Events

We are excited to announce our third journal club by Meritxell Bach Cuadra and Delphine Ribes! This journal club will examine key factors influencing the integration of AI into clinical workflows by focusing on uncertainty quantification as a technical indicator of model trustworthiness and on stakeholder perspectives on trust, transparency, and safety in explainable AI systems. Through these two complementary viewpoints, we will discuss how both methodological design and human factors shape the responsible adoption of AI tools in clinical practice.

📝 Relevant papers

Structural-based uncertainty in deep learning across anatomical scales: Analysis in white matter lesion segmentation. Molchanova N., Raina V., Malinin A., La Rosa F., Depeursinge A., Gales M., Granziera C., Müller H., Graziani M., Bach Cuadra M.

Stakeholder-centered Design of Explainable AI for MRI analysis in Multiple Sclerosis: Generative insights toward clinical integration. Motta M., Zhan W., Molchanova N., Spagnolo F., Baez Lugo S., Clara E., M. Gordaliza P., Cagol A., Dunet V., Pistocchi S., Mutke M. A., Borràs Ferrís L., Gobbo B., Reyes M., Ruberte E., Erard F., Henchoz N., Müller H. Granziera C., Depeursinge A., Bach Cuadra M., Ribes Lemay D.

Introducing the speakers

Meritxell Bach Cuadra has an electrical engineering background and graduated PhD from EPFL. She is Associate Professor at the Faculty of Biology and Medicine of UNIL, Head of the CIBM Signal Processing CHUV-UNIL Trustworthy Medical Image Analysis Section, and leads the Medical Image Analysis Laboratory (MIAL) at CHUV. Her research focuses on novel image processing and trustworthy machine learning for medical image analysis, addressing healthcare bias while ensuring robust, reproducible, and domain-shift–resistant validation for reliable diagnosis and prognosis.

Affiliations: CIBM Center for Biomedical Imaging, Radiology Department, University Hospital Lausanne (CHUV) and Lausanne University (UNIL), Switzerland

Delphine Ribes: Delphine’s work spans research and real-world applications. With a background in electrical engineering and expertise in medical image processing, she has experience in research labs and healthcare settings. As the head of the algorithmic and software engineering group at EPFL+ECAL Lab, she focuses on interdisciplinary approaches that merge engineering, design, and clinical insights to foster technology adoption in healthcare.

Affiliations: EPFL+ECAL LAB, EPFL, Switzerland

We are excited to announce our second journal club by MS patient expert Joke Soetaert! Joke will talk about the perspective of people with MS on AI. Their needs will guide AI development, which is why you should definitely attend!

Introducing the speaker

Joke Soetaert has been pursuing her dream job as a midwife in neonatology and maternity for seven years, where she thrives on hands-on patient care. Prior to that, she worked for five years as a nurse in the operating room. During her transition to her current role, she noticed the first symptoms of what was later diagnosed as multiple sclerosis in 2019. She immediately felt a strong need for medical knowledge, delving into the scientific literature while also participating as a subject in several research studies in Belgium and the Netherlands. In 2021, she began volunteering as the coordinator of the youth program at MS-Liga Vlaanderen, a community fostering positive peer connections and providing information to young people with MS up to 35 years old and their environment.

For the past four years, she has also served as an MS patient expert, applying her professional medical background and personal experience in collaborations with MS professionals, pharmaceutical companies and other stakeholders. She is a member of patient advisory boards in several hospitals around the country. Additionally, she participates in (inter)national conferences such as ECTRIMS to stay up to date with the latest developments in the MS field, and last year presented her first abstract and poster at the EMSP congress in Prague, focusing on the patient perspective of MS and comorbidities.

We are planning our first iAIMS Journal Club, in which lead author Prof. Jaime Lynn Speiser will discuss the following paper 📝:

Speiser, Jaime L., Wesley T. Kerr, and Andreas Ziegler. "Common critiques and recommendations for studies in neurology using machine learning methods." Neurology 103.7 (2024): e209861.

Introducing the speaker

Dr. Speiser is a biostatistician focused on prediction modeling with applications in medicine. Her work involves developing novel machine learning methodology for prediction modeling, providing guidance for best practices for developing prediction models, and collaborating with medical researchers to develop models that inform clinical decision making in the learning health system.

Dr. Speiser received her B.S. in mathematics at Elon University and M.S. in statistics at the Ohio State University. She completed her Ph.D. in biostatistics at the Medical University of South Carolina, where she was awarded the Distinguished Graduate Student Award at the top of her class. Dr. Speiser received the Lester R Curtin Award from the American Statistical Association. She serves on the executive committees of the American Statistical Association’s Statistical Learning and Data Science Section and Statistics and Data Science in Aging Interest Group.

Dr. Speiser is currently funded by an NIH K25 award and is the co-leader for the Biostatistics core of Wake Forest’s Pepper Center. Her paper comparing random forest variable selection methods is a top cited paper in the journal Expert Systems with Applications with over 1700 citations.