Rapid classification of autism for public health surveillance


This presentation given August 3, 2017 describes work toward applying machine learning methods to CDC’s autism surveillance program. CDC’s population-based autism surveillance is labor-intensive and costly, as it requires clinicians to manually review children’s medical and educational records for descriptions of autism symptoms. Using the words in these records, our team is building algorithms to predict which children will meet the surveillance case definition for autism. This talk describes our early results, recent progress, and perspectives gained from working with textual data.


Matthew Maenner, PhD, Epidemiologist, National Center on Birth Defects and Developmental Disabilities, US Centers for Disease Control and Prevention 

Primary Topic Areas: 
Original Publication Year: 
Event/Publication Date: 
August, 2017

August 04, 2017

Contact Us


288 Grove Street, Box 203
Braintree, MA 02184
(617) 779 0880

This Knowledge Repository is made possible through the activities of the Centers for Disease Control and Prevention Cooperative Agreement/Grant #1 NU500E000098-01, National Surveillance Program Community of Practice (NSSP-CoP): Strengthening Health Surveillance Capabilities Nationwide, which is in the interest of public health.

Site created by Fusani Applications