Author ORCID Identifier
Degree Year
2020
Document Type
Thesis - Open Access
Degree Name
Bachelor of Arts
Department
Psychology
Committee Member(s)
Nancy Darling
Adam Eck
Paul H. Thibodeau
Keywords
Chronic pain, Machine learning, Feasibility assessment
Abstract
"Chronic pain affects between 15 to 40% of adolescents worldwide. The impact and prevalence of chronic pain can be felt every day in terms of missed school days, strained familial relationships, and financial stress. While rehabilitation programs specifically designed for chronic pain management exist, they cannot always adapt to the idiosyncratic nature of chronic pain. Machine learning presents a framework to use diary data from individuals in pain and make predictions about the trajectories of their pain and related functioning. This study's goal is to assess the feasibility of using machine learning to predict pain and functioning by constructing, training, and evaluating multiple models that take a variable-centered approach to chronic pain.”
Repository Citation
Kramer, Max A., "Assessing the Feasibility of Machine Learning to Predict Chronic Pain in Adolescence" (2020). Honors Papers. 701.
https://digitalcommons.oberlin.edu/honors/701
