Relational machine learning for electronic health record-driven phenotyping

Journal of Biomedical Informatics

Volumn 52, Issue , 2014, Pages 260-270

  Peissig, Peggy L ^a   Santos Costa, Vitor ^b   Caldwell, Michael D ^a   Rottscheit, Carla ^a   Berg, Richard L ^a   Mendonca, Eneida A ^c   Page, David ^c,d  

^a MARSHFIELD CLINIC   (United States)

^b UNIVERSITY OF PORTO   (Portugal)

^c UNIVERSITY OF WISCONSIN SCHOOL OF MEDICINE AND PUBLIC HEALTH   (United States)

^d University of Wisconsin   (United States)

Author keywords

Electronic health record; Inductive logic programming; Machine learning; Phenotyping; Relational machine learning

Indexed keywords

COMPUTER CIRCUITS; DIAGNOSIS; E-LEARNING; EHEALTH; HEALTH RISKS; LEARNING SYSTEMS; MACHINE LEARNING; MEDICAL COMPUTING; RECORDS MANAGEMENT;

BEHAVIORAL OBSERVATION; BINOMIAL DISTRIBUTION; ELECTRONIC HEALTH RECORD; INTERNATIONAL CLASSIFICATION OF DISEASE; INTERPRETABLE RULES; PHENOTYPING; RECEIVER OPERATING CHARACTERISTICS; STATISTICAL SIGNIFICANCE;

INDUCTIVE LOGIC PROGRAMMING (ILP);

ACUTE HEART INFARCTION; ALGORITHM; ARTICLE; BINOMIAL DISTRIBUTION; CATARACT; COMPUTER AIDED DESIGN; CONGESTIVE HEART FAILURE; CONTROLLED STUDY; DEEP VEIN THROMBOSIS; DEMENTIA; DIABETIC RETINOPATHY; ELECTRONIC MEDICAL RECORD; HEART ATRIUM FIBRILLATION; ICD-9; LIVER INJURY; MACHINE LEARNING; MEASUREMENT ACCURACY; NON INSULIN DEPENDENT DIABETES MELLITUS; PHENOTYPE; RECEIVER OPERATING CHARACTERISTIC; ARTIFICIAL INTELLIGENCE; CLASSIFICATION; DATA MINING; FACTUAL DATABASE; HUMAN; PROCEDURES;

ALGORITHMS; ARTIFICIAL INTELLIGENCE; DATA MINING; DATABASES, FACTUAL; ELECTRONIC HEALTH RECORDS; HUMANS;

EID: 84919848159     PISSN: 15320464     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.jbi.2014.07.007     Document Type: Article

References (45)

1. Wojczynski M.K., Tiwari H.K. Definition of phenotype. Adv Genet 2008, 60:75-105.
2. Rice J.P., Saccone N.L., Rasmussen E. Definition of the phenotype. Adv Genet 2001, 42:69-76.
3. Gurwitz D., Pirmohamed M. Pharmacogenomics: the importance of accurate phenotypes. Pharmacogenomics 2010, 11:469-470.
4. Samuels D.C., Burn D.J., Chinnery P.F. Detecting new neurodegenerative disease genes: does phenotype accuracy limit the horizon?. Trends Genet 2009, 25:486-488.
5. Kho A.N., Pacheco J.A., Peissig P.L., et al. Electronic medical records for genetic research: results of the eMERGE Consortium. Sci Transl Med 2011, 3:3-79.
6. Newton K.M., Peissig P.L., Kho A.N., et al. Validation of electronic medical record-based phenotyping algorithms: results and lessons learned from the eMERGE network. J Am Med Inform Assoc 2013, 20:e147-e154.
7. Carroll R.J., Eyler A.E., Denny J.C. Naïve electronic health record phenotype identification for rheumatoid arthritis. AMIA Annu Symp Proc 2011, 2011:189-196.
8. Anand V., Downs S.M. An empirical validation of Recursive Noisy OR (RNOR) rule for asthma prediction. AMIA Annu Symp Proc 2010, 2010:16-20.
9. Xu H., Fu Z., Shah A., et al. Extracting and integrating data from entire electronic health records for detecting colorectal cancer cases. AMIA Annu Symp Proc 2011, 2011:1564-1572.
10. Huang Y., McCullagh P., Black N., et al. Feature selection and classification model construction on type 2 diabetic patients' data. Artif Intell Med 2007, 41:251-262.
11. Dingcheng L, Simon G, Pathak J, et al. Using association rule mining for phenotype extraction from electronic health records. In: Proceeding of the American Medical Informatics Association Annual Symposium; 2013. CR1: 142-6.
12. Pakhomov S., Weston S.A. Electronic medical records for clinical research: application to the identification of heart failure. Am J Manag Care 2007, 13:281-288.
13. Wu J., Roy J., Stewart W.F. Prediction modeling using EHR data: challenges, strategies, and a comparison of machine learning approaches. Med Care 2010, 48:S106-S113.
14. Page D, Santos Costa V, Natarajan S, et al. Identifying adverse drug events by relational learning. In: Hoffman J, Selman B, editors. In: Proceedings of the 26th Annual AAAI Conference on Artificial Intelligence. AAAI Publications; 2012. http://www.aaai.org/ocs/index.php/AAAI/AAAI12/paper/view/4941.
15. Introduction to statistical relational learning. In: Statistical relational learning 2007, MIT Press, Cambridge, MA. L. Getoor, B. Taskar (Eds.).
16. Fox B.I., Hollingsworth J.C., Gray M.D., et al. Developing an expert panel process to refine health outcome definitions in observational data. J Biomed Inform 2013, 46:795-804.
17. De Raedt L. Logical and relational learning: from ILP to MRDM (cognitive technologies) 2008, Springer-Verlag, New York.
18. Lavrac N., Dzeroski S. Inductive logic programming - techniques and applications, Ellis Horwood series in artificial intelligence 1994, Prentice Hall, Upper Saddle River, NJ.
19. Burnside E.S., Davis J., Chatwal J., et al. Probabilistic computer model developed from clinical data in national mammography database format to classify mammographic findings. Radiology 2009, 251:663-672.
20. Liu J, Zhang C, McCarty C, et al. Graphical-model based multiple testing under dependence, with applications to genome-wide association studies. In: Proceedings of the 28th conference on uncertainty in artificial intelligence (UAI); 2012.
21. Davis J, Lantz E, Page D, et al. Machine learning for personalized medicine: will this drug give me a heart attack? International Conference of Machine Learning (ICML); workshop on machine learning in health care applications. Helsinki, Finland, July, 2008.
22. Weiss J, Natarajan S, Peissig P, et al. Statistical relational learning to predict primary myocardial infarction from electronic health records. AAAI conference on Innovative Applications in AI (IAAI.); 2012.
23. Davis J, Santos Costa V, Berg E, et al. Demand-driven clustering in relational domains for predicting adverse drug events. In: Proceedings of the International Conference on Machine Leaning (ICML); 2012. http://icml.cc/discuss/2012/644.html.
24. Berg B, Peissig P, Page D. Relational rule-learning on high-dimensional medical data, neural and information processing systems (NIPS) workshop on predictive models for personalized medicine, Whistler, BC; 2010.
25. Kawaler E., Cobian A., Peissig P., et al. Learning to predict post-hospitalization VTE risk from EHR data. AMIA Annu Symp Proc 2012, 2012:436-445.
26. Relational data mining 2001, Springer-Verlag, Berlin Heidelberg. S. Dzeroski, N. Lavrac (Eds.).
27. Muggleton S. Inductive logic programming: 6th international workshop, ILP-96, Stockholm, Sweden, August 26-28, 1996, selected papers (Lecture notes in computer science/Lecture notes in artificial intelligence) 1997, Springer-Verlag, Berlin Heidelberg.
28. Peissig P.L., Rasmussen L.V., Berg R.L., et al. Importance of multi-modal approaches to effectively identify cataract cases from electronic health records. J Am Med Inform Assoc 2012, 19:225-234.
29. Ramakrishnan R. Database management systems 2003, McGraw-Hill, New York. 3rd ed.
30. Linder J.A., Ma J., Bates D.W., et al. Electronic health record use and the quality of ambulatory care in the United States. Arch Intern Med 2007, 167:1400-1405.
31. Srinivasan A. The Aleph user manual. Oxford; 2001. http://www.di.ubi.pt/~jpaulo/competence/tutorials/aleph.pdf.
32. Maclure M. The case-crossover design: a method for studying transient effects on the risk of acute events. Am J Epidemiol 1991, 133(2):144-153.
33. WEKA. http://weka.sourceforge.net/doc.dev/weka/classifiers/rules/PART.html.
34. Quinlan J.R. C4.5: Programs for machine learning 1993, Morgan Kaufman, San Francisco.
35. Breiman L., Friedman J., Stone C.J. Classification and regression trees 1984, Chapman Hall, CRC, New York.
36. Cohen WW. Fast effective rule induction. In: Twelfth international conference on machine learning (ML95); 1995. p. 115-23.
37. Sing T., Sander O., Beerenwinkel N., et al. ROCR: visualizing classifier performance in R. Bioinformatics 2005, 21:3940-3941.
38. Kho A.N., Hayes M.G., Rasmussen-Torvik L., et al. Use of diverse electronic medical record systems to identify genetic risk for type 2 diabetes within a genome-wide association study. J Am Med Inform Assoc 2012, 19:212-218.
39. Denny J.C., Crawford D.C., Ritchie M.D., et al. Variants near FOXE1 are associated with hypothyroidism and other thyroid conditions: using electronic medical records for genome-and phenome-wide studies. Am J Hum Genet 2011, 89:529-542.
40. Ho M.L., Lawrence N., van Walraven C., et al. The accuracy of using integrated electronic health care data to identify patients with undiagnosed diabetes mellitus. J Eval Clin Pract 2012, 18:606-611.
41. Kudyakov R., Bowen J., Ewen E., et al. Electronic health record use to classify patients with newly diagnosed versus preexisting type 2 diabetes: infrastructure for comparative effectiveness research and population health management. Popul Health Manag 2012, 15:3-11.
42. McCarty C.A., Chisholm R.L., Chute C.G., et al. The eMERGE network: a consortium of biorepositories linked to electronic medical records data for conducting genomic studies. BMC Med Genomics 2011, 4:13.
43. Thilaganathan B., Athanasiou S., Ozmen S., et al. Umbilical cord blood erythroblast count as an index of intrauterine hypoxia. Arch Dis Child Fetal Neonatal Ed 1994, 70:F192-F194.
44. Penz J.F., Wilcox A.B., Hurdle J.F. Automated identification of adverse events related to central venous catheters. J Biomed Inform 2007, 40:174-182.
45. Saria S., McElvain G., Rajani A.K., et al. Combining structured and free-text data for automatic coding of patient outcomes. AMIA Annu Symp Proc 2010, 2010:712-716.