Machine learning-based prediction of persistent oppositional defiant behavior for 5 years

Abstract

Background

Early detection of oppositional defiant behavior is warranted for timely intervention in children at risk. This study aimed to build a predictive model of persistent oppositional defiant behavior based on a machine learning algorithm.

Methods

With nationwide cohort data collected from 2012 to 2017, a tree-based ensemble model, random forest, was exploited to build a predictive model for persistent oppositional defiant behavior. The persistent oppositional defiant behavior was defined by the presence of oppositional defiant behavior for all the five years. The area under the receiver operating characteristic curve (AUC), overall accuracy, sensitivity, specificity, and Matthew’s correlation coefficients (MCC) were measured.

Results

Data of 1,323 children were used for building the machine learning-based predictive model. The baseline mean ± standard deviation month-age of the participants was 51.0 ± 1.2 months. The proportion of persistent oppositional defiant behavior was 0.98% (13/1323). In the hold-out test set, the overall accuracy, AUC, sensitivity, specificity, and MCC were 0.955, 0.982, 1.000, 0.954, and 0.417, respectively.

Conclusion

Our study demonstrated that the machine learning-based approach is useful for predicting persistent oppositional defiant behavior in preschool-aged children.

Keywords:

• Machine learning
• random forest
• oppositional defiant disorder
• externalizing behavior
• children

Disclosure statement

The authors declare that they have no conflicts of interest concerning this paper.

Additional information

Funding

This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP; Ministry of Science, ICT & Future Planning) [NRF-2017R1C1B5073684].

Notes on contributors

Kyoung-Sae Na

Kyoung-Sae Na is an Associate Professor in the Department of Psychiatry, Gachon University Gil Medical Center, Incheon, Republic of Korea. He received Ph.D. (Psychiatry) degrees from Korea University. As the first author or corresponding author, he has published about 50 research papers in SSCI/SCI/SCIE journal. His current research interests are Mood disorder, Suicide, Meta-analysis, Machine Learning, and Artificial Intelligence. He is a member of the Korean Neuropsychiatric Association and the Korean Medical Association.

Zong Woo Geem

Zong Woo Geem is an Associate Professor in the Department of Energy IT at Gachon University, South Korea. He has obtained B.Eng. in Chung-Ang University, Ph.D. in Korea University, and M.Sc. in Johns Hopkins University, and research at Virginia Tech, University of Maryland - College Park, and Johns Hopkins University. He invented a music-inspired optimization algorithm, Harmony Search, which has been applied to various scientific and engineering problems. His research interest includes phenomenon-mimicking algorithms and their applications to energy, environment, and water fields. He has served various journals as an editor (Associate Editor for Engineering Optimization; Guest Editor for Swarm & Evolutionary Computation, Int. Journal of Bio-Inspired Computation, Journal of Applied Mathematics, Applied Sciences, Complexity, and Sustainability).

Seo-Eun Cho

Seo-Eun Cho is a Clinical Associate Professor in the Department of Psychiatry, Gachon University Gil Medical Center, Incheon, Republic of Korea. She received a Master's degree in Medicine from Gachon Medical School in 2012. She obtained a License of the board-certified psychiatrist (No. 3569) in 2017. She is also working as a Research Professor, Gachon University Gil Medical Center, and Vice-Director, Incheon Counselling Center for Fertility and Depression. Her areas of current research interest are Psychoanalysis, Meta-analysis, and Machine Learning. She is a member of the Korean Neuropsychiatric Association, Korean Association of Psychoanalysis, and the Korean Medical Association.