Hosp Pharm 2016;51(7):599–603

2016 © Thomas Land Publishers, Inc.

www.hospital-pharmacy.com
doi: 10.1310/hpj5107–599

Director’s Forum
Big Data: Implications for Health System Pharmacy
Laura B. Stokes, PharmD*; Joseph W. Rogers, PharmD, MS†; John B. Hertig, PharmD, MS, CPPS‡;
and Robert J. Weber, PharmD, MS, BCPS, FASHP, FNAP§

Big Data refers to datasets that are so large and complex that traditional methods and hardware
for collecting, sharing, and analyzing them are not possible. Big Data that is accurate leads to more
confident decision making, improved operational efficiency, and reduced costs. The rapid growth
of health care information results in Big Data around health services, treatments, and outcomes,
and Big Data can be used to analyze the benefit of health system pharmacy services. The goal of
this article is to provide a perspective on how Big Data can be applied to health system pharmacy.
It will define Big Data, describe the impact of Big Data on population health, review specific
implications of Big Data in health system pharmacy, and describe an approach for pharmacy lead-
ers to effectively use Big Data. A few strategies involved in managing Big Data in health system
pharmacy include identifying potential opportunities for Big Data, prioritizing those opportuni-
ties, protecting privacy concerns, promoting data transparency, and communicating outcomes.
As health care information expands in its content and becomes more integrated, Big Data can
enhance the development of patient-centered pharmacy services.

INTRODUCTION first science and health care program to use Big Data;
Health care is becoming increasingly complex the magnitude of computing required to sequence the
with the advent of new treatments, evolving provider massive amount of genetic information challenged
roles, changing legislation and payment models, and paradigms in data-processing capacity.
health information technology. The electronic medi- Big Data can also be a powerful tool for phar-
cal record (EMR) is a form of health care technology macy directors regardless of the size of their depart-
used by providers and patients to access and manage ments. Leaders must understand the concept of Big
medical information. Computer desktops, laptops, Data, how organizations can use it, and pharmacy’s
and mobile devices provide efficient and effective role in that plan. The goal of this article is to provide
ways of viewing and processing medical information. perspective on how Big Data can be applied to health
EMRs also have interoperable capabilities; various system pharmacy. It will define Big Data, describe
applications can be viewed in one program providing the impact of Big Data on population health, review
a comprehensive view of a patient’s medical history. specific implications of Big Data in health system
Big Data has been associated with nuclear phys- pharmacy, and describe an approach for leaders to
ics, supercomputers, and defense simulations. Tech- effectively use Big Data. As health care information
nology advances, particularly in banking and retail, expands and becomes more integrated, Big Data will
enable the use of Big Data in business. For example, enable the growth and expansion of patient-centered
retail vendors use Big Data to enhance the understand- pharmacy services.
ing of consumer demand; purchasing patterns can be
tracked using reward cards and loyalty programs so BIG DATA DEFINITION
that decision makers can more effectively interpret Big Data is defined as data sets that are so large
customer needs.1 The Human Genome P ­ roject was the and complex that traditional computing methods are

*
PGY1 Health System Pharmacy Administration Resident; The University of Texas MD Anderson Cancer Center, Houston,
Texas; † PGY2 Health System Pharmacy Administration Resident, Memorial Hermann Health System, Houston, Texas; ‡Asso-
ciate Director, Purdue University College of Pharmacy, Fishers, Indiana; §Administrator, Pharmacy Services, The Ohio State
University Wexner Medical Center, Columbus, Ohio

Hospital Pharmacy 599

Director’s Forum

not capable of handling the information.2 Big Data tion. If patients are incorrectly identified as high risk,
results from the rapid assimilation of information the benefit of enhanced care management interven-
that is complex, is large in byte size, and is from many tions is lost. Additionally, in the case of readmission
different sources. Big Data gathers and stores health and triage, clinical workflow algorithms can be used
care outcomes resulting from advances in technology, to help identify patient-specific parameters, prioritize
treatments, and analytics and transmits this infor- patients according to risk factors, and minimize the
mation very quickly to data warehouses. Common time to appropriate therapy. Big Data may be used to
examples of how Big Data is used today include Net- measure the effectiveness of this algorithm.7
flix’s ability to predict how you will rate a given film Innovation in health care is influenced by finan-
using a variety of complex variables3 and Facebook’s cial models, patient needs, provider motivation, and
use of subscriber information to target posts and technology advances. Big Data may play an impor-
advertisements of interest.4 A few examples of Big tant role in driving health care innovation. Table 2
Data in health care include the demonstration of how summarizes how Big Data supports health care inno-
medication prescribing patterns differ in relation to vation through data demand, supply, technology, and
outcomes in various locations or the prediction of a government assistance.8
patient’s therapy success based on models built from Future cost projections suggest that health care
data from similar patients. expenditures in the United States will continue to
Some major sources for Big Data in health care increase. The aging baby boomer population, increased
are the electronic medical record (EMR), administra- prevalence of chronic disease states, technological
tive claims information, and clinical decision support advances, costly end-of-life care, and other operational
databases, like First Databank. EMRs include real- issues contribute to this projection.1 Health care legis-
time clinical data, such as patient identifiers (admis- lation is moving toward measuring quality health care
sion numbers), vital signs, diagnoses, and coded outcomes. Additionally, incentives and reimbursement
therapies. Administrative data include information for services depend on quality outcomes. In a chang-
from the Centers for Medicare & Medicaid Services ing health care landscape, where accountable care
or commercial insurance claims. All of these data organizations and patient-centered medical homes
are relevant and accessible to health system phar- are becoming the norm, the implications of Big Data
macy leaders. Table 1 summarizes different types and are at the forefront of progressive operational change.
sources of health care data.5 Big Data may be most effectively used to pro-
vide patients and providers with information based
IMPACT OF BIG DATA ON POPULATION HEALTH on population statistics to determine the best treat-
Population health is defined as the health out- ment options.2 EMR data can be used on a large
comes of a group of individuals, including the distribu- scale to provide insight on patient outcomes. These
tion of such outcomes within the group.6 Big Data may data include length of stay, risk factors for compli-
provide population health statistics for various medi- cations, or disease progression; all of these data can
cation-related indicators such as readmissions, patient be extrapolated to populations to predict o ­ utcomes.
triage and prioritization, adverse drug events, and Using ­real-time data in intensive care units or emer-
expensive medications. Bates and colleagues described gency departments to rapidly detect changes in
the need for enhanced ­methods of ­identifying high- patient status and apply appropriate treatments is
cost and high-risk patients to ensure effective interven- another example of the use of Big Data.1

Table 1. Types of health care data5

Type Source Attributes
Administrative • G overnment (CMS) • I nsurance billing
• National surveys (Medical Expenditure Panel Survey) • Financial reporting
• Commercial vendors (health plans, PBMs, etc) • Lacks clinical detail
Clinical •  ospital EMR
H • Clinical data collected for patient care
• Physician EMR
• Integrated delivery network EMR
• Clinical database
Note: CMS = Centers for Medicare & Medicaid Services: EMR = electronic medical record; PBMs = pharmacy benefit manager.

600 Volume 51, July-August 2016

 Director’s Forum

Table 2. Aligning Big Data to support health care innovation8

• C ost pressures
Demand for data
• Need to act quickly (first movers show impact, while late adopters only “keep up”)
• C linical data available across continuum of care
Supply of data
• Non–health care consumer data readily accessible
• A dvances in combining administrative claims data with clinical data
Technological capability
• Analytics
• G overnment emphasis on transparency
Market changes
• Interoperable standards between competitors in the private sector

Each stakeholder within the health system has and international normalized ratio (INR) testing
different goals for the use of Big Data. Patients may for warfarin therapy; in the future, this mechanism
utilize these data to empower their health care deci- of care delivery will be increasingly prevalent. Pay-
sions, whereas providers may use Big Data to obtain ers may use Big Data to develop sustainable business
real-time information about their patients or for deci- models secondary to the transition away from the
sion support. Health applications – or “apps” – have fee-for-service payment model. Finally, governmen-
been created to help manage many chronic disease tal agencies may use Big Data to reduce health care
states, including diabetes, and to enable smoking ces- costs and enforce health care regulations related to
sation and improve nutrition. Ochsner Health Sys- the quality of patient outcomes.1 Each stakeholder
tem, New Orleans, Louisiana, has implemented a within the health system will use Big Data in unreal-
stand-alone “O Bar,” where patients can walk in at ized capacities in the future.
any time to ask questions about health apps they are As information technology grows more capable
using and receive recommendations about other apps of translating Big Data, evidence-based guidelines may
and technologies for wellness.9 not be as applicable to patient care. Some of the popu-
Pharmaceutical and medical device companies lation health outcomes may demonstrate treatment
may use the data to better understand the mechanisms approaches different than those suggested by some
of diseases and their progression to develop safe, guidelines. Providers may use clinical decision support
targeted therapies with the fewest possible adverse tools to help ensure the safety and appropriate use of
events. Analysis of large datasets can enable predictive medication therapy given patient-specific factors such
modeling, which will result in a more efficient medica- as weight and creatinine clearance. As Big Data becomes
tion therapy development process. Advanced statisti- more prevalent in practice, providers will use this infor-
cal analysis and optimized study designs will result mation to develop treatment plans for each patient.
in stronger therapy trials with medications and their Another challenge related to the use of Big
intended populations. Big Data will also be a useful Data is the impact on Health Insurance Portability
tool in surveillance for adverse medication events, and Accountability Act of 1996 (HIPAA) privacy
both before and after market. The ideal impact of standards. There is debate among health care lead-
Big Data on the pharmaceutical industry is to ensure ers as to the public benefit of Big Data and the pro-
that the right patient has the right medication at the tection of patient privacy (HIPAA concerns). The
right time.1 Medical device companies market prod- integration of multiple systems and the combina-
ucts for home monitoring of medication levels and as tion of data from a variety of sources is concerning
surrogate markers of chronic diseases. A health care to some patients. HIPAA does not directly address
provider often transmits data electronically from the the complexity of data manipulation today; much
patient’s home device to the EMR for review. work is necessary to truly understand the real pri-
Providers review the data and make adjustments vacy risks associated with using Big Data in popu-
to medications or the therapy plan over the phone. lation health.
Providers can monitor patients for safety and adverse
events without seeing them in person. This gives APPLICATION OF BIG DATA TO HEALTH SYSTEM
patients increased access to health care without the PHARMACY
cost and inconvenience of an in-office visit. This is Most EMRs have clinical decision support tools to
common practice in blood glucose level ­monitoring guide the most appropriate prescribing of m
­ edication.

Hospital Pharmacy 601

Director’s Forum

Clinical decision support tools related to pharmacy generated has significantly increased. As information
include medication dose buttons, medication alerts technology can better organize and analyze the data,
such as duplicate therapy or drug-drug interaction the opportunity to use data as benchmarking tools
alerts, and warning pop-ups to alert users of poten- between institutions will continue to increase. Clini-
tially unsafe practice. Clinical decision support tools cal benchmarking databases can be used to identify
can also be used in other aspects of patient care to best practices, sources of waste within a workflow,
increase efficiency and improve the quality of care and resource utilization.10 These data can be used
provided.1 Potential applications include database by directors of pharmacy to identify problems and
maintenance, increased metrics and tools available in devise strategies for resolution or cost reduction.
inpatient and outpatient areas, and tools targeting pop-
ulation trends. The clinical data maintained within the GUIDING PRINCIPLES FOR USING BIG DATA
EMR can be used to identify patients who are at risk As health care moves toward utilizing Big Data to
for complications and would benefit from early inter- optimize patient care outcomes while reducing health
ventions or proactive care. This concept will become care costs, pharmacy leaders can use the following guid-
more applicable with increasing advances in informa- ing principles to effectively use Big Data (Figure 1).11
tion technology and advanced analytical skills.2 Improve the core business first. By evaluating the core
EMRs also contain financial, operational, business, leaders can identify all of the potential
and genetic data that can be used to evaluate the opportunities for Big Data within their organization.
appropriateness of treatment options for individual If this step is not taken, all of the benefits of the data
patients. Over the past 5 years, the amount of data may not be realized due to unidentified applications.

Optimization of
clinical decision
support tools

Claims and cost Formulary

data that management
provide and adverse
information on event
utilization monitoring

Big Data uses

within Health
System
Pharmacy

Enhanced Measure the

application of quality of care
evidence-based and patient
medicine outcomes

Better care
transitions via
data related to
medication
adherence

Figure 1. Using Big Data to promote health system pharmacy operations

and management.11

602 Volume 51, July-August 2016

 Director’s Forum

Define organizational model and talent strategy. Deter- tem pharmacy leaders must understand Big Data and
mining who will design and implement Big Data how they can use its elements to improve their phar-
­initiatives within an organization is one of the first macy practice model. Medication use outcomes can
steps necessary when planning a process change. be predicted by Big Data provided there is a strategy
Successful strategies include initiatives led within or for its application. The strategies offered in this arti-
across business units, through functional groups, cle should guide the pharmacy director in the future
or at the executive level. when handling Big Data. As health care information
Make it a priority. Especially within health care, it is expands in its content and becomes more integrated,
imperative that leaders buy in to the application of Big Data will be a valuable tool for enhancing the
Big Data as a tool to improve patient care outcomes. development of patient-centered pharmacy services.
If the application of Big Data is a priority beyond the
initial planning stages, the organizational workforce REFERENCES
will be ready for the changes. Additionally, leadership
1. Feldman B. Big data in healthcare: Hype and hope.
should focus on recruitment of the right talent and DrBonnie360.com. https://www.ghdonline.org/uploads/big-
concentrate significant efforts on strategic areas. data-in-healthcare_B_Kaplan_2012.pdf. Published October
Establish a vision from the top-down; establish innovation 2012. Accessed April 1, 2016.
from the bottom-up. When leaders set a vision and a strat- 2. Bates D, Saria S, Ohno-Machado L, Shah A, Escobar
egy, it allows end users to innovate and increases oppor- G. Big data in health care: Using analytics to identify and
tunities. However, this is only possible in an environ- manage high-risk and high-cost patients. Health Affairs.
ment where local innovation is the culture. The vision 2014;33(7):1123-1131.
set for the use of Big Data must go beyond performance 3. Krumholz H. Big data and new knowledge in medicine:
metrics and should encompass transformational change The thinking, training, and tools needed for a learning health
within the institution in order to get necessary buy in system. Health Affairs. 2014;33(7):1163-1170.
from front-line personnel. Engaging employees to exe- 4. De Montcheuil T. Facebook: A decade of big data. Wired.
cute the vision results in empowered employees com- http://www.wired.com/insights/2014/03/facebook-decade-
mitted to the established goals. big-data/. Published March 2014. Accessed April 26, 2016.
Set diverse goals. Goals associated with the implica- 5. Aparasu R, ed. Research Methods for Pharmaceutical Prac-
tions of Big Data should vary in size and target date. tice and Policy. Gurnee, IL: Pharmaceutical Product Press; 2010.
By establishing short-, medium-, and long-term goals,
6. Kindig D, Stoddart G. What is population health? Am J
momentum is established early on and maintained
Publ Health. 2003;93(3):380-383.
throughout the life of the project.
Strive for transparency. Data transparency in health 7. Raghupathi W, Raghupathi V. Big data analytics in health-
care: Promise and potential. Health Information Sci Syst.
care is important in terms of regulatory compliance.
2014;2(3):1-10.
To meet regulatory standards in health care, the data
must be HIPAA compliant and secure. Understanding 8. Groves P, Kayyali B, Knott D, Van Kuiken S. The big
how the data is procured and providing transparency data revolution in healthcare. Center for US Health System
Reform Business Technology Office. http://www.mckinsey.
about the strengths and limitations of the data is nec- com/industries/healthcare-systems-and-services/our-insights/
essary for health care leaders. Additionally, making the-big-data-revolution-in-us-health-care. Published January
data available for internal and external benchmark- 2013. Accessed April 1, 2015.
ing can be mutually beneficial for patient outcomes,
9. Ochsner’s O bar uses interactive health technology to
workflow efficiencies, resource utilization, and health enhance patient engagement. New Orleans, LA: Ochsner
care expenditure. Health System Public Relations Department; July 30, 2014.
Internal and external communication. Transparent https://news.ochsner.org/news-releases/ochsners-o-bar-uses-
communication with stakeholders, both internal interactive-health-technology-to-enhance-patient-engage/.
and external, will help leaders refine viewpoints and Accessed May 11, 2016.
ensure congruency of agendas. 10. O’Neal B, Weber R. Director’s Forum: Benchmarking
drug prescribing using clinical databases: A tool for practice
CONCLUSION model enhancement. Hosp Pharm. 2011;46(10):809-814.
Big Data is generated by the rapid assimilation 11. Ma C, Smith HW, Chu C, Juarez D. Big data in pharmacy
of technology from a variety of resources that range practice: Current use, challenges, and the future. Integrated
from simple to complex in their content. Health sys- Pharm Res Pract. 2015;4:91-99. 

Hospital Pharmacy 603