Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K050670
    Date Cleared
    2005-03-30

    (15 days)

    Product Code
    Regulation Number
    870.2920
    Reference & Predicate Devices
    Why did this record match?
    Device Name :

    SENSOR MOBILE SM 100 VITAPHONE 1001R REMOS

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

    Symptomatic disturbances of cardiac rhythm such as palpitations, fatigue, heart racing, fluttering, chest discomfort or pain.

    Device Description

    The telemedical system "sensor mobile" comprises the patient activated Tele-ECG device SM100 / vitaphone 100IR and the REMOS Receiving Software. The SM100 / vitaphone 100IR records and stores one-channel ECG episodes and transmits these data by means of a telephone or a mobile phone to a receiving station equipped with the REMOS Receiving Software for further processing. The Tele ECG device "sensor mobile" SM 100 / vitaphone 100IR, manufactured by TMS, is capable of recording, storing and transmitting up to three ECG episodes of 3C seconds each. The "sensor mobile" SM 100 is placed on the chest for post-event recording. The device is patient activated by pressing the record button. The 30-second ECG is stored in the device memory for later acoustic transmission via telephone or mobile phone in form of digital data (FSK) or via infrared (IrDA) and IrDA-enabled mobile phone to a telemedical central station equipped with the "sensor mobile" Receiving Software REMOS. The transmission is activated by pressing the send button. The device does not impair internal pacemakers and implantable cardioverters / defibrillators. The "sensor mobile" Receiving Software REMOS receives the digital ECG data via telephone line and stores it into a database. The receiving software is designed for automatic operation 24 hours a day. The ECG data will be converted to a human readable output in PDF file format with anonymized patient / user information.

    AI/ML Overview

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

    Acceptance Criteria and Device Performance

    The submission focuses on establishing substantial equivalence to a predicate device rather than defining specific performance-based acceptance criteria for diagnostic accuracy. Therefore, the "acceptance criteria" are interpreted as the critical competitive features where the new device ("sensor mobile") demonstrates either equivalence or improvement over the predicate device (PHD™ K963904 Heart Alert, Inc.), particularly in areas that reflect signal fidelity or patient convenience. The "reported device performance" refers to the capabilities of the "sensor mobile".

    Acceptance Criteria (inferred from comparison to predicate)"sensor mobile" Reported Device Performance
    Battery Life (convenience)5 Years
    CMRR (signal fidelity)80 dB
    Bandwidth (signal fidelity)0.5 - 40 Hz
    Resolution (signal fidelity)6 mV
    Memory Hold Time (safety/convenience)5 Years
    AD Accuracy (ECG output quality)12 Bit
    Pacemaker Spike Recognition (diagnostic capability)Yes
    Digital Transmission (convenience)IrDA
    ECG Output Format (archiving/processing)PDF file format, 5mm grid

    Study Details

    The provided document describes a clinical testing for the "sensor mobile" system.

    1. Sample size used for the test set and the data provenance:

      • Test Set Sample Size: 80 patients. One hundred ECG examples from these patients were transmitted and interpreted.
      • Data Provenance: The document does not explicitly state the country of origin but implies it was conducted by "TMS" (Telemedizinische Systeme GmbH), a German company. It is a prospective study as it describes "clinical testing" performed by TMS, transmitting and interpreting ECGs.
    2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

      • The document states that "98 percent of the received ECGs could be interpreted." It does not specify the number of experts, their qualifications, or how many were involved in establishing the ground truth or interpretation for the test set.
    3. Adjudication method for the test set:

      • The document does not describe any specific adjudication method (e.g., 2+1, 3+1). It only mentions that ECGs were "interpreted."
    4. 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 explicitly described. The "sensor mobile" is a Tele-ECG device for recording and transmitting, with the "REMOS Receiving Software" for further processing and converting to a human-readable PDF. The study focuses on the interpretability of the transmitted ECGs, not on the improvement of human readers with AI assistance.
    5. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:

      • No, a standalone algorithm-only performance study was not conducted or described. The system involves human interpretation of the transmitted ECGs. The software converts data to a human-readable format, implying human evaluation is part of the process.
    6. The type of ground truth used:

      • The ground truth appears to be based on expert interpretation of the received ECGs. The document states that "98 percent of the received ECGs could be interpreted" and mentions detection of basic rhythms, pacemaker function, and QRS complexes. This implies clinical experts were involved in verifying the physiological information present in the ECGs.
    7. The sample size for the training set:

      • The document does not specify a training set sample size. This submission is for a medical device (Tele-ECG system) which involves a hardware device and receiving software to transmit and present ECG data. It doesn't describe a machine-learning algorithm that would typically require a training set for model development.
    8. How the ground truth for the training set was established:

      • Since no training set is described for a machine-learning algorithm, the concept of establishing ground truth for a training set is not applicable here. The focus is on the successful transmission and interpretability of real patient ECGs in the clinical testing phase.
    Ask a Question

    Ask a specific question about this device

    Page 1 of 1