OBJECTIVES: The detection of autism spectrum disorder (ASD) is based on behavioral observations. To build a more objective data-driven method for screening and diagnosing ASD, many studies have attempted to incorporate artificial intelligence (AI) technologies. Therefore, the purpose of this literature review is to summarize the studies that used AI in the assessment process and examine whether other behavioral data could potentially be used to distinguish ASD characteristics. METHODS: Based on our search and exclusion criteria, we reviewed 13 studies. RESULTS: To improve the accuracy of outcomes, AI algorithms have been used to identify items in assessment instruments that are most predictive of ASD. Creating a smaller subset and therefore reducing the lengthy evaluation process, studies have tested the efficiency of identifying individuals with ASD from those without. Other studies have examined the feasibility of using other behavioral observational features as potential supportive data. CONCLUSION: While previous studies have shown high accuracy, sensitivity, and specificity in classifying ASD and non-ASD individuals, there remain many challenges regarding feasibility in the real-world that need to be resolved before AI methods can be fully integrated into the healthcare system as clinical decision support systems.
Artificial Intelligence ; Autism Spectrum Disorder ; Autistic Disorder ; Behavior Observation Techniques ; Decision Support Systems, Clinical ; Delivery of Health Care ; Diagnosis ; Mass Screening ; Methods ; Sensitivity and Specificity

OBJECTIVE: To explore the methods to detect and intervene children's late-onset hearing loss early which are suitable for basic-level hospitals. METHOD: Udiology and imaging diagnosis had been given to the children who passed the newborn hearing screening but showed auditory behavior disorders in the growth process, and individualized interventions were given according to the results of diagnosis. Seven children with high risk for hereditary deafness were sent to superior hospital and had molecular screening of common mutations of inherited deafness carried out, then corresponding prevention guidance and intervention were given to them. RESULT: Fifty-two cases with late-onset hearing loss or verbal disorders were detected by auditory behavior observations,including 4 cases of auditory neuropathy, 4 cases of unilateral sensorineural deafness, 27 cases of secretory otitis media. 13 cases of bilateral sensorineural deafness and 4 cases of autism. Seven newborns with high risk of hereditary deafness were sent to the Third Affiliated Hospital of Sun Yat-Sen University and received molecular screening of common mutations of inherited deafness. One case with GJB2 compound heterozygous mutations was detected and followed up to 4 years old, he was found bilateral moderate hearing loss and accepted the hearing aids at 2 years old. Mitochondrial DNA 1555 a > G heterogeneity mutation in 2 cases and GJB2 235 delC single heterozygous mutations in 3 cases, no mutation in 1 case, all these 6 cases have been followed-up until now, their hearing are normal. CONCLUSION Children's auditory behavior observations and the superior hospitals referral performing high risk individual screening for newborns with high risk for hereditary deafness can detect children's late-onset hearing loss in time, this model is suitable for basic-level hospitals.
Behavior Observation Techniques ; Child ; Connexin 26 ; Connexins ; genetics ; DNA Mutational Analysis ; DNA, Mitochondrial ; genetics ; Deafness ; diagnosis ; genetics ; Early Diagnosis ; Genetic Testing ; Hearing Tests ; Heterozygote ; Humans ; Infant, Newborn ; Male ; Mutation