Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K181863
    Device Name
    Elvie Pump
    Date Cleared
    2018-10-10

    (90 days)

    Product Code
    Regulation Number
    884.5160
    Reference & Predicate Devices
    Why did this record match?
    Device Name :

    Elvie Pump

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

    The Elvie Pump is a powered breast pump to be used by lactating women to express and collect milk from their breasts. The Elvie Pump is intended for a single user.

    Device Description

    The Elvie Pump is an electric breast pump system comprised of a single or double portable unit that integrates the pump body and milk collection bottle. It consists of a pump (motor unit) and includes a breast shield, bottle, seal, valve, spout and bra adjustor. All components (minus the pump) are reusable and may be manually cleaned. The kit components may be purchased separately and are available in different sizes and configurations.
    The Elvie Pump includes piezoelectric pump technology which generates negative pressure on the nipple to express milk, which is collected in the integrated milk collection bottle. It is designed to work in the user's nursing bra and has a rechargeable battery so it can be used hands-free without external power cords or milk collection tubes.
    The Elvie Pump is a battery-powered electro-mechanical device that contains software. It can be controlled through the physical interface on the device or through a mobile companion app, which also provides real-time milk monitoring, pump battery life, pumping time elapsed and pumping history information.
    All milk contacting components are constructed out of food grade materials that are compliant with 21 CFR 174-179.

    AI/ML Overview

    This document is a 510(k) summary for the Elvie Pump and does not describe acceptance criteria or a study that proves the device meets specific performance criteria through clinical trials or comparative effectiveness studies. Instead, it outlines the device's characteristics, its intended use, and its substantial equivalence to a predicate device based on non-clinical performance tests.

    Therefore, most of the requested information regarding acceptance criteria, study design, sample sizes, ground truth establishment, expert involvement, and MRMC studies cannot be extracted from the provided text.

    However, I can provide the information available from the document:

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

    The document does not explicitly present a table of acceptance criteria with corresponding performance results in a formal way for a clinical study comparing the Elvie Pump against specific performance metrics linked to patient outcomes or clinical effectiveness. Instead, it lists non-clinical performance tests that demonstrate the device meets its own specifications, which serve as internal "acceptance criteria" for engineering and safety.

    Non-Clinical Performance Test CategoryDevice Performance (as reported)
    BiocompatibilityPatient-contacting components are biocompatible (per ISO 10993-5, ISO 10993-10).
    Software ValidationValidated for a minor level of concern (per FDA guidance May 11, 2005); includes cybersecurity assessment and validation of milk measurement algorithm.
    Simulated Use Testing (Usability)Compliant with IEC 62366-1.
    Use Life TestingSupports proposed use life.
    Electrical SafetyCompliant with IEC 60601-1 and IEC 60601-1-11.
    Electromagnetic CompatibilityCompliant with IEC 60601-1-2.
    Cleaning ValidationReprocessing instructions in labeling are validated.
    Device Performance (Vacuum & Backflow)Meets specifications for vacuum performance and backflow.

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

    Not mentioned in the document. The listed tests are non-clinical (e.g., biocompatibility on materials, software validation, electrical safety), not clinical studies with human test sets.

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

    Not applicable. The document describes non-clinical engineering and safety tests, not studies requiring expert-established ground truths for clinical evaluation.

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

    Not applicable. This is not a clinical study.

    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 MRMC comparative effectiveness study was mentioned. The device is a powered breast pump, not an AI-assisted diagnostic or interpretive tool that would typically involve human readers.

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

    While the device includes software and has a "milk measurement algorithm," the document only states that the "milk measurement algorithm" was validated as part of software validation. It does not provide details of a standalone performance study for this specific algorithm or its performance metrics.

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

    For the non-clinical tests:

    • Biocompatibility: Standards (ISO 10993) and established laboratory protocols.
    • Software Validation: Requirements specifications, internal validation protocols, and FDA guidance.
    • Usability: IEC 62366-1 standard.
    • Electrical Safety/EMC: Relevant IEC 60601 series standards.
    • Cleaning Validation: Effectiveness against microbial load reduction/soil removal as per internal protocols.
    • Device Performance (Vacuum/Backflow): Engineering specifications for the Elvie Pump.

    8. The sample size for the training set

    Not applicable. This document does not describe a machine learning model's development with a training set for clinical applications. The "software" and "microcontroller" mentioned are likely for controlling the pump's mechanical functions and user interface, not for AI-based analysis requiring training data in the traditional sense.

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

    Not applicable, as there is no mention of a training set for an AI/machine learning model.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1