Examining the use of decision trees in population health surveillance research: an application to youth mental health survey data in the COMPASS study

Abstract

Introduction In population health surveillance research, survey data are commonly analyzed using regression methods; however, these methods have limited ability to examine complex relationships. In contrast, decision tree models are ideally suited for segmenting populations and examining complex interactions among factors, and their use within health research is growing. This article provides a methodological overview of decision trees and their application to youth mental health survey data. Methods The performance of two popular decision tree techniques, the classification and regression tree (CART) and conditional inference tree (CTREE) techniques, is compared to traditional linear and logistic regression models through an application to youth mental health outcomes in the COMPASS study. Data were collected from 74 501 students across 136 schools in Canada. Anxiety, depression and psychosocial well-being outcomes were measured along with 23 sociodemographic and health behaviour predictors. Model performance was assessed using measures of prediction accuracy, parsimony and relative variable importance. Results Decision tree and regression models consistently identified the same sets of most important predictors for each outcome, indicating a general level of agreement between methods. Tree models had lower prediction accuracy but were more parsimonious and placed greater relative importance on key differentiating factors. Conclusion Decision trees provide a means of identifying high-risk subgroups to whom prevention and intervention efforts can be targeted, making them a useful tool to address research questions that cannot be answered by traditional regression methods.

Utilizing decision tree machine model to map dental students’ preferred learning styles with suitable instructional strategies

“…Through data-driven approaches and the application of decision trees supervised model, automated detection of LS was made possible. Decision tree is reported to be widely applied in learning programs in various domains including health sciences [ 18 , 19 ]. In this study, the model was trained specifically by the system developer to determine the students’ LS and recommend the best IS for it.…”

Do sociodemographic risk profiles for adolescents engaging in weekly e-cigarette, cigarette, and dual product use differ?

“…The CART algorithm divides the sample into subgroups by iteratively choosing the sociodemographic variables and cut points that provide maximum separation between groups with respect to probability of e-cigarette or dual product use. Overviews of the CART method in the context of public health are available [ 21 , 22 ]. A stable classification tree for cigarette-only use could not be constructed due to the small number of cigarette-only users.…”

Intervention Algorithm for College Students' Psychological Problems Based on Decision Tree

“…By incorporating mechanisms for ongoing monitoring and support, such as periodic check-ins, treatment plan adjustments, and relapse prevention strategies, the algorithm ensures that students receive the comprehensive care necessary for longterm success. Additionally, the algorithm remains dynamic, capable of adapting to changing circumstances or escalating concerns, thereby enabling timely and responsive intervention [15]. Crucially, the intervention algorithm incorporates robust crisis management protocols to address acute situations or emergencies effectively.…”

“…explore the use of probabilistic decision trees for predicting university students likely to experience suicidal ideation, demonstrating the application of decision tree methodologies in risk assessment and prevention efforts. Jia (2022) employs neural network optimization techniques to predict college students' psychological crises, offering a novel approach to early intervention strategies Battista et al (2023). examine the use of decision trees in population health surveillance, emphasizing their utility in identifying trends and patterns in youth mental health data.…”