AI for Future Healthcare

TDW III: AI for Future Healthcare

Theme Development Workshop
16 December 2021 | 9:00- 17:30 CEST

Identify common goals between academia and the healthcare sector as well as other relevant stakeholders, and define promising approaches for European research and innovation in Trustworthy AI.

Use the opportunity to discuss with other experts the importance and the use of AI in the Healthcare Sector.

Please note that registration for the workshop is closed.

AI for Future Healthcare


Due to Covid 19 the workshop will be held online with a mixed programme of presentations and in-depth discussions about specific sub-topics in smaller groups (Breakout sessions). This gives you the opportunity to discuss with selected experts and contribute to the strategic research and innovation agenda for AI in Europe.

Part 1

9:00-9:15Welcome & Objectives
9:15-9:30AI in Healthcare
Prof. Dr. Ulf Nehrbass, Luxembourg Institute of Health
9:30-9:45AI, genomics & precision medicine
– Dr. Alfonso Valencia, Barcelona Supercomputing Center
9:45-10:00Coffee Break & Socialising
10:00~11:30Parallel Breakout sessions
11:30-12:30Plenary presentation of key findings from the Sessions
12:30-13:30Lunch Break & Socializing

Part 2

13:30-13:45AI use cases in healthcare industry
– Dr. Nicolas Pezzotti, Philips Research
13:45-14:00AI in healthcare management and
– Anna Forment, NTTData
14:00-15:30Parallel Breakout sessions
15:30~15:45Coffee Break & Socialising
15:45-16:45Plenary presentation of key
findings from the Breakout sessions
16:45-17:30Closing & Socialising

Breakout sessions

1.Trustworthy AI for Future Healthcare
With this session, we would like to initially define the strategic challenges and derive relevant major topics for Trustworthy AI from the perspective of future healthcare.

2. Data sharing in the Healthcare Sector
More and more data are being generated from various sources (e.g., medical devices, smart devices, public records), in different geographies, and is often owned by different parties like academia, hospitals, the industry as well as governments. Data sharing can improve AI analysis, but also brings several challenges. This breakout session will brainstorm on the challenges and benefits of data sharing, as well as potential technologies

3. Trustworthy AI aspects on time series data analysis
In personal, connected and in-hospital care, time-series data is a common and important form of input data (e.g., toothbrush localization, sleep phase determination through headphones). This breakout session will focus on the most important trustworthy AI components, challenges, and solutions for this type of data and its analysis

4. Trustworthy AI aspects on image segmentation and reconstruction
In clinical imaging, image segmentation and reconstruction are very important use cases, including cancer diagnosis and X-ray image denoising. This breakout session will therefore focus on the most important trustworthy AI components, challenges, and solutions for these use cases.

5. AI and genomics: Building Precision Medicine using reliable AI
This breakout session will discuss and analyse reliable AI techniques (especially machine learning and deep learning) and how they support bioinformatics in clinical diagnosis.

6. AI in infodemics
The infodemic phenomenon concerns with the overabundance of information, not necessarily reliable, circulating online and offline about an epidemic outbreak. This session will discuss about infodemics and the role of AI to assess the infodemic risk, with potential applications to public health.

We invite the community to suggest further topics of interest for the breakout sessions. Please use the online application form for your suggestions.

7. Trustworthy aspects for NLP
In patient intake and engagement, medical documentation, automatic report generation, EMR analysis and forecasting, NLP is widely used. This breakout session will therefore focus on the most important trustworthy AI components, challenges, and solutions for these use cases.

8. Federated learning approaches for the Healthcare sector
This breakout session will discuss and analyse federated learning approaches to facilitate the analysis of health data stored across different stakeholders and/or borders. This should, for instance, avoid the transfer or exchange of data and ensure increased security.

9. Explainable AI in Healthcare
Health data is particularly sensitive, and solutions developed with the help of AI are often difficult to understand. The aim of this breakout session is therefore to dive into explainable AI in order to promote the acceptance of digital health solutions in society.

10. AI expertise in the Healthcare Sector
The healthcare sector faces several challenges in attracting talents and empowering their employees to provide AI-based solutions. What are the specific needs for AI training and upskilling programmes, and how can these needs be aligned with academic activities and doctoral programmes?

11. HPC-AI convergence and the Healthcare Sector
HPC can propel AI applications toward grand challenges in healthcare: genomics, drug design, diagnostic. This breakout session will brainstorm on the open problems of HPC-AI convergence, such as programming and execution models, accuracy, reproducibility, portability.

12. AI and bioinformatics: integrating learning and biomedical knowledge
This session will focus on the key research challenge of developing learning models that are aware of and consistent with biomedical concepts and knowledge. We will brainstorm on promising learning paradigms, e.g., deep learning for graphs and learning-reasoning integration, as well as relevant knowledge source, e.g., interactomes

Theme Development Workshops cut across multiple ICT-48 Networks of AI Excellence Centres while bringing together researchers, industry representatives, and other stakeholders to identify industry trends and needs and match these to AI capabilities in Europe.

TDWs are co-organised by the VISION project in close cooperation with the TAILOR and HumanE-AI-Net projects as well as with CLAIRE AISBL.

Organising Committee