Machine Learning for Diagnosis of Cardiovascular & Infectious Diseases
Cardiovascular diseases are commonly diagnosed by cardiologists via inspecting electrocardiogram waveforms, these decisions can be supported by a data-driven automatic approach. Infectious diseases, such as hand foot and mouth disease (HFMD) and tetanus are serious infectious diseases in the developing world. While tetanus has a high mortality rate, HFMD often affects a large number of infants and young children. Autonomic nervous system dysfunction (ANSD) is the main cause of death for infectious disease patients; however, its detection is difficult at early stages. This presentation aim to provide a proof-of-principle to detect the cardiovascular abnormality an ANSD level automatically by applying machine learning methods to physiological patient data, which can be collected using low-cost wearable sensors.
Girmaw completed his PhD at Queen Mary College, University of London under the Erasmus Mundus Joint Doctorate Program in Interactive and Cognitive Environments with UPC-BarcelonaTech. His PhD research focused on computer vision and machine learning algorithms for human activity recognition using wearable sensors. He also investigated the hierarchical and temporal modelling of activities in first-person vision and the integration of multiple modalities using deep neural networks. Girmaw is interested in developing deep learning techniques for healthcare applications including cardiovascular disease, cancer, and infectious diseases. His research involves close collaboration with clinicians in China and Vietnam.