Predicting Core Characteristics of ASD Through Facial Emotion Recognition and Eye Tracking in Youth

The differential outcomes procedure for improving the recognition of dynamic facial expressions of emotion in people with autism spectrum disorders and first-degree relatives

Previous research highlights impairments in the recognition of facial expression of emotion in individuals diagnosed with Autism Spectrum Disorder (ASD). Relatives of people with ASD may exhibit similar, albeit subtler, impairments, referred to as the Broad Autism Phenotype (BAP). Recently, the Differential outcomes procedure (DOP) has been shown to enhance this ability in young adults using dynamic stimuli, with fewer intensity levels required to identify fear and surprise. The present study aimed to extend these findings to adults diagnosed with ASD (ASD group), and relatives of people diagnosed with ASD (BAP group). A Bayesian Generalized Linear Model was employed for statistical inference. The results indicated that the ASD DOP group performed worse than the BAP DOP group in fear trials. The social dimension of autism negatively impacted performance in some conditions, while positive relationships were found between the repetitive behavior dimension and performance for the ASD group. The opposite pattern was observed in the BAP group. These results suggest the importance of considering different dimensions of autism when conducting research on its relationship with other variables. Finally, participants in both ASD and BAP groups required less intensity to identify certain emotions when the DOP was applied, highlighting its potential utility for improving dynamic facial emotion recognition.

Predicting Autistic Traits Using Eye Movement during Visual Perspective Taking and Facial Emotion Identification

Autistic traits are broad in severity and difficult to measure quantitatively. Quantitative measurement would be helpful in determining the effectiveness of training and therapy for autistic traits. The development of eye-tracking technology has made it easier to understand autistic traits. Previous works showed that autistic traits can be predicted from eye movements in the facial emotion identification task. It may be possible to measure autistic traits more accurately than the only prediction from facial emotion identification ability. In this study, we used a visual perspective taking task. The results showed that the Social Responsiveness Scale-2 score, which is associated with autistic traits, was predicted at 0.414 in Spearman's correlation coefficient by using eye movements obtained from the two tasks.

Machine learning based on eye-tracking data to identify Autism Spectrum Disorder: A systematic review and meta-analysis

BACKGROUND

Machine learning has been widely used to identify Autism Spectrum Disorder (ASD) based on eye-tracking, but its accuracy is uncertain. We aimed to summarize the available evidence on the performances of machine learning algorithms in classifying ASD and typically developing (TD) individuals based on eye-tracking data.

METHODS

We searched Medline, Embase, Web of Science, Scopus, Cochrane Library, IEEE Xplore Digital Library, Wan Fang Database, China National Knowledge Infrastructure, Chinese BioMedical Literature Database, VIP Database for Chinese Technical Periodicals, from database inception to December 24, 2021. Studies using machine learning methods to classify ASD and TD individuals based on eye-tracking technologies were included. We extracted the data on study population, model performances, algorithms of machine learning, and paradigms of eye-tracking. This study is registered with PROSPERO, CRD42022296037.

RESULTS

261 articles were identified, of which 24 studies with sample sizes ranging from 28 to 141 were included (n = 1396 individuals). Machine learning based on eye-tracking yielded the pooled classified accuracy of 81 % (I² = 73 %), specificity of 79 % (I² = 61 %), and sensitivity of 84 % (I² = 61 %) in classifying ASD and TD individuals. In subgroup analysis, the accuracy was 88 % (95 % CI: 85-91 %), 79 % (95 % CI: 72-84 %), 71 % (95 % CI: 59-91 %) for preschool-aged, school-aged, and adolescent-adult group. Eye-tracking stimuli and machine learning algorithms varied widely across studies, with social, static, and active stimuli and Support Vector Machine and Random Forest most commonly reported. Regarding the model performance evaluation, 15 studies reported their final results on validation datasets, four based on testing datasets, and five did not report whether they used validation datasets. Most studies failed to report the information on eye-tracking hardware and the implementation process.

CONCLUSION

Using eye-tracking data, machine learning has shown potential in identifying ASD individuals with high accuracy, especially in preschool-aged children. However, the heterogeneity between studies, the absence of test set-based performance evaluations, the small sample size, and the non-standardized implementation of eye-tracking might deteriorate the reliability of results. Further well-designed and well-executed studies with comprehensive and transparent reporting are needed to determine the optimal eye-tracking paradigms and machine learning algorithms.