Vivian Beaumont Allen Professor of Biomedical Informatics, Columbia University
Chair, Department of Biomedical Informatics, Columbia University
Director, Medical Informatics Services, NewYork-Presbyterian Hospital/Columbia
George Hripcsak, MD, MS, is Vivian Beaumont Allen Professor and Chair of Columbia University’s Department of Biomedical Informatics and Director of Medical Informatics Services for NewYork-Presbyterian Hospital/Columbia Campus. He is a board-certified internist with degrees in chemistry, medicine, and biostatistics. Dr. Hripcsak’s current research focus is on the clinical information stored in electronic health records and on the development of next-generation health record systems. Using nonlinear time series analysis, machine learning, knowledge engineering, and natural language processing, he is developing the methods necessary to support clinical research and patient safety initiatives. He leads the Observational Health Data Sciences and Informatics (OHDSI) coordinating center; OHDSI is an international network with 180 researchers and 600 million patient records. For his work in precision medicine, he serves as a PI on Columbia’s eMERGE grant, as a PI on Columbia’s regional recruitment center for the All of Us precision medicine program, and as site PI for Columbia’s role on the All of Us Data and Research Center. He co-chaired the Meaningful Use Workgroup of U.S. Department of Health and Human Services’s Office of the National Coordinator of Health Information Technology; it defines the criteria by which health care providers collect incentives for using electronic health records. He led the effort to create the Arden Syntax, a language for representing health knowledge that has become a national standard. Dr. Hripcsak is a fellow of the National Academy of Medicine, the American College of Medical Informatics, and the New York Academy of Medicine, and he chaired the U.S. National Library of Medicine’s Biomedical Library and Informatics Review Committee. He has published over 350 papers.
Research openings: I welcome PhD and MD postdoctoral candidates interested in working on any of the research listed below. Experience in a relevant methodological area (e.g. nonlinear dynamics) and domain area (medicine, physiology) would be ideal. I also welcome Columbia graduate and undergraduate students.
1. Phenotyping. My work in decision support led me to realize that the main obstacle was our inability to exploit clinical data effectively. I therefore helped to create the informatics field now known as “phenotyping” with early publications in use of symbolic reasoning and machine learning to map raw health record data to clinical concepts. My work continues in this area to this day.
a. Hripcsak G, Johnson SB, Clayton PD. Desperately seeking data: knowledge base-database links. Proc Annu Symp Comput Appl Med Care 1993:639-43.
b. Wilcox A, Hripcsak G. Knowledge discovery and data mining to assist natural language understanding. Proc Amia Symp 1998:835-9.
c. Wilcox AB, Hripcsak G. The role of domain knowledge in automating medical text report classification. J Am Med Inform Assoc 2003;10:330-8. PMC181983
d. Hripcsak G, Albers DJ. Next-generation phenotyping of electronic health records. J Am Med Inform Assoc 2013;20:117–21:
2. Use of non-linear time series analysis in clinical phenotyping. My recent work in phenotyping has turned to the use of non-linear time series analysis to improve use of clinical data and understanding of physiologic processes, and I have begun to study the health care process itself and how it affects the recording of data so that we can reduce the bias associated with observational studies. This time series work was published not just in the top informatics journals, but also in top physics journals in non-linear science.
a. Albers DJ, Hripcsak G. A statistical dynamics approach to the study of human health data: resolving population scale diurnal variation in laboratory data. Physics Letters A 2010;374:1159-64.
b. Albers DJ, Hripcsak G. Using time-delayed mutual information to discover and interpret temporal correlation structure in complex populations. Chaos 2012;22:013111; doi:10.1063/1.3675621.
c. Hripcsak G, Albers DJ, Perotte A. Exploiting time in electronic health record correlations. J Am Med Inform Assoc 2011;18:Suppl 1 i109-i115.
d. Hripcsak G, Albers DJ, Perotte A. Parameterizing time in electronic health record studies. J Am Med Inform Assoc 2015 Feb 26. pii: ocu051. doi: 10.1093/jamia/ocu051.
e. Albers DJ, Levine M, Gluckman B, Ginsberg H, Hripcsak G, Mamykina L. Personalized glucose forecasting for type 2 diabetes using data assimilation. PLoS Comput Biol 2017;13:e1005232. doi: 10.1371/journal.pcbi.1005232:
3. Observational research and bridging phenotype and genotype. As PI of the Observational Health Data Sciences and Informatics (OHDSI) coordinating center, I assist the research community with its 600-million patient-record network, developing and applying new methods in observational research. As a PI on the Columbia eMERGE grant, as a PI of the Columbia PMI Cohort Program regional healthcare provider organization, and as site PI for Columbia’s role on the PMI Cohort Program Data and Research Support Center, I work in converting electronic health record data to a form useful for correlating with genomic information.
a. Ryan PB, Madigan D, Stang PE, Schuemie MJ, Hripcsak G. Medication-wide association studies. CPT: Pharmacometrics & Systems Pharmacology 2013;2,e76;doi:10.1038/psp.2013.52. PMC4026636
b. Overby CL, Pathak J, Gottesman O, Haerian K, Perotte A, Murphy S, Bruce K, Johnson S, Talwalkar J, Shen Y, Ellis S, Kullo I, Chute C, Friedman C, Bottinger E, Hripcsak G, Weng C. A collaborative approach to developing an electronic health record phenotyping algorithm for drug-induced liver injury. J Am Med Inform Assoc 2013 Dec;20(e2):e243-52. doi: 10.1136/amiajnl-2013-001930. PMC3861914
c. Duke JD, Ryan PB, Suchard MA, Hripcsak G, Jin P, Reich C, Schwalm MS, Khoma Y, Wu Y, Xu H, Shah NH, Banda JM, Schuemie MJ. Risk of angioedema associated with levetiracetam compared with phenytoin: Findings of the observational health data sciences and informatics research network. Epilepsia 2017 doi: 10.1111/epi.13828.
d. Hripcsak G, Ryan P, Duke J, Shah NH, Park RW, Huser V, Suchard MA, Schuemie M, DeFalco F, Perotte A, Banda J, Reich C, Shilling L, Matheny M, Meeker D, Pratt N, Madigan D. Addressing clinical questions at scale: OHDSI characterization of treatment pathways. Proc Natl Acad Sci USA 2016. DOI: 10.1073/pnas.1510502113:
4. Electronic health records and automated decision support. My earliest work was in health knowledge representation and decision support. I led the creation of the Arden Syntax, which is a standard for representing health knowledge related to alerts and reminders. It was adopted as an international standard and today sits under the Health Level Seven (HL7) standards organization. Paralleling my career-long work building and running electronic health records and setting national policy for health records (co-chairing the Meaningful Use Workgroup), I have been publishing on the use and effect of health records.
a. Hripcsak G, Hripcsak G, Ludemann P, Pryor TA, Wigertz OB, Clayton PD. Rationale for the Arden Syntax. Comput Biomed Res 1994;27:291–324.
b. Shea S, Hripcsak G. Accelerating the use of electronic health records in physician practices. NEJM 2010;362:192-5.
c. Hripcsak G, Vawdrey DK, Fred MR, Bostwick SB. Use of electronic clinical documentation: time spent and team interactions. J Am Med Inform Assoc 2011;18:112-7.
d. Green RA, Hripcsak G, Salmasian H, Lazar EJ, Bostwick SB, Bakken SR,Vawdrey DK. Intercepting Wrong-Patient Orders in a Computerized Provider Order Entry System. Ann Emerg Med 2014 Dec 17. pii: S0196-0644(14)01558-3. doi: 10.1016/j.annemergmed.2014.11.017:
5. Natural language processing evaluation and temporal processing. I developed new methods for evaluating natural language processing and published the first large-scale evaluation of natural language processing in health care, followed by the first prospective trial demonstrating that natural language processing could improve health care quality (respiratory isolation). I subsequently published studies showing use of natural language processing for quality measurement and for public health surveillance. I developed new methods for temporal data in narrative reports with a demonstration of its performance.
a. Hripcsak G, Friedman C, Alderson PO, DuMouchel W, Johnson SB, Clayton PD. Unlocking clinical data from narrative reports: a study of natural language processing. Ann Intern Med 1995;122:681–8.
b. Knirsch C, Jain NL, Pablos-Mendez A, Friedman C, Hripcsak G. Respiratory isolation of tuberculosis patients using clinical guidelines and an automated clinical decision support system. Infect Control Hosp Epidemiol 1998;19:94–100.
c. Hripcsak G, Zhou L, Parsons S, Das AK, Johnson SB. Modeling electronic discharge summaries as a simple temporal constraint satisfaction problem. J Am Med Inform Assoc 2005;12:55–63.
d. Zhou L, Parsons S, Hripcsak G. The evaluation of a temporal reasoning system in processing clinical discharge summaries. J Am Med Inform Assoc 2008;15:99-106. PMC2274869
e. Hripcsak G, Elhadad N, Chen C, Zhou L, Morrison FP. Using empirical semantic correlation to interpret temporal assertions in clinical texts. J Am Med Inform Assoc 2009;16:220-7:
As Director of Medical Informatics Services for NewYork-Presbyterian Hospital/Columbia, I oversee the clinical data warehouse, terminology, iNYP, immunization, and physician outreach and collaborate on clinician documentation, health information exchange, and patient portals.
We offer programs at all levels of informatics training, including PhDs, master's degrees, postdoctoral fellowship, certificate training, and education for students in medicine, nursing, dentistry, and public health. See www.dbmi.columbia.edu. I am accepting Columbia graduate and undergraduate students, and I have slots for postdocs in my areas of research.
Hripcsak, MD, MS
622 West 168th Street, PH20
New York, NY 10032