Use of a standardized nursing language for documentation of nursin.docx

Use of a standardized nursing language for documentation of
nursing care is vital both to the nursing profession and to the
bedside/direct care nurse. The purpose of this article is to
provide examples of the usefulness of standardized languages to
direct care/bedside nurses. Currently, the American Nurses
Association has approved thirteen standardized languages that
support nursing practice, only ten of which are considered
languages specific to nursing care. The purpose of this article is
to offer a definition of standardized language in nursing, to
describe how standardized nursing languages are applied in the
clinical setting, and to explain the benefits of standardizing
nursing languages. These benefits include: better
communication among nurses and other health care providers,
increased visibility of nursing interventions, improved patient
care, enhanced data collection to evaluate nursing care
outcomes, greater adherence to standards of care, and facilitated
assessment of nursing competency. Implications of standardized
language for nursing education, research, and administration are
also presented.
Keywords: North American Nursing Diagnosis Association
(NANDA); Nursing Intervention Classification (NIC); Nursing
Outcome Classification (NOC); nursing judgments; patient care;
quality care; standardized nursing language; communication
Citation: Rutherford, M., (Jan. 31, 2008) "Standardized Nursing
Language: What Does It Mean for Nursing Practice? "OJIN: The
Online Journal of Issues in Nursing. Vol. 13 No. 1.
Recently a visit was made by the author to the labor and
delivery unit of a local community hospital to observe the
nurses' recent implementation of the Nursing Intervention
Classification (NIC) (McCloskey-Dochterman & Bulechek,
2004) and the Nursing Outcome Classification (NOC)

(Moorehead, Johnson, & Maas, 2004) systems for nursing care
documentation within their electronic health care records
system. �it is impossible for medicine, nursing, or any health
care-related discipline to implement the use of [electronic
documentation] without having a standardized language or
vocabulary to describe key components of the care process.
During the conversation, one nurse made a statement that was
somewhat alarming, saying, "We document our care using
standardized nursing languages but we don't fully understand
why we do." The statement led the author to wonder how many
practicing nurses might benefit from an article explaining how
standardized nursing languages will improve patient care and
play an important role in building a body of evidence-based
outcomes for nursing.
Most articles in the nursing literature that reference
standardized nursing languages are related to research or are
scholarly discussions addressing the fine points surrounding the
development or evaluation of these languages. Although the
value of a specific, standardized nursing language may be
addressed, there often is limited, in-depth discussion about the
application to nursing practice.
Practicing nurses need to know why it is important to document
care using standardized nursing languages, especially as more
and more organizations are moving to electronic documentation
(ED) and the use of electronic health records. In fact, it is
impossible for medicine, nursing, or any health care-related
discipline to implement the use of ED without having a
standardized language or vocabulary to describe key
components of the care process. It is important to understand
the many ways in which utilization of nursing languages will
provide benefits to nursing practice and patient outcomes.
Norma Lang has stated, "If we cannot name it, we cannot
control it, practice it, teach it, finance it, or put it into public

policy" (Clark & Lang, 1992, p. 109). Although nursing care
has historically been associated with medical diagnoses, �today
nursing needs a unique language to express what it does so that
nurses can be compensated for the care provided. nurses need an
explicit language to better establish their standards and
influence the regulations that guide their practice.
A standardized nursing language should be defined so that
nursing care can be communicated accurately among nurses and
other health care providers. Once standardized, a term can be
measured and coded. Measurement of the nursing care through a
standardized vocabulary by way of an ED will lead to the
development of large databases. From these databases,
evidence-based standards can be developed to validate the
contribution of nurses to patient outcomes.
The purpose of this article is to offer a definition of
standardized language in nursing, to describe how standardized
nursing languages are applied in the clinical arena, and to
explain the benefits of standardizing nursing languages. These
benefits include: better communication among nurses and other
health care providers, increased visibility of nursing
interventions, improved patient care, enhanced data collection
to evaluate nursing care outcomes, greater adherence to
standards of care, and facilitated assessment of nursing
competency. Implications of standardized language for nursing
education, research, and administration are also presented.
Standardized Language Defined
Keenan (1999) observed that throughout history nurses have
documented nursing care using individual and unit-specific
methods; consequently, there is a wide range of terminology to
describe the same care. Although there are other more complex
explanations, Keenan supplies a straightforward definition of
standardized nursing language as a "common language, readily
understood by all nurses, to describe care" (Keenan, p. 12). The

Association of Perioperative Registered Nurses (AORN) (n.d.)
adds a dimension by explaining that a standardized language
"provides nurses with a common means of communication."
Both convey the idea that nurses need to agree upon a common
terminology to describe assessments, interventions, and
outcomes related to the documentation of nursing care. In this
way, nurses from different units, hospitals, geographic areas, or
countries will be able to use commonly understood terminology
to identify the specific problem or intervention implied and the
outcome observed. Standardizing the language of care
(developing a taxonomy) with commonly accepted definitions of
terms allows a discipline to use an electronic documentation
system.
Consider, for example, documentation related to vaginal
bleeding for a postpartum, obstetrical patient. Most nurses
document the amount as small, moderate, or large. But exactly
how much is small, moderate, or large? Is small considered an
area the size of a fifty-cent piece on the pad? Or is it an area the
size of a grapefruit? Patients benefit when nurses are precise in
the definition and communication of their assessments which
dictate the type and amount of nursing care necessary to
effectively treat the patient.
The Duke University School of Nursing website <
www.nursing.duke.edu> has a list of guidelines for the nurse to
use for evaluation of a standardized nursing language. The
language should facilitate communication among nurses, be
complete and concise, facilitate comparisons across settings and
locales, support the visibility of nursing, and evaluate the
effectiveness of nursing care through the measurement of
nursing outcomes. In addition to these guidelines the language
should describe nursing outcomes by use of a computer-
compatible coding system so a comprehensive analysis of the
data can be accomplished.

Current Standardized Nursing Languages and Their
Applications
The Committee for Nursing Practice Information Infrastructure
(CNPII of the American Nurses Association (ANA) has
recognized thirteen standardized languages, one of which has
been retired. Two are minimum data sets, seven are nursing
specific, and two are interdisciplinary. The ANA (2006b)
Recognized Terminologies and Data Element Sets outlines the
components of each of these languages.
The submission of a language for recognition by CNPPII is a
voluntary process for the developers. This terminology is
evaluated by the committee to determine if it meets a set of
criteria. "The criteria, which are updated periodically, state that
the data set, classification, or nomenclature must provide a
rationale for its development and support the nursing process by
providing clinically useful terminology. The concepts must be
clear and ambiguous, and there must be documentation of utility
in practice, as well as validity, and reliability. Additionally,
there must be a named group who will be responsible for
maintaining and revising the system" (Thede & Sewell, 2010, p.
293).
Another ANA committee, the Nursing Information and Data Set
Evaluation Center (NIDSEC), evaluates implementation of a
terminology by a vendor. This approval is similar to obtaining
the good seal of approval from Good Housekeeping or the
United Laboratories (UL) seal on products. The approval
signifies that the documentation in the standardized language
supports the documentation of nursing practice and conforms to
standards pertaining to computerized information systems. The
language is evaluated against standards that follow the Joint
Commission's model for evaluation. The language must support
documentation on a nursing information system (NIS) or
computerized patient record system (CPR). The criteria used by
the ANA to evaluate how the standardized language(s) are

implemented, include how the terms can be connected, how
easily the records can be stored and retrieved, and how well the
security and confidentiality of the records are maintained. The
recognition is valid for three years. A new application must be
submitted at the end of the three years for further recognition.
Some, but not all of the standardized languages are copyrighted.
(The previous paragraphs were updated 2/23/09. See previous
content.)
Vendors may also have their software packages evaluated by
NIDSEC. The evaluation is a type of quality control on the
vendor. An application packet must be purchased, priced at
$100, then the fee for the evaluation is $20,000 (American
Nurses Association, 2004). The only product currently
recognized is Cerner Corporation CareNet
Solution
s (American Nurses Association, 2004). The recognition
signifies that the software in the Cerner system has met the
standards set by NIDSEC. The direct care/bedside nurse must
understand the importance of the inclusion of standardized
nursing languages in the software sold by vendors and demand
the use of a standardized nursing language in these systems.
Benefits of Standardized Languages
The use of standardized nursing languages has many advantages
for the direct care/bedside nurse. These include: better

assessment of nursing competency. These advantages for the
bedside/direct care nurse are discussed below.
Better Communication among Nurses and Other Health Care
Providers
Improved communication with other nurses, health care
professionals, and administrators of the institutions in which
nurses work is a key benefit of using a standardized nursing
language. Physicians realized the value of a standardized
language in 1893 (The International Statistical Classification of
Diseases and Related Health Problems, 2003) with the
beginning of the standardization of medical diagnosis that has
become the International Classification of Diseases (ICD-10)
(Clark & Phil, 1999). A more recent language, the Diagnostic
and Statistical Manual of Mental Disorders (DSM-IV), provides
a common language for mental disorders. When an obstetrician
lists "failure to progress" on a patient's chart or a psychiatrist
names the diagnosis "paranoid schizophrenia, chronic," other
physicians, health care practitioners, and third-party payers
understand the patient's diagnosis.
Improved communication with other nurses, health care

professionals, and administrators of the institutions in which
nurses work is a key benefit of using a standardized nursing
language. ICD-10 and DSM-IV are coded by a system of
numbers for input into computers. The IDC-10 is a coding
system used mainly for billing purposes by organizations and
practitioners while the DSM-IV is a categorization system for
psychiatric diagnoses. The DSM-IV categories have an ICD-10
counterpart code that is used for billing purposes.
Nurses lacked a standardized language to communicate their
practice until the North American Nursing Diagnosis (NANDA),
was introduced in 1973. Since then several more languages have
been developed. The Nursing Minimum Data Set (NMDS) was
developed in 1988 (Prophet & Delaney, 1998) followed by the
Nursing Management Minimum Data Set (NMMDS) in 1989
(Huber, Schumacher, & Delaney, 1997). The Clinical Care
Classification (CCC) was developed in 1991 for use in
hospitals, ambulatory care clinics, and other settings (Saba,
2003). The standardized language developed for home, public
health, and school health is the Omaha System (The Omaha
System, 2004). The Nursing Intervention Classification (NIC)
was published for the first time in 1992; it is currently in its
fourth edition (McCloskey-Dochterman & Bulachek, 2004). The
most current edition of the Nursing Outcomes Classification
system (NOC), as of this writing, is the third edition published

in 2004 (Moorhead, Johnson, & Maas, 2004). Both are used
across a number of settings.
Use of standardized nursing languages promises to enhance
communication of nursing care nationally and internationally.
This is important because it will alert nurses to helpful
interventions that may not be in current use in their areas. Two
presentations at the NANDA, NIC, NOC 2004 Conference
illustrated the use of a standardized nursing language in other
countries (Baena de Morales Lopes, Jose dos Reis, & Higa,
2004; Lee, 2004). Lee (2004) used 360 nurse experts in quality
assurance to identify five patient outcomes from the NOC
(Johnson, Maas, & Moorhead, 2000) criteria to evaluate the
quality of nursing care in Korean hospitals. The five NOC
outcomes selected by the nurse experts as standards to evaluate
the quality of care were vital signs status; knowledge: infection
control; pain control behavior; safety behavior: fall prevention;
and infection status.
Baena de Morales Lopes et al. (2004) identified the major
nursing diagnoses and interventions in a protocol used for
victims of sexual violence in Sao Paulo, Brazil. The major
nursing diagnoses identified were: rape-trauma syndrome, acute
pain, fear/anxiety, risk for infection, impaired skin integrity,
and altered comfort. Through the use of these nursing

diagnoses, specific interventions were identified, such as
administration of appropriate medications with explanations of
expected side effects, emotional support, helping the client to a
shower and clean clothes, and referrals to needed agencies. The
authors used these diagnoses in providing care for 748 clients
and concluded that use of the nursing diagnoses contributed to
the establishment of bonds with their clients. These are just two
examples illustrating how a standardized language has been
used across nursing specialties and around the world.
Increased Visibility of Nursing Interventions
Nurses need to express exactly what it is that they do for
patients. Nurses need to express exactly what it is that they do
for patients. Pearson (2003) has stated, "Nursing has a long
tradition of over-reliance on handing down both information and
knowledge by word-of-mouth" (p. 271). Because nurses use
informal notes to verbally report to one another, rather than
patient records and care plans, their work remains invisible.
Pearson states that at the present time the preponderance of care
documentation focuses on protection from litigation rather than
patient care provided. He anticipates that use of computerized
nursing documentation systems, located close to the patient,
will lead to more patient-centered and consistent
documentation. Increased sensitivity to the nursing care
activities provided by these computerized documentation

systems will help highlight the contribution of nurses to patient
outcomes, making nursing more visible.
Nursing practice, in addition to the interventions, treatments,
and procedures, includes the use of observation skills and
experience to make nursing judgments about patient care.
Because nurses use informal notes to verbally report to one
another, rather than patient records and care plans, their work
remains invisible. Interventions that should be undertaken to in
support nursing judgments and that demonstrate the depth of
nursing judgment are built into the standardized nursing
languages. For example, one activity listed under labor
induction in the NIC language is that of re-evaluating cervical
status and verifying presentation before initiating further
induction measures (McCloskey-Dochterman & Bulechek,
2004). This activity guides the nurse to assess the dilatation and
effacement of the cervix and presentation of the fetus, before
making a judgment about continuing the induction procedure.
LaDuke (2000) provides an additional example of using the NIC
to make nursing interventions visible. For example, LaDuke
noted that the intervention of emotional support, described by
McCloskey-Dochterman & Bulechek (2004) requires
"interpersonal skills, critical thinking and time" (LaDuke, p.
43). NIC identifies emotional support as a specific intervention,

provides a distinct definition for it, and lists specific activities
to provide emotional support. Identification of emotional
support as a specific intervention gives nurses a standardized
nursing language to describe the specific activities necessary
for the intervention of emotional support.
Improved Patient Care
The use of a standardized nursing language can improve patient
care. Cavendish (2001) surveyed sixty-four members of the
National Association of School Nurses to obtain their
perceptions of the most frequent complaints for abdominal pain.
They used the NIC and NOC to determine the interventions and
outcomes of children after acute abdomen had been ruled out.
Nurses identified the chief complaints of the children, the most
frequent etiology, the most frequent pain management activities
from the NIC, and the change in NOC outcomes after
intervention.
The three chief complaints were nausea, headache, and
vomiting; the character of the pain was described as
crampy/mild or moderate; and the three most identified
etiologies were psychosocial problems, viral syndromes, and
relationship to menses. The psychosocial problems included test
anxiety, separation anxiety, and interpersonal problems.
Nutrition accounted for a large number of abdominal

complaints, such as skipping meals, eating junk food, and food
intolerances. Cultural backgrounds of the children, such as the
practice of fasting during Ramadan, were identified as causes
for abdominal complaints.
The three top pain management activities from NIC were:
observe for nonverbal cues of discomfort, perform
comprehensive assessment of pain (location, characteristics,
duration, frequency, quality, severity, precipitating factors), and
reduce or eliminate factors that precipitate/increase pain
experience (e.g., fear, fatigue, and lack of knowledge)
(Cavendish, 2001). Cavendish described a decrease in
symptoms, based on the Nursing Outcomes Classification
Symptom Severity Indicators, following the intervention.
Symptom intensity decreased 6.25%, symptom persistence
decreased 4.69%, symptom frequency decreased 6.25%, and
associated discomfort decreased 41.06% (p. 272). Similar
studies are needed to provide evidence that specific nursing
interventions improve patient outcomes.
Enhanced Data Collection to Evaluate Nursing Care Outcomes
The use of a standardized language to record nursing care can
provide the consistency necessary to compare the quality of
outcomes for various nursing interventions across settings.The
use of a standardized language to record nursing care can

provide the consistency necessary to compare the quality of
outcomes for various nursing interventions across settings. As
stated earlier, more organizations are moving to electronic
documentation (ED) and electronic health records. When the
nursing care data stored in these computer systems are in a
standardized nursing language, large local, state, and national
data repositories can be constructed that will facilitate
benchmarking with other hospitals and settings that provide
nursing care. The National Quality Forum (NQF) (NQF, 2006),
is in the process of developing national standards for the
measurement and reporting of health care performance data. The
Nursing Care Measures Project is one of the 24 projects on
which the NQF is developing consensus-based, national
standards to use as mechanisms for quality improvement and
measurement initiatives to improve American health care. The
NQF has stated, "Given the importance of nursing care, the
absence of standardized nursing care performance measures is a
major void in healthcare quality assurance and work system
performance"(NQF, May 2003, p. 1).
Patient outcomes are also related to the uniqueness of the
individual, the care given by other health care professionals,
and the environment in which the care is provided. The
American Nurses Association's National Center for Nursing
Quality (NCNQ) maintains a database called the National

Database of Nursing Quality Indicators™ (NDNQI)® (American
Nurses Association, 2006a). This database collects nurse-
sensitive and unit-specific indicators from health care
organizations, compares this data with organizations of similar
size having similar units, and sends the comparison findings
back to the participating organization. This activity facilitates
longitudinal benchmarking as the database has been ongoing
since the early 1990's (National Database, 2004).
The already-mentioned NOC system outcomes are nurse-
sensitive outcomes, which means the they are sensitive to those
interventions performed primarily by nurses (Moorehead et al.,
2004). Because the NOC system measures nursing outcomes on
a numerical rating scale, it, too, facilitates the benchmarking of
nursing practices across facilities, regions, and countries. The
current edition of NOC (2004), which assesses the impact of
nursing care on the individual, the family, and the community,
contains 330 outcomes classified in seven domains and 29
classes.
A NOC outcome common to nurses who work with elderly
patients who have a swallowing impairment is aspiration
prevention (Moorehead et al., 2004). Patient behaviors
indicating this outcome include identifying risk factors,
avoiding risk factors, positioning self upright for

eating/drinking, and choosing liquids and foods of proper
consistency. Rating each indictor on a scale from one (never
demonstrated) to five (consistently demonstrated) helps track
risk for aspiration in individuals at various stages of illness
during the hospitalization. It also gives an indication of a
person's compliance in following the prevention measures and
the nurse's success in patient education.
A NOC outcome that labor nurses frequently use is pain level
(Moorehead et al., 2004), related to the severity and intensity of
pain a woman experiences with contractions. The pain level can
be assessed before and after the use of coping techniques such
as breathing exercises and repositioning. Indicators for this
specific pain outcome include: reported pain, moaning and
crying, facial expressions of pain, restlessness, narrowed focus,
respiratory rate, pulse rate, blood pressure, and perspiration (p.
421) and are rated on a scale from severe ( 1) to none ( 5). The
difference between the numerical ratings for each indicator
before and after use of the coping techniques estimates the
success of the intervention in achieving the outcome of reducing
the pain level for laboring mothers.
Greater Adherence to Standards of Care
Related to the quality of nursing care is the level of adherence
to the standards of care for a given patient population. The NIC

and NOC standardized nursing language systems are based on
both the input of expert nurses and the standards of care from
various professional organizations. For example, the NIC
intervention of electronic fetal monitoring: intrapartum
(McCloskey-Dochterman & Bulechek, 2004) is supported by
publications of expert authors and researchers in the field of
fetal monitoring and by standards of care from the Association
of Women's Health, Obstetric and Neonatal Nurses (AWHONN).
The first activity listed under electronic fetal monitoring:
intrapartum is to verify maternal and fetal heart rates before
initiation of electronic fetal monitoring (p. 328), which is
understood to be one of the gold standards for electronic fetal
monitoring. There are several reasons why both heart rates need
to be identified. The nurse must be sure that it is the fetal heart
rate being monitored and not the heart rate of the mother.
Moreover, it is important to ascertain the exact position of the
fetus before positioning the fetal monitor's transducer. This
illustration exemplifies how important standards are reinforced
by the NIC activities.
Facilitated Assessment of Nursing Competency
Standardized language can also be used to assess nursing
competency. Health care facilities are required to demonstrate
the competence of staff for the Joint Commission. The nursing
interventions delineated in standardized nursing languages can

be used as a standard by which to assess nurse competency in
the performance of these interventions. A Midwestern hospital
is already doing this (Nolan, 2004). Using an example from the
NIC system, specifically intrapartal care (McCloskey-
Dochterman & Bulechek, 2004), a nurse's competency can be
established by a preceptor's watching to see whether the nurse is
performing the recommended activities, such as a vaginal
examination or the assessment of the fetus presentation. The
preceptor can also evaluate the nurse's teaching skills regarding
what the patient should expect during labor, using the activities
listed under the teaching intervention.
Implications of Standardized Language for Nursing Education,
Research, and Administration
In addition to enhancing the care provided by direct care nurses,
standardized language has implications for nursing education,
research, and administration. Nurse educators can use the
knowledge inherent in standardized nursing languages to
educate future nurses. Such a system can be used to describe the
unique roles of the nurse. Nurse educators can teach students to
use systems such as the CCC and Omaha System when in the
community health fields, or the use of the NANDA, NIC, NOC
terminology when in the acute care setting. References to the
primary resources upon which each intervention is based are
listed at the end of each individual intervention to provide

information supporting each intervention. By referring to the
references associated with these nursing standards, nurse
educators can role model the use of standardized language to
help students recognize the body of knowledge upon which the
standards are built. Tying the standardized language to
education and practice will enhance its implementation and
expand practicing nurses' knowledge of interventions,
outcomes, and languages. Armed with an appreciation of the
value of standardized language, students can champion further
development and use of the standardized nursing languages once
they enter professional practice.
The use of standardized languages can provide a launching
point for conducting research on standardized languages. The
research conducted by the two teams of educators at the
University of Iowa on the NIC and NOC are excellent examples
of the research that can be done on the standardized nursing
languages using computerized databases designed for research
(McCloskey-Dochterman & Bulechek, 2004; Moorehead et al.,
2004).
Nursing research performed with�larger sample sizes�using
databases may reveal more powerful patterns with stronger
implications for practice than can past research that depended
on small samples. Although nursing researchers have

traditionally used historic data (data describing completed
activities), computerized documentation based on a standardized
language can enable researchers and quality improvement staff
to use "real-time" data. This data is more readily accessible and
retrievable as compared to the traditional, time-consuming task
of sifting through stacks of charts for the needed information.
When the bedside nurse documents via a nursing information
system having a standardized language, the data are stored by
the hospital, usually in a data warehouse. When the aggregate
data are accessed by administrators and researchers, trends in
patient care can be uncovered (Zytkowski, 2003), best practices
of nursing care unlocked, efficiencies in nursing care
discovered, and a relevant knowledge base for nursing can be
built. Nursing research performed with these larger sample sizes
achieved by using databases may reveal more powerful patterns
with stronger implications for practice than can past research
that depended on small samples.
Kennedy (2003) states that one byproduct of accurate
documentation of patient care is an estimation of acuity level.
Patient care data entered into a computer and stored in a
database can be used to help develop and adjust nursing
schedules based on the projected patient census and acuity.
Utilizing a standardized nursing language to document care can

more precisely reflect the care given, assess acuity levels, and
predict appropriate staffing. Use of a standardized nursing
documentation system can provide data to support
reimbursement to a health care agency for the care provided by
professional nurses.
Summary
The ultimate goal should be the development of one
standardized nursing language for all nurses. Use of a
standardized language is not something that is done just because
it will be useful to others. Use of a standardized language has
far reaching ramifications that will help in the delivery of
nursing care and demonstrate the value of nursing to others. The
benefits of a standardized nursing language include: better
assessment of nursing competency.
The ultimate goal should be the development of one
standardized nursing language for all nurses. Although that goal
has not yet been attained, examples of work toward it can be
demonstrated. The International Council of Nurses (ICN) has
developed the International Classification for Nursing Practice

(ICNP) (ICN, 2006) in an attempt to establish a common
language for nursing practice. The ICNP is a combinatorial
terminology that cross-maps local terms, vocabularies, and
classifications.
The Nursing Intervention Classification (NIC) and Nursing
Outcome Classification (NOC) were developed as companion
languages. These have linkages to other nursing languages, such
as NANDA nursing diagnoses, the Omaha System, and Oasis for
home health care, among others. Both are included in
Systematized Nomenclature of Medicine's (SNOMED)
multidisciplinary record system. NIC has been translated into
nine foreign languages and NOC into seven foreign languages.
By using one standardized nursing language, nurses from all
over the world will be able to communicate with one another,
with the goal of improving care for patients globally. Nurses
will be able to convey the important work they do, making
nursing more visible.
Correction Notice: The paragraphs below appeared in this
article on the original publication date of January 31, 2008. The
information in these paragraphs has been revised in the above
article as of February 23, 2009 to clarify the difference between
CNPII and NIDSEC. (See current content.)

Current Standardized Nursing Languages and Their
Applications
The Nursing Information and Data Set Evaluation Center
(NIDSEC) of the American Nurses Association (ANA) (2004)
recognizes thirteen standardized languages that support nursing
practice, ten of which document nursing care. The ANA (2006b)
Recognized Terminologies and Data Element Sets outlines the
components of each of these languages.
The submission of a language for approval by the NIDSEC is a
voluntary process for the developers. This approval is similar to
obtaining the good seal of approval from Good Housekeeping or
the United Laboratories (UL) seal on products. The approval
signifies that the documentation in the standardized language
supports the documentation of nursing practice and conforms to
standards pertaining to computerized information systems. The
language is evaluated against standards that follow the Joint
Commission's model for evaluation. The language must support
documentation on a nursing information system (NIS) or
computerized patient record system (CPR). The criteria used by
the ANA to evaluate the standardized languages include the
terminology used, how the terms can be connected, how easily
the records can be stored and retrieved, and how well the
security and confidentiality of the records are maintained. The

recognition is valid for three years. A new application must be
submitted at the end of the three years for further recognition.
Some, but not all of the standardized languages are copyrighted.
References
Rutherford, M. A. (2008). Standardized Nursing Language:
What Does It Mean for Nursing Practice? Online Journal of
Issues in Nursing, 13(1), 1–12. https://doi-
org.ezp.waldenulibrary.org/10.3912/OJIN.Vol13No01PPT05
Technological Forecasting & Social Change 126 (2018) 3–13
Contents lists available at ScienceDirect
Technological Forecasting & Social Change
Big data analytics: Understanding its capabilities and potential
benefits
for healthcare organizations
Yichuan Wang a,⁎, LeeAnn Kung b, Terry Anthony Byrd a
a Raymond J. Harbert College of Business, Auburn University,
405 W. Magnolia Ave., Auburn, AL 36849, USA
b Rohrer College of Business, Rowan University, 201 Mullica
Hill Road, Glassboro, NJ 08028, USA

⁎ Corresponding author.
E-mail addresses: [email protected] (Y. Wang), k
[email protected] (T.A. Byrd).
http://dx.doi.org/10.1016/j.techfore.2015.12.019
0040-1625/© 2016 Elsevier Inc. All rights reserved.
a b s t r a c t
a r t i c l e i n f o
Article history:
Received 17 June 2015
Received in revised form 11 November 2015
Accepted 12 December 2015
Available online 26 February 2016
To date, health care industry has not fully grasped the potential
benefits to be gained from big data analytics.
While the constantly growing body of academic research on big
data analytics is mostly technology oriented, a
better understanding of the strategic implications of big data is
urgently needed. To address this lack, this
study examines the historical development, architectural design
and component functionalities of big data ana-
lytics. From content analysis of 26 big data implementation
cases in healthcare, we were able to identify five big

data analytics capabilities: analytical capability for patterns of
care, unstructured data analytical capability, deci-
sion support capability, predictive capability, and
traceability.We alsomapped the benefits driven by big data an-
alytics in terms of information technology (IT) infrastructure,
operational, organizational, managerial and
strategic areas. In addition, we recommend five strategies for
healthcare organizations that are considering to
adopt big data analytics technologies. Our findingswill help
healthcare organizations understand the big data an-
alytics capabilities and potential benefits and support them
seeking to formulate more effective data-driven an-
alytics strategies.
© 2016 Elsevier Inc. All rights reserved.
Keywords:
Big data analytics
Big data analytics architecture
Big data analytics capabilities
Business value of information technology (IT)
Health care
1. Introduction
Information technology (IT)-related challenges such as
inadequate

integration of healthcare systems and poor healthcare
information
management are seriously hampering efforts to transform IT
value to
business value in the U.S. healthcare sector (Bodenheimer,
2005;
Grantmakers In Health, 2012; Herrick et al., 2010; The Kaiser
Family
Foundation, 2012). The high volume digital flood of
information that
is being generated at ever-higher velocities and varieties in
healthcare
adds complexity to the equation. The consequences are
unnecessary in-
creases in medical costs and time for both patients and
healthcare ser-
vice providers. Thus, healthcare organizations are seeking
effective IT
artifacts that will enable them to consolidate organizational
resources
to deliver a high quality patient experience, improve
organizational per-
formance, andmaybe even create new,more effective data-driven
busi-
ness models (Agarwal et al., 2010; Goh et al., 2011; Ker et al.,

2014).
One promising breakthrough is the application of big data
analytics.
Big data analytics that is evolved frombusiness intelligence
anddecision
support systems enable healthcare organizations to analyze an
im-
mense volume, variety and velocity of data across a wide range
of
healthcare networks to support evidence-based decision making
and
action taking (Watson, 2014; Raghupathi and Raghupathi,
2014). Big
[email protected] (L. Kung),
data analytics encompasses the various analytical techniques
such as
descriptive analytics and mining/predictive analytics that are
ideal for
analyzing a large proportion of text-based health documents and
other unstructured clinical data (e.g., physician's written notes
and pre-
scriptions and medical imaging) (Groves et al., 2013). New
database
management systems such as MongoDB, MarkLogic and Apache

Cassandra for data integration and retrieval, allow data being
trans-
ferred between traditional and new operating systems. To store
the
huge volume and various formats of data, there are Apache
HBase and
NoSQL systems. These big data analytics tools with
sophisticated func-
tionalities facilitate clinical information integration and provide
fresh
business insights to help healthcare organizations meet patients'
needs and futuremarket trends, and thus improve quality of care
and fi-
nancial performance (Jiang et al., 2014; Murdoch and Detsky,
2013;
Wang et al., 2015).
A technological understanding of big data analytics has been
studied
well by computer scientists (see a systemic review of big data
research
from Wamba et al., 2015). Yet, healthcare organizations
continue to
struggle to gain the benefits from their investments on big data
analyt-

ics and some of them are skeptical about its power, although
they invest
in big data analytics in hope for healthcare transformation
(Murdoch
and Detsky, 2013; Shah and Pathak, 2014). Evidence shows that
only
42% of healthcare organizations surveyed are adopting rigorous
analyt-
ics approaches to support their decision-making process; only
16% of
them have substantial experience using analytics across a broad
range
of functions (Cortada et al., 2012). This implies that healthcare
http://crossmark.crossref.org/dialog/?doi=10.1016/j.techfore.20
15.12.019&domain=pdf
mailto:[email protected]
http://www.sciencedirect.com/science/journal/00401625
4 Y. Wang et al. / Technological Forecasting & Social Change
126 (2018) 3–13
practitioners still vaguely understand how big data analytics can

create
value for their organizations (Sharma et al., 2014). As such,
there is an
urgent need to understand the managerial, economic, and
strategic im-
pact of big data analytics and explore its potential benefits
driven by big
data analytics. This will enable healthcare practitioners to fully
seize the
power of big data analytics.
To this end, twomain goals of this study are:first, to identify big
data
analytics capabilities; and second, to explore the potential
benefits it
may bring. By doing so, we hope to give healthcare organization
a
more current comprehensive understanding of big data analytics
and
how it helps to transform organizations. In this paper, we begin
by pro-
viding the historical context and developing big data analytics
architec-
ture in healthcare, and then move on to conceptualizing big data
analytics capabilities and potential benefits in healthcare. We

conduct-
ed a content analysis of 26 big data implementation cases in
health
care which lead to the identification of five major big data
analytics ca-
pabilities and potential benefits derived from its application. In
conclud-
ing sections, we present several strategies for being successful
with big
data analytics in healthcare settings as well as the limitations of
this
study, and direction of future research.
2. Background
2.1. Big data analytics: past and present
The history of big data analytics is inextricably linked with that
of
data science. The term “big data” was used for the first time in
1997
byMichael Cox andDavid Ellsworth in a paper presented at an
IEEE con-
ference to explain the visualization of data and the challenges it
posed

for computer systems (Cox and Ellsworth, 1997). By the end of
the
1990s, the rapid IT innovations and technology improvements
had en-
abled generation of large amount of data but little useable
information
in comparison. Concepts of business intelligence (BI) created to
empha-
size the importance of collection, integration, analysis, and
interpreta-
tion of business information and how this set of process can
help
businesses makemore appropriate decisions and obtain a better
under-
standing of market behaviors and trends.
The period of 2001 to 2008was the evolutionary stage for big
data
development. Big data was first defined in terms of its volume,
veloc-
ity, and variety (3Vs), after which it became possible to develop
more sophisticated software to fulfill the needs of handling
informa-
tion explosion accordingly. Software and application
developments

like Extensible Markup Language (XML) Web services,
database
management systems, and Hadoop added analytics modules and
functions to core modules that focused on enhancing usability
for
end users, and enabled users to process huge amounts of data
across
and within organizations collaboratively and in real-time. At the
same time, healthcare organizations were starting to digitize
their
medical records and aggregate clinical data in huge electronic
data-
bases. This development made the health data storable, usable,
searchable, and actionable, and helped healthcare providers
practice
more effective medicine.
At the beginning of 2009, big data analytics entered the
revolution-
ary stage (Bryant et al., 2008). Not only had big-data computing
become
a breakthrough innovation for business intelligence, but also re-
searchers were predicting that data management and its
techniques
were about to shift from structured data into unstructured data,

and
from a static terminal environment to a ubiquitous cloud-based
envi-
ronment. Big data analytics computing pioneer industries such
as
banks and e-commercewere beginning to have an impact on
improving
business processes and workforce effectiveness, reducing
enterprise
costs and attracting new customers. In regards to healthcare
industry,
as of 2011, stored health care data had reached 150 exabytes (1
EB =
1018 bytes) worldwide, mainly in the form of electronic health
records
(Institute for Health Technology Transformation, 2013).
However,
most of the potential value creation is still in its infancy,
because
predictivemodeling and simulation techniques for analyzing
healthcare
data as a whole have not yet been adequately developed.
More recent trend of big data analytics technology has been
towards

the use of cloud in conjunction with data. Enterprises have
increasingly
adopted a “big data in the cloud” solution such as software-as-
a-service
(SaaS) that offers an attractive alternative with lower cost.
According to
the Gartner's, 2013 IT trend prediction, taking advantage of
cloud com-
puting services for big data analytics systems that support a
real-time
analytic capability and cost-effective storage will become a
preferred
IT solution by 2016. The main trend in the healthcare industry
is a
shift in data type from structure-based to semi-structured based
(e.g., home monitoring, telehealth, sensor-based wireless
devices) and
unstructured data (e.g., transcribed notes, images, and video).
The in-
creasing use of sensors and remote monitors is a key factor
supporting
the rise of home healthcare services, meaning that the amount of
data
being generated from sensors will continue to grow
significantly. This

will in turn improve the quality of healthcare services
throughmore ac-
curate analysis and prediction.
2.2. Big data analytics architecture
To reach our goals of this studywhich are to describe the big
data an-
alytics capability profile and its potential benefits, it is
necessary to un-
derstand its architecture, components and functionalities. The
first
action taken is to explore best practice of big data analytics
architecture
in healthcare. We invited four IT experts (two practitioners and
two ac-
ademics) to participate in a five-round evaluation processwhich
includ-
ed brainstorming and discussions. The resulted big data
analytics
architecture is rooted in the concept of data life cycle
framework that
starts with data capture, proceeds via data transformation, and
culmi-
nates with data consumption. Fig. 1 depicts the proposed best

practice
big data analytics architecture that is loosely comprised of
fivemajor ar-
chitectural layers: (1) data, (2) data aggregation, (3) analytics,
(4) infor-
mation exploration, and (5) data governance. These logical
layers make
up the big data analytics components that perform specific
functions,
and will therefore enable healthcare managers to understand
how to
transform the healthcare data from various sources into
meaningful
clinical information through big data implementations.
2.2.1. Data layer
This layer includes all the data sources necessary to provide the
insights required to support daily operations and solve business
problems. Data is divided into structured data such as
traditional
electronic healthcare records (EHRs), semi-structured data such
as
the logs of health monitoring devices, and unstructured data
such

as clinical images. These clinical data are collected from
various in-
ternal or external locations, and will be stored immediately into
ap-
propriate databases, depending on the content format.
2.2.2. Data aggregation layer
This layer is responsible for handling data from the various data
sources. In this layer, data will be intelligently digested by
performing
three steps: data acquisition, transformation, and storage. The
primary
goal of data acquisition is to read data provided from various
communi-
cation channels, frequencies, sizes, and formats. This step is
often a
major obstacle in the early stages of implementing big data
analytics,
because these incoming data characteristics might vary
considerably.
Here, the cost may well exceed the budget available for
establishing
new data warehouses, and extending their capacity to avoid
workload

bottlenecks. During the transformation step, the transformation
engine
must be capable of moving, cleaning, splitting, translating,
merging,
sorting, and validating data. For example, structured data such
as that
typically contained in an eclectic medical record might be
extracted
from healthcare information systems and subsequently
converted into
a specific standard data format, sorted by the specified criterion
(e.g., patient name, location, or medical history), and then the
record
Fig. 1. Big data analytics architecture in health care.
5Y. Wang et al. / Technological Forecasting & Social Change
126 (2018) 3–13
validated against data quality rules. Finally, the data are loaded
into the
target databases such as Hadoop distributed file systems
(HDFS) or in a
Hadoop cloud for further processing and analysis. The data

storage prin-
ciples are based on compliance regulations, data governance
policies
and access controls. Data storage methods can be implemented
and
completed in batch processes or in real time.
2.2.3. Analytics layer
This layer is responsible for processing all kinds of data and
performing appropriate analyses. In this layer, data analysis can
be di-
vided into threemajor components: HadoopMap/Reduce, stream
com-
puting, and in-database analytics, depending on the type of data
and the
purpose of the analysis. Mapreduce is the most commonly used
pro-
grammingmodel in big data analytics which provides the ability
to pro-
cess large volumes of data in batch form cost-effectively, as
well as
allowing the analysis of both unstructured and structured data in
amas-
sively parallel processing (MPP) environment. Stream
computing can

support high performance stream data processing in near real
time or
real time. With a real time analysis, users can track data in
motion, re-
spond to unexpected events as they happen and quickly
determine
next-best actions. For example, in the case of healthcare fraud
detection,
stream computing is an important analytical tool that assists in
predicting the likelihood of illegal transactions or deliberate
misuse of
customer accounts. Transactions and accounts will be analyzed
in real
time and alarms generated immediately to prevent myriad frauds
across healthcare sectors. In-database analytics refers to a data
mining
approach built on an analytic platform that allows data to be
processed
within the datawarehouse. This component provides high-speed
paral-
lel processing, scalability, and optimization features geared
toward big
data analytics, and offers a secure environment for confidential
enter-
prise information. However, the results provided from in-

database ana-
lytics are neither current nor real time and it is therefore likely
to
generate reports with a static prediction. Typically, this analytic
compo-
nent in healthcare organizations is useful for supporting
preventative
healthcare practice and improving pharmaceutical management.
The
analytics layer also provides exceptional support for evidence
based
medical practices by analyzing EHRs, patterns of care, care
experience,
and individual patients' habits and medical histories.
2.2.4. Information exploration layer
This layer generates outputs such as various visualization
reports,
real-time informationmonitoring, andmeaningful business
insights de-
rived from the analytics layer to users in the organization.
Similar to tra-
ditional business intelligence platforms, reporting is a critical
big data

analytics feature that allows data to be visualized in a useful
way to sup-
port users' daily operations and help managers to make faster,
better
decisions. However, the most important output for health care
may
well be its real-timemonitoring of information such as alerts and
proac-
tive notifications, real time data navigation, and operational key
perfor-
mance indicators (KPIs). This information is analyzed from
sources such
as smart phones and personal medical devices and can be sent to
inter-
ested users or made available in the form of dashboards in real
time for
monitoring patients' health and preventing accidental medical
events.
2.2.5. Data governance layer
This layer is comprised of master data management (MDM),
data
life-cycle management, and data security and privacy
management.

This layer emphasizes the “how-to” as in how to harness data in
the or-
ganization. The first component of data governance, master data
man-
agement, is regarded as the processes, governance, policies,
standards,
and tools for managing data. Data is properly standardized,
removed,
and incorporated in order to create the immediacy,
completeness, accu-
racy, and availability of master data for supporting data analysis
and de-
cision making. The second component, data life-cycle
management, is
the process of managing business information throughout its
lifecycle,
from archiving data, through maintaining data warehouse,
testing and
delivering different application systems, to deleting and
disposing of
data. By managing data effectively over its lifetime, firms are
better
equipped to provide competitive offerings to meet market needs
and
support business goals with lower timeline overruns and cost.

The
third component, data security and privacy management, is the
plat-
form for providing enterprise-level data activities in terms of
discovery,
configuration assessment, monitoring, auditing, and protection
(IBM,
126 (2018) 3–13
2012). Due to the nature of complexity in data management,
organiza-
tions have to face ethical, legal, and regulatory challengeswith
data gov-
ernance (Phillips-Wren et al., 2015). Particularly in healthcare
industry,
it is essential to implement rigorous data rules and control
mechanisms
for highly sensitive clinical data to prevent security breaches
and pro-
tect patient privacy. By adopting suitable policies, standards,
and com-
pliance requirements to restrict users' permissions will ensure

the
new system satisfies healthcare regulations and creates a safe
environ-
ment for the proper use of patient information.
2.3. Big data analytics capability
Several definitions for big data analytics capability have been
de-
veloped in the literature (see Table 1). In general, big data
analytics
capability refers to the ability to manage a huge volume of
disparate
data to allow users to implement data analysis and reaction
(Hurwitz
et al., 2013). Wixom et al. (2013) indicate that big data
analytics ca-
pability for maximizing enterprise business value should
encompass
speed to insight which is the ability to transform raw data into
usable
information and pervasive use which is the ability to use
business
analytics across the enterprise. With a lens of analytics
adoption,
LaLalle et al. (2011) categorize big data analytics capability

into
three levels: aspirational, experienced, and transformed. The
former
two levels of analytics capabilities focus on using business
analytics
technologies to achieve cost reduction and operation
optimization.
The last level of capability is aimed to drive customer
profitability
and making targeted investments in niche analytics.
Moreover, with a view of adoption benefit, Simon (2013)
defines
big data analytics capability as the ability to gather enormous
variety
of data - structured, unstructured and semi-structured data -
from
current and former customers to gain useful knowledge to
support bet-
ter decision-making, to predict customer behavior via predictive
analyt-
ics software, and to retain valuable customers by providing real-
time
offers. Based on the resource-based view, Cosic et al. (2012)
define big

data analytics capability as “the ability to utilize resources to
perform
a business analytics task, based on the interaction between IT
assets
and other firm resources (p. 4)”.
In this study, we define big data analytics capability through an
in-
formation lifecycle management (ILM) view. Storage
Networking
Industry Association (2009) describes ILM as “the policies,
processes,
practices, services and tools used to align the business value of
informa-
tion with the most appropriate and cost-effective infrastructure
from
the time when information is created through its final
disposition
(p. 2).” Generally, data regardless of its structure in a system
has been
followed this cycle, startingwith collection, through repository
and pro-
cess, and ending up with dissemination of data. The concept of
ILM
helps us to understand all the phases of information life cycle in

busi-
ness analytics architecture (Jagadish et al., 2014). Therefore,
with a
Table 1
The definition of big data analytics capability from prior
research.
Sources Viewpoints Definitions
Cosic et al. (2012) Resource based view • The ability to ut
Hurwitz et al. (2013) 3V of big data • The ability to m
reaction
LaLalle et al. (2011) Analytics adoption • Achieve cost red
• Drive customer
Simon (2013) Adoption benefit • The ability to ga
customer servic
Trkman et al. (2010) Business process • Analytics in plan
• Analytics in sou
• Analytics in mak
• Analytics in deli

Wixom et al. (2013) Business value • Speed to insight
• Pervasive use
view of ILM, we define big data analytics capability in the
context of
health care as
the ability to acquire, store, process and analyze large amount
of health
data in various forms, and deliver meaningful information to
users that
allows them to discover business values and insights in a timely
fashion.
2.4. Conceptualizing the potential benefit of big data analytics
To capture the potential benefits from big data analytics, a
multidi-
mensional benefit framework (see Table 2), including IT
infrastructure
benefits, operational benefits, organizational benefits,
managerial bene-
fits, and strategic benefits (Shang and Seddon, 2002) was used
to classi-
fy the statements related to the benefits from the collected 26
big data

cases in health care.We choose Shang & Seddon's framework to
classify
the potential benefits of big data analytics for three reasons.
First, our
exploratory work is to provide a specific set of benefit sub-
dimensions
in the big analytics context. This framework will help us to
identify
the benefits of big data analytics into proper categories. Second,
this
framework is designed for managers to assess the benefits of
their com-
panies' enterprise systems. It has been refined by many studies
related
to ERP systems and specific information system (IS)
architectures
(Esteves, 2009; Gefen and Ragowsky, 2005; Mueller et al.,
2010). In
this regard, this framework is suitable as a more generic and
systemic
model for categorizing the benefits of big data analytics system.
Third,
this framework also provides a clear guide for assessing and
classifying
benefits fromenterprise systems. This guide also suggests

theways how
to validate the IS benefit framework through implementation
cases,
which is helpful for our study.
3. Research methods
To reach our goals of this study, we used a quantitative
approach,
more specifically, a multiple cases content analysis to gain
understand-
ing and categorization of big data analytics capabilities and
potential
benefits derived from its application. The cases collection,
approach
and procedures for analyzing the cases are described in the
following
subsections.
3.1. Cases collection
Our cases were drawn from current and past big data projects
mate-
rial from multiple sources such as practical journals, print
publications,

case collections, and reports from companies, vendors,
consultants or
analysts. The absence of academic discussion in our case
collection is
due to the incipient nature of such in the field of healthcare.
The follow-
ing case selection criteria were applied: (1) the case presents an
actual
implementation of big data platforms or initiatives, and (2) it
clearly
ilize resources to perform a business analytics task
anage a huge volume of disparate data to allow users to
implement data analysis and
uction and operation optimization
profitability and making targeted investments in niche analytics
ther enormous variety of data from customers to gain business
insights to optimize
e
rce
e
ver

Table 2
The overview of enterprise systems' multidimensional benefit
framework.
Benefit dimension Description Sub-dimensions
IT infrastructure benefits Sharable and reusable IT resources
that provide a foundation for present and future
business applications
• Building business flexibility for current and future
changes
• IT cost reduction
• Increased IT infrastructure capability
Operational benefits The benefits obtained from the
improvement of operational activities • Cost reduction
• Cycle time reduction
• Productivity improvement
• Quality improvement
• Customer service improvement
Managerial benefits The benefits obtained from business

management activities which involve allocation
and control of the firms' resources, monitoring of operations
and supporting of
business strategic decisions
• Better resource management
• Improved decision making and planning
• Performance improvement
Strategic benefits The benefits obtained from strategic activities
which involve long-range planning
regarding high-level decisions
• Support for business growth
• Support for business alliance
• Building for business innovations
• Building cost leadership
• Generating product differentiation
• Building external linkages
Organizational benefits The benefits arise when the use of an
enterprise system benefits an organization in
terms of focus, cohesion, learning, and execution of its chosen
strategies.

• Changing work patterns
• Facilitating organizational learning
• Empowerment
• Building common vision
126 (2018) 3–13
describes the software they introduce and benefits obtaining
from the
implementation. We excluded reports from one particular
vendor due
to their connection to one of our experts whowere invited for
the eval-
uation. We were able to collect 26 big data cases specifically
related to
the healthcare industries. Of these cases, 14 (53.8%) were
collected
from the materials released by vendors or companies, 2 cases
(7.7%)
from journal databases, and 10 cases (38.4%) fromprint
publications, in-
cluding healthcare institute reports and case collections.
Categorizing
by region, 17 cases were collected from Northern America, 7
cases

from Europe, and others from Asia-Pacific region. The cases we
used
are listed in Appendix A.
3.2. Research approach and process
Weapplied content analysis to gain insights from the cases
collected.
Content analysis is a method for extracting various themes and
topics
from text, and it can be understood as, “an empirically grounded
meth-
od, exploratory in process, and predictive or inferential in
intent.” Spe-
cifically, this study followed inductive content analysis,
because the
knowledge about big data implementation in health care is
fragmented
(Raghupathi and Raghupathi, 2014). A three-phase research
process for
inductive content analysis (i.e., preparation, organizing, and
reporting)
suggested by Elo and Kyngäs (2008) was performed in order to
ensure
a better understanding of big data analytics capabilities and

benefits in
the healthcare context.
The preparation phase starts with selecting the “themes”
(informa-
tive and persuasive nature of case material), which can be
sentences,
paragraphs, or a portion of a page (Elo and Kyngäs, 2008). For
this
study, themes from casematerials were captured by a senior
consultant
who has over 15 years working experience with a multinational
tech-
nology and consulting corporation headquartered in the United
States,
and currently is involved in several big data analytics projects.
The
senior consultant manually highlighted the textual contents that
completely describe how a big data analytics solution and its
function-
alities create the big-data-enabled IT capabilities and potential
benefits
while reading through all 26 big data cases for a couple of
times. Subse-
quently, a total of 136 statements directly related to the IT

capabilities
and 179 statements related to the potential benefits were
obtained
and recorded in a Microsoft Excel spreadsheet.
The second phase is to organize the qualitative data emerged
from phase one through open coding, creating categories and
abstraction (Elo and Kyngäs, 2008). In the process of open
coding,
the 136 statements were analyzed by one of the authors, and
then
grouped into preliminary conceptual themes based on their
similar-
ities. The purpose is to reduce the number of categories by
collapsing
those that are similar into broader higher order generic
categories
(Burnard, 1991; Dey, 1993; Downe-Wamboldt, 1992). In order
to in-
crease the interrater reliability, the second author went through
the
same process independently. The two coders agreed on 84% of
the
categorization. Most discrepancies occurred between the two
coders

are on the categories of analytical capability. Disagreements
were re-
solved after discussions and reassessments of the case to
eventually
arrive at a consensus. After consolidating the coding results, the
two
coders named each generic category of big data analytics
capabilities
using content-characteristic words.
4. Results
4.1. Capability profile of big data analytics in healthcare
Overall, the five generic categories of big data analytics
capabilities
we identified from 136 statements in our review of the cases are
analyt-
ical capability for patterns of care (coded as part of 43
statements), un-
structured data analytical capability (32), decision support
capability
(23), predictive capability (21), and traceability (17). These are
de-
scribed in turn below.

4.1.1. Analytical capability for patterns of care
Analytical capability refers to the analytical techniques
typically
used in a big data analytics system to process datawith an
immense vol-
ume (from terabytes to exabytes), variety (from text to graph)
and ve-
locity (from batch to streaming) via unique data storage,
management,
analysis, and visualization technologies (Chen et al., 2012;
Simon,
2013). Analytical capabilities in healthcare can be used to
identify pat-
terns of care and discover associations frommassive healthcare
records,
thus providing a broader view for evidence-based clinical
practice.
Healthcare analytical systems provide solutions that fill a
growing
need and allow healthcare organizations to parallel process
large data
volumes, manipulate real-time, or near real time data, and
capture all

patients' visual data or medical records. In doing so, this
analysis can
identify previously unnoticed patterns in patients related to
hospital
readmissions and support a better balance between capacity and
cost.
126 (2018) 3–13
Interestingly, analyzing patient preference patterns also helps
hospitals
to recognize the utility of participating in future clinical trials
and iden-
tify new potential markets.
4.1.2. Unstructured data analytical capability
An analytical process in a big data analytics system starts by
acquir-
ing data fromboth inside andoutside the healthcare sectors,
storing it in
distributed database systems, filtering it according to specific
discovery
criteria, and then analyzing it to integrate meaningful outcomes

for the
data warehouse, as shown in Fig. 2. After unstructured data has
been
gathered across multiple healthcare units, it is stored in a
Hadoop dis-
tributed file system andNoSQL database thatmaintain it until it
is called
up in response to users' requests. NoSQL databases support the
storage
of both unstructured and semi-structured data frommultiple
sources in
multiple formats in real time. The core of the analytic process is
the
MapReduce algorithms implemented by Apache Hadoop.
MapReduce
is a data analysis process that captures data from the database
and pro-
cesses it by executing “Map” and “Reduce” procedures, which
break
down large job objective into a set of discrete tasks, iteratively
on com-
puting nodes. After the data has been analyzed, the resultswill
be stored
in a data warehouse and made visually accessible for users to
facilitate

decision-making on appropriate actions.
The main difference in analytical capability between big data
an-
alytics systems and traditional data management systems is that
the
former has a unique ability to analyze semi-structured or
unstruc-
tured data. Unstructured and semi-structured data in healthcare
refer to information that can neither be stored in a traditional
rela-
tional database nor fit into predefined data models. Some
examples
are XML-based EHRs, clinical images, medical transcripts, and
lab
results. Most importantly, the ability to analyze unstructured
data
plays a pivotal role in the success of big data analytics in
healthcare
settings since 80% of health data is unstructured. According to a
2011 investigation by the TDWI research (Russom, 2011), the
ben-
efits of analyzing unstructured data capability are illustrated by
the successful implementation of targeted marketing, providing
revenue-generating insights and building customer

segmentation.
One of our cases, Leeds Teaching Hospitals in the UK analyze
ap-
proximately one million unstructured case files per month, and
have identified 30 distinct scenarios where there is room for im-
provement in either costs or operating procedures by taking
advan-
tage of natural language processing (NLP). This enables Leeds
to
improve efficiency and control costs through identifying costly
healthcare services such as unnecessary extra diagnostic tests
and
treatments.
Fig. 2. The process of analyzing unstructu
4.1.3. Decision support capability
Decision support capability emphasizes the ability to produce
re-
ports about daily healthcare services to aid managers' decisions
and
actions. In general, this capability yields sharable information
and
knowledge such as historical reporting, executive summaries,
drill-
down queries, statistical analyses, and time series comparisons.

Such information can be utilized to provide a comprehensive
view
to support the implementation of evidence-based medicine, to
de-
tect advanced warnings for disease surveillance, and to develop
per-
sonalized patient care. Some information is deployed in real
time
(e.g., medical devices' dashboard metrics) while other
information
(e.g., daily reports) will be presented in summary form.
The reports generated by the big data analytics systems are
distinct
from transitional IT systems, showing that it is often helpful to
assess
past and current operation environment across all organizational
levels.
The reports are createdwith a systemic and comprehensive
perspective
and the results evaluated in the proper context to enable
managers to
recognize feasible opportunities for improvement, particularly
regard-
ing long-term strategic decisions. From our case analysis, we

found
that Premier Healthcare Alliance collects data from different
depart-
mental systems and sends it to a central data warehouse. After
near-
real-time data processing, the reports generated are then used to
help
users recognize emerging healthcare issues such as patient
safety and
appropriate medication use.
4.1.4. Predictive capability
Predictive capability is the ability to build and assess a model
aimed
at generating accurate predictions of new observations, where
new can
be interpreted temporally and or cross-sectionally (Shmueli and
Koppius, 2011).Wessler (2013) defines predictive capability as
the pro-
cess of using a set of sophisticated statistical tools to develop
models
and estimations of what the environment will do in the future.
By defi-
nition, predictive capability emphasizes the prediction of future

trends
and exploration of new insights through extraction of
information
from large data sets. To create predictive capability,
organizations
have to rely on a predictive analytics platform that incorporate
data
warehouses, predictive analytics algorithms (e.g., regression
analysis,
machine learning, and neural networks), and reporting
dashboards
that provide optimal decisions to users. This platformmakes it
possible
to cross reference current and historical data to generate
context-aware
recommendations that enable managers to make predictions
about fu-
ture events and trends.
In healthcare, predictive analytics has been widely utilized to
reduce
the degree of uncertainty such as mitigating preventable
readmissions,
enablingmanagers tomake better decisions faster and hence
supporting

red data in health care organizations.
126 (2018) 3–13
preventive care (Bardhan et al., 2014; Simon, 2013). From our
case anal-
ysis, we found that Texas Health Harris Methodist Hospital
Alliance ana-
lyzes data from medical sensors to predict patients' movements
and
monitor patients' actions throughout their hospital stay. In doing
so,
Texas Health Harris Methodist Hospital Alliance is able to
leverage re-
ports, alerting, key performance indicators (KPIs), and
interactive visual-
izations created by predictive analytics to provide needed
services more
efficiently, optimize existing operations, and improve the
prevention of
medical risk.
Moreover, predictive analytics allows healthcare organizations

to
assess their current service situations to help them disentangle
the
complex structure of clinical costs, identify best clinical
practices, and
gain a broad understanding of future healthcare trends based on
an
in-depth knowledge of patients' lifestyles, habits, disease
management
and surveillance (Groves et al., 2013). For instance, I + Plus, an
advanced analytical solution with three-level analysis (i.e.,
claims,
aggregated, and admission) used in an Australian healthcare
organiza-
tion, provides claim-based intelligence to facilitate customers
claim
governance, balance cost and quality, and evaluate payment
models
(Srinivasan and Arunasalam, 2013). Specifically, through these
predic-
tive analytical patterns managers can review a summary of cost
and
profit related to each healthcare service, identify any claim
anomalies
based on comparisons between current and historical indicators,

and
thus make proactive (not reactive) decisions by utilizing
productive
models.
4.1.5. Traceability
Traceability is the ability to track output data from all the
system's IT
components throughout the organization's service units.
Healthcare-
related data such as activity and cost data, clinical data,
pharmaceutical
R&D data, patient behavior and sentiment data are commonly
collected
in real time or near real time from payers, healthcare services,
pharma-
ceutical companies, consumers and stakeholders outside
healthcare
(Groves et al., 2013). Traditional methods for harnessing these
data
are insufficient when faced with the volumes experienced in this
con-
text, which results in unnecessary redundancy in data
transformation

and movement, and a high rate of inconsistent data. Using big
data an-
alytics algorithms, on the other hand, enables authorized users
to gain
access to large national or local data pools and capture patient
records
simultaneously from different healthcare systems or devices.
This not
Table 3
Breaking down the potential benefits driven by big data
analytics in health care.
Potential benefits of big data analytics Elements
IT infrastructure benefits Reduce system redundancy
Avoid unnecessary IT costs
Transfer data quickly among healthcare IT syst
Better use of healthcare systems
Process standardization among various healthc
Reduce IT maintenance costs regarding data st
Operational benefits Improve the quality and accuracy of
clinical de
Process a large number of health records in sec
Reduce the time of patient travel

Immediate access to clinical data to analyze
Shorten the time of diagnostic test
Reductions in surgery-related hospitalizations
Explore inconceivable new research avenues
Organizational benefits Detect interoperability problems much
more q
Improve cross-functional communication and c
and IT staffs
Enable to share data with other institutions an
Managerial benefits Gain insights quickly about changing
healthcar
Provide members of the board and heads of de
clinical setting
Optimization of business growth-related decisi
Strategic benefits Provide a big picture view of treatment
deliver
Create high competitive healthcare services
Total
only reduces conflicts between different healthcare sectors, but
also de-
creases the difficulties in linking the data to healthcare

workflow for
process optimization.
The primary goal of traceability is to make data consistent,
visible
and easily accessible for analysis. Traceability in healthcare
facilitates
monitoring the relation between patients' needs and possible
solutions
through tracking all the datasets provided by the various
healthcare ser-
vices or devices. For example, the use of remote patient
monitoring and
sensing technologies has become more widespread for
personalized
care and home care in U.S. hospitals. Big data analytics, with
its trace-
ability, can track information that is created by the devices in
real
time, such as the use of Telehealth Response Watch in home
care ser-
vices. This makes it possible to gather location, event and
physiological
information, including time stamps, from each patient wearing
the de-

vice. This information is immediately deposited into appropriate
data-
bases (e.g., NoSQL and the Hadoop distributed file system), for
review
by medical staff when needed with excellent suitability and
scalability.
Similarly, incorporating information from radio frequency
identification
devices (RFID) into big data analytics systems enables hospitals
to take
prompt action to improve medical supply utilization rates and
reduce
delays in patient flow. From our case analysis, we found that
Brigham
and Women's Hospital (BWH) provides a typical example of the
use
of in-depth traceability in large longitudinal healthcare
databases to
identify drug risk. By integrating big-data algorithms into the
legacy IT
systems,medical staff can automaticallymonitor drug safety by
tracking
warning signals triggered by alarm systems.
In the next subsection, we will describe the results of our

second re-
search objective, which are the benefits healthcare
organizations could
drive from big data analytics.
4.2. Potential benefits of big data analytics
Our results from content analysis reveal that the big data
analytics
derived benefits can be classified into five categories: IT
infrastructure
benefits, operational benefits, organizational benefits,
managerial bene-
fits, and strategic benefits, as summarized in Table 3. The
twomost com-
pelling benefits of big data analytics are IT infrastructure
(coded as part
of 79 statements) and Operational benefits (73). The results also
show
that reduce system redundancy (19), avoid unnecessary IT costs
(17),
and transfer data quickly among healthcare IT systems (17) are
the
Frequency

19 79
17
ems 17
13
are IT systems 9
orage 4
cisions 21 73
onds 16
15
8
8
3
2
uickly than traditional manual methods 8 13
ollaboration among administrative staffs, researchers, clinicians
3
d add new services, content sources and research partners 2
e trends in the market 5 9
partment with sound decision-support information on the daily 2

ons 2
y for meeting future need 3 5
2
179
126 (2018) 3–13
elements most mentioned in the category of IT infrastructure
benefit;
improve the quality and accuracy of clinical decisions (21),
process a
large number of health records in seconds (16), and reduce the
time of pa-
tient travel (15) are the elements with high frequency in the
category of
operational benefits. This implies that big data analytics has a
twofold
potential as it implements in an organization. It not only
improves IT ef-
fectiveness and efficiency, but also supports the optimization of
clinical
operations. In addition, our results also indicate that big data

analytics is
still at an early stage of development in healthcare due to the
limited
benefits of big data analytics at the organizational, managerial,
and stra-
tegic levels.
5. The strategies for success with big data analytics
To create a data-driven organization, practitioners have to
identify
the strategic and business value of big data analytics, rather
thanmerely
concentrating on a technological understanding of its
implementation
(Wang et al., 2014). However, evidence from a survey of 400
companies
around the world shows that 77% of companies surveyed do not
have
clear strategies for using big data analytics effectively
(Wegener and
Sinha, 2013). These companies failed to describe how big data
analytics
will shape their business performance and transform their
business

models. Especially for healthcare industries, healthcare
transformation
through implementing big data analytics is still in the very early
stages.
Attention is sorely needed for research to formulate appropriate
strate-
gies that will enable healthcare organizations to move forward
to lever-
age big data analytics most efficiently and effectively. Thus, we
recommend the following five strategies for being successful
with big
data analytics in healthcare settings.
5.1. Implementing (big) data governance
Data governance is an extension of IT governance that focuses
on
leveraging enterprise-wide data resources to create business
value. In-
deed, big data analytics is a double-edged sword for IT
investment, po-
tentially incurring huge financial burden for healthcare
organizations
with poor governance. On the other hand, with appropriate data
gover-

nance, big data analytics has the potential to equip
organizations to har-
ness themountains of heterogeneous data, information, and
knowledge
from a complex array of internal applications (e.g., inpatient
and ambu-
latory EHRs) and healthcare networks' applications (e.g.,
laboratory and
pharmacy information systems). Success in data governance
requires a
series of organizational changes in business processes since all
the data
has to be well understood, trusted, accessible, and secure in a
data-
driven setting. Thus, several issues should be taken into
consideration
when developing data governance for a healthcare organization.
The first step is to formulate the missions of data governance,
with
clearly focused goals, execution procedures, governance
metrics, and
performancemeasures. In other words, a strong data governance
proto-
col should be defined to provide clear guidelines for data

availability,
criticality, authenticity, sharing, and retention that enable
healthcare or-
ganizations to harness data effectively from the time it is
acquired,
stored, analyzed, and finally used. This allows healthcare
organizations
to ensure the appropriate use of big data and build sustainable
compet-
itive advantages. Second, healthcare organizations should
review the
data they gather within all their units and realize their value.
Once the
value of these data has been defined, managers can make
decisions on
which datasets to be incorporated in their big data analytics
framework,
thereby minimizing cost and complexity. Finally, information
integra-
tion is the key to success in big data analytics implementation,
because
the challenges involved in integrating information across
systems and
data sources within the enterprise remain problematic in many
in-

stances. In particular, most healthcare organizations encounter
difficul-
ties in integrating data from legacy systems into big data
analytics
frameworks. Managers need to develop robust data governance
before
introducing big data analytics in their organization.
To create a strong data governance environment, The University
of
Kansas Hospital has established a data governance committee
for man-
aging the availability, usability, integrity, and security of the
organization's data. This committee has three different
groupswith spe-
cific responsibilities. The data governance executive group is
responsi-
ble of overseeing vision and strategy for improvement data
quality,
while the data advisory group establishes procedures and
execution
plans to address data quality issues, work priorities and the
creation of
working groups. The data governance support group is
composed of
technology, process improvement and clinical experts that

provide sup-
port to the former two groups. With respective to the best
practices of
data governance, this committee provides users a secure
commitment
from senior leaders, implements data sharing processes and
technolo-
gies that users could rely on for quality data pulled from
disparate
sources and systems, and identifies a data gap and a disruption
in
reporting key organizational metrics. With the strong data
governance
in big data analytics platforms, The University of Kansas
Hospital has
achieved more than 70 standardized enterprise data definition
ap-
provals in the first year and created a multi-year business
intelligence/
data governance roadmap.
5.2. Developing an information sharing culture
A prerequisite for implementing big data analytics successfully
is

that the target healthcare organizations foster information
sharing cul-
ture. This is critical for reducing any resistance to new
informationman-
agement systems from physicians and nurses. Without an
information
sharing culture, data collection and delivery will be limited,
with conse-
quent adverse impacts on the effectiveness of the big data
analytical and
predictive capabilities. To address this issue, healthcare
organizations
should engage data providers from the earliest stage of the big
data
transition process and develop policies that encourage and
reward
them for collecting data and meeting standards for data
delivery. This
will significantly improve the quality of data and the accuracy
of analy-
sis and prediction.
5.3. Training key personnel to use big data analytics
The key to utilize the outputs from big data analytics effectively

is
to equip managers and employees with relevant professional
com-
petencies, such as critical thinking and the skills of making an
appro-
priate interpretation of the results. Because incorrect
interpretation
of the reports generated could lead to serious errors of judgment
and questionable decisions. Therefore, it is important that
healthcare
organizations provide analytical training courses in areas such
as basic
statistics, data mining and business intelligence to those
employees
who will play a critical support role in the new information-rich
work
environment. According to a recent survey by the American
Manage-
ment Association (2013), mentoring, cross-functional team-
based
training and self-study are beneficial training approaches to
help em-
ployees develop the big data analytical skills theywill need.
Alternative-
ly, healthcare organizations can adjust their job selection

criteria to
recruit prospective employees who already have the necessary
analyti-
cal skills.
5.4. Incorporating cloud computing into the organization's big
data
analytics
Most hospitals are small and medium sized enterprises (SMEs),
and often struggle with cost and data storage issues. Due to the
rapid changes of technology, big data, and the general increase
in
data-intensive operations, healthcare organizations are facing
some
challenges: storage, analysis, and bottom line. The needs to
store dif-
ferent formats of data and access to them for decision making
have
pushed healthcare organizations seeking better solutions other
than traditional storage servers and processes. A typical model
for

126 (2018) 3–13
the storage of big data is clustered network-attached storage
(NAS),
which is a costly distributed file system for SMEs. A usage-
based
charging model such as cloud computing services is an
attractive al-
ternative. Cloud computing is a network-based infrastructure
capa-
ble of storing large scale of data in virtualized spaces and
performing complex computing near real time. The combination
of
lower cost and powerful and timely processing and analyzing
make
cloud computing an ideal option for healthcare SMEs to fully
take ad-
vantage of big data analytics.
However, storing healthcare data in a public cloud raises two
major
concerns: security and patient privacy (Sahoo et al., 2014).
Although the
public cloud is a significant cost savings option, it also presents
higher

security risk and may lead to the loss of control of patient
privacy
since the access to data is managed by a third party vendor. A
private
cloud, on the other hand, provides a more secure environment
and
keeps the critical data in-house, but increases the budget for big
data an-
alytics projects. Healthcaremanagersmust strike a balance
between the
cost-effectiveness of the different cloud choices and patient
information
protection when adopting big data analytics.
5.5. Generating new business ideas from big data analytics
New idea generation is not only necessary for organizational
innova-
tion, but also can lead to changes in business operations that
will in-
crease productivity and build competitive advantages. This
could be
achieved through the use of powerful big data predictive
analytics
tools. These tools can provide detailed reporting and identify

market
trends that allow companies to accelerate new business ideas
and gen-
erate creative thinking. In addition to using big data analytics to
answer
knownquestions,managers should encourage users to leverage
outputs
such as reports, alerting, KPIs, and interactive visualizations, to
discover
new ideas and market opportunities, and assess the feasibility of
ideas
(Kwon et al., 2015).
6. Limitation, future research and conclusion
Through analyzing big data cases, our research has provided a
better
understanding how healthcare organizations can leverage big
data ana-
lytics as ameans of transforming IT to gain business value.
However, like
any other study, ours has limitations. The primary limitation of
this
study is the data source. One challenge in the health care
industry is

that its IT adoption usually lags behind other industries, which
is one
of the main reasons that cases are hard to find. Although efforts
were
made tofind cases fromdifferent sources, themajority of the
cases iden-
tified for this study came from vendors. There is therefore a
potential
bias, as vendors usually only publicize their “success” stories.
Further
Case Case name Country
1 Wissenschaftliches Institut der AOK (WIdO) Germany
2 Brigham and Women's Hospital United States
3 The Norwegian Knowledge Centre for the Health Services
(NOKC) Norway
4 Memorial Healthcare System United States
5 University of Ontario Institute of Technology Canada
6 Premier healthcare alliance United States
7 Bangkok Hospital Thailand
8 Rizzoli Orthopedic Institute Italy
9 Universitätsklinikum Erlangen Germany
10 Fondazione IRCCS Istituto Nazionale dei Tumori (INT) Italy
11 Fraunhofer FOKUS Germany
12 Leeds Teaching Hospitals UK

13 Beth Israel Deaconess Medical Center United States
14 Atlantic Health System United States
15 Private health institution in Australia Australia
16 University Hospitals Case Medical Center United States
Appendix A. Case List
and better discovery could be done through collecting and
analyzing
primary data. Given the growing number of healthcare
organizations
adopting big data analytics, the sample frame for collecting
primary
data becomes larger. Examining the impact of big data analytics
capabil-
ities on healthcare organization performance with quantitative
analysis
method based on primary data could shed different lights.
In addition to requiring empirical analysis of big data analytics
en-
abled transformation, our study also expose the needs formore
scientif-
ic and quantitative studies, focusing on some of the business
analytics
capability elements we identified. This especially applies to

analytical
and decision support capabilities, which are cited frequently in
the big
data cases. With a growing amount of diverse and unstructured
data,
there is an urgent need for advanced analytic techniques, such
as deep
machine learning algorithm that allows computers to detect
items of in-
terest in large quantities of unstructured data, and to deduce
relation-
ships without needing specific models or programming
instructions.
We thus expect future scientific studies to take developing
efficient un-
structured data analytical algorithms and applications as
primary tech-
nological developments.
Finally, the foundation to generate any IT business value is the
link
among the three core dimensions: process, IT, and people
(Melville
et al., 2004). However, this study merely focuses on the IT
angle, ignor-

ing the people side of this capability as the cases barely
highlight the im-
portance of analytical personnel. Indeed, analytical personnel
who have
an analytic mindset play a critical role in helping drive business
value
from big data analytics (Davenport et al., 2010).We thus expect
that fu-
ture research should take analytical personnel into consideration
in the
big data analytics framework.
In conclusion, the cases demonstrate that big data analytics
could be
an effective IT artifact to potentially create IT capabilities and
business
benefits. Through analyzing these cases,we sought to
understand better
howhealthcare organizations can leverage big data analytics as
ameans
to create business value for health care.Wealso identifiedfive
strategies
that healthcare organizations could use to implement their big
data an-
alytics initiatives.

Acknowledgement
An earlier version was presented at HICSS (Hawaii
International
Conference on System Sciences) 2015. We would like to thank
the ses-
sion chair and reviewers from HICSS, and TFSC reviewers for
their in-
sightful comments and suggestions to improve this manuscript.
In
addition, we would like to thank Dr. Ting from IBM for
providing his
knowledge and practical experience in assisting the formulating
of the
big data analytics architecture model.
Sources
Released by vendors or companies IBM
IBM
IBM
IBM
IBM
IBM
IBM
IBM

IBM
IBM
IBM
Intel/Microsoft
Microsoft
EMC2/Intel
Practical journals IT Professional
Journal of the American Medical Informatics
(continued on next page)
(continued)
Case Case name Country Sources
Association
17 Texas Health Harris Methodist Hospital United States Print
publications Medcitynews/Modern Healthcare.com
18 Mount Sinai Medical Center United States MIT Technology
Review/Science Translational
Medicine

19 Indiana University Health United States Health Catalyst
20 Mission Health United States
21 MultiCare Health System United States
22 North Memorial Health Care United States
23 OSF HealthCare United States
24 Partners HealthCare United States
25 The University of Kansas Hospital United States
26 Texas Children's Hospital United States
Appendix A (continued)
126 (2018) 3–13
References
Agarwal, R., Gao, G., DesRoches, C., Jha, A.K., 2010. Research
commentary — the digital
transformation of healthcare: current status and the road ahead.
Inf. Syst. Res. 21
(4), 796–809.
American Management Association (AMA), 2013. Conquering
Big Data: Building Analyt-
ical Skills in Your Organization. American Management
Association Press.

Bardhan, I., Oh, J.H., Zheng, Z., Kirksey, K., 2014. Predictive
analytics for readmission of pa-
tients with congestive heart failure. Inf. Syst. Res. 26 (1), 19–
39.
Bodenheimer, T., 2005. High and rising health care costs. Part
1: seeking an explanation.
Ann. Intern. Med. 142 (10), 847–854.
Bryant, R.E., Katz, R.H., Lazowska, E.D., 2008. Big-data
computing: creating revolutionary
breakthroughs in commerce, science, and society computing.
Computing Research
Initiatives for the 21st Century. Computing Research
Association (Available at
http://www.cra.org/ccc/files/docs/init/Big_Data.pdf).
Burnard, P., 1991. A method of analysing interview transcripts
in qualitative research.
Nurse Educ. Today 11 (6), 461–466.
Chen, H., Chiang, R.H.L., Storey, V.C., 2012. Business
intelligence and analytics: from big
data to dig impact. MIS Q. 36 (4), 1165–1188.

Cortada, J.W., Gordon, D., Lenihan, B., 2012. The Value of
Analytics in Healthcare: From In-
sights to Outcomes. IBM Global Business Services, Somers,
NY.
Cosic, R., Shanks, G., Maynard, S., 2012. Towards a business
analytics capability maturity
model. Proceeding of 23rd Australasian Conference on
Information Systems, Geelon,
Australia.
Cox, M., Ellsworth, D., 1997. Application-controlled demand
paging for out-of-core visual-
ization. Proceedings of the 8th IEEE Conference on
Visualization. IEEE Computer Soci-
ety Press, Los Alamitos, CA.
Davenport, T.H., Harris, J.S., Morison, R., 2010. Analytics at
Work. Harvard Business School
Press, Cambridge, MA.
Dey, I., 1993. Qualitative Data Analysis. A User-friendly Guide
for Social Scientists.
Routledge, London.

Downe-Wamboldt, B., 1992. Content analysis: method,
applications, and issues. Health
Care Women Int. 13 (3), 313–321.
Elo, S., Kyngäs, H., 2008. The qualitative content analysis
process. J. Adv. Nurs. 62 (1),
107–115.
Esteves, J., 2009. A benefits realisation road-map framework
for ERP usage in small and
medium-sized enterprises. J. Enterp. Inf. Manag. 22 (1/2), 25–
35.
Gartner, 2013. Gartner says cloud computing will become the
bulk of new IT spend by
2016. Retrieved from
http://www.gartner.com/newsroom/id/2613015.
Gefen, D., Ragowsky, A., 2005. A multi-level approach to
measuring the benefits of an ERP
system in manufacturing firms. Inf. Syst. Manag. 22 (1), 18–25.
Goh, J.M., Gao, G., Agarwal, R., 2011. Evolving work routines:
adaptive routinization of in-

formation technology in healthcare. Inf. Syst. Res. 22 (3), 565–
585.
Grantmakers In Health, 2012. Transforming Health Care
Delivery: Why It Matters and
What Will it Take. Grantmakers In Health, Washington, DC.
Groves, P., Kayyali, B., Knott, D., Kuiken, S.V., 2013. The
“Big Data” Revolution in
Healthcare: Accelerating Value and Innovation. McKinsey &
Company.
Herrick, D.M., Gorman, L., Goodman, J.C., 2010. Health
Information Technology: Benefits
and Problems. National Center for Policy Analysis, Dallas,
Texas.
Hurwitz, J., Nugent, A., Hapler, F., Kaufman, M., 2013. Big
Data for Dummies. JohnWiley &
Sons, Hoboken, New Jersey.
IBM, 2012. Understanding Holistic Database Security: 8 Steps
to Successfully Securing En-
terprise Data Sources. IBM Corporation.

Use of a standardized nursing language for documentation of nursin.docx

Use of a standardized nursing language for documentation of nursin.docx

Recommended

Recommended

More Related Content

Similar to Use of a standardized nursing language for documentation of nursin.docx

Similar to Use of a standardized nursing language for documentation of nursin.docx (20)

More from jessiehampson

More from jessiehampson (20)

Recently uploaded

Recently uploaded (20)

Use of a standardized nursing language for documentation of nursin.docx