A comprehensive review of early detection of COVID-19 based on machine learning and deep learning models

Abstrak

This paper reviews the use of machine learning (ML) and deep learning (DL) for early coronavirus disease (COVID-19) detection, highlighting their potential to overcome the limitations of traditional diagnostic methods such as long processing times and high costs. We analyze studies applying ML and DL to imaging, clinical, and genomic data, assessing their performance in terms of accuracy, sensitivity, specificity, and efficiency. The review discusses the advantages, limitations, and challenges of these models, including data quality, generalizability, and ethical considerations. It also suggests future research directions for improving model efficacy, such as integrating multi-modal data and developing more interpretable models. This concise review serves as a guide for researchers, healthcare practitioners, and policymakers on the advancements and prospects of ML and DL in early COVID-19 detection, promoting further innovation and collaboration in this vital public health domain.