Extreme Heat And Mental Health-Related Outcomes In Adolescent Populations: A Machine Learning Approach
- ASU Author/Contributor (non-ASU co-authors, if there are any, appear on document)
- Luke Wertis (Creator)
- Institution
- Appalachian State University (ASU )
- Web Site: https://library.appstate.edu/
- Advisor
- Margaret Sugg
Abstract: There is growing evidence indicating that extreme environmental conditions in summer months have an adverse impact on mental and behavioral disorders (MBD), but there is limited research looking at adolescent populations. The objective of this study was to apply a machine learning approach to identify key environmental conditions that predicted MBD-related emergency room (ER) visits in adolescents in select cities (i.e., Asheville, Charlotte, Greenville, Hickory, Raleigh, Wilingminton) in North Carolina. Daily MBD-related ER visits, which totaled over 42,000 records were paired with daily environmental conditions, including hot ambient temperatures, as well as sociodemographic variables to determine if certain environmental conditions lead to higher vulnerability to exacerbated mental health conditions. Four machine learning models (i.e., generalized linear model, generalized additive model, extreme gradient boosting, random forest) and a distributed lag non-linear model (DLNM) were used to assess the impact of multiple environmental and sociodemographic variables had on MBD-related ER visits. The best-performing machine learning model, determined by root-mean-squared error (RMSE) and mean absolute error (MAE) values, from the all-cities scenario, and a DLNM was then applied to each of the six individual cities. In the all-cities scenario, sociodemographic variables contributed the greatest to the overall MBD prediction. In the individual cities scenario, four cities had a 24-hour difference in the maximum temperature, and two of the cities had a 24-hour difference in the minimum temperature, maximum temperature, or NDVI as a leading predictor of MBD emergency department visits. Results from this study can provide new guidance on the application of machine learning models for predicting mental health conditions during high-temperature events, as well as help inform what variables contribute to youth mental and behavioral response during high-temperature events.
Extreme Heat And Mental Health-Related Outcomes In Adolescent Populations: A Machine Learning Approach
PDF (Portable Document Format)
1157 KB
Created on 8/7/2023
Views: 524
Additional Information
- Publication
- Thesis
- Wertis, L. (2023). Extreme Heat And Mental Health-Related Outcomes In Adolescent Populations: A Machine Learning Approach. Unpublished Master’s Thesis. Appalachian State University, Boone, NC.
- Language: English
- Date: 2023
- Keywords
- Machine Learning, Mental and Behavioral Disorders, Distributed Lag Non-Linear Model, Adolescents