Cervical cancer recently overtook maternal mortality as one of the top causes of death in women worldwide. However, just one-third of the world’s women have had cervical cancer screenings.
In a recent study, researchers from Uppsala University, Karolinska Institutet, and the University of Helsinki investigated whether an AI-supported technique could be used to screen women for cervical cancer in Kenya and Tanzania.
In our study, we showed how AI can be used to detect cervical cancer in areas where there is otherwise limited access to pathologists and laboratories. Using digital tools, samples can be analysed faster and with fewer experts involved, meaning that more women can get access to screening. But for the AI to really work, it takes more than just the technology – it needs investments in staff, equipment, and trust in the healthcare system.
Nina Linder, Study Lead Author and Visiting Professor, Department of Women's and Children’s Health, Uppsala University
Tested 3,000 Women
In this study, 3,000 women who would not have otherwise been offered cervical cancer screening went to rural hospitals where pathologists examined and digitized cervical cell and human papillomavirus (HPV) samples were collected on-site. AI was then used to analyze the samples.
The researchers trained local nurses, laboratory personnel, and pathologists to utilize the system and worked with healthcare officials to incorporate it into routine treatment. Women who showed symptoms of cervical cancer got treatment in accordance with national recommendations.
AI Required Consistency in the Images
One of the most difficult aspects of employing AI was that the images provided for analysis were not always consistent. Cells are stained so that they can be easily seen under a microscope. Staining chemicals, and hence cell color, might vary between countries and deliveries, resulting in images that the AI was expected to analyze that were not always consistent.
The AI method worked well technically, but unreliability in the supply of reagents, variations in reagent quality, and power outages all affected accuracy as well as the capacity to perform these tests rapidly, including HPV analyses.
Nina Linder, Study Lead Author and Visiting Professor, Department of Women's and Children’s Health, Uppsala University
Another challenge was locating women who had shown indications of cancer and needed follow-up care.
“In Tanzania, we had quite a few problems with follow-up. Some women did not come back, and when we later checked their samples, it turned out that they had changes that needed treatment. Sometimes it is difficult for local doctors to find the patients and get them to understand that they need treatment. We followed up as best we can and tried to give all women the opportunity for further investigations,” Linder further added.
Can Increase Trust in the Healthcare System
Although the study shows both the benefits and drawbacks of the AI technology, the researchers consider it a first step toward studying AI-supported diagnostics in more comprehensive healthcare programs and for more women’s diseases.
“For decades, diagnostic methods that are proven to be effective for women’s health – such as cell-sample based cervical cancer screening – have been dependent on highly trained experts. With the latest advances in medical AI, we can now re-evaluate these methods and introduce them even in resource-limited settings, making life-saving diagnostics far more accessible.”
Johan Lundin, Study Co-Author and Professor, Karolinska Institutet
Another crucial contribution is that it creates local awareness about the importance of screening.
When women see that there is reliable healthcare to go to and that they do get help, it lowers the threshold to seek care, which strengthens health as well as social engagement.
Nina Linder, Study Lead Author and Visiting Professor, Department of Women's and Children’s Health, Uppsala University
The study was carried out in partnership with Uppsala University, the Institute for Molecular Medicine Finland (FIMM) at the University of Helsinki, and Karolinska Institutet in Sweden. Kinondo Kwetu Hospital in Kwale County, Kenya, and Muhimbili University of Health and Allied Sciences (MUHAS) in Tanzania were important clinical collaborators in the study.
Journal Reference:
Linder, N. et.al. (2025) AI supported diagnostic innovations for impact in global women’s health. BMJ. doi.org/ 10.1136/bmj-2025-086009.