AI4Lungs: How Artificial Intelligence advances lung health

In modern healthcare systems, Artificial Intelligence (AI) can support physicians in making faster and more precise decisions, especially in the diagnosis and treatment of lung diseases. The EU-funded project AI4Lungs brings together 18 partners from across Europe to develop AI-based tools, data models, and decision support systems that improve clinical outcomes and resource efficiency.

The project collects more than 2,500 real patient records provided by clinical partners to train AI algorithms. Using these data, a digital twin platform simulates patient scenarios and generates tailored therapy recommendations.
“Our contribution to the project is to develop this decision support system and integrate it seamlessly into AI-supported data analysis,” explains Dr. Jonas Flechsig from Fraunhofer ITWM.
“Together with our project partners, we have already made significant progress this year. We have introduced the digital twin platform and can ensure that we comply with the new EU AI regulations.”

The AI4Lungs project combines diagnostic methods such as medical imaging, digital stethoscopy, liquid biopsies, and molecular pathology. The resulting multimodal data are analyzed using deep learning, ensemble learning, and computational linguistics.

The analysis results feed into a clinical decision support system (CDSS) that assists physicians and patients in determining the most suitable treatment pathway. The system uses knowledge-based methods, multi-criteria decision-making, and explainable AI to ensure transparent recommendations.

Medical data collection requires strict compliance with privacy and fairness standards. Legal and ethics partners Timelex and Deloitte ensure that the project meets the requirements of the EU AI Act.
“It is crucial that the design and implementation of AI tools are aligned with the future requirements of the AI Act from the outset,” says Marta Wilińska, legal expert at Timelex.

Marcel Rebbert, digital ethics expert at Deloitte, adds: “By following strict digital ethics principles when integrating AI tools into clinical workflows, doctors retain full decision-making power while being able to use AI for resource-intensive tasks such as diagnosis and treatment planning. This human-in-the-loop approach improves treatment outcomes and promotes sustainable healthcare systems.”

Project partner Future Needs focuses on fostering cooperation between European research initiatives.
“Building synergies with other EU projects that share a common mission is critical to accelerating progress. By working together, we grow faster and increase our collective impact,” says Emma Tsai, Head of Dissemination at Future Needs.

MEDICA-tradefair.com; Source: Fraunhofer Institute for Industrial Mathematics ITWM