AI-Based Diagnosis of Novel Coronavirus Using Radiograph Images

Résumé fourni par la source

The therapeutic value of artificial intelligence (ML) in the diagnosis of viral illnesses has been illustrated by the outbreak of COVID-19. This chapter digs into the modern uses of Artificial Intelligence and Machine Learning (ML) algorithms for COVID-19 diagnosis, with a focus on chest imaging procedures like as CT and X-rays. Additionally, we explored ML's strengths, such as its capacity to analyze enormous datasets and detect patterns in medical imagery. But there are still issues to deal with, like the scarcity of data, privacy issues, and machine learning's incapacity to evaluate the severity of health conditions. However, several machine learning methods, such as decision trees, random forests, and convolutional neural networks, are reviewed in this research concerning COVID-19 diagnosis. Subsequently, we highlight the efficacy of several models in COVID-19 screening, such as XGBoost and Truncated Inception Net. Moreover, the chapter discusses potential strategies for machine learning in COVID-19 diagnosis, emphasizing the crucial role of collaboration among data scientists and healthcare experts. It is imperative to confront data bias and incorporate more comprehensive patient data than just chest imaging. All things considered, machine learning presents a potential pathway toward quick and precise COVID-19 diagnosis; nonetheless, conquering existing obstacles is necessary for ML to be widely used in healthcare institutions.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.