WP5 will work on providing the means for analyzing complex data sets comprised of different layers of information. This will enable molecular and clinical data to be linked to predicting outcomes. Its activity will be centered on the description, analysis, and modeling of the data collected, which will then be generated into a personalized medicine framework. Tools and models will be implemented to answer the most important disease-specific questions and will be applicable to cross-disease analyses.
- Harmonizing data according to their heterogeneity and complexity, with a special emphasis on statistical data cleaning (which identifies and corrects any abnormalities in the data) and statistical harmonization (normalization);
- Characterizing any variables that impact the data collected;
- Describing and modeling outcomes, particularly those related to disease progression, responder/non-responder factors, quality of life, healthcare resource use, and cost;
- Using economic analysis tools to identify and compare the value of HM care;
- Integrating data to create a holistic approach in a personalized medicine framework;
- Reporting on the cost-effectiveness of therapies and their societal value (including information on the quality of life).
AEMPS, Amgen, AP-HP, Barts Health, Bayer, BFArM, EBMT, ELN, EORTC, Erasmus MC, ERIC, FISM Onlus, GFM, GMV, Goethe University, GPOH, GRAALL, GRL-SANGER, HHU, HULAFE, IECSCYL-IBSAL, IJC, Janssen, LeukaNET, LMU, LYSA, MediSapiens, MenarinI, MLL, MU, Newcastle University, NICE, Novartis, OPBG, Takeda, Ulm University, UNIBO, UNITO, University of Cambridge, University of Helsinki, University of Navarra, University of Rome Tor Vergata, University of York, VHIO, VIB, Vumc.
First Year Achievements
Considerable progress has been made in terms of establishing the Big Data platform and the methodology for analyzing data:
- HARMONY's Big Data platform has been established;
- A common data model that adheres to the FAIR (findable, accessible, interoperable, and reusable) data-sharing principles has been created;
- HARMONY has begun developing and testing models based on available data on AML (TCGA public data, UNIBO internal data and Sanger Institute data);
- HARMONY has started analyzing the description of datasets;
- Methods working on methods for gene network analyses are beginning to be developed.
WP5 will focus on demonstrating the value of harmonizing heterogeneous HM patient data sources: developing novel analytical algorithms to identify molecular predictors of clinical outcomes and efficacious therapies, trends in economic and social impacts and improve patient quality of life.
- Statistical harmonization and analysis of complex HM patient data sets including different layers of information, such as molecular omics and clinical data;
- Identification of specific molecular biomarkers to better predict clinical outcomes and outcomes from treatment in patients with HMs, to stratify therapeutic approaches and begin to build a framework for personalized medicine;
- Development of novel algorithms based on statistical and machine learning techniques to analyze data and build predictive models to improve the way in which we analyze HM patient data;
- Deployment of the above-mentioned algorithms on the Data Platform and dissemination among partners in order to foster their utilization and learning;
- Assessment of the societal and economic impact of patient treatment regimens and improvement of patient management and quality of life via health economics and epidemiological methods.