Bridging AI, Robotics, and Healthcare: an interview with Prof. Alexander Schlaefer

How can artificial intelligence and robotics revolutionize healthcare? What challenges remain in making AI-driven solutions safe and effective for clinical use? These questions drive the research of Prof. Alexander Schlaefer, a leading expert in medical robotics and AI at Hamburg University of Technology (TUHH) in Germany and a project manager in SustAInLivWork. His work focuses on developing intelligent systems that enhance diagnostics, treatment planning, and robotic-assisted procedures. In this interview, he shares insights into the advancements and challenges in this fast-evolving field.

Q: Could you tell us about your research group and the Medical Technology & Biomechanics Research Cluster at TUHH?

At TUHH, we foster a dynamic and interdisciplinary approach, encouraging collaboration between various research fields. Research is organized in clusters, where experts from different fields but with a shared research interest collaborate. For example, our Medical Technology and Biomechanics cluster brings together scientists with backgrounds including mechanical engineering, process engineering, computer science, mathematics, and even ethics. The latter is particularly interesting when considering the impact of AI on medical technology. We also maintain strong partnerships with clinicians, for example at Hamburg’s university hospital UKE, to ensure the practical relevance of our work – developing Technology for Humanity, which is the motto of TUHH.

The Institute of Medical Technology and Intelligent Systems was established in 2013 when I joined TUHH. One motivation was to strengthen medical technology research within the School of Electrical Engineering, Computer Science, and Mathematics. Our work focuses on AI methods for complex systems. For instance, in radiation therapy robotics, we explore how to optimize treatment planning to minimize damage to healthy tissue while effectively targeting cancer. This involves using machine learning to predict organ motion and developing algorithms that solve highly complex planning problems.

One example for successful interdisciplinary collaboration is our recent work with colleagues from mechanical engineering to study soft materials. Unlike autonomous cars which must avoid obstacles, medical robots interact directly with human tissue. Understanding tissue properties such as elasticity could help develop safer and more autonomous surgical robots. Machine learning also plays a role here, allowing us to estimate tissue characteristics and improve tumour detection, as tumours tend to be stiffer than surrounding tissue.

Q: AI in healthcare is a hot topic. What are some AI applications already in use?

AI is already deeply embedded in medical imaging – one of the most powerful diagnostic tools available today. For example, deep learning excels at detecting and classifying lesions in medical scans, assisting clinicians in diagnosing conditions ranging from brain tumours to coronary artery disease.

Beyond diagnostics, AI influences the organization of healthcare systems, improving hospital workflows, resource allocation, and even patient monitoring. However, given the complexity of the healthcare sector, these changes take time.

Q: What’s next for AI in medicine, and what challenges remain?

AI is already transforming clinical decision-making, diagnosis, and treatment planning, but there is much more potential to be unlocked. One of the biggest obstacles remains data quality and availability. Healthcare data is complex and sensitive, making it more difficult to access and use for AI applications.

Patient safety and regulatory approval are very important but also slow down the adoption of AI-driven solutions. Unlike consumer tech, medical innovations must undergo rigorous testing before reaching patients.

Q: What role do universities and projects like SustAInLivWork play in AI-driven healthcare advancements?

Academic research often pushes boundaries far beyond current clinical practice, experimenting with new AI methods. However, translating these innovations into practical clinical solutions remains a challenge. Initiatives like SustAInLivWork help to bridge this gap by facilitating collaborations between academia, industry, and healthcare professionals, ensuring that AI advancements are both scientifically sound and clinically implementable.

Q: Are there any AI-driven healthcare innovations already making an impact?

Yes, many, although innovation in medical technology takes time due to safety and certification requirements. AI is already assisting physicians and patients, improving diagnostics, automating administrative tasks, or supporting robot-assisted surgery. In the future, we will likely see more AI-powered medical devices, increasing accessibility to healthcare solutions.

Q: From your point of view, what have been the biggest surprises or challenges in applying AI to healthcare?

One major challenge is access to high-quality data, which remains a bottleneck for AI development. AI models are only as good as the data they are trained on, and in medicine, data is often incomplete, biased, or difficult to share due to privacy concerns.

Q: What are some common misconceptions about AI in medicine?

• Saying that AI is “thinking”. While AI can detect complex patterns, it doesn’t “think” in a human sense. It can also fail in surprisingly simple ways, and more research is needed to make sure its is safe and sound.
• Believing that AI works on its own. While AI is powerful, it still requires human expertise to frame problems and adapt methods effectively.
• Reducing AI to deep learning. I think that particularly robotics will play a prominent role, also contributing to the next wave of medical AI innovation.

Q: What advice would you give to young researchers interested in this field?

Learn the fundamentals of AI and robotics, and don’t be afraid to get hands-on with real-world systems and data. The field is still evolving, and there are countless opportunities to improve AI applications – especially in healthcare. Most importantly, remain critical and analytical about AI’s outputs and limitations.

AI and robotics are reshaping the future of healthcare, but significant challenges remain in ensuring safety, effectiveness, and real-world implementation. With researchers like Prof. Alexander Schlaefer leading the way, the bridge between AI innovation and clinical application is becoming stronger. Stay tuned for more insights from the world of AI-driven medical technology at SustAInLivWork.