Big Data Analysis in Medicine
The term “Big Data” refers to the amalgamation and processing of huge data sets that are composed of different data types (e.g. clinical, genomic, imaging, pathological, etc.) and have rapidly become more massive and complex, particularly with the advent of new technologies. Big Data within the context of biomedical research is a major problem that needs to be solved due to substantial increases in the amount of medical data routinely generated and collected by healthcare providers over the last two decades. A recent PubMed search for the term “big data” yields 1470 entries, with the earliest occurring in 2003. A breakdown by year shows the majority of publications are from 2012 or later. In 2011, the McKinsey Global Institute issued a 156-page report titled “Big data: The next frontier for innovation, competition, and productivity”. This report indicated $300 billion in potential annual value in Big Data to health care in the U. S., with a shortage of 140,000 to 190,000 individuals with the required deep analytical skills, indicating a need for programs to train the next generation of scientists with the necessary skill set to deal with all aspects of Big Data.
The current main challenge is that our ability to advance medical care and efficiently translate science into modern medicine is bounded by our capacity to process and understand these big data. So, there is an urgent need to develop and integrate new statistical, mathematical, visualization, and computational models with the ability to analyze Big Data in order to retrieve useful information to aid clinicians in accurately diagnosing and treating patients to improve patient outcomes. Thus, the main objective of this proposal is to develop new computational models and implement new state-of-the-art machine learning approaches to analyze and integrate multiple data types for the creation of a decision matrix that aids clinicians in the early diagnosis and identification of high risk patients for human diseases and disorders.
Ayman El-Baz, Ph.D., Professor, Distinguished University Scholar, and Chair of Bioengineering Department at the University of Louisville, KY. Dr. El-Baz earned his bachelor's and master degrees in Electrical Engineering in 1997 and 2001. He earned his doctoral degrees in electrical engineering from the University of Louisville in 2006. In 2009, Dr. El-Baz was named a Coulter Fellow for his contribution in the biomedical translational research. In 2018, Dr. El-Baz was named an American Institute for Medical and Biological Engineering (AIMBE) Fellow for outstanding achievement in medical imaging and outstanding leadership in education, scholarship, and service to the field of bioengineering. In 2020, Dr. El-Baz was named a National Academy of Inventors (NAI, the first one from the Middle East) Fellow for his contribution in the field of Artificial Intelligence (AI) and Medical Imaging (MI). In 2017, Dr. El-Baz was selected by the Biomedical Engineering Society to be an ABET program evaluator. Dr. El-Baz has 21 years of hands-on experience in the fields of bio-imaging modeling, big data, artificial intelligence, assured non-invasive computer-assisted diagnosis systems. His work related to novel image analysis techniques for autism, dyslexia, and lung cancer has earned multiple awards, including the Wallace H. Coulter Foundation Early Career Translational Research Award in Biomedical Engineering Phase I & Phase II, a Research Scholar Grant from the American Cancer Society (ACS), first place at the annual Research Louisville 2002, 2005, 2006, 2008, 2009, 2010, 2011 and 2012 meetings, and the "Best Paper Award in Medical Image Processing" from the prestigious ICGST International Conference on Graphics, Vision and Image Processing (GVIP-2005). He has been invited to present his research on image-based techniques for early diagnosis of lung cancer at the Siemens Research Corporation and Siemens Medical Solutions. As PI/Co-I, he has been awarded 50 grants totaling $29.0 million in funding from sponsors including NIH, DOD, NSF, and the American Cancer Society. I have published 46 books, 178 papers in prestigious high-impact journals, 253 papers in extremely selective peer-reviewed conferences in my field, 214 abstracts, 38 patents, 2 software licensing Technologies, 7 software copyrights, 2 tutorials, and 32 invited talks. Dr. El-Baz has around 15K citations with 58 H-index. Dr. El-Baz mentored/advised 29 students, leading to 15 Ph.D. dissertations and 14 master’s theses. Four of my Ph.D. advisees have won John M. Houchens dissertation awards, and our research group has received 189 national/international awards and travel scholarships.
