(310 days)
Not Found
No
The document explicitly states "Mentions AI, DNN, or ML: Not Found" and describes an algorithm trained on expert-annotated data, but does not use terms that indicate the use of an AI model, such as neural networks or machine learning.
No
The device is described as a "Seizure Detection Software" intended to "mark previously acquired sections of EEG recordings" to "assist qualified clinical practitioners in the assessment of EEG traces." It explicitly states that it "does not provide any diagnostic conclusion" and "cannot be used as a substitute for real time monitoring." This indicates it's an assistive tool for diagnosis, not a device that directly treats or prevents a condition.
No
The intended use statement explicitly states, "The Ceribell Seizure Detection Software does not provide any diagnostic conclusion about the subject's condition." Its purpose is to assist qualified clinical practitioners in the assessment of EEG traces by marking sections of EEG recordings that may correspond to electrographic seizures.
Yes
The device explicitly states in its "Device Description" that it is a "software-only device." There is no mention of hardware components being part of this 510(k) submission.
No.
This device analyzes previously acquired EEG recordings to assist in the assessment of EEG traces, which means it processes signals/images/data from the human body, but does not provide diagnostic conclusions. It is not an in vitro diagnostic device according to the definition of IVDs.
Yes
The letter explicitly states, "The Ceribell Seizure Detection Software has been cleared by the FDA with an Authorized PCCP."
Intended Use / Indications for Use
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.
Product codes
OMB
Device Description
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.
Mentions image processing
Not Found
Mentions AI, DNN, or ML
Not Found
Input Imaging Modality
EEG recordings
Anatomical Site
Not Found
Indicated Patient Age Range
patients greater or equal to 1 year of age
Intended User / Care Setting
qualified clinical practitioners / acute care hospital settings
Description of the training set, sample size, data source, and annotation protocol
The reviewing neurologists did not have access to any of the outputs from the Seizure Detection Software; the experts were fully blinded. Importantly, none of the data in the validation dataset were used for training of the Seizure Detection algorithm; the validation dataset is completely independent.
Description of the test set, sample size, data source, and annotation protocol
The EEG recordings dataset used for performance validation was gathered from real-world clinical usage of the Ceribell Pocket EEG Device in acute care hospital settings. There were no patient inclusion or exclusion criteria applied, therefore the data are fully representative of the intended patient population. To form the reference standard for seizures, the EEG recordings were retrospectively reviewed by a panel of expert neurologists who were fellowship trained in epilepsy or neurophysiology. A two-thirds majority agreement was required to form a determination of seizures.
Total Number of Patients: 1701.
Seizure Episodes with Seizure Burden ≥10%: 346.
Seizure Episodes with Seizure Burden ≥50%: 143.
Seizure Episodes with Seizure Burden ≥90%: 68.
Summary of Performance Studies
The Ceribell Seizure Detection Software is validated by evaluating the performance of the Seizure Detection algorithm on a dataset of EEG recordings representative of the intended patient population.
Performance of the Seizure Detection algorithm was assessed by evaluating the positive percent agreement (PPA) and the false positive rate per hour (FP/hr) of the algorithm compared to the expert reviewer reference standard.
-
Positive Percent Agreement (PPA):
For each threshold of Seizure Burden activity (Frequent, Abundant, Continuous)
Lower bound of the 95% confidence interval ≥ 70% PPA -
False Positive rate per hour (FP/hr):
For each threshold of Seizure Burden activity (Frequent, Abundant, Continuous)
Upper bound of the 95% confidence interval ≤ 0.446 FP/hr
Performance against the acceptance criteria was assessed for the age ranges of 1-11, 2-17 and 18+. The overall performance for all patients was also evaluated. In all cases, the acceptance criteria were met, and the Seizure Detection algorithm PASSES.
Overall results:
Seizure Episodes with Seizure Burden ≥10% (Frequent): PPA 93.93% (95% CI: 90.03, 96.52), FP/hr 0.1763 (95% CI: 0.1670, 0.1859). Pass.
Seizure Episodes with Seizure Burden ≥50% (Abundant): PPA 96.50% (95% CI: 92.12, 98.77), FP/hr 0.08180 (95% CI: 0.0754, 0.0885). Pass.
Seizure Episodes with Seizure Burden ≥90% (Continuous): PPA 94.12% (95% CI: 85.45, 98.48), FP/hr 0.03951 (95% CI: 0.0351, 0.0443). Pass.
Key Metrics
Positive Percent Agreement (PPA), False Positive rate per hour (FP/hr)
Predicate Device(s)
Reference Device(s)
Not Found
Predetermined Change Control Plan (PCCP) - All Relevant Information
The Ceribell Seizure Detection Software has been cleared by the FDA with an Authorized PCCP. The Authorized PCCP outlines specific modifications intended to improve algorithm clinical or computational performance through the expansion of training data and optimization of the algorithm. The PCCP outlines Ceribell's data management and algorithm development practices, including how and when performance is evaluated.
The PCCP also defines validation requirements for algorithm updates. Prior to release, the updated algorithm is validated through testing against previously established acceptance criteria using an independent validation data set. Updates will be implemented using a validated Software Update process. When an update is performed, Ceribell will update this operator manual and notify customers of the update.
§ 882.1400 Electroencephalograph.
(a)
Identification. An electroencephalograph is a device used to measure and record the electrical activity of the patient's brain obtained by placing two or more electrodes on the head.(b)
Classification. Class II (performance standards).
FDA 510(k) Clearance Letter - Ceribell Seizure Detection Software
Page 1
U.S. Food & Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993
www.fda.gov
Doc ID # 04017.07.05
April 9, 2025
Ceribell, Inc.
Raymond Woo, Ph.D.
CTO
360 North Pastoria Avenue
Sunnyvale, California 94085
Re: K241589
Trade/Device Name: Ceribell Seizure Detection Software
Regulation Number: 21 CFR 882.1400
Regulation Name: Electroencephalograph
Regulatory Class: Class II
Product Code: OMB
Dated: March 10, 2025
Received: March 10, 2025
Dear Dr. Raymond Woo:
We have reviewed your section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (the Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database available at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.
FDA's substantial equivalence determination also included the review and clearance of your Predetermined Change Control Plan (PCCP). Under section 515C(b)(1) of the Act, a new premarket notification is not required for a change to a device cleared under section 510(k) of the Act, if such change is consistent with an
Page 2
K241589 - Raymond Woo, Ph.D. Page 2
established PCCP granted pursuant to section 515C(b)(2) of the Act. Under 21 CFR 807.81(a)(3), a new premarket notification is required if there is a major change or modification in the intended use of a device, or if there is a change or modification in a device that could significantly affect the safety or effectiveness of the device, e.g., a significant change or modification in design, material, chemical composition, energy source, or manufacturing process. Accordingly, if deviations from the established PCCP result in a major change or modification in the intended use of the device, or result in a change or modification in the device that could significantly affect the safety or effectiveness of the device, then a new premarket notification would be required consistent with section 515C(b)(1) of the Act and 21 CFR 807.81(a)(3). Failure to submit such a premarket submission would constitute adulteration and misbranding under sections 501(f)(1)(B) and 502(o) of the Act, respectively.
Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).
Your device is also subject to, among other requirements, the Quality System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30, Design controls; 21 CFR 820.90, Nonconforming product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change requires premarket review, the QS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.30 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting (reporting of medical device-related adverse events) (21 CFR Part 803) for devices or postmarketing safety reporting (21 CFR Part 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reporting-combination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.
All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Rule"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/unique-device-identification-system-udi-system.
Page 3
K241589 - Raymond Woo, Ph.D. Page 3
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-devices/medical-device-safety/medical-device-reporting-mdr-how-report-medical-device-problems.
For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
Jay R. Gupta -S
Jay Gupta
Assistant Director
DHT5A: Division of Neurosurgical,
Neurointerventional, and
Neurodiagnostic Devices
OHT5: Office of Neurological and
Physical Medicine Devices
Office of Product Evaluation and Quality
Center for Devices and Radiological Health
Enclosure
Page 4
DEPARTMENT OF HEALTH AND HUMAN SERVICES
Food and Drug Administration
Form Approved: OMB No. 0910-0120
Expiration Date: 07/31/2026
See PRA Statement below.
Indications for Use
Submission Number (if known)
K241589
Device Name
Ceribell Seizure Detection Software
Indications for Use (Describe)
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.
Type of Use (Select one or both, as applicable)
☒ Prescription Use (Part 21 CFR 801 Subpart D)
☐ Over-The-Counter Use (21 CFR 801 Subpart C)
CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
Department of Health and Human Services
Food and Drug Administration
Office of Chief Information Officer
Paperwork Reduction Act (PRA) Staff
PRAStaff@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
Page 5
K241589 510(k) Summary
This summary is being submitted in accordance with the requirements of 21 CFR 807.92.
Submitter Information:
Ceribell, Inc.
360 North Pastoria Ave
Sunnyvale, California 94085
Phone: 1-800-763-0183
Contact Person:
Raymond Woo, PhD
CTO
E-mail: ray@ceribell.com
Phone: 650-556-4349
Alternate Contact Person:
Tom McDougal
Associate Director of Regulatory
E-mail: tom.mcdougal@ceribell.com
Device Information:
Trade Name: Ceribell Seizure Detection Software
Common Name: Automatic Event Detection Software For Full-Montage Electroencephalograph
Classification Name: Electroencephalograph (21CFR 882.1400)
Device Class: II
Product Code: OMB
Predicate Device:
K191301, Ceribell Pocket EEG Device (Ceribell, Inc.)
Date Prepared:
March 10, 2025
Device Description:
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.
Page 6
Indications for Use:
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.
Comparison of Intended Use and Technological Characteristics with the Predicate Devices:
Compared to the predicate device, the subject device has the same intended use and is indicated for an expanded patient population aged 1 year or older. The subject device does not include any hardware component; it is a software-only device that comprises only seizure detection software. The subject device software algorithm has been updated and clinically validated for the intended patient population. Apart from these differences, the subject device and predicate device share the same technological characteristics, clinical workflow, and underlying operating principles. The following tables summarizes the substantial equivalence comparison between the subject device and the predicate device.
Substantial Equivalence Table
| Parameter | Predicate Device
Ceribell Pocket EEG Device (K191301) | Subject Device
Ceribell Seizure Detection Software (K241589) | Substantially Equivalent? |
|-----------|-----------------------------------------------------------|------------------------------------------------------------------|---------------------------|
| Intended Use | The Ceribell Pocket EEG Device is a portable EEG monitoring system that records, stores and presents EEG signals in visual and audible formats in real time. The visual and audible signals assist trained medical staff to make neurological diagnoses. The Pocket EEG Device EEG Recording Viewer software incorporates a Seizure Detection component that is intended to mark previously acquired sections EEG recordings that may correspond to electrographic seizures in order to assist qualified clinical practitioners in the assessment of EEG traces. | Same as for the Seizure Detection component of the Predicate Device:
The Ceribell Seizure Detection Software is intended to mark previously acquired sections EEG recordings that may correspond to electrographic seizures in order to assist qualified clinical practitioners in the assessment of EEG traces. | Yes; the intended use of the subject device is within the intended use of the predicate device. |
| Indications for Use | The Ceribell Pocket EEG Device is intended to record and store EEG signals, and to present the EEG signals in visual and audible formats in real time. The visual | The Ceribell Seizure Detection Software is intended to mark previously acquired sections of EEG recordings in patients | Yes; the revised indications for use fall within the same intended use as that of |
Page 7
Substantial Equivalence Table (continued)
| Parameter | Predicate Device
Ceribell Pocket EEG Device (K191301) | Subject Device
Ceribell Seizure Detection Software (K241589) | Substantially Equivalent? |
|-----------|-----------------------------------------------------------|------------------------------------------------------------------|---------------------------|
| | and audible signals assist trained medical staff to make neurological diagnoses. The Pocket EEG Device is intended to be used in a professional healthcare facility environment.
Additionally, the EEG Recording Viewer Software component of the Pocket EEG Device incorporates a Seizure Detection component that is intended to mark previously acquired sections of EEG recordings in patients greater than or equal to 8 years of age that may correspond to electrographic seizures in order to assist qualified clinical practitioners in the assessment of EEG traces. The Seizure Detection component 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. Notifications include an on-screen display on the Pocket EEG Device and the optional sending of an e-mail message to a clinician. Delays of up to several minutes can occur between the beginning of a seizure and when the Seizure Detection notifications will be shown to a user.
The Pocket EEG Device 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 trained expert. | 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 predicate device. As demonstrated by clinical performance data, the change in intended age range for the patient population of the Seizure Detection Software does not raise new or different questions of safety or effectiveness. |
| Intended Patient Population | • EEG acquisition, recording, storing, and display: All ages
• Seizure Detection module: ages 18 and older | Seizure Detection software: ages 1 and older | Yes; as demonstrated by clinical performance data, the change in age range for the Seizure Detection Software does not raise any new or different questions of safety or effectiveness. The revised indications for use fall within the same intended use as |
Page 8
Substantial Equivalence Table (continued)
| Parameter | Predicate Device
Ceribell Pocket EEG Device (K191301) | Subject Device
Ceribell Seizure Detection Software (K241589) | Substantially Equivalent? |
|-----------|-----------------------------------------------------------|------------------------------------------------------------------|---------------------------|
| | and audible signals assist trained medical staff to make neurological diagnoses. The Pocket EEG Device is intended to be used in a professional healthcare facility environment.
Additionally, the EEG Recording Viewer Software component of the Pocket EEG Device incorporates a Seizure Detection component that is intended to mark previously acquired sections of EEG recordings in patients greater than or equal to 8 years of age that may correspond to electrographic seizures in order to assist qualified clinical practitioners in the assessment of EEG traces. The Seizure Detection component 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. Notifications include an on-screen display on the Pocket EEG Device and the optional sending of an e-mail message to a clinician. Delays of up to several minutes can occur between the beginning of a seizure and when the Seizure Detection notifications will be shown to a user.
The Pocket EEG Device 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 trained expert. | 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 predicate device. As demonstrated by clinical performance data, the change in intended age range for the patient population of the Seizure Detection Software does not raise new or different questions of safety or effectiveness. |
| Intended Patient Population | • EEG acquisition, recording, storing, and display: All ages
• Seizure Detection module: ages 18 and older | Seizure Detection software: ages 1 and older | Yes; as demonstrated by clinical performance data, the change in age range for the Seizure Detection Software does not raise any new or different questions of safety or effectiveness. The revised indications for use fall within the same intended use as that of the predicate device. As demonstrated by clinical performance data, the change in intended age range for the patient population of the Seizure Detection Software does not raise new or different questions of safety or effectiveness. |
| Intended Location of Use | Professional healthcare facilities | Same as predicate device | Yes; no change. |
Non-clinical Testing:
Software verification and validation testing was conducted, and documentation provided as recommended by the FDA Guidance for Industry and FDA Staff, Content of Premarket Submissions for Device Software Functions. In addition, tests according to "IEC 62366-1:2015, Medical Devices Part 1—Application of usability engineering to medical devices" have been performed.
Software verification and validation activities support the safety and effectiveness of the Ceribell Seizure Detection Software.
Performance Data:
The following clinical performance data were submitted to support a determination of substantial equivalence:
The Ceribell Seizure Detection Software is validated by evaluating the performance of the Seizure Detection algorithm on a dataset of EEG recordings representative of the intended patient population.
The EEG recordings dataset used for performance validation was gathered from real-world clinical usage of the Ceribell Pocket EEG Device in acute care hospital settings. There were no patient inclusion or exclusion criteria applied, therefore the data are fully representative of the intended patient population. To form the reference standard for seizures, the EEG recordings were retrospectively reviewed by a panel of expert neurologists who were fellowship trained in epilepsy or neurophysiology. A two-thirds majority agreement was required to form a determination of seizures.
The reviewing neurologists did not have access to any of the outputs from the Seizure Detection Software; the experts were fully blinded. Importantly, none of the data in the validation dataset were used for training of the Seizure Detection algorithm; the validation dataset is completely independent.
Details on the validation dataset are provided in the tables below:
PERFORMANCE VALIDATION DATASET
| Age Group | Number of Patients |
|---|---|
| Ages 1-11 | 450 |
| Ages 12-17 | 392 |
| Ages 18+ | 859 |
Page 9
| Total | 1701 |
DISTRIBUTION OF SEIZURE EPISODES MEETING THE ACNS DEFINITIONS OF FREQUENT, ABUNDANT, AND CONTINUOUS PER THE ESTABLISHED MAJORITY AGREEMENT BETWEEN 3 EXPERT REVIEWERS
| Ages 1-11 | Ages 12-17 | Ages 18+ | Total | |
|---|---|---|---|---|
| Seizure Episodes with Seizure Burden ≥10% (meeting ACNS definition of 'Frequent' activity) | 129 | 77 | 140 | 346 |
| Seizure Episodes with Seizure Burden ≥50% (meeting ACNS definition of 'Abundant' activity) | 60 | 22 | 61 | 143 |
| Seizure Episodes with Seizure Burden ≥90% (meeting ACNS definition of 'Continuous' activity) | 27 | 10 | 31 | 68 |
Acceptance Criteria
Performance of the Seizure Detection algorithm was assessed by evaluating the positive percent agreement (PPA) and the false positive rate per hour (FP/hr) of the algorithm compared to the expert reviewer reference standard:
-
Positive Percent Agreement (PPA):
For each threshold of Seizure Burden activity (Frequent, Abundant, Continuous)
Lower bound of the 95% confidence interval ≥ 70% PPA -
False Positive rate per hour (FP/hr):
For each threshold of Seizure Burden activity (Frequent, Abundant, Continuous)
Upper bound of the 95% confidence interval ≤ 0.446 FP/hr
Device Performance
Performance against the acceptance criteria was assessed for the age ranges of 1-11, 2-17 and 18+. The overall performance for all patients was also evaluated. In all cases, the acceptance criteria were met, and the Seizure Detection algorithm PASSES. The detailed results for PPA and FP/hr are shown in the following table:
| Activity Category | Age Group | Positive Percent Agreement (PPA) | 95% Confidence Interval | False Positive Rate (FP/hr) | 95% Confidence Interval | Pass / Fail |
|---|---|---|---|---|---|---|
| Seizure Episodes with Seizure Burden ≥10% (meeting ACNS definition of 'Frequent' activity) | Ages 1-11 | 96.12% | [88.35, 99.28] | 0.2700 | [0.2445, 0.2986] | Pass |
| Ages 12-17 | 87.01% | [73.16, 93.55] | 0.2141 | [0.1920, 0.2394] | Pass |
Page 10
| Activity Category | Age Group | Positive Percent Agreement (PPA) | 95% Confidence Interval | False Positive Rate (FP/hr) | 95% Confidence Interval | Pass / Fail |
|---|---|---|---|---|---|---|
| ACNS definition of 'Frequent' activity) | Ages 18+ | 95.71% | [91.30, 98.43] | 0.1343 | [0.1250, 0.1445] | Pass |
| Overall | 93.93% | [90.03, 96.52] | 0.1763 | [0.1670, 0.1859] | Pass | |
| Seizure Episodes with Seizure Burden ≥50% (meeting ACNS definition of 'Abundant' activity) | Ages 1-11 | 96.67% | [87.50, 100.00] | 0.1561 | [0.1369, 0.1772] | Pass |
| Ages 12-17 | 95.45% | [73.33, 100.00] | 0.0921 | [0.0776, 0.1082] | Pass | |
| Ages 18+ | 96.72% | [88.37, 100.0] | 0.0547 | [0.0480, 0.0615] | Pass | |
| Overall | 96.50% | [92.12, 98.77] | 0.08180 | [0.0754, 0.0885] | Pass | |
| Seizure Episodes with Seizure Burden ≥90% (meeting ACNS definition of 'Continuous' activity) | Ages 1-11 | 92.59% | [76.00, 100] | 0.0843 | [0.0697, 0.1006] | Pass |
| Ages 12-17 | 100.0% | [100, 100] | 0.0399 | [0.0301, 0.0511] | Pass | |
| Ages 18+ | 93.55% | [78.26, 100.0] | 0.0249 | [0.0204, 0.0299] | Pass | |
| Overall | 94.12% | [85.45, 98.48] | 0.03951 | [0.0351, 0.0443] | Pass |
Acceptance Criteria:
PPA: Lower bound of the 95% confidence interval ≥ 70% PPA
FP/hr: Upper Bound of the 95% confidence interval ≤ 0.446 FP/hr
Subgroup Performance
Subgroup analyses were performed to assess the impact of EEG recording duration, site, and, as shown above, age. All subgroup analyses demonstrated acceptable variation among subgroups, supporting performance across the intended use population.
Predetermined Change Control Plan (PCCP):
The Ceribell Seizure Detection Software has been cleared by the FDA with an Authorized PCCP. The Authorized PCCP outlines specific modifications intended to improve algorithm clinical or computational performance through the expansion of training data and optimization of the algorithm. The PCCP outlines Ceribell's data management and algorithm development practices, including how and when performance is evaluated.
The PCCP also defines validation requirements for algorithm updates. Prior to release, the updated algorithm is validated through testing against previously established acceptance criteria using an independent validation data set. Updates will be implemented using a validated Software Update process. When an update is performed, Ceribell will update this operator manual and notify customers of the update.
Conclusions:
The Ceribell Seizure Detection Software has the same intended use as the predicate device. In addition, it has the same technological characteristic, clinical workflow, and underlying operating principles. The expansion of the intended patient age range for the Seizure Detection Software has been validated through performance testing using the same methodology and acceptance criteria as
Page 11
applied to the predicate device. Therefore, the Ceribell Seizure Detection Software is substantially equivalent to the cleared predicate device.