Theodoros Zanos, PhD is the head of the Neural and Data Science Lab and an Assistant Professor at the Feinstein Institutes for Medical Research and the Zucker School of Medicine, Hofstra Northwell. He received his Engineering diploma in electrical and computer engineering from the Aristotle University of Thessaloniki in Greece in 2004, his Master of Science and his Doctorate in biomedical engineering from the University of Southern California, Viterbi School of Engineering in 2006 and 2009 respectively. In 2009, Dr. Zanos was recruited as a postdoctoral fellow to work at the Montreal Neurological Institute (MNI), McGill, in Montreal, Canada and in 2016, he joined the Institute of Bioelectronic Medicine at the Feinstein Institutes for Medical Research as the first faculty member and principal investigator.
His current research focuses on developing novel artificial intelligence and machine learning tools to enable early diagnosis, disease severity assessment, and personalization and adaptability of therapies. To this end, his team combines neural and physiological signal processing, machine learning and neurophysiology and big healthcare data analytics. The two main goals of the Neural and Data Science lab are 1) to understand how the nervous system senses the state and affects the function of the immune, metabolic and cardiopulmonary systems, in order to develop neuromodulation devices that are able to diagnose and treat various diseases and conditions and 2) to combine multiple healthcare data modalities (EHR, continuous vitals, imaging, unstructured notes) with cutting edge machine learning methods to develop clinical predictive and diagnostic models.
Dr. Zanos has authored more than 30 peer-reviewed publications with more than 3.5k citations, in journals like Neuron, PNAS, JAMA, Nature Machine Intelligence, npj Digital Medicine, Journal of Neuroscience and others and his research has been featured in PBS, Scientific American, CNET and other media outlets. He has been awarded the Excellence in Research Award in 2018, the Jean Timmins Award in 2012 and the Center of Excellence in Commercialization and Research Award in 2010. He recently led the COVID-19 Northwell Machine Learning group, which rapidly developed and deployed a suite of Machine Learning-based predictive models that augmented healthcare resources by guiding clinical decision-making, in order to improve both operations- and patient-centered outcomes during the pandemic and beyond.
Machine Learning in Bioelectronic Medicine and Clinical Predictive Models
One of the most exciting areas of healthcare research lies at the intersection of artificial intelligence and medicine. At the Neural and Data Science lab, we are combining the ever-expanding power of machine learning methods with ever-increasing healthcare data and new medical device technologies that aim to replace drugs with electrons. We aim to develop a new way to diagnose and treat diseases using data, algorithms and electricity. I will provide an overview of some ways that machine learning methods can be the foundation of new technologies that will enable early diagnosis of diseases, prediction of clinical deterioration and personalization of bioelectronic therapies. I will also give an example of how we used “emergency” machine learning, to provide clinical insights and decision support during the early months of the COVID-19 pandemic and the numerous challenges such an effort entails.