Learning statistical models of phenotypes using noisy labeled training data

Journal of the American Medical Informatics Association

Volumn 23, Issue 6, 2016, Pages 1166-1173

  Agarwal, Vibhu ^a   Podchiyska, Tanya ^a   Banda, Juan M ^a   Goel, Veena ^a,b   Leung, Tiffany I ^b   Minty, Evan P ^a,c   Sweeney, Timothy E ^a,d   Gyang, Elsie ^a   Shah, Nigam H ^a  

^a STANFORD UNIVERSITY SCHOOL OF MEDICINE   (United States)

^b STANFORD UNIVERSITY   (United States)

^c UNIVERSITY OF CALGARY   (Canada)

^d STANFORD UNIVERSITY MEDICAL CENTER   (United States)

Author keywords

Electronic health record; High throughput; Machine learning; Noisy labels; Phenotyping

Indexed keywords

ACCURACY; ARTICLE; CHRONIC DISEASE; DATA ANALYSIS; ELECTRONIC HEALTH RECORD; FEASIBILITY STUDY; GOLD STANDARD; HEART INFARCTION; HUMAN; LOGISTIC REGRESSION ANALYSIS; MACHINE LEARNING; NON INSULIN DEPENDENT DIABETES MELLITUS; PHENOTYPE; STATISTICAL MODEL; ALGORITHM; CONTROLLED VOCABULARY; MEDICAL INFORMATICS;

ALGORITHMS; DIABETES MELLITUS, TYPE 2; ELECTRONIC HEALTH RECORDS; HUMANS; LOGISTIC MODELS; MACHINE LEARNING; MEDICAL INFORMATICS COMPUTING; MODELS, STATISTICAL; MYOCARDIAL INFARCTION; PHENOTYPE; VOCABULARY, CONTROLLED;

EID: 84994689614     PISSN: 10675027     EISSN: 1527974X     Source Type: Journal    
DOI: 10.1093/jamia/ocw028     Document Type: Article

References (48)

1. Longhurst CA, Harrington RA, and Shah NH. A 'green button' for using aggregate patient data at the point of care. Health Aff (Millwood). 2014;33(7):1229-1235.
2. Pathak J, Kho AN, and Denny JC. Electronic health records-driven phenotyping: challenges, recent advances, and perspectives. J Am Med Inform Assoc. 2013;20(e2):e206-e211.
3. Shah NH. Mining the ultimate phenome repository. Nat Biotechnol. 2013;31(12):1095-1097.
4. Shivade C, Raghavan P, Fosler-Lussier E, Embi PJ, Elhadad N, Johnson SB, et al. A review of approaches to identifying patient phenotype cohorts using electronic health records. J Am Med Inform Assoc. 2014;21(2):221-230.
5. Gottesman O, Kuivaniemi H, Tromp G, Faucett WA, Li R, Manolio TA, et al. The Electronic Medical Records and Genomics (eMERGE) Network: past, present, and future. GenetMed. 2013;15(10):761-771.
6. McCarty CA, Chisholm RL, Chute CG, Kullo IJ, Jarvik GP, Larson EB, 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.
7. Wei WQ and Denny JC. Extracting research-quality phenotypes from electronic health records to support precision medicine. Genome Med. 2015;7(1):41.
8. Denny JC, Bastarache L, Ritchie MD, Carroll RJ, Zink R, Mosley JD, et al. Systematic comparison of phenome-wide association study of electronic medical record data and genome-wide association study data. Nat Biotechnol. 2013;31(12):1102-1110.
9. Carroll RJ, Eyler AE, and Denny JC. Intelligent use and clinical benefits of electronic health records in rheumatoid arthritis. Expert Rev Clin Immunol. 2015;11(3):329-337.
10. Ritchie MD, Verma SS, Hall MA, Goodloe RJ, Berg RL, Carrell DS, et al. Electronicmedical records and genomics (eMERGE) network exploration in cataract: several new potential susceptibility loci. Mol Vis. 2014;20:1281-1295.
11. Lin C, Karlson EW, Dligach D, Ramirez MP, Miller TA, Mo H, et al. Automatic identification of methotrexate-induced liver toxicity in patients with rheumatoid arthritis from the electronic medical record. J Am Med Inform Assoc. 2014.
12. Jiang M, Chen Y, Liu M, Rosenbloom ST, Mani S, Denny JC, et al. A study of machine-learning-based approaches to extract clinical entities and their assertions from discharge summaries. J Am Med Inform Assoc. 2011; 18(5):601-606.
13. Wright A, Pang J, Feblowitz JC, Maloney FL, Wilcox AR, Ramelson HZ, et al. A method and knowledge base for automated inference of patient problems from structured data in an electronic medical record. J Am Med Inform Assoc. 2011;18(6):859-867.
14. Newton KM, Peissig PL, Kho AN, Bielinski SJ, Berg RL, Choudhary V, 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(e1):e147-e154.
15. Overby CL, Pathak J, Gottesman O, Haerian K, Perotte A, Murphy S, et al. A collaborative approach to developing an electronic health record phenotyping algorithm for drug-induced liver injury. J Am Med Inform Assoc. 2013;20(e2):e243-e252.
16. Bayley KB, Belnap T, Savitz L, Masica AL, Shah N, and Fleming NS. Challenges in using electronic health record data for CER: experience of 4 learning organizations and solutions applied. Med Care. 2013;51(8 Suppl 3):S80-S86.
17. Barlas S. Hospitals scramble to meet deadlines for adopting electronic health records: pharmacy systems will be updated slowly but surely. P T. 2011;36(1):37-40.
18. PheKB. Phenotype KnowledgeBase. Available from: http://www.phekb.org. Accessed 12 February 2015.
19. Liao KP, Cai T, Gainer V, Goryachev S, Zeng-treitler Q, Raychaudhuri S, et al. Electronic medical records for discovery research in rheumatoid arthritis. Arthritis Care Res (Hoboken). 2010;62(8):1120-1127.
20. Carrell DS, Halgrim S, Tran DT, Buist DS, Chubak J, Chapman WWet al. Using natural language processing to improve efficiency of manual chart abstraction in research: the case of breast cancer recurrence. Am J Epidemiol. 2014;179(6):749-758.
21. Carroll RJ, Thompson WK, Eyler AE, Mandelin AM, Cai T, Zink RM, et al. Portability of an algorithm to identify rheumatoid arthritis in electronic health records. J Am Med Inform Assoc. 2012;19(e1):e162-e169.
22. Boland MR, Hripcsak G, Shen Y, Chung WK, and Weng C. Defining a comprehensive verotype using electronic health records for personalized medicine. J Am Med Inform Assoc. 2013;20(e2):e232-e238.
23. Tian TY, Zlateva I, and Anderson DR. Using electronic health records data to identify patients with chronic pain in a primary care setting. J Am Med Inform Assoc. 2013;20(e2):e275-e280.
24. Chute CG. Invited commentary: Observational research in the age of the electronic health record. Am J Epidemiol. 2014;179(6):759-761.
25. Castro VM, Apperson WK, Gainer VS, Ananthakrishnan AN, Goodson AP, Wang TD, et al. Evaluation of matched control algorithms in EHR-based phenotyping studies: a case study of inflammatory bowel disease comorbidities. J Biomed Inform. 2014;52:105-111.
26. Chen Y, Carroll RJ, Hinz ER, Shah A, Eyler AE, Denny JC, et al. Applying active learning to high-throughput phenotyping algorithms for electronic health records data. J Am Med Inform Assoc. 2013;20(e2):e253-e259.
27. Sinnott JA, Dai W, Liao KP, Shaw SY, Ananthakrishnan AN, Gainer VS, et al. Improving the power of genetic association tests with imperfect phenotype derived from electronic medical records. Hum Genet. 2014;133(11): 1369-1382.
28. Peissig PL, Santos Costa V, Caldwell MD, Rottscheit C, Berg RL, Mendonca EA, et al. Relational machine learning for electronic health record-driven phenotyping. J Biomed Inform. 2014;52:260-270.
29. Simon HU. General bounds on the number of examples needed for learning probabilistic concepts. J Comput Syst Sci. 1996;52(2):239-254.
30. Aslam JA and Decatur SE. On the sample complexity of noise-tolerant learning. Inform Process Lett. 1996;57(4):189-195.
31. Observational Medical Outcomes Partnership. Health Outcomes of Interest. Available from: http://omop.org/HOI Accessed 13 December 2014.
32. Halpern Y, Choi Y, Horng S, and Sontag D. ElectronicMedical Record Phenotyping using the Anchor & Learn Framework. J Am Med Inform Assoc. 2016.
33. Jung K, LePendu P, Iyer S, Bauer-Mehren A, Percha B, and Shah NH. Functional evaluation of out-of-the-box text-mining tools for data-mining tasks. J Am Med Inform Assoc. 2015;22(1):121-131.
34. Agarwal V, Lependu P, Podchiyska T, Barber R, Boland M, Hripcsak G, et al. Using narratives as a source to automatically learn phenotype models, in 1st Workshop on Data Mining for Medical Informatics. 2014, AMIA 2014 Annual Symposium: Washington DC.
35. Hastie T, Tibshirani R, and Friedman J. The Elements of Statistical Learning. Vol. 2. New York: Springer; 2009.
36. Friedman J, Hastie T, and Tibshirani R. Regularization Paths for Generalized Linear Models via Coordinate Descent. J Stat Softw. 2010;33(1):1-22.
37. Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et al. Scikit-learn: Machine learning in Python. J Machine Learning Res. 2011;12:2825-2830.
38. Yu S, Liao KP, Shaw SY, Gainer VS, Churchill SE, Szolovits P, et al. Toward high-throughput phenotyping: unbiased automated feature extraction and 90 selection from knowledge sources. J Am Med Inform Assoc. 2015.
39. Wei WQ, Leibson CL, Ransom JE, Kho AN, Caraballo PJ, Chai HS, et al. Impact of data fragmentation across healthcare centers on the accuracy of a high-throughput clinical phenotyping algorithm for specifying subjects with type 2 diabetes mellitus. J Am Med Inform Assoc. 2012;19(2):219-224.
40. Platt R, Carnahan RM, Brown JS, Chrischilles E, Curtis LH, Hennessy S, et al. The U.S. Food and Drug Administration's Mini-Sentinel program: status and direction. Pharmacoepidemiol Drug Saf. 2012;21 Suppl 1:1-8.
41. Pathak J, Bailey KR, Beebe CE, Bethard S, Carrell DC, Chen PJ, et al. Normalization and standardization of electronic health records for highthroughput phenotyping: the SHARPn consortium. J Am Med Inform Assoc. 2013;20(e2):e341-e348.
42. OHDSI. Aphrodite. 2015; Available from: https://github.com/OHDSI/Aphrodite. Accessed 7 November 2015.
43. OHDSI. Observational Health Data Sciences and Informatics. Available from: http://www.ohdsi.org. Accessed 7 November 2015.
44. Denny JC. Chapter 13: Mining electronic health records in the genomics era. PLoS Comput Biol. 2012;8(12):e1002823.
45. Ng K, Sun J, Hu J, and Wang F. Personalized Predictive Modeling and Risk Factor Identification using Patient Similarity. AMIA Jt Summits Transl Sci Proc. 2015;2015:132-136.
46. Celi LAG, Tang RJ, Villarroel MC, Davidzon GA, Lester WT, and Chueh HC. A clinical database-driven approach to decision support: Predicting mortality among patients with acute kidney injury. J Healthcare Engineering. 2011;2(1):97-110.
47. Hripcsak G and Albers DJ. Next-generation phenotyping of electronic health records. J Am Med Inform Assoc. 2013;20(1):117-121.
48. Agarwal S and Yu H. Biomedical negation scope detection with conditional random fields. J Am Med Inform Assoc. 2010;17(6):696-701.