Objective: We describe the development and evaluation of a system that uses machine learning and natural language processing techniques to identify potential candidates for surgical intervention for drug-resistant pediatric epilepsy. The data are comprised of free-text clinical notes extracted from the electronic health record (EHR). Both known clinical outcomes from the EHR and manual chart annotations provide gold standards for the patient’s status. The following hypotheses are then tested: 1) machine learning methods can identify epilepsy surgery candidates as well as physicians do and 2) machine learning methods can identify candidates earlier than physicians do. These hypotheses are tested by systematically evaluating the effects of the data source, amount of training data, class balance, classification algorithm, and feature set on classifier performance. The results support both hypotheses, with F-measures ranging from 0.71 to 0.82. The feature set, classification algorithm, amount of training data, class balance, and gold standard all significantly affected classification performance. It was further observed that classification performance was better than the highest agreement between two annotators, even at one year before documented surgery referral. The results demonstrate that such machine learning methods can contribute to predicting pediatric epilepsy surgery candidates and reducing lag time to surgery referral.
Individuals with methyl CpG binding protein 2 (MECP2) duplication syndrome (MDS) have varying degrees of severity in their mobility, hand use, developmental skills, and susceptibility to infections. In the present study, we examine the relationship between duplication size, gene content, and overall phenotype in MDS using a clinical severity scale. Other genes typically duplicated within Xq28 (eg, GDI1, RAB39B, FLNA) are associated with distinct clinical features independent of MECP2. We additionally compare the phenotype of this cohort (n = 48) to other reported cohorts with MDS. Utilizing existing indices of clinical severity in Rett syndrome, we found that larger duplication size correlates with higher severity in total clinical severity scores (r = 0.36; P = 0.02), and in total motor behavioral assessment inventory scores (r = 0.31; P = 0.05). Greater severity was associated with having the RAB39B gene duplicated, although most of these participants also had large duplications. Results suggest that developmental delays in the first 6 months of life, hypotonia, vasomotor disturbances, constipation, drooling, and bruxism are common in MDS. This is the first study to show that duplication size is related to clinical severity. Future studies should examine whether large duplications which do not encompass RAB39B also contribute to clinical severity. Results also suggest the need for creating an MDS specific severity scale.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.