Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K191113
    Manufacturer
    Date Cleared
    2019-09-18

    (145 days)

    Product Code
    Regulation Number
    890.5850
    Reference & Predicate Devices
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use
    • Increasing local blood circulation
    • Edema reduction
    • Immediate post-surgical stimulation of the calf muscles to prevent venous thrombosis
    • Stimulation of the calf muscles to prevent venous thrombosis in non-surgical patients at risk for venous thromboembolism
    Device Description

    The geko™ T-2 and geko™ T-3 are single patient use, disposable (after 24 hours), fully integrated neuromuscular stimulator devices. Each model is composed of a constant current pulse generator with embedded software and a lithium-ion battery enclosed in a molded plastic casing, and a silver electrode with a hydrogel coating which provides a means of attachment of the device and electrical contact with the patient. Two buttons are used to control the On/Off function and increase or decrease the intensity level of the device output, which is achieved through changes in the delivered pulse width. The devices are applied so that the electrodes lie over the common peroneal nerve behind the knee. Stimulation of the common peroneal nerve causes contraction of the calf muscles through the direct activation of the motor neurons, resulting in increased blood flow. The stimulus intensity varies with the pulse width, which can be set a follows depending on the device model:

    • geko™ T-2: 7 levels ranging from 50 usec to 400 µsec @ 27 mA
    • geko™ T-3: 11 levels ranging from 35 to 280 µsec @ 27 mA, 280 to 400 µsec @ . 38 mA, and 400 to 560 µsec at 54 mA
      The asymmetric biphasic waveform results in a net charge of zero to the patient during each pulse cycle. The pulse rate is fixed at a frequency of 1 Hz for all device models and is used to isometrically stimulate the leg and foot muscles with a cadence and energy similar to that of walking.
      Both device models have the same principles of operation and the same indications for use. The choice of device model depends on the level of stimulation needed to achieve a visible contraction (twitch) of the patient's calf and dorsiflexion of the foot.
    AI/ML Overview

    The provided text describes a 510(k) premarket notification for the geko™ T-2 and geko™ T-3 Neuromuscular Stimulators, primarily focusing on adding a new indication for "Stimulation of the calf muscles to prevent venous thrombosis in non-surgical patients at risk for venous thromboembolism."

    Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the provided text:

    1. A table of acceptance criteria and the reported device performance

    The document does not explicitly state formal "acceptance criteria" with specific numerical targets. Instead, the performance is reported in terms of observed VTE rates for different prophylaxis methods. The primary comparison is non-inferiority to Intermittent Pneumatic Compression (IPC).

    Acceptance Criteria CategoryReported Device Performance (geko™ only group)Comparison Group (IPC only group)
    Effectiveness (VTE Prevention)0% incidence of VTE within 90 days (0/122 patients)2.4% incidence of VTE within 90 days (11/463 patients)
    Non-Inferiority to IPCThe geko™ was non-inferior to IPC within 0.5% (p=0.05) in preventing VTE.N/A
    Safety and TolerabilityNo adverse device-related events reported.81 subjects switched from IPC to geko™ due to non-compliance or dissatisfaction with IPC.

    2. Sample size used for the test set and the data provenance

    • Sample Size for Effectiveness Testing (geko™ only group): 122 patients
    • Total Patients in Study: 1000 patients (subdivided into various prophylaxis groups)
    • Data Provenance:
      • Country of Origin: Royal Stoke University Hospital (RSUH) in Stoke-On-Trent, England, UK.
      • Retrospective or Prospective: The study was conducted between November 1, 2016, and March 3, 2018, and patients were followed for 90 days post-discharge. This description indicates a prospective observational clinical study, where patients were entered and followed over time. However, the study is referred to as a "real-world clinical study" and not a "randomized, controlled clinical study."

    3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

    The document does not specify the number of experts used to establish the ground truth (diagnosis of VTE) or their qualifications. It states that patients were admitted with "a confirmed diagnosis of acute stroke" and were "assessed for VTE risk." VTE incidence was then assessed over 90 days. It is implied that standard hospital protocols and medical professionals (likely clinicians, radiologists for imaging verification) would have established these diagnoses, but specific details about expert reviewers for VTE adjudication are not provided.

    4. Adjudication method (e.g., 2+1, 3+1, none) for the test set

    The document does not specify any formal adjudication method (like 2+1 or 3+1) for confirming VTE diagnoses within the study. It refers to patients being "assessed for incidence of VTE," which usually implies standard clinical diagnostic practices.

    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

    The study described is a clinical effectiveness study of a medical device (neuromuscular stimulator), not a diagnostic imaging AI study. Therefore, an MRMC comparative effectiveness study involving human readers and AI assistance was not conducted and is not relevant to this submission. The device is a physical stimulator, not an AI diagnostic tool.

    6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

    This question is not applicable. The device is a physical neuromuscular stimulator and does not involve an algorithm working in "standalone" mode in the context of AI. Its performance is directly tied to its physical application to a patient.

    7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

    The ground truth for effectiveness was based on the incidence of Venous Thromboembolism (VTE) within a 90-day follow-up period. This is outcomes data (clinical endpoint). While not explicitly stated, the diagnosis of VTE would presumably have relied on standard clinical diagnostic methods, which often include imaging (e.g., ultrasound, venography) confirmed by medical professionals.

    8. The sample size for the training set

    This question is not applicable. The geko™ device is a physical medical device and does not involve a "training set" in the context of machine learning. The clinical study investigated its direct physiological effect.

    9. How the ground truth for the training set was established

    This question is not applicable, as there is no "training set" for this type of device.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1