STTR Phase I: A Wearable Carbon Nanotube Sensor Array for Accurate Seizure Prediction Via Measurement of Pre-seizure Volatile Organic Compounds

The broader impact/commercial potential of this Small Business Technology Transfer (STTR) Phase I project is the development of the first scalable, non-invasive wearable device capable of predicting epileptic seizures 10–45 minutes before onset. Epilepsy affects more than 3.4 million people in the United States, and existing technologies detect seizures only after they begin, offering little opportunity for prevention. By enabling advance warning, this technology has the potential to reduce seizure-related injuries, emergency interventions, and loss of independence during high-risk activities such as driving, bathing, or sleeping. Commercially, the project advances a differentiated wearable platform addressing a critical unmet need in epilepsy management that is not served by current detection devices. The technology is positioned for entry into both clinical and direct-to-consumer markets through a sustainable subscription-based model, with long-term opportunities for reimbursement alignment. Successful commercialization would establish a new category of predictive neurological monitoring, drive growth in U.S.-based medical device manufacturing, and create a foundation for broader applications of chemical biosensing in acute neurological and cardiovascular conditions. This Small Business Technology Transfer (STTR) Phase I project seeks to transform seizure monitoring from reactive detection to proactive prediction by developing a wearable device that detects a validated panel of nine pre-seizure volatile organic compounds (VOCs) emitted from the skin prior to seizure onset. Current seizure monitors rely on indirect physiological signals that are highly confounded by normal activity, resulting in high false-positive rates and minimal warning time. The project will leverage a functionalized carbon nanotube field-effect transistor (CNT-FET) sensor array with sub-ppb sensitivity, combined with machine-learning algorithms, to recognize preictal VOC patterns. Phase I objectives include optimizing sensor selectivity and stability, integrating the sensor array into a wearable prototype, and collecting synchronized VOC and EEG data in an epilepsy monitoring unit to train and refine predictive algorithms. Sensor outputs will be benchmarked against gas chromatography–mass spectrometry to validate accuracy and reproducibility. Anticipated outcomes include a validated wearable prototype and a predictive model achieving clinically meaningful accuracy, establishing feasibility for Phase II clinical validation and commercialization. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria. NSF Award ID: 2604491 | Program: 01002627DB NSF RESEARCH & RELATED ACTIVIT | Principal Investigator: Ashley Galanti | Institution: AMG DETECTION, INC., DULUTH, GA | Award Amount: $305,000 View on NSF Award Search: https://www.nsf.gov/awardsearch/show-award/?AWD_ID=2604491 View on Research.gov: https://www.research.gov/awardapi-service/v1/awards/2604491.html