Our team specializes in real-time computer assisted monitoring of electroencephalograms (EEGs) in the intensive care unit (ICU). In previous work, we have demonstrated a clear and urgent market for such technology, and we have created a proof-of-concept solution using state-of-the-art machine learning tools. We have also developed a community of stakeholders, partners, and collaborators to aid us in bringing our tools to market. We seek to further prepare our technology for market by (a) adapting our existing offline tools into a real-time application, and (b) further reducing our false alarm rates. We continue to engage with our various partners in order to strengthen our commercialization and marketing strategy.
We use cutting edge deep learning software trained on the world's most comprehensive EEG data archive. The result is a software tool that can detect seizures in the ICU at a level of performance similar to that of trained neurologists. Critically, we can detect seizures with a sensitivity of 50% with 2.5 false alarms per 24 hours. We know from our extensive market research that this level of performance is reasonably close to the performance required for clinical acceptance, and outperforms tools with similar features that are already on the market.