ABSTRACT
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.
ABSTRACT
BACKGROUND: In adults, prefrontal, thalamic, and cerebellar brain injury is associated with excessive ethanol intake. As these brain structures are actively maturing during adolescence, we hypothesized that subjects with adolescent-onset alcohol use disorders, compared with control subjects, would have smaller brain volumes in these areas. Thus, we compared prefrontal-thalamic-cerebellar measures of adolescents and young adults with adolescent-onset alcohol use disorders (AUD, defined as DSM-IV alcohol dependence or abuse) with those of sociodemographically similar control subjects. METHODS: Magnetic resonance imaging was used to measure prefrontal cortex, thalamic, and cerebellar volumes in 14 subjects (eight males, six females) with an AUD (mean age, 17.0+/-2.1 years) and 28 control subjects (16 males, 12 females; 16.9+/-2.3 years). All AUD subjects were recruited from substance abuse treatment programs and had comorbid mental disorders. RESULTS: Subjects with alcohol use disorders had smaller prefrontal cortex and prefrontal cortex white matter volumes compared with control subjects. Right, left, and total thalamic, pons/brainstem, right and left cerebellar hemispheric, total cerebellar, and cerebellar vermis volumes did not differ between groups. There was a significant sex-by-group effect, indicating that males with an adolescent-onset AUD compared with control males had smaller cerebellar volumes, whereas the two female groups did not differ in cerebellar volumes. Prefrontal cortex volume variables significantly correlated with measures of alcohol consumption. CONCLUSIONS: These findings suggest that a smaller prefrontal cortex is associated with early-onset drinking in individuals with comorbid mental disorders. Further studies are warranted to examine if a smaller prefrontal cortex represents a vulnerability to, or a consequence of, early-onset drinking.
