Published in Scientific Reports, the study led at FIMM by Dr. Johan Lundin and Dr. NIna Linder compares manual microscopy with two AI-based methods - autonomous AI and expert-verified AI - for diagnosing parasitic worm infections in stool samples collected from school children in Kenya.
The findings mark a significant step forward in using AI to address diagnostic needs for neglected tropical diseases and highlight FIMM’s and the partner institutes’ leadership in global digital health innovation.
Soil-transmitted helminths, which include roundworm, whipworm, and hookworm, are among the most prevalent neglected tropical diseases, affecting over 600 million people worldwide.
The AI-based method used portable whole-slide scanners and deep learning algorithms. Among more than 700 digitised samples, the expert-verified AI detected more infections than traditional manual microscopy, particularly for light-intensity infections that are often missed.
More specifically, sensitivity for detecting hookworm, Trichuris trichiura, and Ascaris lumbricoides reached 92%, 94%, and 100% respectively with expert-verified AI, while specificity remained above 97% for all species.
“This research shows the potential of combining portable imaging with AI to overcome long-standing diagnostic challenges in global health,” says Dr. Johan Lundin, senior co-author from FIMM and KaroIinska Institutet.
“Our method could provide accurate, fast, and scalable diagnostics at the point of care, particularly important as global STH prevalence declines and more sensitive methods are required for disease monitoring," says Dr. Nina Linder, the other senior co-author from FIMM and Uppsala University.
The expert-verified AI system allows local experts to confirm AI findings in under one minute, drastically reducing workload while increasing accuracy.
"The fact that the expert-verified AI had the highest sensitivity for all species shows how AI can help find the needle (parasite egg) in the haystack, enhancing human capabilities and diagnostics," says the first author of the article, Doctoral Researcher Joar von Bahr.
The study was carried out in collaboration between the Institute for Molecular Medicine Finland (FIMM) at the University of Helsinki, Karolinska Institutet, Uppsala University, Muhimbili University of Health and Allied Sciences and Kinondo Kwetu Hospital, and was supported by the Erling-Persson Foundation, the Swedish Research Council, and several private foundations in Finland.
Original publication:
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