Machine Learning in Epidemiology and Health Outcomes Research

Annual Review of Public Health - Tập 41 Số 1 - Trang 21-36 - 2020
Timothy L. Wiemken1, Robert Kelley2
1Center for Health Outcomes Research, Saint Louis University, Saint Louis, Missouri 63104, USA;
2Department of Computer Science, Bellarmine University, Louisville, Kentucky 40205, USA;

Tóm tắt

Machine learning approaches to modeling of epidemiologic data are becoming increasingly more prevalent in the literature. These methods have the potential to improve our understanding of health and opportunities for intervention, far beyond our past capabilities. This article provides a walkthrough for creating supervised machine learning models with current examples from the literature. From identifying an appropriate sample and selecting features through training, testing, and assessing performance, the end-to-end approach to machine learning can be a daunting task. We take the reader through each step in the process and discuss novel concepts in the area of machine learning, including identifying treatment effects and explaining the output from machine learning models.

Từ khóa


Tài liệu tham khảo

10.1371/journal.pone.0179805

10.1073/pnas.1510489113

10.18297/jri/vol1/iss1/5

10.1016/S2213-8587(17)30176-6

10.1016/j.epidem.2018.05.006

10.1016/j.aca.2012.11.007

Bellman R., 2015, Adaptive Control Processes: A Guided Tour

Bergstra J, 2012, J. Mach. Learn. Res., 13, 281

10.1016/S0004-3702(97)00063-5

10.1093/biostatistics/kxh002

10.1023/A:1010933404324

10.1214/ss/1009213726

10.1186/s12913-017-2445-3

10.1613/jair.953

10.2174/1574893612666170718153316

Chernozhukov V, Chetverikov D, Demirer M, Duflo E, Hansen C, et al. 2016. Double/debiased machine learning for treatment and causal parameters. arXiv:160800060 [Econ. Stat.]

10.1371/journal.pone.0208737

10.1080/14760584.2018.1493928

10.1016/j.annemergmed.2018.11.036

10.1093/jamia/ocz036

10.1186/1472-6947-12-8

10.1371/journal.pmed.1002702

Forbes, 2018, Forbes

10.1016/j.jbi.2018.12.003

10.1371/journal.pone.0208442

10.1093/poq/nfs036

10.1097/EDE.0b013e3182785741

10.1007/978-0-387-84858-7

10.1093/bioinformatics/bti171

10.1214/12-AOAS593

Jaderberg M, Dalibard V, Osindero S, Czarnecki WM, Donahue J, et al. 2017. Population based training of neural networks. arXiv:1711.09846 [Cs]

10.1038/nrg3208

10.1109/DSAA.2015.7344858

10.1002/da.22731

10.7326/M13-2946

10.1073/pnas.1804597116

10.1038/s41467-018-07619-7

10.1016/j.scitotenv.2018.11.022

10.1038/s41467-018-04316-3

10.1002/gepi.20307

10.1038/s41467-018-04243-3

10.1111/2041-210X.12232

10.1016/j.media.2017.12.009

10.1002/sim.7623

R. Soc. (G. B.), 2017, Machine learning: the power and promise of computers that learn by example

10.1146/annurev-publhealth-040617-014158

10.1109/34.75512

10.1145/2939672.2939778

10.1038/sc.2017.38

10.1037/h0042519

10.1038/s41746-018-0045-1

10.1371/journal.pone.0118432

10.1147/rd.33.0210

10.1016/j.ssmph.2017.11.008

10.1093/aje/kwt312

10.1038/s41598-019-38491-0

10.1214/10-STS330

10.2105/AJPH.93.7.1137

Srivastava N, 2014, J. Mach. Learn. Res., 15, 1929

10.1093/bioinformatics/btr597

10.3389/fmicb.2018.00343

Tibshirani R., 1996, J. R. Stat. Soc. B, 58, 267, 10.1111/j.2517-6161.1996.tb02080.x

10.1016/j.knosys.2012.11.005

10.1093/mind/LIX.236.433

10.1186/1471-2288-14-137

10.1080/01621459.2017.1319839

10.1016/j.ins.2018.09.046

Wiemken TL, Public Health Rep

10.18297/jri/vol1/iss3/10/

10.18297/jri/vol1/iss1/1/

10.18297/jri/vol3/iss1/1

Thông tin
Thông tin xuất bản

Annual Review of Public Health

Tập 41 Số 1

21-36

Thông tin tác giả