A harmonious partnership meets technological excellence
"The most exciting aspect is that by applying technology, we are able to advance medical knowledge concerning hematological malignancies, one of the most complex diseases from a medical and data perspective," says Michel van Speybroeck, responsible for the architecture of the HARMONY Big Data Platform. As a data scientist with 20 years of experience, he highlights that the most significant potential in the HARMONY Alliance lies in cooperation between stakeholders and the trust that binds all their efforts together. The project stands out in many ways. It's a well-constructed organism with an innovative approach to data analysis and management, which enabled notable progress to be made over a short time period.
"We established a broad community, set robust data safety and privacy regulations, created a seamless governance model, developed novel methods of data analysis and harmonization, and we built a technical infrastructure. All that required and continues to require a very substantial coordinated effort between multiple stakeholders. But with the commitment of our Partners, Associated Member and Patient cluster, everything works as it should. And this is the unique feature of the HARMONY Big Data Platform: teamwork and precision," points out van Speybroeck. "Besides, let's not forget the scientific challenge – the HARMONY Alliance is oriented towards 14 blood cancers". The HARMONY researchers access various data streams from different sources to generate meaningful results for both patients and clinicians. Read about the HARMONY blood cancer focus >
From recognizing disease characteristics to progress in medicine
Many variables may be used to characterize hematological cancers: clinical data, genomics, imaging data, diagnostics, electronic health records. In order to answer the as yet unanswered questions and gain complete knowledge, researchers must analyze these different types of data from various sources. The multimodal data must first be fused and harmonized to make it readable for algorithms.
"Long hours in computer labs are required before we can gain scientific insights from the data. We must deal with the data collected for different purposes and in different formats. In the first step, we have to make them consistent and create data sets prepared for big data analysis. All of these processes remain invisible even to our members but they are essential," notes van Speybroeck. "Sometimes it requires many discussions to decide on the meaning of one particular variable." It is also noteworthy that the HARMONY Big Data platform, launched in 2017, has been built on the latest advancements in machine learning and artificial intelligence. For instance, it relies on spark technology – a unified analytics engine for large-scale data processing. The OMOP Common Data Model allows the researchers to harmonize and analyze different databases donated by the HARMONY Alliance members. "Having these open-source tools in place, we saved 1-2 years which would normally be required for the development of a dedicated data model."
Unexplored territories of science, where anything could happen
As soon as data processing is scalable and robust, scientists can start addressing research questions. They have access to a brand new tool – a virtual "microscope" allowing them to investigate big data sets. Michel van Speybroeck emphasizes that although technology is a beautiful part of science, it's only an enabler at the end of the day. "The outcomes arise from linking people truly committed to developing better therapy and care options for patients with blood cancer." In this kind of teamwork, trust plays a central role. Being a pioneer in leveraging artificial intelligence for Hematological Malignances also requires blazing new administrative trails. The HARMONY Alliance managed to develop data security and data processing standards consistent with EU legislation and ethical guidelines. This novel approach could become a blueprint for similar projects. Nonetheless, van Speybroeck hopes that the legal framework in this area will become more transparent and consistent, thereby facilitating the power of AI in medicine in the future. "I believe that success breeds success. The first papers based on the outcomes from the HARMONY Big Data Platform have already been published. And it's only the beginning of how data science can help to speed up research for the good of the patient," concludes van Speybroeck.
The HARMONY Big Data Platform: A central data base where the anonymous data donated by our partners and Associated Members is collected securely following all legal and ethical requirements, harmonized and then analyzed. Here emerge various data sets from different data providers – pharma, biobanks, hospitals, interventional, and non-interventional trials.
Related articles:
HARMONY (since 2017) and HARMONY PLUS (since 2020) have received funding from the Innovative Medicines Initiative 2 Joint Undertaking, under grant agreement No. 116026 for HARMONY and grant agreement No. 945406 for HARMONY PLUS. This Joint Undertaking receives support from the European Union’s Horizon 2020 Research and Innovation Programme and the European Federation of Pharmaceutical Industries and Associations (EFPIA).
Become involved! Connect with us and find out what we can offer you >
Receive the latest news. Click here to subscribe!