Clinical Evaluation of a Novel and Mobile Autism Risk Assessment

Abstract

The Mobile Autism Risk Assessment (MARA) is a new, electronically administered, 7-question autism spectrum disorder (ASD) screen to triage those at highest risk for ASD. Children 16 months–17 years (N = 222) were screened during their first visit in a developmental-behavioral pediatric clinic. MARA scores were compared to diagnosis from the clinical encounter. Participant median age was 5.8 years, 76.1 % were male, and most participants had an intelligence/developmental quotient score >85; 69 of the participants (31 %) received a clinical diagnosis of ASD. The sensitivity of the MARA in detecting ASD was 89.9 % [95 % CI = 82.7–97]; the specificity was 79.7 % [95 % CI = 73.4–86.1]. In a high-risk clinical setting, the MARA shows promise as a screen to distinguish ASD from other developmental/behavioral disorders.

Applications of Supervised Machine Learning in Autism Spectrum Disorder Research: a Review

“…The seven-item ADI-R classifier has also undergone further evaluation by Duda et al (2016a). In this study, a mobile application, the Mobile Autism Risk Assessment (MARA), was used to administer the ADI-R questionnaire.…”

Machine learning approach for early detection of autism by combining questionnaire and home video screening

“…Cognoa 6 provides a data driven alternative screening method powered by machine learning and validated by multiple clinical studies 7,8 . To date, Cognoa has been used by over 150,000 parents in the US and internationally using web and native smartphone mobile app tools.…”

Screening in toddlers and preschoolers at risk for autism spectrum disorder: Evaluating a novel mobile‐health screening tool

“…The questionnaire was validated in a sample of 222 subjects averaging 5.8 years of age who had presented to a diagnostic center. The sensitivity and specificity estimates for ASD in this study were 0.90 and 0.80 respectively [Duda et al, ].…”

“…This narrowband, Level 1 screening tool has a two‐phase approach to help identify whether a child falls into an at‐risk category for developmental delays. Extant research has documented the algorithm development and initial clinical validation of the Cognoa measure [e.g., Duda, Daniels, & Wall, ; Kosmicki, Sochat, Duda, & Wall, ; Wall, Kosmicki, Deluca, Harstad, & Fusaro, ]. A more comprehensive methodological description is included below given the novelty of the tool.…”