Facial Morphometric Features in Autism Spectrum Disorder: Preliminary Findings From Canonical Discriminant Analysis.

Area of Science:

• Neurodevelopmental Disorders
• Biometric Analysis
• Medical Imaging

Background:

• Autism spectrum disorder (ASD) is a neurodevelopmental condition impacting social communication and behavior.
• Early diagnosis of ASD is crucial for intervention but often delayed, limiting access to support.
• Current diagnostic methods can be time-consuming; novel approaches are needed.

Purpose of the Study:

• To investigate the potential of facial morphometric analysis using canonical discriminant analysis (CDA) to differentiate children with ASD from typically developing (TD) children.
• To identify specific facial regions that contribute most significantly to group differentiation.

Main Methods:

• A proof-of-concept study involving 40 children with ASD and 40 age/gender-matched TD controls.
• Standardized facial photographs were analyzed for anthropometric landmarks and inter-landmark distances using ImageJ software.
• Canonical discriminant analysis (CDA) was employed to build a statistical classification model.

Main Results:

• Overall facial morphology alone did not significantly differentiate ASD and TD groups.
• Specific facial regions, notably the eyes and lips, demonstrated significant discriminatory power.
• Combining overall facial and organ-specific measurements yielded the strongest separation (canonical correlation = 0.74).

Conclusions:

• Specific facial morphometric features, particularly around the eyes and lips, may serve as potential indicators for differentiating ASD.
• Facial morphometrics show promise as a supplementary, non-invasive research tool for ASD studies.
• Further validation with larger, diverse samples is essential for potential clinical or screening applications.