With the decision, ClarityPro becomes the first and only device to offer new technology add-on payment reimbursement for the diagnosis of electrographic status epilepticus.
The FDA granted 510(k) clearance to Ceribell’s new software, ClarityPro, for the diagnosis of electrographic status epilepticus (ESE) in adults over the age of 18, becoming the first such tool available. Subsequently, the US Centers for Medicare and Medicaid Services (CMS) gave new technology add-on payment (NTAP) for ClarityPro for up to $913.90 per eligible Medicare patient case.
This point-of-care EEG system delivers real-time seizure monitoring with around-the-clock alerts, enabling more precise treatment of patients with suspected non-convulsive seizures. The only such device to diagnose ESE according to the American Clinical Neurophysiology Society definition of ESE, ClarityPro utilizes a machine learning algorithm to analyze EEG signals and generate bedside alerts.
"These decisions from the FDA and CMS are further validation that Ceribell's clinical impact is significant for patients," Jane Chao, PhD, co-founder and chief executive officer at Ceribell, said in a statement. "This dedicated reimbursement from CMS will also expand access to this vital technology to more Americans, especially seniors and critically ill patients who are more likely to suffer from neurological illnesses."
With the decision, ClarityPro becomes the first and only intensive care unit monitoring device to receive CMS NTAP reimbursement, which is expected to become available on October 1, 2023. The idea behind ClarityPro is that it will streamline the EEG review process by flagging all portions of the EEG that could contain seizures or other areas of concern, enabling more faster and more confident triage. Prior to its approval, it received breakthrough device designation.
A 2021 retrospective study published in Neurocritical care featured 353 patients who underwent evaluation of possible seizures. Otherwise known as the CLARITY study, the trial spanned across 6 US hospitals with 1052 hours of EEG examined. A majority of the neurologists labeled the EEGs as normal or slow activity (n = 249), highly epileptiform patterns (HEP; n = 87) or seizures (n = 17; 9 longer than 5 minutes and 8 shorter than 5 minutes).
Findings showed that Clarity detected more than 90% of seizure burden, thereby triggering an alert for impending status epilepticus, in 9 out of 9 cases, equating to a 100% sensitivity. Of the 179 EEG recordings in which Clarity detected no seizures, seizures were identified by the expert reviewers in only 2 cases. In both cases, the seizures were less than 30 seconds in duration, indicating a negative predictive value of 99%.
In the study, the specificity of seizure burden notification more than 90% was 93.0%, resulting in a false detection for 24 of 353 EEGs. In 21 (87.5%) of these false detections, the expert consensus categorization of the EEG was HELP, indicating that there was concerning epileptiform activity present in the record, even if no unequivocal seizures were agreed to be present by both reviewers.
When the 4 reviewers identifications of status epilepticus were compared with the majority consensus, individual expert rates displayed variability in both sensitivity (range, 20-89%) and specificity (range, 94-99%). Each expert reviewed a different subset of the 353 total recordings. Overall, experts displayed greater specificity compared with Clarity, and each of the reviewers misclassified at least 1 case of status epilepticus.
At the conclusion of the analysis, investigators wrote "Claritγ provides highly sensitive detection of status epilepticus and may be useful as a risk stratification tool that could expedite diagnosis and treatment of patients with nonconvulsive seizures. We believe that machine learning tools will never replace a careful history and examination filtered through a well-honed clinical acumen of the user and recommend its safe use by interpreting its output in the context of proper clinical judgment."