Validity of Diagnostic Support Model for Attention Deficit Hyperactivity Disorder: A Machine Learning Approach.

An accurate and early diagnosis of attention deficit hyperactivity disorder can improve health outcomes and prevent unnecessary medical expenses. This study developed a diagnostic support model using a machine learning approach to effectively screen individuals for attention deficit hyperactivity disorder. Three models were developed: a logistic regression model, a classification and regression tree (CART), and a neural network. The models were assessed by using a receiver operating characteristic analysis. In total, 74 participants were enrolled into the disorder group, while 21 participants were enrolled in the control group. The sensitivity and specificity of each model, indicating the rate of true positive and true negative results, respectively, were assessed. The CART model demonstrated a superior performance compared to the other two models, with region values of receiver operating characteristic analyses in the following order: CART (0.848) > logistic regression model (0.826) > neural network (0.67). The sensitivity and specificity of the CART model were 78.8% and 50%, respectively. This model can be applied to other neuroscience research fields, including the diagnoses of autism spectrum disorder, Tourette syndrome, and dementia. This will enhance the effect and practical value of our research.

Reliability and validity of DS-ADHD: A decision support system on attention deficit hyperactivity disorders.

BACKGROUND AND OBJECTIVES: The purpose of this study is to examine the reliability of the clinical use of the self-built decision support system, diagnosis-supported attention deficit hyperactivity disorder (DS-ADHD), in an effort to develop the DS-ADHD system, by probing into the development of indicating patterns of past screening support systems for ADHD. METHODS: The study collected data based on 107 subjects, who were divided into two groups, non-ADHD and ADHD, based on the doctor's determination, using the DSM-IV diagnostic standards. The two groups then underwent Test of Variables of Attention (TOVA) and DS-ADHD testing. The survey and testing results underwent one-way ANOVA and split-half method statistical analysis, in order to further understand whether there were any differences between the DS-ADHD and the identification tools used in today's clinical trials. RESULTS: The results of the study are as follows: 1) The ROC area between the TOVA and the clinical identification rate is 0.787 (95% confidence interval: 0.701-0.872); 2) The ROC area between the DS-ADHD and the clinical identification rate is 0.867 (95% confidence interval: 0.801-0.933). CONCLUSIONS: The study results show that DS-ADHD has the characteristics of screening for ADHD, based on its reliability and validity. It does not display any statistical differences when compared with TOVA systems that are currently on the market. However, the system is more effective and the accuracy rate is better than TOVA. It is a good tool to screen ADHD not only in Chinese children, but also in western country.