Upcoming Events

Early detection of malign patterns in patients’ biological signals can save millions of lives. Despite the steady improvement of AI-based techniques, the practical clinical application of these methods is mostly constrained to an offline evaluation of the patients’ data. Previous studies have identified organic electrochemical devices (OECTs) as ideal candidates for biosignal monitoring [1,2]. However, their use for pattern recognition in real-time was never demonstrated. I will show how OECTs can be employed to produce and characterize brain-inspired networks composed of polymeric dendritic fibers [3] and employ them for classification tasks[4]. The machine learning approach known as reservoir computing is ideal for such applications. For instance, analysis of heartbeats resulted in the classification of 4 classes of arrhythmic heartbeats with an accuracy of 88%. With the same architecture, biofluids e.g., blood, can be actively monitored. The aim of this study is to introduce a novel paradigm for biocompatible computational platforms and may enable the development of ultra-low power consumption hardware-based artificial neural networks capable of interacting with body fluids and biological tissues.

For more information click here