Imperial College London
Portrait Picture

Erik Mayer

Faculty of Medicine, Department of Surgery & Cancer

Clinical Reader in Urology
 
 
 
//

Contact

 

e.mayer Website

 
 
//

Location

 

1020Queen Elizabeth the Queen Mother Wing (QEQM)St Mary's Campus

//

Summary

 

Publications

Citation

BibTex format

@inbook{Altuncu:2019,
author = {Altuncu, MT and Sorin, E and Symons, JD and Mayer, E and Yaliraki, SN and Toni, F and Barahona, M},
title = {Extracting information from free text through unsupervised graph-based  clustering: an application to patient incident records},
url = {http://arxiv.org/abs/1909.00183v1},
year = {2019}
}
Download

RIS format (EndNote, RefMan)

TY  - CHAP
AB  - The large volume of text in electronic healthcare records often remainsunderused due to a lack of methodologies to extract interpretable content. Herewe present an unsupervised framework for the analysis of free text thatcombines text-embedding with paragraph vectors and graph-theoretical multiscalecommunity detection. We analyse text from a corpus of patient incident reportsfrom the National Health Service in England to find content-based clusters ofreports in an unsupervised manner and at different levels of resolution. Ourunsupervised method extracts groups with high intrinsic textual consistency andcompares well against categories hand-coded by healthcare personnel. We alsoshow how to use our content-driven clusters to improve the supervisedprediction of the degree of harm of the incident based on the text of thereport. Finally, we discuss future directions to monitor reports over time, andto detect emerging trends outside pre-existing categories.
AU  - Altuncu,MT
AU  - Sorin,E
AU  - Symons,JD
AU  - Mayer,E
AU  - Yaliraki,SN
AU  - Toni,F
AU  - Barahona,M
PY  - 2019///
TI  - Extracting information from free text through unsupervised graph-based  clustering: an application to patient incident records
UR  - http://arxiv.org/abs/1909.00183v1
ER  -
Download