Application of a Bayesian Network Learning Model to Predict Longitudinal Trajectories of Executive Function Difficulties in Elementary School Students

Abstract

Executive function is the mental ability to modulate behavior or thinking to accomplish a task. This is developmentally important for children's academic achievements and ability to adjust to school. We classified executive function difficulties (EFDs) in longitudinal trajectories in Korean children from 7 to 10 years old. We found predictors of EFDs using latent class growth analysis and Bayesian network learning methods with Panel Study data. Three types of latent class models of executive function difficulties were identified: low, intermediate, and high EFDs. The modeling performance of the high EFD group was excellent (AUC = .91), and the predictors were the child's gender, temperamental emotionality, happiness, DSM (Diagnostic and Statistical Manual of Mental Disorders) anxiety problems, and the mother's depression as well as coparenting conflict recognized by the mother. The results show that using latent class growth analysis and Bayesian network learning are helpful in classifying the longitudinal EFD patterns in elementary school students. Furthermore, school-age EFD is affected by emotional problems in parents and children that continue from early life. These findings can support children's development and prevent risk by preclassifying children who may experience persistent EFD and tracing causes.

Keywords: Bayesian network learning; elementary school students; executive function difficulties.

Figure 1

Schematic view of the methodology. (A) As a sample selection step, samples with no missing EF longitudinal data and predictors were selected for four years, after which samples with missing values were removed. (B) The longitudinal latent layer of EF was confirmed using the lcmm package. The pink line is class 1, the green line is class 2, and the blue line is class 3. (C) Using the BNL algorithm with the bnlearn and bootnet package, probabilistic prediction models for classifying EF latent layers were developed, and the performances of the classification models were compared and analyzed. The red circles are the Effect nodes (C_EFPT) of model 4 (threshold = .85) and the yellow circles are the parent nodes (C_GEND, C_5TS2, C_8HPY, C_8BC10, M_8DPR, M_8CR7).

Figure 2

The mean and 95CI in EFD trajectory. For each wave 8–11 period, the mean of the EFD of the three latent layers and the confidence interval (Bootstrapping = 1000, 95% CI) by Bootstrapping are graphed. At all times, the mean of class 1 is the smallest, and the mean of class 3 is the largest.

Figure 3

Differences of predictor’s z-values between EFD trajectory patterns.

Figure 4

Spearman’s rank correlation analysis. When the risk of children’s EFD is taken as the ordinal variable, the larger the circle, the greater the probability of rejecting the null hypothesis of the rank correlation. The darker the blue, the greater the positive correlation, and the darker the red, the greater the negative correlation.

Figure 5

ROC curve. In the Bayesian network approach, the predictive performance (threshold = .85) of Model 3 and 4 are excellent and Model 2 is good.

Figure 6

Class 1+2: Class 3 (threshold = .85). Bayesian network structure. Each node is a factor. The final effect node (red) in this study is a label indicating the type of EFD of each learning model (Bootstrapping = 2000). The red circles are the Effect nodes (C_EFPT) of model 4 (threshold = .85) and the yellow circles are the parent nodes (C_GEND, C_5TS2, C_8HPY, C_8BC10, M_8DPR, M_8CR7).

Figure 7

The relative importance of input variables. Assuming that the contribution of the variable with the highest contribution to the prediction is 100, the contribution of the remaining variables is expressed as a relative ratio.