TRANSLATIONAL MEDICAL RESEARCH
BMBF e: Med MultiPath –A Generic Multi-layer Model for Integrating Multiple Types of Pathway Knowledge
Currently the integration of prior knowledge about biological pathways as well as re-tracing the use of specific pathway knowledge in scientific publications is in-efficient and cumbersome. This junior group aims at facilitating the integration of pathway knowledge and boosting reproducible research in clinical research in general and in Systems Medicine in particular. This research project aims at easing data integration via a new generic multi-layer pathway modeling framework. The central idea is the definition of a multi-layer pathway modeling framework which offers a generic and extendable format for integrating multiple pathway types and further knowledge sources influencing these pathways. Its outstanding feature is the inclusion of procedures allowing automatic pathway transformations and their documentation.
BMBF e: Med MyPathSem - A Knowledge Base for Integrating Patient-specific Pathways for Individualized Treatment Decisions in Clinical Applications
Molecular biomarkers play an increasing role for diagnosis and prediction of progession or therapy response in complex diseases such as cancer. Individualized treatment decisions and specialized drugs warrant the need to broaden the focus from singular biomarkers to pathways. While Omics technologies allow the parallel measurement of many different markers, pathway databases offer vast amounts of knowledge on biological networks.
Our aim is to present the most relevant, meaningful and interpretable patient-specific pathways to clinicians and researchers. Thus, we aim to reduce the gap between patient centered routine documentation and ontology-driven pathway and gene annotation and establish a seamless data- flow from single patient data to Systems Medicine.
BMBF e: Med coNfirm - Systems Medicine of a Heart Disease Network for Improving Multilevel Heart Health
coNfirm is working with conditions of cardiovascular diseases such as heart failure, myocardial infarct and atrial fibrillation. The project aims to identify disease-spanning features and mechanisms using Systems Medicine approaches to gain profound knowledge of cardiovascular diseases. This is essential for the development of personalized medicine, including diagnostic, preventive and therapeutic measures.
The "coNfirm" network brings together nine e: Med groups, which are combining and evaluating different experimental datasets and clinical information obtained from project partners. To facilitate an efficient data exchange, datasets are harmonized and experimental standards as well as legal requirements are created. The developed tools for combining and exchanging big datasets can be transferred to many different areas to gain more insight in this field. This knowledge will be passed on to the e: Med community in workshops.
BMBF DIFUTURE Consortium: Data Integration for Future Medicine
DIFUTURE is one of the four consortia selected by the German Ministry of Education and Research for funding during the development and networking phase in the Medical Informatics Initiative (http://www.medizininformatik-initiative.de/en).
DIFUTURE aims to provide medical professionals and researchers with data of comprehensive depth and breadth – to improve healthcare processes, accelerate innovation, and achieve tangible benefits for patients. DIFUTURE will improve data quality, data availability, and data integration. Data and knowledge need to be available at the point of care as a basis for targeted diagnosis and therapy.
From an informatics perspective, we will adhere to state-of-the-art software engineering processes, and (a) start with a vision and global goals, (b) proceed to concrete goals, (c) specify analyses and data required for concrete improvements, (d) implement concepts and methods of secure data sharing, and (e) realize and evaluate concrete solutions. We will base our approach on sound architectural models.
We are clearly aware of the data security and privacy challenges of this initiative, with its unparalleled size and scope in Germany. We will provide strong levels of security by innovative combinations of privacy protection measures and by distributed approaches for federated analyses.
The DIFUTURE consortium is funded by BMBF during the development and networking phase since January 2018.
StMGP Project CARE REGIO
The increasing digitalization in nursing enables new forms of research and training through the electronic availability of data from the health care system. This requires initiatives to strengthen interoperability and standardization as well as new interfaces between systems. As part of the joint project "CARE REGIO" funded by the Bavarian State Ministry of Health and Nursing, the University of Augsburg together with the University of Applied Sciences in Augsburg, Neu-Ulm, and Kempten as well as the University Hospital in Augsburg are developing solutions to establish a leading region for digitally supported nursingin Bavarian Swabia. The project stands for a new, patient-centered care and research along a supply chain that starts before a possible hospital stay and reaches far into the post-hospital phase.
Junior Research Group "Modular Knowledge- and Data-Driven Molekular Tumor Board" (MoMoTuBo)
in a molecular tumor board, therapy decisions for cancer patients are taken based on a set of different data types (clinical data, radiological data, histopathological data, genomic data, gene expressuib data, and other high-throughput data). In addition, specific features are prioritized using bioinformatic methods (e.g. specific mutation and gene expression patterns), which are then used together with database research (mostly performed manually) to compile therapy suggestions and discuss in a disciplinary manner. However, it stays unclear how progressive knowledge and data from external sources can be integrated in the activity of a molecular tumor board as a standard-driven process. On the other hand, there is no systematic acquisition of previous patients and recommendations, that would make comparison of current and previous similar cases possible. In order to refer to big numbers of patients' cases, an interconnection between moelcular tumor boards in different locations should be established. The goals here are as follows:
- The conceptioning of a modular platform, in which reproducibility, documentation and update mechanisms can be realized alongside the processes.
- Creating concepts to bind clinical routine with research data.
- Reinforcing the automation of data integartion and the reprocessing including external knowledge.
- Developing of machine learning processes for the analysis in context of MTBs, for example the usage of unstructured knowledge (e.g. Doctor Reports), geenration of complex signatures to model therapy Therapieansprechen and identification of similar patients.
- The implementation of a prototype and open-source software for a modular, reproducible software platform of a MTB.
Basal cell carcinoma (BCC) is the most common cancer in humans. Up to now, these skin tumors have been detected relatively late clinically and by reflected light microscopy, so that they often require extensive surgery by means of micrographic surgery. The optical coherence tomography (OCT) is a non-invasive diagnostic tool for the early detection of subclinical BCC. Small BCC can be treated with a Nd:YAG laser instead of surgery instead of surgery.
In the OCTOLAB project, optical coherence tomography (OCT) for the diagnosis of basal cell carcinoma (BCC) will be integrated with a long-pulsed infrared laser for the therapy of BCC. In addition, diagnostics and therapy will be based on artificial intelligence (AI). AI will not only determine image parameters in the OCT images for the diagnosis of BCC including tumor thickness, tumor size, and subtype, but also control the laser therapy in terms of energy density, pulse length, and repetition rate, and finally verify the therapy success. This combined device for automated diagnostics and therapy could contribute to early detection and individualized minimally invasive therapy of BCC.
For consumers, choosing the appropriate products to take care of their skin is not always easy. An interesting and flexible solution for them would therefore be to take photos of themselves with their cell phones and let an AI do the rest.
GRAND-AID pursues the goal of using images of the face to achieve an assessment of the skin using a neural network. For the possible conditions, such as impurities, recommendations for individual care are to be developed by the Clinic for Dermatology and Allergology of the University Hospital Augsburg under Prof. Dr. med. Julia Welzel with the Augsburg cosmetics manufacturer Grandel - The Beautyness Company. At the end of the project, it should be possible to take pictures of one's own face on a website of Grandel - The Beautyness Company. Based on the images taken, a neural network will classify the condition of the skin. This classification shall be provided to the customer and serve for an individual selection of skin care products from Grandel - The Beautyness Company.