1. What is meant by Big Data in healthcare?
Big Data in healthcare has often been defined with reference to the “three Vs” of data: Volume (a large amount of data), Variety (different types of data), and Velocity (data arriving at high speed). However, the notion of Big Data goes beyond the characteristics of data itself and includes how data are used, as is captured in the following definition from a recent European Commission funded study:
“Big Data in Health refers to largely routinely or automatically collected datasets, which are electronically captured and stored. It is reusable in the sense of multipurpose data and compromises the fusion and connection of existing databases for the purpose of improving health and health system performance. It does not refer to data collected for a specific study.”
(European Commission, Study on Big Data in Public Health, Telemedicine and Healthcare. 2016.)
2. How is Big Data in healthcare collected and analysed?
Healthcare systems routinely collect large amounts of data as patients use various healthcare services. For example, information on the fact that a patient has visited the doctor, as well as medicines prescribed would be included in the patient’s record. This information is required to provide the patient with optimal care, but also plays an important role in ensuring healthcare providers are reimbursed for their services. Beyond the “one-dimensional” collection of data, computer programmes help to combine and enrich data from different sources, thus generating an added value compared to the originally isolated datasets.
In broader terms, the analytic methods applied are to support all stages of the health technology life cycle from basic research (such as genomics, proteomics and metabolomics data) to reimbursement decisions (such as economic modelling methods) and subgroup identification (such as imaging data).
3. Who can use Big Data in healthcare and how?
The smarter use of healthcare data is expected to improve healthcare outcomes and make healthcare systems more efficient, accessible and resilient. It can also contribute to improved research and development, and lead to more effective policy making. Big Data can be used especially by healthcare services, the academia, policy makers, and the industry. A few examples on the use of Big Data in healthcare are the following:
• achieving better health outcomes
• improving the effectiveness of treatments and increasing patient safety
• monitoring healthcare services
• detection of population-level effects
• more efficient recruitment and selection of patients for clinical trials
4. What are the benefits of using Big Data for patients?
Big Data has been attributed as having “transformative potential” in healthcare systems, with benefits across the entire pathway of care delivery for all stakeholders. Linkage of previously separated data sets and their analysis using appropriate Big Data analytics offer new ways to accelerate research and to identify the right treatment for individual patients (personalised medicine). Access to large data sets gives a more comprehensive picture of patients, allows patient-related outcomes to be measured more accurately, and supports decision-makers in shaping healthcare systems.
5. What are health outcomes?
According to an explanation given by the International Consortium for Health Outcomes Measurement (ICHOM) in 2016:
“Outcomes are the results of treatment that patients care about most. Outcomes are not ‘outputs’; they are not lab results; they are not technical details. They’re real-world results, like physical functioning or level of pain or quality of life”.
6. Why is value-based and outcomes-focused healthcare important?
One of the primary goals of healthcare is improving the overall health of the population. Efficiently allocating funds to pay for care is a key factor, and it is crucial that scarce resources are spent wisely on treatments that offer the most benefits to patients, that is, better outcomes. Therefore, a value-based approach to healthcare would ensure that the healthcare system receives the greatest benefit from investment of public funds when deciding between treatment alternatives.
7. What is the Big Data for Better Outcomes Programme (BD4BO)? Where is its place within IMI?
Big Data for Better Outcomes (BD4BO) is part of the public-private Innovative Medicines Initiative 2 (IMI-2) – the world’s largest life sciences public/private partnership. BD4BO’s mission is to improve health outcomes and healthcare systems in Europe by maximising the potential of Big Data.
The Programme currently consists of research in four disease-specific areas: Alzheimer’s disease; haematological malignancies; heart diseases and prostate cancer are already ongoing and new projects in other disease areas will evolve. These projects will lead the way in using Real-World Evidence (RWE) to complement evidence obtained from clinical trials. RWE means using sources such as registries and electronic health records, but potentially also more novel sources of data such as from wearable technology like smartwatches or smartphones.
BD4BO and its projects aspires to become the “go-to” source for pan-European outcomes data and a trusted partner for patients, researchers, healthcare professionals, and decision-makers alike.
8. Which projects comprise the BD4BO Programme? Are future topics being considered?
The BD4BO Programme is composed of several projects, currently including projects in disease-specific areas as listed below. These disease-specific projects are supported by the Big Data for Better Outcomes, Policy Innovation and Healthcare Systems Transformation (DO->IT) Consortium, and the European Health Data Network (EHDN) project which aims to be a federated network of relevant and high quality data sources.
The disease-specific projects are:
ROADMAP – stands for: Real World Outcomes Across the Alzheimer’s Disease spectrum for better care: Multi-modal data Access Platform. The project aims to provide the foundation for a Europe-wide integrated data environment and framework for Real-World Evidence across the spectrum of Alzheimer’s disease. (www.roadmap-alzheimer.org)
HARMONY – stands for Healthcare Alliance for Resourceful Medicines Offensive against Neoplasm in Haematology. The Big Data platform developed by HARMONY, a European Network of Excellence for Big Data in haematology, is aimed at improving the outcomes of patients with haematological malignancies through the use of Big Data-sharing among all relevant stakeholders. (www.harmony-alliance.eu)
BigData@Heart – BigData@Heart’s goal is to develop clinically-relevant disease phenotypes, scalable insights from Real-World Evidence and insights driving drug development and personalised medicine through advanced analytics. (www.bigdata-heart.eu)
PROSTATE CANCER – upcoming project to be launched in 2018.
9. How can patient data contribute to improved outcomes?
A much more active participation of patients is needed to achieve the BD4BO Programme’s ambitious core objective: to develop an approach within existing data systems to efficiently enable initiation, maintenance, and evaluation of the right treatment to the right patient at the right time in healthcare systems.
The Programme plans to unlock a wealth of patient-reported outcome measures based on digital data mining with the aim of developing preventative and personalised approaches to care for the benefit of patients. Patients are the ultimate beneficiaries of improved outcomes so they are encouraged to play a more active role as consortium members and contributors.
10. How is patient data protected in the BD4BO project?
The Programme will provide a structure for empowering patients as data owners and partners in research. Recognising the ultimate right of patients to their personal data, including the right to opt out of data sharing, it will ensure that the informed consent templates and data privacy standards strike a balance between protecting individual privacy and promoting innovation. A toolkit will be developed that includes best practices and training materials for collaborating with patients, and informing them about data privacy in research.
11. How can I find information on the implementation of the BD4BO Programme?
The outcomes and results of the Programme, as well as relevant news, information on conferences and other events, our newsletters, publications and press releases will be communicated on our website: bd4bo.eu
12. How has Big Data been used in healthcare previously?
Historically, Big Data has been under-utilised due to lack of advanced technology to extract insights and data sharing among national healthcare systems. Many of today's investments in large datasets and Real-World Evidence are uncoordinated, duplicative, and inefficient due to lack of agreement on standardised IT-solutions. Other reasons include: terminology and outcomes to measure patient benefits, lack of appropriate data sources and methods to collect, analyse, report and use/interpret data.
13. What are the biggest challenges facing the use of Big Data in healthcare?
There are many challenges to overcome – the most important are:
• Security: perhaps the #1 concern of the healthcare industry is protecting data from a vast array of threats.
• Data capture: the lack of harmonised data capture systems must be improved to increase its overall quality and usability
• Clean data: more advances in cleaning data are needed to ensure datasets are accurate, consistent, relevant and not corrupted.
• Storage: as the volume of data is rapidly increasing, the safe and cost-effective storage of data is more critical than ever.
• Curation: developing complete, accurate and up-to-date metadata is vital to any data governance plan.
• Querying/sharing: data silos and interoperability problems can prevent query tools from accessing information. Standardisation and the use of common languages will help ensure the completeness and accuracy of stored data and facilitate data sharing.
• Reporting: again, to ensure consistency and completeness, data reporting must be standarised.
• Updating: data is not static and often requires updates. Organisations must ensure they understand what data can be updated manually vs. automated and that they are not creating unnecessary and costly duplicate records.
14. How have policy makers reacted to Big Data developments in healthcare?
European policy makers have made Big Data in healthcare a political priority. This led to the creation of a partnership between the EC and the European pharmaceutical industry represented by EFPIA - the European Federation of Pharmaceutical Industries and Associations. Following on from this, the Innovative Medicines Initiative 2 (IMI2), with a budget of almost €3.3 billion, was created to run from 2014 -2020. This represents the world’s largest life sciences public/private partnership!
15. What does high value treatment mean? How will it contribute to more effective care?
High value treatment means health outcomes achieved per euro spent. It’s about maximising what matters for patients and uniting the interests of all healthcare stakeholders. By its very definition, it’s goal is to make significant strides in pharma’s ability to anticipate, prevent and treat a broad spectrum of life-threatening diseases across the entire treatment pathway. This can be achieved by maximising the transformational potential of Big Data.
16. As the volume of healthcare data and its likelihood to be targeted by fraudsters increases, what measures are being taken to protect my private data?
Just like your financial data managed by your bank, the data protection industry continues to work diligently to stay ahead of fraudsters and safeguard the integrity of healthcare data. Patients are the ultimate beneficiaries of improved outcomes, so they are encouraged to be more active supporters and contributors to initiatives like BD4BO. Patient information is anonymous and patients will always have the right to opt-out of any data-sharing system.