Classifying Conduct Disorder Using a Biopsychosocial Model and Machine Learning Method

Abstract

Background: Conduct disorder (CD) is a common syndrome with far-reaching effects. Risk factors for the development of CD span social, psychological, and biological domains. Researchers note that predictive models of CD are limited if the focus is on a single risk factor or even a single domain. Machine learning methods are optimized for the extraction of trends across multidomain data but have yet to be implemented in predicting the development of CD.

Methods: Social (e.g., family, income), psychological (e.g., psychiatric, neuropsychological), and biological (e.g., resting-state graph metrics) risk factors were measured using data from the baseline visit of the Adolescent Brain Cognitive Development Study when youth were 9 to 10 years old (N = 2368). Applying a feed-forward neural network machine learning method, risk factors were used to predict CD diagnoses 2 years later.

Results: A model with factors that included social, psychological, and biological domains outperformed models representing factors within any single domain, predicting the presence of a CD diagnosis with 91.18% accuracy. Within each domain, certain factors stood out in terms of their relationship to CD (social: lower parental monitoring, more aggression in the household, lower income; psychological: greater attention-deficit/hyperactivity disorder and oppositional defiant disorder symptoms, worse crystallized cognition and card sorting performance; biological: disruptions in the topology of subcortical and frontoparietal networks).

Conclusions: The development of an accurate, sensitive, and specific predictive model of CD has the potential to aid in prevention and intervention efforts. Key risk factors for CD appear best characterized as reflecting unpredictable, impulsive, deprived, and emotional external and internal contexts.

Keywords: Biopsychosocial; Conduct disorder; Family; Graph analysis; Machine learning.

Figure 1.. Network Architecture

Note. The model consists of 52 input neurons, 18 hidden neurons, and one output neuron. Line thickness is proportional to the magnitude of each weight and bias term. Black lines indicate positive parameters and grey lines indicate negative parameters.

Figure 2.. Feature Importance

Note. Features are ordered from left to right by increasing absolute value of importance. The importance values assigned to each variable are in units that are based directly on the summed product of the connection weights. The 10 most important features in the model, excluding covariates, are highlighted. Bars in the positive direction represent a positive association with a CD diagnosis, whereas bars in the negative direction represent a negative association with a CD diagnosis.

Figure 3.. Sensitivity Plots

Note. The sensitivity plots display the relationship between model predictions and the risk factors. The explanatory variable denotes risk factor values, and the response variable denotes the probability that a participant is diagnosed with CD at the two-year follow-up assessment. Panel A presents sensitivity plots for the social risk factors, Panel B presents sensitivity plots for psychological risk factors, and Panel C presents sensitivity plots for biological risk factors. The risk factors of family members throwing objects, ADHD and ODD symptomatology, and frontoparietal efficiency positively correlate with the likelihood of developing CD, while the risk factors of income, parental monitoring, crystallized cognition, card sorting ability, subcortical efficiency, and frontoparietal degree negatively correlate with the likelihood of developing CD.