Clinical research is an integral part of advancing and improving healthcare. Through research, healthcare professionals can ensure that the medicines and medical devices that help treat us are safe and effective to use.<\/p>\n\n\n\n
But what use are breakthrough medical interventions without accurate and comprehensive clinical data \u2013 and how can we make sure that the right data is in the right hands and time to make the most of these interventions? <\/p>\n\n\n\n
Data-driven research fuels the continuous improvement of healthcare, helping to create what\u2019s known as a \u2018learning\u2019 health system \u2013 namely, a system that incorporates the latest evidence in the form of data and intelligence into clinical healthcare.<\/p>\n\n\n\n
Learning health systems go by many names: data hubs, living labs, innovation or informatics hubs, learning networks, learning laboratories, or data-driven improvement initiatives, to name a few.<\/p>\n\n\n\n
Regardless of their name, learning health systems offer the potential to improve diagnostic accuracy and efficiency, deliver precision medicine, advance drug discovery, support clinical performance, and reduce the risk of errors and adverse events.<\/p>\n\n\n\n
Researchers who incorporate data-driven research and insights into their work stand to reap the rewards \u2013 but ensuring access to data is robust, which can be easily interpreted and translated into everyday clinical practice, are some of the many challenges that must be navigated.<\/p>\n\n\n\n
Considerable time and effort are often required from data scientists to resolve issues with clinical data, potentially delaying research efforts. As health data continues to grow exponentially, through sources such as electronic health information (EHI), the challenge of resolving these issues will continue to grow, too.<\/p>\n\n\n\n
While there is no \u2018silver bullet\u2019 to address this, the role of clinical research data management is becoming increasingly important. If health data is managed well, it can generate reliable and statistically sound data which has the potential to greatly advance science \u2013 but how can data be managed most effectively?<\/p>\n\n\n\n
When it comes to data, most researchers don\u2019t have a single source of truth which they can rely on. While the amount of health data available is exploding, much of this data is held in disparate, siloed systems.<\/p>\n\n\n\n
In many instances, researchers need to access data beyond that of their own health system. While \u2018information blocking\u2019 rules (defined as any practice likely to interfere with the access, exchange, or use of EHI otherwise permitted by law) are in place, accessing data can still remain challenging.<\/p>\n\n\n\n
Further complicating matters, different health entities\u2019 data systems are often not \u2018interoperable\u2019 \u2013 or in other words, these systems aren\u2019t able to exchange and use health information from one another to benefit research.<\/p>\n\n\n\n
This adds time and potential cost to the research process and can also lead to duplication of effort between different research projects under current processes. Well-curated data that could potentially be used on another project will potentially be thrown out or lost at the end of the original research initiative.<\/p>\n\n\n\n
The disjointed nature of healthcare data highlights the need for a system that allows clinicians and researchers to effectively and efficiently navigate a complex maze of data. This system has the potential to ensure that the right data ends up in the right hands, at the right time.<\/p>\n\n\n\n
The \u201cright data\u201d is a person\u2019s data compiled from seamlessly linked traditional (clinical care data) and non-traditional (social determinants of health) sources. Privacy is of paramount importance, so data must also be securely transferred to the \u201cright hands\u201d of an authorised data scientist or researcher.<\/p>\n\n\n\n
The \u201cright time\u201d means that data should be able to be exchanged easily in order to be quickly compiled and analysed to make a difference. Deploying a well-designed, modern data platform that is interoperable and able to aggregate a wide range of health data, both traditional and emerging, is key.<\/p>\n\n\n\n
Introducing such a platform will allow the right data to end up in the right hands at the right time. This will assist data scientists and researchers in accessing and using data as efficiently as possible, speeding up the time required to release research findings into operational use.<\/p>\n\n\n\n