Essence of Soft Computing in Healthcare

International Journal of Trend in Scientific Research and Development (IJTSRD)
Volume 6 Issue 2, January-February 2022 Available Online: www.ijtsrd.com e-ISSN: 2456 – 6470
@ IJTSRD | Unique Paper ID – IJTSRD49264 | Volume – 6 | Issue – 2 | Jan-Feb 2022 Page 542
Essence of Soft Computing in Healthcare
Matthew N. O. Sadiku1
, Uwakwe C. Chukwu2
, Abayomi Ajayi-Majebi3
, Sarhan M. Musa1
1
Roy G. Perry College of Engineering, Prairie View A&M University, Prairie View, TX, USA
2
Department of Engineering Technology, South Carolina State University, Orangeburg, SC, USA
3
Department of Manufacturing Engineering, Central State University, Wilberforce, OH, USA
ABSTRACT
Soft-computing is a branch of computer science that utilizes
approximations to find imprecise solutions to complex problems.
Soft-computing techniques are tolerant of imprecision, uncertainty,
partial truth, and approximations, and are characterized by their
tractability, robustness, and low solution cost. The impact of soft
computing in medical diagnosis cannot be overemphasized. A large
number of soft computing methods have been successfully applied
for diseases diagnosis and prediction. This paper is an introduction on
the applications of soft computing in healthcare.
KEYWORDS: soft computing, hard computing, computer science,
healthcare
How to cite this paper: Matthew N. O.
Sadiku | Uwakwe C. Chukwu | Abayomi
Ajayi-Majebi | Sarhan M. Musa
"Essence of Soft Computing in
Healthcare" Published in International
Journal of Trend in
Scientific Research
and Development
(ijtsrd), ISSN:
2456-6470,
Volume-6 | Issue-2,
February 2022,
pp.542-547, URL:
www.ijtsrd.com/papers/ijtsrd49264.pdf
Copyright © 2022 by author (s) and
International Journal of Trend in
Scientific Research and Development
Journal. This is an
Open Access article
distributed under the
terms of the Creative Commons
Attribution License (CC BY 4.0)
(http://creativecommons.org/licenses/by/4.0)
INTRODUCTION
We often come across problems that do not have
precise information to solve them. There are certain
scenarios which do not have exact and precise
parameters. Such problems cannot be solved by
traditional problem-solving methods. This is where
soft-computing comes into play.
The term “soft computing” was coined by Lofti A.
Zadeh in 1991. Since then, the area has experienced
rapid development. Soft Computing became a
discipline within computer science in the early 1990s.
The terms “machine intelligence” and “computational
intelligence” have been used to have close meaning as
soft computing.
The principal premise of soft computing (SC) is that
we live in a world that is imprecise and uncertain.
Soft computing refers to the use of “inexact”
solutions to computationally hard tasks [2].
Healthcare basically deals with the detection,
treatment, analysis, prediction and prevention of a
disease, injury, illness or any other impairment. The
key segments of the healthcare industry is shown in
Figure 1 [3]. A proper healthcare system that would
supplement has become the need of the hour. The
crisis of healthcare resources in terms of man and
machine in our society has become crucial. The rural
people are not getting proper treatment due to the lack
of doctors and some die due to improper diagnosis by
the chock doctors. The question is how to minimize
this calamity. Researchers are seeking a solution that
would provide the best results with no side-effects
and cost effective. It has been observed that in
healthcare system could not go ahead a single step
without soft computing [4]. Healthcare organizations
seek to derive valuable insights employing data
mining and soft computing techniques on the vast
data stores that have been accumulated over the years.
The parameters that form the foundation in the
development of good healthcare systems include
quality, acceptability, scalability, efficiency,
consistency, coverage, continuity and most
importantly cost.
IJTSRD49264

International Journal of Trend in Scientific Research and Development @ www.ijtsrd.com eISSN: 2456-6470
Conventional computing or hard computing (HC)
requires an analytical, precisely stated model. Hard
computing is deterministic and precise. Health care
systems, however, are less ideal, highly uncertain,
and stochastic in nature. There is lot of uncertainty
and imprecision involved. Soft computing techniques
have also been applied successfully in healthcare data
for effectively diagnosing diseases and obtaining
better results in comparison to traditional approaches.
These approaches include neural networks,
probabilistic models, evolutionary algorithms,
artificial neural networks, fuzzy logic swarm
intelligence, etc. Figure 2 compares hard computing
and soft computing [5].
OVERVIEW OF SOFT COMPUTING
Soft computing (SC) is a branch of computer science
that resembles the processes of the human brain. It
may also be regarded as a newly emerging
multidisciplinary field. Its main objective is to
develop intelligent machines in order to solve real-
world problems. It differs from the conventional hard
computing as it can handle uncertainty, imprecision
easily. While conventional hard computing is based
on crisp values and binary numbers, SC uses soft
values and fuzzy sets.
Soft computing, also known as a computational
intelligence¸ is based on natural as well as artificial
ideas. It differs from conventional computing that is
hard computing. It is tolerance of imprecision,
uncertainty, partial truth to achieve tractability,
approximation, robustness, low solution cost, and
better rapport with reality. In fact the role model for
soft computing is human mind [6].
Soft computing refers to a collection of
computational techniques in computer science,
artificial intelligence, and machine learning. The
techniques aim to exploit the tolerance of imprecision
and uncertainty to achieve tractability, robustness,
and low solution cost. Its principle components
include:
Expert systems
Neural networks,
Machine learning
Probabilistic reasoning
Evolutionary algorithms
Artificial neural networks
Fuzzy logic
Swarm intelligence
Interactive computational models
These computation methods or technologies provide
information processing capabilities to solve complex
practical problems. Some of these techniques are
illustrated in Figure 3 [7].
APPLICATIONS OF SC IN HEALTHCARE
Soft computing is used for solving real-life problems
and can be applied in different fields such as
education, healthcare, business, industry, engineering,
power systems, transportation, communication
systems, wireless communications, data mining,
home appliances, robotics, etc. [8]. In the healthcare
industry, one wrong decision can result in loss of
lives or permanent damage to the patients. Medical
doctors are increasingly turning to soft computing to
diagnose the patients’ ailments from the symptoms
accurately and avoid wrong diagnosis. Typical
applications of soft computing in healthcare include
the following:
Medical Decision Making: Healthcare
practitioners need to diagnose a disease and make
a decision about the treatments. Patients have
symptoms, which are manifestations of the
disease or a group of diseases. For proper
diagnosis, the corrective treatment involves
identifying the underlying cause of symptoms.
Over the years, researchers from computer
science, mathematics, and medical sciences have
developed intelligent tools for supporting medical
decision making. Modern digital technologies
have allowed several soft computing systems to
be successfully developed and used by healthcare
professionals. In healthcare, decision making has
relied traditionally on rule-based reasoning
systems. Intelligent system based on soft
computing (SC) techniques can help patient and
doctors to express their observations that is
inherently vague. SC techniques can handle such
inputs and deduce some inference. SC not only
helps in analyzing data but it is also very effective
in finding relationship between diagnosis,
treatment and prediction of the result in many
clinical scenarios [9].
Medical Diagnosis: Fast and reliable medical
diagnosis is of vital importance in today’s global
world. For example, SARS or the bird flu are
highly contagious and can threaten the world if
they are not fought immediately and with high
efficiency. It is necessary to quickly and surely
diagnose the disease regardless of where the case
is encountered in the world. Depending on
indicators such as blood pressure and the health
history of the patient, a first diagnosis is compiled
using automated decision support systems [10].
Soft-computing techniques have been proposed to
handle vagueness and imprecision in the
diagnosis process. Soft-computing techniques in
the diagnosis of tropical diseases such as malaria,
leishmaniasis, typhoid fever, schistosomiasis,

yellow fever, onchocerciasis, lymphatic filariasis,
ebola, chagas disease, chicken pox, African
trypanosomiasis, and dengue. Since traditional
diagnostic techniques could not curb the menace
of tropical diseases, it is high-time soft computing
techniques-which are cheaper, varied, and can
handle fuzzy and confusable problems – should
be employed [11].
Cardiac Health: Based on the heart rate
variability (HRV) analysis, cardiology experts can
make an assessment for both the cardiac health
and the condition of the autonomic nervous
system that is responsible for controlling heart
activity and, consequently, they try to prevent
cardiovascular mortality. An enhanced ECG-
based decision making system can exploit a
collection of ontological models representing the
ECG and HRV feature sets and a fuzzy inference
engine [12].
Kidney Diseases: Kidney failure implies that
one’s kidney have unexpectedly stopped
functioning. Chronic kidney sickness depicts
anomalous kidney function. Treatment may avoid
or delay its progression, either by reducing and
preventing the development of some associated
complications, such as hypertension, obesity,
diabetes mellitus, and cardiovascular
complications. An early intervention can
significantly improve the prognosis. A hybrid
decision support system will allow one to
consider incomplete, unknown, and even
contradictory information, complemented with an
approach to computing centered on artificial
neural networks [13].
Medical Image Analysis: Soft computing
techniques are used in medical image analysis and
processing with real-world medical imaging
applications. This includes image enhancement,
segmentation, classification-based soft
computing, and their application in diagnostic
imaging, as well as an extensive background for
the development of intelligent systems based on
soft computing used in medical image analysis
and processing. The soft computing approaches
include fuzzylogic, neural networks, evolutionary
computing, rough sets, and swarm intelligence
[14].
Prediction Chronic Diseases: The chronic
disease is one of the biggest diseases facing
societies all over the world. The chronic diseases
such as cancer, asthma, heart, and diabetics are
non-communicable diseases (NCD) as compared
with another global disease that is an extremely
serious type of global disease. The World Health
Organization (WHO) has reported the chronic
disease is one of the highest grave diseases that
threaten human life in this world. They illuminate
the behavioral habits from environmental factors
that belong to increasing chronic diseases such as
factors (unhealthy diet, physical inactivity,
tobacco and alcohol use, air pollution, age, and
heredity). A soft computing algorithm can
improve the prediction process [15].
Patient Health Monitoring: Health monitoring
systems integrate health monitoring things like
sensors and medical devices for remotely observe
patient’s records to provide smarter and
intelligent healthcare services. They are becoming
common in for the patients of type geriatric,
dying, long suffering etc. either in the hospitals
and homes. The health monitoring often monitors
blood pressure, diabetes, respiration, body
temperature, food and liquid intake, calories
burnt, oxygen consumption, sleep quality,
medicine remainder, etc. Tracking patient data
from a health monitoring system helps the doctors
to take preventive measures to save the life for a
patient. Various devices like blood pressure
monitor, temperature monitor, diabetes monitor,
heart beat monitor, medicine remainder, etc. may
be connected to the patients. The doctors collect
the data of their patients regularly using these
devices and analyze the data. Using the
computational intelligence and soft computing
methods, the doctors analyze the data and make
predictions. The monitoring system using soft
computing techniques is not only limited to
classification and prediction, it is extended to
other supervised and unsupervised learning
algorithms to monitor, diagnose, and treat the
patients [16].
Infectious Disease Modeling: This is a multi-
disciplinary research activity that has made
significant inroads as a valuable and practical tool
for public health experts and decision makers.
Realistic infectious disease modeling must
incorporate parameters aggregated from disparate
database sources. These data may be incomplete,
imprecise, insufficiently specific, or collated at
varying levels of information granularity. With
the ability to deal with imprecise, approximate,
and vague scenarios, soft computing can play an
important role in expanding the use of these
models. Some soft computing approaches have
been used for infectious disease modeling. The
single greatest challenge with infectious disease
modeling is that models are often developed with
only the modelers in mind and not the public

health experts. Soft computing based approaches
to infectious disease modeling do not suffer from
this deficiency [17].
Privacy Preservation Electronic Health: One of
the biggest challenges facing healthcare is
protecting the important sensitive data of
electronic health records (EHRs) that are
available over web. The real issues on EHRs is
hiding the sensitive huge data especially stored in
distributed environment and shared between
numbers of stakeholders. It is very important to
eliminate the superfluous data and maintains the
privacy of individual record stored in EHRs. To
construct an effective privacy framework for
EHR’s, fuzzy logic system is applied on different
dataset that are available. In fuzzy logic-based
privacy preservation model, the sensitive
attributes of electronic health records values are
set into five linguistic values such as Low, Very
Low, Middle, High and Very High [18].
BENEFITS AND CHALLENGES
Soft computing methods can adapt themselves
according to problem domain. This makes soft
computing techniques more powerful, reliable, and
efficient. It also makes the soft computing approaches
more suitable and competent for healthcare data [19].
Soft Computing techniques aided by the technological
advancements would undoubtedly curb the shortage
in the availability of proper healthcare.
Implementation of soft computing systems for
medical applications should be supported by a solid
security shield that ensures the privacy and safety of
medical data. There is a noticeable “research divide”
between the universities and the community at large,
which is sending the wrong signals to governments,
the WHO, and other stakeholders. Research results
are buried in the archives of universities with little or
no publicity to the larger community.
CONCLUSION
Soft computing is essentially the study of science of
reasoning, thinking, analyzing, and detecting that
correlates the real world problems to the biological
inspired methods. It is one of the front running
technologies which is defining the future of
computing. Soft computing approaches play a vital
role in solving the different kinds of problems and
provide promising solutions. The approaches have
also been applied in healthcare data for effectively
diagnosing diseases and obtaining better results in
comparison to traditional approaches. Soft computing
approaches can adapt themselves according to
problem domain.
Healthcare organizations should be laying the cultural
foundation today for upcoming technology changes in
the near future. What will be needed in the future is
not just the breakthroughs in technology, but
breakthroughs in creative thinking and the ability of
leaders to think differently [20]. The shortage of
healthcare practitioners and increased demand could
crash healthcare systems in the coming years. More
information about soft computing in healthcare can be
found in the books in [14,21-27] and the following
related journals:
Soft Computing
Applied Soft Computing Journal
Applied Computational Intelligence and Soft
Computing
Journal of Healthcare Engineering
Journal of Soft Computing and Decision Support
Systems
International Journal on Soft Computing
REFERENCES
[1] K. Taylor, “What is soft computing?”
https://www.hitechnectar.com/blogs/application
s-soft-computing/
[2] M. N. O. Sadiku, Y. Wang, S. Cui, S. M. Musa,
“Soft computing: An introduction,”
International Journal of Advanced Research in
Computer Science and Software Engineering,
vol. 8, no. 6, June 2018, pp. 63-65.
[3] “All about healthcare industry: Key segments,
value chain, needs and competitive advantage,”
https://www.predictiveanalyticstoday.com/what
-is-healthcare-industry/
[4] S. Das and M. K. Sanyal, “Application of AI
and soft computing in healthcare: A review and
speculation,” International Journal ff Scientific
& Technology Research, vol. 8, no. 11,
November 2019, pp. 1786-1806.
[5] B. Xavier, and P. B. Dahikar, “A
comprehensive study on the significance of soft
computing in healthcare systems,”
International Journal of Engineering Research
& Technology, vol. 4, no. v2, February 2015,
pp. 278-281.
[6] S. K. Das et al., “On soft computing techniques
in various areas,” Computer Science &
Information Technology, 2013, pp. 59-68.
[7] “Difference between AI and soft computing,”
March 2020,
https://www.geeksforgeeks.org/difference-
between-ai-and-soft-computing/
[8] M. Dahiya, “Applications of soft computing in
various areas,” International Journal of

Engineering Sciences & Research Technology,
vol. 6, no. 5, May 2017, pp. 712-716.
[9] A. Bhatia, V. Mago, and R. Singh, “Use of soft
computing techniques in medical decision
making: A survey,” Proceedings of
International Conference on Advances in
Computing, Communications and Informatics,
September 2014, pp. 1131-1137.
[10] M. Ulieru, M. Hadzic, and E. Chang, “Soft
computing agents for e-Health application to
the research and control of unknown diseases,”
Information Sciences, vol. 176, no. 9, May
2006, pp.1190-1214.
[11] S. B. Oyong et al., “Application of soft
computing techniques in the diagnosis of
tropical diseases: A systematic review,”
Journal of Tropical Diseases and Public
Health,vol. 8, no. 5, 2020.
[12] G. Acampora et al., “Evaluating cardiac health
through semantic soft computing techniques,”
Soft Computing, vol. 16, 2012, pp.1165–1181.
[13] J. Neves et al., “A soft computing approach to
kidney diseases evaluation,” Journal of
Medical Systems, vol. 39, Article number 131,
August 2015.
[14] N. Dey et al., Soft Computing Based Medical
Image Analysis. Springer, 2018.
[15] T. H. H. Aldhyani, A. S. A. Alshebami, M. Y.
Alzahrani, “Soft computing model to predict
chronic diseases,” Journal of Information
Science and Engineering, vol 36, 2020, pp.
365-376.
[16] Y. V. R. N. Pawan, K. B. Prakash, and P. K.
Vadla, “Patient health monitoring using soft
computing techniques,” IOP Conference
Series: Materials Science and Engineering, vol.
872, 2020.
[17] N. J. Pizzi, “Soft computing and infectious
disease modeling: A review and prescription,”
Proceedings of the Annual Meeting of the North
American Fuzzy Information Processing
Society, August, 2012.
[18] A. Kumar, R. Kumar, and S. S. Sodhi,
“Intelligent privacy preservation electronic
health record framework using soft
computing,” Journal of Information and
Optimization Sciences, vol. 41, no. 7, 2020, pp.
1615-1632.
[19] S. Gambhir, S. K. Malik, and Y. Kumar, “Role
of soft computing approaches in healthcare
domain: A mini review,” Journal of Medical
Systems, vol. 40, no. 12, October 2016, pp. 1–
20.
[20] D. Marbury, “Six healthcare technologies
coming in the next 10 years,” February 2019,
https://www.managedhealthcareexecutive.com/
view/six-healthcare-technologies-coming-next-
10-years
[21] H. Malik, A. Iqbal, and A. K. Yadav 9eds.),
Soft Computing in Condition Monitoring and
Diagnostics of Electrical and Mechanical
Systems: Novel Methods for Condition
Monitoring and Diagnostics. Springer, 2020.
[22] A. M. Mishra, G. Suseendran, T. N. Phung, Soft
Computing Applications and Techniques in
Healthcare. Boca Raton, FL: CRC Press, 2020.
[23] M. Gui et al., Computational Intelligence and
Soft Computing Applications in Healthcare
Management Science. IGI Global, 2020.
[24] R. Ali and M. M. S. Beg, Applications of Soft
Computing for the Web. Springer 2017.
[25] P. Debnath and S. A. Mohiuddine (eds.), Soft
Computing Techniques in Engineering, Health,
Mathematical and Social Sciences. Boca Raton,
FL: CRC Press, 2022.
[26] F. Saeed et al. (eds.), Recent Trends in Data
Science and Soft Computing: Proceedings of
the 3rd International Conference of Reliable
Information and Communication Technology.
Springer 2019.
[27] S. Borah and R. Panigrahi (eds.), Applied Soft
Computing: Techniques and Applications.
Apple Academic Press, 2022.

Figure 1 The key segments of the healthcare industry [3].
Figure 2 Comparing hard computing with soft computing [5].
Figure 3 Soft computing approaches [7]

Essence of Soft Computing in Healthcare

More Related Content

What's hot (20)

Similar to Essence of Soft Computing in Healthcare (20)

More from ijtsrd (20)

Recently uploaded (20)

Essence of Soft Computing in Healthcare