Improving sensitivity of machine learning methods for automated case identification from free-text electronic medical records

BMC Medical Informatics and Decision Making

Volumn 13, Issue 1, 2013, Pages

  Afzal, Zubair ^a   Schuemie, Martijn J ^a   Van Blijderveen, Jan C ^a   Sen, Elif F ^a   Sturkenboom, Miriam Cjm ^a   Kors, Jan A ^a  

^a ERASMUS MEDICAL CENTER   (Netherlands)

Author keywords

Class imbalance; Cost sensitive learning; Electronic health records; Improving sensitivity; Random sampling

Indexed keywords

ACUTE KIDNEY FAILURE; ALGORITHM; ARTICLE; ARTIFICIAL INTELLIGENCE; BILIARY TRACT DISEASE; COMPARATIVE STUDY; ELECTRONIC MEDICAL RECORD; HUMAN; INFORMATION PROCESSING; LIVER DISEASE; METHODOLOGY;

ACUTE KIDNEY INJURY; ALGORITHMS; ARTIFICIAL INTELLIGENCE; BILIARY TRACT DISEASES; DATA COLLECTION; ELECTRONIC HEALTH RECORDS; HUMANS; LIVER DISEASES;

EID: 84874398938     PISSN: None     EISSN: 14726947     Source Type: Journal    
DOI: 10.1186/1472-6947-13-30     Document Type: Article

References (59)

1. Secondary use of electronic health record data: spontaneous triggered adverse drug event reporting. Linder JA, Haas JS, Iyer A, Labuzetta MA, Ibara M, Celeste M, Getty G, Bates DW, Pharmacoepidemiol Drug Saf 2010 19 1211 1215 10.1002/pds.2027 21155192
2. Temporal pattern discovery in longitudinal electronic patient records. Norén GN, Hopstadius J, Bate A, Star K, Edwards IR, Data Min Knowl Discov 2009 20 361 387
3. Electronic health records and adverse drug events after patient transfer. Boockvar KS, Livote EE, Goldstein N, Nebeker JR, Siu A, Fried T, Qual Saf Health Care 2010 19 16 21127100
4. Identifying clinical/translational research cohorts: ascertainment via querying an integrated multi-source database. Hurdle JF, Haroldsen SC, Hammer A, Spigle C, Fraser AM, Mineau GP, Courdy SJ, J Am Med Inform Assoc 2013 20 164 171 10.1136/amiajnl-2012-001050 23059733
5. Postmarketing surveillance based on electronic patient records: the IPCI project. Vlug A, Van der Lei J, Mosseveld B, Van Wijk M, Van der Linden P, MC S, Van Bemmel J, Methods Inf Med 1999 38 339 344 10805025 (Pubitemid 30030067)
6. Electronic medical records for discovery research in rheumatoid arthritis. Liao KP, Cai T, Gainer V, Goryachev S, Zeng-treitler Q, Raychaudhuri S, Szolovits P, Churchill S, Murphy S, Kohane I, Karlson EW, Plenge RM, Arthritis Care Res (Hoboken) 2010 62 1120 1127 10.1002/acr.20184
7. A systematic literature review of automated clinical coding and classification systems. Stanfill MH, Williams M, Fenton SH, Jenders RA, Hersh WR, J Am Med Inform Assoc 2010 17 646 651 10.1136/jamia.2009.001024 20962126
8. A computer case definition for sudden cardiac death. Chung CP, Murray KT, Stein CM, Hall K, Ray WA, Pharmacoepidemiol Drug Saf 2010 19 563 572 20029823
9. An automated database case definition for serious bleeding related to oral anticoagulant use. Cunningham A, Stein CM, Chung CP, Daugherty JR, Smalley WE, Ray WA, Pharmacoepidemiol Drug Saf 2011 20 560 566 10.1002/pds.2109 21387461
10. Accuracy of Veterans Administration databases for a diagnosis of rheumatoid arthritis. Singh JA, Holmgren AR, Noorbaloochi S, Arthritis Rheum 2004 51 952 957 10.1002/art.20827 15593102 (Pubitemid 39648188)
11. What does validation of cases in electronic record databases mean? The potential contribution of free text. Nicholson A, Tate AR, Koeling R, Cassell JA, Pharmacoepidemiol Drug Saf 2011 20 321 324 10.1002/pds.2086 21351316
12. Extracting information from textual documents in the electronic health record: a review of recent research. Meystre SM, Savova GK, Kipper-Schuler KC, Hurdle JF, Yearb Med Inform 2008 47 128 144
13. Using electronic medical records to enable large-scale studies in psychiatry: treatment resistant depression as a model. Perlis RH, Iosifescu DV, Castro VM, Murphy SN, Gainer VS, Minnier J, Cai T, Goryachev S, Zeng Q, Gallagher PJ, Fava M, Weilburg JB, Churchill SE, Kohane IS, Smoller JW, Psychol Med 2012 42 41 50 10.1017/S0033291711000997 21682950
14. Elkin PL, Froehling D, Wahner-Roedler D, Trusko B, Welsh G, Ma H, Asatryan AX, Tokars JI, Rosenbloom ST, Brown SH, NLP-based identification of pneumonia cases from free-text radiological reports AMIA Annu Symp Proc. 2008 172 176
15. Discovering peripheral arterial disease cases from radiology notes using natural language processing division of biomedical statistics and informatics, 2 division of cardiovascular diseases. Savova GK, Fan J, Ye Z, Murphy SP, Zheng J, Chute CG, Kullo IJ, AMIA Annu Symp Proc 2010 2010 722 726 21347073
16. Electronic medical records for clinical research: application to the identification of heart failure. Pakhomov S, Weston SA, Jacobsen SJ, Chute CG, Meverden R, Roger VL, Am J Manag Care 2007 13 281 288 17567225 (Pubitemid 46983137)
17. Comparing methods for identifying pancreatic cancer patients using electronic data sources. Friedlin J, Overhage M, Al-Haddad Ma, Waters Ja, Aguilar-Saavedra JJR, Kesterson J, Schmidt M, AMIA Annu Symp Proc 2010 2010 237 241 http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3041435/ 21346976
18. Using electronic patient records to discover disease correlations and stratify patient cohorts. Roque FS, Jensen PB, Schmock H, Dalgaard M, Andreatta M, Hansen T, Søeby K, Bredkjær S, Juul A, Werge T, Jensen LJ, Brunak S, PLoS Comput Biol 2011 7 1002141 10.1371/journal.pcbi.1002141 21901084
19. Automatic construction of rule-based ICD-9-CM coding systems. Farkas R, Szarvas G, BMC Bioinforma 2008 9 3 10 10.1186/1471-2105-9-S3-S10 (Pubitemid 351959570)
20. Electronic health record-based cardiac risk assessment and identification of unmet preventive needs. Persell SD, Dunne AP, Lloyd-Jones DM, Baker DW, Med Care 2009 47 418 424 10.1097/MLR.0b013e31818dce21 19238100
21. Extracting diagnoses and investigation results from unstructured text in electronic health records by semi-supervised machine learning. Wang Z, Shah AD, Tate AR, Denaxas S, Shawe-Taylor J, Hemingway H, PLoS One 2012 7 30412 10.1371/journal.pone.0030412 22276193
22. Mayo clinic NLP system for patient smoking status identification. Savova GK, Ogren PV, Duffy PH, Buntrock JD, Chute CG, J Am Med Inform Assoc 2008 15 25 28 17947622 (Pubitemid 350216491)
23. Identifying smokers with a medical extraction system. Clark C, Good K, Jezierny L, Macpherson M, Wilson B, Chajewska U, J Am Med Inform Assoc 2007 15 36 39 10.1197/jamia.M2442 17947619
24. Automating classification of free-text electronic health records for epidemiological studies. Schuemie MJ, Sen E, 't Jong GW, van Soest EM, Sturkenboom MC, Kors JA, Pharmacoepidemiol Drug Saf 2012 21 651 658 10.1002/pds.3205 22271492
25. Learning from imbalanced data. Garcia EA, IEEE Trans Knowl Data Eng 2009 21 1263 1284
26. Boosted classification trees and class probability / quantile estimation. Mease D, Wyner AJ, J Mach Learn Res 2007 8 409 439 (Pubitemid 46434120)
27. Countering imbalanced datasets to improve adverse drug event predictive models in labor and delivery. Taft LM, Evans RS, Shyu CR, Egger MJ, Chawla N, Mitchell JA, Thornton SN, Bray B, Varner M, J Biomed Inform 2009 42 356 364 10.1016/j.jbi.2008.09.001 18824133
28. An empirical comparison of repetitive undersampling techniques. Van Hulse J, Khoshgoftaar TM, Napolitano A, 2009 IEEE International Conference on Information Reuse & Integration 2009 29 34
29. Data Mining for Imbalanced Datasets: An Overview. Chawla NV, Data Mining and Knowledge Discovery Handbook Boston, MA: Springer US, Maimon O, Rokach L, 2010 875 886
30. Experimental perspectives on learning from imbalanced data. Van Hulse J, Khoshgoftaar TM, Napolitano A, Proceedings of the 24th international conference on Machine learning-ICML '07 New York, New York, USA: ACM Press 2007 935 942
31. SMOTE: synthetic minority over-sampling technique. Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP, Artif Intell 2002 16 321 357 (Pubitemid 43057176)
32. C4.5, Class Imbalance, and Cost Sensitivity: Why Under-Sampling beats Over-Sampling. Drummond C, Holte RC, Workshop on Learning from Imbalanced Data Sets II (ICML 2003) 2003 1 8
33. The Class Imbalance Problem: Significance and Strategies. Japkowicz N, Proceedings of the 2000 International Conference on Artificial Intelligence (ICAI) 2000 111 117
34. Ling CX, Sheng VS, Cost-Sensitive Learning and the Class Imbalance Problem In Encyclopedia of Machine Learning: Springer 2011
35. Cost-sensitive classification with inadequate labeled data. Wang T, Qin Z, Zhang S, Zhang C, Inf Syst 2012 37 508 516 10.1016/j.is.2011.10.009
36. The class imbalance problem: a systematic study. Japkowicz N, Stephen S, Intell Data Anal 2002 6 429 449
37. Cost-sensitive boosting for classification of imbalanced data. Sun Y, Kamel M, Wong A, Wang Y, Pattern Recognit 2007 40 3358 3378 10.1016/j.patcog. 2007.04.009 (Pubitemid 47223287)
38. Training cost-sensitive neural networks with methods addressing the class imbalance problem. Zhou Z, Member S, Liu X, IEEE Trans Knowl Data Eng 2006 18 63 77 (Pubitemid 43145089)
39. Does cost-sensitive learning beat sampling for classifying rare classes? McCarthy K, Zabar B, Weiss G, Proceedings of the 1st international workshop on Utility-based data mining-UBDM '05 New York, New York, USA: ACM Press 2005 69 77
40. The Influence of Class Imbalance on Cost-Sensitive Learning: An Empirical Study. Liu X, Zhou Z, Sixth International Conference on Data Mining (ICDM'06) 2006 970 974
41. A coefficient of agreement for nominal scales. Cohen J, Educ Psychol Meas 1960 20 37 46 10.1177/001316446002000104
42. A simple algorithm for identifying negated findings and diseases in discharge summaries. Chapman WW, Bridewell W, Hanbury P, Cooper GF, Buchanan BG, J Biomed Inform 2001 34 301 310 10.1006/jbin.2001.1029 12123149 (Pubitemid 34694864)
43. Chi2: feature selection and discretization of numeric attributes. Setiono R, Liu H, Proceedings of 7th IEEE International Conference on Tools with Artificial Intelligence IEEE Comput. Soc. Press 1995 388 391 10.1109/TAI.1995.479783
44. Ensemble classification of paired data. Adler W, Brenning A, Potapov S, Schmid M, Lausen B, Comput Stat Data Anal 2011 55 1933 1941 10.1016/j.csda.2010. 11.017
45. Boosting for Learning Multiple Classes with Imbalanced Class Distribution. Sun Y, Kamel M, Wang Y, Sixth International Conference on Data Mining (ICDM'06) Washington, DC, USA: IEEE Computer Society 2006 592 602 10.1109/ICDM.2006.29
46. Applying Support Vector Machines to Imbalanced Datasets. Akbani R, Kwek S, Japkowicz N, In Proceedings of the 15th European Conference on Machine Learning (ECML} 2004 39 50 (Pubitemid 41050079)
47. Chen C, Liaw A, Breiman L, Using Random Forest to Learn Imbalanced Data Discovery. 2004 1 12
48. Domingos P, MetaCost: A General Method for Making Classifiers Cost-Sensitive New York, New York, USA: ACM Press Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining-KDD '99. 1999 155 164
49. The WEKA data mining software. Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH, ACM SIGKDD Explorations Newsletter, Volume 11 2009 10
50. C4.5: Programs for Machine Learning by J. Ross Quinlan. Morgan Kaufmann Publishers, Inc., 1993. Salzberg SL, Mach Learn 1994 16 235 240
51. LIBSVM: a library for support vector machines. Chang C-C, Lin C-J, ACM Transactions on Intelligent Systems and Technology, Volume 2 2011 1 27
52. A practical guide to support vector classification. Hsu C, Chang C, Lin C, Bioinformatics 2010 1 1 16
53. Fast Effective Rule Induction. Cohen WW, Proceedings of the Twelfth International Conference on Machine Learning, Prieditis A, Morgan Kaufmann RS, 1995 115 123
54. Induction of decision trees. Quinlan JR, Mach Learn 1986 1 81 106
55. Learning when training data are costly: the effect of class distribution on tree induction. Weiss GM, Provost F, J Artif Intell Res 2003 19 315 354 (Pubitemid 41525924)
56. Toward Scalable Learning with Non-uniform Class and Cost Distributions: A Case Study in Credit Card Fraud Detection. Chan PK, Stolfo SJ, Proceedings of the Fourth International Conference on Knowledge Discovery and Data Mining, Volume 164 1998 164 168
57. Ruch P, Baud RH, Geiddbühler A, Lovis C, Rassinoux AM, Rivière A, Looking back or looking all around: comparing two spell checking strategies for documents edition in an electronic patient record Proc AMIA Symp. 2001 568 72
58. ConText: an algorithm for determining negation, experiencer, and temporal status from clinical reports. Harkema H, Dowling JN, Thornblade T, Chapman WW, J Biomed Inform 2009 42 839 851 10.1016/j.jbi.2009.05.002 19435614
59. Apostolova E, Tomuro N, Demner-fushman D, Automatic Extraction of Lexico-Syntactic Patterns for Detection of Negation and Speculation Scopes Portland, Oregon, USA: Association for Computational Linguistics Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers-Volume 2. 2011 283 287