Joar von Bahr explores the potential of AI-supported digital microscopy in resource-limited settings
Joar von Bahr recently completed his half-time review, marking an important milestone in his PhD studies. His research explores how AI-supported digital microscopy can improve access to reliable diagnostics in resource-limited settings, with current work focusing on parasitic infections and cervical cancer screening. We asked Joar to tell us more about his research and what he hopes to achieve in the second half of his PhD.
Could you give a short overview of your PhD project
The focus of my PhD is to investigate the use of AI supported digital microscopy for medical diagnostics in settings with limited resources. Together with colleagues in Kenya and Tanzania, we have investigated how these methods can be used to diagnose soil-transmitted helminth infections and identify precancerous changes in cervical cancer screening. The overall goal is to explore how AI supported digital microscopy can make reliable diagnostics more accessible to people who currently have limited access to them.
Are there specific areas you would like to focus on during the second half of the project?
Our results so far have shown the potential of AI supported digital microscopy, but there is still work to be done before these systems can be used in routine clinical practice. During the second half of my PhD, I would like to focus more on developing these systems to perform reliably in low resource settings, particularly by simplifying laboratory workflows and reducing their dependence on laboratory infrastructure. Ultimately, I hope this work will help translate the promising results from our studies into better and more accessible diagnostics for patients.
What key insights or findings have emerged so far?
One of the most important findings so far is the potential of AI supported digital microscopy to improve diagnostics in settings with limited resources. Both our scoping review and our study on soil-transmitted helminths indicate that AI may improve diagnostic accuracy compared with conventional manual microscopy. These findings have encouraged me to continue working on how this technology can be used to make accurate diagnostics more accessible in clinical practice.
Joar von Bahr successfully passed his half-time review on 21 October 2026.
Titel: Artificial intelligence supported digital microscopy in low resource primary healthcare settings
Half time board:
Balázs Ács, Associate Professor, Department of Oncology Pathology, Karolinska Institutet
Giulia Gaudenzi, Assistant Professor, Department of Global Public Health, Karolinska Institutet
Constance Boissin, Research Specialist, Department of Medical Epidemiology and Biostatistics, Karolinska Institutet
Main supervisor:
Johan Lundin, Professor of Medical Technology, Department of Global Public Health, Karolinska Institutet, and Research Director, Institute for Molecular Medicine Finland, FIMM, University of Helsinki
Co supervisor:
Nina Linder, Visiting Professor, Department of Women's and Children's Health, Uppsala University, and Senior Researcher, Institute for Molecular Medicine Finland, FIMM, University of Helsinki