Using big data tools, large amounts of clinical and genomic data can be analysed to improve personalised care and significantly reduce healthcare costs.
Big data is an important element of digital health and refers to data processing applications that capture, search, analyse and visualise huge and complex datasets that are so big that traditional processing techniques fail to effectively handle them.
The digital health industry produces large amounts of clinical, financial, administrative and genomic data and needs big data tools to manage it.
In recent times, the digital health industry has been embracing big data tools at a furious pace and this is creating a paradigm shift in healthcare delivery pathways.
The National Health Service (NHS) of the United Kingdom is already using big data tools to analyse vast clinical datasets to examine effectiveness of new drugs and to reduce costs of expensive treatments in use today.
Big data tools transcend clinical R&D and have the potential to create large-scale improvements in how digital health is delivered such as:
Improved Quality and Efficiency in Healthcare
Chronic diseases such as diabetes are consuming an increasing share in an already expanding healthcare expenditure.
Using big data tools with their new analytics, millions of electronic health records (EHR) can be mined to identify statistically valid trends and effective outcomes across large populations. Such assessments help in optimally allocating healthcare resources and improving quality and efficiency.
For example, Brigham and Women’s Hospital in Boston analysed big data on orthopaedic joint replacement therapies from various sources and used it to systematically standardise the surgery procedures to reduce costs and improve outcomes.
Early Disease Detection
By employing digital health sensors that can monitor important biochemical markers, we can gather crucial data which can be analysed in real-time using big data tools to identify potential adverse events, medication side effects, allergic reactions and infections – which in turn helps physicians, organisations and governments to identify, prevent and manage diseases much earlier.
In a joint project by University of Ontario and IBM, big data streaming analytics techniques were used to successfully predict the onset of nosocomial infections in newborn babies 24 hours before the actual appearance of symptoms.
Precise Individual Treatment
Delivering personalised healthcare to each individual patient has always been a goal of digital health. Big data is a big step forward in that direction.
Big data can identify disease characteristics of a patient that are similar to a larger population. Using published research data and individual genetic information, it can make inferences that help in providing better interventions tailored to individual patients.
IBM has released a prototype program that predicts the most likely outcomes for diabetes patients by comparing the individual’s personal digital health data with disease management protocols and population health management averages. This resulted in a significant improvement in the management of symptoms.
Population Health Management
Big data combines and analyses patient information, health information, health insurance and public health data using big data tools, to improve clinical and financial results across large disease-specific and condition-specific patient populations.
UK’s NHS has unveiled plans to sequence genomes of more than a hundred thousand people in the next three to five years to improve population health management outcomes by feeding the resultant data into research of cancer and other genetic diseases.
Future applications of big data in the digital health industry are believed to be even more interesting and radical.
It can help to reduce wide variations in healthcare practices and outcomes across geographies, patients and providers. Big data also helps to significantly reduce healthcare costs by reducing undertreatment and overtreatment through personalised care.