Artificial intelligence united with virtual reality technology creates a new method that changes our ability to detect Autism Spectrum Disorder (ASD) among children. The diagnostic tool developed by the Human-Tech Institute at Universitat Politècnica de València (UPV) analyses child movements and eye behavior in virtual space during everyday tasks with more than 85% accuracy.
A More Natural Way to Detect Autism
Autism evaluations in traditional settings depend mainly on interview methods along with psychological assessments. The new assessment system creates settings based on familiar environments which enable children to carry out their interactions through natural spaces. The system records natural behaviors which assessment facilities in labs commonly lack access to.
The system develops virtual environments through standard commercial screens and cameras for children to execute their tasks. The deep learning model tracks and analyzes their behavior to precisely detect autism earliest signs. The detection method enhances both clinical accuracy and accessibility and decreases total expenses.
Key Highlights:
- The virtual reality artificial intelligence detection system provides ASD identification with a success rate exceeding 85%.
- The system features realistic virtual environments allowing children to interact effectively with scenes which tend to produce genuine behavioral outcomes.
- The system uses available market technologies which enable deployment across different early-intervention centers.
The Science Behind It
Researchers examined child interactions in virtual spaces to establish the most effective artificial intelligence systems for detecting symptoms of ASD. The victorious algorithm outperformed traditional approaches by detecting behavioral markers of motor actions and eye movement direction with excellence.
The model achieves better ASD diagnosis through speedier and lower-cost operations and objective assessment methods.
Years of Research Pay Off
Within the last eight years the Human-Tech Institute worked alongside clinical experts to improve this method. Doctoral researcher Eleonora Minissi emphasized the diagnostic significance of motor patterns even though studies predominantly focus on autism research through social behaviors.
Her research develops motor activity into an effective tool along with ease of evaluation for diagnosing autism which supports continued innovation in AI healthcare technologies.
