Analyzing Machine Learning Frameworks for Detection of Monkeypox Virus Across the Globe

Recently, Monkeypox has spread to numerous nations, causing a life-threatening health concerns to both humans as well as animals. This sudden appearance of Monkeypox cases in different countries has shuttered the entire world. In this view, researchers are kept on proposing novel frameworks based on machine learning in order to ensure timely as well as efficient detection of Monkeypox virus across the world. This study has shown a comparative analysis of numerous existing frameworks based on machine learning in terms of four different metrics i.e. accuracy, precision, recall and Fl-score. Further, graphical analysis shows that researchers are kept on trying to provide best performance in the detection of Monkeypox across the globe. It is also found that some of the frameworks are only able to provide best performance with smaller datasets and without considering any other relevant attributes like security. In the current year, this research gap of utilizing smaller datasets and non-considering of other attributes like security of patients' data is seen to be decreasing gradually.