Is Smiling the Key? Machine Learning Analytics Detect Subtle Patterns in Micro-Expressions of Infants with ASD.
Gianpaolo AlvariCesare FurlanelloPaola VenutiPublished in: Journal of clinical medicine (2021)
Time is a key factor to consider in Autism Spectrum Disorder. Detecting the condition as early as possible is crucial in terms of treatment success. Despite advances in the literature, it is still difficult to identify early markers able to effectively forecast the manifestation of symptoms. Artificial intelligence (AI) provides effective alternatives for behavior screening. To this end, we investigated facial expressions in 18 autistic and 15 typical infants during their first ecological interactions, between 6 and 12 months of age. We employed Openface, an AI-based software designed to systematically analyze facial micro-movements in images in order to extract the subtle dynamics of Social Smiles in unconstrained Home Videos. Reduced frequency and activation intensity of Social Smiles was computed for children with autism. Machine Learning models enabled us to map facial behavior consistently, exposing early differences hardly detectable by non-expert naked eye. This outcome contributes to enhancing the potential of AI as a supportive tool for the clinical framework.
Keyphrases
- artificial intelligence
- machine learning
- big data
- autism spectrum disorder
- deep learning
- healthcare
- intellectual disability
- attention deficit hyperactivity disorder
- systematic review
- mental health
- soft tissue
- oxidative stress
- risk assessment
- convolutional neural network
- depressive symptoms
- single molecule
- magnetic resonance imaging
- computed tomography
- physical activity
- combination therapy
- magnetic resonance
- anti inflammatory
- working memory