Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Mar 22;11(3):574.
doi: 10.3390/diagnostics11030574.

Use of Machine Learning to Investigate the Quantitative Checklist for Autism in Toddlers (Q-CHAT) towards Early Autism Screening

Gennaro Tartarisco  1 , Giovanni Cicceri  2 , Davide Di Pietro  2 , Elisa Leonardi  1 , Stefania Aiello  1 , Flavia Marino  1 , Flavia Chiarotti  3 , Antonella Gagliano  4 , Giuseppe Maurizio Arduino  5 , Fabio Apicella  6 , Filippo Muratori  6   7 , Dario Bruneo  2 , Carrie Allison  8 , Simon Baron Cohen  8 , David Vagni  1 , Giovanni Pioggia  1 , Liliana Ruta  1
Affiliations

Use of Machine Learning to Investigate the Quantitative Checklist for Autism in Toddlers (Q-CHAT) towards Early Autism Screening

Gennaro Tartarisco et al. Diagnostics (Basel). .

Abstract

In the past two decades, several screening instruments were developed to detect toddlers who may be autistic both in clinical and unselected samples. Among others, the Quantitative CHecklist for Autism in Toddlers (Q-CHAT) is a quantitative and normally distributed measure of autistic traits that demonstrates good psychometric properties in different settings and cultures. Recently, machine learning (ML) has been applied to behavioral science to improve the classification performance of autism screening and diagnostic tools, but mainly in children, adolescents, and adults. In this study, we used ML to investigate the accuracy and reliability of the Q-CHAT in discriminating young autistic children from those without. Five different ML algorithms (random forest (RF), naïve Bayes (NB), support vector machine (SVM), logistic regression (LR), and K-nearest neighbors (KNN)) were applied to investigate the complete set of Q-CHAT items. Our results showed that ML achieved an overall accuracy of 90%, and the SVM was the most effective, being able to classify autism with 95% accuracy. Furthermore, using the SVM-recursive feature elimination (RFE) approach, we selected a subset of 14 items ensuring 91% accuracy, while 83% accuracy was obtained from the 3 best discriminating items in common to ours and the previously reported Q-CHAT-10. This evidence confirms the high performance and cross-cultural validity of the Q-CHAT, and supports the application of ML to create shorter and faster versions of the instrument, maintaining high classification accuracy, to be used as a quick, easy, and high-performance tool in primary-care settings.

Keywords: Q-CHAT; autism; early screening; machine learning.

PubMed Disclaimer

Conflict of interest statement

All authors declare no potential conflicts of interest, including any financial, personal or other relationships with other people or organizations relevant to the subject of their manuscript.

Figures

Figure 1
Figure 1
Overview of the entire analytical process. Collected questionnaires processed with machine-learning (ML) models and a feature-selection algorithm. Training phase (ML training) and validation (ML validation) used fivefold cross-validation. Lastly, hyperparameters were automatically tuned on the best-evaluated ML model, and output performance was reported.
Figure 2
Figure 2
(a) Area under curve for Quantitative CHecklist for Autism in Toddlers (Q-CHAT; autism vs typically developing (TD)) comparing all 5 machine-learning models with all features; (b) histogram of predictions of best-performing model (SVM).
Figure 3
Figure 3
Learning curves to diagnose SVM model performance.
Figure 4
Figure 4
Accuracy selecting an increasing number of Q-CHAT items using SVM–recursive feature elimination (RFE) algorithm.
See this image and copyright information in PMC

References

    1. Diagnostic and Statistical Manual of Mental Disorders: DSM-5. 5th ed. American Psychiatric Association; Washington, DC, USA: 2013.
    1. Elsabbagh M., Johnson M.H. Getting Answers from Babies about Autism. Trends Cogn. Sci. 2010;14:81–87. doi: 10.1016/j.tics.2009.12.005. - DOI - PubMed
    1. Thabtah F., Peebles D. Early Autism Screening: A Comprehensive Review. Int. J. Environ. Res. Public. Health. 2019;16:3502. doi: 10.3390/ijerph16183502. - DOI - PMC - PubMed
    1. McPheeters M.L., Weitlauf A., Vehorn A., Taylor C., Sathe N.A., Krishnaswami S., Fonnesbeck C., Warren Z.E. U.S. Preventive Services Task Force Evidence Syntheses, Formerly Systematic Evidence Reviews. Agency for Healthcare Research and Quality; Rockville, MD, USA: 2016. Screening for Autism Spectrum Disorder in Young Children. - PubMed
    1. Dereu M., Roeyers H., Raymaekers R., Meirsschaut M., Warreyn P. How Useful Are Screening Instruments for Toddlers to Predict Outcome at Age 4? General Development, Language Skills, and Symptom Severity in Children with a False Positive Screen for Autism Spectrum Disorder. Eur. Child Adolesc. Psychiatry. 2012;21:541–551. doi: 10.1007/s00787-012-0280-y. - DOI - PubMed

LinkOut - more resources