Search Results

The Ceribell Seizure Detection Software is intended to mark previously acquired sections of EEG recordings in patients greater or equal to 1 year of age that may correspond to electrographic seizures in order to assist qualified clinical practitioners in the assessment of EEG traces. The Seizure Detection Software also provides notifications to the user when detected seizure prevalence is "Frequent", "Abundant", or "Continuous, per the definitions of the American Clinical Neurophysiology Society Guideline 14. Delays of up to several minutes can occur between the beginning of a seizure and when the Seizure Section notifications will be shown to a user.

The Ceribell Seizure Detection Software does not provide any diagnostic conclusion about the subject's condition and Seizure Detection notifications cannot be used as a substitute for real time monitoring of the underlying EEG by a training expert.

The Ceribell Seizure Detection Software is a software-only device that is intended to mark previously acquired sections of EEG recordings that may correspond to electrographic seizures in order to assist qualified clinical practitioners in the assessment of EEG traces.

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided FDA 510(k) clearance letter:

1. Table of Acceptance Criteria & Reported Device Performance

2. Sample Size and Data Provenance for the Test Set

• Sample Size for Test Set:
  • Total Number of Patients: 1701
    • Ages 1-11: 450 patients
    • Ages 12-17: 392 patients
    • Ages 18+: 859 patients
• Data Provenance: The EEG recordings dataset used for performance validation was gathered from real-world clinical usage of the Ceribell Pocket EEG Device. The specific country of origin is not explicitly stated, but it's implied to be from acute care hospital settings where the predicate device (Ceribell Pocket EEG Device) is used. The data is retrospective as it was previously acquired. There were no patient inclusion or exclusion criteria applied, indicating a representative sample of the intended patient population.

3. Number of Experts and Qualifications for Ground Truth

• Number of Experts: More than three expert neurologists (implied by "a two-thirds majority agreement was required"). The tables later specify "3 expert reviewers" for the seizure burden distribution, suggesting at least 3, and possibly more given the "two-thirds majority" rule.
• Qualifications of Experts: Fellowship trained in epilepsy or neurophysiology. No specific years of experience are mentioned.

4. Adjudication Method for the Test Set

• Adjudication Method: A two-thirds majority agreement among the expert neurologists was required to establish the ground truth for seizures. This implies a method of consensus. The experts were fully blinded to the outputs of the Seizure Detection Software.

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

• Was an MRMC study done? No. The documentation describes a standalone algorithm performance study, not a comparative effectiveness study involving human readers with and without AI assistance.
• Effect Size: Not applicable, as no MRMC study was performed.

6. Standalone Algorithm Performance

• Was a standalone study done? Yes. The study directly evaluates the "performance of the Seizure Detection algorithm" by comparing its output (algorithm marks/notifications) against the expert-established ground truth. The algorithm's PPA and FP/hr metrics are presented, which are standard for standalone AI performance.

7. Type of Ground Truth Used

• Type of Ground Truth: Expert consensus (specifically, a two-thirds majority agreement among fellowship-trained neurologists reviewing EEG recordings). This is clinical expert ground truth based on visual review of EEG.

8. Sample Size for the Training Set

• Sample Size for Training Set: Not explicitly stated. The document only mentions that "none of the data in the validation dataset were used for training of the Seizure Detection algorithm; the validation dataset is completely independent." This ensures the integrity of the test set but does not provide information about the training set size.

9. How Ground Truth for the Training Set Was Established

• Ground Truth Establishment for Training Set: Not explicitly stated. The document focuses exclusively on the validation dataset's ground truth methodology. However, given the nature of deep learning models, it's highly probable that the training data also underwent a rigorous ground truth labeling process, likely similar to (or potentially identical in methodology to) the validation set, though this is not detailed here.

Ask a specific question about this device

• autoSCORE is intended for the review, monitoring and analysis of EEG recordings made by electroencephalogram (EEG) devices using scalp electrodes and to aid neurologists in the assessment of EEG. This device is intended to be used by qualified medical practitioners who will exercise professional judgment in using the information.

• The spike detection component of autoSCORE is intended to mark previously acquired sections of the patient's EEG recordings that may correspond to spikes, in order to assist qualified clinical practitioners in the assessment of EEG traces. The spike detection component is intended to be used in patients at least three months old for EEGs 4 hours. The autoSCORE component has not been assessed for intracranial recordings.

• autoSCORE is intended to assess the probability that previously acquired sections of EEG recordings contain abnormalities, and classifies these into pre-defined types of abnormalities, including epileptiform and non-epileptiform abnormalities. autoSCORE does not have a user interface. autoSCORE sends this information to the EEG reviewing software to indicate where markers indicating abnormality are to be placed in the EEG. autoSCORE also provides the probability that EEG recordings include abnormalities and the type of abnormalities. The user is required to review the EEG and exercise their clinical judgement to independently make a conclusion supporting or not supporting brain disease.

• This device does not provide any diagnostic conclusion about the patient's condition to the user. The device is not intended to detect or classify seizures.

autoSCORE is a software only device.

autoSCORE is an AI model that has been trained with standard deep learning principles using a large training dataset. The model will be locked in the field, so it cannot learn from data to which it is exposed when in use. It can only be used with a compatible electroencephalogram (EEG) reviewing software, which acquires and displays the EEG. The model has no user interface. The form of the visualization of the annotations is determined and provided by the EEG reviewing software.

autoSCORE has been trained to identify and then indicate to the user sections of EEG which may include abnormalities and to provide the level of probability of the presence of an abnormality. The algorithm also provides categorization of identified areas of abnormality into the four predefined types of abnormalities, again including a probability of that predefined abnormality type. This is performed by identifying epileptiform abnormalities/spikes (Focal epileptiform and generalised epileptiform) as well identifying non-epileptiform abnormalities (Focal non-epileptiform and Diffuse Non-Epileptiform).

This data is then provided by the algorithm to the EEG reviewing software, for it to display as part of the EEG output for the clinician to review. autoSCORE does not provide any diagnostic conclusion about the patient's condition nor treatment options to the user, and does not replace visual assessment of the EEG by the user. This device is intended to be used by qualified medical practitioners who will exercise professional judgment in using the information.

Acceptance Criteria and Study for autoSCORE (V 2.0.0)

This response outlines the acceptance criteria for autoSCORE (V 2.0.0) and the study conducted to demonstrate the device meets these criteria, based on the provided FDA 510(k) clearance letter.

1. Table of Acceptance Criteria and Reported Device Performance

The FDA clearance document does not explicitly present a table of predefined acceptance criteria (e.g., minimum PPV of X%, minimum Sensitivity of Y%). Instead, the regulatory strategy appears to be a demonstration of substantial equivalence through comparison to predicate devices and human expert consensus. The "Performance Validation" section (Section 7) outlines the metrics evaluated, and the "Validation Summary" (Section 7.2.6) states the conclusion of similarity.

Therefore, the "acceptance criteria" are implied to be that the device performs similarly to the predicate devices and/or to human experts, particularly in terms of Positive Predictive Value (PPV), as this was deemed clinically critical.

Here’s a table summarizing the reported device performance, which the manufacturer concluded met the implicit "acceptance criteria" by demonstrating substantial equivalence:

Ask a specific question about this device

1. Persyst 15 EEG Review and Analysis Software is intended for the review, monitoring and analysis of EEG recordings made by electroencephalogram (EEG) devices to aid neurologists in the assessment of EEG. This device is intended to be used by qualified medical practitioners who will exercise professional judgment in using the information.
2. The Seizure Detection and Seizure Probability component of Persyst 15 is intended to mark previously acquired sections of the adult (greater than or equal to 18 years) EEG recordings that may correspond to electrographic seizures, in order to assist qualified clinical practitioners in the assessment of EEG traces. EEG recordings should be obtained with a full scalp montage according to the standard 10/20 system. Alternatively, the Seizure Detection can operate using reduced set of electrodes including Fp1, F7, T3, O1, Fp2, F8, T3, T6, O2, but will have decreased sensitivity for seizures due to its limited spatial sampling.
3. The Neonatal Seizure Detection component of Persyst 15 is intended to mark previously acquired sections of neonatal patients' (defined as near-term or term neonates of conceptional age between 36 and 44 weeks and less than two weeks of chronologic age) EEG recordings that may correspond to electrographic seizures, in order to assist qualified clinical practitioners in the assessment of EEG traces. EEG recordings should be obtained with scalp-recorded EEG using the standard International 10-20 system electrode placement, modified for neonates (this includes electrode sites Fp1/2 or alternate F1/2, C3/4, T3/4, O1/2, and Cz, optionally including Fz). Alternatively, the Neonatal Seizure Detection component can operate using a more reduced set of electrodes including C3/4, Fp1/2 (F1/2), and O1/2 (recorded in such a manner to allow creation of montage C3-4, Fp1-O1, Fp2-O2), or an even more simplified electrode set including only C3/4 and Cz (arranged as C3-Cz and C4-Cz), but the three-electrode montage will have decreased sensitivity for seizures due to its limited spatial sampling.
4. The Spike Detection component of Persyst 15 is intended to mark previously acquired sections of the patient's EEG recordings that may correspond to spikes, in order to assist qualified clinical practitioners in the assessment of EEG traces. The Spike Detection component is intended to be used in patients at least one month old. Persyst 15 Spike Detection performance has not been assessed for intracranial recordings.
5. Persyst 15 EEG Review and Analysis Software includes the Persyst Imaging Workflow (PW), an imaging viewer. It is intended for use by qualified clinical practitioners on both adult and pediatric subjects at least 12 years of age to interpret EEG data in conjunction with any type of neuroimaging including magnetic resonance imaging (MRI) or computed tomography scans (CT). Persyst Imaging Workflow is not intended to provide diagnostic information.
6. The Persyst ESI component of Persyst 15 is intended for use by a trained/qualified EEG technologist or physician on both adult and pediatric subjects at least 3 years of age for the visualization of human brain function by fusing a variety of EEG information with rendered images of an individualized head model and an individualized MRI image.
7. The Persyst 15 sleep state feature provides the user with output concerning wake-sleep states (wake or sleep,) present in an EEG recording as an aid in assessing which states are present and when they are present. The EEG being assessed for sleep state should utilize standard 10-20 system electrode recording positions and contain the expected EEG patterns of typical wake and sleep, with no major persistent pathological alterations. The sleep state output is subject to user confirmation via EEG waveform review and is not intended for the diagnosis of sleep disorders (e.g.: sleep apnea, narcolepsy, restless leg syndrome). The sleep state feature is intended for adult and pediatric subjects at least 13 years and older.
8. Persyst 15 includes the calculation and display of a set of quantitative measures intended to monitor and analyze the EEG waveform. These include FFT, Rhythmicity, Peak Envelope, Artifact Intensity. Amplitude. Relative Symmetry, and Suppression Ratio. Automatic event marking is not applicable to quantitative measures. These quantitative EEG measures should always be interpreted in conjunction with review of the original EEG waveforms.
9. Persyst 15 displays physiological signals, including the calculation and display of a heart rate measurement based on the ECG channel in the EEG recording, which are intended to aid in the analysis of an EEG. Heart rate measurement of Persyst 15 is not applicable to patients with pacemaker and/or active implantable devices.
10. The aEEG functionality included in Persyst 15 is intended to monitor the state of the brain. The automated event marking function of Persyst 15 is not applicable to aEEG.
11. Persyst 15 provides notifications for seizure detection, quantitative EEG and aEEG that can be used when processing a record during acquisition. These include an on screen display and the optional sending of an email message. Delays of up to several minutes can occur between the beginning of a seizure and when the Persyst 15 notifications will be shown to a user. Persyst 15 notifications cannot be used as a substitute for real time monitoring of the underlying EEG by a trained expert.
12. Persyst 15 AR (Artifact Reduction) is intended to reduce EMG, eye movement, and electrode artifacts in a standard 10-20 EEG recording. AR does not remove the entire artifact signal, and is not effective for other types of artifacts. AR may modify portions of waveforms representing cerebral activity. Waveforms must still be read by a qualified medical practitioner trained in recognizing artifact, and any interpretation or diagnosis must be made with reference to the original waveforms.
13. This device does not provide any diagnostic conclusion about the patient's condition to the user.

Not Found

Ask a specific question about this device

1. LVIS NeuroMatch Software is intended for the review, monitoring and analysis of electroencephalogram (EEG) recordings made by EEG devices using scalp electrodes and to aid neurologists in the assessment of EEG. The device is intended to be used by qualified medical practitioners who will exercise professional judgement in using the information.

2. The Seizure Detection component of LVIS NeuroMatch is intended to mark previously acquired sections of adult EEG recordings from patients greater than or equal to 18 years old that may correspond to electrographic seizures, in order to assist qualified medical practitioners in the assessment of EEG traces. EEG recordings should be obtained with a full scalp montage according to the electrodes from the International Standard 10-20 placement.

3. The Spike Detection component of LVIS NeuroMatch is intended to mark previously acquired sections of adult EEG recordings from patients >18 years old that may correspond to spikes, in order to assist qualified medical practitioners in the assessment of EEG traces. LVIS NeuroMatch Spike Detection performance has not been assessed for intracranial recordings.

4. LVIS NeuroMatch includes the calculation and display of a set of quantitative measures intended to monitor and analyze EEG waveforms. These include Artifact Strength, Asymmetry Spectrogram, and Fast Fourier Transform (FFT) Spectrogram. These quantitative EEG measures should always be interpreted in conjunction with review of the original EEG waveforms.

5. LVIS NeuroMatch displays physiological signals such as electrocardiogram (ECG/EKG) if it is provided in the EEG recording.

6. The aEEG functionality included in LVIS NeuroMatch is intended to monitor the state of the brain.

7. LVIS NeuroMatch Artifact Reduction (AR) is intended to reduce muscle and eye movements, in EEG signals from the International Standard 10-20 placement. AR does not remove the entire artifact signal and is not effective for other types of artifacts. AR may modify portions of waveforms representing cerebral activity. Waveforms must still be read by a qualified medical practitioner trained in recognizing artifacts, and any interpretation or diagnosis must be made with reference to the original waveforms.

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

NeuroMatch is a cloud-based software as a medical device (SaMD) intended to review, monitor, display, and analyze previously acquired and/or near real-time electroencephalogram (EEG) data from patients 18 years old or older. The device is not intended to substitute for real-time monitoring of EEG. The software includes advanced algorithms that perform artifact reduction, seizure detection, and spike detection.

Here's a breakdown of the acceptance criteria and the study details for the NeuroMatch device, based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

For Seizure Detection:

For Spike Detection:

2. Sample Sizes and Data Provenance

For Seizure Detection Validation:

• Test Set Sample Size:
  • Patients: 181 patients with at least 1 verified seizure event, and 10 control patients with 0 verified seizure events.
  • EEG Hours: 979.40 hours from seizure patients, 80 hours from control patients.
  • Events: 504 events used for sensitivity calculation (capped at 6 events per patient).
• Data Provenance: Data collected from three independent and geographically diverse medical institutions. The document indicates this data was "completely separate and independent from the data used to design and train the algorithm," implying it is retrospective data. Country of origin is not explicitly stated but implied to be the US based on the FDA submission.

For Spike Detection Validation:

• Test Set Sample Size:
  • Patients: 149 patients with at least 1 verified spike event.
  • Total EEG minutes (hours): 2752.72 minutes (~45.9 hours).
• Data Provenance: Data collected from three independent and geographically diverse medical institutions. This dataset was also "completely separate and independent from the data used to design and train the algorithm," indicating retrospective data. Country of origin is not explicitly stated.

3. Number and Qualifications of Experts for Ground Truth

• Number of Experts: Three independent EEG-trained neurologists.
• Qualifications of Experts: EEG trained neurologists. More specific details like years of experience are not provided.

4. Adjudication Method for the Test Set

• Seizure Detection: A reference standard was established by a panel of three independent EEG trained neurologists. Seizures were identified based on a 2 out of 3 majority rule.
• Spike Detection: The reference standard was established by a panel of three independent EEG trained neurologists. Spikes were identified with majority consensus among the annotating physicians (i.e., consensus of at least 2 out of the 3 physicians).

5. MRMC Comparative Effectiveness Study

No, a multi-reader multi-case (MRMC) comparative effectiveness study evaluating human reader improvement with AI assistance versus without AI assistance was not explicitly described in the provided text. The study compares the algorithm's performance (NeuroMatch) to a predicate algorithm's performance (Persyst 14), not human performance.

6. Standalone Performance Study

Yes, a standalone (algorithm only without human-in-the-loop performance) study was done for both seizure and spike detection. The results presented in the tables are direct comparisons between the NeuroMatch algorithm and the Persyst 14 predicate algorithm, both run on the validation dataset against a ground truth established by experts.

7. Type of Ground Truth Used

The ground truth used for both seizure and spike detection was expert consensus, specifically "consensus of at least 2 out of the 3 physicians" (majority rule) from independent EEG-trained neurologists.

8. Sample Size for the Training Set

The sample size for the training set is not explicitly provided in the given document. The document states that the validation dataset "was completely separate and independent from the data used to design and train the algorithm," but it does not specify the details of the training data.

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

The method for establishing ground truth for the training set is not explicitly provided in the document. It only states that the validation set was independent of the data used for training and design.

Ask a specific question about this device

The REMI-AI Rapid Detection Module (REMI-AI RDM) is a seizure detection module which is integrated into the REMI Remote EEG Monitoring System and is only indicated for use within non-ICU (Intensive Care Unit) healthcare settings. REMI-AI RDM has not been validated for and is not indicated for detection of electrographic status epilepticus.

REMI-AI RDM conducts automated analysis of REMI EEG data in near real-time and provides notifications of potential electrographic seizures (events) through the REMI System when seizure prevalence of 10% or greater (indicating seizure activity of at least 30 seconds within a 5-minute rolling window) is detected. When seizure prevalence is displayed, the notification also displays the corresponding event detection confidence. Notifications are intended to be used by qualified clinicians who will exercise professional judgment in their application. Detected events are also annotated in the associated REMI EEG record as an aide to the qualified physician's REMI EEG review.

Delays of up to several minutes may occur between the detection of an event and the generation of an event notification, and are thus not a substitute for real-time monitoring. REMI-AI RDM does not make any diagnostic conclusion about the subject's condition and is intended as a physiological signal monitor. REMI-AI RDM is indicated for use with adult and pediatric patients (6+ years).

REMI-AI RDM conducts automated analysis of EEG data collected by the REMI System in near real-time. REMI-AI RDM provides notifications of the prevalence and confidence of potential electrographic seizures, having a combined prevalence of 10% or greater, which correlates with a duration of at least 30 seconds of activity within a rolling 5 minute window of EEG.

REMI-AI RDM notifications are presented through the REMI Mobile software application, and are intended to be used by qualified clinicians who will exercise professional judgment in their interpretation. Notifications include the prevalence and confidence value for the event and are marked in the associated EEG record in order to assist qualified clinicians in their assessment.

REMI-AI RDM notifications identify when a section of EEG is consistent with seizure characteristics it has been trained to recognize. When a notification is presented, clinical context and facility procedures should inform next steps in patient evaluation and management. REMI-AI RDM does not make any treatment or management recommendations.

Here's a summary of the acceptance criteria and study details for the REMI-AI Rapid Detection Module (REMI-AI RDM), based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

Ask a specific question about this device

1. encevis is intended for the review, monitoring and analysis of EEG recordings made by electroencephalogram (EEG) devices using scalp electrodes and to aid neurologists in the assessment of EEG. This device is intended to be used by qualified medical practitioners who will exercise professional judgment in using the information.

2. The seizure detection component of encevis is intended to mark previously acquired sections of adult (greater than or equal to 18 years) EEG recordings that may correspond to electrographic seizures, in order to assist qualified clinical practitioners in the assessment of EEG traces. EEG recordings should be obtained with a full scalp montage according to the standard 10/20-system.

3. The spike detection component of encevis is intended to mark previously acquired sections of the patient's EEG recordings that may correspond to spikes, in order to assist qualified clinical practitioners in the assessment of EEG traces. The Spike detection component is intended to be used in adult patients greater than or equal to 18 years. encevis Spike detection performance has not been assessed for intracranial recordings.

4. encevis includes the calculation and display of a set of quantitative measures intended to monitor and analyze the EEG waveform. These include frequency bands, rhythmic and periodic patterns, burst suppression and spectrogram. These quantitative EEG measures should always be interpreted in conjunction with review of the original EEG waveforms.

5. The aEEG functionality included in encevis is intended to monitor the state of the brain.

6. encevis provides notifications on an on-screen display for seizure detection, electrographic status epilepticus detection, spike detection, quantitative EEG and aEEG that can be used when processing a record during acquisition (online) or based on stored EEG files (offline). Notifications can also be provided to external systems via the external interfaces to make them accessible to the user through the external system in a human-readable format. Delays of up to several minutes can occur between the beginning of a seizure, electrographic status epilepticus, the occurrence of a spike or detection of quantitative EEG features and when the encevis notifications will be shown to a user. encevis notifications cannot be used as a substitute for real time monitoring of the underlying EEG by a trained expert.

7. encevis PureEEG (Artifact Reduction) is intended to reduce EMG and electrode artifacts in a standard 10-20 EEG recording. PureEEG does not remove the entire artifact signal and is not effective for other types of artifacts. PureEEG may modify portions of waveforms representing cerebral activity. Waveforms must still be read by a qualified medical practitioner trained in recognizing artifact, and any interpretation or diagnosis must be made with reference to the original waveforms.

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

9. The encevis Component for Detection of Seizures and Electrographic Status Epilepticus is indicated for the detection of Seizures and Electrographic Status Epilepticus in patients greater than or equal to 18 years of age who are at risk for seizures. The Component for Detection of Seizures and Electrographic Status Epilepticus of encevis analyzes EEG waveforms and identifies patterns that may be consistent with seizures and electrographic status epilepticus as defined in the American Clinical Neurophysiology Society's Guideline 14. EEG recordings should be obtained with a full scalp montage according to the standard 10/20-system. The diagnostic output does also include a measure of seizure prevalence ("seizure burden") within a 10 minute (short-term seizure burden) and a 60 minute (hourly seizure burden) moving window. The output of the Component for Detection of Seizures and Electrographic Status Epilepticus of encevis is intended to be used as a diagnostic output for determining patient treatment in acute-care environments. Detections from the Component for Detection of Seizures and Electrographic Status Epilepticus of encevis provide one input to the clinician that is intended to be used in conjunction with other elements of clinical practice to determine the appropriate treatment course for the patient. The Component for Detection of Seizures and Electrographic Status Epilepticus of encevis is intended for detection of electrographic status epilepticus only. The Component for Detection of Seizures and Electrographic Status Epilepticus of encevis does not substitute for the review of the underlying EEG by a qualified clinician with respect to any other types of pathological EEG patterns. The Component for Detection of Seizures and Electrographic Status Epilepticus of encevis is not intended for use in Epilepsy Monitoring Units.

encevis combines several modalities for viewing and analyzing EEG data in one integrated software package. The software package can be used both as a standalone desktop application for opening and analyzing stored EEG files (offline mode) and as a module for integration into external EEG systems via the provided API interfaces, enabling the processing of real-time streaming data in online mode. encevis consists of the following modalities: encevis EEG-viewer, Artefact reduction encevis PureEEG, Seizure detection of encevis NeuroTrend, Detection of seizures and status epilepticus of encevis acute care, Spike detection encevis EpiSpike, Pattern detection and aEEG, Spectrogram, External Interface "encevis AITInterface", External Interface "encevis SeizureICUInterface".

Here's a breakdown of the acceptance criteria and study details for the encevis (2.1) device, based on the provided text:

Acceptance Criteria and Device Performance

The document outlines acceptance criteria and performance for several components of the encevis (2.1) device.

Table 1: Acceptance Criteria and Reported Device Performance

Study Details

2. Sample Size and Data Provenance

• Seizure Detection:
  • Test Set: 55 subjects (1603 hours of EEG data, max 30 hours per subject)
  • Data Provenance: Retrospective, patients from an epilepsy monitoring unit. Countries of origin are not specified, but the context implies it is likely from a clinical setting.
• Seizure Detection and Status Epilepticus (Acute Care):
  • Test Set: 81 patients (62.4 hours of EEG data)
  • Data Provenance: Retrospective, neurological/general intermediate care units or neurological/general intensive care units at two different sites in the US (31 patients) and outside of US (50 patients).
• Spike Detection:
  • Test Set: 23 patients
  • Data Provenance: Retrospective, patients from an epilepsy monitoring unit. Countries of origin are not specified, but the context implies it is likely from a clinical setting.
• Artifact Reduction:
  • Test Set: 128 EEG data records (10 seconds each) from different patient groups (60 epilepsy monitoring, 65 ICU patients).
  • Data Provenance: Retrospective, epilepsy monitoring units and ICU settings.
• Rhythmic and Periodic Patterns:
  • Test Set: 83 long-term EEGs from ICU patients, first minute of each hour, split into three 20-second segments (11935 common annotation segments).
  • Data Provenance: Prospective, two different centers. Countries are not specified.
• aEEG:
  • Test Set: "Real EEG data" for comparison with Persyst. (Specific sample size not provided for this comparison). Also sinusoidal test data.
  • Data Provenance: Not explicitly stated, but "real EEG data" implies clinical origin.
• Frequency Bands:
  • Test Set: Sinusoidal test data and manually selected EEG recordings from epilepsy/ICU patients. (Specific sample size not provided).
  • Data Provenance: Not explicitly stated, but "manually selected EEG recordings from epilepsy- or ICU patients" implies clinical origin.
• Burst Suppression:
  • Test Set: 83 long-term EEGs from intensive care patients (3978 valid annotation segments from the first minute of each hour).
  • Data Provenance: Retrospective?, two different centers. Countries are not specified.
• Spectrogram:
  • Test Set: Artificially created data and real EEG data. (Specific sample size not provided).
  • Data Provenance: Not explicitly stated, but "real EEG data" implies clinical origin.

3. Number of Experts and Qualifications for Ground Truth

• Seizure Detection: 3 independent neurologists, blinded review. Qualifications not explicitly stated beyond "independent neurologists".
• Seizure Detection and Status Epilepticus (Acute Care): 6 experienced, board-certified, and independent Neurologists, blinded review. Qualifications specified as "experienced, board-certified".
• Spike Detection: 3 independent neurologists, blinded review. Qualifications not explicitly stated beyond "independent neurologists".
• Artifact Reduction: 3 independent epileptologists or neurologists, blinded review.
• Rhythmic and Periodic Patterns: 2 clinical neurophysiologists, naive to the EEGs.
• Burst Suppression: 2 clinical EEG experts.

4. Adjudication Method for Test Set

• Seizure Detection: An event was considered a "true seizure" if the time interval of two out of three reviewers overlapped by at least 1 second.
• Seizure Detection and Status Epilepticus (Acute Care): Reference standard for seizures derived from 6 independent neurologists. Reference standard for ESE and seizure burden derived from consensus seizure annotations. The specific voting rule for "consensus" is not explicitly stated, but implies agreement among experts.
• Spike Detection: An event was considered a "true spike" if the time interval of two out of three reviewers overlapped.
• Artifact Reduction: Not explicitly stated for artifact detection itself, but for identifying clean EEG patterns and artifacts, 3 independent epileptologists or neurologists were involved. Implies consensus or agreement.
• Rhythmic and Periodic Patterns: Annotations had to be consistent between both reviewers to be used in sensitivity and specificity measurement. Cohens' kappa statistic (0.66) indicates substantial agreement.
• Burst Suppression: The detection performance was analyzed for consensus annotations of the two reviewers. Consensus annotations only included segments where both reviewers showed the same decision.

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

There is no explicit mention of an MRMC comparative effectiveness study where human readers improve with AI vs without AI assistance. The studies primarily focus on the standalone performance of the AI algorithms and compare them to predicate devices (other algorithms). In the case of "Rhythmic and Periodic Patterns", human reader agreement (inter-reader agreement) is used to establish ground truth, not to evaluate human performance with/without AI assistance.

6. Standalone Performance Study

Yes, standalone (algorithm only without human-in-the-loop performance) studies were done for all major components. The reported metrics like PPA, NPA, NDR, sensitivity, and specificity are all measures of the algorithm's performance against the established ground truth.

7. Type of Ground Truth Used

• Expert Consensus: This is the predominant type of ground truth used across all evaluated components. Experts (neurologists, epileptologists, clinical neurophysiologists) retrospectively reviewed EEG recordings and marked events like seizures, spikes, ESE, and patterns.
• Artificial Data: Used for validating aEEG, frequency bands, and spectrogram for initial functional verification.
• Pre-calculated Values: Used for validating the quantitative measure of amplitude loss in burst suppression.

8. Sample Size for the Training Set

The document does not provide information on the sample size used for the training set for any of the encevis (2.1) components. The studies described are validation studies using a test set.

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

Since the document does not provide information on the training set, it does not describe how the ground truth for the training set was established.

Ask a specific question about this device

1. autoSCORE is intended for the review, monitoring and analysis of EEG recordings made by electroencephalogram (EEG) devices using scalp electrodes and to aid neurologists in the assessment of EEG. This device is intended to be used by qualified medical practitioners who will exercise professional judgment in using the information.
2. The spike detection component of autoSCORE is intended to mark previously acquired sections of the patient's EEG recordings that may correspond to spikes, in order to assist qualified clinical practitioners in the assessment of EEG traces. The spike detection component is intended to be used in patients at least three months old. The autoSCORE component has not been assessed for intracranial recordings.
3. autoSCORE is intended to assess the probability that previously acquired sections of EEG recordings contain abnormalities, and classifies these into pre-defined types of abnormalities, including epileptiform abnormalities. autoSCORE does not have a user interface. autoSCORE sends this information to the EEG reviewing software to indicate where markers indicating abnormality are to be placed in the EEG. autoSCORE also provides the probability that EEG recordings include abnormalities and the type of abnormalities. The user is required to review the EEG and exercise their clinical judgendently make a conclusion supporting or not supporting brain disease.
4. This device does not provide any diagnostic conclusion about the patient's condition to the user. The device is not intended to detect or classify seizures.

autoSCORE is a software-only decision support product intended to be used with compatible electroencephalography (EEG) review software. It is intended to assist the user when reviewing EEG recordings, by assessing the probability that previously acquired sections of EEG recordings contain abnormalities, and classifying these into pre-defined types of abnormality. autoSCORE sends this information to the EEG software to indicate where markers indicating abnormality are to be placed in the EEG. autoSCORE uses an algorithm that has been trained with standard deep learning principles using a large training dataset. autoSCORE also provides an overview of the probability that EEG recordings and sections of EEG recordings include abnormalities, and which type(s) of abnormality they include. This is performed by identifying spikes of epileptiform abnormalities (Focal epileptiform and Generalized epileptiform) as well identifying non-epileptiform abnormalities (Focal Nonepileptiform and Diffuse Non-epileptiform). The user is required to review the EEG and exercise their clinical judgement to independently make a conclusion supporting or not supporting brain disease. autoSCORE cannot detect or classify seizures. The recorded EEG activity is not altered by the information provided by autoSCORE. autoSCORE is not intended to provide information for diagnosis but to assist clinical workflow when using the EEG software.

The FDA 510(k) summary for Holberg EEG AS's autoSCORE device provides extensive information regarding its acceptance criteria and the study proving it meets these criteria. Here's a breakdown of the requested information:

Acceptance Criteria and Device Performance for autoSCORE

The acceptance criteria for autoSCORE are established by its performance metrics in comparison to human expert assessments and predicate devices. The device is intended to assist medical practitioners in the review, monitoring, and analysis of EEG recordings by identifying and classifying abnormalities, particularly epileptic and non-epileptic events.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly defined by the performance metrics (Sensitivity, Specificity, PPV, NPV, Correlation Coefficient) shown to be comparable to or exceeding those of human experts or predicate devices. Since specific numeric thresholds for acceptance are not explicitly stated, the reported performance metrics are presented as evidence of meeting acceptable clinical performance.

Table 1: Reported Performance of autoSCORE (Summarized from document)

Note: For detailed confidence intervals and marker-level performance, refer to Tables 4, 5, 6, 7, and 8 in the original document.

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

The clinical validation was performed across five separate datasets:

• Part 1 (Single-Center): 4,850 EEGs. Data provenance not explicitly stated but implied to be from routine EEG assessment in a hospital setting. Retrospective.
• Part 2 (Multi-Center): 100 EEGs. Data provenance not explicitly stated but implied to be from routine EEG assessment in various hospital settings. Retrospective.
• Part 3 (Direct Comparison to Primary Predicate): Same 100 EEGs as Part 2. Retrospective.
• Part 4 (Benchmarking against Primary and Secondary Predicates): 58 EEGs. Data provenance not explicitly stated but implied to be from routine EEG assessment. Retrospective.
• Part 5 (Hold-out Dataset, Two Centers): 1,315 EEGs. Data provenance not explicitly stated but implied to be from routine EEG assessment in two hospital settings. Retrospective.

None of the EEGs used in the validation were used for the development of the AI model. The document does not explicitly state the country of origin for the data, but the company address in Norway suggests a European origin.

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

• Part 1 & 5: Ground truth established by multiple Human Experts (HEs), with a single HE reviewer per EEG.
  • Part 1: 9 HEs, each assessing more than 1% of the EEGs.
  • Part 5: 15 HEs, each assessing more than 1% of the EEGs.
  • Qualifications: "Qualified medical practitioners" or "neurologists" who exercise professional judgment. In Parts 1 and 5, their assessments were part of "routine EEG assessment in their respective hospitals," implying they are experienced clinicians.
• Part 2 & 3: Ground truth established by HE consensus.
  • Part 2 & 3: 11 independent HEs reviewed 100 EEGs.
  • Qualifications: "Independent human experts." Implied to be qualified clinical practitioners.
• Part 4: Ground truth established by HE consensus.
  • Part 4: 3 HEs.
  • Qualifications: "HEs." Implied to be qualified clinical practitioners.

4. Adjudication Method for the Test Set

• Part 1 & 5 (Recording and Marker Level): Ground truth was established by single HE reviewer per EEG. While multiple HEs contributed, each EEG had a single "reference standard" HE assessment. This is a "none" or "single-reader" adjudication in the context of individual EEG ground truth, though the overall dataset was reviewed by multiple HEs.
• Part 2 & 3 (Recording Level): Ground truth was based on HE consensus of 11 HEs, assessing if EEGs were normal/abnormal and contained specific abnormality categories. This implies a form of majority consensus or agreement-based adjudication among the 11 experts. The granularity of probability grouping was 9 percentage points.
• Part 4 (Recording and Marker Level): Ground truth was majority consensus scoring of 3 HEs.

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?

The study described is a direct comparison of autoSCORE's performance against human experts and predicate devices, effectively evaluating the AI's standalone or augmented performance rather than the improvement of human readers when assisted by AI. The document states autoSCORE is a "decision support product intended to be used with compatible electroencephalography (EEG) review software" and that the "user is required to review the EEG and exercise their clinical judgement to independently make a conclusion." However, it does not present an MRMC comparative effectiveness study that quantifies the improvement of human readers assisted by AI versus without AI assistance.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done?

Yes, the study primarily assesses the standalone performance of the autoSCORE algorithm by comparing its outputs directly against human expert assessments (considered the ground truth) and outputs from predicate devices. The tables summarizing sensitivity, specificity, PPV, NPV, and correlation coefficients directly reflect the algorithm's performance.

7. The Type of Ground Truth Used (Expert Consensus, Pathology, Outcomes Data, etc.)

The ground truth used for the test sets was primarily human expert assessment (or consensus of human experts).

• Parts 1 and 5 used individual HE assessments as the reference standard (routine clinical assessments).
• Parts 2, 3, and 4 used expert consensus as the reference standard.
  No pathology or outcomes data were used to establish the ground truth.

8. The Sample Size for the Training Set

The document explicitly states that "None of the EEGs used in the validation were used in the development of the AI model." However, the specific sample size of the training set is not provided in the provided document. It only mentions that "autoSCORE uses an algorithm that has been trained with standard deep learning principles using a large training dataset."

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

The document does not explicitly describe how the ground truth for the training set was established. It only refers to "standard deep learning principles" and a "large training dataset." It notes that the HEs providing the reference standards for the validation phase (Studies 1, 2, 3, and 4) were different from those who participated in the development portion of the process. This implies that human experts were involved in creating the ground truth for the training data, but the method (e.g., single expert, multi-expert consensus, specific rules) is not detailed.

Ask a specific question about this device

The REMI-AI Discrete Detection Module (REMI-AI DDM) is indicated for the analysis of REMI Remote EEG Monitoring System electroencephalogram (EEG) recordings. REMI-AI DDM is intended to be used by physicians qualified to analyze and interpret EEG who will exercise professional judgment in using the information.

As an aide to the qualified physician's REMI EEG review, REMI-AI DDM marks previously acquired sections of REMI EEG that may correspond to neurological events of interest indicative of potential electrographic seizures lasting at least 10 seconds in duration. REMI-AI DDM is indicated for use with adult and pediatric patients (6+ years).

REMI-AI DDM does not mark REMI EEG records in real time and does not provide any diagnostic conclusion about the patient's condition to the user.

REMI-Al Discrete Detection Module (REMI-AI DDM) is a software as a medical device (SaMD) that automatically identifies and annotates discrete seizure-like events in previously acquired electroencephalography (EEG) traces to aid a qualified physician in their review of REMI EEG records. REMI-AI DDM analyzes previously acquired EEG data from 4-channel recordings obtained from bilateral, bipolar scalp EEG recordings at both the frontal and temporoparietal regions, collected and stored by the REMI Remote EEG Monitoring System. REMI-AI DDM analyzes EEG recordings and detects regions of the data that may correspond to electrographic seizures lasting at least 10 seconds in duration. These regions are annotated in the REMI EEG file as discrete events and are provided to assist in REMI EEG review.

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the provided text:

Acceptance Criteria and Device Performance

Ask a specific question about this device

1. LVIS NeuroMatch Software is intended for the review, monitoring and analysis of electroencephalogram (EEG) recordings made by EEG devices using scalp electrodes and to aid neurologists in the assessment of EEG. The device is intended to be used by qualified medical practitioners who will exercise professional judgement in using the information. 2. LVIS NeuroMatch includes the calculation and display of a set of quantitative measures intended to monitor and analyze EEG waveforms. These include Artifact Strength, Asymmetry Spectrogram, Autocorrelation Spectrogram, and Fast Fourier Transform (FFT) Spectrogram. These quantitative EEG measures should always be interpreted in conjunction with review of the original EEG waveforms.

2. LVIS NeuroMatch displays physiological signals such as electrocardiogram (ECG/EKC) if it is provided in the EEG recording.

3. The aEEG functionality included in LVIS NeuroMatch is intended to monitor the state of the brain.

4. LVIS NeuroMatch Artifact Reduction (AR) is intended to reduce muscle and eye movements in EEG signals from the International Standard 10-20 placement. AR does not remove the entifact signal and is not effective for other types of artifacts. AR may modify portions of waveforms representing cerebral activity. Waveforms must still be read by a qualified medical practitioner trained in recognizing artifacts, and any interpretation or diagnosis must be made with reference to the original waveforms.

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

Not Found

This document does not contain information about acceptance criteria or a study proving the device meets acceptance criteria. It is a 510(k) clearance letter from the FDA for the LVIS NeuroMatch® device, outlining its indications for use and regulatory compliance.

Ask a specific question about this device

The Ceribell Status Epilepticus Monitor software is indicated for the diagnosis of Electrographic Status Epilepticus in patients greater than or equal to 18 years of age who are at risk for seizure. The Ceribell Status Epilepticus Monitor software analyzes EEG waveforms and identifies patterns that may be consistent with electrographic status epileptious as defined in the American Clinical Neurophysiology Society's Guideline 14.

The diagnostic output of the Ceribell Status Epilepticus Monitor is intended to be used as an aid for determining patient treatment in acute-care environments. The device's diagnosis of Electrographic Status Epilepticus provides one input to the clinician that is intended to be used in conjunction with other elements of clinical practice to determine the appropriate treatment course for the patient.

The Ceribell Status Epilepticus Monitor is intended for diagnosis of Electrographic Status Epilepticus only. The device does not substitute for the review of the underlying EEG by a qualified clinician with respect to any other types of pathological EEG patterns. The device is not intended for use in Epilepsy Monitoring Units.

The Ceribell Status Epilepticus Monitor is a software as medical device that analyzes EEG waveforms for the intended use of recognizing electrographic status epilepticus (ESE). The subject device software is intended for use only with the Ceribell Pocket EEG Device (K191301), which is also the predicate device. The predicate device contains a software module that performs detection of seizures in a similar manner as the subject device. The user workflow and instructions for starting an EEG recording on a patient are unchanged compared to the predicate device.

The user places the Ceribell Instant EEG Headband (K210805) on the patient, the headband contains 10 electrodes that are arranged in a bipolar montage and correspond to the following locations following the 10-20 electrode naming convention: Fp1, F7, T3, T5, O1, Fp2, F8, T3, T6, O2. The 10 electrodes form 8 channels (4 on the left hemisphere, 4 on the right hemisphere) that are analyzed by the subject device's ESE detection algorithm.

Here's a summary of the acceptance criteria and the study that proves the device meets them, based on the provided text:

Acceptance Criteria and Device Performance

The Ceribell Status Epilepticus Monitor underwent clinical validation to assess its performance in diagnosing Electrographic Status Epilepticus (ESE). The primary performance metrics were sensitivity and specificity.

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size for the Test Set and Data Provenance

• Sample Size: 350 subjects
• Data Provenance: Retrospective study using previously-collected EEG data from 6 hospitals of varying size and geographic locations. The data represents "real-world data" from a fixed one-year time period. All included subjects were ≥ 18 years of age.

3. Number of Experts and Qualifications for Ground Truth

• Number of Experts: A team of "qualified neurologists" (specific number not given, but plural).
• Qualifications of Experts: Described as "qualified neurologists." No further details on years of experience or specific subspecialties are provided in the document.

4. Adjudication Method for the Test Set

• Adjudication Method: "Majority opinion of the expert reviewers." This indicates a consensus-based approach. For example, if there were three reviewers, at least two would need to agree.

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

• MRMC Study: No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not explicitly stated as having been performed. The study focused on the standalone performance of the algorithm against expert-established ground truth.
• Effect Size of Human Readers with vs. Without AI Assistance: Not applicable, as an MRMC study with human-in-the-loop performance was not described.

6. Standalone (Algorithm Only) Performance

• Standalone Performance: Yes, the study describes the standalone (algorithm-only) performance of the Ceribell Status Epilepticus Monitor. The device algorithm was run on the collected dataset, and its output was compared against the expert-established ground truth.

7. Type of Ground Truth Used

• Ground Truth Type: Expert consensus. Specifically, a "team of qualified neurologists independently review[ed] and categorize[d] each EEG; the ground-truth reference standard is established by a majority opinion of the expert reviewers."

8. Sample Size for the Training Set

• The document does not explicitly state the sample size used for the training set. The clinical validation study described is a retrospective study of the algorithm's performance on a test set (350 subjects).

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

• The document does not explicitly state how the ground truth for the training set was established, as details about the training phase itself are not provided in this summary. The focus is on the clinical validation study.

Ask a specific question about this device