Text Similarity Searching: From reference finding, to ethics studies to clinician decision support systems
The final DUKE/UNC Joint Health Informatics Seminar of the spring.
Title: Text Similarity Searching: From reference finding, to ethics studies to clinician decision support systems
Presenter: Dr. Harold "Skip" Garner
The Garner Lab has developed a new way to search text and compare documents using a new search engine, eTBLAST (etblast.org). This search engine can be used to find new, related and therefore relevant information. This new search approach has been used to help researchers find better literature, find inappropriately similar literature and identify plagiarized papers in MedLine. The results of our work have been reported in Nature, Science and elsewhere. Most recently we have used eTBLAST to find and associate text from the medical literature, clinical trials, and other sources to create an automated system for delivering decision support information automatically from the analysis of a patients evolving Electronic Health Record.
Dr. Garner received his BS in Nuclear Engineering (minor in computer science) at the University of Missouri - Rolla in 1976. He received a Ph.D. in plasma/high temperature matter physics from the University of Wisconsin, Madison in 1982. He also holds an honorary professional engineering degree.
Dr. Garner worked for General Atomics from 1982 to 1994. In 1994 he joined the University of Texas Southwestern Medical (UTSW) Center as the P. O’B. Montgomery, M.D. Distinguished Chair, and Professor of Biochemistry and Internal Medicine where he was a founding member of 3 centers, and was chair of the Biomedical Engineering Graduate Program. While at UTSW he developed three primary lines of applied bioinformatics research: text data mining; advanced data analytical techniques for data intensive “-omics” research areas; and new compute and analytic technologies for genomics biomarker and drug discovery focused on cancer and neurological diseases. These lines of research grew after his move in 2009 to Virginia Tech to assume the Director of the Medical Informatics Division of the Virginia Bioinformatics Institute. He is a professor in the departments of Biological Sciences, Computer Science, and the School of Medicine. Additional information as to his laboratory’s research and on-line computational resources can be found on the World Wide Web at http://innovation.vbi.vt.edu <http://innovation.vbi.vt.edu> .
He is a founder of several biotech companies, including Helix, BioAutomation, Light Biology now Nimblegen/Roche, Xanapath, HelioText and Genomeon and sits on numerous corporate advisory boards and advises for numerous governmental agencies. Dr. Garner holds over 20 national and international patents, and was the inventor of the text based similarity searching and hypothesis generation technologies that are the underlying methods and applications for this proposal. Dr. Garner has made contributions to 10 books and has over 160 peer-reviewed publications.
Duke University Health System Clinical Education & Professional Development is authorized by IACET to offer .1 CEU per presentation to participants who attend the entire presentation, sign the sign-in sheet, and complete and return the feedback/evaluation form at the conclusion of each presentation. Partial credit is not awarded.
To view the seminar live:
The presentations are also available by video conference. To join – after the conference has started, click the link below:
Username: guest Password: guest
Health Informatics Coordinator
School of Information and Library Science
101 Manning Hall; CB #3360
Chapel Hill, NC 27599-3360