A Machine Learning Strategy for Autism Screening in Toddlers.

OBJECTIVE Autism spectrum disorder (ASD) screening can improve prognosis via early diagnosis and intervention, but lack of time and training can deter pediatric screening. The Modified Checklist for Autism in Toddlers, Revised (M-CHAT-R) is a widely used screener but requires follow-up questions and error-prone human scoring and interpretation. We consider an automated machine learning (ML) method for overcoming barriers to ASD screening, specifically using the feedforward neural network (fNN). METHODS The fNN technique was applied using archival M-CHAT-R data of 14,995 toddlers (age 16-30 months, 46.51% male). The 20 M-CHAT-R items were inputs, and ASD diagnosis after follow-up and diagnostic evaluation (i.e., ASD or not ASD) was the output. The sample was divided into subgroups by race (i.e., white and black), sex (i.e., boys and girls), and maternal education (i.e., below and above 15 years of education completed) to examine subgroup differences. Each subgroup was evaluated for best-performing fNN models. RESULTS For the total sample, best results yielded 99.72% correct classification using 18 items. Best results yielded 99.92% correct classification using 14 items for white toddlers and 99.79% correct classification using 18 items for black toddlers. In boys, best results yielded 99.64% correct classification using 18 items, whereas best results yielded 99.95% correct classification using 18 items in girls. For the case when maternal education is 15 years or less (i.e., associate degree and below), best results were 99.75% correct classification when using 16 items. Results were essentially the same when maternal education was 16 years or more (i.e., above associate degree); that is, 99.70% correct classification was obtained using 16 items. CONCLUSION The ML method was comparable to the M-CHAT-R with follow-up items in accuracy of ASD diagnosis while using fewer items. Therefore, ML may be a beneficial tool in implementing automatic, efficient scoring that negates the need for labor-intensive follow-up and circumvents human error, providing an advantage over previous screening methods.

[1]  J. Nackashi.  Medical Home Initiatives for Children With Special Needs Project Advisory Committee , 2016, Pediatric Clinical Practice Guidelines & Policies.

[2]  M. Weinstein,et al.  Economic Burden of Childhood Autism Spectrum Disorders , 2012, Pediatrics.

[3]  C. Newschaffer,et al.  Autism Spectrum Disorder Screening and Management Practices Among General Pediatric Providers , 2006, Journal of developmental and behavioral pediatrics : JDBP.

[4]  Z. Warren,et al.  Prevalence of Autism Spectrum Disorder Among Children Aged 8 Years — Autism and Developmental Disabilities Monitoring Network, 11 Sites, United States, 2016 , 2020, Morbidity and mortality weekly report. Surveillance summaries.

[5]  Letitia R. Naigles,et al.  Intervention for Optimal Outcome in Children and Adolescents with a History of Autism , 2014, Journal of developmental and behavioral pediatrics : JDBP.

[6]  Cynthia D. Zubritsky,et al.  Factors Associated With Age of Diagnosis Among Children With Autism Spectrum Disorders , 2005, Pediatrics.

[7]  Geraldine Dawson,et al.  Approaches to enhancing the early detection of autism spectrum disorders: a systematic review of the literature. , 2014, Journal of the American Academy of Child and Adolescent Psychiatry.

[8]  M. J. Morrier,et al.  Ethnic Disproportionality in Students with Autism Spectrum Disorders. , 2008 .

[9]  A. Fenick,et al.  Developmental and Autism Screening: A Survey Across Six States , 2012 .

[10]  J. Pinto-Martin,et al.  Developmental stages of developmental screening: steps to implementation of a successful program. , 2005, American journal of public health.

[11]  J. Baio,et al.  Prevalence of Autism Spectrum Disorders: Autism and Developmental Disabilities Monitoring Network, United States, 2006. Morbidity and Mortality Weekly Report. Surveillance Summaries. Volume 58, Number SS-10. , 2009 .

[12]  Diana L. Robins,et al.  Large-Scale Use of the Modified Checklist for Autism in Low-Risk Toddlers , 2013, Pediatrics.

[13]  A. Scarpa,et al.  The Modified Checklist for Autism in Toddlers: Reliability in a Diverse Rural American Sample , 2013, Journal of Autism and Developmental Disorders.

[14]  C. Johnson,et al.  Identification and Evaluation of Children With Autism Spectrum Disorders , 2007, Pediatrics.

[15]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[16]  J. Baio.  Prevalence of autism spectrum disorders--Autism and Developmental Disabilities Monitoring Network, 14 sites, United States, 2008. , 2012, Morbidity and mortality weekly report. Surveillance summaries.

[17]  A. Scarpa,et al.  The importance of physician knowledge of autism spectrum disorder: results of a parent survey , 2007, BMC pediatrics.

[18]  D. Robins,et al.  Validation of the Modified Checklist for Autism in Toddlers, Revised With Follow-up (M-CHAT-R/F) , 2014, Pediatrics.

[19]  J. Listerud,et al.  Race differences in the age at diagnosis among medicaid-eligible children with autism. , 2002, Journal of the American Academy of Child and Adolescent Psychiatry.