Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K202776
    Date Cleared
    2021-03-01

    (161 days)

    Product Code
    Regulation Number
    870.2700
    Reference & Predicate Devices
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The Fingertip pulse oximeter is a handheld non-invasive device intended for spot-checking of oxygen saturation of arterial hemoglobin (SpO2) and Pulse Rate of adult, adolescent and child patients in hospital-type facilities, and homecare.

    Device Description

    Fingertip pulse oximeter, LOX100A, LOX100B, LOX100C, LOX100D, mainly include of signal acquisition module, signal processing module, prompt module, detector, and emitter LED, display and user interface module, power supply module, the device is used to measure the patient's blood oxygen saturation (SpO2) and pulse rate (PR). The device is mainly composed of main board PCB, lamp panel PCB, sensor, OLED screen, button, silicone gel pad and enclosure.

    AI/ML Overview

    Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) summary for the Fingertip pulse oximeter:

    Device: Fingertip pulse oximeter (Model LOX100A, LOX100B, LOX100C, LOX100D) by Shenzhen LEPU Intelligent Medical Equipment Co., Ltd.

    1. Table of Acceptance Criteria and Reported Device Performance

    The provided document details the comparison of the subject device against a predicate device (K161560) and adherence to relevant standards. The "Acceptance Criteria" are implied by the requirements of these standards and the equivalence to the predicate, with "Reported Device Performance" reflecting the subject device's demonstrated capabilities.

    Acceptance Criterion (Implied by Standard/Predicate)Reported Device Performance (Subject Device)Pass/FailComment
    SpO2 Measurement Range: 70%~100%70%~100%PassSame as predicate.
    SpO2 Accuracy (70%~100%): <= +/-2%+/-2% (70%~100%)PassMeets ISO 80601-2-61 requirements.
    SpO2 Accuracy (70%~80%): <= +/-2%+/-2%PassMeets ISO 80601-2-61 requirements.
    SpO2 Accuracy (80%~90%): <= +/-2%+/-2%PassMeets ISO 80601-2-61 requirements.
    SpO2 Accuracy (90%~100%): <= +/-2%+/-2%PassMeets ISO 80601-2-61 requirements.
    SpO2 Accuracy (Low Perfusion): <= +/-2% (70-100%)+/-2% (70%~100%)PassVerified to meet ISO 80601-2-61; predicate does not mention.
    SpO2 Resolution: 1%1%PassSame as predicate.
    Pulse Rate Measurement Range: 30bpm~250bpm30bpm~250bpmPassSame as predicate.
    Pulse Rate Accuracy (30bpm~250bpm): +/-2bpm or +/-2% (whichever is larger)+/-2bpm or +/-2% (whichever is larger)PassConfirmed to be the same as predicate when detailed.
    Pulse Rate Accuracy (30-99bpm): +/-2bpm+/-2bpmPassSame as predicate.
    Pulse Rate Accuracy (100-250bpm): +/-2%+/-2%PassSame as predicate.
    Pulse Rate Accuracy (Low Perfusion): +/-2bpm or +/-2% (whichever is larger)+/-2bpm or +/-2% (whichever is larger)PassVerified to meet ISO 80601-2-61; predicate does not mention.
    Pulse Rate Resolution: 1bpm1bpmPassMeets ISO 80601-2-61 and actual use requirements.
    Biocompatibility: ISO 10993 Series RequirementsCytotoxicity, Skin Sensitization, Skin Irritation tests meet ISO 10993 requirementsPassTest results met requirements.
    Electrical Safety: IEC 60601-1 and IEC 60601-1-11Meets requirementsPassSame as predicate.
    Electromagnetic Compatibility: IEC 60601-1-2Meets requirementsPassSame as predicate.
    Software Level of Concern: ModerateModeratePassSame as predicate.
    Working Temperature: 5°C~40°C5°C~40°CPassSame as predicate.
    Storage/Transport Temperature: -20°C55°C (Subject device) vs. -25°C70°C (Predicate) vs ISO 80601-2-61Verified to meet ISO 80601-2-61 requirementsPassDifferent from predicate but verified to meet standards.
    Relative Humidity: <=80% working, <=93% storage (Subject device) vs. 15%~93% operating, <=93% storage/transport (Predicate) vs ISO 80601-2-61Verified to meet ISO 80601-2-61 requirementsPassDifferent from predicate but verified to meet standards.
    Atmospheric Pressure: 70kPa-106kPa70kPa-106kPaPassSame as predicate.
    Clinical Study for SpO2 Accuracy: Adherence to Annex EE of ISO 80601-2-61SpO2 accuracy of 1.52% Arms during steady state conditions over 70-100% rangePassMeets requirements.
    Cleaning and Disinfection Validation: Compliance with FDA Guidance for Reprocessing Medical DevicesValidated cleaning and disinfection process, compliant with FDA guidancePassConfirmed.

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

    • Test Set Sample Size: 12 healthy adult volunteer subjects.
    • Data Provenance: Retrospective (implied, as the study results are presented as completed data for review), conducted on healthy adult volunteers. The document does not explicitly state the country of origin, but given the company's location (Shenzhen, China) and common regulatory practices, it's likely the study was conducted there or in a region with compatible regulatory/ethical standards.

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

    The document states that arterial blood samples were analyzed on a "reference co-oximeter" to provide the functional SaO2 for comparison. This implies an objective, instrumental ground truth, not one established by human experts. Therefore, the "number of experts" for ground truth establishment is not applicable in this context. The co-oximeter itself serves as the gold standard.

    4. Adjudication Method for the Test Set

    Not applicable. The ground truth for SpO2 accuracy was established objectively by a co-oximeter, not through human expert consensus requiring adjudication.

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

    No. An MRMC study was not described. The study focused on the device's standalone accuracy against a measured physiological ground truth (co-oximetry), not on evaluating human reader performance with or without AI assistance. This device (a pulse oximeter) is a direct measurement device, not an AI diagnostic aid that assists human interpretation.

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

    Yes. The clinical study described is a standalone performance test of the device, where the Fingertip pulse oximeter's SpO2 readings were directly compared to arterial blood co-oximeter readings. There's no human "in the loop" for interpreting the device's output influencing the accuracy validation.

    7. The Type of Ground Truth Used

    The ground truth used for SpO2 accuracy was outcomes data in the form of arterial blood co-oximetry readings (functional SaO2). This is considered a highly objective, gold-standard method for determining true arterial oxygen saturation.

    8. The Sample Size for the Training Set

    The document does not specify a separate "training set" sample size. For a pulse oximeter, the core measurement principle is based on pre-established physiological principles (Lambert-Beer law, absorption characteristics of oxygenated/deoxygenated hemoglobin), not on machine learning models that require distinct training and test sets in the same way. The device's calibration and algorithm development would have utilized extensive physiological data, but this is distinct from a "training set" for a new AI algorithm.

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

    Given that this is a pulse oximeter and not an AI-driven diagnostic image analysis tool, the concept of a "training set" with ground truth in the typical machine learning sense is not applicable here. The device's underlying algorithm relies on the physical properties of light absorption by blood components, which were established through fundamental scientific research over many decades. The device is calibrated and validated against established standards (like ISO 80601-2-61) and objective physiological measurements (like CO-oximetry) rather than "training" an AI model.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1