A machine learning approach to differentiate between COVID-19 and influenza infection using synthetic infection and immune response data

Mathematical Biosciences and Engineering

Suzan Farhang-Sardroodi¹  Jane M Heffernan¹  Hsu Kiang Ooi²  Mohammad Sajjad Ghaemi²  Morgan Craig³ 

[1] 1. Modelling Infection and Immunity Lab, Mathematics Statistics, York University, Toronto, Canada 2. Centre for Disease Modelling (CDM), Mathematics Statistics, York University, Toronto, Canada;3. Digital Technologies Research Centre, National Research Council Canada, Toronto, ON, Canada;4. Sainte-Justine University Hospital Research Centre and Department of Mathematics and Statistics, Université de Montréal, Montreal, Quebec, Canada;

关键词: biological systems;    mechanistic model;    infectious disease;    influenza (flu);    covid-19;    machine learning;    classification;    logistic regression;    regularization;    lasso;    ridge;    pls-da;   

DOI  :  10.3934/mbe.2022272

来源: DOAJ

【 摘 要 】

Data analysis is widely used to generate new insights into human disease mechanisms and provide better treatment methods. In this work, we used the mechanistic models of viral infection to generate synthetic data of influenza and COVID-19 patients. We then developed and validated a supervised machine learning model that can distinguish between the two infections. Influenza and COVID-19 are contagious respiratory illnesses that are caused by different pathogenic viruses but appeared with similar initial presentations. While having the same primary signs COVID-19 can produce more severe symptoms, illnesses, and higher mortality. The predictive model performance was externally evaluated by the ROC AUC metric (area under the receiver operating characteristic curve) on 100 virtual patients from each cohort and was able to achieve at least AUC = 91% using our multiclass classifier. The current investigation highlighted the ability of machine learning models to accurately identify two different diseases based on major components of viral infection and immune response. The model predicted a dominant role for viral load and productively infected cells through the feature selection process.

【 授权许可】

Unknown