Home-based eye tracking for early autism screening: a scoping review of approaches, evidence, and implementation challenges - PubMed
3 hours ago
- #eye-tracking
- #autism-screening
- #digital-biomarkers
- Early identification of autism spectrum disorder (ASD) is crucial for improving developmental outcomes, yet faces challenges like diagnostic delays, subjectivity, and limited resources.
- Eye-tracking provides objective measures of social attention and could enhance early screening accessibility when used on consumer devices in home settings.
- The review synthesized evidence on home-deployable eye-tracking as digital biomarkers for early ASD screening, covering machine learning methods and real-world implementation feasibility.
- Following the Arksey and O'Malley framework and Joanna Briggs Institute methodology, 90 studies from 2015-2025 were analyzed using a Population, Concept, Context (PCC) framework.
- Results show reported discrimination from moderate to high, with sample sizes ranging from 30 to over 1,000 and ages from 5 months to 18 years.
- Studies were categorized by system type (hardware-based, wearable, webcam-based, home-deployed) and purpose, with most being exploratory or feasibility evaluations.
- Common tasks included faces/social scenes, biological motion, and joint-attention cues; metrics included fixation proportion, dwell time, saccade dynamics, and interest-area contrasts.
- Supervised learning (e.g., SVM, random forests) and deep learning were used, but external validation and calibration robustness were inconsistently reported.
- Practical barriers included ambient-light variability, viewing distance, caregiver facilitation, device heterogeneity, and data privacy/governance issues.
- Only three studies collected data in home-deployed settings, none with externally validated accuracy, highlighting the need for prospective multisite home-based trials and standardized protocols.