Research Article
COVID-19 Patient Outcome Prediction Using Selected Features from Emergency Department Data and Feed-Forward Neural Networks
@INPROCEEDINGS{10.1007/978-3-030-70569-5_21, author={Sophie Peacock and Mattia Cinelli and Frank S. Heldt and Lachlan McLachlan and Marcela P. Vizcaychipi and Alex McCarthy and Nadezda Lipunova and Robert A. Fletcher and Anne Hancock and Robert D\'{y}richen and Fernando Andreotti and Rabia T. Khan}, title={COVID-19 Patient Outcome Prediction Using Selected Features from Emergency Department Data and Feed-Forward Neural Networks}, proceedings={Wireless Mobile Communication and Healthcare. 9th EAI International Conference, MobiHealth 2020, Virtual Event, November 19, 2020, Proceedings}, proceedings_a={MOBIHEALTH}, year={2021}, month={7}, keywords={Machine learning COVID-19 Electronic health records}, doi={10.1007/978-3-030-70569-5_21} }- Sophie Peacock
Mattia Cinelli
Frank S. Heldt
Lachlan McLachlan
Marcela P. Vizcaychipi
Alex McCarthy
Nadezda Lipunova
Robert A. Fletcher
Anne Hancock
Robert Dürichen
Fernando Andreotti
Rabia T. Khan
Year: 2021
COVID-19 Patient Outcome Prediction Using Selected Features from Emergency Department Data and Feed-Forward Neural Networks
MOBIHEALTH
Springer
DOI: 10.1007/978-3-030-70569-5_21
Abstract
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.
