You are here

Printer-friendly versionPrinter-friendly version
Staff Scientist
Phone Number: (
Expertise and Research Interests: 

Mehmet Kayaalp's work focuses on computational linguistics, machine learning and probabilistic graphical models on the domain of medical informatics. He has published a number of articles on each of these subjects. He leads NLM efforts on de-identifying narrative clinical reports.

Dr. Kayaalp started working on biomedical informatics projects in the mid-1980s during his medical education at the University of Istanbul, from which he received his MD. He pursued his interest in biomedical informatics as a research scholar at Southern Methodist University in Dallas, Texas. He later matriculated at SMU, where he earned an MS in Computer Science, and successfully completed his PhD coursework and doctoral exams. Toward his dissertation work, he worked on an Office of Naval Research-funded computational linguistics project, developing various probabilistic linguistic models based on Markov random field theory. Upon the departure of his advisor from SMU, Dr. Kayaalp moved to the University of Pittsburgh, where he worked with Drs. Gregory F. Cooper and Bruce G. Buchanan on Bayesian networks and machine learning in various biomedical informatics projects. He received his Ph.D. degree in Intelligent Systems from University of Pittsburgh with a specialization in Biomedical Informatics.

Dr. Kayaalp has worked on various software engineering projects during his career but his main interest has remained artificial intelligence. In the 1990s, he developed the concept of multifaceted ontological networks, by recognizing the fact that everyone cannot agree on a single scientific or philosophic view of the world, but multiple views and interpretations of the same world have to coexist and compete for the progress of science and culture. The method of multifaceted ontological networks is a means to cope with the exponential growth of scientific information. It proposes a systematic organization of scientific information from various disciplines through a non-ambiguous formalism of logic without excluding any particular scientific observation or interpretation of the world.

Professional Activities: 

Dr. Kayaalp was appointed as the physician and the chief medical officer to a transportation regiment, where he managed the operation of an Army clinic supervising other medical and Army personnel. In the early 1990s, he worked as a research scholar in the Department of Computer Science and Engineering at Southern Methodist University, Dallas, Texas. During his studies in computer science, he worked at SMU in various academic capacities including teaching and research positions. In University of Pittsburgh, he worked at the Center for Biomedical Informatics, (currently known as the Department of Biomedical Informatics), where he participated as a research assistant to the Integrated Advanced Information Management Systems project funded by National Library of Medicine.

Publications/Tools by Mehmet Kayaalp: 
Gay CW, Kayaalp M, Aronson AR. Semi-Automatic Indexing of Full Text Biomedical Articles AMIA Annu Symp Proc. 2005:271-5
Kayaalp M. Bayesian Methods for Diagnosing Physiological Conditions of Human Subjects from Multivariate Time Series Biosensor Data Physiological Data Modeling Contest, the Twenty-First International Conference on Machine Learning (ICML), 2004 July.
Kayaalp M. Modeling and Learning Methods; A Report to the Board of Scientific Counselors May 2004 Technical Report to the LHNCBC Board of Scientific Counselors.
Kayaalp M, Aronson AR, Humphrey SM, Ide NC, Tanabe LK, Smith LH, Demner-Fushman D, Loane RF, Mork JG, Bodenreider O. Methods for accurate retrieval of MEDLINE citations in functional genomics. The Twelfth Text Retrieval Conference (TREC 2003). 2003:441-50.
Buchanan BG, Chapman W, Cooper GF, Hanbury P, Kayaalp M, Ramachandran M, Saul M. Creating a Software Tool for the Clinical Researcher -- the IPS System Proc AMIA Symp. 2002: : 1210.
Cooper GF, Buchanan BG, Chapman W, Hanbury P, Kayaalp M, Saul M. IPS: A System That Uses Machine Learning to Help Locate Patient Records for Clinical Research. Proc AMIA Symp. 2001: : 813.
Kayaalp M, Cooper GF, Clemont G. Predicting ICU mortality: a comparison of stationary and nonstationary temporal models. Proc AMIA Symp. 2000:418-22.
Aronis JM, Cooper GF, Kayaalp M, Buchanan BG. Identifying patient subgroups with simple Bayes'. Proc AMIA Symp. 1999:658-62.
Cooper GF, Buchanan BG, Kayaalp M, Saul M, Vries JK. Using computer modeling to help identify patient subgroups in clinical data repositories. Proc AMIA Symp. 1998:180-4.