Importance of Machine Learning in Medicine: An Ethical Perspective

This research study explores the role of machine learning in medicine and its ethical implications. The study is carried out with a sample size of 18 respondents and uses primary and secondary data. The research objectives, questions, literature review, methodology, limitations, and recommendations are discussed.

Business Research Method 1
Business Research Method Proposal

Business Research Method 2
Executive Summary
The research study is taken into consideration for the purpose of identifying the importance of
machine learning in medicine. The use of technology has developed the medical industry in an
extended edge. In relation to this study, the role of ethical aspect in context of machine learning
in medicine is also explored in depth manner. This study is carried out with sample size of 18
respondents as the experts in medical industry. Additionally, the primary and secondary data
have been used to gather the data from targeted population. The problem for this research is
defined as the utility and importance of machine learning in the medicine. On the other hand, the
research study is limited in sampling size, data, time and financial resources. Over the data
analysis, it can be concluded that the machine learning is important in the medicine to innovate
the new ways of resolving the medical disease in most feasible manner.

Business Research Method 3
Table of Contents
Executive summary.........................................................................................................................2
Introduction......................................................................................................................................4
Research objectives.........................................................................................................................5
Research questions...........................................................................................................................5
Literature Review............................................................................................................................7
To investigate the importance of machine learning in medicine.................................................7
To assess the ethical acceptance of machine learning in medicine:..........................................10
Research Methodology Design......................................................................................................12
Sampling........................................................................................................................................15
Limitations and Caveats of study..................................................................................................17
Data analysis and interpretation.....................................................................................................18
Conclusion.....................................................................................................................................29
Recommendations..........................................................................................................................30
Reference.......................................................................................................................................31
Appendix........................................................................................................................................35
Questionnaire.............................................................................................................................35

Business Research Method 4
Introduction
The medical industry is one of the growing industries in the global market. In relation to this, the
advancement of technology has also developed the medical industry in a new era of competitive
environment. In the recent years, the application of machines in diagnosis of disease has also
increased. The main aim of this study is to explore the role and importance of machine learning
in medicine with respect to its development and advancement in technology. Along with this,
this investigation is also carried out with respect to the assessment of ethical accept of machine
learning in the medicine. The literature is described with the inclusion of proposition and
hypotheses about the utility of machines in medical industry.
The main reason for carrying out this research is to identify the practical implications of
machines in the medical industry and how the machines are supporting the doctors and
researchers. This study is focused on determining the applicability of machine learning to
enhance the relevancy of technological system in advancement of medical industry. The chosen
topic is relatively important for the investigation as it has came into the light with the emergence
of hi- tech machines in medical problem diagnosing. At the same time, it is also crucial to study
as the technology has given the automated machines that are useful to evolve the new medicine
and automatic diagnosis for medical treatment. With relation to this, the investigation is also
deriving implications on the medical students to explore the knowledge about their study. Along
with this, it might also be useful for the professionals to find the innovative ideas from the study
to lead new inventions in this field.

Business Research Method 5
Research objectives
The research is carried out for determined objectives with relation to the medical industry. The
main objectives of this investigation are as follows
 To investigate the importance of machine learning in medicine
o To develop understanding about concept of machine learning in medicine
o To evaluate examples of application of machine learning in medicine
o To develop the understanding about Brain Age Project as part of applications of
machine learning medicine sector
 To assess the ethical acceptance of machine learning in medicine
o To analyze different ethical issues that are faced with application of machine
learning in medicine sector
o To evaluate the impact of ethical issues or challenges, if not resolved timely with
application of machine learning in medicine sector
o To provide recommendations for overcoming the occurrence of ethical issues and
challenges with application of machine learning in medicine sector
Research questions
The research questions have been designed on basis of devised aims and objectives, which are as
below
 What is the importance of machine learning in the medicine?
o What is the concept of machine learning in medicine sector?
o What are different examples of application of machine learning in medicine
sector?

Business Research Method 6
o What is Brain Age Project as part of applications of machine learning medicine
sector?
 How the ethical aspects of machine learning in medicine can determine?
o What are different ethical issues that are faced with application of machine
learning in medicine sector?
o What can be the consequences of ethical issues or challenges, if they are not
resolved timely with application of machine learning in medicine sector?
o What recommendations can be given for overcoming the occurrence of ethical
issues and challenges with application of machine learning in medicine sector?

Business Research Method 7
Literature Review
To investigate the importance of machine learning in medicine
To develop understanding about concept of machine learning in medicine
According to Meng et al. (2016), machine learning can be defined as the use of computer
enabled algorithms and artificial intelligence for purpose of making important calculations and
interpretations of data with regards to a particular problem. The machine learning can enhance
the ability of human being to make different complex decisions with better level of accuracy. In
contrast to this, Jordan and Mitchell (2015) depict that machine learning stands for the usage of
an automated data analytical model that is taken into account for making different types of
calculations and statistical algorithms. This data analytical model is based on the application of
computer enabled technologies, software and artificial intelligence. One of the key attributes of
machine learning is that it takes into account the minimum level of human intervention in the
calculation, as human is needed for feeding the inputs or raw data for calculations.
To evaluate examples of application of machine learning in medicine
Cufoglu and Coskun (2016) explain that there are different types of new treatments that are
visible in the field of medicine like brain age project. Machine learning can play a vital role in
this type of treatment for finding resolution to the challenges that are faced in today’s ageing
society in the healthcare system. As per a report published by authorities of European Union
Eurostat the growth rate of population is very high. At the same time, life expectancy is also
increasing across the Europe but issues of good health are not increasing with the same rate.
There is need of highly efficient and advance medical support system for purpose of meeting the
increase life expectancy need of people. According to this report, the problem of dementia will

Business Research Method 8
become as a major healthcare problem for future generations. As per observation of Daly and
Walsh (2018), WHO or World Health Organization has provided estimation that the number of
patients with the health issue of dementia will increase to 75 million by end of 2030 and its triple
times by end of 2050. These are certain facts that are already known by the healthcare
professionals. So there is need of finding out some solution to the indicated health issues. The
solution to these problems can only be ascertained through application of advance technologies
and innovations emerging in the field of medicine sector. Machine learning is anticipated as a
primary component that is required for origination of innovations in the field of medicine and
healthcare sector. In contrast to this, the application of artificial intelligence enables the
computers to analyze data, perform different calculations in order to determine specific pattern
available in the data and to provide better decisions to human being.
In the views of Cabitza et al. (2017), machine learning plays an important role in the field of
medicine and medical line. In healthcare sector, the application of machine learning is taken into
account for different purposes of research and development works, conducting diagnosis of
different disease symbols, and for better analysis of treatment outcomes. Example of a company
that is using machine learning technique in the field of medicine is Deep Mind Health of Google.
Core focus of this initiative is to find out solution to problem of macular degeneration in aging
eyes. In support of this, Faggella (2018) comments that machine learning technology is highly
adopted by the healthcare experts for diagnosis and identification of ailments with regards to any
disease in the field of medicine. IBM Watson Genomics is example of an initiative that is
planned and implemented with Quest Diagnostics that has emphasized on integration of genomic
tumor sequencing with the cognitive computing for purpose of making the strides in precision
medicine. Another example of application of machine learning in the field of medicine is Berg

Business Research Method 9
that is a bio-pharma company that is situated in the city of Boston. This company is consistently
using artificial intelligence (or AI) technology for performing the research and diagnosis. This
company is also involved in usage of machine learning technique and AI for therapeutic
treatments in different fields like oncology.
To develop the understanding about Brain Age Project as part of applications of machine
learning medicine sector
Example of application of artificial intelligence in medicine is medical image recognition, which
is mainly based on concept of deep learning. This technology (i.e. deep learning) was emerged in
1960s. These technologies are quite helpful today with the usage of improvements in parallel
data processing, usage of new algorithms, and the better data access. Example of application of
machine learning is visible in the case of Prof. Dr. med. Christian Wachinge. Prof. Wachinge is
the head of laboratory at the Ludwig-Maximilians-Universität (LMU) Munich in the department
of Child and Adolescent Psychiatry (Kharrat et al., 2010). Prof. Wachinge mainly deals in
medical imaging with the application of AI. He has emphasized that the data analytics need in
medical field has opened new opportunities for the computer scientists. In other words, there is
high demand for staff that can perform tasks or responsibilities of analysis and interpretation of
medical records for extraction of meaningful pattern. In University Hospital Munich, Prof.
Wachinge has used the machine intelligence for finding solution to different health issues like
brain abnormalities, and the mental illness (Pardoe et al., 2017). The Brain Age Project is
example of such initiative. This project has been carried out with the uses of SAP. Under this
project, the employees of LMU Munich have been organized into team (i.e. SAP Machine
Learning Team). This team has the goal of identification of new methods or ways for harnessing

Business Research Method 10
the machine learning in order to find business solutions in medicine field through application of
SAP.
Through Brain Age Project, the LMU team was dedicated to support the patients and doctors for
identification of advance treatment methods. Due to the work of LMU team and application of
SAP machine learning, a framework was developed in accordance to age estimation in neuro-
imaging. As a result of work on Brain Age Project, manual interpretation of brain scans resulting
from MRI technology is a time consuming process. In this context, the data obtained from MRI
scans of the healthy volunteers were used for purpose of creating machine learning model for
ascertainment of ageing signs of the brains. This model has proved to be effective for the
physicians for estimation of age of the brain (Cole et al., 2015). The application of deep machine
learning can be highly effective for helping physicians for conducting automatic analysis of brain
structure, even when the patient is on device or diagnosis machine. Apart from these, the usage
of machine learning technology will be effective to reduce the cost of medical care for both
patients and healthcare professionals. But for this, there is need of continuous research in the
field of application of machine learning, AI and big data analytics in medicine.
To assess the ethical acceptance of machine learning in medicine:
To analyze different ethical issues that is faced with application of machine learning in
medicine sector
As per the findings of Char et al. (2018), there are different ethical issues or challenges that may
be encountered with the application of machine learning in medicine field. The usage of machine
learning can only be productive, if the benefits of this technology are realized by healthcare
experts. The human biases in decision making can hamper the productivity of machine learning
technology in medicine sector. Another ethical issue with the application of machine learning is

Business Research Method 11
that there is possibility that repository being created is just the collection of thoughts of minds of
medical experts not the actual risks. It is also an ethical issue that there is possibility of error in
the designing or programming of algorithms to be used in the calculation and analysis. This type
of ethical issue was faced with Uber’s software tool Greyball. Example of a deception was
visible at Volkswagen in which company designed algorithms in a way to allow its vehicle
models to pass the emission tests. This type of algorithm mistakes can make the usage of
machine learning in medicine and health care sector worthless for both doctors and patients.
To evaluate the impact of ethical issues or challenges, if not resolved timely with
application of machine learning in medicine sector:
In accordance to Choy et al. (2018), there are different consequences that may be faced by the
healthcare organizations and health care professionals if the ethical issues or challenges are not
resolved timely. The poor quality issue may be faced by the healthcare professionals and
patients, if the ethical issues arise with the application of machine learning in medicine. For
example, if the machine learning algorithm is designed poorly, the results produced by such
system cannot provide accurate results about health of a patient. This way, the quality of
diagnosis, medication and treatment may hamper as a result of occurrence of ethical issues. In
contrast to this, Obermeyer and Emanuel (2016) state that one of the biggest issue that may be
faced by healthcare experts due to emergence of ethical issues with the application of machine
learning in medicine field. The legal actions may be faced by the organizations and professionals
working in healthcare sector. As a result of this, the huge fines may be faced by the healthcare
organizations and even their license may be dismissed by the regulatory bodies due to such
incidents.

Business Research Method 12
To provide recommendations for overcoming the occurrence of ethical issues and
challenges with application of machine learning in medicine sector:
In the opinions of Erickson et al. (2017), occurrence of ethical issues can be prevented through
high level of training of the people involved in programming and application of machine learning
in medicine. Only the productive and valid data should be taken into account for designing
machine learning algorithms in the automated systems in medical and healthcare sector. In order
to avoid biased decision making, it is very important to issue special directions to the healthcare
staff to follow the results produced by automated healthcare systems. In addition to this
Kickingereder et al. (2016) indicated that the development of repository should be constructed
through inclusion of actual risks not just the thoughts from minds of healthcare professionals.
Apart from this, the internal control system of company should be very powerful that can avoid
occurrence of any deception from internal players of the organization.
Research Methodology Design
The research designing is an important part of the study which supports the researchers in
context of data collection and analyzing the data in relevant manner. The research methodology
is developed for the study to engage into the gathering of information with respect to the
investigation of research problem (Novikov and Novikov, 2013). This research study is carried
out in order to explore the importance of machine learning in the medicine with including the
ethical acceptance of machines in the medicine line.
Research onion
The research onion is developed with the inclusion of research philosophies, designing,
approaches, data collection strategy and the time horizon for the investigation.

Business Research Method 13
(Source: Politano, et. al, 2018)
Research philosophies
In the research study, the practical implications lead to the chosen of research philosophies. The
philosophies are the approaches which involve the development of information/ knowledge,
source and nature of information with related to the research problem (Ledford and Gast,
2014).The major philosophies are developed for research assessment as positivism,
interpretivism and realism. The positivism aspect deals with the large data size and structure of
study. On the other hand, interpretivism deals with the small samples in the depth manner and it
engaged with the qualitative investigations. The realism philosophy is focused on choosing the
philosophies based on the subject matter as per relevancy. In this study, positivism philosophy is
appropriate because it emphasizes on the quantitative measurement (Malik et. al, 2016).
Research approach
The research approach is devised on basis of the hypothesis with relation to the investigation as
there are two major approaches as inductive and deductive in which deductive is concerned to
the testing of validity of assumptions of study (Danial and Harland, 2016). On the other hand,

Business Research Method 14
inductive approach deals with generation of untested conclusion to evolve the new theories and
generalization. The inductive approach is chosen because of its emergence with new theory
based on the collected data.
Research design
The research designing is also important part of the research investigation in which the blue print
or sketch of the study is developed to carry the research. There are two types of research
designing such as qualitative and quantitative (Shea and Yanow, 2013). This research is basically
investigated on basis of mixed methods as inclusion of numerical and descriptive analysis for
research problem.
Data collection methods
The strategy of data collection is important to gather the required and justified information so
there is a need of suitable method for having the right kind of information. Basically, two
methods are used such as primary and secondary in which primary method is evolved as the
collection of new and first hand data (Freytag and Young, 2017). On the other hand, secondary
data are the previously gather data as journals, articles, newspaper, annual report and government
publication. For this study, primary method of data collection is adopted through survey and the
secondary information is also used to conclude the stated problem (Neelankavil, 2015).
Data analysis method
The gathering of relevant data is not the end of research, there is also need of analyzing the data/
information to reach at summary (Roller and Lavrakas, 2015). There are several methods that
can be used such as SPSS, MS Excel, descriptive and graphical methods but in order to carry out
the analysis of data, MS Excel is used to interpret the data in easy and well presentation manner
(Jackson, 2012).

Business Research Method 15
Ethical consideration
The ethics are undeniable while engaging into the collection of data from the large size
population so the ethical issues such as informed consent in which it is essential to inform the
respondents about the purpose of study (Wilson, 2014).Along with this, the beneficence is also
determined as issue while particular study should not harm the participants. Moreover, the issue
of personal information confidentiality is also arisen as it is the moral duty of researcher to not to
disclose the personal information of respondents with any internal and external parties. On the
other hand, privacy is also an ethical problem that should be maintained by the surveyor. In
context to this study, the researcher will be focused on the adoption and implementation of
ethical standard to proceed with the investigation (Urquhart, 2012).
Sampling
The sampling is referred as the technique in which the particular number of observations or
people is selected from the large scale population. It is a systematic process, in which the sample
as a representative group of participants is chosen which helps the researcher to identifying the
right number of people. The target population can be defined as the entire group of population
from which the sample is drawn for research investigation (Seber and Salehi, 2012).On the other
hand, the major sampling techniques are as simple random sampling, stratified sampling, cluster
sampling, multistage sampling and systematic sampling. Where, the simple random sampling
consist with the n number of sample in direct manner and can easily be occurring. On the other
hand, stratified sampling is dealing with the different characteristic of population. The cluster
sampling is chosen in which the each member of population is assigned group which called the
cluster. Apart from this, the multistage sampling is referred as the choosing more than one

Business Research Method 16
sampling techniques such as, stage 1 cluster sampling is chosen and further the simple random
sampling method is chosen (Postawa, 2012). Moreover, the systematic simple random sampling
is a technique in which the entire population is grouped and one people chosen from each group.
In order to carry out this research study, simple random sampling method is chosen because the
group of population is wide so it is appropriate for this study. For this investigation, sample size
is chosen as 18through simple random sampling.

Business Research Method 17
Limitations and Caveats of study
The research study is significant in the investigation in the problem assessment but it is limited in
some manner as the sample size is very less as 18 with the comparison of its entire population
size. It might not derive significant results above the research problem (Chance et. al, 2013). On
the other hand, this study is limited in the importance of machine learning in medicine so it is
limited in research investigation. The time duration is also limited so the extended study might
not be elaborated with relation to the problem statement.

Business Research Method 18
Data analysis and interpretation
Q1.
Gender
No. of
Respondents
Male 10
Female 8
Total 18
It is identified from the above pie diagram that the total respondents in the study were 18 out of
which 10 were male consists of 56% of the population and 8 female experts.
Q2.
Work experience
Work
experience
No of
respondents

Business Research Method 19
1-5 Years 4
5 – 10 Years 5
10 -15 Years 6
More than 15
Years 3
Total 18
As per the responses of the experts in the field of pharmaceutical industry it is identified that the
majority of the respondents were having experience of more than 10-15 years it is about 1/3 of
the population. The experts working for 5-10 years are 5 depicting 27.77% of the population.
Q3.
Awareness towards machine learning Responses
(A) Strongly agree 7
(B) Agree 5
(C) Disagree 5

Business Research Method 20
(D) Strongly disagree 1
While interviewing about the awareness of the experts towards machine learning, it is identified
that 7 respondents were strongly in the favor of machine learning at the same time 5 respondents
were also in favor and 5 were against the importance of machine learning depicting no use of
machine learning in medical field.
Q4.
Importance of machine learning in
advancement of technology Responses
(A) Strongly agree 5
(B) Agree 7
(C) Disagree 4
(D) Strongly disagree 2

Business Research Method 21
From the above analysis, it is identified that majority of the respondents are in favor of
importance of machine learning in advancement of the technology. Around 66.66% respondents
were accepting its importance in advancement. On the other side, 6 respondents feel no
contribution of machine learning in advancement of technology.
Q5.
Importance of Machine learning in
Automated data analysis Respondents
(A) Strongly agree 3
(B) Agree 9
(C) Disagree 5
(D) Strongly disagree 1

Business Research Method 22
From the above chart, it can be said that 3 respondents strongly supports the machine learning in
automated data analysis and 9 respondents almost 50% are also supporting the machine learning
in automated data analysis. There were 5 respondents that are against the automated data analysis
with the help of machine learning.
Q.6 Impact of brain age project
Implication of brain age project Respondents
(A) To determine the age of brain 1
(B) To resolve the brain problem in effective
manner
4
(C) Reducing cost 5
(D) All of above 8

Business Research Method 23
From the brain age project application, it can be stated that the brain age project is useful for
identifying the age brain, to solve the brain problems in cost effective manner.
Q7.
In order to know identify the major challenges in relation to the machine learning in medicine,
the medical experts were asked to select any from the given options. The responses are
summarized in the below table:
Challenges with relation to machine
learning
No. of
respondents
(A) Less human intervention 4
(B) Need hi-tech system 6
(C) Lack of medical support 3
(D) All of the above 5
Total 18
From the above table, it can be identified that 6 out of 18 participants believe that there is a need
for hi-tech system, while 3 respondents stated that there is a lack of medical support. 4 out of 18

Business Research Method 24
respondents said that less human intervention is the major challenge while 5 said that all of the
three create challenges in machine learning. It is illustrated below using a diagram:
Q8.
This question was asked to know whether AI is useful to explore the interpretation of medical
record for solution of Dementia and less life expectancy medical problems. The responses
obtained were summarized in the following table:
Usefulness of Artificial Intelligence No. of
respondents
(A) Strongly agree 6
(B) Agree 3
(C) Disagree 4
(D) Strongly disagree 5
Total 18
From the above table, it has been analyzed that 9 out of 18 participants, that is., 50% of the
respondents agree with the statement. On the other hand, remaining 50% do not agree with this.

Business Research Method 25
It shows that AI is useful but may not be suitable in many cases. These responses are
shown below using a bar diagram:
Q9.
The researcher asked this question to determine the ethical issues with the use of AI while
resolving the medicine problems. The responses are presented in the below table:
Major ethical issues of AI No. of
respondents
(A) Human biasness 4
(B) Real risk resolution 6
(C) Error in designing of algorithm 3
(D) All of the above 5
Total 18
On the basis of the above table, it can be analyzed that 6 out of 18 participants feel that real risk
resolution is the major associated ethical risk, while 4 of them chose human biasness. On the

Business Research Method 26
other hand, 3 respondents believed that error in designing of algorithm is the ethical issue.
However, the remaining 5 considered these all.
Q10. Challenge of not resolving the ethical accept issues in machine learning
Major challenge while not solving the ethical
acceptance issue
Respondents
(A) Poor quality 4
(B) Issue with diagnosis and treatment 2
(C) Legal issues 5
(D) All of these 7

Business Research Method 27
From the above depicted graph, it can be stated that major issue will be faced if the ethical
challenges are not resolved such as poor quality, issues with treatment and diagnosis and legal
challenges.
Q11
Below are the responses of participants regarding the effective ways to overcome machine
learning challenge:
Ways to overcome the challenges No. of
respondents
(A) Integration of human with technology 6
(B) Proper command on designing and
programming
2
(C) Qualitative testing for computer based
algorithm
5
(D) All of the above 5
Total 18

Business Research Method 28
The above table shows that maximum experts (6) believe in the integration of human with
technology to overcome the challenges, while the least (2) participants stated that proper
command on designing and programming is the best way. On the other hand, 5 out of 18
considered qualitative testing for computer based algorithm as the best way to overcome the
issue, and the remaining 5 preferred that all the ways should be implemented. The responses are
shown using below bar diagram:

Business Research Method 29
Conclusion
In the above dissertation, the application of machine learning such as Artificial Intelligence in
the healthcare industry has been analyzed and reviewed. It can be concluded that machine
learning is an important tool for the medical experts in diagnosing and evaluating various kinds
of diseases and healthcare information in an effective manner. From the literature reviews, it can
be concluded that successful machine learning should have the essential elements in order to deal
with the structured data such as genetic information, EP details, and images, along with the
mining of unstructured data. However, it has also been observed that there exist a number of key
challenges associated with the use of machine learning by the experts. In order to utilize it in an
ethical and efficient manner, the sophisticated algorithms are required to be trained using
healthcare data prior to the assistance to physicians regarding the disease treatment suggestions.
In addition to this, it has also been examined that although machine learning technologies are
able to attentions in the healthcare sector, the real-world problems are still need to be resolved as
soon as possible.

Business Research Method 30
Recommendations
It can be recommended that the major issues related to the ethical practices and accuracy of the
data is wholly dependent on the inputs provided in the machine leaning. There is a strong need
for the medical experts to input accurate and actual information. The information related to the
thoughts and experiences may lead to manipulate the results which will lead to failure of the
objective. In addition to this, there is also need to use the machine learning for the benefit of the
people at large it is need to use the machine learning in appropriate manner for the purpose of
better decision making, optimized innovation, and improved efficiency of clinical trials and so
on (Faggella, 2018).
The use of the machine learning and artificial intelligence will lead to diagnose the disease at
early stage and it will provide accurate position of the treatment possibility for the critical
diseases through medicine treatment especially in case of cancer, oncology and others (Faggella,
2018). It will also be possible to provide personalized treatments based on the health data pairing
with predictive analysis. It is also recommended that it will also support in drug discovery and
clinical trials in less expense.

Business Research Method 31
Reference
Cabitza, F., Rasoini, R. and Gensini, G.F. (2017) Unintended consequences of machine learning
in medicine. Jama, 318(6), pp. 517-518.
Chance, B., Gibson, Q. and Eisenhardt, R. (2013) Rapid Mixing and Sampling Techniques in
Biochemistry. Netherlands: Elsevier.
Char, D.S., Shah, N.H. and Magnus, D. (2018) Implementing machine learning in health care—
addressing ethical challenges. The New England journal of medicine, 378(11), pp. 981-996.
Choy, G., Khalilzadeh, O., Michalski, M., Do, S., Samir, A.E., Pianykh, O.S., Geis, J.R.,
Pandharipande, P.V., Brink, J.A. and Dreyer, K.J. (2018) Current applications and future impact
of machine learning in radiology. Radiology, 288(2), pp. 318-328.
Cole, J.H., Leech, R. and Sharp, D.J. (2015) Prediction of brain age suggests accelerated atrophy
after traumatic brain injury. Annals of neurology, 77(4), pp. 571-581.
Cufoglu, A. and Coskun, A. (2016) Testing and analysis of activities of daily living data with
machine learning algorithms. International Journal of Advanced Computer Science &
Applications, 7(3), pp. 436-441.
Daly, A. and Walsh, D. (2018) Dementia—a major public health problem: the role of in-patient
psychiatric facilities. Irish Journal of Medical Science (1971), pp. 01-07.
Danial, D. and Harland, T. (2017) Higher Education Research Methodology: A Step-by-Step
Guide to the Research Process. UK: Routledge.
Erickson, B.J., Korfiatis, P., Akkus, Z. and Kline, T.L. (2017) Machine learning for medical
imaging. Radiographics, 37(2), pp. 505-515.

Business Research Method 32
Faggella, D. (2018) 7 Applications of Machine Learning in Pharma and Medicine. [Online].
Available at: https://www.techemergence.com/machine-learning-in-pharma-medicine/
(Accessed: 2 October 2018).
Freytag, P. and Young, L. (2017) Collaborative Research Design: Working with Business for
Meaningful Findings. Germany: Springer.
Hart, C. (2018) Doing a Literature Review: Releasing the Research Imagination. UK: Sage.
Jackson, S. (2012) Research Methods and Statistics: A Critical Thinking Approach. USA:
Cengage Learning.
Jordan, M.I. and Mitchell, T.M. (2015) Machine learning: Trends, perspectives, and
prospects. Science, 349(6245), pp. 255-260.
Kharrat, A., Gasmi, K., Messaoud, M.B., Benamrane, N. and Abid, M. (2010) A hybrid approach
for automatic classification of brain MRI using genetic algorithm and support vector
machine. Leonardo journal of sciences, 17(1), pp. 71-82.
Kickingereder, P., Bonekamp, D., Nowosielski, M., Kratz, A., Sill, M., Burth, S., Wick, A.,
Eidel, O., Schlemmer, H.P., Radbruch, A. and Debus, J. (2016) Radiogenomics of glioblastoma:
machine learning–based classification of molecular characteristics by using multiparametric and
multiregional MR imaging features. Radiology, 281(3), pp. 907-918.
Ledford, J. and Gast, D. (2014) Single Case Research Methodology: Applications in Special
Education and Behavioral Sciences. UK: Routledge.
Malik, S. Kumar, N. and Smarandache, F. (2016) Uses of Sampling Techniques & Inventory
Control with Capacity Constraints. USA; Infinite Stud.

Business Research Method 33
Meng, X., Bradley, J., Yavuz, B., Sparks, E., Venkataraman, S., Liu, D., Freeman, J., Tsai, D.B.,
Amde, M., Owen, S. and Xin, D. (2016) Mllib: Machine learning in apache spark. The Journal of
Machine Learning Research, 17(1), pp. 1235-1241.
Neelankavil, J. (2015) International Business Research.USA: M.E. Sharpe.
Novikov, A., and Novikov, D. (2013) Research Methodology: From Philosophy of Science to
Research Design. USA: CRC Press.
Obermeyer, Z. and Emanuel, E.J. (2016) Predicting the future—big data, machine learning, and
clinical medicine. The New England journal of medicine, 375(13), pp. 1216-1230.
Pardoe, H.R., Cole, J.H., Blackmon, K., Thesen, T. and Kuzniecky, R. (2017) Structural brain
changes in medically refractory focal epilepsy resemble premature brain aging. Epilepsy
research, 133, pp. 28-32.
Politano, P., Walton, R. and Parrish, A. (2018) Statistics and Research Methodology: A Gentle
Conversation. USA: Lulu.com.
Postawa, A. (2012) Best Practice Guide on Sampling and Monitoring of Metals in Drinking
Water. UK: IWA Publishing.
Roller, M. and Lavrakas, P. (2015) Applied Qualitative Research Design: A Total Quality
Framework Approach. USA: Guilford Publications.
Seber, G. and Salehi, M. (2012) Adaptive Sampling Designs: Inference for Sparse and Clustered
Populations. Germany: Springer Science and Business Media.
Shea, P. and Yanow, D. (2013) Interpretive Research Design: Concepts and Processes. UK:
Routledge.
Urquhart, C. (2012) Grounded Theory for Qualitative Research: A Practical Guide. USA:
SAGE.

Business Research Method 34
Wilson, J. (2014) Essentials of Business Research: A Guide to Doing Your Research Project.
USA: SAGE.

Business Research Method 35
Appendix
Questionnaire
Q.1. What is your gender?
(A) Male
(B) Female
Q.2. How much is work experience in medical sector?
(A)1-5 Years
(B) 5 – 10 Years
(C) 10 -15 Years
(D) More than 15 Years
Q.3.Are you aware about the machine learning in the medicine?
(A) Strongly agree
(B) Agree
(C) Disagree
(D) Strongly disagree
Q.4. Have you experienced the importance of machine learning in medicine with the
advancement of technology?
(A) Strongly agree
(B) Agree
(C) Disagree
(D) Strongly disagree
Q.5. Is the machine learning is effective to use of automated data analysis?

Business Research Method 36
(A) Strongly agree
(B) Agree
(C) Disagree
(D) Strongly disagree
Q.6. Do you have implications about the brain age project application about to implications of
artificial intelligence?
(A)To determine the age of brain
(B) To resolve the brain problem in effective manner
(C) Reducing cost
(D) All of above
Q.7. What is the majorchallenge with relation to the machine learning in the medicine?
(A) Less human intervention
(B) Need hi-tech system
(C) Lack of medical support
(D) All of the above
Q.8. Is artificial intelligence is useful to explore the interpretation of medical record for solution
of Dementia and less life expectancy medical problems?
(A) Strongly agree
(B) Agree
(C) Disagree
(D) Strongly disagree
Q.9. What is the major ethical issue of artificial intelligence while resolving the medicine
problems?

Business Research Method 37
(A)Human biasness
(B) Real risk resolution
(C) Error in designing of algorithm
(D) All of the above
Q.10. Can you have the major problem if the ethical issues are not resolved in relation to
machine learning in medicine?
(A) Poor quality
(B) Issue with diagnosis and treatment
(C) Legal issues
(D) All of these
Q.11. How can the challenge of machine learning in medicine can be improved?
(A)Integration of human with technology
(B)Proper command on designing and programming
(C) Qualitative testing for computer based algorithm
(D)All of the above