Luke E K Achenie1, Angela Scarpa2,3, Reina S Factor2,3, Tao Wang4, Diana L Robins5, D Scott McCrickard6. 1. Departments of Chemical Engineering. 2. Psychology. 3. Virginia Tech Center for Autism Research, Blacksburg, VA. 4. Department of Economics, University of California, Riverside, CA. 5. A.J. Drexel Autism Institute, Drexel University, Philadelphia, PA. 6. Computer Science, Virginia Polytechnic Institute and State University, Blacksburg, VA.
Abstract
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.
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.
Authors: Jennifer A Pinto-Martin; Margaret Dunkle; Marian Earls; Dane Fliedner; Cynthia Landes Journal: Am J Public Health Date: 2005-09-29 Impact factor: 9.308
Authors: David S Mandell; John Listerud; Susan E Levy; Jennifer A Pinto-Martin Journal: J Am Acad Child Adolesc Psychiatry Date: 2002-12 Impact factor: 8.829
Authors: Felipe Yu Matsushita; Vera Lucia Jornada Krebs; Werther Brunow de Carvalho Journal: Rev Assoc Med Bras (1992) Date: 2022-06-24 Impact factor: 1.712