Identification of the most indicative and discriminative features from diagnostic instruments for children with autism. Issue 2 (2nd July 2021)

• Record Type: Journal Article
• Authors: Stroth, Sanna; Tauscher, Johannes; Wolff, Nicole; Küpper, Charlotte; Poustka, Luise; Roepke, Stefan; Roessner, Veit; Heider, Dominik; Kamp‐Becker, Inge
• Is Part Of: JCPP advances. Volume 1:Issue 2(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2021-07-02
• Subjects: ADI‐R -- ADOS -- autism spectrum disorder -- diagnostic‐gold‐standard -- differential‐diagnosis -- machine learning; Child psychiatry -- Periodicals; Child psychology -- Periodicals; Adolescent psychiatry -- Periodicals; Adolescent psychology -- Periodicals; 618.9289
• DOI: 10.1002/jcv2.12023
• Languages: English
• ISSNs: 2692-9384

Abstract

Abstract: Background: Diagnosing autism spectrum disorder (ASD) is complex and time‐consuming. The present work systematically examines the importance of items from the Autism Diagnostic Interview‐Revised (ADI‐R) and Autism Diagnostic Observation Schedule (ADOS) in discerning children with and without ASD. Knowledge of the most discriminative features and their underlying concepts may prove valuable for the future training tools that assist clinicians to substantiate or extenuate a suspicion of ASD in nonverbal and minimally verbal children. Methods: In two samples of nonverbal ( N = 466) and minimally verbal ( N = 566) children with ASD ( N = 509) and other mental disorders or developmental delays ( N = 523), we applied random forests (RFs) to (i) the combination of ADI‐R and ADOS data versus (ii) ADOS data alone. We compared the predictive performance of reduced feature models against outcomes provided by models containing all features. Results: For nonverbal children, the RF classifier indicated social orientation to be most powerful in differentiating ASD from non‐ASD cases. In minimally verbal children, we find language/speech peculiarities in combination with facial/nonverbal expressions and reciprocity to be most distinctive. Conclusion: Based on machine learning strategies, we carve out those symptoms of ASD that prove to be central for the differentiation of ASD cases from those with other developmental or mental disorders (high specificity in minimally verbal children). These core concepts ought to be considered in the future training tools for clinicians.