Search Results

The E3 and Profile system is an electrodiagnostic device used to generate photic signals and to measure and display the electrical signals generated by the retina and the visual nervous system. It displays digitized electroretinogram (ERG), visual evoked potential (VEP) and sensory electro-oculogram (EOG) signals, power spectra and topographic maps. These functions are controlled and interpreted by trained medical professionals, for use with patients who are experiencing visual system abnormalities.

Photopic stimuli are presented to the patient using LEDs or a monitor, using various number of elements in separately stimulated fields. Various modes are available for preferential stimulation of different retinal mechanism and isolation of signal from different retinal lavers. Data is recorded by up to 5 recording channels using conventional EEG electrodes (not provided with the device). During the period of time that the system is acquiring data (1-20 minutes), there is a real time display of the raw and processed data presented to the user. Once the resulting individual waveforms are acquired, the signals are analyzed by software using algorithms for spatial filtering and artifact rejection. Data may be presented in a number of forms, including waves recorded at each of the points tested, color plots, or 3D topographical representation.

The provided text describes the regulatory clearance of a medical device, the E3 and Profile system, but it does not contain the detailed information necessary to answer the questions about acceptance criteria and study proving device performance in the context of an AI/ML device.

The document states:

• The device is an electrodiagnostic device used to generate photic signals and to measure and display electrical signals generated by the retina and visual nervous system (ERG, VEP, EOG).
• It displays digitized signals, power spectra, and topographic maps.
• These functions are controlled and interpreted by trained medical professionals.
• The device was tested against various IEC and ISO standards related to medical electrical equipment, risk management, usability, and software life cycle.

Crucially, there is no mention of an AI/ML component in the E3 and Profile system, nor any studies that would involve AI-specific acceptance criteria, human reader improvement with AI assistance, standalone AI performance, or ground truth establishment relevant to AI model training and testing. The "software" mentioned appears to be for data acquisition, processing, and display, interpreted by human experts, rather than an AI performing diagnostic tasks.

Therefore, I cannot provide the requested information. The document focuses on establishing substantial equivalence to a predicate device based on device features and specifications and intended use, not on the performance of an AI algorithm against specific acceptance criteria.

Ask a specific question about this device

The Vision Monitor MonCvONE system is a non-invasive medical device used to generate photic stimulations and to register the responses including electrical responses generated by the retina and the visual nervous system in addition to psychophysical and pupillary responses. It displays digitized electroretinogram (ERG), visual evoked potential (VEP), sensory electro-oculogram (EOG), light and dark adapted perimetry thresholds, dark adaptometry, full field stimulus threshold (FST), photo aversion thresholds (PAT), pupillometry as curves, power spectra and topographic maps. These functions are controlled and interpreted by trained medical professionals.

Photopic stimuli are presented to the patient on a hemispherical cupola. Various modes are available for preferential stimulation of different visual functions. Electrophysiological data is recorded by up to 5 recording channels using conventional EEG electrodes (not provided with the device). Psychophysical responses are recorded with a press button and pupillometry responses recorded with an eye tracker.

During the period of time that the system is acquiring data (1-20 minutes), there is a real time display of the raw and processed data presented to the operator. Once the resulting individual responses are acquired, the signals are analyzed by software using algorithms for spatial filtering and artifact rejection. Data may be presented in a number of forms, including waves recorded at each of the points tested, color plots, or 3D topographical representation.

Here's an analysis of the provided text, outlining the acceptance criteria and the study details for the Vision Monitor-MonCvONE device:

Acceptance Criteria and Device Performance

Study Details

Based on the provided text, the submission describes non-clinical testing rather than a clinical study involving human patients to establish the device's performance against ground truth.

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

   • The document describes non-clinical bench testing including technical, functional, and compatibility tests. It does not mention a test set of patient data with a specific sample size. The testing focuses on the device's adherence to standards and its internal components' functionality.
   • Data provenance: Not applicable as no patient data test set is described.

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

   • Not applicable. The document describes engineering and safety testing against defined standards and specifications, not interpretation of medical data by experts to establish ground truth for a test set.

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

   • Not applicable. There is no mention of a test set requiring adjudication. The testing described is based on engineering principles and regulatory standards.

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. The document does not describe an MRMC study, nor does it indicate that the device involves AI for interpretation by human readers. The device generates and displays physiological data; "These functions are controlled and interpreted by trained medical professionals."

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

   • The document describes the device as a system that generates photic stimulations and registers responses, with software for analysis and display. However, it explicitly states, "These functions are controlled and interpreted by trained medical professionals." This indicates that the device is intended for use with human-in-the-loop interpretation, and no standalone (algorithm-only) performance claim or study is detailed. The described tests are about the device's performance in generating and recording data, and its software's functionality, not its diagnostic accuracy in an unsupervised manner.

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

   • The ground truth for the described testing is based on engineering specifications, regulatory standards (e.g., IEC 60601-1, ISO 14971), and functional requirements for generating, recording, and processing electrophysiological signals. There is no mention of a clinical ground truth (like pathology or expert consensus on patient cases) being used for the performance claims in this submission.

7. The sample size for the training set:

   • Not applicable. The device is a measurement and display system, not an AI or machine learning algorithm that requires a training set of data.

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

   • Not applicable, as there is no training set mentioned for this device.

Ask a specific question about this device

LED PHOTIC System is an accessory indicated for photic activation of brain during the electroencephalographic (EEG) studies. It always has to be used in combination with an EEG system, in order to evaluate particular anomalies of the brain activity due to the intermittent photic stimulation. The product must be used only by qualified personnel (physicians or technicians of neurophysiopathology) for the execution of EEG exams in a professional environment.

LED PHOTIC System is an accessory indicated for photic activation of brain during the electroencephalographic(EEG) studies. It is to be used in combination with an EEG system, in order to evaluate particular anomalies of the brain activity due to the intermittent photic stimulation.

The LED PHOTIC Systemis managed by the EEG system software for setting some parameters, IC, and the power supply called LED PHOTIC IC POWER is an integral part of the LED PHOTIC System.

The provided text describes the regulatory clearance for a medical device called "LED PHOTIC System" and its comparison to a predicate device. However, it does not contain information about a study proving the device meets specific acceptance criteria in the context of an AI/ML-driven medical device.

The document is a 510(k) premarket notification summary for a Class II medical device, which is an accessory for EEG studies to provide photic stimulation. The performance testing mentioned focuses on safety standards (electrical safety, usability, EMC compliance, photobiological safety), not on accuracy, sensitivity, specificity, or other performance metrics typically associated with AI/ML device evaluations.

Therefore, I cannot fulfill your request for the following information based on the provided text:

• A table of acceptance criteria and the reported device performance: The document only lists safety standard compliance, not performance criteria for diagnostic accuracy or similar AI/ML metrics.
• Sample size used for the test set and the data provenance: No such testing is described for diagnostic performance. The safety tests would have their own sample sizes (e.g., number of units tested) but these are not provided.
• Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable, as there's no diagnostic performance study described.
• Adjudication method for the test set: Not applicable.
• 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, as the device is a photic stimulator, not an AI/ML diagnostic aid.
• If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable.
• The type of ground truth used: Not applicable.
• The sample size for the training set: Not applicable (no AI/ML algorithm mentioned).
• How the ground truth for the training set was established: Not applicable.

The "Performance Testing" section only states:

• The LED PHOTIC System was tested and found compliant to the following safety standards:
  • IEC 60601-1:2005+A1:2012: Medical Electrical safety
  • IEC 60601-1-6:2010+A1:2013: Usability
  • IEC 60601-2:2014: EMC Compliance
  • IEC 62471:2006: Photobiological Safety

This submission is about establishing substantial equivalence to a predicate device (Lifelines Photic Stimulator K101691) primarily based on shared intended use, similar operational principles, and compliance with general medical device safety standards. It is not an evaluation of an AI-driven system.

Ask a specific question about this device

The Vision Monitor MonPackONE system is an electrodiagnostic device used to generate photic signals and to measure and display the electrical signals generated by the retina and the visual nervous system. It displays digitized electroretinogram (ERG), visual evoked potential (VEP) and sensory electro-oculogram (EOG) signals, power spectra and topographic maps. These functions are controlled and interpreted by trained medical professionals.

Photopic stimuli are presented to the patient on a LCD-screen at a various number of elements in separately stimulated fields. Various modes are available for preferential stimulation of different retinal mechanism and isolation of signal from different retinal layers. Data is recorded by up to 5 recording channels using conventional EEG electrodes (not provided with the device).

During the period of time that the system is acquiring data (1-20 minutes), there is a real time display of the raw and processed data presented to the user. Once the resulting individual waveforms are acquired, the signals are analyzed by software using algorithms for spatial filtering and artifact rejection. Data may be presented in a number of forms, including waves recorded at each of the points tested, color plots, or 3D topoqraphical representation.

The provided text is a 510(k) summary for the Vision Monitor MonPackONE device and does not contain information about the acceptance criteria and study proving a device meets those criteria in the context of an AI/ML algorithm. The document primarily focuses on establishing substantial equivalence to a predicate device for a medical device that measures and displays electrophysiological signals from the retina and visual nervous system.

Therefore, I cannot extract the requested information regarding acceptance criteria, device performance, sample sizes, ground truth establishment, or multi-reader multi-case studies, as these types of details typically apply to studies validating AI/ML diagnostic tools, which is not the subject of this 510(k) summary.

Ask a specific question about this device

The Nurochek System is intended for prescription use in healthcare facilities or clinical research environments for subjects ages 14 years and older. The Nurochek System is indicated for the generation of visual evoked potentials (VEPs) and to acquire, transmit, display and store electroencephalograms (EEGs) during the generation of VEPs. The Nurochek System only acquires and displays physiological signals: no claims are being made for use as a diagnostic criterion or for the analysis of the acquired signals with respect to the accuracy, precision and reliability.

The Nurochek System combines hardware, firmware and software to generate and acquire physiological signals, specifically, VEPs. These VEPs are generated by a visual stimulus delivered through the Nurochek headset worn by the subject. This visual stimulus is a short-duration flash of white light. The Nurochek headset acquires the VEPs from the rear of the head and transmits the resulting EEG to the Nurochek software application to be displayed to the user and stored. These acquired signals are intended to be analyzed by a Physician. The Nurochek System operates on the principles of generating VEPs via photic simulation and acquiring the VEPs via EEG. Photic stimulation is provided through short-duration flashes of white light from multiple LEDs located in the front of the headset to direct the stimulus into the subject's eyes. The VEPs are acquired by an EEG comprising of a total of 5 electrode interfaces with hydrophilic foam cylinders saturated with saline solution to provide electrical contact to the subject's scalp. A Bluetooth receiver and transmitter located within the Nurochek headset allows it to communicate with and be controlled by the Nurochek software application. The Nurochek software application provides a graphical user interface which allows: Collection of the subject details and consent, Initiation of a study and tracking of patient information, Acquisition and transmission of signals wirelessly to and from the headset, Display of the contact quality of electrodes to the subject's scalp, Recording, processing and display of EEG signals received from the headset, and Manage previous EEG recordings of VEPs.

The provided document, a 510(k) Premarket Notification for the Nurochek System, focuses on demonstrating substantial equivalence to predicate devices rather than proving the device meets specific acceptance criteria through a detailed clinical study with performance metrics. While it mentions non-clinical performance data and a small clinical study, it does not explicitly provide a table of acceptance criteria with corresponding performance data in the format requested.

The document states that "The Nurochek System only acquires and displays physiological signals: no claims are being made for use as a diagnostic criterion or for the analysis of the acquired signals with respect to the accuracy, precision and reliability." This statement is critical as it limits the scope of claims and thus the type of performance data required for acceptance. The study described focuses on functional equivalence in signal acquisition rather than diagnostic accuracy.

Despite this, I can extract information related to the device's performance based on the functional capabilities and a small clinical study mentioned.

Here's an attempt to answer your request based on the provided text, acknowledging the limitations in scope for a device that "only acquires and displays physiological signals and makes no claims in relation to diagnoses."

1. Table of acceptance criteria and the reported device performance:

Since the document defines the device as one that "only acquires and displays physiological signals" and makes "no claims ... for the analysis of the acquired signals with respect to the accuracy, precision and reliability," the acceptance criteria are not in terms of diagnostic performance (e.g., sensitivity, specificity). Instead, they are related to the functional equivalence of signal acquisition and display compared to a benchmark device, and safety/technical compliance.

• Dynamic Range: Nurochek: +/- 187,500 μV (superior) vs. Predicate: +/- 1000μV.
• Resolution: Nurochek: 0.02μV (superior/more accurate) vs. Predicate: 0.03μV.
• Peak to Peak Noise: Nurochek: 1.97μV (typical) (lower/superior) vs. Predicate: 3.7μV (typical).
• Common Mode Rejection Ratio: Nurochek: 110 dB vs. Predicate: 110 dB (same).
• Input Impedance: Nurochek: 1GOhm vs. Predicate: 100GOhm (Both exceed OSET recommendation of 10 MOhm).
• Impedance Check Functionality: Both have impedance check. |

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

• Test Set Sample Size: 20 participants for the clinical study comparing SSVEP detection.
• Data Provenance: The document does not explicitly state the country of origin for the clinical study data or if it was retrospective or prospective. Given the submitter (Cryptych Pty Ltd) is based in North Sydney, NSW, Australia, and the submission is to the FDA, it's possible the study was conducted in Australia, but this is not confirmed. It was a "clinical study," which typically implies prospective data collection, but this is also not definitively stated as "prospective."

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

• The document mentions using the "clinical EEG Compumedics Grael EEG as a reference device and benchmark" for the clinical study. It does not mention experts establishing a "ground truth" in the traditional sense of labeling data (e.g., for diagnostic AI). The comparison was presumably based on the raw or processed signals from the two devices themselves.
• Given the device "only acquires and displays physiological signals" and makes "no claims ... for the analysis of the acquired signals with respect to the accuracy, precision and reliability," the concept of "ground truth" for diagnostic accuracy is not applicable as per the device's intended use. The "ground truth" essentially refers to the output of the benchmark medical device.

4. Adjudication method for the test set:

• Not applicable as the study involved comparing raw physiological signal acquisition between two devices, not interpretation or diagnosis requiring expert consensus/adjudication. The statement "both systems functioned identically in their ability to detect SSVEPs" suggests a direct comparison of the acquired signals or derived metrics.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

• No, a multi-reader multi-case (MRMC) comparative effectiveness study was not performed.
• This device is not an AI-assisted diagnostic tool, but rather a device for acquiring and displaying physiological signals (VEPs and EEGs). Therefore, a study on human reader improvement with AI assistance is not relevant to its stated indications for use.

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

• The non-clinical performance data (electrical safety, light safety, biocompatibility, cleaning, mechanical, firmware/software) represent standalone testing of the device's technical aspects and capabilities.
• The clinical study was a comparison of signal acquisition between the Nurochek System and a reference EEG device; it wasn't an "algorithm-only" performance study in an AI context, but rather a verification of the physiological signal acquisition system.

7. The type of ground truth used:

• The "ground truth" for the clinical study was the performance of a cleared predicate/reference medical device (Compumedics Grael EEG) in detecting SSVEPs. This falls under the category of "comparison to a reference standard medical device."
• For the non-clinical tests, the "ground truth" was compliance with established international and national standards (e.g., IEC, ISO, ANSI, FDA guidances).

8. The sample size for the training set:

• The document implies that the device "only acquires and displays physiological signals," and the software manages and displays these. It does not describe a machine learning model that would require a "training set" in the sense of supervised learning for classification or prediction. Therefore, the concept of a training set for an AI model is not applicable here. The software validation refers to standard software engineering verification and validation activities (IEC 62304), not AI model training.

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

• As a training set for an AI model is not applicable, this question is not relevant.

Ask a specific question about this device

The Natus Photic Stimulator is indicated for photic activation of the EEG study and in the generation of visual evoked potentials.

The Natus Medical Incorporated (Natus) DBA Excel-Tech Ltd. (XLTEK) Photic Stimulator is used by trained medical staff in a medical environment to apply photic flashes to the patient during neurophysiology studies such as electroencephalographic (EEG) studies, where it is used as an activation to test photo-sensibility related to epilepsy.

The Natus Photic Stimulator is typically used by EEG technicians in the hospital environment in fixed, mobile or portable systems, and with patients of all ages. The lamp head assembly is mounted on an arm allowing easy placement at 30 cm away from the patient's face. The arm is ergonomically designed so that the lamp can be move and rotated in the direction of the patient using a handgrip on the lamp.

Trigger pulses applied to the trigger input of the Natus Photic Stimulator generate 1 millisecond photic flashes at specific frequencies, typically in the range of 0.5 Hz to 60 Hz by a white light emitting diode (LED) lamp. The basic operating mode consists of generating a single flash per trigger pulse applied. Flash intensity has a maximum range from 22,000 lux up to 75,000 lux measured at 30 cm from the LED lamp at the position of highest intensity and 3,520 lux to 12,000 lux calculated at 75cm. The frequency and intensity of the flash is controlled by the acquisition software.

It can also be used along with evoked potential devices for stimulating visual evoked potentials.

This document describes the Natus Photic Stimulator, a device used in neurophysiology studies. The information provided focuses on the device's technical specifications and compliance with regulatory standards, rather than clinical performance or AI integration.

Therefore, the following information regarding acceptance criteria and study details cannot be fully extracted as it pertains to clinical performance and AI, which are not the primary focus of this submission. The document primarily reports on technical and safety performance testing.

Here's what can be extracted based on the provided text:

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

The document does not detail specific acceptance criteria for clinical performance (e.g., sensitivity, specificity, accuracy) akin to what would be provided for a diagnostic AI device. Instead, the "acceptance criteria" are compliance with various technical and safety standards.

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

This information is not provided. The performance testing described is bench testing against technical and safety standards, not a clinical study on a patient population.

3. 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)

This is not applicable as the submission describes device safety and performance testing against engineering standards, not a clinical evaluation requiring expert interpretation of ground truth in patient data.

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

This is not applicable. The performance testing involves engineering verification and validation, not clinical adjudication of patient cases.

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

There is no mention of AI assistance or a MRMC study in this document. This submission is for a photic stimulator, which is a hardware device for neurophysiology studies, not an AI software.

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

This is not applicable. The device is a hardware photic stimulator, and the performance testing focuses on its compliance with safety and technical standards as a standalone physical device.

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

The "ground truth" for the device's performance is compliance with established international and national technical, electrical, electromagnetic, usability, and photobiological safety standards (e.g., IEC 60601 series, IEC 62366, IEC 62471, ANSI Z80.36). This is verified through objective measurements and tests against those standards, not through clinical ground truth like pathology or expert consensus on patient outcomes.

8. The sample size for the training set

This is not applicable. This device is not an AI algorithm trained on data.

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

This is not applicable. This device is not an AI algorithm trained on data.

Ask a specific question about this device

Ask a specific question about this device

The SightSaver™ is an evoked response photic stimulator that is used to apply a visible light stimulus to a patient's eyes for use in evoked response measurements or for electroencephalogram (EEG) activation.

The SightSaver™ Visual Stimulator is designed to be used in hospital and clinical settings by trained medical personnel and is for prescription use only.

The SightSaver™ Visual Stimulator is used to expose the eyes to light in order to elicit a physiological response. LEDs inside the device flash light at the eye. The SightSaver™ Visual Stimulator is disposable and made with specifically shaped self-sticking adhesive foam padding which conforms to the periocular region of the patient's face.

The SightSaver™ is designed to be connected to a triggering and acquisition system which records, analyzes, or processes the patient's responses.

The triggering and acquisition system is not included as part of the 510(k).

Here's a breakdown of the acceptance criteria and study information based on the provided text, focusing on what is explicitly stated:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text does not explicitly detail a table of acceptance criteria with corresponding device performance for the SightSaver™ Visual Stimulator. The submission focuses on demonstrating substantial equivalence to predicate devices, rather than meeting specific performance metrics against predefined criteria.

However, it does implicitly suggest one key performance/safety criterion that the device meets or exceeds:

The document states: "The SightSaver™ Visual Stimulator has been tested to higher safety performance standards compared with the predicate devices but is the same as the predicate devices in: Intended use, Overall design and form factor, Technological characteristics." This implies that while specific performance metrics aren't listed, the device met or exceeded relevant safety and performance standards, notably ISO 15004-2, which the predicates did not.

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

The provided 510(k) summary does not contain any information about a test set sample size or data provenance (e.g., country of origin, retrospective/prospective) for a clinical study evaluating the SightSaver™ Visual Stimulator's performance. The submission primarily relies on a comparison to predicate devices and adherence to standards.

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

As there is no mention of a test set or clinical study in the provided text, there is no information regarding the number or qualifications of experts used to establish ground truth.

4. Adjudication method for the test set

Similarly, due to the absence of a described test set or clinical study, there is no information about an adjudication method.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, and if so, what was the effect size of how much human readers improve with AI vs without AI assistance

The SightSaver™ Visual Stimulator is described as an "evoked response photic stimulator" and not an AI-powered diagnostic device designed to assist human readers. Therefore, no MRMC comparative effectiveness study involving AI assistance for human readers was done or is relevant to this device.

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

The device is a hardware stimulator and not an algorithm. Therefore, no standalone algorithm performance study was done or is relevant. The device functions by exposing eyes to light for evoked response measurements, and its performance would be assessed through its electrical and optical characteristics, not as a standalone diagnostic algorithm.

7. The type of ground truth used

Since no clinical study evaluating diagnostic accuracy or a similar measure is described, no specific type of ground truth (e.g., expert consensus, pathology, outcomes data) for such a study is mentioned. The "ground truth" for the device's function is its ability to produce a visible light stimulus according to specifications for evoked response measurements or EEG activation.

8. The sample size for the training set

The provided text does not contain any information about a training set since the device is a hardware stimulator and not a machine learning algorithm.

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

As there is no mention of a training set, there is no information on how ground truth for a training set was established.

Ask a specific question about this device

Electrophysiological Test Unit for quantifying the response to visual stimulation by measuring the Visual Evoked Potential.

The Visionsearch1 System consists of specialist software and the supporting computer and peripherals. The System displays multifocal visual patterns to evoke response in the retina which are transmitted to the visual cortex. The System then detects responses in the visual cortex using specific, validated third party EEG electrodes and biological amplifier. After analyzing the EEG, the System displays the electrical response from each segment of the retina. It also allows the user to compare the response time between eyes and compare an individual's measurements to those from a set of data that the user has compiled as reference.

The Visionsearch1 System is an electrophysiological test unit intended for quantifying responses to visual stimulation by measuring Visual Evoked Potentials (VEP).

1. Table of Acceptance Criteria and Reported Device Performance

The provided document does not explicitly state quantitative acceptance criteria or a specific study to prove the device meets these criteria in the traditional sense of a clinical trial with performance metrics like sensitivity, specificity, or accuracy.

Instead, the submission for the Visionsearch1 System focuses on demonstrating substantial equivalence to a predicate device, the RETIScan/RETIPort (K023525). The effectiveness is asserted through compliance with established standards and comparison of technological characteristics.

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

The document does not describe a clinical performance study with a specific "test set" in terms of patient data. The validation discussed is primarily related to software functionality and technical equivalence.

• No "test set" of patient data is explicitly mentioned for performance evaluation.
• The data provenance is not applicable as no specific patient data test set is used to demonstrate performance.

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

Not applicable. No clinical test set with ground truth established by experts is described in this submission.

4. Adjudication method for the test set

Not applicable. No clinical test set requiring adjudication 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 Visionsearch1 System is a diagnostic device for measuring VEP, not an AI-assisted diagnostic tool for interpretation by human readers. Therefore, an MRMC study comparing human reader performance with and without AI assistance is not relevant to this device's submission.

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

This submission does not detail a standalone performance study in the context of an algorithm's diagnostic output. The device itself is standalone in terms of generating and analyzing electrophysiological signals. Its "performance" is assessed through its technical specifications, compliance with standards, and functional equivalence to the predicate, rather than an independent diagnostic accuracy study using a clinical dataset. The "independent laboratory verification of software functionality" implies a form of standalone testing, but not clinical performance.

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

Not applicable in the context of a clinical performance study for diagnostic accuracy. The "ground truth" for the device's development and validation appears to be the established technical and functional performance of the predicate device and compliance with regulatory standards for medical device software and safety.

8. The sample size for the training set

Not applicable. The Visionsearch1 System measures physiological responses, it is not an AI/ML algorithm that is "trained" on a dataset of patient images or clinical data.

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

Not applicable, as there is no training set for an AI/ML algorithm described.

Ask a specific question about this device

The NOVA is an electrophysiological device that generates photic stimuli, and records, processes and analyzes the resultant visual evoked potential (VEP) signals to provide information about the visual system structural and neural abnormalities.

Checkerboard, Horizontal grating, Vertical grating, Sinusoidal grating, Flash, monochromatic pattern onset or color pattern onset Contrast Photic stimuli are presented to the patient on a calibrated computer monitor at various numbers of elements in separately stimulated fields. The fields are varied in spatial size over a number of cycles. The fields are also phase reversed at different temporal frequencies. The signals are analyzed by the software algorithm for spatial/temporal filtering and artifact rejection. Data may be presented in numerical and graphical form. The device also utilizes attention grabbing features specifically for children or non attentive adults. In particular, a picture is presented prior to the onset of the VEP pattern stimulus. During the picture presentation no data is collected. Age appropriate music is also available to patient as well. The music is only intended as an attention facilitator. From a hardware standpoint the NOVA system is identical to that of the Enfant, ® which was cleared under K043491. The only difference between the two devices is the software.

The provided text describes the Diopsys™ NOVA VEP Vision Testing System, focusing on its substantial equivalence to predicate devices rather than proving its performance against specific acceptance criteria through a clinical study. The performance data section refers to verification and validation activities, which are internal engineering tests, not clinical efficacy studies.

Therefore, much of the requested information regarding acceptance criteria, sample size for test sets, data provenance, expert ground truth, adjudication methods, MRMC studies, standalone performance, and training set details cannot be extracted from the given document.

However, I can provide what is available:

1. Table of Acceptance Criteria and Reported Device Performance:

The document does not explicitly state "acceptance criteria" for clinical performance. Instead, it lists various verification and validation activities for the software and hardware. The "reported device performance" in this context refers to the successful completion of these internal tests.

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

• The document describes verification and validation activities, which typically involve internal testing of the device and software, not a clinical "test set" with a specified sample size of patient data.
• Data Provenance: Not applicable for these internal engineering tests. No information about country of origin or retrospective/prospective nature of patient data is provided.

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

• Not applicable. The performance data pertains to internal engineering verification and validation, not clinical ground truth established by experts.

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

• Not applicable. No clinical test set requiring expert adjudication 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:

• No MRMC or comparative effectiveness study is mentioned. The device is a diagnostic tool (VEP system), and the submission focuses on its substantial equivalence to predicate VEP systems, not its impact on human reader performance.

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

• The "Performance Data" section describes software verification and validation, including "Comparison of EEG Response Verifies VEP recording compared to known recording." This, along with "Signal Test Procedure VEP recordings are displayed as expected," suggests standalone performance of the algorithm in processing and displaying VEP data. However, it's not a clinical standalone performance study in the context of diagnostic accuracy against a ground truth. It's more about the algorithm functioning as intended with known inputs.

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

• For the verification and validation (V&V) activities described, the "ground truth" is primarily based on known specifications, expected behaviors, and known recordings. For example, "Verifies VEP stimulus parameters meet specification" and "Verifies VEP recording compared to known recording." This is not clinical ground truth.

8. The sample size for the training set:

• The document does not mention any training data or training set for the device's software/algorithms. This is common for VEP systems, which often use established signal processing techniques rather than machine learning models requiring extensive training data.

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

• Not applicable, as no training set is mentioned.

Ask a specific question about this device