On 5 March 2026, the hybrid INDICATE Round Table titled “Challenges and opportunities of federated infrastructures in medical research” will take place. The event will bring together leading experts to exchange experiences between EU projects, discuss challenges and lessons learned, and foster networking opportunities. The programme will be moderated by INDICATE Co-PI’s Michel van Genderen and Christian Jung.

The programme will start with welcome remarks from Malte Kelm, Director at the University Hospital Düsseldorf, and John Laffey, Research Chair of the European Society of Intensive Care Medicine. The welcome will be followed by short project pitches from key European initiatives, including:

• INDICATE – presented by Jan van den Brand (Technical Lead INDICATE)
• NUM Rapid – presented by Falk von Dincklage
• Eucare – presented by Björn-Erik Ole Jensen
• Irish Critical Care Clinical Trials Network – presented by Bairbre McNicholas
• Num SN CritCare – presented by Patrick Meybohm

Following the pitches, a panel discussion will explore the main challenges, lessons learned, and opportunities for federated infrastructures with Patrick Rockenschaub, including a presentation of Genome of Europe by Helen Ray-Jones and Jeroen van Rooij.

The round table will conclude with reflections on strengthening collaboration across Europe, fostering dialogue among a select group of researchers, clinicians, and project leaders working at the forefront of data-driven medical research.

Find a detailed overview of the programme below

11.00 – 11.15	Welcome by Malte Kelm, Director at the University Hospital Düsseldorf, and John Laffey, Research Chair of the European Society of Intensive Care Medicine (ESICM).  Moderated by Christian Jung & Michel van Genderen (INDICATE PI’s)
11.15 – 12.15	Presentations of all projects – INDICATE – presented by Jan van den Brand (Technical Lead INDICATE) – NUM Rapid – presented by Falk von Dincklage – Eucare – presented by Björn-Erik Ole Jensen – Irish Critical Care Clinical Trials Network – presented by Bairbre McNicholas – Num SN CritCare – presented by Patrick Meybohm
12.15 – 12.30	Coffee break
12.30 – 13.45	Intro | A summary of the top challenges and lessons learned by Patrick Rockenschaub Panel Discussion | Discussion of challenges and lessons learned  Presentation of Genome of Europe by Helen Ray-Jones and Jeroen van Rooij
13.45 – 14.00	Closing – Concluding words by Michel van Genderen (INDICATE PI)

During the recent ESICM event, Intensive Care Innovation, Maurizio Cecconi delivered a talk titled “Innovations: what should they mean for Intensive Care.” He explored the role of technological and organizational innovation in shaping the future of intensive care, highlighting clinical impact, implementation, patient value and the INDICATE Project.

Maurizio is a member of the INDICATE External Expert Advisory Board and also participated as a jury member during the INDICATE Hackathon organized taking place before the start of the ESICM Intensive Care Innovation forum. His engagement underlines the strong connection between international expertise, innovation, and the goals of the INDICATE programme.

Maurizio: “What stayed with me most was the quality of the conversations: clinicians, engineers, data scientists, industry, and innovators genuinely sitting at the same table to discuss how innovation, AI, and digital tools can actually improve patient care, not in theory, but in real life, but we need to work together to achieve a full implementation at the bedside. From crisis preparedness to everyday intensive care, from data infrastructure to decision support, one message was clear: innovation only matters if it is actionable and scalable.”

Read more

ICU clinicians, engineers, and data scientists from across Europe gathered for the INDICATE Hackathon, exploring how federated ICU data can improve patient care, drive equitable AI, and deliver real-world clinical value. 

Two main challenges guided the teams:

1.  Equitable AI Model Performance Across Diverse European ICU Populations
2. Value Proposition & Long-term Sustainability

The morning started with a keynote from Michel van Genderen, INDICATE PI, providing us with valuable insights about federated ICU data across Europe and the role of AI in improving patient care: “Trust is key: the performance of AI models is limited when trained on limited datasets. Research has shown that sociodemographic factors, like a patient’s ethnicity, can affect AI outputs. We must ensure that the AI we build accounts for these factors responsibly.”

After the Use-Case presentation by INDICATE Use Case expert Paul Hilders (Amsterdam UMC) and the challenges presented by Stefan Buijsman (TU Delft) and INDICATE Technical Lead Jan van den Brand (Erasmus MC) the morning hack session got started! The teams worked intensively on the challenges. Mentors supported teams as they explored technical, ethical, regulatory, and clinical dimensions. Over lunch, expert feedback sessions helped teams sharpen and improve their concepts before pitch prep began.

In the afternoon, participants refined their storytelling, and took the stage during the ESICM Intensive Care Innovation, to pitch their solutions to the jury concluding Jan van den Brand, Stefan Buijsman, Hayley Every, Paul Hilders and Maurizio Cecconi.

A big congratulations to the winning team of Challenge 1: Boris Delange, Celia Alvarez Romero, René Schmiedler, Stefan Bartos and Maria Gonzalez Lopez. Their solution was all about how to overcome bias through transparent AI. 

Also a big congratulations to the winning team of Challenge 2: Giovanna Mercurio, John Gardner, Marcel van der Kuil and Colm Coffey. Their solution offered a unique value proposition by enabling a self-sustaining ecosystem in which all stakeholders – from bedside to industry – derive value from shared, privacy-preserving data.

The hackathon was moderated by Yolanda Sanchez and organized by the INDICATE Work Package 5 team. 

A huge thank you to all participants, mentors, and jury members for building the future of responsible, equitable AI in intensive care.

Step into the future of Intensive Care innovation by participating in our Hackathon on ICU federated data usage. This dynamic event invites ICU clinicians, engineers, data scientists, and startups from the INDICATE and EIT Health network to co-create a vision for a global, real-time federated data infrastructure. 

Together, we’ll explore how to securely link ICU data across national and EU systems using anonymization techniques and federated learning. While ensuring full compliance with EU regulations and the AI Act. Participants will gain hands-on experience implementing Equitable AI Models Across Diverse European ICU Populations​ and help us build the Value-based proposition of Federated ICU Data Usage, guided by expert mentors. Expect rich cross-pollination of ideas and help shape ethical frameworks for deploying clinical and research algorithms.

Expert speakers

The challenges

Participants will form teams and work intensively over a set period to complete a Problem-Solution Fit Canvas, a tool that facilitates problem analysis and translates it into actionable plans. Through close collaboration, teams will gain a comprehensive understanding of the multi-faceted challenges, which includes technology constraints, regulatory hurdles, resource access, and market demand. This will enable them to conceptualize effective solutions in response to the identified problem. They will also be asked to work on specific outcomes for their chosen challenge:  

• Topic 1 challenge: Equitable AI Model Performance Across Diverse European ICU Populations 
• Topic 2 challenge: Value-based Proposition & Long-term Sustainability 

Jury

The four jury members for the hackathon are:

Use Case – Virtual digital twin of mechanical ventilation  

This use case is dedicated to developing a virtual digital twin for critically ill patients, a process that involves numerous sequential decisions made every hour. This use case is particularly suited for reinforcement learning, which will be employed to determine the optimal treatment choices tailored to the specific conditions of individual patients at any given moment. 

A primary focus will be optimizing mechanical ventilation settings for treating respiratory failure. Crucial to this use case is the leverage of the MIMIC-EU dataset, as referenced in the INDICATE Use Case. The integration of this diverse and extensive dataset is key in customizing treatment decisions for a wide variety of patient profiles, thereby enhancing the generalizability of the developed models. 

Furthermore, supervised machine learning will be utilized to predict and prevent the need for reintubation and to guide clinicians on data collection for improved predictive accuracy. The outcomes of this work will be disseminated through scientific literature and a pre-print on the knowledge platform, facilitating the rapid exchange of best clinical practices across Europe.

Program

08.00 – 08.30	Registration & Breakfast
08.30 – 08.40	Welcome & Opening Remarks
08.40 – 09.00	Keynote: Basics of Federated Data across EU, from AI Models to sustainability
09.00 – 09.10	Use Case presentation: Mechanical Ventilation Digital Twin
09.10 – 09.20	Presentation of challenges
09.20 – 09.30	Overview of the deliverables
09.30 – 12.00	Hack Session: Ideation and Solution building (Mentors available)
12.00 – 13.10	Feedback Lunch! 20min for a feedback session with experts and 50 minutes for feedback implementation lunch
13.10 – 13.20	Presentation: How to better communicate your idea
13.20 – 14.15	Pitch Prep!
14.15 – 14.30	Coffee break
14.30 – 15.50	Reintegration with the ESICM Innovation Forum programme
15.50 – 16.50	Team Pitches (6 teams – 5 minutes per team + short jury Q&A)
16.50 – 17.20	Coffee break and jury deliberation
17.20 – 17.35	Awarding Ceremony, Audience Award, Closing Remarks & Next Steps
17.35 – 18.35	Reintegration with the ESICM Innovation Forum programme

Join us for this collaborative opportunity to discuss how to better implement the ICU federated data infrastructure on Thursday 5th of February from 8:00hrs to 17:00hrs in Amsterdam. Let’s build the future of ICU data. Secure, smart, and shared.

The Hackathon will be a part of the 2026 ESICM Intensive Care Innovation Forum.

We are delighted to announce that Michel van Genderen, Principle Investigator (PI) of the INDICATE project, has been appointed Adjunct Professor in the Department of Biostatistics and Bioinformatics at Duke University School of Medicine. In this role, he will focus on the global alignment of responsible AI development and implementation in healthcare.

As PI of INDICATE, Michel is dedicated to ensuring that AI strengthens clinical decision-making in Intensive Care Units (ICUs) while maintaining medical responsibility, trust, and human-centered care.

The INDICATE project addresses critical challenges faced by European ICUs that currently limit data-driven innovation and AI implementation. Despite being data-rich environments, ICU datasets are often small, and the lack of standardized, secure mechanisms for cross-border data sharing restricts AI’s transformative potential in healthcare. INDICATE aims to overcome these barriers by developing a federated ICU data infrastructure, enabling secure, cross-border access to large-scale, diverse datasets to advance patient-centered, AI-enabled care.

AI in Healthcare: ‘Often seen as a band-aid for structural problems’

Recently, INDICATE co-lead Michel van Genderen shared his expertise on the Dutch Radio national news program De Nieuws BV (BNN VARA) at NPO Radio 1, discussing the challenges of implementing artificial intelligence in healthcare. 

Artificial intelligence is often presented as the solution to the growing problems in healthcare. From administrative burdens to staff shortages, in theory, AI could provide relief. But in practice, only two percent of the AI applications studied are actually used on the care floor. “We conducted this research in 2021 as well, and we see exactly the same outcome now,” says internist-intensivist Michel van Genderen on De Nieuws BV. “We simply aren’t making any progress.”

According to the internist, the problem doesn’t lie in a lack of innovation, but in how that innovation is implemented. AI is often applied on top of existing healthcare systems without fundamentally changing those systems. AI is used because it can be used, not because it actually solves a real problem. “Healthcare is like a car,” Van Genderen explains. “And what we’re doing now is trying to install all these new gadgets, while the car itself actually needs to be redesigned. Many AI models are technically very impressive, but in practice they don’t solve a relevant, existing problem.”

---

“Predicting models can perform very well based on a dataset, but the real question is: what use is it for a doctor or patient? What problem are we actually solving with this?”

---

Clinical Application

This is evident, for example, in AI models that predict the likelihood of a patient dying. “Predicting models can perform very well based on a dataset,” says the internist. “But the real question is: what use is it for a doctor or patient?” Without a clear clinical application, the added value of these kinds of tools remains limited. The fundamental question “What problem are we actually solving with this?” is, according to Van Genderen, too rarely asked when developing AI applications.

The AI Hype

The AI hype is reinforced by consumer behavior. Technologies like ChatGPT are adopted rapidly, often without critical questions about reliability. This pattern can also be seen in healthcare. “We tend to think: this is new and smart, so we should use it,” says the internist. But in healthcare, different standards apply: transparency, safety, and explainability are crucial. “AI sells well and sounds promising, but it doesn’t always provide good solutions.” Discussions about responsibility are quickly seen as a hindrance to progress, whereas that responsibility is actually essential.

Innovation is Necessary

This nuance is important because the problems in healthcare are real. Van Genderen points to his experiences during the COVID-19 pandemic: the demand for care is growing rapidly, while the number of healthcare workers is falling behind. Technological innovation is therefore necessary. According to Van Genderen, AI is too often seen as a band-aid for structural problems. “Some of the things we try to solve with AI might not even need solving,” he suggests.

Ethics by Design

Recent research shows that language models respond differently in medical diagnoses when sociodemographic characteristics are included. In some cases, this leads to a completely different, and sometimes incorrect, assessment. Such “black-box” models undermine the trust of healthcare professionals and patients. Van Genderen argues that trust is essential for successful innovation. That’s why he advocates for so-called ethics by design – ethical, legal, and societal considerations that must be incorporated from the very start of the development process. “If you do it afterward, it’s already too late,” he states.

Read the full article or watch the radio item here (in Dutch).

Source: De Nieuws BV NPO Radio 1