Karim Lekadir is an ICREA Research Professor in the Department of Mathematics and Computer Science at the University of Barcelona. He studied mathematics and computer science as an undergraduate in France and Germany. He obtained his PhD from Imperial College London and was a postdoctoral researcher at Stanford University. He investigates new data science techniques for trustworthy and ethical artificial intelligence in medicine. He has been PI in 18 EU-funded projects, coordinated 6 Horizon projects, and was awarded an ERC Consolidator grant to investigate new AI techniques tailored to resource-limited settings.
Research interests
My research lies at the intersection of artificial intelligence (AI), medicine and social sciences. I am interested in AI solutions that are that are effective, ethical, and trustworthy. I work a lot with European grants, which allowed me to specialise in generalisable AI solutions that can adapt across different environments. A key research interest of mine is AI for global health, such as through my ERC Consolidator Grant AIMIX 'Inclusive AI for accessible medical imaging across resource-limited settings'. Here, my team and I are developing new AI approaches for under-served populations in rural African regions, addressing obstacles such as limited data, basic equipment and clinician shortages. My research also focuses on fairness in AI, always aiming for AI tools that provide equitable care across demographics, regardless of gender, age, ethnicity, or economic status. My research touches on several medical fields, including oncology, cardiology, mental health, and women’s health.
Selected publications
- Zhou ZH, Lu YS, Bai JY, Campello VM, Feng F & Lekadir K 2025, 'Segment Anything Model for fetal head-pubic symphysis segmentation in intrapartum ultrasound image analysis', Expert systems with applications, 263 -125699.
- Lekadir K et al. 2025, 'FUTURE-AI: international consensus guideline for trustworthy and deployable artificial intelligence in healthcare', Bmj-british medical journal, 388 - e081554.
Dang VN, Campello VM, Hernández-González J, Lekadir K 2025, '- Empirical Comparison of Post-processing Debiasing Methods for Machine Learning Classifiers in Healthcare', Journal of healthcare informatics research, 9 - 3 - 465 - 493.
- Osuala R, Lekadir K et al. 2025, 'Simulating dynamic tumor contrast enhancement in breast MRI using conditional generative adversarial networks', Journal of medical imaging, 12 .
- Pujadas ER, Lekadir K et al. 2025, 'Longitudinal Prediction of Mental Health Outcomes in Vulnerable Youth using Machine Learning', Cognitive computation, 17 - 5 -152.
Selected research activities
- FUTURE-AI guideline on trustworthy AI in healthcare published in The BMJ as first author (Impact Factor 93,7).
- Invited speaker at the Mobile World Congress (A code of practice for trustworthy and ethical AI in healthcare).
- Invited talk at the European Congress of Radiology (Workforce challenges & AI in low-to-middle income countries).
- Completed large-scale public engagement activities on AI-powered pregnancy screening in rural Africa (ERC AIMIX project).
- Lead PI of the MAMA-MIA benchmark on AI-driven breast cancer image analysis at MICCAI 2025.
- ERC PoC grant started (AIFIX - Inclusive artificial intelligence using adaptive federated learning across high- and low-resource settings).
- EDCTP project AFRICAI-RI started (role: Project Coordinator).
- Co-founder of a spin-off company on distributed AI (Fedder AI).
- Member of the EIBIR Scientific Advisory Board, MICCAI Society Board and AFRICAI Network.
- Two new graduated PhDs (Richard Osuala and Lidia Garrucho).