Early Detection of Monkeypox Based on Visible Symptoms using Deep Learning

Abstract

Monkeypox is one of the zoonotic diseases that has been transmitted to humans from animals. Recently, it has been spreading widely among people. It is classified as an Orthopoxvirus with an animal source. In some cases, infection with this disease can lead to death. The clinical symptoms of this disease are similar to those of chickenpox. Rapid clinical identification and diagnosis of monkeypox can be challenging due to its similarity to measles and smallpox. This paper aims to identify monkeypox based on the symptoms that appear in patients during the infection period, infections, and fever on the human body, without the need to locate the site of infection on the skin. This is challenging due to the similarity of symptoms between different types of poxviruses. This paper summarizes the global spread of monkeypox, with the design of a deep learning model to predict the disease. The paper concludes by emphasizing the need for an automated system for prediction and diagnosis of monkeypox to make the environment safer for individuals.