Next Generation Sequencing (NGS) technologies has revolutionized genomics data research by facilitating high-throughput sequencing of genetic material that comes from different sources, such as Whole Exome Sequencing (WES) and RNA Sequencing (RNAseq). The exploitation and integration of this wealth of heterogeneous sequencing data remains a major challenge. There is a clear need for approaches that attempt to process and combine the aforementioned sources in order to create an integrated profile of a patient that will allow us to build the complete picture of a disease. This work introduces such an integrated profile using Chronic Lymphocytic Leukemia (CLL) as the exemplary cancer type. The approach described in this paper links the various NGS sources with the patients’ clinical data. The resulting profile efficiently summarizes the large-scale datasets, links the results with the clinical profile of the patient and correlates indicators arising from different data types. With the use of state-of-the-art machine learning techniques and the association of the clinical information with these indicators, which served as the feature pool for the classification, it has been possible to build efficient predictive models. To ensure reproducibility of the results, open data were exclusively used in the classification assessment. The final goal is to design a complete genomic profile of a cancer patient. The profile includes summarization and visualization of the results of WES and RNAseq analysis (specific variants and significantly expressed genes, respectively) and the clinical profile, integration/comparison of these results and a prediction regarding the disease trajectory. Concluding, this work has managed to produce a comprehensive clinico-genetic profile of a patient by successfully integrating heterogeneous data sources. The proposed profile can contribute to the medical research providing new possibilities in personalized medicine and prognostic views.

A huge amount of imaging data is becoming available worldwide and an incredible range of possible improvements can be provided by artificial intelligence algorithms in clinical care for diagnosis and decision support. In this context, it has become essential to properly manage and handle these medical images and to define which metadata have to be considered, in order for the images to provide their full potential. Metadata are additional data associated with the images, which provide a complete description of the image acquisition, curation, analysis, and of the relevant clinical variables associated with the images. Currently, several data models are available to describe one or more subcategories of metadata, but a unique, common, and standard data model capable of fully representing the heterogeneity of medical metadata has not been yet developed. This paper reports the state of the art on metadata models for medical imaging, the current limitations and further developments, and describes the strategy adopted by the Horizon 2020 “AI for Health Imaging” projects, which are all dedicated to the creation of imaging biobanks.

No abstract

No abstract

No abstract