
    SpO2 Accuracy (0-69%)UnspecifiedUnspecified
    PR Measuring Range30-235 BPM30-240 BPM
    PR Resolution1 bpm1 bpm
    PR Accuracy (30-99 bpm)±2 bpm±1 bpm or ±1%, whichever is greater
    PR Accuracy (100-235 bpm)±1%±1 bpm or ±1%, whichever is greater
    BiocompatibilityISO 10993-5 and ISO 10993-10Complies (Cytotoxicity, Sensitization, Irritation)
    Electrical SafetyIEC 60601-1, IEC 60601-1-11Complies (IEC 60601-1:2005/A1:2012, IEC 60601-1-11:2015, ISO 80601-2-61:2011)
    EMCIEC 60601-1-2Complies (IEC 60601-1-2:2014)
    Software Level of Concern(Implied "moderate" for predicate)Moderate

    Note: The acceptance criteria for the C101H1 are largely established by demonstrating substantial equivalence to the predicate device (Fingertip Pulse Oximeter A310/ K153021) and adherence to relevant international standards. The performance metrics listed for the predicate device serve as the de facto acceptance criteria for the C101H1 in terms of comparable specifications.

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

    • Sample Size for Clinical Test Set (SpO2 accuracy): 12 healthy adult volunteer subjects.
    • Data Provenance: The study was conducted on a volunteer population, implying a prospective study. The location is not explicitly stated, but given the manufacturer's location in Shenzhen, China (as indicated in the 510(k) summary), it is highly likely that the study was conducted there, or at least with subjects geographically accessible to the company or its clinical partners.

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

    • The document describes the ground truth for SpO2 accuracy as being established by arterial blood CO-Oximetry. This method itself is the "expert" or gold standard. There isn't information provided about individual experts, such as physicians or lab technicians, establishing the ground truth; rather, it relies on the accuracy of the CO-Oximetry device and its operation. It states "Arterial blood samples were drawn during simultaneous data collection from the test devices. The blood was immediately analyzed on reference CO-Oximetry providing functional SaO2 for the SpO2 accuracy comparison."

    4. Adjudication Method for the Test Set

    • Not applicable for this type of test. The ground truth (SaO2 from CO-Oximetry) is an objective measurement, not a subjective interpretation requiring adjudication among multiple experts. The device's reading is compared directly to this objective ground truth.

    5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, If So, What Was the Effect Size of How Much Human Readers Improve with AI vs Without AI Assistance

    • No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. This device is a Pulse Oximeter, which provides a direct physiological measurement (SpO2 and PR). It does not involve human readers interpreting images or data where AI assistance would be relevant.

    6. If a Standalone (i.e., Algorithm Only Without Human-in-the-Loop Performance) Was Done

    • Yes, the performance study for SpO2 accuracy is a standalone performance evaluation of the device's algorithm. The "C101H1 Pulse Oximeter" itself, without human interpretation influencing the measurement output, was evaluated against the gold standard CO-Oximetry. While humans operate the device, the core "performance" reported (A_rms) directly reflects the device's measurement accuracy.

    7. The Type of Ground Truth Used

    • The ground truth used for the SpO2 accuracy test was objective measurement from a gold-standard device: arterial blood CO-Oximetry, which provides functional SaO2.

    8. The Sample Size for the Training Set

    • The document does not specify a separate training set for the clinical performance evaluation. The clinical trial described focused on validation of the device's accuracy against a reference standard using 12 healthy volunteers. Pulse oximeters typically use fixed algorithms based on known light absorption properties of oxygenated and deoxygenated hemoglobin, rather than machine learning algorithms requiring a distinct training phase on clinical data. Performance testing (e.g., pulse rate accuracy, cleaning/disinfection) does not typically involve "training data" in the AI sense.

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

    • As no explicit training set is mentioned in the context of device performance in this document, this question is not applicable. The underlying physics and algorithms are generally developed based on a foundational understanding of spectroscopy and validated through engineering tests and subsequent clinical trials like the one described.
    Ask a Question

    Ask a specific question about this device

    Page 1 of 1