Research
Biomedical Informatics research covers a broad spectrum of inquiry - from the analysis of genomic microarray datasets to the evaluation of hospital organizations during the adoption of new technology. This spectrum reflects the many facets of Biomedical Informatics, which can be defined as “the scientific field that deals with biomedical information, data, and knowledge – their storage, retrieval, and optimal use for problem-solving and decision-making.” (Shortliffe & Blois, 2001). Below we present our faculty’s major funded research areas. We welcome your ideas for collaboration and invite individuals interested in training with us to contact us for further information.
Genomic and Proteomic Data: Analysis and Data Mining
Vanathi Gopalakrishnan, PhD is exploring the application of technology to the analysis of datasets from biological studies. Her research encompasses the application of symbolic machine learning techniques to the mining of structural and genomic databases in order to learn useful models and associations. Gopalakrishnan is the recipient of a K25 award from the National Institute of General Medical Sciences.
Sample of Related Publications:
Gopalakrishnan V, Livingston G, Hennessy D, Buchanan B, Rosenberg JM. Machine-learning techniques for macromolecular crystallization data. Acta Crystallogr D Biol Crystallogr. 2004 Oct;60(Pt 10):1705-16. Epub 2004 Sep 23. PMID: 15388916
Datawarehouses and Repositories
Michael J. Becich MD, PhD, professor and chair of the Department of Biomedical Informatics, focuses on developing datawarehouses and data mining strategies for genomic and proteomic data derived from high throughput methodologies such as expression microarrays and tissue microarrays. His interests also include tissue bank information systems, clinical information systems and imaging repositories that currently operating in the Pathology Department at University of Pittsburgh. He is also the leader for the University of Pittsburgh’s Cancer Biomedical Informatics Grid (caBIG) projects and the Informatics Co-Director of Pitt’s Clinical and Translational Science Institute. Becich currently serves as PI or Co-PI on eight funded grants, including grants from the NCI, the Department of Defense, Agency for Healthcare Research and Quality, and the PA Commonwealth Department of Health.
Sample of Related Publications:
Patel AA, Kajdacsy-Balla A, Berman JJ, Bosland M, Datta MW, Dhir R, Gilbertson J, Melamed J, Orenstein J, Tai KF, Becich MJ. The development of common data elements for a multi-institute prostate cancer tissue bank: The Cooperative Prostate Cancer Tissue Resource (CPCTR) experience. BMC Cancer. 2005 Aug 21;5:108.
Bayesian Modeling and Machine Learning Methods
Making accurate healthcare predictions from electronically stored patient data is a research focus of Gregory F. Cooper, MD, PhD, an associate professor and vice chair of the Department of Biomedical Informatics. With his current R01 grant, Cooper is exploring if patient-specific models of sepsis, heart failure and substance use disorders can offer more accurate predictions than population-wide models. Shyam Visweswaran, MD, PhD, an assistant professor of biomedical informatics, collaborates with Cooper on this project. Cooper also has a grant from the National Science Foundation to explore Bayesian Modeling for Biosurveillance.
Sample of Related Publications:
Cooper GF, Abraham V, Aliferis CF, Aronis JM, Buchanan BG, Caruana R, Fine MJ, Janosky JE, Livingston G, Mitchell T, Monti S, Spirtes P. Predicting dire outcomes of patients with community acquired pneumonia. J Biomed Inform. 2005 Oct;38(5):347-66. Epub 2005 Mar 17.
Visweswaran S, Cooper GF. Patient-specific models for predicting the outcomes of patients with community acquired pneumonia. AMIA Annu Symp Proc. 2005;:759-63.
Natural Language Processing
Patient data often is electronically stored in free text fields resulting in relatively inaccessible information. Two DBMI faculty members, Wendy Chapman, PhD and Rebecca Crowley, MD, MSIS, have been exploring the application of Natural Language Processing (NLP) techniques to the identification and retrieval of relevant free text information. Chapman has been exploring this approach in her K25 grant using emergency department notes and Crowley has developed the Cancer Text In Information Extraction System (caTIES) for Surgical Pathology Reports. Crowley has developed the Cancer Text In Information Extraction System (caTIES) for Surgical Pathology Reports and has a new collaborative grant with the National Center for Biomedical Ontology (NCBO) to develop the ODIE Toolkit-Methods for Information and Extraction using ontologies and ontology enrichment using clinical text.
Sample of Related Publications:
Chapman WW, Dowling JN, Wagner MM. Classification of emergency department chief complaints into 7 syndromes: A retrospective analysis of 527,228 patients. Ann Emerg Med. 2005 Nov;46(5):445-55. Epub 2005 Jul 1.
Liu K, Chapman W, Hwa R, Crowley RS, Heuristic sample selection to minimize reference standard training set for a part-of-speech tagger. J Am Med Inform Assoc, 2007 Sep-Oct; 14(5):641-50.
Intelligent Tutoring Systems and Simulations
Rebecca Crowley, MD, MSIS, also has received R01 funding and R25 funding to develop an Intelligent Tutoring System for teaching visual diagnostic skills in pathology. Crowley and Dana Grzybicki, MD, PhD are collaborators on an AHRQ grant exploring whether the use of this tutoring system can reduce medical errors in melanoma diagnoses. Roger Day, ScD, has received long-standing funding from the NCI to develop an application (OncoTCap) that provides both a simulation of the evolution of heterogeneous tumors and interfaces which can be used to promote understanding of important issues of cancer treatment.
Sample of Related Publications:
Crowley RS, Legowski E, Medvedeva, OM, Tseytlin E, Roh E and Jukic D. Evaluation of an Intelligent Tutoring System in Pathology: Effects of External Representation on Performance Gains, Metacognition, and Acceptance. J Am Med Inform Assoc. 2007 14(2): 182-190.
Day RS. Challenges of biological realism and validation in simulation-based medical education. Artif Intell Med. 2006 Sep;38(1):47-66. Epub 2006 Apr 18.
Grzybicki DM, Turcsanyi B, Becich MJ, Gupta D, Gilbertson JR, Raab SS. Database construction for improving patient safety by examining pathology errors. Am J Clin Pathol. 2005 Oct;124(4):500-9.
Image Analysis
Like free-text medical notes, medical images present information detection and extraction challenges. Brian Chapman, PhD is exploring through his R21 grant new image analysis methods for magnetic resonance images of the liver with the goal of detecting liver cancer nodules that are not characterized by tumor hypervascularity.
Sample of Related Publications:
Chapman BE, Yankelevitz DF, Henschke CI, Gur D. Lung cancer screening: Simulations of effects of imperfect detection on temporal dynamics. Radiology. 2005 Feb;234(2):582-90.
Consumer Health Informatics
The research of Valerie Monaco, PhD, MHCI focuses on consumer health informatics. Monaco's funded projects explore improving patient access to cancer clinical trial information, assisting low-literacy populations with online health searches (R21 grant), and evaluating patient understanding of the online test results presented in personal health records.
Sample of Related Publications:
Monaco V, Krills SK. On-line information about cancer clinical trials: Evaluating the Web sites of comprehensive cancer centers. AMIA Annu Symp Proc. 2003;:470-4.
Public Health Informatics and Biosurveillance
Several faculty members, including William Hogan, MD (funded by R01 grant) and Garrick Wallstrom, PhD (also funded by an R01 grant), investigate methods for real-time detection and assessment of disease outbreaks within the Realtime Outbreak and Disease Surveillance (RODS) Laboratory. Founded in part by Michael Wagner, MD, PhD and Rich Tsui PhD, the RODS Laboratory is a collaboration between researchers at the University of Pittsburgh and the Auton Lab in Carnegie Mellon University’s School of Computer Science. Current research interests of the faculty include algorithm development, assessment of novel types of surveillance data, natural language processing and analyses of detectability. Current funding sources include the Centers for Disease Control, the National Library of Medicine, and the Department of Homeland Security.
Sample of Related Publications:
Hogan WR, Tsui FC, Ivanov O, Gesteland PH, Grannis S, Overhage JM, Robinson JM, Wagner MM; Indiana-Pennsylvania-Utah Collaboration. Detection of pediatric respiratory and diarrheal outbreaks from sales of over-the-counter electrolyte products. J Am Med Inform Assoc. 2003 Nov-Dec;10(6):555-62. Epub 2003 Aug 4.
Wallstrom GL, Wagner M, Hogan W. High-fidelity injection detectability experiments: a tool for evaluating syndromic surveillance systems. MMWR Morb Mortal Wkly Rep. 2005 Aug 26;54 Suppl:85-91.
Wagner MM, Wallstrom GL, Onisko A. Issue a boil-water advisory or wait for definitive information? A decision analysis. AMIA Annu Symp Proc. 2005;:774-8.
Tsui FC, Espino JU, Weng Y, Choudary A, Su HD, Wagner MM. Key design elements of a data utility for national biosurveillance: event-driven architecture, caching, and Web service model. AMIA Annu Symp Proc. 2005;:739-43.