Automated data-adaptive analytics for electronic healthcare data to study causal treatment effects

Clinical Epidemiology

Volumn 10, Issue , 2018, Pages 771-788

  Schneeweiss, Sebastian ^a,b  

^a BRIGHAM AND WOMEN S HOSPITAL   (United States)

^b HARVARD MEDICAL SCHOOL   (United States)

Author keywords

Artificial intelligence; Automation; Causal conclusions; Confounding (epidemiology); Confounding adjustment; Health care databases; High dimensional data; Machine learning; Propensity scores; Real world data

Indexed keywords

ARTIFICIAL INTELLIGENCE; AUTOMATION; HUMAN; MACHINE LEARNING; PROPENSITY SCORE; REVIEW; SIMULATION;

EID: 85057739630     PISSN: None     EISSN: 11791349     Source Type: Journal    
DOI: 10.2147/CLEP.S166545     Document Type: Review

References (120)

1. Arana A, Rivero E, TCG E. What do we show and who does so? An analysis of the abstracts presented at the 19th ICPE. Pharmacoepidemiol Drug Saf. 2004;30:S330–S331.
2. Suissa S, Garbe E. Primer: administrative health databases in observational studies of drug effects – advantages and disadvantages. Nat Clin Pract Rheumatol. 2007;3(12):725–732.
3. Schneeweiss S, Avorn J. A review of uses of health care utilization databases for epidemiologic research on therapeutics. J Clin Epidemiol. 2005;58(4):323–337.
4. Ray WA. Evaluating medication effects outside of clinical trials: new-user designs. Am J Epidemiol. 2003;158(9):915–920.
5. Johnson ES, Bartman BA, Briesacher BA, et al. The incident user design in comparative effectiveness research. Pharmacoepidemiol Drug Saf. 2013;22(1):1–6.
6. Seeger JD, Walker AM, Williams PL, Saperia GM, Sacks FM. A propensity score-matched cohort study of the effect of statins, mainly fluvastatin, on the occurrence of acute myocardial infarction. Am J Cardiol. 2003;92(12):1447–1451.
7. Graham DJ, Reichman ME, Wernecke M, et al. Cardiovascular, bleeding, and mortality risks in elderly Medicare patients treated with dabigatran or warfarin for nonvalvular atrial fibrillation. Circulation. 2015;131(2):157–164.
8. Schneeweiss S, Seeger JD, Landon J, Walker AM. Aprotinin during coronary-artery bypass grafting and risk of death. N Engl J Med. 2008;358(8):771–783.
9. Kim SC, Solomon DH, Rogers JR, et al. Cardiovascular safety of tocilizumab versus tumor necrosis factor inhibitors in patients with rheumatoid arthritis – a Multi-database Cohort Study. Arthritis Rheum. 2016;69(6):1154–1164.
10. Ray WA, Chung CP, Murray KT, Hall K, Stein CM. Atypical antipsychotic drugs and the risk of sudden cardiac death. N Engl J Med. 2009;360(3):225–235.
11. Wang PS, Schneeweiss S, Avorn J, et al. Risk of death in elderly users of conventional vs. atypical antipsychotic medications. N Engl J Med. 2005;353(22):2335–2341.
12. Ebrahim S, Sohani ZN, Montoya L, et al. Reanalyses of randomized clinical trial data. JAMA. 2014;312(10):1024–1032.
13. Poynter JN, Gruber SB, Higgins PD, et al. Statins and the risk of colorectal cancer. N Engl J Med. 2005;352(21):2184–2192.
14. Go AS, Lee WY, Yang J, Lo JC, Gurwitz JH. Statin therapy and risks for death and hospitalization in chronic heart failure. JAMA. 2006;296(17):2105–2111.
15. Chan KA, Andrade SE, Boles M, et al. Inhibitors of hydroxymethylgl-utaryl-coenzyme A reductase and risk of fracture among older women. Lancet. 2000;355(9222):2185–2188.
16. Franklin JM, Schneeweiss S. When and how can real world data analyses substitute for randomized controlled trials? Clin Pharmacol Ther. 2017;102(6):924–933.
17. Walker AM. Confounding by indication. Epidemiology. 1996;7(4): 335–336.
18. Petri H, Urquhart J. Channeling bias in the interpretation of drug effects. Stat Med. 1991;10(4):577–581.
19. Maclure M, Schneeweiss S. Causation of bias: the episcope. Epidemiology. 2001;12(1):114–122.
20. Glynn RJ, Knight EL, Levin R, Avorn J. Paradoxical relations of drug treatment with mortality in older persons. Epidemiology. 2001;12(6):682–689.
21. Setoguchi S, Warner Stevenson L, Stewart GC, et al. Influence of healthy candidate bias in assessing clinical effectiveness for implant-able cardioverter-defibrillators: cohort study of older patients with heart failure. BMJ. 2014;348:g2866.
22. Schneeweiss S, Rassen JA, Glynn RJ, Avorn J, Mogun H, Brookhart MA. High-dimensional propensity score adjustment in studies of treatment effects using health care claims data. Epidemiology. 2009;20(4):512–522.
23. Cadarette SM, Ban JK, Consiglio GP, et al. Diffusion of innovations model helps interpret the comparative uptake of two methodological innovations: co-authorship network analysis and recommendations for the integration of novel methods in practice. J Clin Epidemiol. 2017;84: 150–160.
24. Schneeweiss S. Understanding secondary databases: a commentary on “Sources of bias for health state characteristics in secondary data-bases”. J Clin Epidemiol. 2007;60(7):648–650.
25. Gini R, Schuemie M, Brown J, et al. Data extraction and management in networks of observational health care databases for scientific research: a comparison of EU-ADR, OMOP, mini-sentinel and MATRICE strategies. EGEMS (Wash DC). 2016;4(1):1189.
26. Curtis LH, Weiner MG, Boudreau DM, et al. Design considerations, architecture, and use of the mini-sentinel distributed data system. Pharmacoepidemiol Drug Saf. 2012;21(suppl 1):23–31.
27. Matcho A, Ryan P, Fife D, Reich C. Fidelity assessment of a clinical practice research datalink conversion to the OMOP common data model. Drug Saf. 2014;37(11):945–959.
28. Schneeweiss S. A basic study design for expedited safety signal evaluation based on electronic healthcare data. Pharmacoepidemiol Drug Saf. 2010;19(8):858–868.
29. Wooldridge JM. Econometric Analysis of Cross Section and Panel Data. Cambridge, MA: MIT Press; 2002.
30. Gelman A, Carlin J, Stern H, Rubin D. Bayesian Data Analysis. New York: Chapman Hall; 1995.
31. Suissa S, Blais L, Ernst P. Patterns of increasing beta-agonist use and the risk of fatal or near-fatal asthma. Eur Respir J. 1994;7(9): 1602–1609.
32. Rassen JA, Schneeweiss S. Using high-dimensional propensity scores to automate confounding control in a distributed medical product safety surveillance system. Pharmacoepidemiol Drug Saf. 2012;21(suppl 1):41–49.
33. Schuster T, Pang M, Platt RW. On the role of marginal confounder prevalence – implications for the high-dimensional propensity score algorithm. Pharmacoepidemiol Drug Saf. 2015;24(9):1004–1007.
34. Robins JM, Mark SD, Whitney KN. Estimating exposure effects by modelling the expectation of exposure conditional on confounders. Biometrics. 1992;48(2):479–495.
35. Brookhart MA, Schneeweiss S, Rothman KJ, Glynn RJ, Avorn J, Stürmer T. Variable selection for propensity score models. Am J Epidemiol. 2006;163(12):1149–1156.
36. Myers JA, Rassen JA, Gagne JJ, et al. Effects of adjusting for instrumental variables on bias and precision of effect estimates. Am J Epidemiol. 2011;174(11):1213–1222.
37. Greenland S. Invited commentary: variable selection versus shrinkage in the control of multiple confounders. Am J Epidemiol. 2008;167(5):523–529; discussion 530–531.
38. Bross ID. Spurious effects from an extraneous variable. J Chronic Dis. 1966;19(6):637–647.
39. Rassen JA, Glynn RJ, Brookhart MA, Schneeweiss S. Covariate selection in high-dimensional propensity score analyses of treatment effects in small samples. Am J Epidemiol. 2011;173(12):1404–1413.
40. Schneeweiss S, Seeger JD, Maclure M, Wang PS, Avorn J, Glynn RJ. Performance of comorbidity scores to control for confounding in epidemiologic studies using claims data. Am J Epidemiol. 2001;154(9): 854–864.
41. Peduzzi P, Concato J, Kemper E, Holford TR, Feinstein AR. A simulation study of the number of events per variable in logistic regression analysis. J Clin Epidemiol. 1996;49(12):1373–1379.
42. Franklin JM, Eddings W, Glynn RJ, Schneeweiss S. Regularized regression versus the high-dimensional propensity score for confounding adjustment in secondary database analyses. Am J Epidemiol. 2015;182(7):651–659.
43. Cepeda MS, Boston R, Farrar JT, Strom BL. Comparison of logistic regression versus propensity score when the number of events is low and there are multiple confounders. Am J Epidemiol. 2003;158(3): 280–287.
44. Sturmer T, Rothman KJ, Avorn J, Glynn RJ. Treatment effects in the presence of unmeasured confounding: dealing with observations in the tails of the propensity score distribution – a simulation study. Am J Epidemiol. 2010;172(7):843–854.
45. Desai RJ, Rothman KJ, Bateman BT, Hernandez-Diaz S, Huybrechts KF. A propensity-score-based fine stratification approach for confounding adjustment when exposure is infrequent. Epidemiology. 2017;28(2):249–257.
46. Hernán MA, Brumback B, Robins JM. Marginal structural models to estimate the causal effect of zidovudine on the survival of HIV-positive men. Epidemiology. 2000;11(5):561–570.
47. Yoshida K, Hernandez-Diaz S, Solomon DH, et al. Matching weights to simultaneously compare three treatment groups: comparison to three-way matching. Epidemiology. 2017;28(3):387–395.
48. Moore KL, Neugebauer R, van der Laan MJ, Tager IB. Causal inference in epidemiological studies with strong confounding. Stat Med. 2012;31(13):1380–1404.
49. Arbogast PG, Ray WA. Use disease risk scores in pharmacoepidemiologic studies. Stat Methods Med Res. 2009;18(1):67–80.
50. Kumamaru H, Schneeweiss S, Glynn RJ, Setoguchi S, Gagne JJ. Dimension reduction and shrinkage methods for high dimensional disease risk scores in historical data. Emerg Themes Epidemiol. 2016;13:5.
51. Kumamaru H, Gagne JJ, Glynn RJ, Setoguchi S, Schneeweiss S. Comparison of high-dimensional confounder summary scores in comparative studies of newly marketed medications. J Clin Epidemiol. 2016;76:200–208.
52. Bombardier C, Laine L, Reicin A, et al; VIGOR Study Group. Comparison of upper gastrointestinal toxicity of rofecoxib and naproxen in patients with rheumatoid arthritis. VIGOR Study Group. N Engl J Med. 2000;343(21):1520–1528.
53. Silverstein FE, Faich G, Goldstein JL, et al. Gastrointestinal toxicity with celecoxib vs nonsteroidal anti-inflammatory drugs for osteo-arthritis and rheumatoid arthritis: the CLASS study: a randomized controlled trial. Celecoxib Long-term Arthritis Safety study. JAMA. 2000;284(10):1247–1255.
54. Garbe E, Kloss S, Suling M, Pigeot I, Schneeweiss S. High-dimensional versus conventional propensity scores in a comparative effectiveness study of coxibs and reduced upper gastrointestinal complications. Eur J Clin Pharmacol. 2013;69(3):549–557.
55. Le HV, Poole C, Brookhart MA, et al. Effects of aggregation of drug and diagnostic codes on the performance of the high-dimensional propensity score algorithm: an empirical example. BMC Med Res Methodol. 2013;13:142.
56. Hallas J, Pottegard A. Performance of the high-dimensional propensity score in a nordic healthcare model. Basic Clin Pharmacol Toxicol. 2017;120(3):312–317.
57. Toh S, Garcia Rodriguez LA, Hernan MA. Confounding adjustment via a semi-automated high-dimensional propensity score algorithm: an application to electronic medical records. Pharmacoepidemiol Drug Saf. 2011;20(8):849–857.
58. Lin KJ, Schneeweiss S. Considerations for the analysis of longitudinal electronic health records linked to claims data to study the effectiveness and safety of drugs. Clin Pharmacol Ther. 2016;100(2):147–159.
59. Zhou M, Wang SV, Leonard CE, et al. Sentinel modular program for propensity score-matched cohort analyses: application to glyburide, glipi-zide, and serious hypoglycemia. Epidemiology. 2017;28(6):838–846.
60. Gangji AS, Cukierman T, Gerstein HC, Goldsmith CH, Clase CM. A systematic review and meta-analysis of hypoglycemia and cardiovascular events: a comparison of glyburide with other secretagogues and with insulin. Diabetes Care. 2007;30(2):389–394.
61. Enders D, Ohlmeier C, Garbe E. The potential of high-dimensional propensity scores in health services research: an exemplary study on the quality of care for elective percutaneous coronary interventions. Health Serv Res. 2018;53(1):197–213.
62. Polinski JM, Schneeweiss S, Glynn RJ, Lii J, Rassen JA. Confronting “confounding by health system use” in Medicare part D: comparative effectiveness of propensity score approaches to confounding adjustment. Pharmacoepidemiol Drug Saf. 2012;21(suppl 2):90–98.
63. Rassen JA, Wahl PM, Angelino E, Seltzer MI, Rosenman MD, Schneeweiss S. Automated use of electronic health record text data to improve validity in pharmacoepidemiology studies. Pharmacoepidemiol Drug Saf. 2013;22(S1):376.
64. Murphy SA, van der Laan MJ, Robins JM; CPPRG. Marginal mean models for dynamic regimes. J Am Stat Assoc. 2001;96(456):1410–1423.
65. Neugebauer R, Schmittdiel JA, Zhu Z, Rassen JA, Seeger JD, Schneeweiss S. High-dimensional propensity score algorithm in comparative effectiveness research with time-varying interventions. Stat Med. 2015;34(5):753–781.
66. Robins JM, Hernan MA, Brumback B. Marginal structural models and causal inference in epidemiology. Epidemiology. 2000;11(5):550–560.
67. Franklin JM, Schneeweiss S, Polinski JM, Rassen JA. Plasmode simulation for the evaluation of pharmacoepidemiologic methods in complex healthcare databases. Comput Stat Data Anal. 2014;72:219–226.
68. Wyss R, Schneeweiss S, van der Laan M, Lendle SD, Ju C, Franklin JM. Using super learner prediction modeling to improve high-dimensional propensity score estimation. Epidemiology. 2018;29(1):96–106.
69. Leacy FP, Stuart EA. On the joint use of propensity and prognostic scores in estimation of the average treatment effect on the treated: a simulation study. Stat Med. 2014;33(20):3488–3508.
70. Guertin JR, Rahme E, LeLorier J. Performance of the high-dimensional propensity score in adjusting for unmeasured confounders. Eur J Clin Pharmacol. 2016;72(12):1497–1505.
71. Rosenbaum PR, Rubin DB. The central role of propensity scores in observational studies for causal effects. Biometrika. 1983;70(1):41–55.
72. Rubin DB. Estimating causal effects from large data sets using propensity scores. Ann Intern Med. 1997;127(8 pt 2):757–763.
73. Setoguchi S, Schneeweiss S, Brookhart MA, Glynn RJ, Cook EF. Evaluating uses of data mining techniques in propensity score estimation: a simulation study. Pharmacoepidemiol Drug Saf. 2008;17(6):546–555.
74. Lee BK, Lessler J, Stuart EA. Improving propensity score weighting using machine learning. Stat Med. 2010;29(3):337–346.
75. Westreich D, Lessler J, Funk MJ. Propensity score estimation: neural networks, support vector machines, decision trees (CART), and meta-classifiers as alternatives to logistic regression. J Clin Epidemiol. 2010;63(8):826–833.
76. Linden A, Yarnold PR. Using classification tree analysis to generate propensity score weights. J Eval Clin Pract. 2017;23(4):703–712.
77. Pearl J. Invited commentary: understanding bias amplification. Am J Epidemiol. 2011;174(11):1223–1227; discussion 1228–1229.
78. Schneeweiss S, Eddings W, Glynn RJ, Patorno E, Rassen J, Franklin JM. Variable selection for confounding adjustment in high-dimensional covariate spaces when analyzing healthcare databases. Epidemiology. 2017;28(2):237–248.
79. Karim ME, Pang M, Platt RW. Can we train machine learning methods to outperform the high-dimensional propensity score algorithm? Epidemiology. 2018;29(2):191–198.
80. Shortreed SM, Ertefaie A. Outcome-adaptive lasso: variable selection for causal inference. Biometrics. 2017;73(4):1111–1122.
81. Patorno E, Glynn RJ, Hernandez-Diaz S, Liu J, Schneeweiss S. Studies with many covariates and few outcomes: selecting covariates and implementing propensity-score-based confounding adjustments. Epidemiology. 2014;25(2):268–278.
82. van der Laan MJ, Polley EC, Hubbard AE. Super learner. Stat Appl Genet Mol Biol. 2007;6:Article25.
83. Ju C, Gruber S, Lendle SD, et al. Scalable collaborative targeted learning for high-dimensional data. Stat Methods Med Res. Epub 2017 Jan 1.
84. Schneeweiss S, Gagne JJ, Glynn RJ, Ruhl M, Rassen JA. Assessing the comparative effectiveness of newly marketed medications: methodological challenges and implications for drug development. Clin Pharmacol Ther. 2011;90(6):777–790.
85. Franklin JM, Eddings W, Austin PC, Stuart EA, Schneeweiss S. Comparing the performance of propensity score methods in healthcare database studies with rare outcomes. Stat Med. 2017;36(12):1946–1963.
86. Glynn RJ, Gagne JJ, Schneeweiss S. Role of disease risk scores in comparative effectiveness research with emerging therapies. Pharmacoepidemiol Drug Saf. 2012;21(suppl 2):138–147.
87. Suissa S. Immortal time bias in pharmaco-epidemiology. Am J Epidemiol. 2008;167(4):492–499.
88. Schisterman EF, Cole SR, Platt RW. Overadjustment bias and unnecessary adjustment in epidemiologic studies. Epidemiology. 2009;20(4):488–495.
89. Greenland S, Pearl J, Robins JM. Causal diagrams for epidemiologic research. Epidemiology. 1999;10(1):37–48.
90. Liu W, Brookhart MA, Setoguchi S. Impact of collider-stratification bias (M-bias) in pharmacoepidemiologic studies: a simulation study. Pharmacoepidemiol Drug Saf. 2010;19(S1):S212.
91. Greenland S. Quantifying biases in causal models: classical confounding vs collider-stratification bias. Epidemiology. 2003;14(3):300–306.
92. Pearl J. On a class of bias-amplifying variables that endanger effect estimates. Paper Presented at: Proceedings of the Twenty-Sixth Conference on Uncertainty in Artificial Intelligence. Corvallis, OR: AUAI; 2012.
93. Angrist JD, Imbens G, Rubin DB. Identification of causal effects using instrumental variables. J Am Stat Assoc. 1996;94(434):444–455.
94. Brookhart MA, Rassen JA, Schneeweiss S. Instrumental variable methods in comparative safety and effectiveness research. Pharmacoepidemiol Drug Saf. 2010;19(6):537–554.
95. Haggstrom J. Data-driven confounder selection via Markov and Bayesian networks. Biometrics. 2017.
96. Kennedy EH, Balakrishnan S. Discussion of “data-driven confounder selection via Markov and Bayesian networks” by Jenny Haggstrom. Biometrics. 2017.
97. Friedman C, Rubin J, Brown J, et al. Toward a science of learning systems: a research agenda for the high-functioning learning health system. J Am Med Inform Assoc. 2015;22(1):43–50.
98. Azoulay L, Yin H, Filion KB, et al. The use of pioglitazone and the risk of bladder cancer in people with type 2 diabetes: nested case-control study. BMJ. 2012;344:e3645.
99. Dormuth CR, Filion KB, Paterson JM, et al; Canadian Network for Observational Drug Effect Studies Investigators. Higher potency statins and the risk of new diabetes: multicentre, observational study of administrative databases. BMJ. 2014;348:g3244.
100. Yu O, Azoulay L, Yin H, Filion KB, Suissa S. Sulfonylureas as initial treatment for type 2 diabetes and the risk of severe hypoglycemia. Am J Med. 2018;131(3):317.e311–317.e322.
101. Franklin JM, Rassen JA, Ackermann D, Bartels DB, Schneeweiss S. Metrics for covariate balance in cohort studies of causal effects. Stat Med. 2014;33(10):1685–1699.
102. Austin PC. Balance diagnostics for comparing the distribution of baseline covariates between treatment groups in propensity-score matched samples. Stat Med. 2009;28(25):3083–3107.
103. Madigan D, Ryan PB, Schuemie M, et al. Evaluating the impact of database heterogeneity on observational study results. Am J Epidemiol. 2013;178(4):645–651.
104. Gagne JJ, Wang SV, Rassen JA, Schneeweiss S. A modular, prospective, semi-automated drug safety monitoring system for use in a distributed data environment. Pharmacoepidemiol Drug Saf. 2014;23(6): 619–627.
105. Connolly JG, Wang SV, Fuller CC, et al. Development and application of two semi-automated tools for targeted medical product surveillance in a distributed data network. Curr Epidemiol Rep. 2017;4(4): 298–306.
106. Gagne JJ, Han X, Hennessy S, et al. Successful comparison of US Food and Drug Administration sentinel analysis tools to traditional approaches in quantifying a known drug-adverse event association. Clin Pharmacol Ther. 2016;100(5):558–564.
107. Filion KB, Chateau D, Targownik LE, et al; CNODES Investigators. Proton pump inhibitors and the risk of hospitalisation for community-acquired pneumonia: replicated cohort studies with meta-analysis. Gut. 2014;63(4):552–558.
108. Filion KB, Azoulay L, Platt RW, et al. A multicenter observational study of incretin-based drugs and heart failure. N Engl J Med. 2016;374(12):1145–1154.
109. Yildirim MA, Goh KI, Cusick ME, Barabasi AL, Vidal M. Drug-target network. Nat Biotechnol. 2007;25(10):1119–1126.
110. Wang RS, Loscalzo J. Illuminating drug action by network integration of disease genes: a case study of myocardial infarction. Mol Biosyst. 2016;12(5):1653–1666.
111. Cheng F, Desai RJ, Handy DE, et al. Network-based approach to prediction and population-based validation of in silico drug repurposing. Nat Commun. 2018.
112. Joffe MM. Exhaustion, automation, theory, and confounding. Epidemiology. 2009;20(4):523–524.
113. Leonard CE, Brensinger CM, Aquilante CL, et al. Comparative safety of sulfonylureas and the risk of sudden cardiac arrest and ventricular arrhythmia. Diabetes Care. 2018;41(4):713–722.
114. Patorno E, Gopalakrishnan C, Franklin JM, et al. Claims-based studies of oral glucose-lowering medications can achieve balance in critical clinical parameters only observed in electronic health records. Diabetes Obes Metab. 2017;20(4):974–984.
115. Eng PM, Seeger JD, Loughlin J, Clifford CR, Mentor S, Walker AM. Supplementary data collection with case-cohort analysis to address potential confounding in a cohort study of thromboembolism in oral contraceptive initiators matched on claims-based propensity scores. Pharmacoepidemiol Drug Saf. 2008;17(3):297–305.
116. Toh S, Reichman ME, Houstoun M, et al. Comparative risk for angioedema associated with the use of drugs that target the renin-angiotensin-aldosterone system. Arch Int Med. 2012;172:1582.
117. Rassen JA, Choudhry NK, Avorn J, Schneeweiss S. Cardiovascular outcomes and mortality in patients using clopidogrel with PPIs after percutaneous coronary intervention. Circulation. 2009;120:2322–2329.
118. Schneeweiss S, Patrick AR, Solomon DH, et al. The comparative safety of antidepressant agents in children regarding suicidal acts. Pediatrics. 2010;125:876–888.
119. Schneeweiss S, Patrick AR, Solomon DH, et al. Variation in the risk of suicide attempts and completed suicides by antidepressant agent in adults. Arch Gen Psychiatry. 2010;67:497–506.
120. Patorno E, Bohn RL, Wahl PM, et al. Anticonvulsant medications and the risk of suicide, attempted suicide, or violent death. JAMA. 2010;303:1401–1409.