Neurava has been awarded a $4 million NIH Blueprint MedTech Optimizer grant to advance the development of an AI-driven risk stratification algorithm for sudden unexpected death in epilepsy (SUDEP), a leading cause of mortality among epilepsy patients.
The project aims to build a predictive platform that integrates multiple physiological signals, including cardiac, respiratory, and oxygenation data, to assess and forecast SUDEP risk. Unlike conventional approaches that primarily detect seizures, the system aims to move toward a more proactive risk prediction and early intervention.
SUDEP remains a critical and poorly understood complication of epilepsy, with current monitoring solutions offering limited ability to quantify individual patient risk. By leveraging machine learning and multimodal data streams, Neurava’s approach seeks to provide clinicians and caregivers with actionable insights that can inform care decisions and potentially prevent fatal outcomes.
The award is part of the NIH Blueprint MedTech programme, which supports the translation of innovative neurotechnology solutions from concept to clinical application. The funding will enable Neurava to further develop and validate its algorithm, with a focus on demonstrating clinical utility and advancing toward regulatory pathways.
The platform builds upon emerging research identifying key biomarkers associated with SUDEP risk, particularly those linked to cardiorespiratory dysfunction. By incorporating these indicators into a unified monitoring and prediction system, the technology represents a shift from reactive seizure management to a more comprehensive, predictive model of epilepsy care.
The development indicates trends in digital health and neurotechnology, where AI-enabled analytics are being applied to continuous patient monitoring data to improve outcomes. In epilepsy care, such advancements could play a significant role in reducing uncertainty and improving long-term disease management.
As the platform enters development, its success will depend on demonstrating reliable risk prediction and achieving clinical adoption, positioning it as a potential new standard in epilepsy monitoring and preventive care.
