Bringing autism diagnosis closer to home: The role of eye-tracking biomarkers in early detection

Autism spectrum disorder (ASD) remains one of the most common developmental disorders in the United States, yet the median age of diagnosis continues to hover near four years¹, despite American Academy of Pediatrics² recommendations for universal screening at 18 and 24 months, and the fact that many caregivers note developmental differences far earlier³. This delay restricts access to early intervention during a critical window of neuroplasticity and forces families into cycles of waitlists, multiple evaluations, and prolonged uncertainty.^4,5,6

From behavioral observation to objective biomarker

Two recent multisite studies published in JAMA Network Open⁷ and JAMA⁸ provide compelling evidence that eye-tracking measures of social visual engagement can aid clinicians in diagnosing autism in children 16 to 30 months old. These studies demonstrate that patterns of gaze—specifically, how young children attend to social versus nonsocial aspects of scenes—can reliably distinguish between children with and without autism. The technology is also user-friendly and rapid, taking approximately 20 minutes to administer, with results being available within another 20 minutes.

In the JAMA Network Open⁷ trial, the device achieved approximately 78% sensitivity and 85% specificity when compared with a gold-standard, expert clinical diagnosis that included developmental assessment and the ADOS-2. While the ADOS-2 has a summary sensitivity of 94% and specificity of 80%,⁹ real-world clinical use can be much lower due to variations in provider skills and potential biases.¹⁰ Eye-tracking technology is not only rapid; it provides a direct and objective measure free from provider bias and relatively free from administration errors.

The FDA¹¹ authorization of eye-tracking technology marks an important shift toward the use of objective, quantifiable measures in developmental assessments. Such biomarkers provide complementary data that may enhance diagnostic precision and efficiency in appropriate clinical contexts.

Integration into clinical workflows

Eye-tracking biomarkers can improve accessibility to autism evaluations and increase efficiency across generalist and specialist settings. Within primary care settings, eye-tracking technology may increase pediatricians’ willingness and confidence in assessing and diagnosing autism by the use of an objective measure. In specialty settings, which typically have long waitlists, these devices can aid in triaging children—accelerating evaluations for those with clear findings while reserving extended assessments for complex or equivocal cases.

Clinics across the country are already using eye-tracking technology within various clinical models to aid in diagnosing autism. The Neurodevelopmental Conditions and Autism Program at Nicklaus Children’s Health System in South Florida has implemented eye-tracking technology in a standardized process at four regional outpatient centers. Clinicians have experienced improved diagnostic certainty, and the average age of autism diagnosis has decreased, thereby providing children and families with earlier access to a range of crucial intervention services. Notably, in real-world clinical use at Nicklaus Children’s Health System, there have been no identified cases of false positive results using eye-tracking technology. However, a small number of children testing negative for autism via eye-tracking technology have subsequently been diagnosed with this condition in the mild-moderate range of severity, indicating that social gaze in ASD is not a homogeneous phenotype.

Similarly, the Autism Diagnostic Clinic at the University of Nebraska Medical Center’s Munroe-Meyer Institute has implemented a triage model. When clinicians are confident a child has autism based on clinical interview and observation, and caregivers report high confidence their child has autism, children are referred for a two-hour evaluation using eye-tracking biomarkers rather than the traditional four-hour assessment model. Both caregivers and providers report high satisfaction with evaluations incorporating eye-tracking technology.

Importantly, early identification does not necessarily increase autism prevalence but can lead to earlier diagnosis and intervention, particularly during a critical period in which treatments are typically more effective and developmental outcomes more favorable. Integrating objective data into diagnostic workflows may also improve inter-clinician reliability and support more consistent standards of care across diverse practice environments.

Addressing skepticism and ensuring responsible implementation

Skepticism toward biomarkers in neurodevelopmental disorders is both expected and healthy. Historically, some commercially marketed technologies have made exaggerated claims or lacked rigorous validation. To ensure responsible integration, continued transparency regarding device performance—including sensitivity, specificity, and predictive values—is critical. Independent replication, alignment with regulatory guidance, and data sharing will help build clinician and payer confidence in these emerging tools.

Furthermore, clinicians must remain aware of the limits of current evidence. While results to date are promising, implementation studies are still needed to determine how well eye-tracking biomarkers perform in broader community or primary care contexts, and how best to integrate them into existing diagnostic frameworks without compromising clinical comprehensiveness.

The path forward

Validated, FDA-cleared biomarker tools represent a promising step toward objective and scalable early autism detection. Their appropriate use can augment—not replace—clinical expertise, providing additional data to guide diagnosis and treatment planning. As the field advances, success will depend on collaboration among researchers, clinicians, regulators, and payers to ensure that biomarker technologies are deployed responsibly, equitably, and in line with empirical evidence. Importantly, providers must have a plan for addressing potential false negatives. For general providers, this may involve referrals to specialty clinics. For specialty providers, this may involve supplementing biomarker data with additional testing.

Understanding that technological devices and other standard diagnostic tools have ongoing limitations in accurately assessing all children with the broad and heterogeneous condition of ASD, eye-tracking biomarkers have allowed the providers at Nicklaus Children’s Health System and the University of Nebraska Medical Center to diagnose very young children with greater frequency and confidence, thereby increasing access to early intervention services. Moreover, eye-tracking biomarkers have been instrumental in ruling out ASD in others, alleviating anxiety for worried parents and reducing unnecessary referrals for further interventions and/or evaluations.

Bringing autism diagnosis closer to home requires bridging the gap between research innovation and clinical practice. Eye-tracking biomarkers, when used within their approved indications and interpreted in context, offer one potential pathway toward earlier, more accurate, and more equitable identification for children and families affected by autism.

References

1. Shaw KA, Williams S, Patrick ME, et al. Prevalence and Early Identification of Autism Spectrum Disorder Among Children Aged 4 and 8 Years - Autism and Developmental Disabilities Monitoring Network, 16 Sites, United States, 2022. MMWR Surveill Summ. 2025;74(2):1-22. Published 2025 Apr 17. doi:10.15585/mmwr.ss7402a1
2. Council on Children With Disabilities; Section on Developmental Behavioral Pediatrics; Bright Futures Steering Committee; Medical Home Initiatives for Children With Special Needs Project Advisory Committee. Identifying infants and young children with developmental disorders in the medical home: an algorithm for developmental surveillance and screening. Pediatrics. 2006;118(1):405-420. doi:10.1542/peds.2006-1231
3. Zuckerman KE, Lindly OJ, Sinche BK. Parental concerns, provider response, and timeliness of autism spectrum disorder diagnosis. J Pediatr. 2015;166(6):1431-9.e1. doi:10.1016/j.jpeds.2015.03.007
4. Daniels AM, Mandell DS. Explaining Differences in Age at Autism Spectrum Disorder Diagnosis: A Critical Review. Autism. 2014;18(5):583-597. doi: 10.1177/1362361313480277
5. Dawson G. Early Behavioral Intervention, Brain Plasticity, and the Prevention of Autism Spectrum Disorder. Dev Psychopathol. 2008;20(3):775-803. doi: 10.1017/S0954579408000370
6. Hyman SL, Levy SE, Myers SM, et al. Identification, Evaluation, and Management of Children with Autism Spectrum Disorder. Pediatrics. 2020;145(1):e20193447. doi: 10.1542/peds.2019-3447
7. Jones W, Klaiman C, et al. Development and Replication of Objective Measurements of Social Visual Engagement to Aid in Early Diagnosis and Assessment of Autism. JAMA Netw Open. 2023;6(9):e2330145. doi: 10.1001/jamanetworkopen.2023.30145
8. Jones W, Klaiman C, Richardson S, et al. Eye-Tracking-Based Measurement of Social Visual Engagement Compared With Expert Clinical Diagnosis of Autism. JAMA. 2023;330(9):854-865. doi:10.1001/jama.2023.13295
9. Randall M, Egberts KJ, Samtani A, et al. Diagnostic tests for autism spectrum disorder (ASD) in preschool children. Cochrane Database Syst Rev. 2018;7(7):CD009044. Published 2018 Jul 24. doi:10.1002/14651858.CD009044.pub2
10. Kamp-Becker, I., Albertowski, K., Becker, J. et al. Diagnostic accuracy of the ADOS and ADOS-2 in clinical practice. Eur Child Adolesc Psychiatry 27, 1193–1207 (2018). https://doi.org/10.1007/s00787-018-1143-y
11. U.S. Food and Drug Administration. Pediatric autism spectrum disorder diagnosis aid. (K213882). U.S. Department of Health and Human Services. 2022. Accessed January 1, 2026. https://www.accessdata.fda.gov/cdrh_docs/pdf21/K213882.pdf