Personalised Medicine: Multidisciplinary Research Towards Implementation



Prof. Dr. Maria-Esther Vidal


Prof. Dr. Maria-Esther Vidal (Scientific Data Management Group), Samaneh Jozashoori (Scientific Data Management Group), Ahmad Sakor (Scientific Data Management Group), Philipp Rohde (Scientific Data Management Group)


Bundesministerium für Gesundheit (BMG)


Januar 2020 - Dezember 2022


In the last decade, a wide range of new treatments have been proposed to heal lung cancer, the leading cause of cancer-related death in the world and its most frequent type. Still, the response to these new options strongly varies between patients, and few guidelines are available on how to optimize the treatment choice. P4-LUCAT aims at developing a technological solution supporting oncologists in the selection of the most appropriate lung cancer treatment. P4-LUCAT will make available a Big Data analytics framework able to integrate patient data, public repositories, and literature evidence. The P4-LUCAT framework will provide the practitioner with information about: (a) the efficacy of a treatment, tailored to the geno- and phenotypical characteristics of the patient; (b) the expected adverse effects and toxicities; and (c) relevant literature supporting these findings. This can only be achieved by integrating different sources of information, including Electronic Health Records, laboratory test results from liquid biopsies, scientific literature, and open structured data. It also requires the integration of techniques spanning from Natural Language Processing to knowledge graphs. P4-LUCAT will impact the healthcare system by supporting better treatment selection decisions, thus reducing toxicities and adverse effects, and increasing treatment effectiveness. Moreover, conscious decisions will have a direct effect on treatment costs, e.g., by reducing the number of visits and unnecessary tests, and increasing quality of life and employability of the patients. In summary, P4-LUCAT will yield a novel scenario, in which an evidence- and data-based information system will support oncologists during decision-making.

The TIB team leads the tasks required to support the integration of heterogeneous data sources and semantification of Big data on demand. These tasks include: i) Creation of a federation of knowledge graphs; ii) query processing techniques over knowledge graphs; iii) data integration techniques. As the outcomes of these tasks, knowledge-driven infrastructures for ingesting, curating, and semantically describing Big data will be make available.


Back to list