Development of data-driven machine learning models and their potential role in predicting dengue outbreak
Bushra Mazhar, Nazish Mazhar Ali, Farkhanda Manzoor, Muhammad Kamran Khan, Muhammad Nasir, Muhammad Ramzan
Abstract
Dengue fever is one of the most widespread vector-borne viral infections in the world, resulting in increased socio-economic burden. WHO has reported that 2.5 billion people are infected with dengue fever across the world, resulting in high mortalities in tropical and subtropical regions. The current article endeavors to present an overview of predicting dengue outbreaks through data-based machine-learning models. This artificial intelligence model uses real world data such as dengue surveillance, climatic variables, and epidemiological data and combines big data with machine learning algorithms to forecast dengue. Monitoring and predicting dengue incidences has been significantly enhanced through innovative approaches. This involves gathering data on various climatic factors, including temperature, rainfall, relative humidity, and wind speed, along with monthly records of dengue cases. The study functions as an efficient warning system, enabling the anticipation of dengue outbreaks. This early warning system not only alerts communities but also aids relevant authorities in implementing crucial preventive measures.