Core Faculty of the Training Program

The core faculty of the Biomedical Informatics Training Program includes faculty from the Department of Biomedical Informatics, as well as faculty from other departments and schools within the University of Pittsburgh.

Ivet Bahar, MS, PhD, is a professor and the John K. Vries chair of the Department of Computational and Systems Biology. Bahar’s research expertise is in modeling and simulations of macromolecular dynamics, and developing new theories and computational tools for analyzing complex biological processes. She has extensive experience in analytical models and quantitative methods for determining the conformational dynamics of proteins and their complexes, as well as molecular dynamics (MD) simulations of biomolecules. She is the developer of the Gaussian Network Model (GNM) theory and software, which opened the way to a wealth of computational studies of protein dynamics and improved our understanding of the structural basis of biomolecular functional mechanisms. Bahar is part of the teaching faculty for Introduction to Computational Structural Biology (MSCBIO2030), a core course for the Joint CMU-Pitt PhD program in Computational Biology, and also cross-listed as a core course for the Molecular Biophysics Graduate Program.

Kayhan Batmanghelich, PhD, is an Assistant Professor of Biomedical Informatics.  His research lies at the intersection of medical vision, machine learning, and bioinformatics. He develop statistical models to analyze and understand medical images in the context of biological and clinical measurements. An example of biological data is genetic variants among individuals in a population. For example, he develop a Bayesian model that relates abnormal brain variations caused by Alzheimer's disease to the genetic risk variants of the disease. Part of his research involves making efficient algorithms that extract insights about the underlying mechanisms of diseases from a large-scale medical dataset. Such projects entail identifying relevant clinical questions, using biological knowledge to build a model, and developing an efficient inference algorithm using scalable optimization techniques. His long-term objective is to expand my research to exploit the wealth of medical data such as clinical health records, medical images, genomic, and radiology reports alongside with interaction (feedback) from clinicians to improve health care.

Michael J. Becich, MD, PhD, Dr. Becich is Professor and inaugural Chairman of the Department of Biomedical Informatics at the University of Pittsburgh School of Medicine. He is jointly appointed in Pathology, Information Sciences/Telecommunications and Clinical/Translational Research. He is Associate Director of the University of Pittsburgh Cancer Institute as well as the Clinical and Translational Science Institute at the University of Pittsburgh School of Medicine. Dr. Becich’s research interests are focused on the interface between clinical informatics and bioinformatics. His research is funded by the CDC, NCATS, NCI, NHLBI and NLM and includes clinical phenotyping of patients for genomic/personalized medicine, tissue banking informatics, clinical informatics and bioinformatics with a special emphasis on data sharing. Dr. Becich is interested in transforming clinical care through translational research and creating a learning health system focused on cost effective, high quality and safe care through personalized medicine. For a full research profile see

Panagiotis Benos, PhD, is Professor of Computational and Systems Biology. Benos’ main research areas include the study of the gene regulation with mathematical methods and computational techniques, and genome analysis with emphasis in the evolution of proteins and DNA regulatory regions. In particular, his laboratory focuses in the development of computational models for gene interactions, the identification of transcription factor binding sites, the study of the relation between protein sequence-structure-function, the study of biochemical and biophysical phenomena at the molecular level, and the analysis of heterogeneous data.

David Boone, PhD, Assistant Professor of Biomedical Informatics.  His research interests include development and implementation of STEM outreach programs, breast cancer biology, transcription and transcriptomics, regulation and function of long noncoding RNAs, and insulin-like growth factor 1 (IGF1) signaling in breast cancer.

Richard Boyce, PhD, is an Associate Professor of Biomedical Informatics. Dr. Boyce is interested in knowledge-based approaches to drug-drug interaction, computational methods, and belief maintenance systems to biomedical knowledge-representation.

Uma Chandran, PhD, MSIS, Research Associate Professor of Biomedical Informatics.  Her research includes a deep experience working with all aspects of genomics data, and have analyzed data from all Next Generation Sequencing (NGS) platforms including RNA Seq, Whole Exome Seq (WXS) and Whole Genome Seq (WGS). 

S. Chakra Chennubhotla, PhD, is an Associate Professor in the Department of Computational and Systems Biology. His group investigates the molecular and cellular origins of human epithelial malignancies (e.g., breast cancer, Barrett’s) through two interrelated approaches: (a) computational pathology and bioimaging, where they develop algorithms to analyze intratumor phenotypic heterogeneity from in situ fluorescent imaging of tissue sections or tissue microarrays and (b) computational biophysics, where they develop models based on anharmonic fluctuations to discern short-lived and rare intermediate conformations that proteins access to fold, bind, and function.

Gregory F. Cooper, MD, PhD, is a Professor of Biomedical Informatics, Computational and Systems Biology, Computer Science, Information Science, and Intelligent Systems Program. Cooper is the vice chair of the Department of Biomedical Informatics. Cooper's general research interest is the application of decision theory, probability theory, and artificial intelligence to address medical informatics research questions. His primary research focus is causal modeling and discovery in medicine and biology. Other interests include data mining of medical databases, the application of Bayesian statistics in medicine, and computer-assisted information retrieval from electronic medical records.

Roger S. Day, ScD, is Emertius Associate Professor of Biomedical Informatics. Dr. Day leads development of the Oncology Thinking Cap computer modeling facility, which uses stochastic models of tumor growth to help cancer researchers do thought experiments about cancer biology and treatment, and to help cancer educators develop their abilities to reason across the bridge from basic cancer science through implications for patients and clinical trials. New aspects of this work are integration with the Cancer Bioinformatics Grid (caBIG) and with knowledge acquisition tools. His work on breast cancer includes collaborations to shed light on contentious dosing issues in adjuvant breast cancer treatment through modeling of the population dynamics and genetic evolution of breast cancers, and through molecular studies of samples of individual cells from tumors. The long-range goal is to radically improve our ability to predict response of individual patients to a variety of cancer therapies and strategies. Day’s other areas of research include statistical model families (“weakest link” models; generalized additive effects models) that reflect the kinds of relationships that exist in the real world of biology and medicine.

Gerald Douglas, PhD, is an Assistant Professor of Biomedical Informatics. His research focuses on applying the principles of medical informatics to improve healthcare in low-resource settings, both within the United States as well as internationally. He has particular interest in user-interface design and user experience. His research builds on techniques developed through 10 years of experience building point-of-care electronic medical record systems in Malawi. These techniques are captured in the curriculum of the graduate-level Principles of Global Health Informatics course, and Global Health Informatics Summer Internship in Malawi, created and taught by Dr. Douglas.

Barbara Epstein, MSLS, is the Director of the University’s Health Sciences Library System (HSLS). Epstein’s research interests include training for health sciences librarianship, information challenges in the decentralized healthcare enterprise, information seeking behavior of varied populations, and the impact of electronic information resources.

Madhavi Ganapathiraju, PhD, is an Associate Professor of Biomedical Informatics, University of Pittsburgh. She holds an MEng degree in Electrical and Communications Engineering from Indian Institute of Science and PhD in Language and Information Technologies from School of Computer Science at Carnegie Mellon University. Her PhD thesis focus was on the application of signal processing and language processing methods to the study of protein and proteome sequences, which led to the development of a high accuracy algorithm for transmembrane helix prediction. Her current research focus is in the area of computational molecular and systems biology, translational bioinformatics and biomedical text mining, using signal processing and machine learning.

Vanathi Gopalakrishnan, PhD, is an Associate Professor of Biomedical Informatics, Intelligent Systems Program, and Computational and Systesm Biology. Dr. Gopalakrishnan is interested in the development of intelligent computational aids for solving clinically relevant biological problems, such as biomarker discovery for neurodegenerative diseases from proteomic mass spectra, macromolecular crystallization, functional MRI data analysis and mapping of protein sequence-structure-function relationships. Her research encompasses the application of machine learning methods such as rule learning and Bayesian techniques, in addition to developing quantitative models of biological phenomena from first principles. Gopalakrishnan teaches a core course titled Introduction to Bioinformatics (BIOINF 2051) each fall term, oversees the Bioinformatics Journal Club, and each summer offers a directed study laboratory course (BIOINF 2053) in conjunction with educators from the Pittsburgh Supercomputing Center.

Steven M. Handler, MD, PhD, CMD, is an Associate Professor of Geriatric Medicine, Division of Geriatric Medicine, University of Pittsburgh. Dr. Handler’s research interests include the application of clinical decision support systems to improve medication safety primarily in the nursing home setting.

Milos Hauskrecht, PhD, is an Associate Professor of Computer Science. Dr. Hauskrecht regularly teaches graduate level artificial intelligence and machine learning courses at the University, as well as advanced Machine Learning and AI seminars. His primary research interests are in probabilistic modeling and the design of efficient optimization, inference and learning algorithms for such models. Hauskrecht applies the models and techniques to analysis of high-throughput proteomic and genomic datasets, data mining and discovery in clinical databases, and decision-making in patient management tasks.

Harry Hochheiser, PhD, is an Assistant Professor of Biomedical Informatics, His research interests are focused on the design of usable systems for use in clinical and research settings. He is particularly interested in using user-centered design techniques to inform the design of highly-interactive information visualization systems for the interpretation of complex data sets in domains such as bioinformatics and electronic health records.

Xia Jiang, PhD, is an Associate Professor of Biomedical Informatics. Dr. Jiang has over 13 years of teaching and research experience in Bayesian Network modeling, machine learning, and algorithm design. One of Dr. Jiang's specific areas of interests is developing advanced computational methods for high-dimensional data analysis. Dr. Jiang is also very interested in translational informatics, in particular, cancer bioinformatics. She will devote her efforts in developing advanced informatics tools that assist the translation of the findings in basic scientific research efficiently and effectively into patient medical care, atrendin research so called “basepairstobedside”. Dr. Jiang’s research collaborators include mathematicians, computer scientists, statisticians, physicians, pathologists, biologists, geneticist, and peer informaticians from Pitt, CMU, NU, and UCSD etc.

Douglas Landsittel, PhD, is a Professor of Biomedical Informatics.  His areas of research include causal inference methods, prognostic and prediction models, design and analysis of biomarker studies, occupational and injury epidemiology, and statistical model of renal function and transplant outcomes.

Young Ji Lee, PhD, MS, RN, is an Assistant Professor of Nursing.  Dr. Lee’s research interests have been focused on structuring and delivering health information through an informatics-based approach to diverse groups, especially to minority populations. Her research has engaged community residents to assess their needs and understand their circumstances in order to empower them to manage their own health through health communication interventions. Methodologically, she has extensive experience in mining big data to reveal hidden relationships between agents. 

Yang Liu, PhD, is Associate Professor of Medicine and Bioengineering.  Dr. Liu integrates multi-disciplinary approaches spanning engineering, optics, physics, chemistry and biology and develops imaging technologies to address important clinical dilemma of how to better predict the individual's cancer progression risk in a large number of at-risk population, and how to improve the diagnostic accuracy of malignancy. Early cancer detection currently relies on screening the entire at-risk population, as with colonoscopy and mammography. Frequent, invasive surveillance of patients at risk for developing cancer carries financial, physical, and emotional burdens because clinicians lack tools to accurately predict which patients will actually progress into malignancy. Current clinical gold standard for diagnosing cancer and predicting cancer progression risk relies on the evaluation of nuclear morphology by a trained pathologist using bright-field microscope, which limits the assessment of nuclear architecture to microscale with very limited performance on a personalized level, especially in patients without the presence of clinically significant lesions such as patients with ulcerative colitis or atypical hyperplasia in breast.

Songjian Lu, PhD, Assistant Professor of Biomedical Informatics.  His research interests include using computational method to search for driver somatic genome alterations, such as somatic mutations, copy number alterations, that are related to cancer development; formulating the biological problems into graph or statistical problems; and designing efficient exact algorithms for the hard computational problems.

Xinghua Lu, MD, PhD, is an Professor of Biomedical Informatics. His research interests include computational methods for identifying signaling pathways underlying biological processes and diseases, statistical methods for acquiring knowledge from biomedical literature, translational bioinformatics and systems/computational biology, natural language processing and text mining.

Ashok Panigrahy, MD, is an Associate Professor of Radiology at the University of Pittsburgh, and the Radiologist-In-Chief, Department of Pediatric Radiology, Children’s Hospital of Pittsburgh. His research interest are neonatal brain injury: evaluation with advanced MR techniques; advanced MR imagining of pediatric brain tumors; and fetal MR imaging.

Bambang Parmanto, PhD, is a Professor of Health Information Management at the School of Health and Rehabilitation Sciences. Dr. Parmanto’s primary research interests include data mining/warehousing, personal health record, Web transcoding, and telerehabilitation. He teaches two courses in the Training Program: Object-oriented and Web Programming (HRS-2422), and Database Systems in Healthcare (HRS-2423).

Mark S. Roberts, MD, MPP, is a Professor of Medicine, Health Policy and Management, and Industrial Engineering. Dr. Roberts is chief of the Section of Decision Sciences and Clinical Systems Modeling in the Division of General Medicine. He also serves as the codirector of the master's program in Clinical Research and the new PhD program in Clinical and Translational Science. Roberts’ research interests include the development and application of clinically realistic mathematical models of disease to investigate and inform questions that cannot easily be examined by randomized controlled trials, such as the optimal timing of an intervention in a chronic disease. Roberts uses modeling techniques such as decision analysis, Monte Carlo Simulation, and discrete event simulation to create representations of disease processes and therapeutic interventions. In addition, he has substantial expertise in the conduct of cost-effectiveness analysis in healthcare, the use of clinical information systems in healthcare, and the measurement and inclusion of patient preferences in clinical decision making.

Ervin Sejdić, PhD, is an Assistant Professor in Department of Electrical and Computer Engineering (Swanson School of Engineering), Department of Bioengineering (Swanson School of Engineering), Department of Biomedical Informatics (School of Medicine) and the Intelligent Systems Program (Kenneth P. Dietrich School of Arts and Sciences). He is also the director of the Innovative Medical Engineering Developments (iMED) Lab at the University of Pittsburgh and the associate director of the RFID Center of Excellence at the University of Pittsburgh. Dr. Sejdić and his lab aim to develop dynamical biomarkers indicative of age- and disease-related changes and their contributions to functional decline under normal and pathological conditions by fostering innovation in computational approaches and instrumentation that can be translated to bedside care. Our research areas include, but not limited to, advanced information systems in medicine, bioinformatics, anticipatory medical devices, rehabilitation engineering, assistive technologies, biomedical and theoretical signal processing, computational biomarkers, brain-computer interfaces, human-computer interfaces.

Srinivasan Suresh, MD, MBA, FAAP, Chief Medical Information Office and Visiting Professor of Pediatrics, Children’s Hospital of Pittsburgh.  His research interests include evidence based care models for common and key illnesses to enhance patient management at point-of-care.

Donald P. Taylor, PhD, MBA, is the Assistant Vice Chancellor for Commercial Translation in Health Sciences, Associate Professor of Biomedical Informatics, Co-Director for the Center for Commercial Applications of Healthcare Data, Co-Director of Clinical and Translational Science Institute (Innovation Core), Associate Director of Center for Medical Innovation. His basic research investigates mechanisms of breast cancer metastatic latency through computational models and human, 3D-perfused micro-scale tissue bioreactors. He explores different approaches for diagnostic and therapeutic treatment of quiescent lesions, and his research has helped suggest that targeting therapeutics to adjacent noncarcinoma cells is a viable strategy to treat metastatic disease.George Tseng, PhD, is a Professor in the Department of Biostatistics.  The general vision and scope of my research group is on the methodological development in statistical genomics and bioinformatics. Our expertise involves data mining of high-throughput genomic, transcriptomic, epigenomic and proteomic data and on the statistical learning methods, including classification, clustering, candidate marker detection and gene regulatory network analysis. My lab has especially focused on methods for information integration of omics studies and analysis of next-generation sequencing data since 2009.

Fu-Chiang (Rich) Tsui, PhD, is an Associate Professor of Biomedical Informatics and the Intelligent Systems Program, and is Associate Director of the Real-time Outbreak and Disease Surveillance (RODS) Laboratory. Dr. Tsui’s research interests include time series analysis, neural networks, digital signal processing, wavelet transforms, and database management as they apply to electronic medical records, medical decision support systems, notification systems, Web design and real-time analysis of clinical signals. He mentors students in master’s and PhD programs, and is also a guest lecturer in the courses Knowledge Representation and Modeling, and Real-time Outbreak and Disease Surveillance.

Shyam Visweswaran, MD, PhD, is an Associate Professor of Biomedical Informatics. Dr. Visweswaran’s research interests include the application of artificial intelligence and machine learning to problems in clinical medicine and bioinformatics with a specific focus on data mining of biomedical data, patient-specific predictive modeling, medical anomaly detection, and decision support systems.

Michael M. Wagner, MD, PhD, is a Professor of Biomedical Informatics and the Intelligent Systems Program, and is the Director of the Real-time Outbreak and Disease Surveillance (RODS) Laboratory. Wagner has developed reminder and alerting systems that are based on probabilistic and decision-theoretic formalisms. His current research in biosurveillance involves collaborations with researchers at Carnegie Mellon University, and many health departments, to develop and evaluate algorithms, decision models, and fielded production systems for biosurveillance. Wagner’s areas of expertise include knowledge representation, intelligent systems, and clinical decision support.

Xiaosong Wang, MD, PhD, is an Associate Professor of Pathology. An overarching challenge of cancer informatics is to identify and recognize the cancer drivers and targets from the daunting amount of big data, especially those that can be therapeutically targeted to improve the clinical outcome. Dr. Wang’s lab applies a multiple disciplinary approach inclusive of integrative bioinformatics, cancer genetics, molecular cancer biology, and translational studies to identify driving genetic aberrations and appropriate cancer targets on the basis of deep sequencing and genomic profiling datasets. His dry lab researches focus on developing innovative and integrative computational technologies and tools to discover causal genetic alternations, viable therapeutic targets, and predictive biomarkers in cancer, as well as understanding the tumorigenic process at systematic level. His wet lab researches focus on experimentally characterizing individual genetic aberrations in breast cancer such as recurrent gene rearrangements and genomic amplifications, as well as qualifying viable cancer targets and predictive biomarkers for precision therapeutics.

Jeremy Weiss, MD, PhD, is Assistant Professor in Health Informatics at Carnegie Mellon University.  His research focuses on the development of machine learning algorithms for analysis of electronic health records (EHRs). The recent growth in EHR usage underlies a transformation in analytic approaches to medical data. His research in machine learning provides tools to characterize and make predictions from EHRs about the health of populations and individuals.

Shandong Wu, PhD, is an Assistant Professor with joint appointments in Radiology, Biomedical Informatics, and Bioengineering. He is also a member of the Biomedical Informatics Training Program Core Faculty, University of Pittsburgh Cancer Institute (UPCI) and Magee-Womens Research Institute, and the Intelligent Systems Program (ISP) of Computer Science. Dr. Wu’s background is in Computer Science (Computer Vision) with additional postdoctoral training (at University of Pennsylvania, School of Medicine, Department of Radiology) in clinical imaging and radiology research specialized in breast cancer research. His research interfaces a broad range of interdisciplinary in computational science and medicine for translational and clinical applications. Dr. Wu’s main research areas include computational biomedical imaging analysis, big (health) data coupled with machine/deep learning, imaging-based clinical studies, radiomics/radiogenomics, and artificial intelligence in clinical informatics/workflows. Current research interests center on computational breast imaging and clinical studies for investigating quantitative imaging-derived biomarkers, models, and systems for breast cancer screening, risk assessment, diagnosis, prognosis, and treatment, towards improving individualized clinical decision-making and precision medicine. Dr. Wu’s research is supported (as a sole Principle Investigator) by National Institute of Health (NIH)/National Cancer Institute (NCI)(R01), Radiological Society of North America (RSNA), University of Pittsburgh Medical Center (UPMC), UPCI-Institute of Precision Medicine, Pitt Clinical and Translational Science Institute, and Nvidia, Inc. Dr. Wu established and leads a multidisciplinary research team with complimentary expertise, including computer scientists, radiologists, pathologists, medical oncologists, biostatisticians, geneticists, postdocs, senior research specialists, students, and international visiting scholars. Dr. Wu has published more than 50 journal and conference papers and participated as key research personnel in more than 20 research projects granted by international-wide research agencies. He has mentored/co-mentored more than 25 students (both undergraduate and graduate) in their research or theses, several of which have resulted in co-authored publications. Dr. Wu is a regular reviewer for many grant agencies/study sections, renowned journals, and conferences.

Zongqi Xia, MD, PhD, is Assistant Professor of Neurology.  Currently, he has three ongoing research initiatives. First, we are participating in a multi-centered, prospective cohort study of individuals at risk for MS. Investigating the risk factors of MS and mapping the sequence of events leading to the onset of disease will pave the way to ultimately test primary prevention strategies in high-risk individuals. Second, we are conducting a longitudinal prospective cohort study to investigate the biological and clinical predictors of disease course and treatment response in MS. Gaining insights into the factors that influence the variable patient response to treatment and the diverse trajectories of disease progression in MS will be the key to provide individually tailored therapy. Third, we are developing computational approaches to ascertain treatment response and testing algorithms that predict treatment response using electronic health records data. Tools that leverage real-life clinical data for outcome prediction in chronic neurological disorders have the potential for widespread dissemination at the point of care.

Vladimir Zadorozhny, PhD, is an Associate Professor in the School of Information Sciences, Graduate Information Science and Technology Program.  His research interests include: networked information systems, heterogeneous information integration and data fusion, complex adaptive systems and crowdsoursing, scalable personalized learning, wireless and sensor data management, query optimization in distributed environments, scalable architectures for wide-area environments with heterogeneous information servers.