Clinical Data and Supporting Evidence: Clarity™ Validation
Clarity has been validated to consistently alert for suspected status epilepticus and rule out seizures
Ceribell with Clarity was demonstrated to differentiate EEGs with and without status epilepticus with high sensitivity and specificity.1,2
Understanding the Clarity AI Algorithm
Clarity is a machine learning algorithm within the Ceribell system that has been trained on thousands of hours of expert annotated critical care EEGs with the goal of alerting to or ruling out life-threatening continuous seizures also known as status epilepticus.
Study Design and Methods2
Retrospective assessment of 1148 clinical EEGs from adult patients, who underwent evaluation with point-of-care EEG system
The analysis assessed the performance of Ceribell with Clarity to triage seizure activity compared to expert reviews
Key Results2
Clarity for detection of status epilepticus
Clarity detected ≥ 90% seizure burden, thereby triggering an alert for suspected status epilepticus, in 20 out of 21 cases
Clarity for ruling out status epilepticus and seizures*
Of the 778 EEG recordings in which Clarity detected no seizures, seizures were identified by the expert reviewers in only 3 cases.
*At 0% seizure burden
Seizure Burden Yield2
- 4% of EEGs resulted in bedside alerts (≥90% seizure burden)
- 28% of EEGs had short, less than 4.5 minutes, seizures or possible seizure that did not result in a bedside alert (1%-89% seizure burden)
- 68% of EEGs likely had no ongoing seizure activity (0% seizure burden)
Resources
In The News
Webinar
Mountainview Hospital: Clarity detected NCSE and Persistent Seizure Activity was Aborted
Watch Our WebinarWebinar
References and Citations
1. Kamousi, B., et al. (2021) Neurocrit Care. 34(3):908-917
2. Karunakaran, S., et al, (2024) AES 2024 Annual Meeting Poster.