Machine learning-based automation of COVID-19 screening using clinical dataset

Authors

Jezreel Sophia C. Lanuzo Institute of Mathematical Sciences and Physics, University of the Philippines Los Baños
Joverlyn Gaudillo Institute of Mathematical Sciences and Physics, University of the Philippines Los Baños
Ranzivelle Marianne Roxas-Villanueva Institute of Mathematical Sciences and Physics, University of the Philippines Los Baños
Beatrice Tiangco Augusto P. Sarmiento Cancer Institute, The Medical City and National Institutes of Health, University of the Philippines Manila
Jason Albia Institute of Mathematical Sciences and Physics, University of the Philippines Los Baños

Abstract

Fast and effective screening of COVID-19 patients can help decrease its mortality rate. In this study, we employed machine learning methods on clinical datasets for automated COVID-19 screening. The model configuration with a decision tree as the classifier, forward selection as a feature selection method, and six features has 91% precision, 85% accuracy, 92% sensitivity, and 91% F1-score. We also determined the following relevant features identified by the employed feature selection technique that helped screen COVID-19 patients: lymphocytes, chest X-ray label, BMI, PCT, eGFR result, and comorbidity chronic lung disease. This study demonstrates the potential of machine learning models trained on clinical data in classifying COVID-19 patients to help facilitate the screening procedure.

Downloads

Issue

2021: Proceedings of the 39th Samahang Pisika ng Pilipinas Physics Conference

Article ID

SPP-2021-3C-05

Section

Biological and Medical Physics

Published

2021-10-04

How to Cite

[1]

JSC Lanuzo, J Gaudillo, RM Roxas-Villanueva, B Tiangco, and J Albia, Machine learning-based automation of COVID-19 screening using clinical dataset, Proceedings of the Samahang Pisika ng Pilipinas 39, SPP-2021-3C-05 (2021). URL: https://proceedings.spp-online.org/article/view/SPP-2021-3C-05.