<![CDATA[Dengue, a fast-spreading vector-borne infectious disease, requires early prediction and prompt decision-making for effective control. To address this issue, we present a comprehensive scoping review and bibliometric analysis (ScoRBA) that aims to map the current literature landscape, identify main research themes, and offer valuable insights into advancements and challenges in dengue infection and machine learning research. Materials for this analysis consist of scholarly articles related to dengue and machine learning research retrieved from the Scopus database. Our method involves a rigorous literature examination, utilizing keyword co-occurrence analysis. Our study reveals a growing interest in dengue and machine learning research, reflected in an increasing number of publications. Through keyword co-occurrence analysis, we identify four major research themes: Data mining using machine learning for dengue prediction, Deep learning approach for dengue prediction models, Neural network optimization for dengue diagnostic systems, and Climate-driven dengue prediction with IoT & remote sensing. Advancements include substantial improvements in prediction models through machine learning and IoT integration, albeit with identified limitations, necessitating ongoing research and refinement. Our findings hold direct implications for public health professionals, academics, and decision-makers, offering data-driven strategies for dengue outbreak control. The identified research themes act as a roadmap for future investigations, guiding the development of more robust tools for early prediction and decision-making in the battle against dengue. This study contributes to understanding the evolving landscape of dengue research, facilitating informed actions to mitigate the impact of this infectious disease. ]]>
Copyrights © 2024
