Cardiorespiratory diseases such as COPD are constituting a big burden in our society. The COVID-19 pandemic has caused increased problems in multimorbid cardiorespiratory patients due to the very nature of the virus that primarily affects the lung function, the endothelium and the overall cardiorespiratory function. Over the past couple of years numerous studies used AI for classification of healthy vs COVID-19 infected subjects using imaging modalities such as X-Rays, CT-Scans, MRIs and US. In this talk we will present a new annotated database from 176 ICU COVID-19 patients including traditional ICU parameters and scores (e.g. APACHE, SOFA), lung sounds, heart sounds and X-Rays. The database was developed using an advanced FHIR and cloud based EHR installed in Thessaloniki and Athens with the acronym CoCross. AI/ML techniques were used to extract the feature vectors from lung sounds recorded with a digital stethoscope, from X-Rays in patients with ARDS, and from the ICU bioparameters and biosignals. Fusing all these features using an AI pipeline provided the best AUC and Accuracy (76%) as it concerns the outcome prediction of the COVID-19 patients. This AI/ML system can evolve in using it in COVID-19 clinics and in post-COVID syndrome since it has identified specific spectral features of adventitious sounds (e.g. squawks, crackles and ronchi) that can be reused in predicting deterioration and complications in multimorbid COVID-19, COPD and CVD/HF patients.
Nicos Maglaveras received the diploma in electrical engineering from the Aristotle University of Thessaloniki (A.U.Th.), Greece, in 1982, and the M.Sc. and Ph.D. degrees in electrical engineering with an emphasis in biomedical engineering from Northwestern University, Evanston, IL, in 1985 and 1988, respectively. He is currently a Professor and Director at the Lab of Computing & Medical Informatics, A.U.Th. He is head of the graduate program in medical informatics at A.U.Th, and is a collaborating researcher with the Center of Research and Technology Hellas, the Hellenic Institute of Transportation (CERTH-HIT). His current research interests include biomedical engineering, cardiovascular engineering, biomedical informatics, ehealth, AAL, personalised health, biosignal analysis, medical imaging, and neurosciences. He has published more than 400 papers in peer reviewed international journals, books and conference proceedings out of which over 130 as full peer review papers in indexed international journals. He has developed graduate and undergraduate courses in the areas of (bio)medical informatics, biomedical signal processing, physiology and biological systems simulation. He has served as a Reviewer in CEC AIM, ICT and DGRT D-HEALTH technical reviews and as reviewer, associate editor and editorial board member in more than 10 international journals, and participated as Coordinator or Core Partner in over 40 national and EU-funded competitive research projects attracting more than 15 MEUROs in funding. He has served as president of the EAMBES in 2008-2010. Dr. Maglaveras has been a member of the IEEE, AMIA, the Greek Technical Chamber, the New York Academy of Sciences, the CEN/TC251, Eta Kappa Nu and an EAMBES Fellow.
