Search Filters

Search Results

Found 4 results

510(k) Data Aggregation

    K Number
    K072359
    Manufacturer
    Date Cleared
    2007-11-08

    (78 days)

    Product Code
    Regulation Number
    878.4040
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    AEARO COMPANY

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

    Aearo Surgical N95 Respirators, N9508C and N9511 are NIOSH approved N95 respirators intended for single use by operating room personnel and other health care workers to protect both the patients and the health care workers from transfer of microorganisms, blood and body fluids, and airborne particulate materials. This includes use as a procedure mask, isolation mask or dental face mask. This device also meets CDC Guidelines for TB Exposure Control.

    Device Description

    These masks are molded cup masks, with a center layer of polypropylene meltblown material sandwiched by inner and outer layers of nonwoven material. The mask has 2 elastic headbands. No fiberglass media is used in this product.

    AI/ML Overview

    Here's an analysis of the provided text regarding the Aearo Company N9508C and N9511C Surgical N95 Respirators, broken down into the requested sections:

    1. Table of Acceptance Criteria and Reported Device Performance

    Performance CharacteristicTest MethodAcceptance CriteriaReported Device Performance (N9508C and N9511C)
    Fluid Resistance Performance (mmHg)ASTM F-1862 @ 80 mmHg29 of 32 must pass (no fluid penetration)32 of 32 passed (no fluid penetration)
    Flammability Class16 CFR 1610Flame spread must be within upper and lower control limits; meets Class INo flame spread on 10 of 10 samples, meets Class I
    Filter EfficiencyNIOSH, 42CFR Part 84>95% EfficientPASS (>95% Efficient, due to NIOSH N95 approval)
    Breathing Resistance (Exhalation)NIOSH 42CFR Part 84$\le$ 25 mm H2O @ 85 lpmPASS ($\le$ 25 mm H2O @ 85 lpm, due to NIOSH N95 approval)
    Breathing Resistance (Inhalation)NIOSH 42CFR Part 84$\le$ 35 mm H2O @ 85 lpmPASS ($\le$ 35 mm H2O @ 85 lpm, due to NIOSH N95 approval)
    Bacterial Filtration EfficiencyASTM F2101-01>99.9%>99.9% on all samples tested
    Biocompatibility: CytotoxicityISO-10993-1 (Agar Overlay)Cytotoxicity score of 2 or lessScore of 0 (no detectable reactivity)
    Biocompatibility: SensitizationISO-10993-1 (Closed Patch)No visible change, Score of 0No visible change, Score of 0 (None of the patched animals had any visible change at the test site 48 hours after the challenge dose, using albino guinea pigs)
    Biocompatibility: Primary Skin IrritationISO-10993-1 (Dermal Irritation, 16 CFR 1500 modified)Negligible, Score of 0Negligible, Score of 0 (No irritation evident on intact or abraded skin after 24 or 72 hours, using 3 rabbits)

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

    • Fluid Resistance (ASTM F-1862): 32 masks tested. The provenance is not explicitly stated as retrospective or prospective, but due to it being part of a 510(k) submission for a new device, it would be considered prospective testing specifically for this device. The country of origin for the data is not specified beyond "Nelson Laboratories" which is a US-based lab.
    • Flammability (16 CFR 1610): 10 samples tested. (Prospective testing by Nelson Laboratories, US).
    • Filter Efficiency (NIOSH 42CFR Part 84): Not explicitly stated, but would be part of the NIOSH certification process for N95 respirators. The NIOSH approval numbers (TC-84A-4268 and TC-84A-4261) indicate the device has met these requirements. (Prospective testing, likely US-based for NIOSH certification).
    • Breathing Resistance (NIOSH 42CFR Part 84): Not explicitly stated, but part of NIOSH certification. (Prospective testing, likely US-based).
    • Bacterial Filtration Efficiency (ASTM F2101-01): "All samples tested," exact number not specified, but typically involves multiple replicates. (Prospective testing by Nelson Laboratories, US).
    • Biocompatibility (ISO-10993):
      • Cytotoxicity: "None of the mask samples tested," exact number not specified. (Prospective testing by Nelson Laboratories, US).
      • Primary Skin Irritation: 3 rabbits. (Prospective testing by AppTec Laboratory Services, US).
      • Delayed Hypersensitivity/Sensitization: Albino guinea pigs (number not specified, but usually several for animal studies). (Prospective testing by Northview Pacific Laboratories, US).

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

    For this type of device (Surgical N95 Respirators), the "ground truth" is established through standardized laboratory testing protocols (e.g., ASTM, NIOSH, ISO standards) rather than expert consensus on medical images or clinical outcomes.

    • The experts involved are the qualified laboratory personnel performing these rigorous, standardized tests. Their qualifications are inherent in their ability to correctly execute these specific test methods and interpret their results according to the standards. No specific number or individual qualifications are provided for these lab personnel in the document, as the focus is on the adherence to established test methodologies.

    4. Adjudication Method for the Test Set

    Not applicable for this type of device testing. The results are quantitative measurements or direct observations (e.g., presence/absence of fluid penetration, flame spread, irritation) that either meet or do not meet predefined criteria. There is no subjective interpretation requiring an adjudication process.

    5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done

    No, an MRMC comparative effectiveness study was not done. This type of study is relevant for diagnostic devices that rely on human interpretation, often with AI assistance, rather than for performance testing of physical protective equipment.

    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 N95 respirator, not an algorithm or AI system. The performance tests are themselves "standalone" in the sense that they measure the physical properties and performance of the respirator without a human-in-the-loop component for interpreting the device's function.

    7. The Type of Ground Truth Used

    The ground truth used for these performance tests is based on:

    • Standardized Test Methodologies: The acceptance criteria and performance measurements are derived directly from established international and national standards (ASTM, NIOSH, ISO, CFR) for the performance of medical devices and personal protective equipment.
    • Physical Measurements and Chemical/Biological Assays: The ground truth is confirmed through objective laboratory measurements and assays (e.g., measuring pressure drop, bacterial filtration efficiency, observing fluid penetration, analyzing cellular reactions).

    8. The Sample Size for the Training Set

    Not applicable. This device is a physical product (respirator), not an AI or machine learning model that requires a training set.

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

    Not applicable, as there is no training set for a physical device.

    Ask a Question

    Ask a specific question about this device

    K Number
    K070168
    Manufacturer
    Date Cleared
    2007-04-18

    (90 days)

    Product Code
    Regulation Number
    878.4040
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    AEARO COMPANY

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

    Aearo Surgical N95 Respirators, N9504C, N9504CS and N9514 are intended for single use by operating room personnel and other health care workers to protect both the patients and the health care workers from transfer of microorganisms, blood and body fluids, and airborne particulate materials. This includes use as a procedure mask. isolation mask or dental face mask. This device also meets CDC Guidelines for TB Exposure Control.

    Device Description

    These masks are molded cup masks, with a center layer of polypropylene meltblown material sandwiched by inner and outer layers of nonwoven material. The mask has 2 elastic headbands. No fiberglass media is used in this product.

    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:

    1. Table of Acceptance Criteria and Reported Device Performance:

    Performance CharacteristicTest MethodAcceptance CriteriaReported Device Performance (N9504C, N9504CS, N9514C)Predicate Device Results (Gerson Isolair APR Model 2735)
    Fluid ResistanceASTM F-1862 @ 80 mmHg29 of 32 show no fluid penetration (from narrative) / 32 of 32 pass (from table)32 of 32 pass32/32 pass
    Flammability Class21 CFR Part 58Flame spread must be within upper and lower control limits / Meets Class INo flame spread on 10 of 10 samples, meets Class IMeets Class I
    Filter EfficiencyNIOSH, 42CFR Part 84≥95% EfficientAverage 97.36% (N9514C), 97.66% (N9504C), and 97.83% (N9504CS) efficient of 20 samplesAverage 96.86% efficient of 20 samples
    Breathing Resistance (Inhalation)NIOSH 42CFR Part 84 (Inhalation)≤35.0 mm H2O @ 85 lpm (implied as max for inhalation)Average 6.2 mm H2O (N9514C), 7.6 mm H2O (N9504C), and 8.0 mm H2O (N9504CS) @ 85 lpm (average of 3 samples each)Average 15.2 mm H2O on 3 samples
    Biocompatibility - CytotoxicityISO-10993-1 / Agar OverlayScore of 2 or lessScore of 0N/A (not provided for predicate)
    Biocompatibility - SensitizationISO-10993-1 / Closed Patch TestNo visible change, Score of 0No visible change, Score of 0N/A (not provided for predicate)
    Biocompatibility - Primary Skin IrritationISO-10993-1 / 16 CFR 1500 (rabbits)Negligible, Score of 0Negligible, Score of 0N/A (not provided for predicate)
    Bacterial Filtration Efficiency (BFE)ASTM F2101-01Not explicitly stated as acceptance criteria in the table, but narrative states "showed a percent BFE of greater than 99.9% on all samples tested" for adequacy of mask as a respiratory barrier for bacteria.Greater than 99.9% on all samples tested (using Staphylococcus aureus biological aerosol)N/A (not explicitly provided for predicate, likely covered by NIOSH certification for predicate as well)

    Notes on Acceptance Criteria:

    • The document sometimes states the acceptance criteria in the narrative and sometimes directly in the table. The table combines this information.
    • For Fluid Resistance, the narrative states "29 of 32 show no fluid penetration," while the table states "32 of 32 pass." The reported performance of "32 of 32 pass" clearly meets both.
    • The breathing resistance acceptance criteria are derived from NIOSH 42CFR Part 84, which specifies maximum allowed resistance for inhalation and exhalation. The provided data are for inhalation.

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

    • Fluid Resistance: 32 masks
    • Flammability Class: 10 samples
    • Filter Efficiency: 20 samples
    • Breathing Resistance: 3 samples for each model (N9514C, N9504C, N9504CS), totaling 9 samples.
    • Bacterial Filtration Efficiency (BFE): "all samples tested" (specific number not given, but described using a biological aerosol of Staphylococcus aureus)
    • Biocompatibility - Cytotoxicity: "None of the mask samples tested" (specific number not given)
    • Biocompatibility - Primary Skin Irritation: 3 rabbits
    • Biocompatibility - Delayed Hypersensitivity: Albino guinea pigs (specific number not given, but based on ISO 10993-10, 2002 requirements)

    Data Provenance: The studies were conducted by various laboratories, including Nelson Laboratories and AppTec Laboratory Services. The location of these labs (e.g., country of origin) is not specified. The studies appear to be prospective tests performed specifically for this 510(k) submission, confirming the device's performance against established standards.


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

    This section is not applicable to this type of device (N95 respirators) and testing. The "ground truth" for these performance characteristics (fluid resistance, flammability, filtration efficiency, biocompatibility) is established by adherence to standardized, objective test methods (e.g., ASTM, NIOSH, ISO) and laboratory measurements, not by expert consensus or interpretations of complex data like medical images. The expertise lies in conducting the tests according to the specified protocols and interpreting the objective results.


    4. Adjudication Method for the Test Set:

    This section is not applicable. Adjudication methods like "2+1" or "3+1" are typically used in studies where individual expert assessments need to be combined or resolved, such as in clinical image interpretation or diagnostic evaluations. The tests performed for this device are objective laboratory measurements with numerical or categorical outcomes (e.g., pass/fail, percentage, score of X).


    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:

    This section is not applicable. MRMC studies are used to evaluate the diagnostic performance of medical devices that involve human interpretation, often assisted by AI. This submission is for an N95 respirator, which is a physical barrier device, not a diagnostic tool requiring human interpretation or AI assistance.


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

    This section is not applicable. "Standalone performance" refers to the performance of an AI algorithm without human involvement. As stated above, this device is not an AI algorithm or a diagnostic tool.


    7. The Type of Ground Truth Used:

    The ground truth for these tests is based on objective, standardized laboratory measurements and physical property assessments using internationally recognized standards (ASTM, NIOSH, ISO).

    • Fluid Resistance: Direct measurement of liquid penetration.
    • Flammability: Observation of flame spread under controlled conditions.
    • Filter Efficiency: Measurement of particle penetration through the material.
    • Breathing Resistance: Measurement of pressure drop across the respirator.
    • Bacterial Filtration Efficiency: Measurement of bacterial penetration.
    • Biocompatibility: In vitro (cytotoxicity) and in vivo (irritation, sensitization on rabbits/guinea pigs) biological responses as per ISO standards.

    8. The Sample Size for the Training Set:

    This section is not applicable. The N95 respirator is a manufactured physical product, not a learning algorithm. Therefore, there is no "training set" in the context of machine learning or AI.


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

    This section is not applicable for the same reason as point 8.

    Ask a Question

    Ask a specific question about this device

    K Number
    K063013
    Manufacturer
    Date Cleared
    2006-12-01

    (60 days)

    Product Code
    Regulation Number
    878.4040
    Reference & Predicate Devices
    N/A
    Why did this record match?
    Applicant Name (Manufacturer) :

    AEARO COMPANY

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

    The Pleats Plus ™ 1054 and 1054S N95 Respirators and Surgical Masks are intended for single use by operating room personnel and other health care workers to protect both the patients and the health care workers from transfer of microorganisms, blood and body fluids, and airborne particulate materials. This includes use as a procedure mask, isolation mask or dental face mask. This device also meets CDC Guidelines for TB Exposure Control.

    Device Description

    These masks are pleated, 3-ply masks, with a center layer of polypropylene meltblown material sandwiched by inner and outer layers of nonwoven material. The mask has 2 braided synthetic elastic headbands and a flexible wire tie nosepiece that allows the respirator to form to the bridge of the wearers nose. No fiberglass media is used in this product.

    AI/ML Overview

    The Abbreviated 510(K) for Aearo Company Pleats Plus™ 1054 and 1054S Surgical N95 Respirators (K063013) describes the acceptance criteria and the studies performed to demonstrate that the device meets these criteria.

    1. Table of Acceptance Criteria and Reported Device Performance

    Performance CharacteristicsTest MethodAcceptance Criteria / Predicate Device ResultsReported Device Performance (Pleats Plus 1054 and 1054S)
    Fluid Resistance PerformanceASTM 1862-00a @ 120mmHg29 of 32 to pass / PASSPASS
    Flammability Class21 CFR part 58Flame spread must be within upper and lower control limits / No flame spread on 10 of 10 samples, meets Class INo flame spread on 10 of 10 samples, meets Class I
    Filter EfficiencyNIOSH, 42CFR Part 84≥95% Efficient / Average 99.11% efficient of 20 samplesAverage 98.45% efficient for 20 samples
    Breathing ResistanceNIOSH 42CFR Part 84≤35.0 mm H2O @ 85 lpm / average 3.5 mm H2O @ 85 lpm for 3 samplesAverage 1.1 mm H2O @ 85 lpm for 3 samples
    Biocompatibility: CytotoxicityISO-10993-1, Agar overlay methodScore of 2 or less / Score of 0Score of 0
    Biocompatibility: SensitizationISO 10993-10:2002 (study based on)No visible change, Score of 0Score of 0
    Biocompatibility: Primary Skin IrritationISO 10993-10:2002 (rabbits)Negligible, Score of 0Score of 0
    Bacterial Filtration Efficiency (BFE)ASTM F2101-01 (Staphylococcus aureus)(Not specified as acceptance criteria in table, but reported as an additional test)Greater than 99.9% on all samples tested

    2. Sample Sizes Used for Each Test and Data Provenance

    Test / Performance CharacteristicSample Size UsedData Provenance / Testing Body
    Fluid Resistance Performance32 samples (implied from "29 of 32 to pass")Not explicitly stated, likely Nelson Laboratories (common for such tests)
    Flammability Class10 samplesNelson Laboratories
    Filter Efficiency20 samplesNIOSH (for certification), specific lab not stated for comparative
    Breathing Resistance3 samplesNIOSH (for certification), specific lab not stated for comparative
    Biocompatibility: CytotoxicityNot specifiedNelson Laboratories
    Biocompatibility: SensitizationNot specifiedAppTec Laboratory Services (rabbits)
    Biocompatibility: Primary Skin IrritationNot specifiedAppTec Laboratory Services (rabbits)
    Bacterial Filtration Efficiency (BFE)Not specifiedNelson Laboratories

    The data provenance is from laboratory testing (e.g., Nelson Laboratories, AppTec Laboratory Services, NIOSH certification). These are prospective tests performed specifically for device evaluation. The country of origin for the manufacturing facility is Handan Hengyong Protective & Clean Products Co., LTD. Jiankang East Street Yongnian County High-Tech Development Area Hebei province, P.R. China, however, the testing laboratories are US-based (Nelson Labs and AppTec).

    3. Number of Experts and Qualifications for Establishing Ground Truth

    This document describes the testing of a physical medical device (N95 respirator) against established performance standards and methods. It does not involve a "ground truth" expert consensus in the same way a diagnostic imaging AI algorithm would. Instead, the "ground truth" is defined by:

    • Standardized test methods: ASTM 1862-00a, 21 CFR part 58, NIOSH 42CFR Part 84, ISO-10993-1, ASTM F2101-01.
    • Regulatory bodies and accredited laboratories: NIOSH approval TC-84A-4320, Nelson Laboratories, AppTec Laboratory Services.

    Therefore, the concept of "number of experts used to establish ground truth" with specific qualifications (like radiologists) is not applicable here. The "experts" are the scientists and technicians in the accredited labs performing the standardized tests according to the protocols set by regulatory bodies.

    4. Adjudication Method for the Test Set

    The concept of an adjudication method (like 2+1, 3+1) is typically relevant for studies where human interpretation or consensus is required (e.g., medical image reading). For the physical testing of the N95 respirator, the results are quantitative and objective measurements against predefined acceptance criteria. Therefore, no adjudication method as described is applicable or performed in this context. The results are reported directly from the laboratory tests.

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

    No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. This type of study is relevant for evaluating the impact of AI algorithms on human reader performance, typically in diagnostic tasks. This submission is for a physical device (N95 respirator), not an AI-powered diagnostic tool.

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

    No, this question is not applicable as the device is a physical N95 respirator, not an algorithm or software. Therefore, there is no "standalone algorithm" performance to report.

    7. Type of Ground Truth Used

    For this device, the "ground truth" is based on:

    • Standardized physical and chemical test results: Objective measurements demonstrating performance against established industry standards and regulatory requirements (e.g., ASTM, NIOSH, ISO, CFR).
    • Predicate device comparison: The device's performance is also compared against a legally marketed predicate device (Pleats Plus 1050), establishing substantial equivalence based on meeting similar performance characteristics.

    8. Sample Size for the Training Set

    This question is not applicable as the device is a physical N95 respirator, not a machine learning algorithm that requires a training set.

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

    This question is not applicable as the device is a physical N95 respirator and does not use a training set in the context of machine learning.

    Ask a Question

    Ask a specific question about this device

    K Number
    K041855
    Manufacturer
    Date Cleared
    2004-11-10

    (124 days)

    Product Code
    Regulation Number
    878.4040
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    AEARO CO.

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

    The Pleats Plus™ 1050 and 1050S N95 Respirators and Surgical Masks are intended for single use by operating room personnel and other health care workers to protect both the patients and the health care workers from transfer of microorganisms, blood and body fluids, and airborne particulate materials. This includes use as a procedure mask, isolation mask or dental face mask. This device also meets CDC Guidelines for TB Exposure Control.

    Device Description

    These masks are pleated, 3-ply masks, with a center layer of polypropylene meltblown material sandwiched by inner and outer layers of nonwoven material. The mask has 2 braided synthetic elastic headbands and a flexible wire tie nosepiece that allows the respirator to form to the bridge of the wearers nose. No fiberglass media is used in this product.

    AI/ML Overview

    Here's a breakdown of the acceptance criteria and study information for the Aearo Company Pleats Plus™ Surgical N95 Respirators, based on the provided text:

    Acceptance Criteria and Reported Device Performance

    Performance CharacteristicsTest MethodAcceptance Criteria/Results (Pleats Plus 1050 and 1050S)Predicate Device Results (Gerson Isolair APR, Type N95 Model 2735)
    Fluid resistance PerformanceASTM 1862-00a @ 120mmHgAcceptance Criteria: 29 of 32 show no fluid penetration.
    Reported Performance: 31 of 32 pass32/32 pass
    Flammability class16 CFR 1610Acceptance Criteria: Flame spread must be within upper and lower control limits.
    Reported Performance: No flame spread on 10 of 10 samples, meets Class IMeets Class I
    Filter efficiencyNIOSH, 42CFR Part 84Acceptance Criteria: ≥95% Efficient
    Reported Performance: Average 99.11% efficient of 20 samplesAverage 96.86% efficient of 20 samples
    Breathing resistanceNIOSH 42CFR Part 84Acceptance Criteria: ≤35.0 mm H20 @ 85 lpm
    Reported Performance: Average 3.5 mm H20 @ 85 lpm of 3 samplesAverage 15.2 mm H20 of 3 samples
    Biocompatibility: CytotoxicityISO-10993-1 / agar overlayAcceptance Criteria: Score of 2 or less
    Reported Performance: Score of 0N/A (Not Applicable as it was not evaluated for the predicate device in this table)
    Biocompatibility: SensitizationISO-10993-1 / closed patchAcceptance Criteria: No visible change
    Reported Performance: Score of 0N/A
    Biocompatibility: Primary Skin IrritationISO-10993-1 / modified 16 CFR 1500Acceptance Criteria: Negligible
    Reported Performance: Score of 0N/A
    Bacterial Filtration Efficiency (BFE)ASTM F2101-01 (using Staphylococcus aureus)Acceptance Criteria: Not explicitly stated but the reported performance exceeds the Filter efficiency criteria of ≥95%.
    Reported Performance: Greater than 95.5% on all samples tested.Not explicitly stated in the comparison table.

    Study Details:

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

      • Fluid resistance: 32 masks were tested. (Provenance not specified, but implied to be from Aearo Company products).
      • Flammability class: 10 samples were tested. (Provenance not specified).
      • Filter efficiency: 20 samples were tested. (Provenance not specified).
      • Breathing resistance: 3 samples were tested. (Provenance not specified).
      • Bacterial Filtration Efficiency (BFE): "All samples tested" showed >95.5% BFE. The number of samples for BFE is not explicitly stated, but it was conducted by Nelson Laboratories.
      • Cytotoxicity: Samples of Pleats Plus were tested by Nelson Laboratories.
      • Primary skin irritation: 3 rabbits were used, tested by NAMSA.
      • Delayed Hypersensitivity (Sensitization): Albino guinea pigs were used, tested by Northview Pacific Laboratories.

      All tests appear to be prospective to demonstrate the device's performance against specific standards. The country of origin for the data is implied to be the United States, given the testing organizations (Nelson Laboratories, NAMSA, Northview Pacific Laboratories) and the submission to the FDA.

    2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
      The document describes performance testing against established standards (e.g., ASTM, NIOSH, CFR, ISO). The "ground truth" for these tests is implicitly defined by the accepted methodologies and criteria of these standards. There is no mention of human experts establishing a subjective ground truth for the performance test set. The results are objective measurements against defined thresholds.

    3. Adjudication method for the test set:
      Not applicable. The tests are objective measurements against published standards and acceptance criteria. There is no mention of physician or expert adjudication as would be seen in diagnostic imaging studies.

    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, an MRMC comparative effectiveness study was not done. This document focuses on the physical barrier and material properties of a surgical N95 respirator, not on the performance of an AI-assisted diagnostic tool or human decision-making.

    5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
      Yes, in a sense, the entire performance testing is "standalone" in that it assesses the device's physical performance independent of human interaction for diagnostic purposes. The device itself, a respirator, is the "algorithm" here, and its performance is measured directly against physical and biological challenges. There's no AI algorithm involved.

    6. The type of ground truth used:
      The ground truth is based on established engineering and biological standards and their defined acceptance criteria. For example, fluid resistance is measured against a specific pressure (120 mmHg) using ASTM, filter efficiency against NIOSH standards, and biocompatibility against ISO-10993. The "ground truth" is a pass/fail against these objective criteria.

    7. The sample size for the training set:
      Not applicable. This notice describes the testing of a physical medical device (respirator), not a machine learning model. Therefore, there is no "training set" in the context of an AI algorithm.

    8. How the ground truth for the training set was established:
      Not applicable. As there is no AI algorithm and no training set, the establishment of ground truth for such a set is irrelevant to this submission.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1