Management Information Systems (CSIT204)

Assignment – Project

How Big Data Analytics is transforming the Healthcare Industry?

By:
Shawrya Mehra
Gaurav Sharma
Amity International Business School
Amity University, Noida
Overview

What is Big Data?

Big data is a term applied to data sets whose size or type is beyond the ability of traditional relational to
capture, manage and process the data with low latency. Big data has one or more of the following
characteristics: high volume, high velocity or high variety. Artificial intelligence (AI), mobile, social and
the Internet of Things (IoT) are driving data complexity through new forms and sources of data. For
example, big data comes from sensors, devices, video/audio, networks, log files, transactional
applications, web, and social media — much of it generated in real time and at a very large scale.

Analysis of big data allows analysts, researchers and business users to make better and faster decisions
using data that was previously inaccessible or unusable. Businesses can use advanced analytics
techniques such as text analytics, machine learning, predictive analytics, data mining, statistics and
natural language processing to gain new insights from previously untapped data sources independently or
together with existing enterprise data.

Big Data Analytics offers a nearly endless source of business and informational insight that can lead to
operational improvement and new opportunities for companies to provide unrealized revenue across
almost every industry. From use cases like customer personalization, to risk mitigation, to fraud detection,
to internal operations analysis, and all the other new use cases arising near-daily, the Value hidden in
company data has companies looking to create a cutting-edge analytics operation.

Discovering value within raw data poses many challenges for IT teams. Every company has different
needs and different data assets. Business initiatives change quickly in an ever-accelerating marketplace,
and keeping up with new directives can require agility and scalability. On top of that, a successful Big
Data Analytics operation requires enormous computing resources, technological infrastructure, and highly
skilled personnel.

Where did the big data arise from?

Big Data emerged from the early-2000s data boom, driven forward by many of the early internet and
technology companies. Software and hardware capabilities could, for the first time in history, keep up
with the massive amounts of unstructured information produced by consumers. New technologies like
search engines, mobile devices, and industrial machines provided as much data as companies could
handle—and the scale continues to grow. In a study conducted by IDC, the Market Intelligence firm
estimated that the global production of data would grow 10 times between 2015 and 2020.

Big Data analytics is a process used to extract meaningful insights, such as hidden patterns, unknown
correlations, market trends, and customer preferences. Big Data analytics provides various advantages—it
can be used for better decision making, preventing fraudulent activities, among other things.
Here are a few advantages of using big data analytics:

Risk Management 

Use Case: Bunco de Oro, a Philippine banking company, uses Big Data analytics to identify fraudulent
activities and discrepancies. The organization leverages it to narrow down a list of suspects or root causes
of problems. 

Product Development and Innovations

Use Case: Rolls-Royce, one of the largest manufacturers of jet engines for airlines and armed forces
across the globe, uses Big Data analytics to analyze how efficient the engine designs are and if there is
any need for improvements. 

Quicker and Better Decision Making Within Organizations

Use Case: Starbucks uses Big Data analytics to make strategic decisions. For example, the company
leverages it to decide if a particular location would be suitable for a new outlet or not. They will analyze
several different factors, such as population, demographics, accessibility of the location, and more.

Improve Customer Experience:

Use Case: Delta Air Lines uses Big Data analysis to improve customer experiences. They monitor tweets
to find out their customers’ experience regarding their journeys, delays, and so on. The airline identifies
negative tweets and does what’s necessary to remedy the situation. By publicly addressing these issues
and offering solutions, it helps the airline build good customer relations.

Big Data and Healthcare

Big Data in Healthcare: Healthcare big data refers to collecting, analyzing and leveraging consumer,
patient, physical, and clinical data that is too vast or complex to be understood by traditional means of
data processing. Instead, big data is often processed by machine learning algorithms and data scientists.
The rise of healthcare big data comes in response to the digitization of healthcare information and the rise
of value-based care, which has encouraged the industry to use data analytics to make strategic business
decisions. Faced with the challenges of healthcare data – such as volume, velocity, variety, and veracity –
health systems need to adopt technology capable of collecting, storing, and analyzing this information to
produce actionable insights. Like every other industry, healthcare organizations are producing data at a
tremendous rate that presents many advantages and challenges at the same time.

In the context of the health care system, which is increasingly data-reliant, data analytics can help derive
insights on systemic wastes of resources, can track individual practitioner performance, and can even
track the health of populations and identify people at risk for chronic diseases. With this information, the
health system can more efficiently allocate resources in order to maximize revenue, population health and
— very importantly — patient care.

Healthcare is a multi-dimensional system established with the sole aim for the prevention, diagnosis, and
treatment of health-related issues or impairments in human beings. The major components of a healthcare
system are the health professionals (physicians or nurses), health facilities (clinics, hospitals for
delivering medicines and other diagnosis or treatment technologies), and a financing institution
supporting the former two. The health professionals belong to various health sectors like dentistry,
medicine, midwifery, nursing, psychology, physiotherapy, and many others. Healthcare is required at
several levels depending on the urgency of situation. Professionals serve it as the first point of
consultation (for primary care), acute care requiring skilled professionals (secondary care), advanced
medical investigation and treatment (tertiary care) and highly uncommon diagnostic or surgical
procedures (quaternary care). At all these levels, the health professionals are responsible for different
kinds of information such as patient’s medical history (diagnosis and prescriptions related data), medical
and clinical data (like data from imaging and laboratory examinations), and other private or personal
medical data. Previously, the common practice to store such medical records for a patient was in the form
of either handwritten notes or typed reports. With the advent of computer systems and its potential, the
digitization of all clinical exams and medical records in the healthcare systems has become a standard and
widely adopted practice nowadays. The big data in healthcare includes the healthcare payer-provider data
(such as EMRs, pharmacy prescription, and insurance records) along with the genomics-driven
experiments (such as genotyping, gene expression data) and other data acquired from the smart web of
internet of things (IoT).

Management and analysis of Big Data: Big data is the huge amounts of a variety of data generated at a
rapid rate. The data gathered from various sources is mostly required for optimizing consumer services
rather than consumer consumption. This is also true for big data from the biomedical research and
healthcare. The major challenge with big data is how to handle this large volume of information. To make
it available for scientific community, the data is required to be stored in a file format that is easily
accessible and readable for an efficient analysis. In the context of healthcare data, another major
challenge is the implementation of high-end computing tools, protocols and high-end hardware in the
clinical setting. Experts from diverse backgrounds including biology, information technology, statistics,
and mathematics are required to work together to achieve this goal. The data collected using the sensors
can be made available on a storage cloud with pre-installed software tools developed by analytic tool
developers.

These tools would have data mining and ML functions developed by AI experts to convert the
information stored as data into knowledge. Upon implementation, it would enhance the efficiency of
acquiring, storing, analyzing, and visualization of big data from healthcare. The main task is to annotate,
integrate, and present this complex data in an appropriate manner for a better understanding. In absence
of such relevant information, the (healthcare) data remains quite cloudy and may not lead the biomedical
researchers any further. Finally, visualization tools developed by computer graphics designers can
efficiently display this newly gained knowledge.

Heterogeneity of data is another challenge in big data analysis. The huge size and highly heterogeneous
nature of big data in healthcare renders it relatively less informative using the conventional technologies.
The most common platforms for operating the software framework that assists big data analysis are high
power computing clusters accessed via grid computing infrastructures. Cloud computing is such a system
that has virtualized storage technologies and provides reliable services. It offers high reliability,
scalability and autonomy along with ubiquitous access, dynamic resource discovery and compos ability.
Such platforms can act as a receiver of data from the ubiquitous sensors, as a computer to analyze and
interpret the data, as well as providing the user with easy to understand web-based visualization.
The potential for big data analytics in healthcare to lead to better outcomes exists across many scenarios,
for example: by analyzing patient characteristics and the cost and outcomes of care to identify the most
clinically and cost effective treatments and offer analysis and tools, thereby influencing provider
behavior; applying advanced analytics to patient profiles (e.g., segmentation and predictive modeling) to
proactively identify individuals who would benefit from preventative care or lifestyle changes; broad
scale disease profiling to identify predictive events and support prevention initiatives; collecting and
publishing data on medical procedures, thus assisting patients in determining the care protocols or
regimens that offer the best value; identifying, predicting and minimizing fraud by implementing
advanced analytic systems for fraud detection and checking the accuracy and consistency of claims; and,
implementing much nearer to real-time, claim authorization; creating new revenue streams by aggregating
and synthesizing patient clinical records and claims data sets to provide data and services to third parties,
for example, licensing data to assist pharmaceutical companies in identifying patients for inclusion in
clinical trials.

By digitizing, combining and effectively using big data, healthcare organizations ranging from single-
physician offices and multi-provider groups to large hospital networks and accountable care organizations
stand to realize significant benefits [2]. Potential benefits include detecting diseases at earlier stages when
they can be treated more easily and effectively; managing specific individual and population health and
detecting health care fraud more quickly and efficiently. Numerous questions can be addressed with big
data analytics.

Areas in which enhanced data and analytics yield the greatest results include: pinpointing patients who
are the greatest consumers of health resources or at the greatest risk for adverse outcomes; providing
individuals with the information they need to make informed decisions and more effectively manage their
own health as well as more easily adopt and track healthier behaviors; identifying treatments, programs
and processes that do not deliver demonstrable benefits or cost too much; reducing readmissions by
identifying environmental or lifestyle factors that increase risk or trigger adverse events and adjusting
treatment plans accordingly; improving outcomes by examining vitals from at-home health monitors;
managing population health by detecting vulnerabilities within patient populations during disease
outbreaks or disasters; and bringing clinical, financial and operational data together to analyze resource
utilization productively and in real time.

The main difference between traditional health analysis and big-data health analytics is the execution of
computer programming. In the traditional system, the healthcare industry depended on other industries for
big data analysis. Many healthcare shareholders trust information technology because of its meaningful
outcomes—their operating systems are functional and they can process the data into standardized forms.
Today, the healthcare industry is faced with the challenge of handling rapidly developing big healthcare
data. The field of big data analytics is growing and has the potential to provide useful insights for the
healthcare system. As noted above, most of the massive amounts of data generated by this system is saved
in hard copies, which must then be digitized. Big data can improve healthcare delivery and reduce its
cost, while supporting advanced patient care, improving patient outcomes, and avoiding unnecessary
costs. Big data analytics is currently used to predict the outcomes of decisions made by physicians, the
outcome of a heart operation for a condition based on patient’s age, current condition, and health status.
Essentially, we can say that the role of big data in the health sector is to manage data sets related to
healthcare, which are complex and difficult to manage using current hardware, software, and management
tools. In addition to the burgeoning volume of healthcare data, reimbursement methods are also changing.

Why is Big Data Important for Healthcare?

Big data has become more influential in healthcare due to three major shifts in the healthcare industry: the
vast amount of data available, growing healthcare costs, and a focus on consumerism. Big data enables
health systems to turn these challenges into opportunities to provide personalized patient journeys and
quality care.

Increasing Volume of Healthcare Data: When health records went digital, the amount of virtual data
health systems had to handle rose steeply. In addition to EHRs, vast amounts of data are sourced in other
ways – through wearable technology, mobile applications, digital marketing efforts, social media, and
more. All of this adds up to an incredible amount of information, spurring health systems to adopt big
data systems and technologies to effectively collect, analyze, and take advantage of this information.

Growing Healthcare Costs: In the past 20 years, the United States has seen a rapid growth in healthcare
costs. Today, healthcare expenses account for around 18 percent of GDP, totaling about $3.4 trillion. This
is partially due to lifestyle factors, as well as government regulations. Through the collection and analysis
of large amounts of data, healthcare organizations will find quantifiable ways to improve performance
and efficiency. This promotes both increased patient satisfaction and your ability to capture greater
market share.

Desire for Personalized Care: Consumers in all industries expect exceptional, convenient, personalized
service – a phenomenon that retail industry executives have dubbed “The Amazon Experience.”
Healthcare is no different. Customers want convenient, personalized care, a new standard to which health
systems must rise. This new model of care focuses on quality, engagement, and retention. Health systems
are turning to healthcare big data to provide the insights necessary to drive this level of personalization.

Like big data in healthcare, the analytics associated with big data is described by three primary
characteristics: volume, velocity and variety.

 Volume: The amount of healthcare data that needs to be stored, managed, processed and
protected is growing at an ever-increasing rate. This situation is exacerbated by strict data
retention requirements. Medical imaging is one area where the growing volume of data is
especially evident. According to IBM, 30 percent of the data stored on the world’s computers are
medical images. Advances in the life sciences industry in the area of cost effective genomic
sequencing are causing data storage needs in this segment to explode. Many traditional solutions
have trouble scaling to accommodate this growing volume of data. “Scale-Out” solutions, where
computing nodes are added to an existing cluster to meet growing demand have several
advantages to traditional “Scale-Up” solutions, where one big, powerful server is replaced with
another bigger more powerful server.

 Velocity: Many existing analytics / data warehouse solutions are batch in nature. Meaning all the
data is periodically copied to a central location in a ‘batch’ (for example every evening). Clinical
and administrative end users of this information are, by definition, not making decisions based on
the latest information. Use cases such as clinical decision support really only work if end-users
have a complete view of the patient with the latest information. Solutions that make use of in-
 memory analytics or column-store databases are typically used to improve the velocity of the data
or “time to insight.”

 Variety: Traditional analytics solutions work very well with structured information, for example
data in a relational database with a well formed schema. However, the majority of healthcare data
is unstructured. Today, much of this unstructured information is unused (for example, doctor’s
free form text notes describing a patient encounter). Sophisticated natural language processing
techniques and infrastructure components such as Hadoop Map-Reduce are being used to
normalize a variety of different data formats, unlocking the data in a sense for clinical and
administrative end users.

What Challenges Arise with Big Data in Healthcare?

A major challenge with healthcare big data is sorting and prioritizing information. Data capacities are so
vast that oftentimes it can be difficult to determine which data points and insights are useful. As a result,
many organizations use AI or machine learning to process this data with exceptional agility.

Another challenge is ensuring that the right access to big data insights and analysis is given to the right
people so they can work intelligently. Even though healthcare data is pulled from many different systems,
organizations need to make sure critical personnel across the industry have comprehensive access to the
information.

There are also a number of data analysis challenges that result from heterogeneous or missing claims data.
The complexity of data is further compounded by each healthcare institution filing claims with data from
other Hospital Information Systems (HIS), or input from hospital personnel at the time of the encounter.
The data becomes even more complex when factoring in all the ambulatory places or service types. As a
result, there are five challenges to overcome in order to obtain accurate claims data:

Billing systems are fragmented and dated – Data is often very “noisy” – practices, groups, and even
service line specialties can be inconsistent. The key is to consider directional data in combination with
your local geographic market knowledge; in other words, data should augment interactions and focused
outreach to physicians, not replace it.

Patients do not have unique patient identifiers – If every patient had a unique identifier, data matching
would not be required. Until that happens, data matching mechanisms are required to look for these data
anomalies and put the right patient claims together.

Diagnosis and procedure codes can be unclear – Even industry-standard grouper tools can obscure
physician activity. Perfect data and perfect insights are very hard to achieve, so you have to advocate for,
and learn to work with, directional data.

Claims data is highly inconsistent – With claims data, any field data that is not required for payment has
a low probability of being completed accurately. In fact, among the few required fields for payment,
along with patient, diagnosis, and procedure information is the “rendering physician” via the NPI1 for
that provider.
It’s difficult to identify the referring physician – The “referring physician” field on available third-
party claims is often inconsistent, incorrect, or not filled at all. In fact, some clearinghouses don’t even
provide the “referring physician” filed because of these inconsistencies.

How Health Care Analytics Improves Patient Care?

Evaluating Practitioner Performance

As health care analytics continues to be better understood and implemented, this promises positive shifts
in the patient experience and quality of care. The McKesson Ongoing Professional Practice Evaluation,
for example, continually evaluates the performance of health care practitioners by aggregating data from
direct observation, complaints, practice patterns, patient outcomes and resource use. The data are
compared alongside various performance measurements such as professionalism, patient care and
interpersonal communication skills.

At the point of delivery, data analytics can continually evaluate physicians in real time, in order to track
and improve the effective practices of practitioners and improve patient care.

Patient Cost
Outcome- and value-based payment initiatives incentivize performance improvement in health care.
Accounting for costs is therefore tied to measuring performance and valuing best practices.

This means that, instead of focusing on reimbursement on a case-by-case basis, overall outcomes
determine payment. Ongoing health care analytics can help identify large patterns that lead to a greater
understanding of population health. A system of interconnected electronic health records available to
physicians helps provide detailed information that can help cut costs by reducing unnecessary care.
Additionally, by identifying trends in population outcomes, prescriptive analytics can estimate individual
patient costs; by doing so, the health care system can better allocate personnel and resources in order to
reduce waste and maximize efficiency.
Understanding patient costs, as well as total program costs, also involves accounting for what happens to
patients outside, as well as inside, of care. Through data analysis we can understand the cost of type-II
diabetes to the health care industry. Because diabetes is preventable through programs of diet and
exercise, paying for the health counseling of high-risk individuals in the population can greatly cut overall
costs to the industry.

Predicting Risk
One of the largest costs to the health care industry involves the treatment of chronic diseases. On a
population-wide level, predictive analytics can help greatly cut costs by predicting which patients are at
higher risk for disease and arrange early intervention, before problems develop. This involves aggregating
data that are related to a variety of factors. These include medical history, demographic or socio-
economic profile, and co morbidities.

Medical history usually includes age, blood pressure, blood glucose, family history of chronic conditions,
and cholesterol levels.
A large percentage of what affects health outcomes is associated with factors outside the purview of
traditional health care. These factors include patient health habits and behaviors, socio-economic factors
like employment and education, and physical environment. In order to improve outcomes, the public
health system must expand its boundaries to account for these ‘outside’ factors. In data analytics, these
metrics can be modeled to predict risk of chronic disease .

What is the Future of Big Data in Healthcare?

In the future, healthcare organizations will adopt big data in greater numbers as it becomes more crucial
for success. Healthcare big data will also continue to help make marketing touch points smarter and more
integrated. Additionally, the amount of data available will grow as wearable technology and the Internet
of Things (IoT) gains popularity. Constant patient monitoring via wearable technology and the IoT will
become standard and will add enormous amounts of information to big data stores. With this information,
healthcare marketers can integrate a large volume of healthcare insights to find and retain patients with
the highest propensity for services.

In the future, the data will probably be more accurate as the technology to track the earlier mentioned data
points will improve massively.

Reducing Costs

Big data is also a great solution to calculate current business models, cost models and expenses. It’s
therefore extremely valuable for healthcare institutions to analyze their current situation based on big data
to save costs.

Additionally, data sets can be analyzed and models can be built in order to predict staff allocation and
other rates based on historical data that clearly shows when it’s busy. For example, during winter holidays
there’s a higher chance for ski – or snowboarding accidents than in the summer.

Thus, health institutions can that money and allocate it to new investments such as equipment or research.
It’s also linked to insurance companies, which save money if the allocation of staff, hospital beds and so
on is better utilized.

Prevent Medical Human Errors

Medication prescription errors are a serious problem for hospitals and other healthcare institutions.
Everyone is still human, so there’s always a chance to make a mistake by prescribing the wrong or
different medication accidentally. In worst case scenarios, it may actually harm the patient with
potentially a catastrophic ending. Big data can be used to reduce human errors. The analysis can be used
to scan a patient’s history of medical records and identify potential errors and flag anything that seems out
of place.

Especially healthcare professionals who cater a lot of patients throughout the day risk a higher chance of
making a mistake. Thus, software to help them out would be the perfect solution.

A high-end research paper “Harvard Research Shows New Technology Can Save Thousands of Lives a
Year by Reducing Prescription Errors” stated that from almost 800,000 analyzed patients, little under
16,000 errors were flagged and 75% of these red-flags were actually validated.
The report also states that U.S. healthcare loses around $20bn are lost per year, as a result of prescription
errors.

The only downside of this newly developed algorithm is that many hospitals and other healthcare
institutions still work with relatively old computers, probably not capable of running such a memory-
heavy software tool.

Identify High-Risk Group

There’s a group of patients that repeatedly end up in the emergency room of hospitals due to certain
illnesses or diseases. This group is one of the cost-heavy groups in the healthcare industry. Big data could
be a massive improvement in order to predict certain patterns and why people keep coming back. Also,
preventative or early care is often not applied. The data can also be used to tailor personalized care.

However, there’s still a lack of data to paint a clear picture of these high-risk groups, at this moment in
time. But it would certainly be a massive improvement come future – if these models can actually be
created based on reliable data, that is.