Diagnostic Tools for Autism Spectrum Disorders

Autism Spectrum Disorders (ASDs) are identified through a combination of structured observational assessments, caregiver interviews, standardised rating scales and emerging digital and biological markers. Traditional instruments such as the Autism Diagnostic Observation Schedule (ADOS) and the Autism Diagnostic Interview-Revised (ADI-R) remain the clinical cornerstone, enabling clinicians to evaluate social communication, play skills and restricted and repetitive behaviours across the lifespan. Complementary parent- or teacher-completed questionnaires such as the Social Responsiveness Scale (SRS) and the Gilliam Autism Rating Scale (GARS) offer scalable screening options. Recent advances have extended diagnostic reach through computer-vision analysis of naturalistic interactions, machine-learning algorithms trained on behavioural or neurophysiological data, and biomarker research, including eye-tracking, electrophysiology and genomic profiling. These modalities promise to augment clinical judgement by improving objectivity, reducing time burden and enhancing accessibility in diverse settings. Attention to cross-cultural adaptation and psychometric validation has elevated the global utility of established tools, while new digital platforms support remote assessment and telehealth delivery. Together, this multi-modal toolkit advances early identification, personalised intervention planning and equitable diagnostic services worldwide.

Research from Nature Portfolio

Recent studies have demonstrated the potential of automated video analysis of diagnostic interviews to streamline ASD classification. By applying computer-vision techniques to capture motion synchrony between clinicians and individuals undergoing the Autism Diagnostic Observation Schedule, researchers developed a support vector machine classifier that achieved above-chance discrimination of ASD versus other psychiatric profiles in a heterogeneous clinical sample. This proof-of-concept highlights the feasibility of scaling objective behavioural markers from standardised interactions, with potential to complement existing diagnostic assessments and reduce clinician workload in real-world settings.

Diagnostic Tools for Autism Spectrum Disorders publication trend

The graph below shows the total number of articles in diagnostic tools for autism spectrum disorders across all publications each year (not limited to Nature Index journals).

Technical terms

Autism Diagnostic Observation Schedule (ADOS-2): A semi-structured observational assessment measuring social interaction, communication and play behaviours across standardised tasks.

Autism Diagnostic Interview-Revised (ADI-R): A comprehensive caregiver interview evaluating developmental history and current behaviours related to social interaction, communication, and restricted or repetitive actions.

Support vector machine: A supervised machine-learning model that classifies data by finding an optimal boundary between defined categories.

Machine learning: Computational techniques that enable algorithms to learn patterns from data and generate predictive models.

Restricted and repetitive behaviours (RRBs): A core diagnostic domain characterised by stereotyped movements, insistence on sameness and highly focused interests.

Gilliam Autism Rating Scale (GARS-3): A norm-referenced questionnaire designed to screen for ASD characteristics across communication, social interaction and behavioural domains in accordance with current diagnostic standards.

References

1. Classifying autism in a clinical population based on motion synchrony: a proof-of-concept study using real-life diagnostic interviews. Scientific Reports (2024).
2. Patterns of autism symptoms: hidden structure in the ADOS and ADI-R instruments. Translational Psychiatry (2020).
3. Abilities and Disabilities—Applying Machine Learning to Disentangle the Role of Intelligence in Diagnosing Autism Spectrum Disorders. Frontiers in Psychiatry (2022).
4. Autism Spectrum Disorder Diagnostic Criteria Changes and Impacts on the Diagnostic Scales-Utility of the 2nd and 3rd Versions of the Gilliam Autism Rating Scale (GARS). Brain Sciences (2022).