Propensity score estimation: neural networks, support vector machines, decision trees (CART), and meta-classifiers as alternatives to logistic regression

Journal of Clinical Epidemiology

Volumn 63, Issue 8, 2010, Pages 826-833

  Westreich, Daniel ^a,b   Lessler, Justin ^c   Funk, Michele Jonsson ^a  

^a IL   (United States)

^b UNIVERSITY OF NORTH CAROLINA SCHOOL OF MEDICINE   (United States)

^c JOHNS HOPKINS BLOOMBERG SCHOOL OF PUBLIC HEALTH   (United States)

Author keywords

Classification and regression trees (CART); Logistic regression; Neural networks; Propensity scores; Recursive partitioning algorithms; Review

Indexed keywords

ALGORITHM; ARTIFICIAL NEURAL NETWORK; DATA ANALYSIS; DECISION TREE; EPIDEMIOLOGICAL DATA; LOGISTIC REGRESSION ANALYSIS; PRIORITY JOURNAL; REVIEW; SUPPORT VECTOR MACHINE; ARTIFICIAL INTELLIGENCE; HUMAN; PROPENSITY SCORE; STATISTICAL ANALYSIS; STATISTICAL MODEL;

ALGORITHMS; ARTIFICIAL INTELLIGENCE; DATA INTERPRETATION, STATISTICAL; DECISION TREES; HUMANS; LOGISTIC MODELS; NEURAL NETWORKS (COMPUTER); PROPENSITY SCORE;

EID: 77953607621     PISSN: 08954356     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.jclinepi.2009.11.020     Document Type: Review

References (47)

1. Rosenbaum P.R., and Rubin D.B. The central role of the propensity score in observational studies for causal effects. Biometrika 70 (1983) 41-55
2. Cepeda M.S., Boston R., Farrar J.T., and Strom B.L. Comparison of logistic regression versus propensity score when the number of events is low and there are multiple confounders. Am J Epidemiol 158 (2003) 280-287
3. Joffe M.M., and Rosenbaum P.R. Invited commentary: propensity scores. Am J Epidemiol 150 (1999) 327-333
4. D'Agostino Jr. R.B. Propensity score methods for bias reduction in the comparison of a treatment to a non-randomized control group. Stat Med 17 (1998) 2265-2281
5. Weitzen S., Lapane K.L., Toledano A.Y., Hume A.L., and Mor V. Principles for modeling propensity scores in medical research: a systematic literature review. Pharmacoepidemiol Drug Saf 13 (2004) 841-853
6. Cook E.F., and Goldman L. Asymmetric stratification. An outline for an efficient method for controlling confounding in cohort studies. Am J Epidemiol 127 (1988) 626-639
7. Glynn R.J., Schneeweiss S., and Sturmer T. Indications for propensity scores and review of their use in pharmacoepidemiology. Basic Clin Pharmacol Toxicol 98 (2006) 253-259
8. McCaffrey D.F., Ridgeway G., and Morral A.R. Propensity score estimation with boosted regression for evaluating causal effects in observational studies. Psychol Methods 9 (2004) 403-425
9. Setoguchi S., Schneeweiss S., Brookhart M.A., Glynn R.J., and Cook E.F. Evaluating uses of data mining techniques in propensity score estimation: a simulation study. Pharmacoepidemiol Drug Saf 17 (2008) 546-555
10. Duda R.O., Hart P.E., and Stork D.G. Pattern classification. 2nd edition (2000), John Wiley and Sons, New York
11. Mitchell T.M. Machine learning (1997), WCB/McGraw-Hill, New York
12. Kleinbaum D.G., and Klein M. Logistic regression. A self-learning text. In: Statistics in Biology and Health. 2nd edition (2002), Springer, New York
13. Brookhart M.A., Schneeweiss S., Rothman K.J., Glynn R.J., Avorn J., and Sturmer T. Variable selection for propensity score models. Am J Epidemiol 163 (2006) 1149-1156
14. Breiman L. Statistical modeling: the two cultures. Stat Sci 16 (2001) 199-231
15. Bishop C.M. Neural networks for pattern recognition (1995), Oxford University Press, New York
16. Barron A.R. Approximation and estimation bounds for artificial neural networks. Machine Learning 14 (1994) 115-133
17. Mhaskar H. Neural networks for optimal approximation of smooth and analytic functions. Neural Comput 8 (1996) 164-177
18. ™. Available at (2008). http://www.sas.com/technologies/analytics/datamining/miner/ Subsection features; accessed September 2, 2009
19. Nagy A. Package: neural. Available at (2009). http://cran.r-project.org/web/packages/neural/neural.pdf (Accessed September 9, 2009)
20. Zhang G.P. Neural networks for classification: a survey. IEEE Trans Systems Man Cybernetics Part C 30 (2000) 451-462
21. Cavuto S., Bravi F., Grassi M., and Apolone G. Propensity score for the analysis of observational data: an introduction and an illustrative example. Drug Dev Res 67 (2006) 208-216
22. du Jardin P., Ponsaille J., Alunni-Perret V., and Quatrehomme G. A comparison between neural network and other metric methods to determine sex from the upper femur in a modern French population. Forensic Sci Int 192 (2009) 127.e1-127.e6
23. Eftekhar B., Mohammad K., Ardebili H.E., Ghodsi M., and Ketabchi E. Comparison of artificial neural network and logistic regression models for prediction of mortality in head trauma based on initial clinical data. BMC Med Inform Decis Mak 5 (2005) 3
24. Burges C.J.C. A tutorial on support vector machines for pattern recognition. Data Mining Knowl Discov 2 (1998) 121-167
25. Zhu J., and Hastie T. Kernel logistic regression and the import vector machine. J Comput Graph Stat 14 (2005) 185-205
26. Meyer D. Support vector machines. Available at (2009). http://cran.r-project.org/web/packages/e1071/vignettes/svmdoc.pdf Accessed September 9, 2009
27. Gunn SR. Support vector machines for classification and regression. Technical Report, ISIS Research Group, Department of Electronics and Computer Science, University of Southampton, UK. 1998.
28. Drucker H., Wu D., and Vapnik V.N. Support vector machines for spam categorization. IEEE Trans Neural Netw 10 (1999) 1048-1054
29. Segal N.H., Pavlidis P., Antonescu C.R., Maki R.G., Noble W.S., DeSantis D., et al. Classification and subtype prediction of adult soft tissue sarcoma by functional genomics. Am J Pathol 163 (2003) 691-700
30. Segal N.H., Pavlidis P., Noble W.S., Antonescu C.R., Viale A., Wesley U.V., et al. Classification of clear-cell sarcoma as a subtype of melanoma by genomic profiling. J Clin Oncol 21 (2003) 1775-1781
31. Sweredoski M.J., and Baldi P. COBEpro: a novel system for predicting continuous B-cell epitopes. Protein Eng Des Sel 22 (2009) 113-120
32. van Putten W. Classification and regression tree analysis (CART) with Stata. Available at (2009). http://fmwww.bc.edu/RePEc/dsug2002/cart.pdf Accessed March 31, 2010
33. Therneau T.M., and Atkinson B. Package: rpart. Available at (2009). http://cran.r-project.org/web/packages/rpart/rpart.pdf (Accessed September 9, 2009)
34. Breiman L., Friedman J., Olshen R., and Stone C. Classification and regression trees (1984), Wadsworth, Belmont, CA
35. Kershaw T.S., Lewis J., Westdahl C., Wang Y.F., Rising S.S., Massey Z., et al. Using Clinical Classification Trees to Identify Individuals At Risk of STDs During Pregnancy. Perspect Sex Reprod Health 39 (2007) 141-148
36. Barosi G., Ambrosetti A., Centra A., Falcone A., Finelli C., Foa P., et al. Splenectomy and risk of blast transformation in myelofibrosis with myeloid metaplasia. Italian Cooperative Study Group on Myeloid with Myeloid Metaplasia. Blood 91 (1998) 3630-3636
37. Schapire RE. The Boosting approach to machine learning: an overview. In: Hansen DD, Holmes MH, Mallick CC, Yu B, editors: Nonlinear Estimation and Classification. New York: Springer; 2003.
38. Breiman L, Cutler A, Liaw A, Wiener M. Breiman and Cutler's random forests for classification and regression, v. 4.5-22: 2007; Available at. http://cran.r-project.org/web/packages/randomForest/index.html. (Accessed December 18, 2007), 2007.
39. Ridgeway G. Generalized boosted models: a guide to the gbm package. Available at http://cran.r-project.org/web/packages/gbm/vignettes/gbm.pdf. Accessed March 31, 2010.
40. Schonlau M. Boosted regression (boosting): an introductory tutorial and a Stata plugin. Stata J 5 (2005) 330-354
41. Harder V.S., Morral A.R., and Arkes J. Marijuana use and depression among adults: testing for causal associations. Addiction 101 (2006) 1463-1472
42. Hernan M.A., Brumback B., and Robins J.M. Marginal structural models to estimate the causal effect of zidovudine on the survival of HIV-positive men. Epidemiology 11 (2000) 561-570
43. Robins J.M., Hernán M.A., and Brumback B. Marginal structural models and causal inference in epidemiology. Epidemiology 11 (2000) 550-560
44. Bang H., and Robins J.M. Doubly robust estimation in missing data and causal inference models. Biometrics 61 (2005) 962-973
45. Lunceford J.K., and Davidian M. Stratification and weighting via the propensity score in estimation of causal treatment effects: a comparative study. Stat Med 23 (2004) 2937-2960
46. Lee B.K., Lessler J., and Stuart E.A. Improving propensity score weighting using machine learning. Stat Med 29 3 (2010) 337-346
47. Dreiseitl S., and Ohno-Machado L. Logistic regression and artificial neural network classification models: a methodology review. J Biomed Inform 35 (2002) 352-359