2^nd ENFIELD Webinar
Bias in Medical AI: Identifying Risks and Ensuring Fairness

23 May 2025, 9:30 - 13:30 (CET)

About the Webinar

Artificial Intelligence is revolutionizing healthcare, enabling faster diagnoses, personalized treatments, and improved patient care. From detecting diseases in medical images to predicting patient risks, AI has the potential to enhance healthcare efficiency and accuracy like never before. However, this powerful technology also comes with challenges, one of the most critical being bias in AI models.

Bias in AI can emerge from multiple sources, including unrepresentative datasets, flawed algorithmic design, and systemic inequalities in healthcare. If left unaddressed, these biases can lead to significant disparities in medical decision-making, negatively impacting healthcare outcomes.

AI in medicine should be a tool for progress, not a source of new inequalities. Ensuring fairness in AI means improving the quality, diversity, and transparency of medical AI systems so that all patients, regardless of race, gender, or socioeconomic status, receive equitable healthcare.

The webinar will explore these challenges, featuring expert insights and case studies towards building fair, ethical, and unbiased AI systems in medicine.

During the webinar, participants will have the opportunity to engage in insightful discussions on various topics, such as the benefits and challenges of AI in medical decision-making, real-world examples of AI bias in medicine, how bias affects medical outcomes, sources of bias in medical AI, strategies to mitigate AI bias in healthcare, and more. They will also be able to share their questions and perspectives, fostering rich and meaningful dialogue.

Join us to be part of the conversation and the solution!

The main topics of the webinar are:

• Ethical Implications of Bias in Medical AI
• Techniques to Detect and Mitigate Bias in Healthcare Data
• Bias in Synthetic Healthcare Data
• Case Studies Analysis
• Developing Systematic Frameworks for Bias Detection

The webinar is organized in the framework of the Horizon Project ENFIELD - European Lighthouse to Manifest Trustworthy and Green AI - and it will take place on the Teams platform (via this link).

Target Audience

The target audience includes young researchers, AI developers & data scientists, healthcare professionals, members of Digital Innovation Hubs, participants from related initiatives and projects, and anyone interested in ethical AI in medicine.

Speakers

Pankaj Pandey

Norwegian University of Science and Technology

Bjørn Morten Hofmann

University of Oslo;
Norwegian University of Science and Technology

Panagiotis Tsakanikas

Institute of Communication and Computer Systems

Sören Möller

Department of Public Health, University of Southern Denmark

Sofia Couto da Rocha

Lusíadas Saúde

Barbara Draghi

Brunel University London;
Medicines and Healthcare products Regulatory Agency

Konstantina Remoundou

Institute of Communication and Computer Systems

Emanuele Koumantakis

Department of Clinical and Biological Sciences, University of Turin

Andrei Olaru

National University of Science and Technology POLITEHNICA Bucharest

Juulia Jylhävä

Faculty of Medicine and Health Technology, Tampere University

Chiara Bellatreccia

University of Bologna

Program

23 May 2025	9:30 - 9:40	European Lighthouse to Manifest Trustworthy and Green AI (ENFIELD) Pankaj Pandey, Norwegian University of Science and Technology, Norway
	9:40 - 10:00	The Ethics of the Inexorable Biases in Medical AI Bjørn Morten Hofmann, Centre for Medical Ethics at the University of Oslo and the Department of Health Science at the Norwegian University of Science and Technology, Norway
	10:00 - 10:20	Pseudo-Individual Predictions as Interventional Health Programs - Shattering the Individual into Data Points Sören Möller, Epidemiology, Biostatistics and Biodemography, Department of Public Health, University of Southern Denmark, Denmark
	10:20 - 10:40	Synthetic Data Bias Amplification in Healthcare Sofia Couto da Rocha, Lusíadas Saúde, Portugal
	10:40 - 11:00	Detect and Mitigate Bias in Patient Data Using Synthetic Data Generators Barbara Draghi, Brunel University London; Medicines and Healthcare products Regulatory Agency, United Kingdom
	11:00 - 11:10	Break
	11:10 - 11:30	Biases in EHR Databases; a Medical vs Statistical Approach through the ICU Readmission Case Konstantina Remoundou, Institute of Communication and Computer Systems, Greece & Emanuele Koumantakis, Department of Clinical and Biological Sciences, University of Turin, Italy
	11:30 - 11:50	Addressing Bias and Data Scarcity in AI-Based Skin Disease Diagnosis with Non-Dermoscopic Images Chiara Bellatreccia, University of Bologna, Italy
	11:50 - 12:10	APPO - Building AI Trust through Bias Identification Panagiotis Tsakanikas, Institute of Communication and Computer Systems, Greece
	12:10 - 12:30	Towards a Framework for Bias Analysis in Data Andrei Olaru, National University of Science and Technology POLITEHNICA Bucharest, Romania
	12:30 - 12:50	AI-Driven NLP Models to Identify Aging-Related Health Issues in Free-Text EHR Data Juulia Jylhävä, Faculty of Medicine and Health Technology, Tampere University, Finland
	12:50 - 13:30	Discussions and Q&A