THE UNIVERSITY OF THE SOUTH PACIFIC

FACULTY OF BUSINESS AND ECONOMICS

SCHOOL OF ACCOUNTING AND FINANCE

AF302 – INFORMATION SYSTEMS

SEMESTER 1, 2020: FACE TO FACE MODE

ASSIGNMENT 1 – COVER SHEET

DUE DATE: SUNDAY, 10th MAY, 2020 AT 11.55PM [FIJI TIME]

WEEK 10

RESEARCH TOPIC:
Machine Learning
Advantages of Machine Learning in Health Care Sector

Student Full Name: Shilpa Shivangni

Student ID Number: S11158771

Tutorial Day and Time: Tuesday 3-5pm

Assignment Question
/50
*Note: Any discrepancy or error in marking should be brought to the notice of Mr.
Krishneel Tiwari immediately on the receipt of the marked manuscript.
 Abstract
In recent years, machine learning and artificial intelligence (AI) has grown exponentially in a
large number of fields in terms of software algorithms, hardware deployment, and
implementations. In this essay, advantages of machine learning in healthcare sector will be
discussed with real life case studies relating to it. The aim of this essay is to know the advantages
and importance of machine learning and artificial intelligence in health care sectors.

Introduction
“Machine learning in general is an artificial intelligence (AI) application which provides systems
with the ability to learn and improve automatically from experience without explicit
programming”[ CITATION Wha17 \l 1033 ] Machine learning is the process of teaching a computer
system how to make accurate predictions when fed data [ CITATION Nic181 \l 1033 ]. Machine
learning literally has countless uses in the healthcare field. Today machine learning helps update
administrative processes in hospitals, monitor and diagnose infectious diseases as well as
automates medical treatments.
“Integrating AI into the healthcare ecosystem allows for a multitude of benefits, including
automating tasks and analyzing big patient data sets to deliver better healthcare faster, and at a
lower cost”[ CITATION Ali19 \l 1033 ]

Machine learning in health care is important as it is used to forecast disease and diagnosis to help
doctors and payers respond sooner, forecast public health hazards by detecting trends and
surfacing high-risk signs and model progression of disease and more.
This essay will discuss certain applications and advantages of machine learning in health care
sector also including some relevant case studies of the topic. It will also discuss the methods
used in compiling this essay with its literature review.

Methodology
i. Type of Research
For compiling this research essay, secondary research was used such as internet that
includes encyclopedia, articles and case studies. Also
 ii. Literature Review
Machine learning in general is an artificial intelligence (AI) application which provides systems
with the ability to learn and improve automatically from experience without explicit
programming. This topic which is advantages of machine learning in health care sector is
important as it helps doctors to forecast diseases and diagnosis in patients faster and allows the
patients to heal faster. This literature review will enable readers to go through the history of
machine learning followed by relevant articles on machine learning in health care sector will be
discussed. The articles and information’s used in these review are from internet source which
will be duly acknowledged.
To begin with, Antonio Espingardeiro had considered the threat that other countries have
experienced since this present crisis for many years – an ageing population that is increasingly
increasing. Scalability and efficiency have always been required in healthcare. With the growing
population to live longer and more people struggling from non-communicable disorders (over
400 million people globally suffering from diabetes alone) needing daily medical tests, we need
to use technologies to completely democratize healthcare. Artificial Intelligence helps care
practitioners to understand better certain clinical problems. “For example, through AI programs,
scientists can explore the huge volume of data that makes up the DNA in the blood of cancer
patients. With this insight, they can detect specific mutations which will eventually be used to
classify those most at risk or identify those that may perhaps require further consultation”
[ CITATION Ant201 \l 1033 ]. In this article, Dr Antonio is explaining that technology is a must to be
used in health care sectors as it really helps doctors and practitioners to find out and understand
more of any health problem.
Moreover, machine learning also helps to keep large amounts of electronic data available at
health centers. According to Jenna Wiens, large amounts of clinical data were ignored. This
restriction was due to both the scale and sophistication of the records, and the lack of records
processing and storage techniques. “These data are frequently underused and undervalued;
however, new and improved methods for data collection and storage (eg, electronic health
records) provide opportunities to tackle the issue of analysis. In particular, machine learning
(ML) has begun to infiltrate the clinical literature broadly” [ CITATION Jen18 \l 1033 ]. With the
rise in the availability of scientifically applicable data sets, researchers have applied ML
techniques to a broad variety of clinical activities, from identifying / diagnosing activities (e.g.,
automated recognition of skin lesions or identification of arrhythmias) to forecasting tasks (e.g.,
forecasting 30-day read missions). It is now easier to detect diseases and diagnose them at a right
time as certain machine learning applications are available which now makes doctors work more
easier. Also, machine learning solves problems of storing and retrieving of large amounts of
clinical data set.
Furthermore, “Effective machine learning implementation enables healthcare professionals in
better decision-making, identifying trends and innovations, and improving the efficiency of
research and clinical trials” [ CITATION Ana17 \l 1033 ]. In this article he has explained how has
machine learning helped in the healthcare sector. With machine learning, healthcare providers
can make smarter choices on treatments and treatment plans for patients, leading to greater
changes in healthcare systems. Previously, gathering and evaluating the vast amount of data for
accurate forecasts and interventions was difficult for healthcare practitioners, because there were
no techniques or resources available. It has now become fairly simple for machine learning, as
big data technologies such as Hadoop are mature enough for wide-scale implementation. Borad
stated that the new approach to healthcare is to avoid the illness with early intervention instead of
continuing into diagnosis and medication. Traditionally, physicians or clinicians use a
probability calculator to determine the likelihood of contracting an illness. Given that
pharmaceutical researchers are unable to predict a possible drug compound effect on targeted
and non-targeted molecules using current analytical methods, the risks of drug failure in clinical
trials are higher. This situation leaves the product development process very expensive and time
consuming. Effective statistical models will save a lot of time in this situation, using machine
learning.
To conclude, after looking summarizing the articles above, it can be stated that there are lots of
advantages of machine learning in the health care sectors such as diagnosis and treatment of
illness and diseases, large amounts of clinical data can be stored and generated without difficulty,
and effectiveness of drug can be found out earlier. Overall, machine learning helps doctors and
practitioners in better decision making in relation to a patient’s medical problem.
 Background of Study
Medical implementation of machine learning / deep learning and AI is one of the most important
and fast-growing areas of our expertise. ML and AI innovations have increasingly entered all
fields of health-care infrastructure, from strengthening health-care administration to developing
new medicines. While machines are unlikely to overtake physicians and nurses entirely, digital
innovations are now changing the healthcare system as we know it. Here we give some
highlights of the applications for machine learning that have arisen in recent years.
To begin with, a human doctor in the present day cannot remember all the details needed to make
a timely yet correct diagnosis. No doctor will learn every part of medical care with the current
glut of manuals, scientific papers, and case studies, and remember every detail of the related
cases. However, it is possible to feed specific data into an AI-based program and allow the
computer to sift through the vast database, instead of relying on much more restricted human
intelligence. Therefore, recognition of the disorder was taken to the forefront of medicinal ML
science. Key market players were among the first to enter the search for the precise diagnosis,
particularly in much-needed areas such as oncology. Boston-based biopharmaceutical company
Berg applies AI to study and improve diagnostics and medical therapies in various fields,
including dosage trials for intravenous tumor therapy, to name only a few. Another example was
the development of technology that addresses problems of ageing eyes by Uk- Based
Partnerships with Moorfields Eye Hospital in London.
Moreover, a popular study field is customized medicine, which will offer a more efficient
diagnosis based on the patient health data combined with predictive analytics. So far, the
dominant testing approach in this area is supervised learning, which enables physicians to choose
from more specific diagnosis sets and predict the likelihood of the assigned condition based on
symptom similarities and genetic knowledge. In 2016, the UK-based health company Babylon
raised $25 million for the creation of an AI-driven healthcare app. It currently offers video
appointments with doctors, while future updates will serve like an AI-doctor: symptoms will be
provided by the application and reviewed against its database. “However, in relation to the
report, Babylon will consider the patient's individualized past and conditions, such as personal
history of wellness, medical histories, everyday activities, heart rate, cholesterol rates, allergies,
etc. Those data are collected by tracking the wearables readings”[ CITATION Mac18 \l 1033 ]

Furthermore, the field of health care reporting is closely connected to customized medical
services. Text classification using vector support devices, as well as optical character
recognition, i.e. translation of handwriting into digitized characters, are both important ML-
based technologies in the field of electronic health information collection and digitization. The
MIT Clinical Machine Learning Group has announced the creation of state-of-the-art digital
electronic health records with built-in ML / AI that will concurrently assist with advice for
diagnosis, therapeutic assessments, and customized care. MIT emphasized the need for robust
ML algorithms that could "read, interpret natural language, and generalize well through medical
settings and organizations from little labeled training data."
To add on, another successful application of ML and AI technology is the detection and analysis
of infectious outbreaks worldwide. The data sources include satellite data, site history, real-time
social media alerts and more. Supporting vector machines and artificial neural networks for
example help forecast malaria outbreaks based on temperature, average monthly rainfall,
cumulative number of positive events, and other data points. "By 2025, according to Harpreet
Singh Buttar, analyst at Frost & Sullivan, AI technologies could be interested in anything from
public health management to digital avatars capable of responding to individual patient requests”
To conclude, it can be stated that machine learning does help in the health care sector. The
articles mentioned above have proved that technologies are a major component in the health care
sector.
 Data or Relevant Case Studies
Advantages of Machine Learning in Health Care Sector
The importance of machine learning in healthcare is the potential to analyze vast data sets
outside the limits of human capability, and then efficiently turn data processing into clinical
knowledge that enable doctors prepare and deliver treatment, potentially contributing to
improved results, reduced cost of service, and enhanced patient satisfaction. This essay will
discuss the important advantages of artificial intelligence in the health care sector.
To begin with, in recent years robotic surgery has achieved huge attention. Machine learning
systems strive to contribute to what is currently available in the healthcare sector, utilizing
robotics for surgical procedures. “Replacing human doctors with robotics has many benefits,
including more complex procedures in smaller environments, and significantly decreases the
likelihood of human-based problems such as shaking hands”[ CITATION Ben18 \l 1033 ]. In robotic
surgery, machine learning primarily focuses on computer vision and is used to calculate
distances to a far higher degree of precision or to classify different sections or organs within the
body.
Moreover, today the healthcare sector has an explosion of patient information which has enabled
the usage of smart electronic healthcare documents essential for healthcare firms. Applications
for machine learning in the development of online digital records include utilizing documents
with built-in artificial intelligence or machine learning to help maintain medical information,
identify clinical problems and recommend recovery strategies.
Furthermore, one of the key uses of ML in healthcare is to classify and treat illnesses and
disorders that are often deemed impossible to diagnosis. That may involve everything from
tumors and other hereditary disorders that are challenging and detect during the early stages. No
doctor will learn every part of medical treatment despite the current glut of manuals, scientific
papers, and case studies, and remember every description of the related cases. However, feeding
an AI-based machine with appropriate data is feasible, thus encouraging the device to sift
through the vast database instead of depending on the more restricted human intelligence.
Adding on, machine learning is also used in the development of drug in the health care sectors.
ML can be extended at all levels of new product development including product chemical /
protein structure design, aim testing, drug safety investigation and clinical trial management.
“The hope is that use of ML in drug discovery will not only help significantly reduce the cost
of introducing new drugs to the market, but also make the drug discovery process faster
(currently 10-15 years including clinical trials) and more cost-effective (currently costs almost $1
billion per new drug)”[ CITATION Man19 \l 1033 ]. AtomNet technology of AI Company Atomwise
uses deep learning algorithms to sift in a day or two across millions of potential molecules which
would usually require months utilizing conventional methods. The program then analyzes
simulations which show how future medication in the human body would act.
To conclude, by reading at the advantages of machine learning, it can be said that machine
learning or artificial intelligence is vital in our health care sectors. It does make the work of
doctors and other health workers easier as it most importantly helps in the monitoring and
diagnosis of diseases in patients.
 Real life Case Studies
Artificial Intelligence in Health Care: Review and Prediction Case Studies
This case study talks about the latest developments of applications in artificial intelligence in
biomedicine, including disease diagnostics, living assistance, biomedical information processing
and biomedical research. Artificial Intelligence requires a device which consists of both
hardware and software. AI's especially obsessed with algorithms from a machine viewpoint. A
neural artificial network (ANN) is a computational structure for the execution of AI algorithms.
AI's main developments of biomedicine can be split down into four groups. The first three
sections listed in this segment are meant to handle big data effectively and to provide easy access
to data to address healthcare-related issues. “Due to the rapid development of AI software and
hardware technologies, AI has been applied in various technical fields, such as the IoT, machine
vision, autonomous driving, natural language processing, and robotics. Most interestingly,
researchers in the biomedical fields have been actively trying to apply AI to help improve
analysis and treatment outcomes and, consequently, increase the efficacy of the overall
healthcare industry. Figure 1 in appendix shows the number of publications in this area in the last
20 years, from 1999 to 2018” [CITATION Arn20 \l 1033 ]. AI technologies utilizing related smart
robotic devices are leading the way for changes in the standard of life in the field of assisted
living for the aged and the disabled. AI will help biomedical researchers not only scan but list
fascinating literature when the amount of study papers is beyond readability. This helps
researchers to develop and evaluate experimental theories to the limit, which are a very critical
part of biomedical science.
This case study evaluates that in biomedicine the most important requirement for AI is disease
diagnostics. AI encourages health care practitioners to make faster and more precise treatments
for several forms of diseases. One essential diagnostic class is focused on in vitro diagnosis
utilizing biosensors or biochips. Another essential diagnostic form of disease is focused on (two-
dimensional) medical imaging and (one-dimensional) signal processing. These methods were
used to treat, control, and forecast illnesses.
 Conclusion
Machine learning literally has countless uses in the healthcare industry. Today, machine learning
helps streamline manual procedures in clinics, monitor and diagnose infectious diseases as well
as personalize patient therapies. This research essay discussed about the advantages of machine
learning in health care sector. In the literature review and background study section, history was
discussed with relevant articles based on advantages of machine learning in health care. All in
all, it can be stated that machine learning is quite helpful in the health care sector.

Recommendation
 References
What is Machine Learning? (2017, March 7). Retrieved April 2, 2020, from ExpertSystem:
https://expertsystem.com/machine-learning-definition/

Benefits of Machine Learning. (2018, August 2). Retrieved April 23, 2020, from BusinessWire:
https://www.businesswire.com/news/home/20180802005410/en/Top-Benefits-Machine-
Learning-Healthcare-Industry-Quantzig

Machine Learning and AI Technologies in the health care industry. (2018, May 8). Retrieved April 25,
2020, from Sciforce: https://medium.com/sciforce/machine-learning-and-ai-technologies-in-
the-healthcare-industry-ad824211be19

Bakre, M. (2019, October 31). 5 Ways machine learning is redefining healthcare. Retrieved April 5, 2020,
from Entreprenuer: https://www.entrepreneur.com/article/341626

Borad, A. (2017, December 21). Healthcare and machine learning: the future with possibilities. Retrieved
April 24, 2020, from InfoChips: https://www.einfochips.com/blog/healthcare-and-machine-
learning-the-future-with-possibilities/

Espingardeiro, A. (2020, April 23). How Technilogy is addressing modern health care challenges.
Retrieved April 26, 2020, from Health Europa: https://www.healtheuropa.eu/how-technology-
is-addressing-modern-healthcare-challenges/99553/

Espingardeiro, A. (2020, April 23). How technology is addressing modern health care challenges.
Retrieved April 26, 2020, from Health Europa: https://www.healtheuropa.eu/how-technology-
is-addressing-modern-healthcare-challenges/99553/

Heath, N. (2018, September 4). What is machine learning. Retrieved April 24, 2020, from ZDNet: 1.
https://www.zdnet.com/article/what-is-machine-learning-everything-you-need-to-know/

Mendez, A. (2020, March 3). artificial intelligence in health care. Retrieved April 23, 2020, from
ScienceDirect: https://www.sciencedirect.com/science/article/pii/S2095809919301535#b0145

Phaneuf, A. (2019, August 1). Use of AI in healthcare and medicine is booming. Retrieved April 6, 2020,
from Business Insider: https://www.businessinsider.com/artificial-intelligence-healthcare

Wiens, J. (2018). Machine Learning for HealthCare: on the verge of a major shift in healthcare
epidemiology . In J. Wiens, Clinical Infectious Diseases (pp. 149-153). Oxford University Press.
 Appendix
Figure 1

“Growing research interest in the application of AI in biomedicine, as