K-numberK241589
Device nameCeribell Seizure Detection Software
ApplicantCeribell, Inc.
Product codeOMB
Device classClass II
Decision dateApr 9, 2025
DecisionSubstantially Equivalent
Regulation882.1400
AI Summary extracted from FDA summary PDF · never regenerated
Intended use

The Ceribell Seizure Detection Software is a software-only device that analyzes previously recorded EEG data to automatically mark sections that may indicate electrographic seizures, assisting qualified clinicians in EEG assessment. It provides notifications when detected seizure prevalence meets American Clinical Neurophysiology Society definitions of 'Frequent,' 'Abundant,' or 'Continuous,' and is intended for patients age 1 year and older in professional healthcare facilities.

Technological characteristics

The subject device is a software-only seizure detection tool with no hardware component, whereas the predicate device (Ceribell Pocket EEG K191301) is a complete portable EEG monitoring system. Both share the same seizure detection algorithm logic and clinical workflow. The subject device expands the approved age range from ≥8 years to ≥1 year, with an updated and clinically validated algorithm for the broader pediatric population.

Test standards cited

IEC 62366-1:2015 (Medical Devices—Application of usability engineering to medical devices) and FDA Guidance for Industry on Content of Premarket Submissions for Device Software Functions were applied. Performance validation used expert neurologist panel review with two-thirds majority agreement as reference standard.

Substantial equivalence argument

The device shares identical intended use (marking potential seizures to assist clinician assessment), same technological characteristics, clinical workflow, and underlying operating principles as the predicate. The key difference—expansion to patients age 1 year or older versus ≥8 years—does not raise new safety or effectiveness questions because clinical performance testing on 1,701 patients across all age groups (1–11, 12–17, 18+) demonstrated consistent algorithm performance exceeding acceptance criteria across all age cohorts, with positive percent agreement ≥87% and false positive rates ≤0.27/hour.

Extracted by AI from the official FDA summary PDF →
Source

View the full FDA submission: accessdata.fda.gov

Researching this as a predicate?
Want a transparent AI-ranking score, AI-discovered related predicates, ongoing safety and warning-letter monitoring, full predicate chain lineage, and a drafted SE rationale — all saved to your own project? That's what an account adds.
Start free trial →

Everything you need for a 510(k) submission. Nothing you don't.

14-day free trial. No setup. Cancel anytime.

Start free trial →
Building an AI or ML-enabled device? Predicate search, PCCP tracking, and AI-specific FDA intelligence — built exclusively for AI/ML devices. Try AIFDA Intel →