CONTACT US: Contact info
|
Citation |
Shukla M, Amberson T, Heagele T, McNeill C, Adams L, Ndayishimiye K, Castner J. Int. J. Environ. Res. Public Health 2024; 21(5): e521. |
|
Copyright |
(Copyright © 2024, MDPI: Multidisciplinary Digital Publishing Institute) |
|
DOI |
|
PMID |
38791736 |
|
Abstract |
Tailored disaster preparedness interventions may be more effective and equitable, yet little is known about specific factors associated with disaster household preparedness for older adults and/or those with African American/Black identities. This study aims to ascertain differences in the importance features of machine learning models of household disaster preparedness for four groups to inform culturally tailored intervention recommendations for nursing practice. A machine learning model was developed and tested by combining data from the 2018, 2019, and 2020 Federal Emergency Management Agency National Household Survey. The primary outcome variable was a composite readiness score. A total of 252 variables from 15,048 participants were included. Over 10% of the sample self-identified as African American/Black and 30.3% reported being 65 years of age or older. Importance features varied regarding financial and insurance preparedness, information seeking and transportation between groups. These results reiterate the need for targeted interventions to support financial resilience and equitable resource access. Notably, older adults with Black racial identities were the only group where TV, TV news, and the Weather Channel was a priority feature for household disaster preparedness. Additionally, reliance on public transportation was most important among older adults with Black racial identities, highlighting priority needs for equity in disaster preparedness and policy. Language: en |
|
Keywords |
*Disaster Planning; *Machine Learning; Adolescent; Adult; Aged; Black or African American/statistics & numerical data; Civil Defense/statistics & numerical data; disaster preparedness; disasters; Family Characteristics; Female; health disparities; Health Status Disparities; Humans; machine learning; Male; Middle Aged; Surveys and Questionnaires; United States; Young Adult |