Objective: This study leverages natural language processing techniques to identify specific practices older adults with chronic pain adopt to enhance well-being.
Method: We applied network topic modeling to open-ended survey responses from 683 adults (57% female) who reported experiencing chronic pain in the Midlife in the United States (MIDUS) study, analyzing responses to the question "What do you do to make your life go well?" Structural equation modeling was used to examine the relationships between identified topics and measures of pain interference and prescription pain medication use, adjusting for sociodemographics and well-being indicators.
Results: The analyses revealed twelve key topics, including avoiding stress, maintaining social connections, and practicing spirituality and faith. Notably, maintaining social connections was negatively associated with pain interference (β = -0.14, SE = 0.05, p < 0.05) and prescription pain medication use (β = -0.11, SE = 0.04, p < 0.05).
Conclusion: The findings demonstrate the utility of network topic modeling in identifying complex psychosocial dimensions influencing chronic pain management, providing insights into the distinct role of well-being practices in shaping pain outcomes.
Keywords: Chronic pain; natural language processing; network psychometrics; topic modeling; well-being.
© The Author(s) 2024. Published by Oxford University Press on behalf of the American Academy of Pain Medicine. All rights reserved. For permissions, please e-mail: [email protected].