Characterizing Sleep Disorders in an Autism-Specific Collection of Electronic Health Records

Background Sleep problems are common in individuals with autism spectrum disorder (ASD). This study reviews one detailed approach to querying the electronic health record (EHR). Methods We developed methods for identifying individuals with ASD and defined their sleep problems using International Classification of Diseases (ICD) codes or key words. We examined treatment responses to melatonin. Results Sleep problems were documented in 86% of patients and using specific keywords yielded more sleep diagnoses than ICD codes alone. About two-thirds of patients benefitted from melatonin. Conclusions Our study provides a framework for using deidentified medical records to characterize sleep, a common co-occurring condition, in ASD. Using specific keywords could be helpful in future work that queries the EHR.