A machine learning approach for retinal images analysis as an objective screening method for children with autism spectrum disorder

Abstract

Background: Autism spectrum disorder (ASD) is characterised by many of features including problem in social interactions, different ways of learning, some children showing a keen interest in specific subjects, inclination to routines, challenges in typical communication, and particular ways of processing sensory information. Early intervention and suitable supports for these children may make a significant contribution to their development. However, considerable difficulties have been encountered in the screening and diagnosis of ASD. The literature has indicated that certain retinal features are significantly associated with ASD. In this study, we investigated the use of machine learning approaches on retinal images to further enhance the classification accuracy.

Methods: Forty-six ASD participants were recruited from three special needs schools and 24 normal control were recruited from the community. Among them, 23 age-gender matched ASD and normal control participant-pairs were constructed for the primary analysis. All retinal images were captured using a nonmydriatic fundus camera. Automatic retinal image analysis (ARIA) methodology applying machine-learning technology was used to optimise the information of the retina to develop a classification model for ASD. The model's validity was then assessed using a 10-fold cross-validation approach to assess its validity.

Findings: The sensitivity and specificity were 95.7% (95% CI 76.0%, 99.8%) and 91.3% (95% CI 70.5%, 98.5%) respectively. The area under the ROC curve was 0.974 (95% CI 0.934, 1.000); however, it was noted that the specificity for female participants might not be as high as that for male participants.

Interpretation: Because ARIA is a fully automatic cloud-based algorithm and relies only on retinal images, it can be used as a risk assessment tool for ASD screening. Further diagnosis and confirmation can then be made by professionals, and potential treatment may be provided at a relatively early stage.

Keywords: Autism spectrum disorder; Automatic retinal image analysis; Machine learning; Risk assessment; screening tool.

Conflict of interest statement

BZ and JL have a patent “Method and device for retinal image analysis” licensed to Health View Bioanalytic Limited, received royalties through the Chinese University of Hong Kong. BZ and JL are founders and shareholders of Health View Bioanalytic Limited, Bioanalytic Holdings Limited, and Bioanalytic International Holdings Limited. ML is director of Bioanalytic Holdings Limited, and Bioanalytic International Holdings Limited. BZ is co-founder and shareholder of Beth Bioinformatics Company Limited. ML reports Spouse of Founder and Shareholder of Health View Bioanlaytic Limited; Honorary Consultant of Health View Bioanalytic Limited. The remaining authors have no conflict of interest to declare.

© 2020 The Author(s).

Figures

Fig. 1

Flowchart of the method presented in our ASD study Note: RGB – Red, Green and Blue ResNet50 – residual network that is 50 layers deep Glmnet – Generalized linear model via penalized maximum likelihood SVM – Support vector machine.(For interpretation of the references to color in this figure legend, the reader is referred to the web version of this article.)

Fig. 2

Box plot for the probability of ASD based on the matched case–control data.