Genomics and Digital Health Frontiers Science Series at Biotech Campus 2025-2026
Genomics and Digital Health Frontiers Science Series are in the program "Genomics and Digital Health" of the doctoral school in "Life Sciences from the Faculties of Medicine and Science" and are open to all programs of the PhD school of Life Science, and external participants. It is taught by PIs participating in the program and several external teachers. It will cover a wide range of selected topics in Digital Health and Data Science for Digital Health..
- Digital Health (DH)
- Genomics
- Methodology in Research
- Ethical and Security Issues in DH
- Semantics and Interoperability
- Computational biomedical sciences
- Natural Language Processing in Health
- Health Data Analytics
- Machine Learning in Health
- Health Data Representation
- Biomedical Signal Processing
- Public Health
- Community Health
On Wednesdays from 11am to 12pm
Room H8-01-D or H8-01-F or H4-02-A (Biotech Campus)
Zoom access https://unige.zoom.us/j/61223662192?pwd=ou7OHlnG6eUNFAluhUeAwgQrR0RlHl.1
More info here
September 10th in H4-02-A Lucille Delisle (UNIGE) baredSC: Bayesian approach to retrieve expression distribution of single-cell data
Bioinformatics analysis of NGS data in the groups of Prof Herrara and Prof. Andrey, Department of Genetic Medicine and Development
October 1th in H8-01-F - Stéphane Meystre (SUPSI) LLMs are (still) not ready for clinical data
Prof. Stéphane Meystre is a physician and biomedical informaticist, expert in applications of AI and more specifically machine learning and natural language processing (NLP) to support more effective clinical care and enable reuse of existing clinical information for precision health and research applications, all while addressing responsible AI requirements. Dr. Meystre is (full) Professor of Biomedical Informatics and Director of the new Institute of Digital Technologies for Personalised Healthcare (MeDiTech) at SUPSI's Department of Innovative Technologies in Lugano, Switzerland.
November 5th in H4-02-A - Timothée Olivier (HUG) Real-World Data in Oncology: challenges and opportunities
Dr. Timothée Olivier is a Swiss oncologist practicing at the Oncology Department of the Geneva University Hospitals and a Privat-Docent at the University of Geneva. He is internationally recognized for his expertise in evidence-based medicine and clinical trial methodology. Dr. Olivier trained at the University of California, San Francisco (UCSF) under Professor Vinay Prasad, who now holds a senior position at the U.S. Food and Drug Administration.
December 3 in room H8-01-F Pablo Jané Soler (HUG/UNIGE) The Imageable Genome
Dr. Pablo Jané is a board-certified nuclear medicine physician at Geneva University Hospitals (HUG) and a former Visiting Fellow at Clare Hall, University of Cambridge. His work focuses on oncology, AI and theranostics, and he’s published in Nature Communications as lead/co-author on “The Imageable Genome” and “The Theranostic Genome”.
January 7th in room H4-02-A - Jérémy Hofmeister (HUG/UNIGE) From Computational Models to In-Vitro and Biological Twins: A Translational Approach to Brain Vessel Modeling
Dr. Jérémy Hofmeister is a board-certified interventional neuroradiologist at Geneva University Hospitals (HUG), Switzerland, specializing in minimally invasive treatment of neurovascular and spinal disorders, with a particular focus on ischemic and hemorrhagic stroke. He conducts research at Campus Biotech Geneva, where he develops AI-based neurovascular modeling approaches integrating advanced image processing and additive manufacturing, both physical (in vitro) and computational. These models are applied in fundamental and translational research, therapeutic device R&D, and clinical research to support the development of treatment strategies and the planning of endovascular interventions
February 4th in room H4-02-A Pr. Philippe Bijlenga (HUG) Stroke Digital Twin in Health from Real World Data
Prof. Philippe Bijlenga is a neurosurgeon at Geneva University Hospitals (HUG) and an associate professor at the Faculty of Medicine of the University of Geneva. A renowned specialist in cerebrovascular diseases, particularly intracranial aneurysms and subarachnoid hemorrhage, he combines clinical expertise with translational research. His work focuses on modeling neurovascular diseases using multimodal data that integrates imaging, clinical, genetic, and biological data, with a strong interest in medical decision support and personalized medicine.
He is actively involved in the European GEMINI (Stroke Digital Twin) project, which aims to develop digital twins of patients to improve the prediction, prevention, and management of strokes. He is also committed to integrating virtual reality, mixed reality, and artificial intelligence into neurosurgery, both for training and clinical practice.
March 4th in room H4-02-A Jean-Louis Raisaro (CHUV) Bringing AI to the clinic with the human in the loop: from predictive AI to medical LLMs
Jean Louis Raisaro is tenure-track Assistant Professor at the Faculty of Biology and Medicine of the University of Lausanne and group lead the Biomedical Data Science Center of the CHUV. His group develops and translates innovative AI and data science solutions to improve clinical care and enable multicenter research. His current research is at the intersection of trustworthy AI methods, including privacy-preserving approaches such as differential privacy and synthetic data generation, clinical Large Language Models (LLM) and agentic systems, as well as multimodal foundation models that integrate clinical data from electronic health records, including clinical text, structured variables, and time-series signals.
April 1st in room H4-02-A Margarita Liarou (CUI/UNIGE) Trajectory inference in healthy and disrupted hematopoiesis
Margarita Liarou is a PhD student in the VIPER group (https://viper.unige.ch/) in the Computer Science Department of UNIGE, supervised by Prof. Stéphane Marchand-Maillet (UNIGE) and Prof. Thomas Matthes (UNIGE/HUG). Her research focuses on the development of computational methods for analyzing flow cytometry data.
https://onlinelibrary.wiley.
https://onlinelibrary.wiley.
May 6th in room H4-02-A Jérôme Schmid (HEdS) Application of robust multimodal deep learning fusion to support medical image diagnosis
Jérôme Schmid is Full Professor at the Geneva School of Health Sciences, part of the University of Applied Sciences and Arts Western Switzerland (HES-SO). His research focuses on medical image acquisition and analysis for computer-aided diagnosis and image-guided surgery, using MRI, CT, X-ray, and SPECT imaging. His team has developed strong expertise in artificial intelligence applied to clinical and educational contexts. Recent works particularly involved the development of multimodal deep learning models able to combine clinical data of different nature and dimension, even in presence of partial or missing data. These models were successfully applied to characterize breast lesions in ultrafast dynamic MRI or diagnose neurodegenerative parkinsonisms in SPECT imaging.
Review of DL-based fusion strategies in the biomedical domain
https://doi.org/10.1093/bib/bbab569
Publications of Prof. Schmid’s team showcasing the application of multimodal DL models
https://doi.org/10.1007/s10278-025-01831-w
https://doi.org/10.1016/j.compbiomed.2025.109721
June 10th in room H4-02-A Janna Hastings (IDIAP) LLMs Automating Structured Clinical Annotations: The New Reproducibility Crisis and Its Mitigation
Large language models (LLMs) are increasingly used to automate structured annotations of clinical data grounded in biomedical ontologies. However, such models perform stochastically, are sensitive to context and prompt formulation, and may evolve without accessible version archives. As a result, they are rapidly introducing a reproducibility crisis. This presentation will examine how this problem can be at least partially mitigated, with concrete examples taken from biochemistry, clinical notes, and evidence synthesis in mental health, concluding with highlighting some persistently open research challenges in this area.
Janna Hastings was born in Cape Town, South Africa where she completed her undergraduate studies in Mathematics and Computer Science. Thereafter, she moved to Cambridge, UK to join the Cheminformatics and Metabolism group at the European Bioinformatics Institute (2006-2015) where she led the development of the ChEBI molecular ontology and metabolism knowledgebase. She completed part-time Master’s degrees in Computer Science (University of South Africa, 2011) and Philosophy (Open University, 2012) before obtaining her PhD in Computational Biology from the University of Cambridge (2015-2019), where she studied the role of metabolism in healthy aging using multi-omics data and a time-series modelling approach. She completed postdoctoral studies at the Otto-von-Guericke University Magdeburg (2019-2022), at the EPFL (2020-2022), and with the Human Behaviour-Change Project at University College London (2017-2022). Between 2022 and 2025 she was an Assistant Professor in the Medical Faculty of the University of Zurich, and since January 2026 she has taken up the position of Senior Research Scientist at the Idiap Research Institute where she leads the Human-Centered Health AI group focused on advancing AI methods for health-related applications, particularly hybrid approaches that combine knowledge with large-scale data.
Website: https://hastingslab.