The COVID-19 pandemic has posed unique challenges for families and caregivers, as well as for autism-focused clinicians, who are faced with providing a thorough and accurate evaluation of children's specific needs and diagnoses in the absence of in-person assessment tools. The shift to telehealth assessments has challenged clinicians to reconsider approaches and assumptions that underlie the diagnostic assessment process, and to adopt new ways of individualizing standard assessments according to family and child needs. Mandates for physical distancing have uncovered deficiencies in diagnostic practices for suspected autism and have illuminated biases that have posed obstacles preventing children and families from receiving the services that they truly need. This Commentary outlines several considerations for improving diagnostic practices as we move forward from the current pandemic and continue to strive to build an adaptable, sustainable, equitable, and family-centered system of care. LAY SUMMARY: Physical distancing and the abrupt end to in-person services for many children on the autism spectrum has forced clinicians to examine the existing challenges with autism spectrum disorder (ASD) diagnostic assessment and consider things they want to keep and things that should be changed in the years ahead. New approaches such as telehealth both alleviated and exacerbated existing disparities, and brought into stark focus the importance of equitable and timely access to family-centered care. This commentary suggests ways of improving clinical practices related to ASD assessment to continue along this path.

Autism spectrum disorder (ASD) can be reliably diagnosed at 18 months, yet significant diagnostic delays persist in the United States. This double-blinded, multi-site, prospective, active comparator cohort study tested the accuracy of an artificial intelligence-based Software as a Medical Device designed to aid primary care healthcare providers (HCPs) in diagnosing ASD. The Device combines behavioral features from three distinct inputs (a caregiver questionnaire, analysis of two short home videos, and an HCP questionnaire) in a gradient boosted decision tree machine learning algorithm to produce either an ASD positive, ASD negative, or indeterminate output. This study compared Device outputs to diagnostic agreement by two or more independent specialists in a cohort of 18-72-month-olds with developmental delay concerns (425 study completers, 36% female, 29% ASD prevalence). Device output PPV for all study completers was 80.8% (95% confidence intervals (CI), 70.3%-88.8%) and NPV was 98.3% (90.6%-100%). For the 31.8% of participants who received a determinate output (ASD positive or negative) Device sensitivity was 98.4% (91.6%-100%) and specificity was 78.9% (67.6%-87.7%). The Device's indeterminate output acts as a risk control measure when inputs are insufficiently granular to make a determinate recommendation with confidence. If this risk control measure were removed, the sensitivity for all study completers would fall to 51.6% (63/122) (95% CI 42.4%, 60.8%), and specificity would fall to 18.5% (56/303) (95% CI 14.3%, 23.3%). Among participants for whom the Device abstained from providing a result, specialists identified that 91% had one or more complex neurodevelopmental disorders. No significant differences in Device performance were found across participants' sex, race/ethnicity, income, or education level. For nearly a third of this primary care sample, the Device enabled timely diagnostic evaluation with a high degree of accuracy. The Device shows promise to significantly increase the number of children able to be diagnosed with ASD in a primary care setting, potentially facilitating earlier intervention and more efficient use of specialist resources.