AI and Portable Microscopy Boost Detection of Parasitic Infections in Primary Healthcare

AI-Supported Microscopy Enhances Detection of Parasitic Infections in Primary Healthcare

A recent study highlights how artificial intelligence (AI) combined with portable digital microscopy improves the detection of soil-transmitted helminth (STH) infections in settings with limited resources. Conducted by a team led by Dr. Johan Lundin, the research compares traditional manual microscopy with two AI-based approaches—autonomous AI and expert-verified AI—using stool samples collected from school children in Kenya.

The study, published in Scientific Reports, demonstrates that AI integration can address diagnostic challenges for neglected tropical diseases. It also underscores the leadership of the Institute for Molecular Medicine Finland (FIMM) and partner institutions in advancing global digital health solutions.

Soil-Transmitted Helminths and Diagnostic Challenges

Soil-transmitted helminths—including roundworm, whipworm, and hookworm—affect more than 600 million people worldwide. These parasitic infections are among the most common neglected tropical diseases, causing significant health burdens in affected communities.

The AI-based method uses portable whole-slide scanners paired with deep learning algorithms to analyze over 700 digitized stool samples. The expert-verified AI approach detected a higher number of infections than manual microscopy, especially in cases with light-intensity infections that traditional methods often miss.

• Hookworm detection sensitivity reached 92%
• Trichuris trichiura detection sensitivity reached 94%
• Ascaris lumbricoides detection sensitivity reached 100%

Specificity remained above 97% for all species, indicating that AI-based diagnostics maintain high accuracy.

Advantages of AI Integration in Diagnostics

According to Dr. Johan Lundin, the combination of portable imaging and AI offers a practical solution to long-standing diagnostic challenges in global health. The method delivers accurate, fast, and scalable diagnostics at the point of care—a critical factor as STH prevalence declines and more sensitive monitoring tools are needed.

Dr. Nina Linder adds that the expert-verified AI system enables local experts to confirm AI findings in less than a minute. This drastically reduces workload while improving diagnostic accuracy.

Joar von Bahr, the study's first author, notes that expert-verified AI’s high sensitivity across all species shows how AI can complement human expertise by identifying parasite eggs that might be easily overlooked.

Collaborative Effort and Support

The study involved collaboration between FIMM at the University of Helsinki, Karolinska Institutet, Uppsala University, Muhimbili University of Health and Allied Sciences, and Kinondo Kwetu Hospital. Funding was provided by the Erling-Persson Foundation, the Swedish Research Council, and several private foundations in Finland.

For those interested in further AI applications in healthcare and diagnostics, exploring advanced training on AI methodologies can be valuable. Resources like Complete AI Training’s courses by skill offer practical learning paths.

Reference

von Bahr, J., Suutala, A., Kucukel, H. et al. AI-supported versus manual microscopy of Kato-Katz smears for diagnosis of soil-transmitted helminth infections in a primary healthcare setting. Sci Rep 15, 20332 (2025). https://doi.org/10.1038/s41598-025-07309-7