Download D. Research Support - Department of Biomedical Informatics

OMB No. 0925-0001 and 0925-0002 (Rev. 10/15 Approved Through 10/31/2018)
BIOGRAPHICAL SKETCH
Provide the following information for the Senior/key personnel and other significant contributors.
Follow this format for each person. DO NOT EXCEED FIVE PAGES.
NAME: Shyam Visweswaran
eRA COMMONS USER NAME (credential, e.g., agency login): vshyam
POSITION TITLE: Associate Professor of Biomedical Informatics
EDUCATION/TRAINING (Begin with baccalaureate or other initial professional education, such as nursing,
include postdoctoral training and residency training if applicable. Add/delete rows as necessary.)
INSTITUTION AND LOCATION
Jawaharlal Institute of Post-Graduate Medical
Education and Research (JIPMER), Pondicherry,
India
University of Illinois at Urbana-Champaign, Urbana,
IL
Boston University Medical Center, Boston, MA
DEGREE
(if
applicable)
Completion
Date
MM/YYYY
M.B.,B.S.
12/1987
Medicine
M.S.
06/1996
Physiology and
Biophysics
Residency in Neurology
06/2000
University of Pittsburgh, Pittsburgh, PA
M.S.
07/2004
University of Pittsburgh, Pittsburgh, PA
Ph.D.
09/2007
FIELD OF STUDY
Biomedical Informatics
& Intelligent Systems
Biomedical Informatics
& Intelligent Systems
A. Personal Statement
I am a tenured Associate Professor of Biomedical Informatics with cross appointments in Computational &
Systems Biology and Clinical & Translational Science Institute at the School of Medicine and in the Intelligent
Systems Program in the School of Arts and Sciences. My training is in informatics, artificial intelligence and
clinical neurology, and my research interests include the application of artificial intelligence and machine
learning to problems in the Learning Health System with a specific focus on developing learning electronic
medical records (EMRs), precision medicine and personalized modeling, enabling reuse of EMR data for
research, and data mining and causal discovery from genomic and biomedical data. In the Department of
Biomedical Informatics, I serve as the Director of Clinical and Translational Informatics, Director of the Center
of Clinical Research Informatics (CCRI), and Co-Director of the Kimball Family Center of Clinical Informatics
(KCI). I also serve as the Co-Director of the Informatics Component for the University of Pittsburgh Clinical
and Translational Science Institute (CTSI), and as a PD/PI for the Pitt Precision Medicine Initiative project that
is a component of the Cohort Program of President Obama’s Precision Medicine Initiative. I was deeply
involved in reorganizing the graduate Biomedical Informatics Training Program’s curriculum which developed a
set of core courses that cover a wide range of foundational topics in biomedical informatics. I serve as the
Biomedical Informatics Program Director for the University of Pittsburgh School of Medicine Medical Scientist
Training Program.
B. Positions and Honors
Positions and Employment
1989-1991
1991-1995
Resident in Anesthesiology, Department of Anesthesiology, Jawaharlal Institute of PostGraduate Medical Education and Research, Pondicherry, India
Research and teaching assistant, Department of Physiology and Biophysics, University of
Illinois at Urbana-Champaign, Urbana, IL
1996
1997-2000
2001-2006
2006-2015
2015200820102011-
Internal Medicine Intern, Department of Medicine, St. Luke’s - Roosevelt Medical Center, New
York, NY
Resident in Neurology, Department of Neurology, Boston University Medical Center, Boston,
MA
Informatics Fellow, Department of Biomedical Informatics, University of Pittsburgh School of
Medicine, Pittsburgh, PA
Assistant Professor, Department of Biomedical Informatics, University of Pittsburgh School of
Medicine, Pittsburgh, PA
Associate Professor, Department of Biomedical Informatics, University of Pittsburgh School of
Medicine, Pittsburgh, PA
Associate Professor, Intelligent Systems Program (Secondary Appointment), University of
Pittsburgh, Pittsburgh, PA
Associate Professor, Clinical and Translational Science Institute (Secondary Appointment),
University of Pittsburgh, Pittsburgh, PA
Associate Professor, Department of Computational Biology (Secondary Appointment),
University of Pittsburgh
Other Experience and Professional Memberships
2001200120152005-
20072011-2012
Member, American Medical Informatics Association
Member, American Association for Artificial Intelligence
Association of Computing Machinery
Ad hoc reviewer for multiple journals, including Artificial Intelligence in Medicine, PLoS ONE,
PLoS Medicine, PLoS Computational Biology, Computers in Biology and Medicine, Medical
Decision Making, Science Translational Medicine, Journal of Biomedical Informatics, and
Journal of the American Medical Informatics Association
Editorial Board Member, International Journal of Medical Engineering and Informatics
NSF Peer Review Committee, Smart Health and Wellbeing Review Panel
Honors
1981-1991
1995-1996
2000-2001
2001-2005
2005
2010
2011
2012
2013
2014
2015
National Science Talent Search Scholarship, Government of India
Excellent Teacher, School of Life Sciences, University of Illinois at Urbana-Champaign,
Champaign, IL
Chief Resident, Department of Neurology, Boston University Medical Center, Boston, MA
National Library of Medicine Post-Doctoral Fellowship
Third place, American Medical Informatics Association (AMIA) Fall Symposium Student Paper
Competition, Washington DC
Homer R. Warner Research Award, AMIA Fall Symposium, Washington DC (for a co-authored
paper)
Marco Ramoni Distinguished Paper Award, AMIA 2011 Joint Summits on Translational Science,
San Francisco, CA (for a co-authored paper)
Distinguished Paper Award, AMIA 2012 Joint Summits on Translational Science, San
Francisco, CA (for a co-authored paper)
Distinguished Paper Award, AMIA 2013 Joint Summits on Translational Science, San
Francisco, CA (for a co-authored paper)
Hattie Becich Award for Best Teacher, Department of Biomedical Informatics, University of
Pittsburgh, Pittsburgh, PA
First place, AMIA Fall Symposium Student Paper Competition, Washington DC (for a lastauthored paper)
C. Contribution to Science
My research is focused on the application of artificial intelligence and machine learning to problems in the
Learning Healthcare System with a specific focus on developing intelligent electronic medical records,
precision medicine and personalized modeling, research data warehousing, and data mining and causal
discovery from genomic and biomedical data.
1. Intelligent electronic medical record and computerized clinical decision support. Electronic medical
records (EMRs) are capturing increasing amounts of patient data that can be leveraged by machinelearning methods for computerized decision support. My work focuses on the development of intelligent
EMRs that contain adaptive and learning components to provide decision support using the right data, at
the right time. I will use the expertise gained from this work to provide guidance in the proposed project in
enhancing the search log functionality and analyzing the resulting data, determining patient and clinician
characteristics as well as task context, and defining and evaluating the recommendation algorithms.
a. Visweswaran, S, Hanbury, P, Saul, M, Cooper, GF. Detecting adverse drug events in discharge
summaries using variations on the simple Bayes model. In: AMIA Annual Symposium Proceedings.
2003; 2003:689-93. PMID: 14728261 PMCID: PMC1479984
b. Visweswaran, S, Mezger, J, Clermont, G, Hauskrecht, M, Cooper, GF. Identifying deviations from
usual medical care using a statistical approach. In: AMIA Annual Symposium Proceedings. 22010
Nov 13; 2010:827-31. PMID: 21347094 PMCID: PMC3041340
c. Hauskrecht, M, Batal, I, Valko, M, Visweswaran, S, Cooper, GF, Clermont, G. Outlier detection for
patient monitoring and alerting. Journal of Biomedical Informatics. 2013 Feb; 46(1):47-55. PMID:
22944172 PMCID: PMC3567774
d. King, AJ, Cooper, GF, Hochheiser, H, Clermont, G, Visweswaran, S. Development and preliminary
evaluation of a prototype of a learning electronic medical record system. In: AMIA Annual
Symposium Proceedings. 2015 Nov 17; 2015:1967-75. PMCID: PMC4765593
2. Precision medicine and personalized modeling. I serve as a PD/PI for the Pitt Precision Medicine
Initiative project that is a component of the Cohort Program of President Obama’s Precision Medicine
Initiative. This project will enroll and collect data and bio specimens for 150,000 individuals for the
Precision Medicine Initiative.
In predictive modeling in medicine, the typical paradigm consists of learning a single model from a
database of individuals, which is then applied to predict outcomes for any future individual. Such a model is
called a population-wide model because it is intended to be applied to an entire population of future
individuals. In contrast, my work focusses on personalized modeling where models are tailored to the
characteristics of the individual at hand. Personalized models that are optimized to perform well for a
specific individual are likely to have better predictive performance than the typical population-wide models
that are optimized to have good predictive performance on average on all future individuals. Moreover,
personalized models can identify features such as genomic factors that are specific for an individual thus
enabling precision medicine.
a. Visweswaran, S, Cooper, GF. Patient-specific models for predicting the outcomes of patients with
community acquired pneumonia. In: AMIA Annual Symposium Proceedings. 2005; 2005:759-63.
PMID: 16779142 PMCID: PMC1560580 (Awarded Third Place in the Student Paper Competition at
the AMIA Annual Symposium, 2005)
b. Visweswaran, S, Angus, DC, Hsieh, M, Weissfeld, L, Yealy, D, Cooper, GF. Learning patientspecific predictive models from clinical data. Journal of Biomedical Informatics. 2010 Oct;43(5):66985. PMID: 20450985 PMCID: PMC2933959
c. Visweswaran, S, Cooper, GF. Learning instance-specific predictive models. Journal of Machine
Learning Research. 2010 Dec; 11:3369-3405. PMCID: PMC4102007
d. Ferreira, A, Cooper, GF, Visweswaran, S. Decision path models for patient-specific modeling of
patient outcomes. In: Proceedings of the Fall Symposium of the American Medical Informatics
Association. 2013 Nov 16; 2013:413-21. PMID: 24551347 PMCID: PMC3900188
e. Visweswaran, S, Ferreira, A, Cooper, GF. Personalized modeling for prediction with decision-path
models. PLoS One. 2015 Jun 22;10(6):e0131022 PMID: 26098570 PMCID: PMC4476684
3. Reuse of EMR data. Several local, regional and national efforts are ongoing that are creating clinical data
repositories for reuse of EMR data for clinical, translational, and informatics research. I lead the efforts for
data harmonization, translation to standard terminologies and mapping to standard value sets for several
projects that include: 1) CTSI-funded i2b2 – based Cohort Discovery Repository, 2) NCATS-funded Accrual
of patients to Clinical Trials (ACT) network, and 3) PCORI-funded PaTH clinical data research network
(CDRN).
a. Amin, W, Borromeo, C, Saul, M, Becich, MJ, Visweswaran, S. Informatics synergies between
PaTH and ACT networks. In: Proceedings of the 2015 Summit on Clinical Research Informatics.
2015 Mar 25; 2015:294-95.
b. Visweswaran, S, Tenenbaum, J, Gouripeddi, R. Secondary use of data for research - EHR, omics
and environmental data. In: AMIA Joint Summits Translational Science Proceedings. 2016 Mar 22.
4. Data mining and causal discovery from biomedical data. Developing efficient data mining and causal
discovery methods for biomarker discovery from high-dimensional genetic variant data is important for
genomic medicine. Genomic medicine is driving precision medicine and focuses on the use of information
obtained from sequences such as whole exomes and whole genomes. Genomic information, in
combination with clinical data, will lead to increased understanding of the biology of human health and
disease, improved prediction of disease and effect of therapy, and ultimately the realization of precision
medicine. My work focuses on single nucleotide variants (SNVs) data obtained from genome-wide studies
(GAWSs), and more recently whole exomes.
a. Jiang, X, Barmada, MM, Visweswaran, S. Identifying genetic interactions in genome-wide data
using Bayesian networks. Genetic Epidemiology. 2010 Sep; 34(6):575-81. PMID: 20568290
PMCID: PMC3931553.
b. Stokes, ME, Barmada, MM, Kamboh, MI, Visweswaran, S. The application of network label
propagation to rank biomarkers in genome-wide Alzheimer's data. BMC Genomics. 2014 Apr
14;15(1):282. PMID: 24731236 PMCID: PMC4234455
c. Aflakparast, M, Masoudi-Nejad, A, Bozorgmehr, JH, Visweswaran, S. Informative Bayesian Model
Selection: A method for identifying interactions in genome-wide data. Molecular BioSystems. 2014
Aug 26; 10(10):2654-62. PMID: 25070634
d. Strobl, EV, Visweswaran, S. Markov boundary discovery with ridge regularized linear models.
Journal of Causal Inference. 2016 Mar; 4(1):31-48.
Complete List of Published Work in MyBibliography:
http://goo.gl/brnulV
D. Research Support
Ongoing Research Support
UG3 OD023253
Reis, Visweswaran, Marroquin (PIs)
07/01/2016 - 06/30/2017
NIH
Precision Approach to healthCARE enrollment Site (PA CARES)
This Precision Medicine Initiative (PMI) Cohort Program Healthcare Provider Organization Enrollment Center
project will enroll 10,000 individuals in year 1 and collect EHR data and bio specimens.
Role: PD/PI
R01 LM012095
Visweswaran (PI)
09/15/2015 - 06/30/2019
NIH/NLM
Development and Evaluation of a Learning Electronic Medical Record System
This project investigates the development of intelligent electronic medical record systems (EMRs) that contain
adaptive and learning components to provide decision support using the right data, at the right time.
Role: PI (Sole)
UL1 TR001857
Reis (PI)
07/01/2016 - 05/31/2021
NIH/NCATS
Informatics Component, Clinical and Translational Science Institute
This grant provides funding support for the University of Pittsburgh’s CTSA program. The Informatics
Component provides informatics support and, in particular, supports maintenance of the Accrual of patients to
Clinical Trials (ACT) data repository network that enables cohort identification for clinical trial accrual across 21
CTSA sites.
Role: Co-Director, Informatics Component
U54 HG008540
Cooper, Bahar, Berg (PI)
10/01/2014 - 06/30/2018
NIH
Center for Causal Modeling and Discovery of Biomedical Knowledge from Big Data
This Center of Excellence is developing, implementing, and evaluating an integrated set of tools that support
causal modeling and discovery of biomedical knowledge from very large and complex biomedical data. It will
make these methods widely available to biomedical and data scientists, highly efficient when applied to big
datasets, and easy to use. The Center will also train biomedical scientists how to apply the methods to their
biomedical data and data scientists how to further develop the methods.
Role: Co-Investigator
R01 GM088224
Hauskrecht, Clermont, Cooper (PI)
08/15/2014 - 05/31/2018
NIH/NIGMS
Real-Time Detection of Deviations in Clinical Care in ICU Data Streams
There remain numerous opportunities to reduce medical errors in that occur during clinical care. This project is
developing and evaluating a new clinical monitoring and alerting framework that uses electronic medical
records and machine-learning methods to send alerts concerning clinical decisions in the ICU that are
unexpected in given the clinical context and may represent medical errors.
Role: Co-Investigator
Completed Research Support (Last Three Years)
UL1 TR000005
Reis (PI)
07/01/2015 - 06/30/2016
NIH/NCATS
Biomedical Informatics Core, Clinical and Translational Science Institute
This grant provides funding support to establish a clinical data repository network across 21 CTSA sites for
enabling cohort identification for accrual of patients to clinical trials.
Role: Co-Director, Informatics Component
CDRN-1306-04912
McTigue, Becich, Hess (PI)
10/01/2015 - 06/30/2016
PCORI
A PaTH towards a Learning Health System in the Mid-Atlantic Region
The PaTH Clinical Data Research Network brings together four Mid-Atlantic Health Systems: University of
Pittsburgh/UPMC, Penn State College of Medicine/Hershey Medical Center, Temple University School of
Medicine/Temple Health, and Johns Hopkins University/ Johns Hopkins Health System. The goal of PaTH is to
assemble and follow a longitudinal cohort of at least 1 million individuals across a variety of health care
settings for conducting patient-centered research.
T15 LM007059-25
Crowley (PI)
07/01/2012 - 01/31/2016
NIH/NLM/NIDR
Pittsburgh Biomedical Informatics Training Program
This grant provides funding support to graduate students in the Biomedical Informatics Training Program,
Department of Biomedical Informatics, University of Pittsburgh.
Role: Co-Investigator
UL1 TR000005-09S1
Reis (PI)
07/01/2014 - 06/30/2015
NIH/NCATS
CTSActs (Clinical and Translational Science Accrual to Clinical Trials)
This grant provides funding support to establish a clinical data repository network across 21 CTSA sites for
enabling cohort identification for accrual of patients to clinical trials.
Role: Co-Investigator