Integrating Explainable AI for Enhanced Dengue Detection from Blood Smears

Abstract: Dengue fever, a mosquito-borne viral infection caused by the DENV virus, has been spreading rapidly across tropical and subtropical regions, posing a major public health concern and contributing to significant global mortality. Accurate identification of dengue cases remains challenging, making it essential to adopt reliable and efficient diagnostic approaches. This study explores an automated method for detecting dengue from peripheral blood smear (PBS) images using deep learning (DL) techniques, which have gained prominence in computer-assisted diagnosis of various medical conditions. The research utilizes the “Dengue Disease using Blood Smears” dataset and applies multiple classification models, including ResNet50, MobileNets, MobileNetV3-Small, MobileNetV3-Large, and a hybrid ensemble of Xception and MobileNet. For object detection, members of the YOLO family—YOLOV5x6, YOLOV5s6, YOLOV8n, and YOLOV9n—are employed. Experimental results reveal that the Xception–MobileNet ensemble yields the highest classification accuracy, while YOLO-based models effectively localize abnormalities in PBS images. These findings highlight the potential of DL-based approaches to enhance dengue diagnosis, offering a promising direction for improving public health surveillance and outcomes.

Dengue Detection, Blood Smears, Transfer Learning, Ensemble Model, YOLOv9, Explainable AI

1. H. A. Alhazmi, W. Ahsan, M. M. E. Taha, M. Albratty, A. Najmi, A. Farasani, A. A. Abdulhaq, and I. A. Darwish, ‘‘Development of screen-printed carbon electrode-based immunosensors for the electro-chemical detection of dengue virus antigen,’’ J. King Saud Univ.-Sci., vol. 35, no. 3, Apr. 2023, Art. no. 102568, doi: 10.1016/j.jksus.2023. 102568. [Google Scholar] [Crossref]

2. H. Mayrose, G. M. Bairy, N. Sampathila, S. Belurkar, and K. Saravu, ‘‘Machine learning-based detection of dengue from blood smear images utilizing platelet and lymphocyte characteristics,’’ Diagnostics, vol. 13, no. 2, p. 220, Jan. 2023, doi: 10.3390/diagnostics13020220. [Google Scholar] [Crossref]

3. M. Katta, R. Sandanalakshmi, G. Srilakshmi, and R. Adireddi, ‘‘An efficient learning model selection for dengue detection,’’ in Intelligent and Cloud Computing (Smart Innovation, Systems and Technologies). Singapore: Springer, 2022, pp. 439–453, doi: 10.1007/ 978-981-16-9873-6_40. [Google Scholar] [Crossref]

4. W. Hoyos, J. Aguilar, and M. Toro, ‘‘A clinical decision-support system for dengue based on fuzzy cognitive maps,’’ Health Care Manage. Sci., vol. 25, no. 4, pp. 666–681, Aug. 2022, doi: 10.1007/s10729-022-09611-6. [Google Scholar] [Crossref]

5. H. Mayrose, N. Sampathila, G. M. Bairy, S. Belurkar, K. Saravu, A. Basu, and S. Khan, ‘‘Intelligent algorithm for detection of dengue using MobileNetV2-based deep features with lymphocyte nucleus,’’ Expert Syst., vol. 40, no. 4, Nov. 2021, Art. no. e12904, doi: 10.1111/exsy.12904. [Google Scholar] [Crossref]

6. Mayrose, H., Sampathila, N., Bairy, G. M., Belurkar, S., Saravu, K., Basu, A., & Khan, S. (2023). Intelligent algorithm for detection of dengue using mobilenetv2‐based deep features with lymphocyte nucleus. Expert Systems, 40(4), e12904. [Google Scholar] [Crossref]

7. Barik, M., Pattanayak, A., Mukherjee, S., Koner, S., Tewari, S., & Vaishnav, S. (2024). AI technology for detecting dengue: A systematic. [Google Scholar] [Crossref]

8. Zahiruddin, H., Zukarnain, Z. A., & Wijaya, A. (2024). A scoping review and bibliometric analysis (ScoRBA) on dengue infection and machine learning research. JOIV: International Journal on Informatics Visualization, 8(4), 2203-2210. [Google Scholar] [Crossref]

9. Deshpande, N. M., Gite, S. S., & Aluvalu, R. (2021). Microscopic Analysis of Blood Cells. Tracking and Preventing Diseases with Artificial Intelligence, 206, 125. [Google Scholar] [Crossref]

10. Asim, M., Zaman, S., Razzaq, A., Qadri, S., Hussain, Z., & Sarfraz, Z. (2023). Classification of Microscopic Malaria Parasitized Images Using Deep Learning Feature Fusion. Lahore Garrison University Research Journal of Computer Science and Information Technology, 7(2), 7-7. [Google Scholar] [Crossref]

• Advanced Techniques for Fake News Detection on Twitter Using NLP and AI: A Comprehensive Review
• Review of Self Compacting Geopolymer Concrete Using Slag Sand as Fine Aggregate
• Performance of Local Construction Contractors – Case Study of Registered Contractors in Monrovia, Liberia
• Cross-Cultural Perspectives on Innovation Management in Multinational Organizations
• Modeling of Reaction Between Dissolved Oxygen (DO) And Biological Oxygen Demand (BOD) in Degradation River