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 application perspective, our approach is use-case driven, i.e. following the needs of physicians and researchers and aiming at benefits for the patients.
With focuses on neurology, oncology, and further disease entities, we will work on early diagnosis, tailored therapies, and therapy decision tools. For a short description of the use cases see below.
Our first use cases are built to form a blueprint for the following ones, and we have already implemented organizational and technical measures, e.g. by convening groups of key persons and by implementing technical solutions. Our efforts will be based on previous and current work in numerous projects (e.g., BBMRI LPC and ADOPT, BioMedBridges, Leading Edge Cluster m4, e:Med).
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 (“safe data” ,“safe setting”, “safe outputs”) and by distributed approaches (e.g., “Data Analysis Trains”).
Outline of the architecture of a data integration centre
We will show that data integration, data sharing, and improved processes for health care and research will improve both research and health care. Physicians will be supported by innovative views on integrated data and by decision support components for personalized treatments. Future medicine will be preventive, personalized, participatory, and digital.
Several use cases have been selected by an internal call for our project:
Multiple Sclerosis (MS). This use case aims at a better understanding of the disease and on disease-modifying therapy of multiple sclerosis: markers and algorithms will be developed to predict the course of disease at onset and to allow early personalized treatment decisions. Clinicians and scientist from the participating sites have been deeply involved in basic and clinical collaborative MS research on imaging, biomarker, genetics, and immunology. Both longitudinal data and integration efforts are already available as a basis for further data collection and integration. Treatment success is expected to be maximized and adverse effects to be minimized.
Parkinson’s Disease (PD). This use case aims at early diagnosis and tailored therapies for Parkinson’s disease. Its goal is the development and intra-consortium deployment of an infrastructure supporting research on early diagnosis of the different subtypes of Parkinson’s disease (PD). Similar to the MS use case, this infrastructure will support the development and validation of therapy decision support systems. Accordingly, both use cases will be rather similar on the level of the required technical infrastructure. We will integrate a comprehensive set of clinical, imaging, and molecular data to delineate personalized disease courses and to facilitate clinical decision support. Alike to the MS use case, tailored stratification strategies are expected to maximize treatment success and to minimize adverse effect.
Precision Oncology. Precision oncology can be applied to all oncological entities. In order to focus our efforts and ensure early adoption by clinicians, we have selected specific clinical applications: indolent lymphoma and checkpoint inhibitor therapies in skin and lung cancer.
Stroke. This use case will utilize available data and biosamples of the partners, and will also focus on the integration of data from different health care sectors: emergency room, stroke unit & intensive care unit, rehabilitation, and other relevant settings for stroke care.
Cardiology. The cardiology use case will integrate clinical data, biosignal analysis with multi-level OMICS data (genomics, transcriptomics, etc.) to derive prognostic information for decision making in the clinical work-up. A first evaluation of the derived processes will be carried out via an observational cohort study.
Barrett Esophagus. This use case addresses the prevention and therapy of adenocarcinoma of the esophagus and the gastroesophageal junction.
Breast Cancer. The breast cancer use case will integrate data from a hospital registry with data of an e-health platform.
DIFUTURE is also planning a cross-consortia use case.