MIRACUM will challenge the data integration centres with three Use Cases
Clinical trials are the gold standard for testing therapies or new diagnostic techniques that have the potential to improve clinical care. However, many clinical studies fail due to insufficient patient recruitment numbers. To improve this process with IT solutions and available routine data, we will integrate recruiting platforms in the hospital information system infrastructure of the MIRACUM university hospitals. This is based on previous research results of a joint project within five German university hospitals (KISREK) and the European IMI/EFPIA EHR4CR project. Based on an analysis of the eligibility criteria of clinical trials running at all MIRACUM partner sites we will define a core list of data elements, which are used most frequently as eligibility criteria in clinical studies. Regular data quality and data completeness evaluations and respective feedback loops will increase the quality and completeness of the required data elements in the MIRACUM hospital information systems and DIZ respectively.
The amount of patient data (clinical, longitudinal, omics) is growing continuously. These data must be brought together and analysed coherently to identify relevant treatment patterns and generate actionable knowledge. This dissemination and translation of predictive modelling research findings into healthcare delivery is still challenging – despite the progresses in predictive modelling research within the recent years. To tap the full potential of these patient data treasures, we first want to demonstrate how to develop, train and evaluate predictive models. This will be done by using machine learning approaches, including deep learning on federated data repositories. In a second step, we will evaluate how to implement them as decision support tools for physicians in the daily routine care processes. A first focus will be on Asthma/COPD as well as brain tumour cases.
Next-generation sequencing technologies have facilitated in-depth characterization of tumor samples. Using this technology, it is now possible to identify so-called „driver mutations“ for many tumor types, that trigger different therapeutic routes. However, the enormous, rapidly increasing number of potentially relevant mutations and the even higher amount of studies, that examine the relevance for tumor treatment, complicates the easy transition of research findings to clinical health care. In addition, it is still not evaluated how in-depth molecular tumor characterization and targeted treatment contributes to cancer patients´ outcome. To answer this question, several clinical trials have been started to test the implementation of Molecular Tumor Boards (MTBs) and measure the effectiveness of personalized treatment strategies for patient outcome. In the MIRACUM conceptual phase, we have already analysed and published the clinical experiences and attitudes towards genome-guided support within eight MIRACUM university hospitals. We also looked on activities, processes and IT solutions at all MIRACUM sites to gain a comprehensive understanding of the requirements and the processes involved in MTBs across these institutions. We plan to establish a generic framework supporting all steps from the analysis of omics data, their interpretation leading to a final therapy decision in the MTBs, and its documentation in the electronic health records at all MIRACUM partner hospitals. MIRACUM patient visualization modules will be implemented in the MTB platform for state-of-the-art presentation of total mutational burden and annotated mutations within a signal pathway of interest.
Hinderer M, Boerries M, Boeker M, Neumaier M, Loubal FP, Acker T, Brunner M, Prokosch HU, Christoph J.
Implementing Pharmacogenomic Clinical Decision Support into German Hospitals.
Stud Health Technol Inform. 2018;247:870-874. Doi: 10.3233/978-1-61499-852-5-870
Hinderer M, Boeker M, Wagner SA, Binder H, Ückert F, Newe S, Hülsemann JL, Neumaier M, Schade-Brittinger C, Acker T, Prokosch HU, Sedlmayr B. The experience of physicians in pharmacogenomic clinical decision support within eight German University Hospitals. Pharmacogenomics. 2017 Jun;18(8):773-785. Epub Jun 8. doi: 10.2217/pgs-2017-0027. PMID: 28593816
Hinderer M, Boeker M, Wagner SA, Lablans M, Newe S, Hülsemann JL, Neumaier M, Binder H, Renz H, Acker T, Prokosch HU, Sedlmayr M. Integrating clinical decision support systems for pharmacogenomic testing into clinical routine – a scoping review of designs of user-system interactions in recent system development. BMC Med Inform Decis Mak. 2017 Jun 6;17(1):81. Doi: 10.1186/s12911-017-0480-y. PMID: 28587608
Hinderer M, Boerries M, Haller F, Wagner S, Sollfrank S, Acker T, Prokosch HU, Christoph J. Supporting Molecular Tumor Boards in Molecular-guided Decision-making – the Current Status of Five German University Hospitals. Stud Health Technol Inform. 2017;236:48-54. Doi: 10.3233/978-1-61499-759-7-48. PMID: 28508778