Analysis of Deep Learning Techniques to Investigate and Support Diagnosis of Virus Borne Diseases
Srishti Choubey, Snehlata Barde, Abhishek Badholia · 2022 3rd International Conference on Electronics and Sustainable Communication Systems (ICESC) · 2022
The poorest individuals, who often reside in remote, rural areas, urban slums, or conflict zones, are disproportionately affected by neglected tropical illnesses (NTDs). Arboviruses are one of the most major subgroups of mosquito-borne NTDs. In Latin America and South America, three kinds of arboviruses impact a major section of the population. The names of these viruses are Dengue, Chikungunya, and Zika. The clinical identification of distinct arboviral infections is a difficult task. Due to the continuous circulation of several arboviruses, all of which have symptoms that are very similar, test results are often erroneous. This study explores the most current advancements in Machine Learning (ML) and Deep Learning (DL) models for the automated classification of arboviral diseases. According to the results, the major focus of the current research is on categorizing dengue using tree-based machine learning approaches. Utilizing a high-quality clinical decision support system for the treatment of arboviral infections may enhance the overall quality of the clinical process, hence increasing the diagnostic and therapeutic accuracy. It should facilitate clinicians' decision-making and, subsequently, increase resource use and the quality of life for patients.