A two-step temporal data augmentation and supervised learning framework for predicting autism diagnosis at 36 months in patients with tuberous sclerosis complex.

Researchers developed a computer program to predict which children with tuberous sclerosis complex will develop autism by age 3. They used brain scans and behavioral tests to make these predictions. The study found that combining brain imaging and behavioral assessments at 24 months of age was effective for early prediction. This could help families access earlier support and interventions for children at high risk of autism.

This study developed a machine learning framework to predict autism diagnosis at 36 months in children with tuberous sclerosis complex (TSC), a population with 25-50% autism risk. Researchers integrated longitudinal brain imaging data (diffusion tensor imaging) from 27 white matter tracts with behavioral assessments (ADOS-2 and ADI-R) collected at multiple time points. A novel two-step data augmentation algorithm addressed irregular data collection timing by interpolating measurements to standardized ages. Regularized logistic regression models showed the most balanced performance across evaluation metrics.

Combining brain imaging at 24 months with behavioral features achieved comparable or slightly better prediction accuracy than using additional 12-month imaging data, suggesting 24-month assessments may be optimal timing for early prediction in this high-risk population.

May enable earlier identification of autism risk in children with TSC, potentially facilitating earlier intervention access. The 24-month assessment timeframe could inform clinical monitoring protocols. However, further validation studies with larger samples and external populations needed before clinical implementation.

Sample size not reported, limiting assessment of statistical power. Single study without external validation. Methodology details for data augmentation and model validation not fully described in abstract. Long-term clinical utility and implementation feasibility unclear.

Autism spectrum disorder (ASD) affects approximately 25-50% of children with tuberous sclerosis complex (TSC). Early identification of ASD in this high-risk population is crucial for timely intervention but remains challenging due to the heterogeneous clinical presentation and complex interplay of genetic, neurological, and environmental factors. This study aimed to integrate longitudinal diffusion tensor imaging (DTI) metrics with early behavioral features using supervised learning algorithms to predict ASD outcomes at 36 months. Data were obtained from the children enrolled in the TSC Autism Center of Excellence Research Network study.

Four DTI metrics: axial diffusivity, fractional anisotropy, mean diffusivity, and radial diffusivity, were measured across 27 major white matter tracts at up to four irregular time points. To account for variability in acquisition timing, we developed a two-step data augmentation algorithm to interpolate each subject's data to standardized ages of 12, 24, and 36 months. In addition, 9 behavioral features from the ADOS-2 and ADI-R assessments at 24 months were included. Supervised learning algorithms were trained to predict ASD diagnosis at 36 months under two input settings.

Performance of the supervised learning algorithms was evaluated with accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve as performance metrics. Regularized logistic regression models, least absolute shrinkage and selection operator and elastic net, demonstrated the most balanced overall performance across most evaluation metrics. Comparing input settings, Setting 1 (DTI at 24 months + behavioral features) achieved comparable or slightly improved performance relative to Setting 2 (DTI at 12 and 24 months + behavioral features) in predicting ASD diagnosis. Integrating early neuroimaging and behavioral data suggests potential for prediction of ASD outcomes at 36 months in children with TSC.

This multimodal machine learning framework highlights 24-month DTI and behavioral measures as key early biomarkers and demonstrates the effectiveness of regularized regression techniques for small-sample, heterogeneous clinical datasets.