EpiFocus, LLC
Where quantitative analysis meets clinical monitoring and treatment.
Purpose
EpiFocus LLC is a neuroscientific datamining company founded to provide practical diagnostic and disease assessment tools from a data driven perspective, enhancing clinical treatment and patient outcomes.​
​
EpiFocus LLC is the product of strong pre-clinical and clinical research initiated and overseen by Dr. Leon Iasemidis, a world leader in non-linear dynamics and seizure prediction, and Dr. Noah Hutson, expert in multimodal systems analysis. Through combination of complex signal processing and analysis, and excellent clinical monitoring, EpiFocus develops technology for automated and semi-automated diagnosis and assessment of a wide variety of conditions utilizing current clinical equipment. We leverage data recorded from multiple organ systems, and take a holistic approach to quantitative analysis of biosignals.
Latest Publications
​In this study, we explored the possibility of developing non-invasive biomarkers for patients with type 1 diabetes (T1D) by quantifying the directional couplings between the cardiac, vascular, and respiratory systems, treating them as interconnected nodes in a network configuration. Towards this goal, we employed a linear directional connectivity measure, the directed transfer function (DTF), estimated by a linear multivariate autoregressive modelling of ECG, respiratory and skin perfusion signals, and a nonlinear method, the dynamical Bayesian inference (DBI) analysis of bivariate phase interactions. The physiological data were recorded concurrently for a relatively short time period (5 min) from 10 healthy control subjects and 10 T1D patients. We found that, in both control and T1D subjects, breathing had greater influence on the heart and perfusion with respect to the opposite coupling direction and that, by both employed methods of analysis, the causal influence of breathing on the heart was significantly decreased (p < 0.05) in T1D patients compared to the control group. These preliminary results, although obtained from a limited number of subjects, provide a strong indication for the usefulness of a network-based multi-modal analysis for the development of biomarkers of T1D-related complications from short-duration data, as well as their potential in the exploration of the pathophysiological mechanisms that underlie this devastating and very widespread disease.
News & Events
Coming Soon!