Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Apr 8;3(4):100482.
doi: 10.1016/j.patter.2022.100482. Epub 2022 Mar 9.

Using machine learning to identify important predictors of COVID-19 infection prevention behaviors during the early phase of the pandemic

Caspar J Van Lissa  1   2 Wolfgang Stroebe  3 Michelle R vanDellen  4 N Pontus Leander  3   5 Maximilian Agostini  3 Tim Draws  6 Andrii Grygoryshyn  7 Ben Gützgow  3 Jannis Kreienkamp  3 Clara S Vetter  7 Georgios Abakoumkin  8 Jamilah Hanum Abdul Khaiyom  9 Vjolica Ahmedi  10 Handan Akkas  11 Carlos A Almenara  12 Mohsin Atta  13 Sabahat Cigdem Bagci  14 Sima Basel  15 Edona Berisha Kida  10 Allan B I Bernardo  16 Nicholas R Buttrick  17 Phatthanakit Chobthamkit  18 Hoon-Seok Choi  19 Mioara Cristea  20 Sára Csaba  21 Kaja Damnjanović  22 Ivan Danyliuk  23 Arobindu Dash  24 Daniela Di Santo  25 Karen M Douglas  26 Violeta Enea  27 Daiane Gracieli Faller  15 Gavan J Fitzsimons  28 Alexandra Gheorghiu  27 Ángel Gómez  29 Ali Hamaidia  30 Qing Han  31 Mai Helmy  32   33 Joevarian Hudiyana  34 Bertus F Jeronimus  3 Ding-Yu Jiang  35 Veljko Jovanović  36 Željka Kamenov  37 Anna Kende  21 Shian-Ling Keng  38 Tra Thi Thanh Kieu  39 Yasin Koc  3 Kamila Kovyazina  40 Inna Kozytska  23 Joshua Krause  3 Arie W Kruglanksi  41 Anton Kurapov  42 Maja Kutlaca  43 Nóra Anna Lantos  21 Edward P Lemay Jr  41 Cokorda Bagus Jaya Lesmana  43 Winnifred R Louis  44 Adrian Lueders  45 Najma Iqbal Malik  13 Anton P Martinez  46 Kira O McCabe  47 Jasmina Mehulić  37 Mirra Noor Milla  34 Idris Mohammed  48 Erica Molinario  49 Manuel Moyano  50 Hayat Muhammad  51 Silvana Mula  25 Hamdi Muluk  33 Solomiia Myroniuk  3 Reza Najafi  52 Claudia F Nisa  15 Boglárka Nyúl  21 Paul A O'Keefe  53 Jose Javier Olivas Osuna  29 Evgeny N Osin  54 Joonha Park  55 Gennaro Pica  56 Antonio Pierro  25 Jonas H Rees  57 Anne Margit Reitsema  3 Elena Resta  25 Marika Rullo  58 Michelle K Ryan  3   59 Adil Samekin  60 Pekka Santtila  61 Edyta M Sasin  15 Birga M Schumpe  7 Heyla A Selim  62 Michael Vicente Stanton  63 Samiah Sultana  3 Robbie M Sutton  26 Eleftheria Tseliou  8 Akira Utsugi  64 Jolien Anne van Breen  65 Kees Van Veen  3 Alexandra Vázquez  29 Robin Wollast  43 Victoria Wai-Lan Yeung  66 Somayeh Zand  49 Iris Lav Žeželj  22 Bang Zheng  67 Andreas Zick  57 Claudia Zúñiga  68 Jocelyn J Bélanger  15
Affiliations

Using machine learning to identify important predictors of COVID-19 infection prevention behaviors during the early phase of the pandemic

Caspar J Van Lissa et al. Patterns (N Y). .

Abstract

Before vaccines for coronavirus disease 2019 (COVID-19) became available, a set of infection-prevention behaviors constituted the primary means to mitigate the virus spread. Our study aimed to identify important predictors of this set of behaviors. Whereas social and health psychological theories suggest a limited set of predictors, machine-learning analyses can identify correlates from a larger pool of candidate predictors. We used random forests to rank 115 candidate correlates of infection-prevention behavior in 56,072 participants across 28 countries, administered in March to May 2020. The machine-learning model predicted 52% of the variance in infection-prevention behavior in a separate test sample-exceeding the performance of psychological models of health behavior. Results indicated the two most important predictors related to individual-level injunctive norms. Illustrating how data-driven methods can complement theory, some of the most important predictors were not derived from theories of health behavior-and some theoretically derived predictors were relatively unimportant.

Keywords: COVID-19; health behaviors; machine learning; public goods dilemma; random forest; social norms.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1
Machine-learning results for self-reported personal infection-prevention behavior Variables ranked in order of relative importance.
Figure 2
Figure 2
Partial-dependence plots depicting bivariate associations between each variable and infection-prevention behaviors

References

    1. Omeife H.O. Coronavirus: distancing and handwashing could lower flu rates, too. MedicalXpress. 2020 https://medicalxpress.com/news/2020-04-coronavirus-distancing-handwashin...
    1. Van Lissa C.J. CRAN; 2018. Metaforest: Exploring Heterogeneity in Meta-Analysis Using Random Forests (0.1.2) [R-Package] https://cran.r-project.org/package=metaforest.
    1. Aw J., Seng J.J.B., Seah S.S.Y., Low L.L. COVID-19 vaccine hesitancy – a scoping review of the literature in high-income countries. Vaccines. 2021;9:900. doi: 10.3390/vaccines9080900. - DOI - PMC - PubMed
    1. Wang Q., Yang L., Jin H., Lin L. Vaccination against COVID-19: a systematic review and meta-analysis of acceptability and its predictors. Prev. Med. 2021;150:106694. - PMC - PubMed
    1. Hastie T., Tibshirani R., Friedman J. Springer; 2009. The Elements of Statistical Learning: Data Mining, Inference, and Prediction.