Skip to main content

Blood cancer: 63k patient datasets readied to reveal ‘untapped’ potential of AI in cancer research

The HARMONY Alliance is using advanced data analysis methods based on artificial intelligence and machine learning to answer questions about haematological malignancies.

03 February 2022
Acute Myeloid Leukemia cells in 3D illustration. Image by Nemes Laszlo via Shutterstock
Acute Myeloid Leukaemia cells in 3D illustration. Harmony will mine 100,000 patient datasets for insights into haematological malignancies. Image by Nemes Laszlo via Shutterstock

100,000 patient datasets, of which 63,000 have already been incorporated into a secure and anonymised ‘data lake’, will be mined for insights into haematological malignancies (blood cancers) and treatment outcomes. The HARMONY Alliance is using advanced data analysis methods based on artificial intelligence and machine learning to answer questions about how to diagnose patients earlier and with greater precision, the best practices that could help doctors make better treatment decisions, how to tackle the unmet patient needs of patients, and the best way to accelerate new drug development.

The HARMONY Big Data Platform is unique; the data lake is one of the largest databases of its kind, and is continuously growing. The datasets have been shared by partners and associated members of the HARMONY Alliance, with utmost care being taken to ensure the anonymisation and the quality of the data. The scientists hope to discover unknown correlations and trends in the data and thus develop new treatment algorithms to be adapted in clinical practice. AI offers many, so-far untapped, opportunities in haematology. It can improve the precision of diagnosis, support risk stratification in Acute Myeloid Leukaemia (AML) and Myelodysplastic Syndromes (MDS) for example, optimise treatment plans, and predict the response to different drugs. Indeed, the Multiple Myeloma group in HARMONY has already achieved results in risk stratification models.

“The first challenge was to prepare a robust research facility. We had to establish the technical infrastructure and shape the security procedures for the secondary use of data. Having the right structure, a network of international experts, and data from over 63,000 patients at the present time, we have recently proceeded to the core phase – data analysis using artificial intelligence (AI). We are excited about the discoveries already published and about the potential that we hope to unlock,” says machine learning and neural networks expert Professor Gastone Castellani, Professor of Applied Physics and Biophysics at the University of Bologna.

"This is just the beginning, our biggest challenge now is to exploit our analytical resources to mine the data, while at the same time transforming the consortium into a self-sustaining institution for the time after the IMI grant ends," says Professor Jesús María Hernández Rivas MD of the University of Salamanca, coordinator of the project.

HARMONY is supported by the Innovative Medicines Initiative, a partnership between the European Union and the European pharmaceutical industry.