Applying Artificial Intelligence for Diagnostic Classification of Korean Autism Spectrum Disorder

Abstract

Objective The primary objective of this study was to predict subgroups of autism spectrum disorder (ASD) based on the Diagnostic Statistical Manual for Mental Disorders-IV Text Revision (DSM-IV-TR) by machine learning (ML). The secondary objective was to set up a ranking of Autism Diagnostic Interview-Revised (ADI-R) diagnostic algorithm items based on ML, and to confirm whether ML can sufficiently predict the diagnosis with these minimum items. Methods In the first experiment, a multiclass decision forest algorithm was applied, and the diagnostic algorithm score value of 1,269 Korean ADI-R test data was used for prediction. In the second experiment, we used 539 Korean ADI-R case data (over 48 months with verbal language) to apply mutual information to rank items used in the ADI diagnostic algorithm. Results In the first experiment, the results of predicting in the case of pervasive developmental disorder not otherwise specified as "ASD" were almost three times higher than predicting it as "No diagnosis. " In the second experiment, the top 10 ranking items of ADI-R were mainly related to the quality abnormality of communication. Conclusion In conclusion, we verified the applicability of ML in diagnosis and found that the application of artificial intelligence for rapid diagnosis or screening of ASD patients may be useful.

Application of artificial intelligence tools in diagnosis and treatmentof mental disorders

“…The authors obtained an average accuracy prediction score of 75% [28]. The usefulness of applying artificial intelligence techniques to diagnose autism spectrum disorders was also highlighted by Choi et al, who analyzed patients to predict the development of ASD with an average accuracy of 96.3% [29]. Wall et al [30] applied machine learning algorithms with data collected from multiple databases of information on ASD, including the Autism Genetic Resource Exchange (AGRE) and the Autism Consortium (AC).…”

“…Autorzy uzyskali średni wynik prognozowania o dokładności 75% [28]. Przydatność stosowania technik sztucznej inteligencji do diagnostyki zaburzeń ze spektrum autyzmu podkreślili również Choi i in., którzy dokonali analizy pacjentów w celu przewidzenia rozwoju ASD ze średnią dokładnością 96,3% [29]. Wall i in.…”

The Promises and Possibilities of Artificial Intelligence in the Delivery of Behavior Analytic Services

“…More directly in the behavioral health realm and specific to many practicing behavior analysts, researchers have begun to develop AI-based tools to diagnose ASD (e.g., Erden et al, 2021;Song et al, 2019). To reduce assessment time, machine learning has been used to identify which assessment questions are the greatest predictors of ASD (e.g., Choi et al, 2020;Kosmicki et al, 2015). In turn, shorter assessment durations may increase the rate at which assessments can be completed and increase overall access to care.…”