The following interview on the topic of ‘language models in clinical use’ was conducted with Dr. Michael von Wagner, specialist in internal medicine, Chief Medical Informatics Officer, Medical Director of the Medical Information Services and Digitalisation Unit, Unit of the Medical Director and Chairman of the Board, Managing Director of the University Centre for Digital Healthcare (UCDHC), Senior Physician at Medical Clinic 1, Frankfurt University Hospital. The interviewer was Dr. Michael Rammensee, Managing Director of the AI Quality & Testing Hub GmbH.
Dr. Michael Rammensee: Mr Wagner, could you first give us an overview of how AI and large language models work in everyday clinical practice and what benefits they offer?
Dr. Michael von Wagner: The use of powerful search engines developed specifically for medical professionals is widespread. They provide access to a wide range of medical information and resources that are crucial for clinical practice and research. Frankfurt University Hospital has launched the SATURN project, which aims to support general practitioners in diagnosing unclear and rare diseases: A smart doctor portal and the use of artificial intelligence are intended to provide patients, particularly those in rural areas, with better and faster diagnostic options.
Dr. Michael Rammensee: Can you tell us something about the use of such information systems and similar systems such as ChatGPT in medical care?
Dr. Michael von Wagner: The systems work similarly to ChatGPT by providing precise answers to general questions and acting as a virtual conversation partner. Although some clinics do not use LLMs due to data protection concerns, I see no reason to ban them for diagnostic support in general. We should not do without such systems.
Dr. Michael Rammensee: How do you see the integration of such systems into hospital information systems (HIS)?
Dr. Michael von Wagner: The integration of systems such as ChatGPT into HIS is an important step. In 9 out of 10 cases, such a co-pilot helps with questions that I might not think of. For example, it could point to a congenital predisposition and suggest testing the family. Unfortunately, the cost of an interface is often very high, which often only justifies implementation if the benefits are significant.
Dr. Michael Rammensee: What challenges do you see in integrating these voice-assisted technologies into everyday clinical practice?
Dr. Michael von Wagner: A major challenge is ensuring that treatment recommendations comply with guidelines and are not based solely on the doctor’s experience. The doctor should not be disempowered, but should be able to make informed decisions together with the patient. Digitalisation is now increasingly accepted by doctors, and the debate about it is subsiding.
Dr. Michael Rammensee: In your opinion, what else needs to happen to make the best use of these technologies?
Dr. Michael von Wagner: More needs to be invested in the preparation of decision templates. Doctors should be able to make informed decisions based on a wide range of information. A paradigm shift towards ‘the patient has a right to their records’ is necessary. The idea of EPA (‘Talk to your patient records’) could offer solutions. However, there is a dilemma when data is automatically transmitted to the patient without explanation, e.g. tumour markers.
Dr. Michael Rammensee: How could these technologies specifically improve patient care?
Dr. Michael von Wagner: In patient care, virtual medical assistants could be used, for example, to record patient consultations, compile family medical histories and store information in a structured manner with metadata. Replacing them with chatbots is certainly not a good idea, but automating smaller tasks such as recording consultations would be a big step forward.
Dr. Michael Rammensee: Finally, how do you see the future of AI governance in healthcare?
Dr. Michael von Wagner: AI governance is an exciting topic and should be considered from the outset. It’s about eliminating redundancies and putting information in chronological order. This will not only improve efficiency, but also significantly increase the quality of patient care.
Dr. Michael Rammensee: Can you explain the importance of interoperability in this context?
Dr. Michael von Wagner: Interoperability is crucial. There are already certified services in other digital areas, such as a messenger service. Interoperability will also become an important feature in AI applications. These developments are not specific to Frankfurt University Hospital, but are generic endeavours.
Many thanks to Dr. Michael von Wagner for his fascinating insights into the topic of ‘language models in clinical use’.