Search Filters

Search Results

Found 53 results

510(k) Data Aggregation

    K Number
    K113117
    Date Cleared
    2012-03-22

    (153 days)

    Product Code
    Regulation Number
    882.1400
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    NIHON KOHDEN AMERICA, INC.

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

    The EEG-1200A series Nerurofax is intended to record, measure and display cerebral and extracerebral activity for EEG and Sleep Studies. This data may be used by the clinician in sleep disorders, epilepsies and other related disorders as an aid in diagnosis

    The device is intended for use by medical personnel in any location within a medical facility, laboratory, clinic or nursing home or outside of a medical facility under direct supervision of a medical professional.

    Device Description

    The EEG-1200A with JE-120A is a digital EEG based on a minimum of a 32-bit computer with a filing function. The device uses Windows Graphic User Interface, receives physiological signals (up to 256 channels with JE-120 electrode junction box) from patients and digitizes the signals, the application of the software reproduces the waveforms, The EEG-1200A with JE-120A consists of a main unit, electrode junction box (head box), PC Unit, Isolation Unit and System Programs. The electrode junction box, monitor, keyboard and mouse connect to the computer. The computer and control panel connect to the main unit. Components requiring AC power plug into the main unit's isolated power supply. The main unit plugs into a hospital grade AC power source. All components fit onto a portable cart. A stand is also available for the electrode junction box. Patient data is stored to hard drive or other commercially available digital storage media. Inputs for Sp02 and EtC02 are available.

    AI/ML Overview

    Here's a breakdown of the acceptance criteria and study information for the Nihon Kohden JE-120A Electrode Junction Box for EEG-1200A, based on the provided document:

    This 510(k) pertains to a Special 510(k) Notification for a device modification, focusing on substantial equivalence to a predicate device. Therefore, the "acceptance criteria" discussed are primarily related to meeting performance specifications and regulatory standards to demonstrate that the new device is as safe and effective as the predicate. The "study" here refers to the testing performed to show compliance with these criteria.


    1. Table of Acceptance Criteria and Reported Device Performance

    The document presents a comparison of technical characteristics between the new device (JE-120A) and the predicate devices (JE-212A/JE-921A). The "acceptance criteria" are implied by the values provided for the predicate devices, and the "reported device performance" is the value for the new device. The goal is to show the new device either meets or exceeds the predicate's performance, or that any differences do not raise new questions of safety or effectiveness.

    CharacteristicPredicate JE-212A + Accessories (e.g., JE-225AK/226AK/227AK+QI-122A)Predicate JE-921A (K#050833)New Device JE-120A+JE-125AK(JE-225AK)/JE-226AK/JE-227AK/JE-228AK+QI-123AAcceptance Criteria (Implied from Predicate)Reported Device Performance (JE-120A)
    Product used withElectroencephalograph EEG-1200A K#080546Electroencephalograph EEG-1200A K#080546Electroencephalograph EEG-1200A K#080546Must be compatible with EEG-1200ACompatible with EEG-1200A
    Intended UseElectrode junction box for EEGElectrode junction box for EEG/PSGElectrode junction box for EEG/PSGEquivalent to predicate's intended useEquivalent to predicate's intended use
    Measurement parametersEEGEEG, ECG, EMG, EOG, respiration, SpO₂, and CO₂EEG, ECG, EMG, EOG, SpO₂, and CO₂Same or expanded measurement parametersSame as JE-921A
    Number of input terminals192 (EEG only)25 (general)256 (general)At least 192 (EEG); 25 (general)256 (general)
    EEG input terminals192144 (JE-125AK)Up to 192Up to 256 (via accessories)
    Multi-purpose input terminals030Not applicable (difference noted in document)0
    Bipolar input terminals0416At least 016
    Respiration input terminals16Input impedance 200M ohmInput impedance 200M ohm16 (for respiration)16 (for respiration)
    Input impedance200M ohmLess than 1.5 micro Vp-pLess than 1.5 micro Vp-pAt least 100M ohm200M ohm
    NoiseLess than 1.5 micro Vp-pMore than 105dBMore than 110dBLess than or equal to 1.5 micro Vp-pLess than 1.5 micro Vp-p
    Rejection ratioMore than 110dB0.08Hz (TC 2 seconds)0.016Hz(TC 10 seconds) or 0.08Hz (TC 2 seconds)At least 105dBMore than 110dB
    Low cut filter0.016Hz (TC 10 seconds) or 0.08Hz (TC 2 seconds)300Hz (-18dB/oct)3000Hz (-18dB/oct)Same or improved filter characteristics0.016Hz or 0.08Hz
    High cut filter3000Hz (-18dB/oct.)YesYesSame or improved filter characteristics3000Hz (-18dB/oct)
    Electrode impedance checkYes16 bit (97nV/LSB)16 bit (97nV/LSB) or 16 bit (388nV/LSB)YesYes
    A/D resolution16 bits (97nV/LSB)1000Hz10000HzEquivalent or higher resolution16 bits (97nV/LSB) or (388nV/LSB)
    Maximum Sampling frequency10000HzNone10000HzEquivalent or higher sampling frequency10000Hz
    SpO₂ inputNoneSpO₂ adapter is connected to this unit directly.SpO₂ adapter is connected to this unit directly.SpO₂ input capability (if applicable)Directly connected
    EtCo2 inputNoneEtCo2 adaptor is connected to this unit directly.EtCo2 adaptor is connected to this unit directly.EtCo2 input capability (if applicable)Directly connected
    Body position sensorNoneDC input terminalsNoneNot applicable (difference noted in document)None
    Mini electrode junction boxOptionOptionOptionOption availableOption available
    Interface with EEGEthernetUSBEthernetEthernet or USBEthernet
    SafetyClass I, Type BFClass I, Type BFClass I, Type BFCompliant with Class I, Type BFClass I, Type BF

    Note: The document implies acceptance criteria by comparing the new device's specifications to those of the predicate devices. The new device is generally shown to be equivalent or to offer improvements (e.g., more channels, higher sampling frequency) without raising new safety/effectiveness concerns.


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

    The document does not explicitly mention a "test set" in the context of patient data or clinical trials for evaluating diagnostic accuracy or performance like an AI algorithm would. This is a 510(k) for a hardware component (electrode junction box) of an EEG system.

    The testing conducted was primarily engineering verification and validation of the device's hardware, software, and compliance with standards. Therefore, the "sample size" would refer to the number of units tested, the number of software modules, or test cases, not patient data.

    • Sample Size: Not applicable in the context of patient data. The testing involved multiple system components and software units.
    • Data Provenance: Not applicable in the context of patient data. The testing was internally conducted by Nihon Kohden Corporation. The reports listed (e.g., A100-000336B, A152-005167, A275-000544, etc.) are internal technical reports from the design control process.

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

    Not applicable. This type of information is relevant for studies evaluating diagnostic performance (e.g., an AI algorithm's ability to classify images). For this device, "ground truth" refers to the expected performance characteristics based on engineering specifications and regulatory standards. The "experts" involved would be the design engineers, quality assurance personnel, and regulatory affairs specialists at Nihon Kohden Corporation, who conduct and review the testing.


    4. Adjudication Method for the Test Set

    Not applicable for this type of device submission. Adjudication methods (like 2+1 or 3+1) are used in clinical studies where disagreement among human readers or evaluators needs to be resolved to establish a definitive ground truth for an outcome. Here, performance is verified against predefined technical specifications and standards.


    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

    Not applicable. This is a hardware component (electrode junction box) for an EEG system, not an AI-powered diagnostic tool requiring human reader studies to assess improvement with AI assistance.


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

    Not applicable. This device is an electrode junction box, a hardware component, not an algorithm.


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

    The "ground truth" for this device is based on:

    • Engineering Specifications: Designed performance parameters (e.g., input impedance, noise levels, frequency response, channel count).
    • Predicate Device Performance: Performance data from the existing, legally marketed predicate devices (EEG-1200A with JE-212A / JE-921A) serves as a benchmark for substantial equivalence.
    • Voluntary Industrial Standards: Compliance with recognized medical electrical equipment safety and performance standards (e.g., IEC 60601-1 series, EN 60601 series, CAN/CSA-C22.2 series).
    • User Needs/Functional Requirements: Verification that the device meets its intended functional requirements as defined by Nihon Kohden (Report # A100-000336B).

    8. The sample size for the training set

    Not applicable. This device is not an AI algorithm that requires a training set of data.


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

    Not applicable. As this is not an AI algorithm, there is no training set or corresponding ground truth establishment process in this context.

    Ask a Question

    Ask a specific question about this device

    K Number
    K120485
    Date Cleared
    2012-03-16

    (28 days)

    Product Code
    Regulation Number
    882.1400
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    NIHON KOHDEN AMERICA, INC.

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

    The QP-160AK Trend program is a software-only device intended to be installed on the EEG-1200A series electroencephalograph to record, calculate, and display EEG data obtained from the EEG-1200A system. This device is intended to be used by qualified medical practitioners, trained in Electroencephalography, who will exercise professional judgment when using the information.

    The intended use for each of the software's outputs is as follows:

    • The EEG and aEEG waveforms are intended to help the user monitor the state of the brain.
    • The user-defined Fast Fourier Transform (FFT) parameters of this software (FFT power) are intended to help the user analyze the EEG waveform.
    • The burst suppression parameters of this software (interval and bursts per minute) are intended to aid in the identification and characterization of areas of burst-suppression pattern in the EEG.

    This device does not provide any diagnostic conclusion about the patient's condition to the user.

    The device is intended for use by medical personnel in any location within a medical facility, laboratory, clinic or nursing home or outside of a medical facility under direct supervision of a medical professional.

    Device Description

    The OP-160AK Trend program is a software-only device intended to be installed on the EEG-1200A series electroencephalograph to record, calculate, and display EEG data obtained from the EEG-1200A system. The QP-160AK EEG Trend program is the same as the previous version of QP-160AK cleared under 510k but has two new trends available (DSA Asymmetry trend and FFT Power Asymmetry trend).

    AI/ML Overview

    Here's an analysis of the acceptance criteria and study information for the Nihon Kohden QP-160AK EEG Trend Program, based on the provided 510(k) summary:

    This 510(k) submission, K120485, is for an updated version of an existing device (K092573, also Nihon Kohden QP-160AK EEG Trend Program) with the addition of two new trends: DSA Asymmetry trend and FFT Power Asymmetry trend.

    The regulatory approach taken is substantial equivalence to the previous version and to other predicate devices (BrainScope Zoom-100DC and Applied Neuroscience NeuroGuide Analysis System) that already include these new trend functionalities.


    1. Table of Acceptance Criteria and Reported Device Performance

    Given the nature of this 510(k) submission, where the new features leverage existing, cleared technology, the "acceptance criteria" are primarily based on the functional equivalence and proper operation of these features. There are no explicitly stated numerical performance metrics (e.g., sensitivity, specificity, accuracy) akin to what might be seen for a diagnostic AI device.

    Acceptance Criteria CategorySpecific CriteriaReported Device Performance / Justification
    Functional Equivalence (New Trends)The new DSA Asymmetry trend functions equivalently to the DSA Asymmetry trend in the predicate devices (BrainScope Zoom-100DC, Applied Neuroscience NeuroGuide Analysis System).The submission explicitly states: "The Brainscope-100DC and the Applied Neuroscience Neuroguide Analysis System (K041263) provide the same DSA Asymmetry trend... as the new QP-160AK." This implies a functional comparison was made and found to be equivalent.
    The new FFT Power Asymmetry trend functions equivalently to the FFT Power Asymmetry trend in the predicate devices (BrainScope Zoom-100DC, Applied Neuroscience NeuroGuide Analysis System).The submission explicitly states: "...and the Applied Neuroscience Neuroguide Analysis System (K041263) provide the same... FFT Power Asymmetry trend as the new QP-160AK." This implies a functional comparison was made and found to be equivalent.
    System Integration & SafetyThe updated QP-160AK EEG Trend Program integrates safely and correctly with the EEG-1200A series electroencephalograph."The QP-160AK EEG Trend Program was subjected to safety and performance testing procedures. The QP-160AK EEG Trend Program has undergone validation and verification testing to ensure conformance to all design requirements."
    Calculation & Display AccuracyThe calculations and display of all EEG trends (including new and existing) are accurate and within specifications."...the system has undergone comparison testing to ensure the substantial equivalence of the calculation and display of EEG trends. These tests verified that the device performed within specifications."
    Intended Use ComplianceThe device continues to meet its stated intended use for monitoring, analyzing, and aiding in identification/characterization of patterns, without providing diagnostic conclusions.The Intended Use statement remains consistent, and the safety and functional testing would confirm that the device operates within the bounds of this intended use.

    Study Information

    This submission does not involve a traditional clinical study with patient cohorts or expert assessments in the way an AI diagnostic algorithm might. Instead, the "study" demonstrating performance is primarily non-clinical verification and validation testing, and comparison to predicate devices, focusing on functional equivalence.

    1. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):

      • The document does not specify the sample size for any test set or the provenance of data used for verification and validation. It only mentions "comparison testing to ensure the substantial equivalence of the calculation and display of EEG trends." This type of testing would typically involve a set of pre-recorded EEG data, but the details are not provided.
      • It is not clear if "test set" here refers to specific patient data or internal engineering test cases. Given the context, it's more likely the latter.
    2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience):

      • Not applicable. There is no mention of external experts or establishing ground truth based on expert review for specific patient cases in a clinical study context. The "ground truth" for functional verification would be the expected output of the algorithms as derived from engineering specifications and comparison to the predicate device's known outputs.
    3. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

      • Not applicable. No clinical adjudication method is described or implied.
    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 MRMC comparative effectiveness study was done or reported. This device is an EEG trend program, which assists qualified practitioners in analyzing EEG data, but it is not presented as an AI-powered diagnostic tool that directly "improves" reader performance in a quantifiable clinical trial. It provides visualization tools for interpretation.
    5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

      • Yes, in a sense. The "comparison testing" and "validation and verification testing" would represent a standalone evaluation of the algorithm and its display capabilities against predefined specifications and the predicate device's output. The device itself is "software-only" and is intended to be installed on an EEG system. However, its intended use is always with a "qualified medical practitioner, trained in Electroencephalography." It does not provide diagnostic conclusions independently.
    6. The type of ground truth used (expert consensus, pathology, outcomes data, etc):

      • The "ground truth" for this type of submission is likely the expected computational output as derived from the established algorithms used in the predicate devices and the mathematical principles of DSA and FFT. It's not a clinical ground truth like pathology or expert consensus on a diagnosis. It's about the accurate calculation and graphical representation of EEG features.
    7. The sample size for the training set:

      • Not applicable. This is not an AI/ML device that requires a training set in the typical sense. It implements established signal processing algorithms (DSA, FFT) that do not learn from data.
    8. How the ground truth for the training set was established:

      • Not applicable, as there is no training set for an AI/ML algorithm.
    Ask a Question

    Ask a specific question about this device

    K Number
    K092573
    Date Cleared
    2010-07-09

    (323 days)

    Product Code
    Regulation Number
    882.1400
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    NIHON KOHDEN AMERICA, INC.

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

    The QP-160AK Trend program is a software-only device intended to be installed on the EEG-1200A series electroencephalograph to record, calculate, and display EEG data obtained from the EEG-1200A system. This device is intended to be used by qualified medical practitioners, trained in Electroencephalography, who will exercise professional judgment when using the information.

    The intended use for each of the software's outputs is as follows:

    • . The EEG and aEEG waveforms are intended to help the user monitor the state of the brain.
    • . The user-defined Fast Fourier Transform (FFT) parameters of this software (FFT power) are intended to help the user analyze the EEG waveform.
    • The burst suppression parameters of this software (interval and bursts per . minute) are intended to aid in the identification and characterization of areas of burstsuppression pattern in the EEG.

    This device does not provide any diagnostic conclusion about the patient's condition to the user.

    Device Description

    The QP-160AK EEG Trend program is a software program stored on electronic media such as CD Rom.

    The EEG-1200A OP-160AK Trend program is a device which is installed on the electroencephalograph EEG-1200A Series and records the EEG waveforms and identifies trends in the EEG data over extended periods of time in order for trained health care professionals to observe changes over time.

    The QP-160AK design features are as follows:

    • Trend display of aEEG and Burst suppression ratio .
    • Display of EEG waveform maximum of 64 channels
    • DC Trend display including analog inputs .
    • Operations of functions by control buttons adapted to touch panels .
    • Data management by NeuroWorkbench .
    AI/ML Overview

    The Nihon Kohden QP-160AK EEG Trend Program is a software-only device intended to be installed on the EEG-1200A series electroencephalograph to record, calculate, and display EEG data. It assists qualified medical practitioners in monitoring brain state, analyzing EEG waveforms using FFT power, and identifying/characterizing burst-suppression patterns. The device does not provide diagnostic conclusions.

    Here's an analysis of the acceptance criteria and the study performed, based on the provided document:

    1. Table of Acceptance Criteria and Reported Device Performance

    The document does not explicitly state quantitative "acceptance criteria" for the QP-160AK EEG Trend Program in terms of specific performance metrics (e.g., accuracy, sensitivity, specificity) for its outputs (aEEG, burst suppression parameters, FFT power). Instead, the performance testing focuses on conformance to design requirements and comparative equivalence to predicate devices.

    The "acceptance criteria" are implied to be that the device:

    • Performs within its specifications (which are not detailed beyond its functional description).
    • Demonstrates substantial equivalence in calculation and display of burst suppression ratio and aEEG compared to predicate devices.
    Acceptance Criterion (Implied)Reported Device Performance
    Conformance to all design requirements"The QP-160AK EEG Trend Program has undergone validation and verification testing to ensure conformance to all design requirements."
    Performance within specifications"These tests verified that the device performed within specifications." (Specific specifications are not provided in this document).
    Substantial equivalence in calculation and display of burst suppression ratio and aEEG to predicate devices"Additionally, the system has undergone comparison testing to ensure the substantial equivalence of the calculation and display of the burst suppression ratio and aEEG."

    The conclusion of substantial equivalence states: "The comparison of technological characteristics and performance testing of the QP-160AK EEG Trend Program demonstrate that its safety, effectiveness, and performance are equivalent to the specified predicate devices." |

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

    The document does not specify the number of EEG recordings or the sample size used for the performance or comparison testing. It also does not mention the country of origin of the data or whether the data was retrospective or prospective.

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

    The document does not specify the number of experts used to establish ground truth or their qualifications. The device is intended to be used by "qualified medical practitioners, trained in Electroencephalography, who will exercise professional judgment." This implies that expert judgment would be the basis for evaluating results, but the specifics of an expert panel for testing are not detailed.

    4. Adjudication Method for the Test Set

    The document does not describe any specific adjudication method (e.g., 2+1, 3+1) used for establishing ground truth or evaluating the device's performance.

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

    A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not conducted or reported in this 510(k) summary. The study described focuses on standalone performance and comparison to predicate devices, not on the improvement of human readers with AI assistance.

    6. Standalone (Algorithm Only) Performance Study

    Yes, a standalone performance assessment was done. The document states: "The QP-160AK EEG Trend Program was subjected to safety and performance testing procedures. The QP-160AK EEG Trend Program has undergone validation and verification testing to ensure conformance to all design requirements." This implies that the algorithm's functionality was evaluated on its own merits as designed. Additionally, comparison testing to ensure substantial equivalence of calculations and display to predicate devices also falls under a standalone assessment of the device's output.

    7. Type of Ground Truth Used

    The type of ground truth used is implicitly expert assessment and comparison to established predicate device outputs, rather than pathology, outcomes data, or a formalized consensus panel. The device is intended to "help the user monitor," "help the user analyze," and "aid in the identification and characterization," suggesting that the "truth" is what expert clinicians would interpret from similar data or how predicate devices present the same information.

    8. Sample Size for the Training Set

    The document does not specify any sample size for a training set. This is consistent with the device type, which is a trend program for an existing EEG system, rather than a machine learning model that typically requires a large training dataset. Its functionality appears to be based on established signal processing algorithms for aEEG, FFT, and burst suppression.

    9. How Ground Truth for the Training Set Was Established

    Since a distinct "training set" for a machine learning model is not applicable or mentioned, the method for establishing ground truth for such a set is also not described. The device's performance validation relies on conformance to design requirements and comparison to predicate devices, implying that its underlying algorithms are based on established physiological principles and methods.

    Ask a Question

    Ask a specific question about this device

    K Number
    K083456
    Date Cleared
    2009-03-02

    (101 days)

    Product Code
    Regulation Number
    868.1400
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    NIHON KOHDEN AMERICA, INC.

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

    The Nihon Kohden TG-970P Series CO2 Sensor Kit is intended for medical purposes to measure the concentration of carbon dioxide in a gas mixture to aid in determining the patient's ventilatory status. Along with other methods indicated by the physician for medical diagnosis, this device is intended as an indicator of patient carbon dioxide concentration during expiration.

    Device Description

    The Nihon Kohden CO2 Sensor Kit, model number TG-970P Series, is intended for medical purposes to measure the concentration of carbon dioxide in a gas mixture to aid in determining the patient's ventilatory (end tidal CO2) status. The device measuring technique is through absorption of infrared radiation. The airway adapter is a Single -Patient Use disposable product.

    The device is intended as an indicator of patient carbon dioxide concentration during expiration for intubated patients. The device is intended for use with patients weighing 7kg or more. The device is not recommended for patients with low tidal volume such as patients weighing less than 7kg or patients with a respiration rate greater than 150 breaths per minute.

    AI/ML Overview

    This document is a 510(k) Summary for a medical device (CO2 Sensor Kit) and does not contain detailed information about a specific study with acceptance criteria and reported device performance. It primarily focuses on demonstrating substantial equivalence to a predicate device.

    Therefore, I cannot provide the requested information from the given text. The document states:

    • "The device performance and specifications are consistent with all requirements for this device type."
    • "To date, no performance standards or special controls are known or established for this type of device."
    • "The device was subject to electromagnetic, environmental, safety and performance testing procedures. These tests verified the safety and efficacy of the device under intended operation for this device."

    However, it does not provide the specific acceptance criteria, reported device performance data, sample sizes, ground truth establishment, or details of efficacy studies (such as MRMC or standalone performance) that typically accompany such claims in a detailed study report. The intent of this 510(k) summary is to assert equivalence rather than present original performance study data against specific criteria.

    Ask a Question

    Ask a specific question about this device

    K Number
    K083271
    Date Cleared
    2008-12-24

    (48 days)

    Product Code
    Regulation Number
    870.1025
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    NIHON KOHDEN AMERICA, INC.

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

    The device is intended to monitor, display and record physiological data to provide cardiac and vital signs monitoring within a medical facility. The device is intended to monitor the electrocardiogram to generate audible and/or visible alarms when an arrhythmia exists. The device is also intended to monitor heart rate, pulse rate, blood oxygen saturation (SpO2), noninvasive blood pressure (NIBP), invasive blood pressure (IBP), body temperature, carbon dioxide concentration (CO2 and EtCO2), and respiratory rate. The device may generate an audible and/or visible alarm when a measured rate falls outside preset limits. The device may also condition and transmit physiological signals via radio frequency. This will be available for use by medical personnel on all patient populations.

    Device Description

    The CGS-9001A Series Communication Gateway Server is an Optional Accessory to the BSM-2300A and BSM-6000 Bedside Monitors, it is a software product that allows the Nihon Kohden Patient Monitoring System to transfer alarm event information from the monitoring device to a third party system. The Communication Gateway Server collects alarm information from all networked patient monitors in a Nihon Kohden Patient Monitoring System and forwards it to a commercially available third party Secondary Alarm Notification System. The alarm notification generated by the third party alarm (not marketed by Nihon Kohden America, Inc.) is for Secondary Alarm Notification Only.

    AI/ML Overview

    The provided text describes a 510(k) summary for the Nihon Kohden BSM-2300A and BSM-6000 Bedside Monitors with the CGS-9001A Communication Gateway Server. The document focuses on regulatory approval based on demonstrating substantial equivalence to a predicate device, rather than a clinical study establishing specific performance acceptance criteria for a new clinical indication.

    Therefore, many of the requested elements for describing specific acceptance criteria and a study that proves the device meets them cannot be fully extracted from this document, as the submission primarily pertains to the safety and performance verification of a device accessory that facilitates alarm information transfer, not a diagnostic or therapeutic AI algorithm.

    However, I can extract the available information and highlight what is not present.

    1. Table of Acceptance Criteria and Reported Device Performance

    Acceptance CriteriaReported Device Performance
    Safety: Device complies with IEC 601-1 sub-clause 56.2(c) implemented by 21 CFR 868 Performance Standard for Electrode Lead Wires and Patient Cables.The device complies with IEC 601-1 sub-clause 56.2(c) implemented by 21 CFR 868 Performance Standard for Electrode Lead Wires and Patient Cables.
    Performance: The device performs within specifications.The BSM-2300A and BSM-6000 Bedside Monitors with the CGS-9001A Series Communication Gateway Server Accessory was subjected to safety and performance testing procedures. These tests verified that the device performed within specifications. (Note: Specific performance specifications are not detailed in this document.)
    Sterility: Not applicable.The device is not sterile.
    Patient Contact: Not applicable for direct contact.The device does not directly contact patients.
    Substantial Equivalence: Device is substantially equivalent to Nihon Kohden predicate device (K011918 and K080342).Nihon Kohden US Lab believes that the device is substantially equivalent to the Nihon Kohden predicate device as stated. The FDA issued a substantial equivalence determination.

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

    This information is not explicitly provided. The documentation refers to "safety and performance testing procedures" but does not detail the sample size (e.g., number of patients, number of alarm events tested) for these tests, nor the data provenance (country of origin, retrospective/prospective). Since the device is a communication gateway for alarm events, the testing would likely involve system integration and alarm transmission validation, rather than a clinical dataset in the traditional sense.

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

    This information is not provided. Given the nature of the device (a communication gateway accessory), the "ground truth" would likely involve technical validation of alarm transmission and accuracy, rather than clinical consensus by medical experts in diagnosing conditions.

    4. Adjudication method for the test set

    This information is not provided.

    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

    A multi-reader multi-case (MRMC) comparative effectiveness study was not done. This type of study is typically performed for diagnostic or AI-powered algorithms where human interpretation of medical images or data is involved. The CGS-9001A is an accessory to facilitate alarm notification and does not involve AI or direct human interpretation of complex medical data for diagnosis.

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

    This is not applicable in the context of an "algorithm only" as found in AI/ML devices. The device's primary function is to collect and forward alarm information. Performance testing would likely focus on the accuracy and reliability of this transmission, which is a standalone function of the accessory. The document states "These tests verified that the device performed within specifications," confirming a form of standalone performance evaluation for its intended function.

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

    The document does not explicitly state the type of "ground truth" used. For a communication gateway device, the ground truth would likely refer to the accurate transmission of alarm data as generated by the bedside monitors to a third-party system, verified against the actual alarm events occurring on the monitors. This would involve comparing the transmitted data with the source data rather than an external clinical ground truth like pathology or expert consensus.

    8. The sample size for the training set

    This information is not applicable and not provided. The CGS-9001A is a software product for alarm communication, not an AI/ML algorithm that requires a training set.

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

    This information is not applicable and not provided, as there is no training set for this device.

    Ask a Question

    Ask a specific question about this device

    K Number
    K082785
    Date Cleared
    2008-11-26

    (64 days)

    Product Code
    Regulation Number
    870.1025
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    NIHON KOHDEN AMERICA, INC.

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

    The device is intended to monitor, display and record physiological data to provide cardiac and vital signs monitoring within a medical facility. The device is intended to produce a visual record of the electrical signals produced by the heart and monitor the electrocardiogram to generate visible and/or audible alarms when an arrhythmia exists. The device is also intended to monitor heart rate, pulse rate, blood oxygen santuation (SpO2), noninvasive blood pressure (NIBP), invasive blood pressure (IBP), body temperature, Cardiac Output (CO), oxygen concentration (FiO2), Carbon dioxide Concentration (C02) and EtCO2 respiratory rate, BIS and inspired and expired anesthetic agents and gases including CO2, O2, N2O, Halothane, Isoflurane, Enflurane, Sevoofburane and Desflurane. Anesthetic agents and gases are detected using the cleared AG-920RA Anesthetic Agent Detection System K020046 cleared for distribution on July 23, 2002. The device also monitors Ventilators, CO2 Monitors, TOF Monitors, BIS Monitors and CCO/SvO2 Monitors .The device may generate an audible and/or visual alsommore a measured rate falls outside preset limits.

    Device Description

    Bedside Monitor, Patient Monitor, Cardiac Monitor, Vital Signs Monitor and Anesthesia Monitor.

    AI/ML Overview

    The provided text does NOT contain information about acceptance criteria or specific studies proving the device meets acceptance criteria in the format requested.

    The document is a 510(k) notification for a bedside monitor, primarily focusing on demonstrating substantial equivalence to a predicate device. It briefly mentions general performance testing and software validation.

    Here's what can be extracted, and what is missing based on your request:

    1. Table of Acceptance Criteria and Reported Device Performance:

    • Not available. The document states that "performance testing procedures" and "software validation" were performed and the "results confirmed that the device performed within specifications," but it does not detail these specifications (acceptance criteria) or the specific performance metrics achieved.

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

    • Not available. The document does not provide details on sample sizes for any test sets or the origin/nature of data used for testing (e.g., retrospective or prospective, country of origin).

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

    • Not available. There is no mention of expert-established ground truth or the involvement of experts in any testing described.

    4. Adjudication method for the test set:

    • Not available. No adjudication method is mentioned.

    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:

    • Not applicable/Not available. This device is a physiological patient monitor, not an AI-assisted diagnostic tool that would typically involve human readers. Therefore, an MRMC study and effect size for human reader improvement are not relevant or discussed.

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

    • Given that this is a bedside monitor with arrhythmia detection, it implies an algorithm operating in standalone mode. However, the document does not provide specific details or a dedicated "standalone study" report. It mentions "software validation tested the operation of the software function of the device," which indirectly supports standalone algorithm testing, but lacks specifics.

    7. The type of ground truth used:

    • Not available. The document does not specify the type of ground truth used for any testing. For a device like this, ground truth would typically be established against known physiological signals or reference equipment, but this is not detailed.

    8. The sample size for the training set:

    • Not available. The document does not mention any training sets, which is typical for a 510(k) for a device like this where the technology is largely established and the changes are minor, not involving new machine learning algorithm development from scratch.

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

    • Not applicable/Not available. As above, no training set is mentioned.

    Summary of available information related to performance testing:

    The document broadly states:

    • "The BSM-9100A Series Bedside Monitor device was subjected to tests for electromagnetic, environmental, safety and performance testing procedures."
    • "These tests verified the operation of the device."
    • "The software validation tested the operation of the software function of the device."
    • "The results confirmed that the device performed within specifications."

    However, these are very general statements and do not provide the detailed information requested regarding specific acceptance criteria, performance metrics, sample sizes, ground truth establishment, or expert involvement. This is common for 510(k) submissions focusing on substantial equivalence with minor changes, where detailed performance data might be referenced internally within the manufacturer's quality system but not explicitly detailed in the public 510(k) summary.

    Ask a Question

    Ask a specific question about this device

    K Number
    K071969
    Date Cleared
    2008-10-06

    (447 days)

    Product Code
    Regulation Number
    882.1870
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    NIHON KOHDEN AMERICA, INC.

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

    Nihon Kohden Sen-4100 Electric Stimulator is used for the intraoperative diagnosis of acute dysfunction in corticospinal tract axonal conduction brought about by mechanical trauma (traction, shearing, laceration, or compression) or vascular insufficiency.

    Device Description

    The SEN-4100A is the stimulator to output electrostimulation pulses. It conducts the constant voltage stimulation that is necessary for MEP (Motor Evoked Potential) measurement, from an electrophysiological viewpoint, diagnosing and analyzing the neuromuscular action potential for a patient provided with anesthesia care in an operating room.

    AI/ML Overview

    The provided text describes the Nihon Kohden SEN-4100 Electric Stimulator, a device used for intraoperative diagnosis of acute dysfunction in corticospinal tract axonal conduction. However, the document does not contain specific acceptance criteria or details of a study that quantifies device performance in terms of metrics like sensitivity, specificity, accuracy, or other performance characteristics.

    Instead, the submission focuses on demonstrating substantial equivalence to a predicate device (Digitimer D185 Multipulse Cortical Stimulator) based on technological characteristics and compliance with electrical safety and performance standards.

    Here's an attempt to answer the questions based on the available information, noting where data is absent:


    1. Table of acceptance criteria and the reported device performance

    Acceptance CriteriaReported Device Performance
    Not explicitly defined in terms of specific performance metrics (e.g., accuracy, sensitivity, specificity, or quantitative output precision).The device's operation, software, and hardware were confirmed to be in accordance with design specifications through design validation.
    Compliance with electrical safety and performance standards (e.g., IEC 60601-1, IEC 60601-1-2).The device was subjected to electromagnetic, environmental, safety, and performance testing procedures, which "verified the proper operation of the device." Specific results of these tests (e.g., measured electromagnetic emissions/immunity levels, environmental withstand limits, actual safety parameter readings) are not detailed within this summary.
    Substantial Equivalence to predicate device (Digitimer D185 Multipulse Cortical Stimulator, K020400).Nihon Kohden believes the SEN-4100 is "substantially equivalent" to the predicate, stating it performs the same function (outputting electrostimulation pulses for MEP measurements and neuromuscular action potential analysis) for the same intended use.

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

    • The document does not mention any clinical "test set" in the context of device performance evaluation (e.g., for diagnostic accuracy). The testing described appears to be engineering validation and verification.

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

    • Not applicable. The submission focuses on substantial equivalence and engineering testing, not a clinical study involving ground truth establishment by experts for a test set.

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

    • Not applicable. No clinical test set or adjudication process is described.

    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

    • Not applicable. The device is an electrical stimulator, not an AI or imaging diagnostic aid, and therefore, an MRMC study is not relevant to its stated function or the information provided.

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

    • Not applicable. This device is an electrical stimulator designed to be used in conjunction with other clinical devices for neurological function (EMG/Stimulator for evoked reaction) and would always involve human operation/interpretation. There is no "algorithm only" performance reported as it's a hardware device.

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

    • For the engineering validation, the "ground truth" was likely the design specifications and established engineering standards (e.g., IEC standards). For the claim of "proper operation," it implies that the device's output and characteristics (e.g., voltage, pulse shape) met predefined engineering targets. No medical or biological ground truth (like pathology or clinical outcomes) was used for performance assessment in this submission.

    8. The sample size for the training set

    • Not applicable. The device is not a machine learning or AI algorithm, so there is no concept of a "training set" in the context of its development or submission.

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

    • Not applicable. As there is no training set mentioned, this question is not relevant.

    In summary, the K071969 submission for the Nihon Kohden SEN-4100 Electric Stimulator primarily relies on demonstrating compliance with recognized electrical safety and performance standards, and substantial equivalence to a legally marketed predicate device based on technological characteristics and intended use. It does not present a study with specific clinical performance metrics (like accuracy or sensitivity) derived from a test set with established ground truth. The "study" referenced is the design validation and engineering testing (electromagnetic, environmental, safety, and performance testing) which "verified the proper operation of the device" according to design specifications and relevant voluntary industrial standards.

    Ask a Question

    Ask a specific question about this device

    K Number
    K080546
    Date Cleared
    2008-08-29

    (183 days)

    Product Code
    Regulation Number
    882.1400
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    NIHON KOHDEN AMERICA, INC.

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

    The EEG-1200A Series Neurofax is intended to record, measure and display cerebral and extracerebral activity for EEG and Sleep Studies. These data may be used by the clinician in Sleep Disorder, Epilepsies and other related disorders as an aid in diagnosis. The device is intended for use by medical personnel in any location within a medical facility, laboratory, clinic or nursing home or outside of a medical facility under direct supervision of a medical professional.

    Device Description

    The EEG-1200A Electroencephalograph is the instrument to provide the information for intervention to utilize derivation, recording, analysis, or each combination of the brain's action potential. The instrument can measure the vital signal (including ECG waveform, EMG waveform, respiration waveform, ocular motility, SpO2 and CO2) in relation to EEG examination and display the waveform on the screen changing the montage and amplifier conditions. In addition, measurement data is available to file into the electric media. Changing the montage and amplifier conditions, then record to the printer, previews the measured data filed into the electric media. EEG data analysis is also executed to use the analysis software.

    AI/ML Overview

    The provided text describes the Nihon Kohden EEG-1200A Series Neurofax, an electroencephalograph (EEG) device. It includes a 510(k) summary, intended use, and a comparison to a predicate device. However, it does not contain information about specific acceptance criteria, a detailed study proving device performance against such criteria, sample sizes for test or training sets, ground truth establishment, expert qualifications, adjudication methods, or MRMC studies for AI devices.

    The "study" mentioned in the document refers to engineering verification and validation testing, not clinical performance studies with human subjects or AI-specific evaluations.

    Therefore, I will extract relevant information from the provided text to construct the table and address the questions as much as possible, indicating when information is "Not provided" by the source.


    Acceptance Criteria and Reported Device Performance

    Acceptance Criteria (Specified in 510(k) context as "Technological Characteristics" comparable to predicate)Reported Device Performance (New Device: EEG-1200A Series Neurofax)
    Number of channels32
    Noise Level (0.53 to 60 Hz)
    Ask a Question

    Ask a specific question about this device

    K Number
    K073550
    Date Cleared
    2008-03-28

    (101 days)

    Product Code
    Regulation Number
    870.1025
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    NIHON KOHDEN AMERICA, INC.

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

    The Prefense EDNS-9000 Series Central Nurse Station is intended for use by medical professionals to provide cardiac and vital signs monitoring for multiple patients within a medical facility.

    The Prefense EDNS-9000 Series Central Nurse Station will display and record physiological data from up to forty telemetry receivers/transmitters and generates an alarm when a measured parameter falls outside a preset limit or when an arrhythmia is detected. Arrhythmia detection and alarm determination are functions of the telemetry receivers/transmitters or individual beside monitor.

    The Prefense EDNS-9000 Series Central Nurse Station is intended for cardiac and vital signs monitoring for multiple patients. The device will display and record physiological data from telemetry receivers/transmitters and alarms when a measured parameter falls outside a preset limit or when an arrhythmia is detected by the telemetry unit.

    This product will be available for use by medical personnel on all patient populations with a medical facility.

    Device Description

    The Prefense EDNS-9000 Series Central Nurse Station is intended for use by medial professionals to provide cardiac and vital signs monitoring for multiple patients within a medical facility. The Prefense EDNS-9000 Series Central Nurse Station will display and record physiological data from up to forty telemetry receiver/transmitters and generates an alarm when a measured parameter falls outside a pre-set limit or when life threatening arrhythmia is detected. Arrhythmia detection and alarm determination are functions of the telemetry receivers (Model ORG-9700 Multiple Patient Receiver, per 510K K071058 Commercial distribution certification dated June 29, 2007) transmitter (Model ZS-940PA, per 510(k) K043517 Commercial Distribution certification dated February 3, 2005).

    The new device receives a small subset (non-invasive telemetry parameters) all of the same information as the predicate device, i.e., receives physiological signal from telemetry transmitters/receivers from ORG 9700 Multiple Patient Receiver signal simultaneously, receives and displays physiological information. generates audible and/or visual alarm indictors when an alarm violation is detected by the telemetry units, stores waveforms for review and printing as full disclosure, stores tabular and graphical trending data for review and printing, provides network communications using commercially available LAN/WAN products, provides remote data access through NetProse access software and records and prints physiological patient data.

    AI/ML Overview

    I am sorry, but based on the provided text, there is no information about specific acceptance criteria or a study proving the device meets them, as requested in your prompt.

    The document discusses the regulatory submission for the NIHON KOHDEN NKUS LAB PREFENSE EDNS-9000 SERIES CENTRAL NURSE STATION, focusing on its substantial equivalence to a predicate device. It briefly mentions "design validation confirmed the operation of the software and hardware of the device is in accordance to the design specifications" and that the device "was subjected to electromagnetic, environmental, safety and performance testing procedures." However, it does not provide details on:

    • A table of acceptance criteria and reported device performance.
    • Sample sizes, data provenance, number of experts, or adjudication methods for any test set.
    • Whether a multi-reader multi-case (MRMC) comparative effectiveness study was done.
    • Whether a standalone performance study was done.
    • The type of ground truth used for any evaluations.
    • Sample size for training sets or how ground truth was established for them.

    The device's description clarifies that "Arrhythmia detection and alarm determination are functions of the telemetry receivers (Model ORG-9700 Multiple Patient Receiver, per 510K K071058 Commercial distribution certification dated June 29, 2007) transmitter (Model ZS-940PA, per 510(k) K043517 Commercial Distribution certification dated February 3, 2005)." This indicates that the core arrhythmia detection logic resides in separate, previously cleared devices, and the Central Nurse Station primarily displays and records data from these units.

    Therefore, I cannot fulfill your request for details on acceptance criteria and study proving their achievement from the provided text.

    Ask a Question

    Ask a specific question about this device

    K Number
    K080342
    Date Cleared
    2008-02-26

    (18 days)

    Product Code
    Regulation Number
    870.1025
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    NIHON KOHDEN AMERICA, INC.

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

    The device is intended to monitor, display and record physiological data to provide cardiac and vital signs monitoring within a medical facility. The device is intended to produce a visual record of the electrical signals produced by the heart and monitor the electrocardiogram to generate audible and/or visible alarms when an arrhythmia exists. The device is also intended to monitor heart rate, blood oxygen saturation (SpO2), non-invasive blood pressure (NIBP), continuous non-invasive blood pressure (CNIBP), invasive blood pressure (IBP), body temperature, BIS, Cardiac Output (CO), oxygen concentration (FiO2), carbon dioxide concentration (CO2) and EtCO2, respiratory rate and inspired and expired anesthetic agents and anesthetic gases including N20, Halothane, Isoflurane, Enflurane, Sevoflurane and Desflurane. The device may generate an audible and/or visual alarm when a measured rate falls outside preset limits. This device may also be used to condition and transmit physiological signals via radio frequency.

    Device Description

    The device is intended to monitor, display and record physiological data to provide cardiac and vital signs monitoring within a medical facility. The device is intended to produce a visual record of the electrical signals produced by the heart and monitor the electrocardiogram to generate visible and/or audible alarms when an arrhythmia exists. The device is also intended to monitor heart rate, pulse rate, blood oxygen saturation (SpO2), non-invasive blood pressure (NIBP), invasive blood pressure (IBP), body temperature, Cardiac Output (CO), oxygen concentration (FiO2), CO2 and EtCO2, respiratory rate, BIS and inspired and expired anesthetic agents and gases including CO2, O2, N2O, Halothane, Isoflurane, Enflurane, Sevoflurane and Desflurane. Anesthetic agents and gases are detected using the cleared AG-920RA Anesthetic Agent Detection System. The device can interface to external equipment to display numerical and waveform data and alarms from the external devices. Supported external devices include AG-920RA Anesthetic Agent Detection System, Ventilators, CO2 Monitors, TOF Monitors, BIS Monitors, CCO/SvO2 Monitors and continuous NIBP Monitors. The device may generate an audible and/or visual alarm when a measured rate falls outside preset limits. This device may also be used to condition and transmit physiological signals via radio frequency.

    AI/ML Overview

    The provided text is a 510(k) Premarket Notification for the NIHON KOHDEN AMERICA, INC. BSM-6000 Series Bedside Monitor. This document is a regulatory submission for premarket approval of a medical device and does not contain the details of a study with acceptance criteria and reported device performance in the format requested.

    Regulatory submissions like this typically refer to compliance with recognized standards (e.g., IEC-60601-1) and internal testing to verify specifications, but they do not typically include detailed study designs, sample sizes for test sets, ground truth establishment, or comparative effectiveness with human readers as would be found in a clinical study report or peer-reviewed publication.

    Therefore, I cannot provide the requested table and information based on the input text. The text states:

    • "The BSM-6000 Series device was subjected to tests to electromagnetic, environmental, safety and performance testing procedures. These tests verified the operation of the device. The software validation tested the operation of the software function of the device. The results confirmed that the device performed within specifications."

    This indicates that internal testing was done, but the specific acceptance criteria, reported performance, sample sizes, and other detailed study information are not present in this 510(k) summary. The purpose of this document is to demonstrate substantial equivalence to a predicate device, not to present a detailed clinical study for novel performance claims.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 6