Machine Learning Based Early Detection Of Dengue Using CBC Data

This research presents a machine learning-based framework for dengue risk assessment using Complete Blood Count (CBC) parameters. The developed system examines routine blood test values to identify patterns associated with dengue infection and generate timely risk predictions. A web-based platform enables users to access the system easily and obtain rapid screening results. The study demonstrates the effectiveness of data-driven techniques in supporting early dengue detection and assisting healthcare professionals during preliminary evaluation. By providing quick and reliable risk assessment, the proposed solution can contribute to improved screening efficiency and informed clinical decision-making.   Future enhancements may focus on incorporating additional clinical indicators and laboratory measurements to strengthen prediction performance. The framework can also be extended to support the identification of other infectious diseases through a unified prediction model. Integration with hospital information systems and electronic health records would enable automated data handling and real-time monitoring. Furthermore, mobile application deployment can improve accessibility in remote and resource-limited areas. The inclusion of explainable artificial intelligence techniques may provide greater transparency in predictions and increase confidence in the system's recommendations.

1.         World Health Organization (WHO), Dengue and Severe Dengue, WHO Fact Sheet, 2023. 2.         Centers for Disease Control and Prevention (CDC), Dengue: Epidemiology and Prevention, CDC Publications, 2023. 3.         Davi, C., et al., “Machine Learning Approaches for Dengue Prediction Using Clinical and Genomic Data,” Journal of Medical Systems, vol. 45, no. 3, pp. 1–12, 2021. 4.         Sarma, J., and Bhattacharyya, D. K., “A Decision Tree-Based Dengue Prediction System,” International Journal of Computer Applications, vol. 176, no. 22, pp. 25–31, 2020. 5.         Fernández, J., et al., “Logistic Regression Model for Dengue Diagnosis Using Hematological Parameters,” BMC Infectious Diseases, vol. 19, no. 1, pp. 1–10, 2019. 6.         Mayrose, J., et al., “Automated Dengue Detection Using Blood Smear Images and Support Vector Machines,” IEEE Access, vol. 8, pp. 115021– 115030, 2020. 7.         Mello, C., et al., “Deep Neural Networks for Dengue Diagnosis Using Clinical Data,” Expert Systems with Applications, vol. 158, 2020. 8.         Pedregosa, F., et al., “Scikit-learn: Machine Learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.