nlp-pucrs/fall-detection

Fall Detection in EHR using Word Embeddings and Deep Learning

fall-detection

Fall Detection in EHR using Word Embeddings and Deep Learning

Author: Henrique D. P. dos Santos, Amanda P. Silva, Maria Carolina O. Maciel, Haline Maria V. Burin, Janete S. Urbanetto and Renata Vieira

Abstract: Electronic health records (EHR) are an important source of information to detect adverse events in patients. In-hospital fall incidents represent the largest category of adverse event reports. The detection of such incidents leads to better understanding of the event and improves the quality of patient health care. In this work, we evaluate several language models with state-of-the art recurrent neural networks (RNN) to detect fall incidents in progress notes. Our experiments show that the deep-learning approach outperforms previous works in the task of detecting fall events. Vector representation of words in the health domain was able to detect falls with an F-Measure of 90%. Additionally, we made available an annotated dataset with 1,078 de-identified progress notes for replication purposes.

Keywords: Fall Detection, Electronic Health Records, Text Classification, Word Embeddings, Deep Learning

Full Text, BibText

Online Experiments

Run our experiments online with Binder

PUCRS A.I. in HealthCare

This project belongs to GIAS at PUCRS, Brazil

fall-detection's Issues

Baseline Model Code

Dear Authors,

I found that this github is incredible useful to learn NLP deep learning. When I started to run the base line method - SVM and Random Forest with TFIDF word weighting, I can't find sample code in your repo. Could you share some it please? Thanks a lot.