Children with autism spectrum disorder produce more ambiguous and less socially meaningful facial expressions: an experimental study using random forest classifiers.

Background: Computer vision combined with human annotation could offer a novel method for exploring facial expression (FE) dynamics in children with autism spectrum disorder (ASD). Methods: We recruited 157 children with typical development (TD) and 36 children with ASD in Paris and Nice to perform two experimental tasks to produce FEs with emotional valence. FEs were explored by judging ratings and by random forest (RF) classifiers. To do so, we located a set of 49 facial landmarks in the task videos, we generated a set of geometric and appearance features and we used RF classifiers to explore how children with ASD differed from TD children when producing FEs. Results: Using multivariate models including other factors known to predict FEs (age, gender, intellectual quotient, emotion subtype, cultural background), ratings from expert raters showed that children with ASD had more difficulty producing FEs than TD children. In addition, when we explored how RF classifiers performed, we found that classification tasks, except for those for sadness, were highly accurate and that RF classifiers needed more facial landmarks to achieve the best classification for children with ASD. Confusion matrices showed that when RF classifiers were tested in children with ASD, anger was often confounded with happiness. Limitations: The sample size of the group of children with ASD was lower than that of the group of TD children. By using several control calculations, we tried to compensate for this limitation. Conclusion: Children with ASD have more difficulty producing socially meaningful FEs. The computer vision methods we used to explore FE dynamics also highlight that the production of FEs in children with ASD carries more ambiguity.

Children Facial Expression Production: Influence of Age, Gender, Emotion Subtype, Elicitation Condition and Culture.

The production of facial expressions (FEs) is an important skill that allows children to share and adapt emotions with their relatives and peers during social interactions. These skills are impaired in children with Autism Spectrum Disorder. However, the way in which typical children develop and master their production of FEs has still not been clearly assessed. This study aimed to explore factors that could influence the production of FEs in childhood such as age, gender, emotion subtype (sadness, anger, joy, and neutral), elicitation task (on request, imitation), area of recruitment (French Riviera and Parisian) and emotion multimodality. A total of one hundred fifty-seven children aged 6-11 years were enrolled in Nice and Paris, France. We asked them to produce FEs in two different tasks: imitation with an avatar model and production on request without a model. Results from a multivariate analysis revealed that: (1) children performed better with age. (2) Positive emotions were easier to produce than negative emotions. (3) Children produced better FE on request (as opposed to imitation); and (4) Riviera children performed better than Parisian children suggesting regional influences on emotion production. We conclude that facial emotion production is a complex developmental process influenced by several factors that needs to be acknowledged in future research.

Teaching Literacy Skills to French Minimally Verbal School-Aged Children with Autism Spectrum Disorders with the Serious Game SEMA-TIC: An Exploratory Study.

Learning to read is very challenging for children with Autism Spectrum Disorders (ASD), but also very important, as it can give them access to new knowledge. This is even more challenging in minimally verbal children, who do not have the verbal abilities to learn through usual methods. To address the learning of literacy skills in French minimally verbal school-aged children with ASD, we designed the serious game SEMA-TIC, which relies on non-verbal cognitive skills and uses specific learning strategies adapted to the features of autistic individuals. This study investigated the usability of SEMA-TIC (in terms of adaptability, efficiency, and effectiveness) for the acquisition of literacy skills in French minimally verbal school-aged children with ASD. Twenty-five children with ASD and no functional language participated in the study. Children in the training group received the SEMA-TIC training over 23 weeks (on average), while no intervention was provided to children in the non-training group. Results indicated that SEMA-TIC presents a suitable usability, as all participants were able to play (adaptability), to complete the training (efficiency) and to acquire significant literacy skills (effectiveness). Indeed, the literacy skills in the training group significantly improved after the training, as measured by specific experimental tasks (alphabet knowledge, word reading, word-non-word discrimination, sentence reading and word segmentation; all p ≤ 0.001) compared to the non-training group. More importantly, 3 out of 12 children of the training group could be considered as word decoders at the end of the intervention, whereas no children of the non-training group became able to decode words efficiently. The present study thus brings preliminary evidence that French minimally verbal school-aged children with ASD are able to learn literacy skills through SEMA-TIC, a specific computerized intervention consisting in a serious game based on non-verbal cognitive skills.

Recommendations for the Use of Serious Games in Neurodegenerative Disorders: 2016 Delphi Panel.

The use of Serious Games (SG) in the health domain is expanding. In the field of neurodegenerative disorders (ND) such as Alzheimer's disease, SG are currently employed both to support and improve the assessment of different functional and cognitive abilities, and to provide alternative solutions for patients' treatment, stimulation, and rehabilitation. As the field is quite young, recommendations on the use of SG in people with ND are still rare. In 2014 we proposed some initial recommendations (Robert et al., 2014). The aim of the present work was to update them, thanks to opinions gathered by experts in the field during an expert Delphi panel. Results confirmed that SG are adapted to elderly people with mild cognitive impairment (MCI) and dementia, and can be employed for several purposes, including assessment, stimulation, and improving wellbeing, with some differences depending on the population (e.g., physical stimulation may be better suited for people with MCI). SG are more adapted for use with trained caregivers (both at home and in clinical settings), with a frequency ranging from 2 to 4 times a week. Importantly, the target of SG, their frequency of use and the context in which they are played depend on the SG typology (e.g., Exergame, cognitive game), and should be personalized with the help of a clinician.

Facing the challenge of teaching emotions to individuals with low- and high-functioning autism using a new Serious game: a pilot study.

BACKGROUND: It is widely accepted that emotion processing difficulties are involved in Autism Spectrum Conditions (ASC). An increasing number of studies have focused on the development of training programs and have shown promising results. However, most of these programs are appropriate for individuals with high-functioning ASC (HFA) but exclude individuals with low-functioning ASC (LFA). We have developed a computer-based game called JeStiMulE based on logical skills to teach emotions to individuals with ASC, independently of their age, intellectual, verbal and academic level. The aim of the present study was to verify the usability of JeStiMulE (which is its adaptability, effectiveness and efficiency) on a heterogeneous ASC group. We hypothesized that after JeStiMulE training, a performance improvement would be found in emotion recognition tasks. METHODS: A heterogeneous group of thirty-three children and adolescents with ASC received two one-hour JeStiMulE sessions per week over four weeks. In order to verify the usability of JeStiMulE, game data were collected for each participant. Furthermore, all participants were presented before and after training with five emotion recognition tasks, two including pictures of game avatars (faces and gestures) and three including pictures of real-life characters (faces, gestures and social scenes). RESULTS: Descriptive data showed suitable adaptability, effectiveness and efficiency of JeStiMulE. Results revealed a significant main effect of Session on avatars (ANOVA: F (1,32) = 98.48, P < .001) and on pictures of real-life characters (ANOVA: F (1,32) = 49.09, P < .001). A significant Session × Task × Emotion interaction was also found for avatars (ANOVA: F (6,192) = 2.84, P = .01). This triple interaction was close to significance for pictures of real-life characters (ANOVA: F (12,384) = 1.73, P = .057). Post-hoc analyses revealed that 30 out of 35 conditions found a significant increase after training. CONCLUSIONS: JeStiMulE appears to be a promising tool to teach emotion recognition not only to individuals with HFA but also those with LFA. JeStiMulE is thus based on ASC-specific skills, offering a model of logical processing of social information to compensate for difficulties with intuitive social processing. TRIAL REGISTRATION: Comité de Protection des Personnes Sud Méditerranée V (CPP): reference number 11.046 (https://cpp-sud-mediterranee-v.fr/).