We’re thrilled to announce the publication of our latest systematic review under the AI4PEP Rapid-VBP Ghana project with the title:
“Trends and Advances in Image-Based Mosquito Identification and Classification Using Machine Learning Models: A Systematic Review”
This paper offers a comprehensive analysis of how machine learning, especially image-based approaches, is being used to address one of the world’s most persistent public health challenges: mosquito-borne diseases.
In the face of growing threats like malaria, dengue, and Zika, the need for scalable and accurate mosquito surveillance is more urgent than ever. Our review examines over 50 peer-reviewed studies from the last two decades, identifying the core algorithms, datasets, and evaluation methods used in this fast-growing field.
Highlights from the review:
- Analysis of traditional ML vs. deep learning (CNNs, ResNet, MobileNet, hybrid models)
- Breakdown of public datasets and open-access tools
- Comparison of accuracy, performance metrics, and regional focus
- Identification of gaps in African representation and real-world deployment
- Roadmap for future research, especially for low-resource and high-burden settings
This paper serves as a valuable resource for:
- AI researchers and developers building mosquito detection tools
- Public health professionals designing data-driven control programs
- Policymakers and donors investing in climate-resilient surveillance systems
- Students and academics looking to explore machine learning in global health
📄 Access the publication here → https://authors.elsevier.com/a/1l8MY2OYdBUsB
We’re proud to contribute to the growing body of AI-for-health research in Africa, and we hope this work supports others working in vector-borne disease prevention and control.