Mining electronic health records: towards better research applications and clinical care
The DOI matches its Crossref record; 117 of the 117 references it cites were found in a registry or an index.
Abstract
Clinical data describing the phenotypes and treatment of patients represents an underused data source that has much greater research potential than is currently realized. Mining of electronic health records (EHRs) has the potential for establishing new patient-stratification principles and for revealing unknown disease correlations. Integrating EHR data with genetic data will also give a finer understanding of genotype-phenotype relationships. However, a broad range of ethical, legal and technical reasons currently hinder the systematic deposition of these data in EHRs and their mining. Here, we consider the potential for furthering medical research and clinical care using EHR data and the challenges that must be overcome before this is a reality.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Conventional relational databases, while efficient for storing structured data, struggle to represent the intricate relationships between clinical events, medications, diagnoses, and patient outcomes (2).”
From Unlocking electronic health records: a hybrid graph RAG approach to safe clinical AI for patient QA (2026) · cites this paper as [2]
Citations
Cites
Enterotypes of the human gut microbiome
MetaHIT Consortium (additional members), Arumugam, M., Raes, J., Pelletier, E., Le Paslier, D., Yamada, T., Mende, D. R., Fernandes, G. R., Tap, J., Bruls, T., et al. (2011) · Nature · doi:10.1038/nature09944 · Cited by 7,548 · cited 1×
“Similar concerns apply to other types of molecular-level data, for example, individual gut microbiome profiles 99 .”
BackgroundSelf-citationThe unified medical language system (UMLS): integrating biomedical terminology
Bodenreider, O. (2004) · Nucleic Acids Research · doi:10.1093/nar/gkh061 · Cited by 4,356 · cited 2×
“Deriving structured information about patient phenotypes from clinical text generally requires named entities or concepts in the text to be recognized and mapped to codes in a relevant controlled vocabulary such as Systematized Nomenclature of Medicine — Clinical Terms (SNOMED CT) 25 or one of the other >100 vocabular…”
BackgroundA tutorial on pilot studies: the what, why and how
Thabane, L., Ma, J., Chu, R., Cheng, J., Ismaila, A., Rios, L. P., Robson, R., Thabane, M., Giangregorio, L., & Goldsmith, C. H. (2010) · BMC Medical Research Methodology · doi:10.1186/1471-2288-10-1 · Cited by 3,384
Goh, K.-I., Cusick, M. E., Valle, D., Childs, B., Vidal, M., & Barabási, A.-L. (2007) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0701361104 · Cited by 3,242 · cited 1×
“This has also been an approach in network medicine, in which diseases are clustered based on shared associated genes, as is seen, for example, in the human disease network 85 .”
BackgroundSavova, G. K., Masanz, J. J., Ogren, P. V., Zheng, J., Sohn, S., Kipper-Schuler, K. C., & Chute, C. G. (2010) · Journal of the American Medical Informatics Association · doi:10.1136/jamia.2009.001560 · Cited by 1,967 · cited 2×
“The Mayo clinic’s clinical Text Analysis and Knowledge Extraction System (cTAKES) 27 , the Informatics for Integrating Biology and the Bedside (i2b2) HITEX 28 and the long-running Medical Language Extraction and Encoding (MedLEE) 29 system from Columbia University are all examples of NLP-based…”
MethodHow to measure comorbiditya critical review of available methods
DEGROOT, V, BECKERMAN, H., LANKHORST, G., & BOUTER, L. (2003) · Journal of Clinical Epidemiology · doi:10.1016/s0895-4356(02)00585-1 · Cited by 1,757 · cited 1×
“In clinical practice, the cumulated disease burden of a patient is often summarized in comorbidity scores such as the Charlson index , and these scores are also often used to interpret confounding effects of comorbid diseases in cohort studies 38 .”
BackgroundHillestad, R., Bigelow, J., Bower, A., Girosi, F., Meili, R., Scoville, R., & Taylor, R. (2005) · Health Affairs · doi:10.1377/hlthaff.24.5.1103 · Cited by 1,675
A review on time series data mining
Fu, T.-C. (2011) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2010.09.007 · Cited by 1,500 · cited 1×
“Health data that are recorded over short timescales (such as time series data of blood glucose levels) are sometimes collected in EHR systems; for these short-term data, various analysis methods exist 59 .”
MethodBuntin, M. B., Burke, M. F., Hoaglin, M. C., & Blumenthal, D. (2011) · Health Affairs · doi:10.1377/hlthaff.2011.0178 · Cited by 1,311
2010 i2b2/VA challenge on concepts, assertions, and relations in clinical text
Uzuner, Ö., South, B. R., Shen, S., & DuVall, S. L. (2011) · Journal of the American Medical Informatics Association · doi:10.1136/amiajnl-2011-000203 · Cited by 1,252
Homer, N., Szelinger, S., Redman, M., Duggan, D., Tembe, W., Muehling, J., Pearson, J. V., Stephan, D. A., Nelson, S. F., & Craig, D. W. (2008) · PLoS Genetics · doi:10.1371/journal.pgen.1000167 · Cited by 1,221
PheWAS: demonstrating the feasibility of a phenome-wide scan to discover gene–disease associations
Denny, J. C., Ritchie, M. D., Basford, M. A., Pulley, J. M., Bastarache, L., Brown-Gentry, K., Wang, D., Masys, D. R., Roden, D. M., & Crawford, D. C. (2010) · Bioinformatics · doi:10.1093/bioinformatics/btq126 · Cited by 1,219 · cited 1×
“A phenome-wide association study (PheWAS) 76 , introduced by Vanderbilt BioVU, starts with the individual SNP and checks for statistical association against hundreds of disease phenotypes of patients that have been genotyped for that SNP. Pharmacogenomics is another research area that is embracing…”
MethodPredicting breast cancer survivability: a comparison of three data mining methods
Delen, D., Walker, G., & Kadam, A. (2005) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2004.07.002 · Cited by 1,218 · cited 1×
“Nature Reviews | Genetics Examples include the prediction of surgery outcome 53 , breast cancer survival 54 and coronary heart disease risk 55 from variables such as age, sex, smoking A simplified illustration of an electronic health record (EHR) research database and some of the data-driven…”
BackgroundSystems Biology and New Technologies Enable Predictive and Preventative Medicine
Hood, L., Heath, J. R., Phelps, M. E., & Lin, B. (2004) · Science · doi:10.1126/science.1104635 · Cited by 1,108 · cited 1×
“Systems-level analyses can drastically reduce the combinatorial problem by grouping individual genetic variants that affect the same molecular machinery, thus increasing the feasibility of turning EHR data into valuable clinical markers relative to single-gene approaches 88,89 .”
BackgroundThygesen, L. C., Daasnes, C., Thaulow, I., & Brønnum-Hansen, H. (2011) · Scandinavian Journal of Public Health · doi:10.1177/1403494811399956 · Cited by 1,084 · cited 1×
“Merged national registries on health and socio-economic status 16 are a valuable source of standardized, longitudinal, population-wide data for traditional epidemiological studies 17,18 .”
BackgroundA Computer-Assisted Management Program for Antibiotics and Other Antiinfective Agents
Evans, R. S., Pestotnik, S. L., Classen, D. C., Clemmer, T. P., Weaver, L. K., Orme, J. F., Lloyd, J. F., & Burke, J. P. (1998) · New England Journal of Medicine · doi:10.1056/nejm199801223380406 · Cited by 1,061 · cited 1×
“Another example is for the early warning of infection, with suggestions for antibiotic treatment and dosage based on physiological data 33 .”
BackgroundDevelopment of a Large-Scale De-Identified DNA Biobank to Enable Personalized Medicine
Roden, D., Pulley, J., Basford, M., Bernard, G., Clayton, E., Balser, Jr., & Masys, D. (2008) · Clinical Pharmacology & Therapeutics · doi:10.1038/clpt.2008.89 · Cited by 983 · cited 1×
“Sanction for the use of EHR data in research in anonymous form is obtained as part of the standard treatment consent form 75 .”
MethodServing the enterprise and beyond with informatics for integrating biology and the bedside (i2b2)
Murphy, S. N., Weber, G., Mendis, M., Gainer, V., Chueh, H. C., Churchill, S., & Kohane, I. (2010) · Journal of the American Medical Informatics Association · doi:10.1136/jamia.2009.000893 · Cited by 925
Savova, G. K., Kipper-Schuler, K. C., Hurdle, J. F., & Meystre, S. M. (2008) · Yearbook of Medical Informatics · doi:10.1055/s-0038-1638592 · Cited by 895 · cited 2×
“22 and the September 2011 special issue of the Journal of the American Medical Informatics Association (JAMIA) 32 .”
BackgroundFish Oil, Raynaud's Syndrome, and Undiscovered Public Knowledge
Swanson, D. R. (1986) · Perspectives in Biology and Medicine · doi:10.1353/pbm.1986.0087 · Cited by 866 · cited 1×
“In text mining of the biomedical literature this approach has long been used to discover hidden associations 51,52 .”
MethodWhen an Entire Country Is a Cohort
Frank, L. (2000) · Science · doi:10.1126/science.287.5462.2398 · Cited by 864 · cited 1×
“Merged national registries on health and socio-economic status 16 are a valuable source of standardized, longitudinal, population-wide data for traditional epidemiological studies 17,18 .”
BackgroundPredictive data mining in clinical medicine: Current issues and guidelines
BELLAZZI, R., & ZUPAN, B. (2008) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2006.11.006 · Cited by 823 · cited 1×
“…in the next sections, exploring this knowledge-discovery potential from multivariate health data increasingly involves a suite of statistical, machine-learning and computational methods that are often referred to as data-mining methods or knowledge discovery in databases (KDD) methods 35–37 .”
BackgroundGreenblum, S., Turnbaugh, P. J., & Borenstein, E. (2012) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1116053109 · Cited by 821 · cited 1×
“Similar types of analyses can be used to interpret differences in the human microbiomes between individuals, as shown in a pathway analysis of gut metagenomics data in the context of obesity and inflammatory bowel disease 83 .”
A General Natural-language Text Processor for Clinical Radiology
Friedman, C., Alderson, P. O., Austin, J. H. M., Cimino, J. J., & Johnson, S. B. (1994) · Journal of the American Medical Informatics Association · doi:10.1136/jamia.1994.95236146 · Cited by 778 · cited 1×
“…Text Analysis and Knowledge Extraction System (cTAKES) 27 , the Informatics for Integrating Biology and the Bedside (i2b2) HITEX 28 and the long-running Medical Language Extraction and Encoding (MedLEE) 29 system from Columbia University are all examples of NLP-based clinical phenotyping systems.”
MethodBlumenthal, D. (2010) · New England Journal of Medicine · doi:10.1056/nejmp0912825 · Cited by 714 · cited 1×
“EHR adoption is growing thanks to initiatives like the US$19 billion HITECH act 10 in the United States and the €2 billion public–private partnership Innovative Medicines Initiative (IMI) 11 in the European Union.”
Backgroundthe eMERGE Team, McCarty, C. A., Chisholm, R. L., Chute, C. G., Kullo, I. J., Jarvik, G. P., Larson, E. B., Li, R., Masys, D. R., Ritchie, M. D., et al. (2011) · BMC Medical Genomics · doi:10.1186/1755-8794-4-13 · Cited by 699 · cited 3×
“This is the scenario realized in the i2b2 framework 63 and in the electronic Medical Records and Genomics Network (eMERGE Network) 64 .”
MethodA COMPUTER-ASSISTED MANAGEMENT PROGRAM FOR ANTIBIOTICS AND OTHER ANTIINFECTIVE AGENTS
Vans, R. S. C. E., Estotnik, S. T. L. P., Lassen, D. A. C. C., Lemmer, T., Eaver, L. I. K. W., Rme, J. A. F. O., Loyd, J. A. F. L., & Urke, J. O. P. B. (1998) · Cited by 692
What can natural language processing do for clinical decision support?
Demner-Fushman, D., Chapman, W. W., & McDonald, C. J. (2009) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2009.08.007 · Cited by 688 · cited 1×
“For complex rules or when the necessary information is not available in structured form, NLP-based processing of text may supplement structured data points 34 .”
BackgroundClinical assessment incorporating a personal genome
Ashley, E. A., Butte, A. J., Wheeler, M. T., Chen, R., Klein, T. E., Dewey, F. E., Dudley, J. T., Ormond, K. E., Pavlovic, A., Morgan, A. A., et al. (2010) · The Lancet · doi:10.1016/s0140-6736(10)60452-7 · Cited by 674
A Dynamic Network Approach for the Study of Human Phenotypes
Hidalgo, C. A., Blumm, N., Barabási, A.-L., & Christakis, N. A. (2009) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1000353 · Cited by 674 · cited 2×
“Establishing patterns of directionality in comorbidity and disease progression is a first step towards using EHRs for predictive purposes, and this has been explored in network analysis studies of Medicare data 42,58 .”
BackgroundGenetic Determinants of Response to Warfarin during Initial Anticoagulation
Schwarz, U. I., Ritchie, M. D., Bradford, Y., Li, C., Dudek, S. M., Frye-Anderson, A., Kim, R. B., Roden, D. M., & Stein, C. M. (2008) · New England Journal of Medicine · doi:10.1056/nejmoa0708078 · Cited by 577 · cited 1×
“Drug efficacy is influenced by genetic variation, as is seen in the example of the dose response to the anticoagulant warfarin being affected by at least three genetic variants 80 .”
BackgroundDeterminants of Under-Reporting of Adverse Drug Reactions: A Systematic Review
Lopez-Gonzalez, E., Herdeiro, M. T., & Figueiras, A. (2009) · Drug Safety · doi:10.2165/00002018-200932010-00002 · Cited by 574 · cited 1×
“In pharmacovigilance , disproportionality methods are used in post-marketing drug surveillance 43 , which is mainly based on the voluntary reporting of adverse drug event (ADE) data to spontaneous reporting databases; such events suffer from gross underreporting 44 .”
MethodAutomated Encoding of Clinical Documents Based on Natural Language Processing
Friedman, C., Shagina, L., Lussier, Y., & Hripcsak, G. (2004) · Journal of the American Medical Informatics Association · doi:10.1197/jamia.m1552 · Cited by 551 · cited 1×
“Although still mostly used in research contexts, MedLEE has demonstrated performance similar to expert human curators 30 and is in clinical operation at several health facilities.”
MethodMedEx: a medication information extraction system for clinical narratives
Xu, H., Stenner, S. P., Doan, S., Johnson, K. B., Waitman, L. R., & Denny, J. C. (2010) · Journal of the American Medical Informatics Association · doi:10.1197/jamia.m3378 · Cited by 531
Extracting medication information from clinical text
Uzuner, Ö., Solti, I., & Cadag, E. (2010) · Journal of the American Medical Informatics Association · doi:10.1136/jamia.2010.003947 · Cited by 466
Kurt, I., Ture, M., & Kurum, A. T. (2008) · Expert Systems with Applications · doi:10.1016/j.eswa.2006.09.004 · Cited by 410 · cited 1×
“Nature Reviews | Genetics Examples include the prediction of surgery outcome 53 , breast cancer survival 54 and coronary heart disease risk 55 from variables such as age, sex, smoking A simplified illustration of an electronic health record (EHR) research database and some of the data-driven…”
BackgroundData from clinical notes: a perspective on the tension between structure and flexible documentation
Rosenbloom, S. T., Denny, J. C., Xu, H., Lorenzi, N., Stead, W. W., & Johnson, K. B. (2011) · Journal of the American Medical Informatics Association · doi:10.1136/jamia.2010.007237 · Cited by 404 · cited 1×
“Free text allows the flexibility to express case nuances and clinical reasoning; this flexibility is valued by clinicians and is not easily replaced by structured reporting formats that are often considered inflexible and time consuming 23 .”
BackgroundRecurrence of Congenital Heart Defects in Families
Øyen, N., Poulsen, G., Boyd, H. A., Wohlfahrt, J., Jensen, P. K. A., & Melbye, M. (2009) · Circulation · doi:10.1161/circulationaha.109.857987 · Cited by 382 · cited 1×
“Merged national registries on health and socio-economic status 16 are a valuable source of standardized, longitudinal, population-wide data for traditional epidemiological studies 17,18 .”
BackgroundSelf-citationWicks, P., Vaughan, T. E., Massagli, M. P., & Heywood, J. (2011) · Nature Biotechnology · doi:10.1038/nbt.1837 · Cited by 362 · cited 1×
“As a special case of today’s data sharing trend, online health resources such as PatientsLikeMe allow patients to share detailed health and treatment information, which again is providing a novel data source for cross-cohort studies 105 .”
BackgroundZeng, Q. T., Goryachev, S., Weiss, S., Sordo, M., Murphy, S. N., & Lazarus, R. (2006) · BMC Medical Informatics and Decision Making · doi:10.1186/1472-6947-6-30 · Cited by 360
Identifying Patient Smoking Status from Medical Discharge Records
Uzuner, O., Goldstein, I., Luo, Y., & Kohane, I. (2008) · Journal of the American Medical Informatics Association · doi:10.1197/jamia.m2408 · Cited by 359
Selected techniques for data mining in medicine
Lavrač, N. (1999) · Artificial Intelligence in Medicine · doi:10.1016/s0933-3657(98)00062-1 · Cited by 351 · cited 1×
“…in the next sections, exploring this knowledge-discovery potential from multivariate health data increasingly involves a suite of statistical, machine-learning and computational methods that are often referred to as data-mining methods or knowledge discovery in databases (KDD) methods 35–37 .”
BackgroundElectronic Medical Records for Genetic Research: Results of the eMERGE Consortium
Kho, A. N., Pacheco, J. A., Peissig, P. L., Rasmussen, L., Newton, K. M., Weston, N., Crane, P. K., Pathak, J., Chute, C. G., Bielinski, S. J., et al. (2011) · Science Translational Medicine · doi:10.1126/scitranslmed.3001807 · Cited by 336 · cited 1×
“A high precision 65,66 of the approach has been documented and demonstrated in genome-wide association studies (GWASs) and other types of cohort research 67–74 .”
BackgroundMeystre, S. M., Friedlin, F. J., South, B. R., Shen, S., & Samore, M. H. (2010) · BMC Medical Research Methodology · doi:10.1186/1471-2288-10-70 · Cited by 329 · cited 1×
“De-identification normally allows researchers to circumvent costly consent regimes 94 , but the lack of identifiers makes certain types of population-wide research impossible, as other information cannot be linked to data subjects.”
BackgroundUsing electronic health records to drive discovery in disease genomics
Kohane, I. S. (2011) · Nature Reviews Genetics · doi:10.1038/nrg2999 · Cited by 325 · cited 1×
“Realizing the full potential of EHR-based recruitment of patients for genetic research requires a framework for the easy acquisition of matched DNA samples and for patient consent 4 .”
BackgroundRitchie, M. D., Denny, J. C., Crawford, D. C., Ramirez, A. H., Weiner, J. B., Pulley, J. M., Basford, M. A., Brown-Gentry, K., Balser, J. R., Masys, D. R., et al. (2010) · The American Journal of Human Genetics · doi:10.1016/j.ajhg.2010.03.003 · Cited by 323
Evaluating re-identification risks with respect to the HIPAA privacy rule
Benitez, K., & Malin, B. (2010) · Journal of the American Medical Informatics Association · doi:10.1136/jamia.2009.000026 · Cited by 301 · cited 1×
“Moreover, despite such precautions, re-identification has been shown on some occasions to be a genuine risk 95 , especially when data on human DNA are involved, as even a relatively small set of markers can enable unique identification 96–98 .”
BackgroundKho, A. N., Hayes, M. G., Rasmussen-Torvik, L., Pacheco, J. A., Thompson, W. K., Armstrong, L. L., Denny, J. C., Peissig, P. L., Miller, A. W., Wei, W.-Q., et al. (2012) · Journal of the American Medical Informatics Association · doi:10.1136/amiajnl-2011-000439 · Cited by 299
Probing genetic overlap among complex human phenotypes
Rzhetsky, A., Wajngurt, D., Park, N., & Zheng, T. (2007) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0704820104 · Cited by 298 · cited 1×
“That being said, it is possible to estimate the degree of genetic overlap between two diseases based on traditional EHR data alone 84 .”
BackgroundWang, X., Hripcsak, G., Markatou, M., & Friedman, C. (2009) · Journal of the American Medical Informatics Association · doi:10.1197/jamia.m3028 · Cited by 288 · cited 1×
“As an alternative, mining of medication and ADE data that are captured routinely in EHRs is being explored as an approach to rapidly uncover drug–ADE associations 45 .”
BackgroundUsing Electronic Patient Records to Discover Disease Correlations and Stratify Patient Cohorts
Roque, F. S., Jensen, P. B., Schmock, H., Dalgaard, M., Andreatta, M., Hansen, T., Søeby, K., Bredkjær, S., Juul, A., Werge, T., et al. (2011) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1002141 · Cited by 282 · cited 3×
“An approach to investigate the underlying molecular aetiology of disease correlations that have been uncovered using EHR data is to map the diseases to known associated genes and proteins, and to investigate the resulting protein–protein interaction network for statistical overlaps 40 .”
BackgroundMethodSelf-citationKho, M. E., Duffett, M., Willison, D. J., Cook, D. J., & Brouwers, M. C. (2009) · BMJ · doi:10.1136/bmj.b866 · Cited by 269 · cited 1×
“From a research point of view this amounts to increased time and cost 91 and the risk of biased data resources owing to differing inclinations to participate among demographic groups 92 .”
BackgroundProkosch, H. (2009) · doi:10.3414/me9132 · Cited by 262
Coloma, P. M., Schuemie, M. J., Trifirò, G., Gini, R., Herings, R., Hippisley‐Cox, J., Mazzaglia, G., Giaquinto, C., Corrao, G., Pedersen, L., et al. (2011) · Pharmacoepidemiology and Drug Safety · doi:10.1002/pds.2053 · Cited by 259 · cited 1×
“Such an approach may be more powerful if data from several countries are pooled, such as in the European Union adverse drug reactions (EU-ADR) project 46 ; the international nature of the project emphasizes once again the importance of EHR interoperability.”
BackgroundIs Deidentification Sufficient to Protect Health Privacy in Research?
Rothstein, M. A. (2010) · The American Journal of Bioethics · doi:10.1080/15265161.2010.494215 · Cited by 253 · cited 1×
“Another public concern that is at odds with loosened consent models is the fear that personal data could be used for research that is in conflict with an individual’s ethical, moral or religious convictions 100 .”
BackgroundThe impact of cellular networks on disease comorbidity
Park, J., Lee, D., Christakis, N. A., & Barabási, A. (2009) · Molecular Systems Biology · doi:10.1038/msb.2009.16 · Cited by 250 · cited 1×
“Using comorbidities from Medicare claims data, Park et al. 86 used gene–disease association data to document that higher comorbidity was related to increased genetic overlap.”
MethodDenny, J. C., Crawford, D. C., Ritchie, M. D., Bielinski, S. J., Basford, M. A., Bradford, Y., Chai, H. S., Bastarache, L., Zuvich, R., Peissig, P., et al. (2011) · The American Journal of Human Genetics · doi:10.1016/j.ajhg.2011.09.008 · Cited by 246
Knaup, P., Hovenga, E. J. S., Heard, S., & Garde, S. (2007) · Methods of Information in Medicine · doi:10.1160/me5001 · Cited by 244 · cited 1×
“…a clinician might want to describe and combines this with international ontologies such as SNOMED CT. Archetypes separate the representation of clinical data from the underlying technical implementation and are authored by domain experts themselves without the need for technical expertise 104 .”
BackgroundLacerda, S. M. S. N., Batlouni, S. R., Costa, G. M. J., Segatelli, T. M., Quirino, B. R., Queiroz, B. M., Kalapothakis, E., & França, L. R. (2010) · PLoS ONE · doi:10.1371/journal.pone.0010740 · Cited by 231
Recognizing Obesity and Comorbidities in Sparse Data
Uzuner, O. (2009) · Journal of the American Medical Informatics Association · doi:10.1197/jamia.m3115 · Cited by 231
A Progress Report On Electronic Health Records In U.S. Hospitals
Jha, A. K., DesRoches, C. M., Kralovec, P. D., & Joshi, M. S. (2010) · Health Affairs · doi:10.1377/hlthaff.2010.0502 · Cited by 225 · cited 1×
“Even though relatively few hospitals have adopted top-level EHR systems covering all aspects of hospital operations, a substantial fraction do have IT infrastructure in place that captures valuable research data from different auxiliary clinical and administrative systems 14 .”
BackgroundBombard, Y., Veenstra, G., Friedman, J. M., Creighton, S., Currie, L., Paulsen, J. S., Bottorff, J. L., Hayden, M. R., & the Canadian Respond-HD Collaborative Research Group (2009) · BMJ · doi:10.1136/bmj.b2175 · Cited by 221
Hospital Computing and the Costs and Quality of Care: A National Study
Himmelstein, D. U., Wright, A., & Woolhandler, S. (2010) · The American Journal of Medicine · doi:10.1016/j.amjmed.2009.09.004 · Cited by 212
Steindel, S. J. (2010) · Journal of the American Medical Informatics Association · doi:10.1136/jamia.2009.001230 · Cited by 197
Perlis, R. H., Iosifescu, D. V., Castro, V. M., Murphy, S. N., Gainer, V. S., Minnier, J., Cai, T., Goryachev, S., Zeng, Q., Gallagher, P. J., et al. (2012) · Psychological Medicine · doi:10.1017/s0033291711000997 · Cited by 193
Data mining and clinical data repositories: Insights from a 667,000 patient data set
Mullins, I. M., Siadaty, M. S., Lyman, J., Scully, K., Garrett, C. T., Greg Miller, W., Muller, R., Robson, B., Apte, C., Weiss, S., et al. (2006) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2005.08.003 · Cited by 179 · cited 1×
“Association rule mining 48,49 is a KDD method that is often applied to the challenge of exploring the enormous combinatorial space of clinical features to identify potential correlations.”
MethodMining multi-item drug adverse effect associations in spontaneous reporting systems
Harpaz, R., Chase, H. S., & Friedman, C. (2010) · BMC Bioinformatics · doi:10.1186/1471-2105-11-s9-s7 · Cited by 171 · cited 1×
“This indicates an increased likelihood of a person being associated with the clinical finding ‘bleeding’ if that patient is also associated with the drugs warfarin and aspirin 50 .”
BackgroundThe Emerging Role of Electronic Medical Records in Pharmacogenomics
Wilke, R. A., Xu, H., Denny, J. C., Roden, D. M., Krauss, R. M., McCarty, C. A., Davis, R. L., Skaar, T., Lamba, J., & Savova, G. (2011) · Clinical Pharmacology & Therapeutics · doi:10.1038/clpt.2010.260 · Cited by 171 · cited 1×
“…by Vanderbilt BioVU, starts with the individual SNP and checks for statistical association against hundreds of disease phenotypes of patients that have been genotyped for that SNP. Pharmacogenomics is another research area that is embracing the integration of EHR data with genetic data 77 .”
BackgroundBuilding a National Health IT System from the Middle Out
Coiera, E. (2009) · Journal of the American Medical Informatics Association · doi:10.1197/jamia.m3183 · Cited by 162 · cited 10×
“With the growing number of recorded features in EHRs, machine-learning methodology has a huge potential for adding and complementing expertise that is currently held by staff in the health-care sector.”
BackgroundInfluentialAn Electronic Health Record Based on Structured Narrative
Johnson, S. B., Henry, S. B., Dine, D., Hyun, S., Mendonça, E. A., Morrison, F. R., Bright, T. J., Vleck, T. T. V., Wrenn, J. O., & Stetson, P. D. (2007) · Journal of the American Medical Informatics Association · doi:10.1197/jamia.m2131 · Cited by 160
Himes, B. E., Dai, Y., Kohane, I. S., Weiss, S. T., & Ramoni, M. F. (2009) · Journal of the American Medical Informatics Association · doi:10.1197/jamia.m2846 · Cited by 143 · cited 1×
“A high precision 65,66 of the approach has been documented and demonstrated in genome-wide association studies (GWASs) and other types of cohort research 67–74 .”
BackgroundWright, A. T., Chen, E. S., & Maloney, F. L. (2010) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2010.09.009 · Cited by 141 · cited 1×
“Association rule mining 48,49 is a KDD method that is often applied to the challenge of exploring the enormous combinatorial space of clinical features to identify potential correlations.”
MethodMasutani, Y., MacMahon, H., & Doi, K. (2002) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2002.806586 · Cited by 137 · cited 1×
“Radiological imaging requests and results are exchanged the same way, but the extraction of information traditionally relies on human 19 ), thus adding a structured component that is usable in CDS systems.”
BackgroundInstrumenting the health care enterprise for discovery research in the genomic eraPreprint
Murphy, S. N., Churchill, S. E., Bry, L., Chueh, H. C., Weiss, S. T., Lazarus, R. M., Zeng, Q. T., Dubey, A. K., Gainer, V. S., Mendis, M., et al. (2009) · Genome Research · doi:10.1101/gr.094615.109 · Cited by 128 · cited 2×
“One of the biggest research promises of EHR systems is to alleviate this bottleneck in cohort studies 62 .”
BackgroundMethodCancer metastasis networks and the prediction of progression patterns
Chen, L. L., Blumm, N., Christakis, N. A., Barabási, A.-Ĺ., & Deisboeck, T. S. (2009) · British Journal of Cancer · doi:10.1038/sj.bjc.6605214 · Cited by 126 · cited 1×
“Establishing patterns of directionality in comorbidity and disease progression is a first step towards using EHRs for predictive purposes, and this has been explored in network analysis studies of Medicare data 42,58 .”
BackgroundAssessing the Privacy Risks of Data Sharing in Genomics
Heeney, C., Hawkins, N., de Vries, J., Boddington, P., & Kaye, J. S. (2010) · Public Health Genomics · doi:10.1159/000294150 · Cited by 125 · cited 1×
“Moreover, despite such precautions, re-identification has been shown on some occasions to be a genuine risk 95 , especially when data on human DNA are involved, as even a relatively small set of markers can enable unique identification 96–98 .”
BackgroundOztekin, A., Delen, D., & Kong, Z. (2009) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2009.04.007 · Cited by 124 · cited 1×
“Nature Reviews | Genetics Examples include the prediction of surgery outcome 53 , breast cancer survival 54 and coronary heart disease risk 55 from variables such as age, sex, smoking A simplified illustration of an electronic health record (EHR) research database and some of the data-driven…”
BackgroundKurreeman, F. A. S., Liao, K. P., Chibnik, L. B., Hickey, B., Stahl, E. A., Gainer, V. S., Li, G., Bry, L., Mahan, S. P., Ardlie, K., et al. (2011) · The American Journal of Human Genetics · doi:10.1016/j.ajhg.2010.12.007 · Cited by 122 · cited 1×
“A high precision 65,66 of the approach has been documented and demonstrated in genome-wide association studies (GWASs) and other types of cohort research 67–74 .”
BackgroundA Genome-Wide Association Study of Red Blood Cell Traits Using the Electronic Medical Record
Kullo, I. J., Ding, K., Jouni, H., Smith, C. Y., & Chute, C. G. (2010) · PLoS ONE · doi:10.1371/journal.pone.0013011 · Cited by 121
Discovering and visualizing indirect associations between biomedical concepts
Tsuruoka, Y., Miwa, M., Hamamoto, K., Tsujii, J., & Ananiadou, S. (2011) · Bioinformatics · doi:10.1093/bioinformatics/btr214 · Cited by 120 · cited 1×
“In text mining of the biomedical literature this approach has long been used to discover hidden associations 51,52 .”
MethodBiomedical informatics and translational medicine
Sarkar, I. N. (2010) · Journal of Translational Medicine · doi:10.1186/1479-5876-8-22 · Cited by 114
Stewart, W. F., Shah, N. R., Selna, M. J., Paulus, R. A., & Walker, J. M. (2007) · Health Affairs · doi:10.1377/hlthaff.26.2.w181 · Cited by 111
Predictive data mining in clinical medicine: a focus on selected methods and applications
Bellazzi, R., Ferrazzi, F., & Sacchi, L. (2011) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.23 · Cited by 107 · cited 1×
“Although some methodology exists 36 , temporal data mining of longitudinal health data is still in its early stages.”
MethodDetailed Clinical Models: A Review
Goossen, W. T. F., Goossen-Baremans, A. T. M., & van der Zel, M. (2010) · Healthcare Informatics Research · doi:10.4258/hir.2010.16.4.201 · Cited by 107 · cited 1×
“True data interoperability requires the development and implementation of standards and clinical-content models 101,102 for the unambiguous representation and exchange of clinical meaning 103 .”
BackgroundRealizing the full potential of electronic health records: the role of natural language processing
Lucila Ohno-machado, A. (2011) · Journal of the American Medical Informatics Association · doi:10.1136/amiajnl-2011-000501 · Cited by 94 · cited 1×
“22 and the September 2011 special issue of the Journal of the American Medical Informatics Association (JAMIA) 32 .”
BackgroundDissecting spatio‐temporal protein networks driving human heart development and related disorders
Lage, K., Møllgård, K., Greenway, S. C., Wakimoto, H., Gorham, J., Workman, C. T., Bendsen, E., Hansen, N. T., Rigina, O., Roque, F. S., et al. (2010) · Molecular Systems Biology · doi:10.1038/msb.2010.36 · Cited by 91 · cited 1×
“Taking a systems-level view of phenotypes can also shed new light on the temporal aspects of phenotypes; for example, in explaining how different mutations in the same genes can lead to disorders that are related to different stages of heart development 82 .”
BackgroundSelf-citationElectronic Health Records, Medical Research, and the Tower of Babel
Kush, R. D., Helton, E. D., Rockhold, F. W., & Hardison, C. D. (2008) · New England Journal of Medicine · doi:10.1056/nejmsb0800209 · Cited by 86
The genome-enabled electronic medical record
Hoffman, M. A. (2006) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2006.02.010 · Cited by 85
Post-Approval Drug Safety Surveillance
Gibbons, R. D., Amatya, A. K., Brown, C. H., Hur, K., Marcus, S. M., Bhaumik, D. K., & Mann, J. J. (2010) · Annual Review of Public Health · doi:10.1146/annurev.publhealth.012809.103649 · Cited by 81 · cited 1×
“In pharmacovigilance , disproportionality methods are used in post-marketing drug surveillance 43 , which is mainly based on the voluntary reporting of adverse drug event (ADE) data to spontaneous reporting databases; such events suffer from gross underreporting 44 .”
MethodMorrison, Z., Robertson, A., Cresswell, K., Crowe, S., & Sheikh, A. (2011) · Journal of Healthcare Engineering · doi:10.1260/2040-2295.2.1.25 · Cited by 81 · cited 1×
“Many national strategies also exist for the development and adoption of nationwide interoperable HIT architectures and EHRs 12,13 .”
BackgroundTaylor, P. A. (2008) · Nature · doi:10.1038/456032a · Cited by 71 · cited 1×
“…been argued that today, when database-driven research can be conducted without interfering with people’s lives, legacy-consent models that have been put in place to protect research subjects from harm are no longer relevant and should be updated or waivered in the interest of the common good 6,93 .”
BackgroundInter-patient distance metrics using SNOMED CT defining relationships
Melton, G. B., Parsons, S., Morrison, F. P., Rothschild, A. S., Markatou, M., & Hripcsak, G. M. (2006) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2006.01.004 · Cited by 71 · cited 1×
“A more direct approach to stratification is to use clustering methods and semantic similarity metrics to group patients 60,61 based on their associated clinical features and temporal patterns 40 (FIG.”
MethodGalas, D. J., & Hood, L. (2009) · Interdisciplinary Bio Central · doi:10.4051/ibc.2009.2.0006 · Cited by 68 · cited 1×
“Systems-level analyses can drastically reduce the combinatorial problem by grouping individual genetic variants that affect the same molecular machinery, thus increasing the feasibility of turning EHR data into valuable clinical markers relative to single-gene approaches 88,89 .”
BackgroundComplement Receptor 1 Gene Variants Are Associated with Erythrocyte Sedimentation Rate
Kullo, I. J., Ding, K., Shameer, K., McCarty, C. A., Jarvik, G. P., Denny, J. C., Ritchie, M. D., Ye, Z., Crosslin, D. R., Chisholm, R. L., et al. (2011) · The American Journal of Human Genetics · doi:10.1016/j.ajhg.2011.05.019 · Cited by 67
Serdén, L., Lindqvist, R., & Rosén, M. (2003) · Health Policy · doi:10.1016/s0168-8510(02)00208-7 · Cited by 64 · cited 1×
“However, because the amount of financial reimbursements depend on which codes are assigned to a given encounter there are biases in coding practice that need to be considered 15 .”
BackgroundRe-Identification of DNA through an Automated Linkage Process
Malin, B., & Sweeney, L. (2018) · Europe PMC (PubMed Central) · doi:10.1184/r1/6625553 · Cited by 58
Exploring Clinical Associations Using ‘-Omics’ Based Enrichment Analyses
Hanauer, D. A., Rhodes, D. R., & Chinnaiyan, A. M. (2009) · PLoS ONE · doi:10.1371/journal.pone.0005203 · Cited by 58 · cited 1×
“Structured and narrative EHR and registry data allow us to approach comorbidity in a data-driven statistical way by using simple contingency tables to quantify comorbidities for any pairs of diseases in terms of the disproportionality with which they co-occur in large cohorts 39–41 (FIG.”
MethodElectronic health records: Implications for drug discovery
Yao, L., Zhang, Y., Li, Y., Sanséau, P., & Agarwal, P. (2011) · Drug Discovery Today · doi:10.1016/j.drudis.2011.05.009 · Cited by 54 · cited 1×
“Similar approaches have been used to investigate off-label drug prescriptions and adverse drug interactions 47 .”
MethodAN OVERVIEW OF INTEROPERABILITY STANDARDS FOR ELECTRONIC HEALTH RECORDS
Begoyan, A. (2007) · Cited by 54
Knaup, P., Bott, O. J., Kohl, C., Lovis, C., & Garde, S. (2007) · PubMed · Cited by 50
Discovering Disease Associations by Integrating Electronic Clinical Data and Medical Literature
Holmes, A. B., Hawson, A., Liu, F., Friedman, C., Khiabanian, H., & Rabadán, R. (2011) · PLoS ONE · doi:10.1371/journal.pone.0021132 · Cited by 49 · cited 2×
“CC, coordinated conjuction; DT, determiner; NNS, plural noun. with medical knowledge extracted through literature mining, has also been attempted 41 .”
MethodHunter, A. J. (2008) · Drug Discovery Today · doi:10.1016/j.drudis.2008.02.009 · Cited by 49 · cited 2×
“EHR adoption is growing thanks to initiatives like the US$19 billion HITECH act 10 in the United States and the €2 billion public–private partnership Innovative Medicines Initiative (IMI) 11 in the European Union.”
BackgroundBiobanking and Pharmacogenomics
McCarty, C. A., & Wilke, R. A. (2010) · Pharmacogenomics · doi:10.2217/pgs.10.13 · Cited by 46 · cited 1×
“It is expected to have large translational impact through basing therapeutic choices and CDS on a patient’s genetics 78,79 .”
BackgroundOnitilo, A. A., McCarty, C. A., Wilke, R. A., Glurich, I., Engel, J. M., Flockhart, D. A., Nguyen, A., Li, L., Mi, D., Skaar, T. C., et al. (2008) · Breast Cancer Research and Treatment · doi:10.1007/s10549-008-0264-2 · Cited by 43 · cited 1×
“One study based on biobanking and EHR data identified genetic variants that are associated with an increased risk of thromboembolism in patients with breast cancer that were treated with Tamoxifen 81 .”
BackgroundIntegration of Genomic Data in Electronic Health Records: Opportunities and Dilemmas
Schmidt, S., & Sax, U. (2005) · Methods of Information in Medicine · doi:10.1055/s-0038-1634006 · Cited by 37 · cited 1×
“Representation of the actual genetic sequence information is currently not well supported in EHR systems but will probably be included as genotyping becomes more widespread in clinical practice 20,21 .”
BackgroundBalancing Privacy, Autonomy, and Scientific Needs In Electronic Health Records Research
Hoffman, S., & Podgurski, A. (2012) · SMU Law Review · doi:10.25172/smulr.65.1.4 · Cited by 37 · cited 1×
“…been argued that today, when database-driven research can be conducted without interfering with people’s lives, legacy-consent models that have been put in place to protect research subjects from harm are no longer relevant and should be updated or waivered in the interest of the common good 6,93 .”
BackgroundProperty, Privacy and the Pursuit of Integrated Electronic Medical RecordsPreprint
Hall, M. A. (2009) · SSRN Electronic Journal · doi:10.2139/ssrn.1334963 · Cited by 33
Cao, H., Melton, G. B., Markatou, M., & Hripcsak, G. M. (2008) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2008.03.006 · Cited by 31
RxTerms - a drug interface terminology derived from RxNorm.
Fung, K. W., McDonald, C. J., & Bray, B. E. (2008) · PubMed Central · Cited by 27
Schildcrout, J. S., Basford, M., Pulley, J. M., Masys, D. R., Roden, D. M., Wang, D., Chute, C. G., Kullo, I. J., Carrell, D., Peissig, P. L., et al. (2010) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2010.07.011 · Cited by 26 · cited 1×
“A high precision 65,66 of the approach has been documented and demonstrated in genome-wide association studies (GWASs) and other types of cohort research 67–74 .”
BackgroundNoble, S., Donovan, J., Turner, E. L., Metcalfe, C., Lane, J. A., Rowlands, M., Neal, D. E., Hamdy, F. C., Ben‐Shlomo, Y., & Martin, R. M. (2009) · Journal of Health Services Research & Policy · doi:10.1258/jhsrp.2008.008085 · Cited by 16 · cited 1×
“From a research point of view this amounts to increased time and cost 91 and the risk of biased data resources owing to differing inclinations to participate among demographic groups 92 .”
BackgroundIntegrating Genomic-Based Clinical Decision Support Into Electronic Health Records
Mallah, A. A., Guelpa, P., Marsh, S., & van Rooij, T. (2010) · Personalized Medicine · doi:10.2217/pme.09.73 · Cited by 14 · cited 1×
“It is expected to have large translational impact through basing therapeutic choices and CDS on a patient’s genetics 78,79 .”
BackgroundTiming of Specimen Collection for Blood Cultures from Febrile Patients with Bacteremia
Khardori, N. M. (2008) · Yearbook of Medicine · doi:10.1016/s0084-3873(08)79089-8 · Cited by 10
Transformations of Variables in Clinical-Therapeutical Research
Martin, L. (1962) · Methods of Information in Medicine · doi:10.1055/s-0038-1636196 · Cited by 9
(2001) · doi:10.1002/pds.4850 · Cited by 7
Using Hidden Markov Models to Characterize Disease Trajectories
Peterson, C., & Ohlsson, M. (2001) · Lund University Publications (Lund University) · Cited by 5
Clinical Differences Between Idiopathic and Scleroderma-Related Pulmonary Hypertension
Hayat, S. Q. (2007) · Yearbook of Medicine · doi:10.1016/s0084-3873(08)70024-5 · Cited by 4
Research works printed but not linked: 1
- Valentino-Devries, J. May the best algorithm win. The Wall Street Journal [online] , (2011).
Cited by
Drug repurposing: progress, challenges and recommendations
Pushpakom, S., Iorio, F., Eyers, P. A., Escott, K. J., Hopper, S., Wells, A., Doig, A., Guilliams, T., Latimer, J., McNamee, C., et al. (2019) · Nature Reviews Drug Discovery · doi:10.1038/nrd.2018.168 · Cited by 4,718
Deep learning for healthcare: review, opportunities and challenges
Miotto, R., Wang, F., Wang, S., Jiang, X., & Dudley, J. T. (2018) · Briefings in Bioinformatics · doi:10.1093/bib/bbx044 · Cited by 3,076
Opportunities and obstacles for deep learning in biology and medicine
Ching, T., Himmelstein, D. S., Beaulieu-Jones, B. K., Kalinin, A. A., Do, B. T., Way, G. P., Ferrero, E., Agapow, P.-M., Zietz, M., Hoffman, M. M., et al. (2018) · Journal of The Royal Society Interface · doi:10.1098/rsif.2017.0387 · Cited by 2,310
“EHRs are designed chiefly for clinical, administrative and financial purposes, such as patient care, insurance and billing [97].”
BackgroundBenefits and limitations of genome-wide association studies
Tam, V., Patel, N., Turcotte, M., Bossé, Y., Paré, G., & Meyre, D. (2019) · Nature Reviews Genetics · doi:10.1038/s41576-019-0127-1 · Cited by 2,092
Miotto, R., Li, L., Kidd, B. A., & Dudley, J. T. (2016) · Scientific Reports · doi:10.1038/srep26094 · Cited by 1,710
“EHR data is challenging to represent and model due to its high dimensionality, noise, heterogeneity, sparseness, incompleteness, random errors, and systematic biases 7,10,11 .”
Background
Metadata
- Authors
- Jensen, P. B., Jensen, L. J., & Brunak, S.
- Affiliations
- University of Copenhagen (DK)
- Corresponding author
- Brunak, Søren
- Venue
- Nature Reviews Genetics
- Published
- 2012-05-02
- Volume
- 13
- Issue
- 6
- Pages
- 395-405
- ISSN
- 1471-0056 (ISSN-L)
- 1471-0064
- OpenAlex
- W2004910511
- Cited by
- 1,680
- References
- 117
- Citations by year
- 2026: 122 · 2025: 98 · 2024: 94 · 2023: 111 · 2022: 128 · 2021: 142 · 2020: 151 · 2019: 181 · 2018: 149 · 2017: 125 · 2016: 128 · 2015: 113 · 2014: 86 · 2013: 40 · 2012: 11
- FWCI
- 13.26
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- www.springer.com/tdm (tdm)
- Locations
- Nature Reviews Genetics (publishedVersion)
- PubMed (publishedVersion)
- Research at the University of Copenhagen (University of Copenhagen) (submittedVersion)
- Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU) (submittedVersion)
- Funders
- Strategiske Forskningsråd
- Novo Nordisk Fonden (NNF10CC1016517)
- Topics
- Health Sciences › Health Professions › Health Information Management › Electronic Health Records Systems
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Health Professions › Health Information Management › Medical Coding and Health Information
- Keywords
- electronic health records, genotype-phenotype correlation, patient stratification, clinical decision-making, genetic data integration
- MeSH terms
- Patient Care, Humans, Primary Health Care, Public Health, Medical Records Systems, Computerized, Information Dissemination, Biomedical Research, Genetic Association Studies, Electronic Health Records
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.