Background Analyzing the unstructured textual data contained in electronic health records (EHRs) has always been a challenging task. Word embedding methods have become an essential foundation for neural network-based approaches in natural language processing (NLP), to learn dense and low-dimensional word representations from large unlabeled corpora that capture the implicit semantics of words. Models like Word2Vec, GloVe or FastText have been broadly applied and reviewed in the bioinformatics and healthcare fields, most often to embed clinical notes or activity and diagnostic codes. Visualization of the learned embeddings has been used in a subset of these works, whether for exploratory or evaluation purposes. However, visualization practices tend to be heterogeneous, and lack overall guidelines. Objective This scoping review aims to describe the methods and strategies used to visualize medical concepts represented using word embedding methods. We aim to understand the objectives of the visualizations and their limits. Methods This scoping review summarizes different methods used to visualize word embeddings in healthcare. We followed the methodology proposed by Arksey and O’Malley (Int J Soc Res Methodol 8:19–32, 2005) and by Levac et al. (Implement Sci 5:69, 2010) to better analyze the data and provide a synthesis of the literature on the matter. Results We first obtained 471 unique articles from a search conducted in PubMed, MedRxiv and arXiv databases. 30 of these were effectively reviewed, based on our inclusion and exclusion criteria. 23 articles were excluded in the full review stage, resulting in the analysis of 7 papers that fully correspond to our inclusion criteria. Included papers pursued a variety of objectives and used distinct methods to evaluate their embeddings and to visualize them. Visualization also served heterogeneous purposes, being alternatively used as a way to explore the embeddings, to evaluate them or to merely illustrate properties otherwise formally assessed. Conclusions Visualization helps to explore embedding results (further dimensionality reduction, synthetic representation). However, it does not exhaust the information conveyed by the embeddings nor constitute a self-sustaining evaluation method of their pertinence.
Health data science is an emerging discipline that bridges computer science, statistics and health domain knowledge. This consists of taking advantage of the large volume of data, often complex, to extract information to improve decision-making. We have created a Master’s degree in Health Data Science to meet the growing need for data scientists in companies and institutions. The training offers, over two years, courses covering computer science, mathematics and statistics, health and biology. With more than 60 professors and lecturers, a total of 835 hours of classes (not including the mandatory 5 months of internship per year), this curriculum has enrolled a total of 53 students today. The feedback from the students and alumni allowed us identifying new needs in terms of training, which may help us to adapt the program for the coming academic years. In particular, we will offer an additional module covering data management, from the edition of the clinical report form to the implementation of a data warehouse with an ETL process. Git and application lifecycle management will be included in programming courses or multidisciplinary projects.
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.