Learning efficient representations for concepts has been proven to be an important basis for many applications such as machine translation or document classification. Proper representations of medical concepts such as diagnosis, medication, procedure codes and visits will have broad applications in healthcare analytics. However, in Electronic Health Records (EHR) the visit sequences of patients include multiple concepts (diagnosis, procedure, and medication codes) per visit. This structure provides two types of relational information, namely sequential order of visits and co-occurrence of the codes within each visit. In this work, we propose Med2Vec, which not only learns distributed representations for both medical codes and visits from a large EHR dataset with over 3 million visits, but also allows us to interpret the learned representations confirmed positively by clinical experts. In the experiments, Med2Vec displays significant improvement in key medical applications compared to popular baselines such as Skipgram, GloVe and stacked autoencoder, while providing clinically meaningful interpretation.
OBJECTIVE:To determine the rate of return visits to pediatric emergency departments (EDs) and identify patient-and visit-level factors associated with return visits and hospitalization upon return. DESIGN AND SETTING:Retrospective cohort study of visits to 23 pediatric EDs in 2012 using data from the Pediatric Health Information System. PARTICIPANTS:Patients <18 years old discharged following an ED visit. MEASURES:The primary outcomes were the rate of return visits within 72 hours of discharge from the ED and of return visits within 72 hours resulting in hospitalization. Results: 1,415,721 of the 1,610,201 ED visits to study hospitals resulted in discharge. Of the discharges, 47,294 patients (3.3%) had a return visit. Of these revisits, 9295 (19.7%) resulted in hospitalization. In multivariate analyses, the odds of having a revisit were higher for patients with a chronic condition (odds ratio [OR]
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.