Imperial College London
Portrait Picture

Dr Marcela P. Vizcaychipi

Faculty of Medicine, Department of Surgery & Cancer

Honorary Clinical Senior Lecturer
 
 
 
//

Contact

 

+44 (0)20 3315 8903m.vizcaychipi Website

 
 
//

Location

 

3.21Chelsea and Westminster HospitalChelsea and Westminster Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Peacock:2021:10.1007/978-3-030-70569-5_21,
author = {Peacock, S and Cinelli, M and Heldt, FS and McLachlan, L and Vizcaychipi, MP and McCarthy, A and Lipunova, N and Fletcher, RA and Hancock, A and Dürichen, R and Andreotti, F and Khan, RT},
doi = {10.1007/978-3-030-70569-5_21},
pages = {323--335},
title = {COVID-19 Patient Outcome Prediction Using Selected Features from Emergency Department Data and Feed-Forward Neural Networks},
url = {http://dx.doi.org/10.1007/978-3-030-70569-5_21},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - The severity of COVID-19 varies dramatically, ranging from asymptomatic infection to severe respiratory failure and death. Currently, few prognostic markers for disease outcomes exist, impairing patient triaging and treatment. Here, we train feed-forward neural networks on electronic health records of 819 confirmed SARS-CoV-2 positive patients admitted to a two-site NHS Trust hospital in London, England. To allow early risk assessment, the models ingest data collected in the emergency department (ED) to predict subsequent admission to intensive care, need for mechanical ventilation and in-hospital mortality. We apply univariate selection and recursive feature elimination to find the minimal subset of clinical variables needed for accurate prediction. Our models achieve AUC-ROC scores of 0.78 to 0.87, outperforming standard clinical risk scores. This accuracy is reached with as few as 13% of clinical variables routinely collected within the ED, which increases the practical applicability of such algorithms. Hence, state-of-the-art neural networks can predict severe COVID-19 accurately and early from a small subset of clinical variables.
AU  - Peacock,S
AU  - Cinelli,M
AU  - Heldt,FS
AU  - McLachlan,L
AU  - Vizcaychipi,MP
AU  - McCarthy,A
AU  - Lipunova,N
AU  - Fletcher,RA
AU  - Hancock,A
AU  - Dürichen,R
AU  - Andreotti,F
AU  - Khan,RT
DO  - 10.1007/978-3-030-70569-5_21
EP  - 335
PY  - 2021///
SN  - 1867-8211
SP  - 323
TI  - COVID-19 Patient Outcome Prediction Using Selected Features from Emergency Department Data and Feed-Forward Neural Networks
UR  - http://dx.doi.org/10.1007/978-3-030-70569-5_21
ER  -
Download