The DESIREE project aims to provide a web-based software ecosystem for the personalized, collaborative and multidisciplinary management of Primary Breast Cancer by specialized Breast Units, from diagnosis to therapy and follow-up.
HORIZON 2020
CALL H2020-PHC-2015-single-stage
TOPIC PHC-30-2015 Digital representation of health data to improve disease diagnosis and treatment
TYPE OF ACTION RIA
PROPOSAL NUMBER 690238
DESIREE has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 690238
Breast cancer is the most common and most deadly type of cancer affecting woman in the EU countries, with more than 460,000 new cases and 130,000 deaths in 2012 (EUCAN2).
Multidisciplinary Breast Units (BUs) were introduced in order to deal efficiently with breast cancer cases, setting guideline-based quality procedures, clinical decisions on cases based on consensus and a high standard of care. However, daily clinical practice and case presentation in the BUs is hampered by the complexity of the disease, the ever-growing amount of patient and disease data available in the digital era, the difficulty in coordination, the pressure exerted by the system and the difficulty in deciding on cases that guidelines do not reflect.
DESIREE will provide decision support on the available therapy options by incorporating experience from previous cases and outcomes, and thus, going beyond the limitations of existing guideline-based decision support systems (DSS). The DSS will be based on a knowledge model that will evolve with experience. Patients’ cases will be represented using a novel complex Digital Breast Cancer Patient (DBCP) model, which incorporates information about the patient clinical history and diagnostic and therapeutic procedures in cycles that may last for years.
The creation of a DBCP-based advanced knowledge model that incorporates clinical guidelines, clinical experience and important patient context information will provide timely advice on decisions and will reduce the number of decisions that the system is not able to reflect. It will also provide the ability to learn from experience and to evaluate the success or failure of previous decisions. It will exploit the information available both from the current case and from previous similar cases obtained by comparison using the DBCP model.
With the advent of eHealth and the advances in diagnostic and therapeutic procedures and key-enabling technologies, a vast amount of digital information is generated from diagnostic and therapeutic procedures. These include medical imaging data from different modalities, biological and genetic data, novel diagnostic tests and biomarkers, risk factors and clinical trials. We aim to incorporate information from multiple sources in the DBCP model to be prospectively exploited for decision support when there is evidence for their applicability in clinical decisions. We will explore the diagnostic and prognostic value of some sources still not applied in practice and we will provide advanced intuitive data mining and visual analytics tools to allow exploiting the multiple information available from retrospective cases and to be able to compare it with the current case.
Specific interactive tools will be also developed for quantitatively analysing medical images and fusing (registering) different imaging modalities with complementary information for enhanced insight. Regarding quantitative analysis, we will develop specific imaging biomarkers for image-based breast tissue characterization and image-based tumour characterization. Breast tissue characterisation is important in breast cancer risk assessment and has demonstrated predictive value for expected outcomes of some treatments. Highly automated cloud-based parallel implementations of these imaging algorithms will allow obtaining these biomarkers for a large number of previous cases, which will be also incorporated in the DBCP for data mining.
The system will be also connected to Genesystems (https://genesystm.com/), a genomic and bioinformatics platform leveraging NGS data offered by Sistemas Genomicos (SIG) that will help personalized diagnostic and treatment and provide valuable information about predictive value in the outcomes of some treatments, based on the patient individual characteristics.
Another objective of DESIREE is to develop a virtual surgery tool that could be applied in clinical practice, based on a multi-scale physiological model that predicts the outcome of breast conservative therapy (BCT). The model will have important physical and psychological implications for the patient regarding the outcome of conservative surgery and will enhance the patient-physician interaction when choosing the treatment. The model has the ability to incorporate the effects at the cellular-tissue level and to show the expected outcomes of radiotherapy (RT) treatments or (neo) adjuvant (systemic) therapies such as chemotherapy.
Finally, the heterogeneous data and knowledge bases, the DSS and the analysis and modelling tools will be integrated into a secure web-based software infrastructure. This web-based software will be provided with highly visual interfaces for exploring the patient case from its DBCP model. It will bring the necessary features for enhancing the coordination and management of different patient cases in the BUs and for exploring all the accumulated heterogeneous multi-scale information from previous patient cases in an intuitive manner.
To sum up, the DESIREE project has the objective of providing software tools to improve coordination and efficiency of Breast Units and to advance in the management, treatment and knowledge discovery in complex Primary Breast Cancer cases. Innovative market opportunities will be provided to the European health industry, offering comprehensive solutions to the clinical community, which claims for an integrated model for breast cancer management and whose model may be exported to other clinical scenarios.
