Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K153605
    Manufacturer
    Date Cleared
    2016-02-11

    (56 days)

    Product Code
    Regulation Number
    880.5725
    Reference & Predicate Devices
    Predicate For
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The iv Watch Model 400 is indicated for the detection of subcutaneous infiltrations and extravasations of 10 cc or less of optically clear, uncolored infusates, as an adjunctive device to the clinical evaluation in the hospital setting of patients 18 years old or greater with peripherally-inserted IVs (PIVs) on the forearm or dorsal aspect of the hand.

    The device is indicated to assess patients for subcutaneous infiltrations and extravasations but should not serve as a substitute for regular clinician assessment of the PIV site. The iv Watch Model 400 is intended for use by physicians, or under the direction of a physician, who have been trained in the use of the iv Watch Model 400.

    Device Description

    The ivWatch Model 400 is a medical device that provides continuous, noninvasive monitoring of human tissue adjacent to peripheral intravenous (PIV) insertion sites on the forearm and dorsal aspect of the hand to aid in the early detection of infiltration and extravasation events. The ivWatch Model 400 consists of the ivWatch Patient Monitor (IPM), a reusable optical sensor cable and a single-use sensor receptacle.

    The ivWatch Model 400 uses visible and near-infrared light to measure changes in the optical properties of the tissue near a PIV insertion site. The IPM contains an optical system that generates visible and near-infrared light signals that are sent through the optical sensor cable to the patient's skin. Simultaneously, the IPM measures the light reflected back through the optical sensor cable from the patient's skin. Measured changes between the emitted and reflected signal are processed by proprietary ivWatch signal processing algorithms to determine if an infiltration event may have occurred. If changes in the optical properties of the tissue near the peripheral IV insertion site are consistent with an infusate pooling in the subcutaneous tissue, the IPM emits audible and visual notifications intended to prompt the clinician to inspect the peripheral IV site for a possible infiltration event.

    AI/ML Overview

    The ivWatch Model 400 is an adjunctive device to aid in the early detection of subcutaneous infiltrations and extravasations of 10 cc or less of optically clear, uncolored infusates in patients 18 years or older with peripherally-inserted IVs (PIVs) on the forearm or dorsal aspect of the hand. The device was submitted for a 510(k) premarket notification (K153605).

    Here's an analysis of the acceptance criteria and study information provided in the document:

    1. Table of Acceptance Criteria and Reported Device Performance

    The device under review is an updated version of the ivWatch Model 400 (K153605), with modifications only to the sensor cable sheathing. The performance data presented focuses on verifying that these modifications do not negatively impact the device's safety and effectiveness compared to the predicate device (K142374). Therefore, the acceptance criteria and results specifically address biocompatibility and reprocessing, as clinical efficacy was not re-evaluated for this submission.

    Performance CharacteristicAcceptance CriteriaResult
    Biocompatibility Testing
    Sensitization (on sheathing of sensor cable)Per ISO 10993-10:2010, Non-sensitizerPass
    Irritation (on sheathing of sensor cable)Per ISO 10993-10:2010, Non-irritantPass
    Cytotoxicity (on sheathing of sensor cable)Per ISO 10993-5:2009, Non-toxicPass
    Reprocessing Validation
    Low Level Disinfection (on sensor cable)Per AAMI TIR12 -2010, AAMI TIR30-2011 and Reprocessing Medical Devices in Health Care Settings: Validation Methods and LabelingPass
    Cleaning (on sensor cable)Per AAMI TIR12 -2010, AAMI TIR30-2011 and Reprocessing Medical Devices in Health Care Settings: Validation Methods and LabelingPass

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

    The document does not detail specific sample sizes for the individual biocompatibility and reprocessing tests beyond indicating that the tests were performed. It broadly states that the testing was performed on the "sheathing of the sensor cable" and "the sensor cable."

    Given the nature of the tests (biocompatibility and reprocessing validation), the "test set" would typically refer to the samples of the modified sensor cable sheathing and sensor cable that underwent the evaluations. The provenance of this data is from tests conducted by ivWatch, LLC for regulatory submission. The document does not specify country of origin for the data or whether it was retrospective or prospective, but such testing is typically prospective, conducted specifically for the submission.

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

    For the biocompatibility and reprocessing tests, "ground truth" is established by adherence to recognized international standards and guidelines (ISO 10993 series and AAMI guidance documents). The "experts" involved would be the certified laboratories and personnel performing these tests, who are qualified to interpret the standards and conduct the specific assays (e.g., cell culture for cytotoxicity, animal models for sensitization/irritation, microbiology for disinfection). The document does not specify the number or specific qualifications of these experts beyond referencing the ISO and AAMI standards.

    4. Adjudication Method for the Test Set

    Adjudication methods like 2+1 or 3+1 (common in image review studies) are not applicable to the type of non-clinical "test sets" described (biocompatibility and reprocessing validation). The results are objectively determined based on the outcomes of standardized scientific assays and compared against predefined pass/fail criteria outlined in the relevant standards.

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

    No MRMC comparative effectiveness study was done for this specific submission (K153605). The document explicitly states, "Clinical testing was not required for this submission." This indicates that the safety and effectiveness of the device's core functionality (detection of infiltrations) was established in a prior submission (K142374), and the current submission only addresses modifications that do not impact that core functionality or clinical performance. Therefore, there is no effect size reported for human readers improving with or without AI assistance, as AI functionality for interpretive purposes is not central to this device's regulatory review.

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

    No standalone study presenting algorithm-only performance metrics (e.g., sensitivity, specificity for infiltration detection) was performed or discussed in this submission. Similar to the MRMC study, this type of performance data would have been part of the original K142374 submission that established the device's fundamental function. The current submission focuses on material and reprocessing changes.

    7. Type of Ground Truth Used

    For the biocompatibility tests (sensitization, irritation, cytotoxicity), the "ground truth" is determined by the biological response observed in standardized in vitro or in vivo tests, as interpreted against the acceptance criteria defined by the ISO 10993 standards.

    For the reprocessing validation (low-level disinfection and cleaning), the "ground truth" is established by demonstrating a predefined reduction in microbial load or removal of organic soil from the device, verified through validated laboratory methods according to AAMI guidance.

    8. Sample Size for the Training Set

    The concept of a "training set" is generally applicable to machine learning algorithms. While the ivWatch Model 400 uses "proprietary ivWatch signal processing algorithms," the document does not discuss the algorithms' development or any associated training sets for this particular submission. The focus is on the physical components of the device. Any algorithm training would have occurred during the development of the original predicate device (K142374).

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

    As no training set is discussed in this specific 510(k) summary, the method for establishing its ground truth is not provided. For such a device, if an algorithm were indeed trained, the ground truth for infiltration detection would likely involve direct clinical observation by healthcare professionals, potentially confirmed by imaging or other objective measures of fluid extravasation, collected prospectively or retrospectively. However, this level of detail is absent from the provided document.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1