Les troubles du spectre de l'autisme (TSA) sont des troubles du développement très fréquents, qui se manifestent pas des difficultés de communication et d'interactions sociales, ainsi que par des comportements répétitifs. Récemment, les techniques de détection automatique des mouvements du corps, la capture de scènes sociales et la mesure de la manipulation d'objets ont évolué de manière impressionnante. Ensemble, ces outils ouvrent la possibilité de modéliser les interactions sociales, d'une manière qui a le potentiel d'améliorer le dépistage et de caractériser finement les symptômes autistiques chez les jeunes enfants.
Notre projet interdisciplinaire combine des compétences d'experts en recherche clinique, en ingénierie et en sciences sociales computationnelles afin de relever de nombreux défis cliniques, scientifiques et techniques. Il s'appuie sur une cohorte de jeunes enfants avec un TSA et de leurs pairs au développement normal appariés selon l'âge, évalués de manière approfondie à l'aide d'évaluations cliniques et cognitives standardisées de référence, ainsi que d'outils neuroscientifiques.
A terme, les nouvelles connaissances amenées par le 'digital phenotyping' des TSA vise à répondre à deux buts principaux: (i) soutenir le dépistage automatisé des TSA chez les jeunes enfants, afin de permettre un diagnostic plus précoce, et (ii) permettre la détection de sous-types d'autisme associés à des pronostics, des sensibilités aux traitements ou des mécanismes neurobiologiques différents, une étape indispensable pour permettre une médecine de précision de l'autisme.
Nowadays, 1 in 59 children is diagnosed with autism spectrum disorders (ASD), which makes this condition one of the most prevalent neurodevelopmental disorders. The hereby project is grounded on the recognition that, on the one hand, early diagnosis at scale of autism in young children requires the development of tools for digital phenotyping and automated screening, through computer vision and Internet of Things sensing. On the other hand, current gold-standard approaches in autism are not intended to provide a precise quantitative estimate of ASD symptoms in children. We therefore aim to examine the potential of digital sensing to provide automated measures of the extended autism phenotype, for the purpose of stratifying autism subtypes in ways that would allow for precision medicine.
Recent developments in digital sensing, big data and machine-learning have offered unforeseen opportunities for seamless sensing of body movement, social scene capture, and measure of object manipulation. Together, these tools are key for modeling social interactions and offer avenues for both improving screening and fine-grained characterization of autistic symptoms in young children. Despite considerable efforts invested to explore such automatic behavioral analysis, most studies in ASD digital phenotyping have been conducted on modest samples sizes, used mono-modal approaches, were focused on eliciting very specific behaviors by largely controlled prompts, and have suffered from technical difficulties in behavior sensing (view points, children population, image resolution for gaze).
To address these limitations, we propose an interdisciplinary project combining the skills of experts in clinical research, engineering and computational social sciences in order to address these clinical, scientific, and technical challenges. It is grounded on the Geneva Autism Cohort consisting of young children with ASD and their age-matched typically developing peers, extensively assessed with gold standard standardized clinical and cognitive assessments, as well as neuroscience tools. Further, our preliminary results demonstrated that relying on a substantial dataset it is feasible to successfully train a deep neural network directly from on a global scene representation (people poses) to predict ASD with above 80% accuracy. This Sinergia proposal is set to stretch a giant leap forward, by investigating three key research directions.
First, from a clinical research perspective, we will design digital tools for screening and automated profiling of autism phenotype. We will test these tools in a structured setting with well-established clinical protocol, as well as in a less structured environment (free play in day-care centers).
Second, with Internet of Things (IoT) sensors, we will investigate the motor skills of very young children, through the integration of inertial and low-cost UWB indoor localization data. Additionally, we will develop a solution for the longitudinal monitoring of fine-grained motor skills development.
Last but not least, our project is rooted in modern computational perception and machine learning. We will investigate novel deep learning and computer vision techniques by leveraging the availability of large behavioral and clinical annotation data. At the core of this effort, we will develop multimodal machine-learning methods and models for the analysis of motor and gaze coordination patterns which are at the core of ASD, and for ASD diagnosis and profiling with a focus towards interpretable models.
Through a careful design and thorough technical implementation, this project will deliver scientific advances in the form of data, models, and methods. These novel insights on deep digital phenotyping of ASD through the fine-grained mechanisms of motor skills and non-verbal com- munication coordination patterns involved in ASD, have the potential to unlock two significant breakthroughs: (i) automatic ASD screening in young children, and (ii) the detection of previously undetected autism subtypes, associated with different prognosis, sensitivity to treatment, or neurobiological mechanisms. Additionally, abiding to the open science standards, we will re- lease what we believe will be the largest curated dataset on autistic data comprising a full set of ASD profile annotations, along with a large range of sensing modalities (skeletons, face cropped - anonymized videos, motricity data). We have also conceived this Sinergia project foster the thorough interdisciplinary training and promotion of young clinical and engineering scientists.
Although primarily aimed at scientific validation, the large place given to the scalability validation of our project has a core translational research component, which could - in a not so far future - help thousands of children get a much earlier diagnosis, quicker access to therapeutic intervention and thus, increase their chances to make significant progress towards a socially inclusive life.
Last updated:26.09.2022
