Search reports, ask a question, or jump to a page.
The problem
Intervention: Machine learning system using weighted naive Bayes algorithm to fuse EEG, eye fixation, and facial expression data for ASD detection
Who it was tested with: Children with autism spectrum disorder and typically developing children (specific sample size not stated).
Experience from people who deliver programmes: stories, case studies and lessons learned. Valuable for understanding how and why, and for spotting what to test next, but not a measure of effect.
The document states: "a hybrid fusion approach based on a weighted naive Bayes algorithm was presented for multimodal data fusion with a classification accuracy of 87.50%." The study tests whether machine learning can classify children with ASD from behavioral and physiological measurements, but the validation methodology and independent testing are not clearly specified, placing this at the practitioner tier.
Study design unclear; sample characteristics and size not reported; validation approach not described; no comparison with standard diagnostic methods; unclear whether results represent test accuracy on held-out data or training data
Across countries and designs
1 study · 1 country
