There is a need for scalable, objective assessment tools to quantify autism-related behaviors in preschool- and school-age children. A significant challenge is the heterogeneous presentation of autism, driven in part by co-occurring conditions such as Attention-Deficit/Hyperactivity Disorder (ADHD). Tools intended for autism must therefore be tested in samples that include ADHD and other comorbidities, not only in autism-versus-neurotypical comparisons. SenseToKnow, a digital phenotyping app, quantifies autism-related behaviors using computer vision, tactile sensors, and machine learning, distinguishing autistic and neurotypical toddlers. We administered SenseToKnow to 183 children aged 40–100 months (3.3–8.3 years): 41 neurotypical, 48 ADHD, 53 autism, and 41 co-occurring autism and ADHD. Two complementary analyses converged. In age-adjusted group comparisons, autistic children, with and without ADHD, exhibited different SenseToKnow features compared to neurotypical and ADHD children, while autistic children with and without ADHD did not differ; children with ADHD alone differed from neurotypical children, particularly during nonsocial stimuli. Furthermore, in regression modeling, autism status was associated with 21 of 23 SenseToKnow features and ADHD status with none. Across both analysis, SenseToKnow features tracked autism status rather than ADHD status, even when the two co-occurred. These results demonstrate that SenseToKnow captures autism-associated behaviors even in the presence of co-occurring ADHD.
Vikram Aikat, Kimberly L. H. Carpenter, J. Matias Di Martino et al.· Scientific Reports· 0 citations
Abstract Objectives Building on innovations for autism detection—where artificial intelligence (AI)-based models monitor clinical data within electronic health records—this study evaluates the context for clinical decision support (CDS) deployment and identifies design preferences. Materials and Methods This observational study utilized contextual inquiry to elicit perspectives from 8 clinicians and twenty caregivers during 18- to 24-month well-child visits at Duke-affiliated clinics. Data were analyzed using rapid qualitative analysis techniques. Results Workflow analysis identified 6 user tasks, 3 technology-user interactions, and 5 clinical decision points. Technologies that streamlined screening included patient portals, digital tablets, and note templates. Clinicians identified 2 major barriers—limited screening tool accuracy and challenges in implementing follow-up steps—and 3 facilitators: electronic screening, early intervention provider input, and staff referral coordination support. For design, CDS should include clear, actionable outputs, with explanations of prediction data, visual summaries linked to next steps, and educational resources. Embedding CDS within the EHR, with outputs delivered at key points during the clinical encounter, along with caregiver-facing materials, would improve workflow efficiency. Discussion Findings highlight key integration points for an autism detection AI-based CDS tool and stress the need for clinical utility and caregiver-centered communication. Effective design requires alignment with clinical workflow, including the timing of outputs, meaningful explanations, and integration with caregiver communication. Conclusion Findings will inform the design of an AI-based CDS tool for autism detection, providing workflow-informed integration points and user preferences. Future work should refine explainability and optimize delivery of outputs within clinical encounters to support decision-making and caregiver engagement.
Adesuwa Emovon, Lauren P. Driggers-Jones, Matthew M Engelhard et al.· JAMIA Open· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
