Tutorial PM5

PM5: Data-Driven Healthcare: Applications to Neurology, Psychiatry and Opthalmology

Keshab K. Parhi, University of Minnesota

Abstract: Availability of large amount of data and computing resources continue to pave the way for data-driven healthcare that was not possible before. Both traditional and deep machine learning methods will play important roles for data-driven healthcare. This tutorial will present a brief review of machine learning methods and their applications to data-driven healthcare. Signal processing approaches for feature selection will be reviewed. Methods to rank features will be discussed. Datadriven healthcare applications from neurology, psychiatry and ophthalmology will be discussed. In the context of neurology, applications of signal processing and machine learning will be demonstrated for applications such as patient-specific seizure prediction and detection using scalp and intra-cranial electroencephalogram (EEG). Applications of causality and network analysis approaches to identify seizure focus will be discussed. Effective seizure prediction can enable closed-loop neuromodulation based on implantable devices. In the context of psychiatry, approaches to discovering biomarkers for schizophrenia from magnetoencephalogram (MEG) will be discussed. Then discovery of local and global biomarkers for mental disorders from functional MRI (fMRI) will be presented. Examples of mental disorders include: borderline personality disorder (BPD), major depressive disorder (MDD) and obsessive compulsive disorder (OCD). Machine learning applications for ophthalmology will address diabetic retinopathy screening, age-related macular degeneration (AMD), and diabetic macular edema (DME) from fundus camera images and optical coherence tomography (OCT) images. Finally, a review of various applications of deep learning for healthcare will be presented.


Keshab K. Parhi

He (Fellow’1996) received the B.Tech. degree from the Indian Institute of Technology (IIT), Kharagpur, in 1982, the M.S.E.E. degree from the University of Pennsylvania, Philadelphia, in 1984, and the Ph.D. degree from the University of California, Berkeley, in 1988. He has been with the University of Minnesota, Minneapolis, since 1988, where he is currently Distinguished McKnight University Professor and Edgar F. Johnson Professor in the Department of Electrical and Computer Engineering. He has published 600 papers, is the inventor of 29 patents, and has authored the textbook VLSI Digital Signal Processing Systems (Wiley, 1999) and coedited the reference book Digital Signal Processing for Multimedia Systems (Marcel Dekker, 1999). Dr. Parhi is widely recognized for his work on high-level transformations of iterative data-flow computations, for developing a formal theory of computing for design of digital signal processing systems, and for his contributions to multi-gigabit Ethernet systems on copper and fiber and for backplanes. His current research addresses VLSI architecture design of signal processing systems, hardware security, and molecular computing. He is also currently working on intelligent classification of biomedical signals and images, for applications such as seizure prediction and detection, schizophrenia classification, biomarkers for mental disorders, brain connectivity, and diabetic retinopathy screening.  Dr. Parhi is the recipient of numerous awards including the 2017 Mac Van Valkenburg award and the 2012 Charles A. Desoer Technical Achievement award from the IEEE Circuits and Systems Society, the 2004 F. E. Terman award from the American Society of Engineering Education, the 2003 IEEE Kiyo Tomiyasu Technical Field Award, the 2001 IEEE W. R. G. Baker prize paper award, and a Golden Jubilee medal from the IEEE Circuits and Systems Society in 2000. He is a Fellow of IEEE (1996) and the American Association for Advancement of Science (AAAS) (2017). He served as the Editor-inChief of the IEEE Trans. Circuits and Systems, Part I during 2004-2005, as Chair of the VLSI Systems and Applications Technical Committee during 2002-2004, and as an elected member of the Board of Governors of the IEEE Circuits and Systems society from 2005 to 2007.