Background: This study was to assess the validity of the Korean version of the semi-structured Diagnostic Interview for Adult ADHD, third edition (DIVA-5). The secondary aim was to compare sociodemographic and psychiatric comorbidities in adult patients with and without a diagnosis of ADHD. Methods: A total of 279 participants were recruited from nine psychiatric outpatient clinics in Korea. All participants were administered the Mini-International Neuropsychiatric Interview (MINI) Plus v.5.0.0, the Adult ADHD Self-Report Scale v1.1 (ASRS-v1.1) Symptom Checklist, and DIVA-5. Diagnosis concordance between two board-certified psychiatrists and DIVA-5 were analysed. Results: The DIVA-5 showed a diagnostic accuracy of 92%, a sensitivity of 91.30%, and a specificity of 93.62%. Significant clinical and demographic differences between ADHD and control groups were found. Conclusion: The Korean version of DIVA-5 is a reliable tool for assessing and diagnosing ADHD in adult Korean populations.

Han Nah Huh, Sung Hee Kang, Soon Young Hwang, and Hanik K. Yoo. J Korean Acad Child Adolesc Psychiatry 2019;30:66-73. https://doi.org/10.5765/jkacap.180033

Geon Ho Bahn, Young Sik Lee, Hanik K Yoo, Eui-Jung Kim, Subin Park, Doug Hyun Han, Minha Hong, Bongseog Kim, Soyoung Irene Lee, Soo Young Bhang, Seung Yup Lee, Jin Pyo Hong, and Yoo-Sook Joung. J Korean Acad Child Adolesc Psychiatry 1999;0:. https://doi.org/10.5765/jkacap.190030

Yoo HK, et al. J Korean Neuropsychiatr Assoc. 2018 Nov;57(4):332-338. https://doi.org/10.4306/jknpa.2018.57.4.332

Background: The diagnosis of attention deficit hyperactivity disorder (ADHD) relies on comprehensive approaches, including clinical interviews, scales, and neuropsychological assessments. However, the process is often limited by issues of reliability and availability.Objective: This study aims to develop a robust machine learning (ML) model using large-scale data from the Comprehensive Attention Test (CAT) to predict ADHD diagnoses.Methods: A total of 11,429 participants were recruited across South Korea and underwent the CAT. Of these, 7,737 were diagnosed with ADHD, including 6,772 with comorbid psychiatric conditions. Additionally, 850 individuals were included as a normal comparison group. Eight ML models were trained on a balanced dataset and validated using 5-fold cross-validation.Results: The CAT, when combined with the ML model, achieved an accuracy exceeding 0.98 in distinguishing pure ADHD cases from normal comparison groups. Classification accuracy was particularly high when distinguishing ADHD with comorbid externalizing disorders from normal control groups, especially in cases with more severe ADHD symptoms.Conclusion: The findings of this study suggest that the CAT, integrated with machine learning models, could serve as a promising tool for diagnosing ADHD.