The Role of Big Data in Medicine
Author: Gail S. Thornton, M.A.
In order to meet the increasing demands placed on the health care system due to increases in longevity and chronic disease awareness levels, delivery systems for health care are changing rapidly and a large portion of the decisions behind these changes are driven by data (Marr, 2015). Practitioners are now attempting to understand as much as possible about patients as early as possible in their lives, so that they can pick up on the warning signs of serious illness at an early stage and thereby possibly prevent or lessen the severity of illness as its onset.
Image SOURCE: Big-Data_Shutterstock_image_132470879
Over the course of the past several decades, rapid advancements have been made in an evolving field, called Big Data, which takes extremely large volumes of data that are analyzed to reveal patterns, trends and associations as well as comprehend their meaning and significance. Big Data also enables business throughout every industry to achieve increases in both efficiency and production (Marr, 2015). The data which are analyzed can originate from business transactions, both financial and nonfinancial (Perry, 2016). This is, particularly true in health care, where Big Data is making great inroads to predict epidemics, help researchers find cures for disease, improve quality of life and decrease the number of preventable deaths (Marr, 2015).
Mobile Technology Is Rapidly Growing
Millions of people throughout the world now use mobile technology to develop and live a healthier lifestyle. Mobile technology, such as smartphones and tablets, enables individuals to undertake self-care measures to help achieve and preserve health. For example, there are applications that measures the distance individuals walk each day, as well as provides calorie counters to plan their diet. Current examples of wearable devices that are specifically designed to achieve this purpose, include Fitbit, Jawbone and Samsung Gear Fit (Marr, 2015). Using this technology, users have the ability to track their progress and upload their data (Marr, 2015). Soon, it will also be possible for users to share their data with their doctors, which allows primary care providers to consider this information when addressing their patients’ care. This technology gives the public access to large, rapidly growing data bases of information, all which leads to achieving and maintaining optimum health.
In the near future, an individual’s data won’t be treated in isolation. It will be compared and analyzed alongside thousands of others, highlighting specific threats and issues through patterns that emerge during the comparison. This enables sophisticated predictive modeling to take place – a doctor will be able to assess the likely result of whichever treatment he or she is considering prescribing, backed up by the data from other patients with the same condition, genetic factors and lifestyle. Programs such as this are the industry’s attempt to tackle one of the biggest hurdles in the quest for data-driven healthcare: The medical industry collects a huge amount of data but it is stored in archives controlled by different doctors’ surgeries, hospitals, clinics and administrative departments (Marr, 2015).
Barriers of Technical Expertise and Integrated Security
The majority of health systems continue to handle their analytics and reporting needs without using Big Data (Adamson, 2016). Yet, at present, the majority of healthcare institutions are overwhelmed with the ordinary problems of regulatory reporting and difficulties with operational dashboards. Two of the primary barriers that impede healthcare facilities from addressing these problems using Big Data are lack of technical expertise and sufficient integrated security (Adamson, 2016). These deficiencies limit the use of Big Data and confine it, for the most part, to research applications because it requires a highly specialized skill set.
Within healthcare settings, HIPAA compliance is an absolute, non-negotiable necessity. No other considerations are understood to take precedence over ensuring the primacy and security of patient data. This is also a problem for Big Data, as experts indicate that there are not many good, integrated methods for managing security (Adamson, 2016). It is recommended that healthcare organizations purchase well-supported, commercial security distribution systems (Adamson, 2016).
Evidence-Based Medicine (EBM) As Gold Standard
Over the course of the past several decades, Evidence-Based Medicine (EBM) has become the gold standard for evaluating the efficacy of new methods and technology (Sim, 2016). EBM and Big Data can be understood as two distinctly different ways for addressing the information produced by empirical research.
The EBM approach is to pose a hypothesis, collect data by implementing a research study, and then analyze findings using biostatistics, which determines whether or not findings support the hypothesis (Sim, 2016). In contrast to this paradigm, the thinking of data science practitioners is derived from a computational tradition that is driven by data, rather than from hypothesis testing (Sim, 2016). Their deductions are based on raw observation and do not encompass context knowledge into consideration of evident production (Sim, 2016). Consequently, use of an algorithm has the potential to detect patterns in the database, without recognizing whether these patterns are “true, spurious or affected by bias” (Sim, 2016).
EBM prioritizes having explicit control of bias, while Big Data approaches seldom incorporate protocol-directed data collection, but rather focus on maximizing precision and external validity through use of the dictum “more data are better than better data” (Sim, 2016).
Both of these methods for understanding knowledge offer advantages and, therefore, experts consider these two methods to be complementary. The advantages of EBM are well-known and Big Data methods offer the potential inherent in expanded research power, particularly, in analytics studies that focus on “classification, prediction, modeling, and simulation” objectives (Sim, 2016).
Adamson, D. (2016). Big data in healthcare made simple: Where it stands today and where it’s going. Health Catalyst. Retrieved from https://www.healthcatalyst.com/big-data-in-healthcare-made-simple
Marr, B. (2015). How big data is changing healthcare. Forbes Magazine. Retrieved from http://www.forbes.com/sites/bernardmarr/2015/04/21/how-big-data-is-changing-healthcare/#5b3a37a32d91
Perry, P. M. (2016). Harnessing the power of big data and data analysis to improve healthcare entities. Hfm (Healthcare Financial Management), 70(1), 74. http://search.ebscohost.com/
Other related articles:
Other related articles published in this Open Access Online Scientific Journal include the following:
10 Most Successful Big Data Technologies
Big Data Self-Delusion
Top 100 Big Data Experts to Follow
Healthcare conglomeration to access Big Data and lower costs
Future of Big Data for Societal Transformation