Exploring the Role of Transportation on Cancer Patient Decision-Making Through Machine Learning Techniques
-
2020-08-01
-
Details:
-
Creators:
-
Corporate Creators:
-
Corporate Contributors:
-
Subject/TRT Terms:
-
Publication/ Report Number:
-
Resource Type:
-
Geographical Coverage:
-
Edition:Final Report
-
Corporate Publisher:
-
Abstract:Transportation barriers are often considered as critical factors that influence healthcare accessibility and cancer patients' decision-making regarding treatments or post-treatment process. Moreover, the built environment and lack of access to affordable and efficient transportation would significantly affect the quality of life of patients with chronic diseases such as cancer. The main goal of this study is to investigate the role of transportation in cancer patients' decision-making. Besides, this study aims to understand how built environment attributes influence the patients’ quality of life (QoL). To achieve these goals, a survey was designed and conducted, and collected data were analyzed using methods from recent advances in data science. Using structural equation models (SEMs), we explored the effects of the built environment and travel distance on tumor-free years. We found that longer travel distance to radiotherapy provider is positively associated with greater tumor-free years after radiotherapy. Furthermore, machine learning models, i.e., logistic regression, random forest, artificial neural network, and support vector machine, were employed to evaluate the contribution of travel behavior and burdens on stopping or continuing radiotherapy and chemotherapy. Results reveal that lack of access to transportation has a significant impact on cancer patients' decision to stop/continue treatment. Also, limited access to private vehicles contributes to the stopping of radiotherapy treatment. Finally, we evaluated the effects of sociodemographic attributes and health-related factors along with the residential built environment, including density, diversity, design, and distance to transit and hospitals on the self-reported QoL in cancer patients after treatment. The results from machine learning models indicated that the travel distance to the closest large hospital, perceived accessibility, distance to transit, and population density are among the most significant predictors of the cancer patients' QoL. This study also has important implications for policy interventions.
-
Format:
-
Funding:
-
Collection(s):
-
Main Document Checksum:
-
Download URL:
-
File Type: