Seminal
The magazine and atlas of EU-funded researchA new publication from the web and AI team at Scott Charnley

Atlas / Portugal

Coordination and Support Action · Running

LAMP-AI LAMP-AI : Contactless AI for Night-time Epilepsy Safety

Coordinator
Lampsy Health, Lda, Portugal
Runs
1 July 2026 to 30 June 2028
Status
Running
EU funding
€351k
Total cost
—
Partners
1 organisations in 1 countries
Type
Coordination and Support Action
Grant agreement
101310739

What the project is doing

In the project's own words, from its summary on CORDIS.

Epilepsy affects over 65 million people worldwide, and nocturnal generalized tonic–clonic seizures significantly increase the risk of SUDEP. Although more than 90% of caregivers express interest in seizure-monitoring technologies, only 12% currently use one, due to discomfort, stigma, or privacy concerns associated with existing wearable or camera-based solutions. Lampsy Health introduces LAMP-AI, an AI-powered ambient monitoring system that identifies seizure-specific movement patterns without physical contact.

Its proprietary computer-vision algorithm, validated on over 2,200 hours of clinical recordings, runs fully on-device to ensure GDPR-compliant, privacy-preserving operation. The solution is patent protected. LAMP-AI brings to market the first contactless, privacy-preserving, clinically validated device for real-time nocturnal seizure detection, discreetly integrated into a household lamp. Through the EIC Pre-Accelerator execution, LAMP-AI will advance the device to a CE-ready Class IIa medical product together with the deployment in hospital and home pilots with leading epilepsy centres.

LAMP-AI will improve safety and quality of life for people with epilepsy, reduce caregiver burden, and accelerate Lampsy Health’s path toward market entry and follow-on investment across Europe

Who is involved

OrganisationCityCountryRole
Lampsy Health, LdaLisboaPortugalCoordinator

Source: CORDIS, European Commission. Data of 5 Nov 2026, reused under the Commission's reuse policy. View on CORDIS · Grant DOI