The implementation of Clinical Decision Support (CDS) solutions is an important prerequisite for reducing the knowledge gap between clinical research and practice, especially in a complex genetic disease such as cancer. However, current CDS solutions are unable to support all the complex decisions required for personalized treatment of cancer patients and become quickly obsolete due to the high rate of change in therapeutic options and knowledge. Our CDS framework enables the development of decision support tools that flexibly integrate a large variety of multiscale models and can leverage the efforts of a large community of modellers. In our implementation, we combine community-developed models described in the literature (e.g. the St. Gallen stratification for early breast cancer) and models derived by mining the comprehensive datasets from clinical trials and care brought together in the p_Medicine collaborative research project. This framework and its underlying solution for models storage, management and execution will also constitute a platform for continuous validation of existing models on new data. Our goal is to enable the reuse of existing models for CDS and for the development of new models, and to support collaboration among modellers, CDS implementers, biomedical researchers and clinicians. We initially develop and deploy our solution in the context of the p-Medicine project in the oncology domain, but we aim to expand our scope and to reach out to a wide community of users in the biomedical area.
Abstract-Clinical decision support (CDS) systems promise to improve the quality of clinical care by helping physicians to make better, more informed decisions efficiently. However, the design and testing of CDS systems for practical medical use is cumbersome. It has been recognized that this may easily lead to a problematic mismatch between the developers' idea of the system and requirements from clinical practice. In this paper, we will present an approach to reduce the complexity of constructing a CDS system. The approach is based on an ontological annotation of data resources, which improves standardization and the semantic processing of data. This, in turn, allows to use data mining tools to automatically create hypotheses for CDS models, which reduces the manual workload in the creation of a new model. The approach is implemented in the context of EU research project p-medicine. A proof of concept implementation on data from an existing Leukemia study is presented.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.