Join ELSA for this outstanding workshop on trustworthy AI models for computational healthcare at EMBL in Heidelberg. The workshop is organised by EMBL and ELSA and takes place in conjunction with the EMBO | EMBL Symposium: AI and biology 2026.
What? In person workshop dedicated to advancing private, fair, robust, reliable, and accountable AI models for healthcare applications to unite machine learning researchers, privacy and fairness specialists, experts in data governance and ethics, computational health and biology researchers, bioinformaticians, and other interdisciplinary practitioners.
When? March 9, 2026
Where? Operon and ATC of EMBL in Heidelberg
About the event
The TrustworthyAI4Health Workshop, co-located with the EMBL AI and Biology Conference, moves toward building private, fair, and reliable AI models for healthcare by emphasizing trustworthiness in model design, evaluation, and deployment. It unites theoretical, clinical, and benchmarking perspectives to promote responsible and transparent AI in medicine. Building on the spirit of the CAMDA Health Privacy Challenge, the workshop aims to broaden the focus to healthcare-specific aspects of trustworthiness throughout the entire AI lifecycle.
We envision this workshop as a collaborative forum for advancing trustworthy AI in healthcare, uniting machine learning researchers, privacy and fairness specialists, experts in data governance and ethics, computational health and biology researchers, bioinformaticians, and other interdisciplinary practitioners to generate new insights and practical pathways forward.
About the EMBO | EMBL Symposium: AI and biology 2026
The ELSA EMBL workshop is co-located with the EMBO | EMBL Symposium: AI and biology 2026. This provides an excellent opportunity to connect with communities focused on AI applications in biology. In addition, our workshop aims to engage researchers from the AI and machine learning domains who are particularly interested in privacy, fairness, explainability, and robustness. We believe the synergy between these two events will greatly enrich the participants’ experience.
Workshop Speakers & Panelists
More speakers and panelists will be announced as the organisation of the workshop progresses.
Florian Buettner, Speaker
Professor
Frankfurt University/DKFZ
More
Florian Buettner is a professor at Goethe-University Frankfurt and the German Cancer Consortium (DKTK)/German Cancer Research Center (DKFZ). His work centers on developing methods for distributional robustness, explainability, and calibrated uncertainty in medical AI.
Jean Louis Raisaro, Speaker
Assistant Professor
CHUV Biomedical Data Science Center
More
Dr. Jean Louis Raisaro holds a PhD in Computer and Communication Sciences from EPFL Lausanne, Switzerland. His work and research focus on the development of technologies to enable safe and privacy-preserving artificial intelligence and machine learning (AI/ML).
Mennatallah El-Assady, Speaker
Assistant Professor
ETH AI Center (CH)
More
Mennatallah El-Assady is an Assistant Professor at the Department of Computer Science of ETH Zurich, where she leads the Interactive Visualization and Intelligence Augmentation Lab (IVIA). Her research interest is in combining data mining and machine learning techniques with visual analytics, specifically for text data.
Peter Koo, Panelist
Associate Professor
Cold Spring Harbor Laboratory
More
Peter Koo is an assistant professor at the Cold Spring Harbor Laboratory. His research focuses on deep learning for regulatory genomics, with particular emphasis on model interpretability, representation learning, and uncovering biological mechanisms from sequence data.
Veronika Cheplygina, Speaker
Professor
IT University of Copenhagen
More
Veronika Cheplygina is a professor at the IT University of Copenhagen. Her research focuses on trustworthy, data‑centric machine learning, addressing dataset quality, fairness, evaluation, and challenges in medical imaging AI.
Call for Posters
We received a stunning number of abstract submissions. Thank you all for your participation! The call for posters is closed.
We invited submissions addressing any of the topics listed below, as well as related areas, that advance reliable, clinically aligned AI systems across diverse data modalities and healthcare environments.
Key Areas of Interest
Privacy & Security
Differential privacy, private synthetic data generation, and healthcare-specific adversarial threat modeling.
Fairness
Techniques and applications that identify and mitigate disparities across demographic groups, clinical subpopulations, and comorbidity profiles.
Interpretability & Explainability
Methods and applications grounded in biological or biomedical knowledge and model logic.
Robustness & Uncertainty
Solutions for noisy, sparse, high-dimensional, or distributionally shifting clinical datasets, with calibrated uncertainty estimation.
Human-AI Trust
Trust calibration, error communication, and evaluations of AI decision support in high-stakes settings such as intensive care or oncology.
Benchmarks & Evaluation
Benchmarks & Evaluation: Model-agnostic trustworthiness metrics, regulatory-informed benchmarks, and frameworks that articulate trade-offs among privacy, fairness, interpretability, uncertainty, and utility.
Poster Format
All accepted abstracts will be presented as physical posters.
Size: A0
Orientation: Portrait
Printing: Authors are responsible for printing and bringing their posters
Accepted posters
A Model-Agnostic Framework for Reproducible Calibration and Evaluation of Simulation Models in Cost-Effectiveness Analysis
by David Gómez-Guillén, David Fernández-López, Jesus Cerquides and Mireia Diaz
A Trustworthy Evaluation Framework for Guideline Adherence Assessment from Clinical Notes
by Linli Zhang
AID-CC: AI Driven Clinical Communication
by Michael Jantscher, Mark Kröll and Sara Steiner
Balancing Privacy and Performance: Memorization and Utility in Differentially Private Medical LLMs
by Farah Briki, Bogdan Kulynych, Mary-Anne Hartley and Jean Louis Raisaro
Benchmarking of Deep Learning Approaches for Anti-Cancer Drug Sensitivity Prediction
by Lutz Herrmann, Lisa-Marie Rolli, Lea Eckhart, Andrea Volkamer and Kerstin Lenhof
Benchmarking of machine learning algorithms and compound representations for toxic endpoint prediction
by Lisa-Marie Rolli, Loulwah Arnaout and Andrea Volkamer
Benchmarking Synthetic EHR Models for Subgroup-level Privacy and Fairness
by Sakshi Taware, Linzh Zhao, Hakime Öztürk, Oliver Stegle and Antti Honkela
Beyond Accuracy: Fairness and Counterfactual Analysis in Myocardial Infarction Mortality Prediction
by Siska Siska, Raad Bin Tareaf and Zuhra Sofyan
Can We Trust This Model? Human-Centered Evaluation Metrics for Clinical AI Systems
by Anıl Kuş
Client Security Alone Fails in Federated Learning: 2D and 3D Attack Insights
by Santhosh Parampottupadam, Ralf Floca, Klaus Maier-Hein, Dimitrios Bounias, Benjamin Hamm, Saikat Roy, Maximilian Zenk and Sinem Sav
Clinically Aligned AI Governance: Integrating Ethics, Risk, and Regulation in Healthcare
by Rajesh Divakaran
Confidence in AI responses to user’s queries
by Zvi Kam
Deep Learning-Assisted Dynamic Mode Decomposition for Non-resonant Background Removal in CARS Spectroscopy
by Adithya Ashok Chalain Valapil, Carl Messerschmidt, Maha Shadaydeh, Michael Schmitt, Jürgen Popp and Joachim Denzler
Differentially Private Genome-Wide Association Studies: Structure, Utility, and Methodological Insights
by Shadi Rahimian, Akito Yamamoto and Mario Fritz
Differentially Private, Time-Inhomogeneous Hidden Markov Models for Synthesizing Genome-Wide Association Datasets
by Shadi Rahimian and Mario Fritz
Discovering Subgroups with Exceptional Survival Characteristics
by Jawad Al Rahwanji, Sascha Xu, Nils Walter and Jilles Vreeken
FedAgree: Leveraging Federated Checkpoints for Label-Free OOD Evaluation via Agreement
by Giuseppe Serra, Ben Werner and Florian Buettner
Interpretability and privacy in the age of AI-driven spatial proteomics
by Loan Vulliard, Teresa Glauner, Yu-Le Wu, Jovan Tanevski, Julio Saez-Rodriguez and Felix Hartmann
LLM-Assisted Construction of Petri net models from biomedical literature
by Adam Aron Rynkiewicz, Paulina Poniatowska-Rynkiewicz, Raul Palma and Piotr Formanowicz
Mask of truth: usage of spurious correlation in medical images by deep learning architectures
by Théo Sourget, Michelle Hestbek-Møller, Amelia Jiménez-Sánchez, Jack Xu and Veronika Cheplygina
Membership inference attack on ECG models
by Zoher Orabe, Antti Airola and Tapio Pahikkala
Mitigating Spurious Correlations in Patch-wise Tumor Classification on High-Resolution Multimodal Images
by Ihab Asaad, Maha Shadaydeh and Joachim Denzler
Prompting General Purpose LLMs to assess Healthcare Privacy Policies under GDPR Article 5
by Maede Rahmanikhalili
Retrieval-Grounded Confidence Scoring for Clinical Feature Extraction
by Patrick Salome
Robustness and repeatability as key element for trust: the LUMINATE case study
by Florinda Coro, Alice Ravizza, Marco Raffo, Filippo Andreucci, Amedeo Franco Bonatti, Carmelo De Maria and Giovanni Vozzi
Toward fair and explainable AI for balanced plate and BMI-based nutrition decision support
by Sylvia Mensah, Offiong Edet and Jonah Ekpong
Toward Trustworthy and Privacy-Preserving Machine Learning for Healthcare IoT Using Hybrid Cryptographic Techniques
by Maryam Anwer
Trustworthy AI Decision Support for Oncology Tumor Boards Through Guideline-Grounded Traceability
by Carl Luis Pöhl
Trustworthy Voice AI for Mental Health: A Multimodal Framework for Robust Crisis Detection
by Owen Parsons, Agnes Norbury, Konstantin Shmelkov, Emilia Molimpakis and Stefano Goria
Uncertainty, Calibration, and Robustness in Clinical VQA
by Arnisa Fazla, Alberto Testoni, Ameen Abu Hanna, Barbara Plank and Iacer Calixto
Registration
Please register until February 21st via the button below – We are excited to welcome you!
We also kindly ask us to inform us if you need to change or cancel your registration. Simply email our organising team.
Schedule
The schedule will be updated as the organisation of the workshop progresses.
8:30 – 9:00
Registration, coffee and snacks
9:00 – 9:10
Welcome and introduction
9:10 – 9:50
Keynote #1: Jean Louis Raisaro
Title: tba.
09:50 – 10:10
Selected Flash Talks
Anıl Kuş
Arnisa Fazla
Farah Briki
Rajesh Divakaran
10:10 – 10:40
Coffee break
10:40 – 11:20
Keynote #2: Mennatallah El-Assady
Title: tba.
11:20 – 12:00
Poster session
12:00 – 13:00
Lunch
13:00 – 13:40
Keynote #3: Florian Buettner
Title: “Robust and uncertainty-aware AI systems for high-stakes applications”
13:40 – 14:20
Keynote #4: Veronika Cheplygina.
Title: “Curious findings about medical image datasets”
14:20 – 14:30
Orientation for discussion sessions
14:30 – 14:55
Coffee break
14:55 – 16:30
Parallel discussion sessions + refreshments
including keynote speakers and organizers as facilitators
16:30 – 17:00
Panel including keynote speakers & Peter Koo
17:00 – 17:10
Closing remarks
Important Dates
| Call for Posters open | December 2025 |
| Abstract Submission Deadline | |
| Review Period | February 2 – 6, 2026 |
| Notifications | February 7, 2026 |
| Deadline to apply for Mobility Funding | February 9, 2026 |
| Registrations close | February 21, 2026 |
Mobility Support
The ELSA Mobility Fund supports eligible attendees who join this workshop. If you are planning to use mobility funding, please apply in a timely manner. You can find all information in our Terms and Conditions.
To apply for mobility funding, please contact the ELSA Travel Office. They will provide you with the respective forms.
Deadline to apply for mobility funding: February 9, 2026
Organizers & Contact
University of Helsinki
EMBL
CISPA
DKFZ / EMBL
Helmholtz Munich
CISPA
In case you have any questions, please reach out to the organisation team via mail.
The Programme Chair Members
We want to express our heartfelt gratitude to our programme chair members for their support: Joonas Jälkö, postdoctoral researcher at the University of Helsinki, and Raffaele Mura, PhD student at the University of Cagliari.
Organisational and communications support
Registration
We are excited to welcome you! Please register for the event via the button below.
If you need to change or cancel your registration, please email our organising team.