Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K233864
    Date Cleared
    2024-05-07

    (153 days)

    Product Code
    Regulation Number
    870.2800
    Reference & Predicate Devices
    Why did this record match?
    Device Name :

    ASSURE Wearable ECG

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

    The ASSURE Wearable ECG is indicated for adult patients who have been prescribed this device by a medical professional, who were previously prescribed the ASSURE WCD system, and who may be asymptomatic or who may suffer from transient symptoms such as palpitations, shortness of breath, dizziness, light-headedness, presyncope, syncope, fatigue, or anxiety. The signal acquired by the ASSURE Wearable ECG is not intended and should not be used for automated or semi-automated analysis. The device does not deliver any therapy, administer any drugs, provide interpretive or diagnostic statements or provide for any life support.

    The ASSURE Wearable ECG is contraindicated for use in patients with an active implantable pacemaker or defibrillator.

    Device Description

    The ASSURE Wearable ECG is a reusable, ambulatory electrocardiography-based, cardiac- and physiologicmonitoring, medical-electrical system whose intended purpose is to inform clinical management of options for diagnosing, monitoring and/or mitigating cardiac conditions after patient's improvement following ASSURE® Wearable Cardioverter Defibrillator (WCD) prescriptive use. The system utilizes the same five-electrode SensorFit™ Garment worn previously with the WCD prescription. The system continuously records ECG data and upon detection, it identifies and records episodes as high and low heart rate, as well as patient-triggered events. The system utilizes the same algorithm detection and episode reporting software marketed in the ASSURE WCD with high (Tachy) and low (Brady) capture for later transmission to the medical professional for interpretation. The system captures and stores ECG episodes, and non-ECG patient activity and wear information to be displayed and reported in counters and trends. Recorded events include ECG waveforms and reports identifying high and low heart rates, as well as patient-triggered events. The system uses a 3axis accelerometer to monitor non-ECG patient activity (steps and wear time).

    The ASSURE Wearable ECG event reports do not contain diagnostic interpretation. The reported events are provided for review by the prescriber to assist in diagnosis of the recently transitioned WCD patient and to assess care options based on the healthcare professional's judgment and experience.

    The ASSURE Wearable Cardiac ECG is a prescription use device. The ASSURE Wearable ECG is intended for use by a patient during their normal daily activities primarily in the home or community setting, but also hospitals, medical clinics, healthcare facilities and transport. The device is non-invasive, and intended to be used on one patient at a time.

    The Wearable Cardiac ECG System is comprised of the following reusable patient-worn components:

    • Monitor Cable Assembly
    • Hub
    • Alert Button
    • Battery Pack
    • SensorFit™ Garment
    • Charger
    AI/ML Overview

    The Kestra Medical Technologies, Inc. ASSURE Wearable ECG (K233864) does not appear to have an artificial intelligence/machine learning component that offers diagnostic interpretation. The provided text states, "The signal acquired by the ASSURE Wearable ECG is not intended and should not be used for automated or semi-automated analysis. The device does not deliver any therapy, administer any drugs, provide interpretive or diagnostic statements, or provide for any life support." and "The ASSURE Wearable ECG event reports do not contain diagnostic interpretation." Therefore, the typical acceptance criteria and study designs for AI/ML devices might not be applicable in the usual sense.

    However, based on the information provided, here's a breakdown regarding the device's technical performance and regulatory compliance, reinterpreting "acceptance criteria" through the lens of general medical device performance and safety standards:

    1. Table of Acceptance Criteria and Reported Device Performance

    Since the device explicitly states it does not perform automated or semi-automated analysis or provide diagnostic statements, traditional AI/ML performance metrics like sensitivity, specificity, or AUC against a ground truth would not be applicable here. Instead, the acceptance criteria are focused on the device's ability to reliably act as a continuous ECG monitor, data recorder, and transmitter, and its compliance with relevant safety and performance standards.

    Acceptance Criteria CategorySpecific Criteria/StandardReported Device Performance
    Basic Safety & Essential PerformanceIEC 60601-1:2005+A1:2012+A2:2020 (General requirements for basic safety and essential performance)Passed successfully
    Electromagnetic Compatibility (EMC)IEC 60601-1-2:2014+A1:2020 (EMC - Requirements and tests)Passed successfully
    Home Healthcare EnvironmentIEC 60601-1-11:2015+A1:2021 (Requirements for medical electrical equipment and medical electrical systems used in the home healthcare environment)Passed successfully
    Ambulatory ECG Systems (Specific Performance)IEC 60601-2-47:2015 (Particular requirements for the basic safety and essential performance of ambulatory electrocardiographic systems)Noted that it intentionally does not meet all performance clauses associated with diagnostic ECG, due to its low-risk patient monitoring design and use of proprietary algorithm detection software developed for a WCD (which is not diagnostic in this context). The implication is that the relevant clauses for its intended function as a monitoring and recording device were met.
    BiocompatibilityISO 10993-1:2018 (Biological evaluation of medical devices Part 1: Evaluation and testing within a risk management process)Passed successfully
    Battery SafetyUL 2054:2004(R2011) (Standard for Household and Commercial Batteries, 2nd Edition)Passed successfully
    Lithium Battery SafetyIEC 62133-2:2017 (Safety requirements for portable sealed secondary cells, and for batteries made from them, for use in portable applications, Part 2: Lithium systems)Passed successfully
    Electromagnetic Immunity (RFID)AIM 7351731:2017 (Medical Electrical Equipment and System Electromagnetic Immunity Test for Exposure to Radio Frequency Identification Readers - An AIM Standard)Passed successfully
    ECG Monitoring & Data HandlingContinuously monitor ECG signal, store ECG event data (high/low heart rate, patient-triggered events), and transmit recorded data to a Kestra display server for clinician review.Bench test results verify the system's ability to perform these functions.

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

    The provided text does not explicitly state the sample size for any clinical or technical test sets involving patient data. The performance section focuses on bench testing against recognized standards. There is no mention of a separate "test set" in the context of diagnostic accuracy from patient data, as the device doesn't provide diagnostic interpretation.

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

    This information is not applicable as the device explicitly states it does not perform automated or semi-automated analysis or provide diagnostic statements. The "ground truth" here is primarily established by adherence to engineering and safety standards, and functional verification through bench testing. Clinical interpretation of the recorded ECG data is left to medical professionals.

    4. Adjudication Method for the Test Set

    This information is not applicable given the device's stated function and the type of performance testing described (bench testing against engineering standards, not diagnostic accuracy studies requiring expert adjudication).

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

    No, a MRMC comparative effectiveness study was not conducted or described. The device's function is to record ECG data, not to interpret it or assist human readers in interpretation. There is no AI component in this device that provides diagnostic assistance to a human reader.

    6. Standalone Performance Study (Algorithm Only Without Human-in-the-Loop Performance)

    While the device uses an "embedded arrhythmia detection algorithm" for auto-triggering events (high and low heart rates), the submission explicitly states that the signal "is not intended and should not be used for automated or semi-automated analysis" and "does not deliver...interpretive or diagnostic statements." Therefore, a standalone performance study in the sense of evaluating the diagnostic accuracy of an AI algorithm was not performed because the device does not claim diagnostic capabilities. Its "algorithm detection and episode reporting software" is for capture and storage of events for later clinician review, not for automated diagnosis.

    7. Type of Ground Truth Used

    For the functional aspects (ECG monitoring, event triggering, data storage/transmission), the "ground truth" would have been established through instrumentation calibration, controlled simulated signals, and direct measurement during bench testing, verifying that the device accurately records ECG, identifies specified rate thresholds, and transfers data as intended. For the safety and performance standards (e.g., IEC 60601 series), the ground truth is adherence to the requirements and test methods outlined in those international standards.

    8. Sample Size for the Training Set

    This information is not applicable. The device, as described, does not utilize machine learning/AI for diagnostic purposes, and therefore would not have a "training set" in the context of developing a diagnostic algorithm. The "proprietary algorithm detection software" for event triggering, while an algorithm, is not presented as a machine learning model requiring a training set for diagnostic output.

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

    This information is not applicable. As no machine learning-based diagnostic algorithm is described, there is no "training set" or corresponding ground truth establishment process mentioned.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1