Integration of ontology with machine learning to predict the presence of covid-19 based on symptoms

TL;DR

This paper presents an integrated approach combining ontology and machine learning to predict COVID-19 presence based on symptoms, achieving higher accuracy than traditional ML methods.

Contribution

It introduces a novel integration of ontology reasoning with decision tree rules to enhance COVID-19 prediction accuracy.

Findings

Ontology-based method achieved 97.4% accuracy

Outperformed various ML classification algorithms

Improved early detection of COVID-19 symptoms

Abstract

Coronavirus (covid 19) is one of the most dangerous viruses that have spread all over the world. With the increasing number of cases infected with the coronavirus, it has become necessary to address this epidemic by all available means. Detection of the covid-19 is currently one of the world's most difficult challenges. Data science and machine learning (ML), for example, can aid in the battle against this pandemic. Furthermore, various research published in this direction proves that ML techniques can identify illness and viral infections more precisely, allowing patients' diseases to be detected at an earlier stage. In this paper, we will present how ontologies can aid in predicting the presence of covid-19 based on symptoms. The integration of ontology and ML is achieved by implementing rules of the decision tree algorithm into ontology reasoner. In addition, we compared the outcomes with various ML classifications used to make predictions. The findings are assessed using performance measures generated from the confusion matrix, such as F-measure, accuracy, precision, and recall. The ontology surpassed all ML algorithms with high accuracy value of 97.4%, according to the results.