AI for equitable diagnostics in women’s health

This is the key conclusion of a new publication in the British Medical Journal by Nina Linder, MD, professor and an international team of researchers, based on real-world implementation of AI-supported cervical cancer screening in Kenya and Tanzania.

Cervical cancer has recently surpassed maternal mortality as a leading cause of death among women globally, making this research especially urgent. The paper provides critical insights into how AI can be responsibly scaled to reduce preventable deaths, while avoiding the risk of widening health disparities.

Drawing on fieldwork in Kenya and Tanzania, the study was conducted by a team led by Dr. Linder and Johan Lundin, MD, professor, in close collaboration with principal investigators from Kenya, Tanzania and Sweden.

They jointly implemented an AI-supported cytology system that digitizes Pap smear samples and enables remote AI analysis with expert verification. The results demonstrate that AI-supported diagnostics can significantly expand access to screening where traditional pathology services are limited.

Technology alone isn't enough

The paper highlights both the promise and the challenges of deploying AI in real-world settings, emphasizing the need for investment in infrastructure, supply chains and community trust.

According to Dr. Linder, AI-enabled cytology can reduce reliance on on-site pathologists, speed up diagnostic turnaround times and expand screening coverage. However, challenges such as power interruptions and reagent variability were shown to affect the reliability of AI results.

Thus, the researchers caution that without investments in infrastructure and integration into local health systems, even the most advanced technologies risk falling short.

"Technology alone is not enough," says Dr. Linder. "To truly benefit women in underserved areas, AI must be embedded within functioning health systems and supported by community trust."

From pilot projects to real-world impact

The team's next steps involve scaling AI-supported diagnostics across broader health programs and conditions, while continuing to strengthen local health systems and community engagement.

"For decades, diagnostic methods that have proven effective for women's health - like Pap smear-based cervical cancer screening - have depended on highly trained experts," says Dr. Lundin. "With recent advances in medical AI, we can now reassess these methods and implement them even in resource-limited settings, making life-saving diagnostics far more accessible."

The paper was published in the British Medical Journal (BMJ) on October 10, 2025, as part of a , developed in partnership with the Gates Foundation. The Collection is comprised of seven woman-led analysis articles and explores how technological, social and systemic innovations can transform women's health globally.

This work was made possible through collaboration with Kinondo Kwetu Hospital (Kenya), Muhimbili University of Health and Allied Sciences (Tanzania), Uppsala University, Karolinska Institutet and the Institute for Molecular Medicine Finland (FIMM) at the University of Helsinki. The study was funded by several foundations, including the Erling-Persson Foundation, Knut and Alice Wallenberg Foundation and the Swedish Research Council.

In addition to their positions at FIMM, Nina Linder, MD, is a Guest Professor of AI-based diagnostics at the Department of Women's and Children's Health, Uppsala University and Johan Lundin, MD, is a Professor of Medical technology at the Department of Global Public Health at Karolinska Institutet.

Original publication: AI-supported diagnostic innovations for impact in global women's health. Linder N., Nyirenda D., Mårtensson A., Kaingu H., Ngasala B., Lundin J. British Medical Journal 2025;391:e086009. doi:

Newsletter