MEDICA is the largest event for the medical industry worldwide. It has been a permanent fixture for over 40 years. Together with their colleagues from the University of Trier, the scientists from the DFKI Trier branch will present exhibits from the field of artificial intelligence in medicine and medical technology.

The exhibits and technologies from the DFKI will be demonstrated at the joint Rhineland-Palatinate stand in Hall 3, Booth E80.

Effective crisis management requires preserving the stability and ability to act on large parts of the overall social system. This requires flexible, timely, and appropriate responses to changing (crisis) situations. The Corona pandemic showed, as did recent extreme weather situations, that the constant adaptation, which is crucial for this, represents a considerable challenge for most actors. With the help of AI, this information can be processed so that the relevant actors receive significant support in the event of a crisis. This ranges from simple documentation to simulation-based training scenarios and training courses.

The crisis management cockpit AScore prepares decision-relevant information by integrating smart cities and agent-based social simulation. As a result, the simulation model is able to make predictions regarding the spread of infections under specific scenarios. The project AKRIMA takes up this approach and aims at strengthening the crisis resilience of critical infrastructures, logistics chains as well as authorities and organizations with security tasks by a simulation-based improvement of crisis response mechanisms.

More Information 

Using the example of skin diseases, research was conducted into how the Covid-19 pandemic affects the diagnosis and treatment of diseases in order to be able to counteract negative effects in a targeted manner.

The aim of this project is to contribute to the creation of structural foundations for the use of artificial intelligence in the medical domain, so that potentials can be identified and used in the short term. In particular, the fact that many individual diseases, such as skin diseases, but also large-scale disease events, such as the COVID-19 pandemic, develop in interaction with the "environment" is to be taken into account; on the one hand, they can be transmitted through interactions with sick people, animals or other sources of infection, or they can also be favoured or triggered in general by environmental factors of all kinds. 

The object of the planned work is therefore the conception and development of a corresponding integrated data and knowledge model from existing sources as well as the prototypical realisation of initial medical applications for individual medicine as well as public health. Here, the focus should be on two medical application fields for which preliminary work already exists: on the one hand, the simulation of the spread of the COVID-19 pandemic and, on the other hand, the diagnosis and treatment of skin diseases. The planned project is to be implemented at the German Research Centre for Artificial Intelligence in the form of a collaboration between researchers from Kaiserslautern and researchers at the newly founded branch office in Trier. The two subject areas SmartCity Living Lab (SCLL) and Pattern Recognition (PR) of the research area Smart Data & Knowledge Services in Kaiserslautern as well as the subject areas Cognitive Social Simulation (CSS) and Experience-Based Learning Systems (EBLS) located at the Trier branch are involved. Through this project, the existing competences will be further merged and networked and the foundation laid for further powerful research in the field of AI-based medicine in the future.

How can the mobility behaviour of patients with heart failure be improved? 

In the SiNuS project, computer simulations are to be used to design and plan behaviour-changing measures (nudging) for heart failure patients. The measures explored in the simulation are to be adapted to the physical performance and emotional state of those affected, so that health-promoting exercise is supported despite fear of physical strain. By means of qualitative surveys and empirical studies, including an age simulation suit, the potential for a simulation-based evaluation of the effectiveness of selected assistance approaches is demonstrated.

Researching and planning health-promoting behaviour in simulations can promote the independence of older people. In doing so, it is possible to adapt the measures to the needs of the persons concerned without time-consuming and burdensome preliminary examinations. In the future, the model is to be transferred to a larger target group as well as to other types of behaviour.

In the KIAFlex project, the aftercare processes are optimised and dynamically adapted to the changing requirements of the patients. The aim is to determine needs in a timely manner in order to improve the individual quality of care.

To this end, an AI-based assistance system is being developed and evaluated to improve clinical, organisational and administrative processes in discharge management. This will considerably relieve the clinical staff and at the same time achieve an improvement in the continuity of care during the transition to follow-up care.

In the OnkoCase project, doctors are supported by new visualisations and analogy-based searches in analysing and making treatment decisions.

In the case of advanced skin cancer, treatment decisions are more often based on the personal experiences of the doctors treating the patient due to a lack of evidence. Significant progress can be made here with a decision support system that is able to support the selection of treatment methods by analysing individual cases with artificial intelligence (AI) methods. For this purpose, previous cases form the basis of experience, which is documented in the form of treatment data in clinical information systems. Decision support systems could thus contribute to ensuring efficient oncological treatment and replace costly observational studies in the future.

SEEVacs: What does the distribution of vaccines among different cohorts mean? Using simulations, effects of vaccinations and new virus variants on pandemic events were investigated.

In the SEEvacs project, DFKI's agent-based simulation model SoSAD is linked with the EpideMSE platform of the Fraunhofer Institute for Industrial Mathematics (ITWM) in order to tap and exploit the synergies of both approaches for the exemplary investigation of vaccination strategies. The focus is on the effects of different vaccination strategies.

Since vaccines are initially only available in limited capacity, an important question at present is who will receive the vaccine and when. Consideration will be given to the vulnerability of the older population as well as the key role as disseminators to younger people. With the combined SoSAD-EpideMSE model it is now possible on the one hand to simulate and compare concrete vaccination scenarios (e.g. 10% of the available vaccine doses go to children, 30% to adults 50% to seniors).

Since the long-term simulation contains many imponderables, the absolute course of infection is not so much decisive as the relative change in the comparison of different scenarios and strategies.