Psychometric properties of the Mandarin version of the autism diagnostic observation Schedule-Generic.

BACKGROUND/PURPOSE: The diagnosis of autism spectrum disorder (ASD), involving multiple components of clinical assessments, is challenging. The Autism Diagnostic Observation Schedule-Generic (ADOS-G), one of the standardized and validated instruments for ASD diagnostic evaluation, has been widely used in many countries. With the preparation of the Mandarin version of the ADOS-G (Mandarin-ADOS-G), this study aims to examine its psychometric properties, including reliability and validity. METHODS: The sample included 554 individuals clinically diagnosed with ASD (477 males, 86.1%) and 50 typically developing (TD) individuals (29 males, 58.0%) who were assessed with different modules of the Mandarin-ADOS-G between 4.1 and 34.0 years old with a mean age of 13.0 years (Module 1, n = 40; Module 2, n = 46; Module 3, n = 275; Module 4, n = 243). We evaluated the inter-rater reliability, test-retest reliability, internal consistency, and concurrent validity with the Chinese Autism Diagnostic Interview-Revised (ADI-R) and Social Responsiveness Scale (SRS) caregiver-report and self-report forms. The discriminative validity of Mandarin-ADOS-G was also examined. RESULTS: The Mandarin-ADOS-G demonstrated good inter-rater reliability (agreement of ADOS classification 0.91), good test-retest reliability (intraclass correlations 0.55-0.73), and low to high good internal consistency (Cronbach's alpha 0.27-0.86). The concurrent validity showed significant correlations with ADI-R (Pearson correlations 0.22-0.37) and the SRS caregiver-report form (Pearson correlations 0.15-0.23). Moreover, all Mandarin-ADOS-G domains successfully differentiated autistic individuals from TD individuals (all p-values <0.001). CONCLUSION: The Mandarin-ADOS-G is a reliable and valid instrument for assisting the diagnosis of ASD in the Mandarin-speaking population.

A Deep Learning Approach for Missing Data Imputation of Rating Scales Assessing Attention-Deficit Hyperactivity Disorder.

A variety of tools and methods have been used to measure behavioral symptoms of attention-deficit/hyperactivity disorder (ADHD). Missing data is a major concern in ADHD behavioral studies. This study used a deep learning method to impute missing data in ADHD rating scales and evaluated the ability of the imputed dataset (i.e., the imputed data replacing the original missing values) to distinguish youths with ADHD from youths without ADHD. The data were collected from 1220 youths, 799 of whom had an ADHD diagnosis, and 421 were typically developing (TD) youths without ADHD, recruited in Northern Taiwan. Participants were assessed using the Conners' Continuous Performance Test, the Chinese versions of the Conners' rating scale-revised: short form for parent and teacher reports, and the Swanson, Nolan, and Pelham, version IV scale for parent and teacher reports. We used deep learning, with information from the original complete dataset (referred to as the reference dataset), to perform missing data imputation and generate an imputation order according to the imputed accuracy of each question. We evaluated the effectiveness of imputation using support vector machine to classify the ADHD and TD groups in the imputed dataset. The imputed dataset can classify ADHD vs. TD up to 89% accuracy, which did not differ from the classification accuracy (89%) using the reference dataset. Most of the behaviors related to oppositional behaviors rated by teachers and hyperactivity/impulsivity rated by both parents and teachers showed high discriminatory accuracy to distinguish ADHD from non-ADHD. Our findings support a deep learning solution for missing data imputation without introducing bias to the data.