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. Dr. 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.
Panagiotis Benos, PhD, is Professor of Computational and Systems Biology. Dr. 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.
Rafael Ceschin, PhD, is an Assistant Professor in the Department of Radiology, UPMC Children’s Hospital of Pittsburgh. His primary area of research is in imaging informatics, mainly applied to neonatal/pediatric neurodevelopment, as well as pediatric brain tumors. His research includes the development of computational pipelines and models for the analysis of neonatal neuroimaging, with a focus on reproducible clinical-translational applications. This work extends into the field of neuroinformatics and health IT, particularly as it pertains to image transfer, data sharing, harmonization, and reproducible analysis. More broadly, he is increasingly active in the application of explainable machine learning in clinical-translational research, implementing algorithms that not only perform a clinical task, but also give clinicians insight into the underlying biological mechanisms driving the algorithm’s performance.
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. Dr. 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.
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.
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. Dr. 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.
Milos Hauskrecht, PhD, is an 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 Associate Professor of Biomedical Informatics and Director, Biomedical Informatics Training Program. 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 Professorvof 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, UCSD, and other institutions.
Charles Jonassaint, PhD, MHS, is an Assistant Professor of Medicine, Social Work and Clinical and Translational Science, School of Medicine. Dr. Jonassaint is a practicing clinical health psychologist focusing on the implementation of behavioral intervention technologies in low-resource settings. He has clinical expertise in chronic disease self-management and cognitive behavioral therapy and has had extensive experience working with underrepresented and underserved patients.
Sandra Kane-Gill, PharmD, MS, FCCM, FCCP is a Professor of Pharmacy and Therapeutics. Dr. Kane-Gill’s interests focus on health service research, including the assessment of economic, clinical, and quality outcomes for critically ill patients. Her goal is to identify effective approaches for the detection, prevention, and management of medication errors and adverse drug events as to improve quality of care and patient safety.
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 an 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.
Hatice Osmanbeyoglu, PhD, is an Assistant Professor of Biomedical Informatics, School of Medicine. Her research include developing integrative statistical and machine learning approaches for extracting therapeutic insight from highly heterogenous omic datasets, clinical and drug response data for the purpose of precision medicine. Projects are in the areas of cancer genomics, epigenetics of drug response, and immunotherapy and are executed through multi-disciplinary collaborations.
Ashok Panigrahy, MD, is an 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 Associate 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.
Yalini Senathirajah, PhD is an Associate Professor of Biomedical Informatics at the University of Pittsburgh. Her main area of research interest is improving the design and usability of electronic health records and health IT systems in general, using a novel paradigm together with modern web technical approaches. This is based on giving nonprogrammer clinicians more control via a drag/drop platform approach which allows them to create their own software and tools. It has promise to increase the software’s efficiency and cognitive support, fit to clinician ways of thinking, work contexts, public health emergencies, ease of use, and evolvability to meet future needs and different specialty and work contexts. Her other major areas of interest are using informatics for patient/consumer engagement, particularly in minority communities and the underserved, global health informatics, and analytics to improve healthcare.
Jonathan Silverstein, MD, MS, FACS, FACMI is the Chief Research Informatics Officer and Professor of Biomedical Informatics. His research interests include clinical informatics, oncology informatics, learning health systems, virtual organizations, vocabularies and imaging/visualization/virtual reality.
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.
Sofia Triantafillou, PhD is an Assistant Professor in Biomedical Informatics. Her main area of research is causal discovery and its applications in Biomedicine. She is interested in developing novel algorithms for causal discovery and inference from observational and experimental data, and then applying them to medical and biological data to uncover their underlying causal mechanisms.
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.
Wilbert Van Panhuis, MD, PhD, is an Assistant Professor in the and . His research in the fields of computational epidemiology and population health informatics aims to improve the efficient use of information for public health action. He uses large-scale public health data with statistical and agent-based simulation models to study the spatial spread of infectious diseases. He leads multiple large-scale global health data initiatives, including , an open-access repository for global disease surveillance data His disease expertise concentrates on vector borne diseases (dengue and Chikungunya) in Latin America and Southeast Asia, especially as related to climate, and on vaccine preventable diseases in the US and EU.
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.
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 an 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.
Erik Wright, PhD, MS, is an Assistant Professor in Biomedical Informatics. His research integrates comparative genomics and experimental evolution to tackle the problem of antibiotic resistance. Although antibiotics have been used by microorganisms for eons, it remains unclear how these organisms have mitigated the rise of antibiotic resistance in their competitors. Dr. Wright studies the strategies that naturally antibiotic-producing bacteria have evolved to discourage the build-up of resistance, and how some bacteria have adapted to overcome antibiotics while paying a minimal price for resistance. The goal of this research is to develop new strategies for treating pathogens in the clinic, ultimately turning the tide against increasing antibiotic resistance.
Shandong Wu, PhD, is an Associate Professor (with tenure) in Radiology (primary) and several other computational sciences at Pitt, and he is an Adjunct Professor in the Machine Learning Department at the Carnegie Mellon University (CMU). Dr. Wu leads the Intelligent Computing for Clinical Imaging (ICCI) lab (16 trainee members and >20 clinician collaborators) and serves as the Technical Director for AI Innovations in Radiology at Pitt/UPMC. He is the founding director of the Pittsburgh Center for Artificial Intelligence Innovation in Medical Imaging (CAIIMI, https://www.aimi.pitt.edu/), which includes more than 90 multidisciplinary members from Pitt, UPMC, and CMU, working on advancing AI research and clinical translation. Dr. Wu’s background is in Computer Science (Computer Vision) with additional clinical training in radiology research. Dr. Wu’s main research areas include computational biomedical imaging analysis, artificial intelligence in clinical/translational applications, big (health) data coupled with machine/deep learning, imaging-based clinical studies, and radiomics/radiogenomics/radioproteomics. Dr. Wu’s research has been growing from focusing on breast cancer imaging (screening, risk assessment, diagnosis, prognosis, and treatment) to cover many other diseases/organs as well, such as brain injury, gastric cancer, intestinalis, orthopedics, liver cancer and transplantation, pancreatic cancer, lung cancer, cardiac arrest, obesity, etc. Dr. Wu is an advocator of and passionate about developing trustworthy medical imaging AI for clinical/translational applications. Dr. Wu received the Pitt Innovator Award in 2019, and his lab received the prestigious "RSNA Trainee Research Award" twice in 2017 and 2019. Dr. Wu’s research is supported by NIH/NCI, RSNA, UPMC Enterprises, Pittsburgh Foundation, Pittsburgh Health Data Alliance, Stanly Marks Research Foundation, University of Pittsburgh Physician (UPP) Foundation, Amazon, and Nvidia. As a PI he has received more than 5 million dollars in research funds over the past 5 years. Dr. Wu has published > 100 papers/abstracts in both computing and clinical fields and he mentored more than 30 students.
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 Professor in the Department of Information and Networked Systems, School of Computing and Information. 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.