ABSTRACT
Severe Acute Respiratory Syndrome (SARS) and Middle East Respiratory Syndrome (MERS) are two of the most serious illnesses caused by the coronavirus (COV) family of viruses, which includes a large number of different viruses. MERS-COV and SARS-COV coronaviruses are the main carriers of these two diseases. Due to a critical shortage of COVID-19 diagnoses, the ongoing COV disease 2019 (COVID-19) pandemic is putting tremendous pressure on healthcare systems around the world. The need for accurate and reliable diagnosis becomes critical as more COVID-19 cases are being reported. Based on the patient’s symptoms and the results of traditional tests, the study suggests utilizing machine learning to build a more precise diagnostic model for COVID-19. In order to develop models that can more accurately predict the presence of an infectious disease, the COVID-19 data can be used to train machine learning algorithms that have been used to identify different infectious diseases. The model can be trained to recognize the initial, mild, and severe stages of COVID-19 infections, allowing for more accurate diagnosis and timely interventions. The dataset is then trained and evaluated using ML methods such as support vector machines (SVMs), random forests, and artificial neural networks (ANNs) to analyze infections. These machine learning techniques can be used to more accurately identify stages of COVID-19 infection by analyzing symptom datasets. The performance of each algorithm was evaluated at various time points on the training set. The empirical result has witnessed that the ANN and random forest algorithms outperformed the SVM model in terms of accuracy for all phases of infections.
