Using a Cloud-Based Machine Learning Classification Tree Analysis to Understand the Demographic Characteristics Associated With COVID-19 Booster Vaccination Among Adults in the United States

Lu Meng; Hannah E Fast; Ryan Saelee; Elizabeth Zell; Bhavini Patel Murthy; Neil Chandra Murthy; Peng-Jun Lu; Lauren Shaw; LaTreace Harris; Lynn Gibbs-Scharf; Terence Chorba

doi:10.1093/ofid/ofac446

Using a Cloud-Based Machine Learning Classification Tree Analysis to Understand the Demographic Characteristics Associated With COVID-19 Booster Vaccination Among Adults in the United States

Open Forum Infect Dis. 2022 Sep 1;9(9):ofac446. doi: 10.1093/ofid/ofac446. eCollection 2022 Sep.

Authors

Lu Meng^{1

2}, Hannah E Fast^{1

3}, Ryan Saelee^{1

3}, Elizabeth Zell^{1

4}, Bhavini Patel Murthy^{1

3}, Neil Chandra Murthy^{1

3}, Peng-Jun Lu^{1

3}, Lauren Shaw^{1

3}, LaTreace Harris^{1

3}, Lynn Gibbs-Scharf^{1

3}, Terence Chorba^{1

5}

Affiliations

¹ CDC COVID-19 Response Team, US Centers for Disease Control and Prevention (CDC), Atlanta, Georgia, USA.
² Federal Civilian Division, General Dynamics Information Technology, Inc., Falls Church, Virginia, USA.
³ Immunization Services Division, National Center for Immunization and Respiratory Diseases, CDC, Atlanta, Georgia, USA.
⁴ Stat-Epi Associates, Inc., Ponte Vedra Beach, Florida, USA.
⁵ Division of Tuberculosis Elimination, National Center for HIV, Viral Hepatitis, STD, and TB Prevention, CDC, Atlanta, Georgia, USA.

Abstract

A tree model identified adults age ≤34 years, Johnson & Johnson primary series recipients, people from racial/ethnic minority groups, residents of nonlarge metro areas, and those living in socially vulnerable communities in the South as less likely to be boosted. These findings can guide clinical/public health outreach toward specific subpopulations.

Keywords: COVID-19; COVID-19 vaccination; booster dose; coronavirus.

Published by Oxford University Press on behalf of Infectious Diseases Society of America 2022.