Skip to main page content
Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
, 7 (8), e43855

Use of Artificial Intelligence to Shorten the Behavioral Diagnosis of Autism


Use of Artificial Intelligence to Shorten the Behavioral Diagnosis of Autism

Dennis P Wall et al. PLoS One.


The Autism Diagnostic Interview-Revised (ADI-R) is one of the most commonly used instruments for assisting in the behavioral diagnosis of autism. The exam consists of 93 questions that must be answered by a care provider within a focused session that often spans 2.5 hours. We used machine learning techniques to study the complete sets of answers to the ADI-R available at the Autism Genetic Research Exchange (AGRE) for 891 individuals diagnosed with autism and 75 individuals who did not meet the criteria for an autism diagnosis. Our analysis showed that 7 of the 93 items contained in the ADI-R were sufficient to classify autism with 99.9% statistical accuracy. We further tested the accuracy of this 7-question classifier against complete sets of answers from two independent sources, a collection of 1654 individuals with autism from the Simons Foundation and a collection of 322 individuals with autism from the Boston Autism Consortium. In both cases, our classifier performed with nearly 100% statistical accuracy, properly categorizing all but one of the individuals from these two resources who previously had been diagnosed with autism through the standard ADI-R. Our ability to measure specificity was limited by the small numbers of non-spectrum cases in the research data used, however, both real and simulated data demonstrated a range in specificity from 99% to 93.8%. With incidence rates rising, the capacity to diagnose autism quickly and effectively requires careful design of behavioral assessment methods. Ours is an initial attempt to retrospectively analyze large data repositories to derive an accurate, but significantly abbreviated approach that may be used for rapid detection and clinical prioritization of individuals likely to have an autism spectrum disorder. Such a tool could assist in streamlining the clinical diagnostic process overall, leading to faster screening and earlier treatment of individuals with autism.

Conflict of interest statement

Competing Interests: The authors have declared that no competing interests exist.


Figure 1
Figure 1. Performance of 15 machine learning algorithms evaluated for classifying autism cases and non-spectrum controls.
Plot comparing 1-specificity and sensitivity for the 15 different machine learning algorithms used to construct classifiers from the 93-item Autism Diagnostic Interview-Revised (ADI-R) instrument from the Autism Genetic Resource Exchange (AGRE). The best performing algorithm was the alternating decision tree (ADTree), followed by LADTree, PART, and FilteredClassifier. Table 2 summarizes the 15 machine learning algorithms in more detail, and the elements contained in the ADTree classifier are listed in Table 3.
Figure 2
Figure 2. Decision tree scores and classification of cases with and without a diagnosis of autism.
The Alternating Decision Tree (ADTree) scores of individuals in the both the AC and AGRE data sets versus their age in years. A majority of the ADTree scores were clustered towards greater magnitudes according to their respective classifications, regardless of age.

Similar articles

See all similar articles

Cited by 19 PubMed Central articles

See all "Cited by" articles


    1. Bailey A, Le Couteur A, Gottesman I, Bolton P, Simonoff E, et al. (1995) Autism as a strongly genetic disorder: evidence from a British twin study. Psychol Med 25: 63–77. - PubMed
    1. Lord C, Rutter M, Le Couteur A (1994) Autism Diagnostic Interview-Revised: a revised version of a diagnostic interview for caregivers of individuals with possible pervasive developmental disorders. J Autism Dev Disord 24: 659–685. - PubMed
    1. Cicchetti DV, Lord C, Koenig K, Klin A, Volkmar FR (2008) Reliability of the ADI-R: multiple examiners evaluate a single case. J Autism Dev Disord 38: 764–770. - PubMed
    1. Poustka F, Lisch S, Ruhl D, Sacher A, Schmotzer G, et al. (1996) The standardized diagnosis of autism, Autism Diagnostic Interview-Revised: interrater reliability of the German form of the interview. Psychopathology 29: 145–153. - PubMed
    1. Hill A, Bolte S, Petrova G, Beltcheva D, Tacheva S, et al. (2001) Stability and interpersonal agreement of the interview-based diagnosis of autism. Psychopathology 34: 187–191. - PubMed

Publication types

LinkOut - more resources