Development of a Risk-Free COVID-19 Screening Algorithm from Routine Blood Tests Using Ensemble Machine Learning

TL;DR

This paper presents a highly accurate ensemble machine learning model that uses routine blood tests for risk-free COVID-19 screening, offering a scalable, low-cost alternative to traditional testing methods.

Contribution

It introduces a novel stacked ensemble machine learning approach that achieves near-perfect accuracy using common blood tests for COVID-19 detection.

Findings

Achieved 100% accuracy, precision, recall, and F1-score in COVID detection

Demonstrated the model's potential for large-scale, low-cost screening

Validated the model's effectiveness through R-curve analysis

Abstract

The Reverse Transcription Polymerase Chain Reaction (RTPCR)} test is the silver bullet diagnostic test to discern COVID infection. Rapid antigen detection is a screening test to identify COVID positive patients in little as 15 minutes, but has a lower sensitivity than the PCR tests. Besides having multiple standardized test kits, many people are getting infected and either recovering or dying even before the test due to the shortage and cost of kits, lack of indispensable specialists and labs, time-consuming result compared to bulk population especially in developing and underdeveloped countries. Intrigued by the parametric deviations in immunological and hematological profile of a COVID patient, this research work leveraged the concept of COVID-19 detection by proposing a risk-free and highly accurate Stacked Ensemble Machine Learning model to identify a COVID patient from communally available-widespread-cheap routine blood tests which gives a promising accuracy, precision, recall and F1-score of 100%. Analysis from R-curve also shows the preciseness of the risk-free model to be implemented. The proposed method has the potential for large scale ubiquitous low-cost screening application. This can add an extra layer of protection in keeping the number of infected cases to a minimum and control the pandemic by identifying asymptomatic or pre-symptomatic people early.