DDPM: A Dengue Disease Prediction and Diagnosis Model Using Sentiment Analysis and Machine Learning Algorithms.

Area of Science:

• Medical Entomology
• Infectious Diseases
• Public Health

Background:

• Dengue viruses, transmitted by Aedes mosquitoes, cause dengue fever, a significant global health concern.
• In 2019, the World Health Organization estimated 100-400 million dengue infections globally, highlighting its status as a top public health risk.
• Accurate early diagnosis and prediction are crucial for timely supportive care and to prevent severe outcomes like dengue hemorrhagic fever and dengue shock syndrome.

Purpose of the Study:

• To develop an effective machine learning method for forecasting dengue fever.
• To address the limitations of current predictive models, which are often in early stages and lack semantic precision at the sentence or phrase level.

Main Methods:

• Proposing the construction of a machine learning model specifically designed for dengue fever prediction.
• Leveraging data from microarrays and RNA-Seq for developing predictive models.
• Addressing limitations of existing text-mining algorithms (e.g., Bayesian inferences, support vector machines) that struggle with fine-grained sentiment analysis.

Main Results:

• The research focuses on constructing a new machine learning approach for dengue fever forecasting.
• The proposed method aims to overcome semantic weaknesses of traditional text analysis techniques.

Conclusions:

• A novel machine learning approach is proposed to enhance the prediction of dengue fever.
• Developing accurate predictive models is essential for early intervention and managing the global dengue burden.