Journal of biomedical informatics
-
Word embeddings have been prevalently used in biomedical Natural Language Processing (NLP) applications due to the ability of the vector representations being able to capture useful semantic properties and linguistic relationships between words. Different textual resources (e.g., Wikipedia and biomedical literature corpus) have been utilized in biomedical NLP to train word embeddings and these word embeddings have been commonly leveraged as feature input to downstream machine learning models. However, there has been little work on evaluating the word embeddings trained from different textual resources. ⋯ Based on the evaluation results, we can draw the following conclusions. First, the word embeddings trained from EHR and MedLit can capture the semantics of medical terms better, and find semantically relevant medical terms closer to human experts' judgments than those trained from GloVe and Google News. Second, there does not exist a consistent global ranking of word embeddings for all downstream biomedical NLP applications. However, adding word embeddings as extra features will improve results on most downstream tasks. Finally, the word embeddings trained from the biomedical domain corpora do not necessarily have better performance than those trained from the general domain corpora for any downstream biomedical NLP task.
-
High-quality cardiopulmonary resuscitation (CPR) is a key factor affecting cardiac arrest survival. Accurate monitoring and real-time feedback are emphasized to improve CPR quality. The purpose of this study was to develop and validate a novel depth estimation algorithm based on a smartwatch equipped with a built-in accelerometer for feedback instructions during CPR. ⋯ Our study indicates that the algorithm developed for estimating CCD based on a smartwatch with a built-in accelerometer is promising. Further studies will be conducted to evaluate its application for CPR training and clinical practice.