A supervised adverse drug reaction signalling framework imitating Bradford Hill's causality considerations

Journal of Biomedical Informatics

Volumn 56, Issue , 2015, Pages 356-368

  Reps, Jenna Marie ^a   Garibaldi, Jonathan M ^a   Aickelin, Uwe ^a   Gibson, Jack E ^a   Hubbard, Richard B ^a  

^a UNIVERSITY OF NOTTINGHAM   (United Kingdom)

Author keywords

Big data; Causal effects; Longitudinal observational data; Pharmacovigilance; Signal detection

Indexed keywords

BIG DATA; SAFETY ENGINEERING; SIGNAL DETECTION; SUPERVISED LEARNING;

ADVERSE DRUG REACTIONS; AREA UNDER THE CURVES; CAUSAL EFFECTS; DISCRIMINATION ABILITY; NEGATIVE SIDE EFFECTS; OBSERVATIONAL DATA; PHARMACOVIGILANCE; WEALTH OF INFORMATION;

DRUG PRODUCTS;

ANTIBIOTIC AGENT; ANTICONVULSIVE AGENT; BENZODIAZEPINE DERIVATIVE; BETA ADRENERGIC RECEPTOR BLOCKING AGENT; BISPHOSPHONIC ACID DERIVATIVE; DIPEPTIDYL CARBOXYPEPTIDASE INHIBITOR; NEUROLEPTIC AGENT; TRICYCLIC ANTIDEPRESSANT AGENT; WARFARIN; ANTIDEPRESSANT AGENT; DRUG;

ACCURACY; AREA UNDER THE CURVE; ARTICLE; AUTOANALYSIS; BIOLOGICAL GRADIENT; BRADFORD HILL CAUSALITY CONSIDERATION; CLASSIFIER; COMPARATIVE STUDY; CONTROLLED STUDY; DATA ANALYSIS; DATA EXTRACTION; DRUG SAFETY; EXPERIMENTATION; FACTUAL DATABASE; HIERARCHAL FEATURES; HUMAN; INFORMATION PROCESSING; LONGITUDINAL OBSERVATIONAL DATABASE; MACHINE LEARNING; OUTCOMES PARTNERSHIP NON SPECIFIED ASSOCIATION REFERENCE SET; PARAMETERS; PRIORITY JOURNAL; PROCESS OPTIMIZATION; RANDOM FOREST; SELECTION BIAS; SENSITIVITY AND SPECIFICITY; STATISTICAL CONCEPTS; STATISTICAL SIGNIFICANCE; SUPERVISED ADVERSE DRUG REACTION SIGNALLING FRAMEWORK; TEMPORALITY; ADVERSE DRUG REACTION; ALGORITHM; COMPUTER PROGRAM; DEVICES; DRUG SURVEILLANCE PROGRAM; EPIDEMIOLOGY; GREAT BRITAIN; LABORATORY DIAGNOSIS; MEDICAL INFORMATICS; OUTCOME ASSESSMENT; PROCEDURES; RECEIVER OPERATING CHARACTERISTIC; SIGNAL TRANSDUCTION;

ADVERSE DRUG REACTION REPORTING SYSTEMS; ALGORITHMS; ANTIDEPRESSIVE AGENTS; AREA UNDER CURVE; DATA COLLECTION; DATABASES, FACTUAL; DRUG-RELATED SIDE EFFECTS AND ADVERSE REACTIONS; EPIDEMIOLOGY; FALSE POSITIVE REACTIONS; GREAT BRITAIN; MEDICAL INFORMATICS; OUTCOME ASSESSMENT (HEALTH CARE); PHARMACEUTICAL PREPARATIONS; ROC CURVE; SENSITIVITY AND SPECIFICITY; SIGNAL TRANSDUCTION; SOFTWARE;

EID: 84938571741     PISSN: 15320464     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.jbi.2015.06.011     Document Type: Article

References (42)

1. Suling M., Pigeot I. Signal detection and monitoring based on longitudinal healthcare data. Pharmaceutics 2012, 4(4):607-640.
2. Ryan P.B., Madigan D., Stang P.E., Marc Overhage J., Racoosin J.A., Hartzema A.G. Empirical assessment of methods for risk identification in healthcare data: results from the experiments of the Observational Medical Outcomes Partnership. Stat. Med. 2012, 31(30):4401-4415.
3. Reps J.M., Garibaldi J.M., Aickelin U., Soria D., Gibson J., Hubbard R. Comparison of algorithms that detect drug side effects using electronic healthcare databases. Soft Comput. 2013, 17(12):2381-2397.
4. Ryan P.B., Schuemie M.J., Welebob E., Duke J., Valentine S., Hartzema A.G. Defining a reference set to support methodological research in drug safety. Drug Safety 2013, 36(1):33-47.
5. Shakir S.A., Layton D. Causal association in pharmacovigilance and pharmacoepidemiology. Drug Safety 2002, 25(6):467-471.
6. Holt R., Peveler R. Antipsychotic drugs and diabetes an application of the Austin Bradford Hill criteria. Diabetologia 2006, 49(7):1467-1476.
7. Perrio M., Voss S., Shakir S.A. Application of the bradford hill criteria to assess the causality of cisapride-induced arrhythmia. Drug Safety 2007, 30(4):333-346.
8. Holt R., Peveler R. Antipsychotic drugs and diabetes - an application of the Austin Bradford Hill criteria. Diabetologia 2006, 49(7):1467-1476.
9. Rawlins M. Spontaneous reporting of adverse drug reactions. i: The data. Brit. J. Clin. Pharmacol. 1988, 26(1):1-5.
10. van Puijenbroek E.P., Bate A., Leufkens H.G., Lindquist M., Orre R., Egberts A.C. A comparison of measures of disproportionality for signal detection in spontaneous reporting systems for adverse drug reactions. Pharmacoepidem. Drug Safety 2002, 11(1):3-10.
11. Hazell L., Shakir S.A. Under-reporting of adverse drug reactions. Drug Safety 2006, 29(5):385-396.
12. Caster O., Juhlin K., Watson S., Norén G.N. Improved statistical signal detection in pharmacovigilance by combining multiple strength-of-evidence aspects in vigiRank. Drug Safety 2014, 37(8):617-628.
13. Van Holle L., Bauchau V. Use of logistic regression to combine two causality criteria for signal detection in vaccine spontaneous report data. Drug Safety 2014, 1-11.
14. J. Reps, J.M. Garibaldi, U. Aickelin, D. Soria, J.E. Gibson, R.B. Hubbard, Attributes for causal inference in electronic healthcare databases, in: CBMS 2013, The 26th IEEE International Symposium on Computer-Based Medical Systems, Porto, 2013, pp. 548-549. http://ima.ac.uk/papers/reps2013a.pdf.
15. Zorych I., Madigan D., Ryan P., Bate A. Disproportionality methods for pharmacovigilance in longitudinal observational databases. Stat. Methods Med. Res. 2013, 22(1):39-56.
16. Norén G.N., Hopstadius J., Bate A., Star K., Edwards I.R. Temporal pattern discovery in longitudinal electronic patient records. Data Min. Knowl. Disc. 2010, 20(3):361-387.
17. Jin H., Chen J., Kelman C., He H., McAullay D., OKeefe C.M. Mining unexpected associations for signalling potential adverse drug reactions from administrative health databases. Advances in Knowledge Discovery and Data Mining 2006, 867-876. Springer.
18. Jin H., Chen J., He H., Kelman C., McAullay D., O'Keefe C.M. Signaling potential adverse drug reactions from administrative health databases. IEEE Trans. Knowl. Data Eng. 2010, 22(6):839-853.
19. Harpaz R., DuMouchel W., Shah N.H., Madigan D., Ryan P., Friedman C. Novel data-mining methodologies for adverse drug event discovery and analysis. Clin. Pharmacol. Therap. 2012, 91(6):1010-1021.
20. Reps J.M., Garibaldi J.M., Aickelin U., Soria D., Gibson J.E., Hubbard R.B. Signalling paediatric side effects using an ensemble of simple study designs. Drug Safety 2014, 37(3):163-170.
21. Brown E.G., Wood L., Wood S. The medical dictionary for regulatory activities (meddra). Drug Safety 1999, 20(2):109-117.
22. Chisholm J. The read clinical classification. BMJ: Brit. Med. J. 1990, 300(6732):1092.
23. Pearl J. Causality: Models, Reasoning and Inference 2000, vol. 29. Cambridge Univ Press.
24. Silverstein C., Brin S., Motwani R., Ullman J. Scalable techniques for mining causal structures. Data Min. Knowl. Disc. 2000, 4(2-3):163-192.
25. Cooper G.F. A simple constraint-based algorithm for efficiently mining observational databases for causal relationships. Data Min. Knowl. Disc. 1997, 1(2):203-224.
26. Lewis J.D., Schinnar R., Bilker W.B., Wang X., Strom B.L. Validation studies of the health improvement network (THIN) database for pharmacoepidemiology research. Pharmacoepidem. Drug Safety 2007, 16(4):393-401.
27. Committee J.F. British National Formulary 2013, vol. 65. Pharmaceutical Press.
28. Lewis J.D., Bilker W.B., Weinstein R.B., Strom B.L. The relationship between time since registration and measured incidence rates in the General Practice Research Database. Pharmacoepidem. Drug Safety 2005, 14(7):443-451.
29. OMOP, NSA Reference Set, 2014. (accessed: 01.11.14). http://omop.org/sites/default/files/OMOP%20NSA_test_ref_full.xls.
30. Li C., Xia J., Deng J., Jiang J. A comparison of measures of disproportionality for signal detection on adverse drug reaction spontaneous reporting database of Guangdong province in China. Pharmacoepidem. Drug Safety 2008, 17(6):593-600.
31. Liaw A., Wiener M. Classification and regression by randomforest. R News 2002, 2(3):18-22.
32. Rothman K.J., Greenland S. Modern Epidemiology 1998, Lippincott-Raven.
33. Weiss N.S. Can the 'specificity' of an association be rehabilitated as a basis for supporting a causal hypothesis?. Epidemiology 2002, 13(1):6-8.
34. Liu Y., Lependu P., Lyer S., Shah N.H. Using temporal patterns in medical records to discern adverse drug events from indications. AMIA Summ. Transl. Sci. Proc. 2012, 2012:47-56.
35. Jung K., LePendu P., Shah N. Automated detection of systematic off-label drug use in free text of electronic medical records. AMIA Summ. Transl. Sci. Proc. 2013, 2013:94-98.
36. Höfler M. The bradford hill considerations on causality: a counterfactual perspective. Emerg. Themes Epidemiol. 2005, 2(1):11-19.
37. Hill A.B. The environment and disease: association or causation?. Proc. Roy. Soc. Med. 1965, 58(5):295-300.
38. M.K.C. from Jed Wing, S. Weston, A. Williams, C. Keefer, A. Engelhardt, caret: Classification and Regression Training, R package version 5.15-044, 2012.
39. Partners HealthCare, S.N. Murphy, V. Castro, J. Colecchi, A. Dubey, V. Gainer, C. Herrick, M. Sordo, Partners Healthcare OMOP Study Report, 2011. (accessed 01.11.14). http://omop.org/sites/default/files/PHCS_Final_OMOP_StudyReport.pdf.
40. DeLong E.R., DeLong D.M., Clarke-Pearson D.L. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 1988, 44(3):837-845.
41. Shvachko K., Kuang H., Radia S., Chansler R. The hadoop distributed file system. 2010 IEEE 26th Symposium on Mass Storage Systems and Technologies (MSST) 2010, 1-10. IEEE.
42. Mirtz T.A., Morgan L., Wyatt L.H., Greene L. An epidemiological examination of the subluxation construct using hill's criteria of causation. Chiropr. Manual Ther. 2009, 17(1):13-19.