Reduced false positives in autism screening via digital biomarkers inferred from deep comorbidity patterns

Here, we develop digital biomarkers for autism spectrum disorder (ASD), computed from patterns of past medical encounters, identifying children at high risk with an area under the receiver operating characteristic exceeding 80% from shortly after 2 years of age for either sex, and across two independent patient databases. We leverage uncharted ASD comorbidities, with no requirement of additional blood work, or procedures, to estimate the autism comorbid risk score (ACoR), during the earliest years when interventions are the most effective. ACoR has superior predictive performance to common questionnaire-based screenings and can reduce their current socioeconomic, ethnic, and demographic biases. In addition, we can condition on current screening scores to either halve the state-of-the-art false-positive rate or boost sensitivity to over 60%, while maintaining specificity above 95%. Thus, ACoR can significantly reduce the median diagnostic age, reducing diagnostic delays and accelerating access to evidence-based interventions.

All data and models needed to evaluate the conclusions in the paper are present in the paper and/or the Supplementary Materials. The Truven and UCM datasets cannot be made available due to ethical and patient privacy considerations. Preliminary software implementation of the pipeline is available at https://github.com/zeroknowledgediscovery/ehrzero, and installation in standard Python environments may be done from https://pypi.org/project/ehrzero/. To enable fast execution, some more compute-intensive features are disabled in this version. Results from this software are for demonstration purposes only and must not be interpreted as medical advice or serve as replacement for such.