MedAI Verdict
Decision support

Clinical Decision Support

Ceribell logo

Ceribell

by Ceribell  ·  US

Last verified

Point-of-care EEG headband with AI seizure detection and a delirium monitor, for hospitals, ICUs and emergency departments.

At a glance

Pricing
No public price. Purchase terms: one-year initial term, auto-renewing yearly unless 90 days notice.
HIPAA
Not disclosed
SOC 2
Not disclosed
EHRs
—
Founded
—
HQ
US
On this page

Independent score  ·  By our public rubric

49/100Solid choice

Editorial rating 3.5 / 5

How it’s computed →
  • Regulatory & Compliance
    12/22

    FDA cleared (16 K-numbers on record)

  • Clinical Integration
    0/11.6

    No EHR integrations listed

  • Evidence Strength
    19.2/30

    4 peer-reviewed papers

  • Vendor & Market
    8.4/18

    Mid-tier funding and adoption

  • Sentiment & Transparency
    1.3/2.5

    Pricing on request, no public amounts

▸ Show all 11 dimensions

Regulatory & Compliance

  • FDA clearance12/12

    FDA cleared (16 K-numbers on record)

  • HIPAA / SOC2 / BAA0/10

    No public HIPAA/SOC2/BAA attestation

Clinical Integration

  • EHR integrations (count)0/6

    No EHR integrations listed

  • Top-3 EHR coverage (Epic / Oracle / Athena)0/5

    None of the top-3 EHRs covered

  • Bidirectional write-back0/1

    No bidirectional write-back documented

Evidence Strength

  • Peer-reviewed papers15/21

    4 peer-reviewed papers

  • RCT / meta-analysis / systematic review5/9

    2 observational study (no RCT)

Vendor & Market

  • Funding & adoption signal8/12

    Mid-tier funding and adoption

  • Years in market0/6

    Founded year not recorded

Sentiment & Transparency

  • Pricing transparency1/3

    Pricing on request, no public amounts

Scored November 2, 2026 · Public scoring method v1.2.0

Point-of-care EEG headband with AI seizure detection and a delirium monitor, for hospitals, ICUs and emergency departments.

No public price. Purchase terms: one-year initial term, auto-renewing yearly unless 90 days notice.

Evidence record

FDA decisions
Show 11 more
Peer-reviewed

4 studies on PubMed: 2 observational, 2 other, published 2023 to 2026. Read the literature summary

Verification
  • Score computed November 2, 2026, method 1.2.0
  • Review written November 2, 2026
Cite this record

MedAI Verdict, Ceribell record, https://medaiverdict.com/tools/ceribell, version November 2, 2026

Bottom line

Sixteen FDA 510(k) decisions stand behind Ceribell, a Nasdaq-listed company (CBLL) in Sunnyvale that sells a point-of-care EEG headband with software for seizure and delirium monitoring. It fits an ICU or emergency department that wants EEG at the bedside without waiting for a formal study. The vendor says the device does not substitute for review by a qualified clinician, so a hospital hoping to cut clinician EEG interpretation from the workflow should look elsewhere. The homepage advertises 95% sensitivity and 97% specificity for status epilepticus detection, which are the vendor's figures.

Which clearances sit behind it?

The FDA database lists 16 substantially equivalent decisions, from K170363 (May 8, 2017, Ceribell Pocket EEG Device) to K261712 (September 16, 2026, EEG Analysis Software). They cover headbands, headcaps, a status epilepticus monitor, a brain monitor and review software. On the software side, K241589 (April 9, 2025) is the Seizure Detection Software and K252070 (November 21, 2025) is the Infant Seizure Detection Software.

The vendor does not name the clearance for its delirium score. K251936 (December 8, 2025), titled Delirium Monitor System, is the only matching FDA record.

What do the algorithms do?

The Clarity page says the seizure software alerts on suspected continuous seizure activity and non-convulsive status epilepticus, estimating seizure burden every 10 seconds from the prior five minutes. The vendor calls it the first and only FDA-cleared AI for detecting electrographic seizures in all ages, from 25-week preterm neonates to adults. The same page describes a delirium model on quantitative EEG features that updates a delirium-biomarker score every 10 seconds. A remote portal shows seizure burden and delirium trends.

What does the literature say?

PubMed lists 29 papers with Ceribell in the title or abstract, and the vendor counts 45 peer-reviewed publications as of October 2025. DECIDE, a multicenter prospective study of rapid-response EEG, appeared in Critical Care Medicine in 2020 (PMID 32618687). Later work covers seizure burden against discharge outcome (Critical Care Medicine 2026, PMID 42223304), prediction of postoperative delirium from point-of-care EEG (2026) and a 2021 economic value model.

What does a purchase involve?

The purchase terms leave fees to each order, paid in advance on net 30 terms, with a one-year initial term that renews yearly unless the buyer gives 90 days' notice. A lost loaned recorder must be reimbursed at $2,500, and no general return or refund policy is stated. The vendor offers a free demo. CMS has set a New Technology Add-on Payment of up to $2,171 incremental for the delirium solution from October 1, 2026, according to the Clarity page.

What does the company report?

In its second-quarter 2026 release, dated August 10, 2026, Ceribell reported $28.1 million in revenue, up 33% year on year, and 712 total active accounts. The homepage cites a FedRAMP High authorization and says the company is in litigation against Natus, a competitor.

The verdict

A hospital that routinely waits on formal EEG for suspected seizures is the clearest match. The delirium function is the newer piece, with a CMS add-on payment from October 1, 2026 and no K number named by the vendor.

Editorial review last generated November 2, 2026. Synthesized from clinician sentiment, peer-reviewed coverage, and our editorial silo picks. Refined by hand where vendor facts change.

What it costs

All tiers are custom-quoted. The vendor does not publish per-provider list pricing.

TierMonthlyAnnualNotes
EnterpriseNot statedNot statedNo public price. Purchase terms: one-year initial term, auto-renewing yearly unless 90 days notice.

Source: vendor pricing page. Last checked November 2, 2026.

What deploys cleanly

Carries FDA 510(k), FedRAMP High per vendor documentation. Independent attestation review is the buyer's responsibility before clinical deployment.

What the literature says

4 peer-reviewed studies indexed on PubMed evaluate Ceribell in clinical contexts. The most relevant are shown below, ranked by editorial relevance score combining title match, study design, recency, and journal tier.

Automated Seizure Detection in Patients with Cardiac Arrest: A Retrospective Review of Ceribell™ Rapid-EEG Recordings. (opens in new tab)
Villamar MF, Ayub N, Koenig SJ· Neurocrit Care· 2023
In patients with cardiac arrest who remain comatose after return of spontaneous circulation, seizures and other abnormalities on electroencephalogram (EEG) are common. Thus, guidelines recommend urgent initiation of EEG for the evaluation of seizures in this population. Point-of-care EEG systems, such as Ceribell™ Rapid Response EEG (Rapid-EEG), allow for prompt initiation of EEG monitoring, albeit through a reduced-channel montage. Rapid-EEG incorporates an automated seizure detection software (Clarity™) to measure seizure burden in real time and alert clinicians at the bedside…
Point-of-Care EEG Artificial Intelligence Measure of Seizure Burden Associates With Clinical Outcome at Discharge. (opens in new tab)
Parvizi J, Armenta Salas M, Aparicio MK, et al.· Crit Care Med· 2026Observational
Point-of-care (POC) electroencephalography (EEG) enabled with artificial intelligence (AI) algorithms hold the potential to address gaps in EEG access and interpretation. We assessed the clinical association of the patterns recognized by one of such systems. Secondary cohort analysis of the retrospective multicenter Seizure Assessment and Forecasting with Efficient Rapid-EEG (SAFER-EEG) study. EEG and clinical data were gathered from three academic centers with access to POC EEG (Ceribell, Sunnyvale, CA) as part of their standard of care. We used a bedside seizure burden (SzB) monitor ("bedsi…
Assessing the performance of artificial intelligence in detecting electrographic status epilepticus when human experts often disagree. (opens in new tab)
Alsherbini K, Armenta Salas M, Karunakaran S, et al.· Front Neurol· 2026
Generating reference standards to train and evaluate the accuracy of artificial intelligence (AI) algorithms poses a significant challenge. Particularly when interpreting complex signals like electroencephalography (EEG), where interrater variability is considerable. We aimed to characterize the impact of interrater variability when evaluating the performance of an AI algorithm for detecting electrographic status epilepticus in point-of-care (POC) limited-montage EEG. We analyzed 604 EEGs collected using a POC EEG system (Ceribell Inc.). Each EEG was independently reviewed by 5-7 blinded expe…
Accuracy of the rapid-response electroencephalography's Automated Seizure Burden Estimator: A follow-up validation study of version 8 (AccuRASE II). (opens in new tab)
Sheikh ZB, Fong MWK, Dhakar MB, et al.· Epilepsia· 2026Observational
Ceribell Inc.'s point-of-care electroencephalographic (EEG) system and artificial intelligence-based Automated Seizure Burden Estimator (ASBE; ClarityPro) have US Food and Drug Administration clearance for diagnosing electrographic status epilepticus (ESE). The AccuRASE study using ASBE version 6 (V6) showed high negative predictive value (NPV) but limited sensitivity and positive predictive value (PPV) at certain thresholds. Version 8 (V8) is the updated algorithm trained with additional EEG samples. We tested V8 on the previously used rapid-response EEG test dataset (not used to train V8).…

See all on PubMed (opens in new tab)