nlp-pucrs / cci-regression

Charlson Comorbidity Index Regression using Clinical Notes

Home Page:http://www.inf.pucrs.br/ia-saude/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Charlson Comorbidity Index Regression

An initial investigation of Charlson comorbidity index Regression based on Clinical Notes

Author: Henrique D. P. dos Santos, Ana Helena D. P. S. Ulbrich, Vinicius Woloszyn, and Renata Vieira

Abstract: The Charlson comorbidity index (CCI) is widely used to predict mortality for patients who may have many comorbid conditions. Such index is also used as an indicator of the patients' complexity inside a hospital. In this paper, we evaluate a variety of feature extraction and regression methods to predict the CCI from clinical notes. We used a tertiary hospital dataset with 48 thousand hospitalizations featuring the CCI annotated by physicians. In our experiments, Dense Neural Networks with Word Embeddings proved to be the best regression method, with a mean absolute error of 0.51.

Full Text, BibText

Complete Reference: Henrique D. P. dos Santos, Ana Helena D. P. S. Ulbrich, Vinicius Woloszyn, and Renata Vieira. 2018. An initial investigation of the Charlson comorbidity index regression based on clinical notes. 31st International Symposium on Computer-Based Medical Systems, CBMS 2018, 6 pages.

Pre-trained Word Vector for Health in Portuguese

http://www.inf.pucrs.br/linatural/wordpress/index.php/recursos-e-ferramentas/word-embeddings-para-saude/

PUCRS NLP Group

This project belongs to NLP Group at PUCRS, Brazil

About

Charlson Comorbidity Index Regression using Clinical Notes

http://www.inf.pucrs.br/ia-saude/

License:Apache License 2.0


Languages

Language:Jupyter Notebook 98.8%Language:Python 1.1%Language:TeX 0.1%