Hindawi

Journal of Healthcare Engineering

Volume 2021, Article ID 6635463, 14 pages
https://doi.org/10.1155/2021/6635463

Review Article
Big Data, Extracting Insights, Comprehension, and Analytics in
Cardiology: An Overview

Hui Xiao ,1 Sikandar Ali ,2 Zhen Zhang,1 Muhammad Shahzad Sarfraz,3 Fang Zhang,1
and Mohammad Faisal 4
1
Zhongnan Hospital of Wuhan University, Information Center, Wuhan 430071, China
2
Department of Computer Science and Technology, China University of Petroleum-Beijing, Beijing 102249, China
3
Department of Computer Science, National University of Computer and Emerging Sciences Islamabad,
Chiniot-Faisalabad Campus, Chiniot, Pakistan
4
Department of Computer Science and Information Technology, University of Malakand, Chakdara, Pakistan

Correspondence should be addressed to Hui Xiao; [email protected] and Sikandar Ali; [email protected]

Received 8 December 2020; Revised 9 January 2021; Accepted 20 January 2021; Published 31 January 2021

Academic Editor: Iván Garcı́a-Magariño

Copyright © 2021 Hui Xiao et al. This is an open access article distributed under the Creative Commons Attribution License,
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Healthcare system facilitates the treatment of patients with the support of wearable, smart, and handheld devices, as well as many
other devices. These devices are producing a huge bulk of data that need to be moulded for extracting meaningful insights from
them for the useful use of researchers and practitioners. Various approaches, methods, and tools are in use for doing so and to
extract meaningful information in the field of healthcare. This information is being used as evidence to further analyze the data for
the early care of patient and to devise treatment. Early care and treatment can facilitate healthcare and the treatment of the patient
and can have immense potentiality of dropping the care cost and quality refining of care and can decrease waste and chances of
error. To facilitate healthcare in general and cardiology in specific, the proposed study presents an overview of the available
literature associated with big data, its insights, and analytics. The presented report will help practitioners and researchers to devise
new solutions for early care in healthcare and in cardiology.

1. Introduction and its provision. Medical big data is produced from the
communication and digitization in healthcare. Healthcare
The increase in use of smart devices such as sensor, actuator, providers and hospital industry provide a huge amount of
and wearable devices, as well as other devices, has produced data from other segments, such as medical equipment,
massive amount of data that need to be shaped in a structure medical insurance medical research, and life science. Huge
way to mine the information and useful insights for the amount of data exists, which grasps the potential of support
useful use of research and practice. This increase of infor- of healthcare and medical tasks. The integration of machine
mation can yield research issues and challenges as extracting learning, artificial intelligence, and advanced analytics offers
useful information becomes a challenging task for research. numerous opportunities for transmuting such data into
The useful insights once drawn in a successful way can actionable and expressive insights for supporting decision-
ultimately care the patient and provide effective treatment in making. This can ultimately make availability of patient care
the early stage. Diverse approaches, methods, and mecha- at high quality and real-time situation response and can
nisms are in practice to tackle the issues of big data and its protect lives on the clinical side and develop the services and
analytics in the field of healthcare in general and cardiology processes, improve the use of resources, and minimize the
in specific. costs on the maintenance and financial front [1, 2].
The role of data processing and information in health- With the rise of advanced approaches such as analytical
care has always been vital in healthcare for decision-making techniques and approaches, the stakeholders of healthcare
2 Journal of Healthcare Engineering

can not only connect the data power for historical analysis of learning approaches and artificial intelligence in cardio-
data but also predict future outcomes with predictive ana- vascular medicine. The effects of emerging technologies on
lytics for defining best accomplishment for present situation cardiovascular medicine are emphasized for providing un-
[3, 4]. Conventionally, the practitioners of clinic rely on derstanding to the clinical practice and to find probable
reserved information accessible to them and their past in- patient assistances. Nazir et al. [12] provided a wide-ranging
volvement for treatment of patients. Data availability from overview of the available big data studies in cardiology. The
diverse sources deals with the chance to have a complete study followed a protocol of systematic literature review for
thought of patient well-being. The use of cutting-edge presenting the published material from 2008 till 2018 as-
technologies against such data aids access to the appropriate sociated with big data features, applications, and analytics in
information at precise place and accurate time for delivering cardiology field. The authors identified 190 potential studies
precise care [5]. and analyzed them. These studies were published in con-
The proposed study presents an overview of the available ferences, books, journals, and many other online materials.
literature associated with big data, its insights, and analytics. The study was presented as an evidence for the researchers
The process of search for the proposed study was done in the and practitioners to devise novel solutions in the area of
popular libraries with the aim of obtaining associated ma- interest. Nazir et al. [13] presented a comprehensive review
terials. The presented report will help practitioners and of the 10 years from 2008 to 2018 associated with the vi-
researchers to devise new solutions for early care in sualization of big data in the area of cardiology. The study
healthcare and in cardiology. identified 53 prospective papers related to visualization of
The remainder of the paper is organized as follows: big data in cardiology. The study was based on protocol with
Section 2 presents the interrelated research to current study. defined research questions, inclusion and exclusion criteria,
Section 3 presents library-based search process for the and quality criteria. These identified studies were analyzed
proposed study. Section 4 concludes the paper. according to the defined research questions. The study
highlighted the increase of the number of researches in the
2. Related Work area and focused on further research and innovations in the
field. These studies were done in order to support the usage
Several approaches have been in practice to tackle diverse of big data in healthcare.
issues of big data and its analytics in healthcare. Pevnick et al. Bizopoulos and Koutsouris [14] surveyed applications of
[6] offered a review that discusses the current and upcoming deep learning that uses structured data and signal and
devices intended for measuring the actions of heart rhythm, imaging modalities from cardiology. The benefits and lim-
heart rate, and thoracic fluid. Various frameworks were itations of applications of deep learning in cardiology and in
presented, which classify and understand the wearable de- medicine in general are discussed. Cannière [15] examined
vices. Mehta et al. [7] presented a systematic mapping study the developments of heart rate variability factors during
for analyzing and identifying the research studies on ana- short-term interval all the way through cardiac rehabilita-
lytics of big data and use of artificial intelligence in tion. Electrocardiography signals, documented with the help
healthcare. The study identified 2421 papers for the year’s of wearable device in 129 patients following cardiac reha-
ranges from 2013 to February 2019. These papers were bilitation program, were analyzed. The findings of the study
evaluated, and the results show that the study will support present appreciated insights into disease monitoring during
the necessity in the use of technologies in healthcare. Ati- cardiac rehabilitation in future application.
tallah et al. [8] surveyed the literature associated with the DL
and IoT applications for smart cities’ developments. Initially, 3. Library-Based Search Process
the basics of IoT were defined followed by the characteristics
of IoT-produced big data. After that, the various structures This study offers to present an overview of the existing
used for analytics of IoT big data were presented. The approaches and methods for big data, its analytics, and
common DL models were surveyed and reviewed the current insights in cardiology. Various popular libraries such as
research employing the IoT and DL for developing services ScienceDirect, IEEE, Springer, and Wiley were searched with
and smart applications for smart cities. The existing issues the aim of obtaining associated materials interconnected to
and challenges encountered throughout the smart city’s the current study. The information gathered from these
development were outlined. Kazmierska [9] presented a libraries was analyzed and presented from different per-
study on the needs of community in translating multisource spectives in the form of different tables and figures. This
data into clinical decision aids. information includes the type of article, number of publi-
Ben-Assuli et al. [10] demonstrated power prediction of cations, topics covered, subject areas, and publication titles.
four popular algorithms and matched their accuracy in Initially, the library of ScienceDirect was checked and the
congestive heart failure predicting initial patient mortality. following information was obtained. Figure 1 depicts the
The results show that the current models outperform those types of articles with publications. The figure shows that a
described in the literature. The results further support the bigger number of publications were in the form of research
policy-makers in allocation of resources for establishment of article.
comprehensive systems of integrated health IT aiming at Figure 2 presents the articles in total with the given year.
simplification of analytics of ML. Dipti Itchhaporia [11] More publications are shown in the year 2020, which shows
analyzed the existing application and state of machine the increase in number of researches.
Journal of Healthcare Engineering 3

120
100

Number of papers
80
60
40
20
0

Encyclopedia

Conference abstracts

Discussion

Editorials
Research articles

Book chapters

Mini reviews

Practice guidelines

Short communicatuions

Others
Review articles

Article type
Figure 1: Article types.

No. of papers

14%

32%

18%

17% 19%

2020 2017
2019 2016
2018
Figure 2: Number of papers published.

Figure 3 depicts the subject areas with the number of The discipline with the total number of articles is shown
publications. in Figure 8. The purpose of this search was to identify the
The library of IEEE was searched for the purpose of disciplines covered by the area.
identifying relevant information. Figure 4 represents the The libraries of Wiley and Taylor & Francis were also part
information of publication topics with the total number of of the proposed study. These libraries were searched for rel-
articles published. evant information and analysis. Figure 9 depicts the publication
The paper type and total number of publications in the types with total number of articles published. In the figure, it is
same library are shown in Figure 5. shown that more papers are published with type journal.
Figure 6 presents the conference location with the Figure 10 presents the number of publications in the
number of publications. given years from 2016 till 2020.
After this, the library of Springer was searched to view After the statistics were obtained, the papers were
the information for the purpose of analysis. Figure 7 reviewed and the details with short descriptions of the
depicts the type of articles with the number of papers were given. Table 1 shows the big data and its an-
publications. alytics in cardiology.
4 Journal of Healthcare Engineering

Medicine and dentistry

Biochemistry, genetics, and molecular
biology
Computer science
Nursing and health professions
Pharmacology, toxicology, and
pharmaceutical science
Social sciences
Engineering
Business, management, and accounting
Chemical engineering
Decision sciences
Figure 3: Subject area with number of articles.

Blood vessels
Signal classification
Medical diagnostic computing
Sleep
Photoplethysmography
Internet of things
Medical signal detection
Pneumodynamics
Medical information systems
Feature extraction
Publication topics

Data mining
Patient diagnosis
Medical disorders
Pattern classification
Cardiovascular system
Big data
Patient monitoring
Data analysis
Electrocardiography
Medical computing
Learning (artificial intelligence)
Health care
Medical signal processing
Diseases
Cardiology
0 10 20 30 40 50 60 70
Number of papers
Figure 4: Publication topic with number of articles.
 Total number

0
1
2
3
4
5
6
7
8
9
10
Rennes
Maastricht, Netherlands
Journal of Healthcare Engineering

Vancouver, BC
Chennai
Orlando, FL
Pisa, Italy
Xi'an, China

30%
Austin, TX, USA

Article
Chapter
Journal

Honolulu, HI
Conference

7%
Palladam
Palladam, India

3%
Singapore, Singapore
Sydney, NSW
No. of papers

Amsterdam
Book
Others

Bangalore

Conference location

Figure 7: Content type.

Beijing

60%

Conference paper
Berlin, Germany
Figure 5: Paper type with number.

Reference work entry

Calgary, AB
Chennai, India
Cochin, India

Figure 6: Conference location with number of articles.

Crans-Montana
Dublin, Ireland
East Sarajevo, Bosnia and …
Gdansk
Islamabad, Pakistan
5
6 Journal of Healthcare Engineering

Cardiology Internal medicine

Health informatics Medicine/public health, general
Artificial intelligence Biomedical engineering and
Computational intelligence bioengineering
Pharmacology/toxicology Imaging/radiology
Public health Biomedicine, general
Intensive/critical care medicine Statistics for life sciences, medicine,
Bioinformatics health sciences
Rheumatology Oncology
Health administration Geriatrics/gerontology
Neuroradiology General practice/family medicine
Big data Information systems and communication
Computational biology/bioinformatics service
Diagnostic radiology Proteomics
Health policy Communications engineering, networks
Health services research Computer communication networks
Innovation/technology management Endocrinology
Management of computing and Health promotion and disease prevention
information systems Information systems applications
Surgery (incl. internet)
Analytical chemistry Interventional radiology
Pediatrics
Ultrasound
Big data/analytics
Figure 8: Discipline with number of articles.
Journal of Healthcare Engineering 7

Reference
works
Books

Journals

Journals
Books
Reference works
Figure 9: Publication type with number of papers.

70
60
Number of articles

50
40
30
20
10

0
2016 2017 2018 2019 2020
Years
Figure 10: Publication in the year.

Table 1: Work in the area of big data and its analytics in cardiology.
Citation Method Description
Devices of wearable technology were intended for measuring
the heart rhythm, heart rate, activity, and thoracic fluid. For
[6] Wearable technology for cardiology
classification and understanding, a framework was given to the
wearable devices for improving healthcare.
475 papers from PubMed library were examined for solutions of
telemedicine to improve medication adherence of
cardiovascular disease patient. 74 articles were assessed. The
[16] Technology for cardiovascular disease patient articles exhibited that suggestions associated with solutions of
telemedicine are typically conflictive. The use of SMS was
considered for patients regarding their medication because of
forgetfulness.
A system of health proactive monitoring is planned for cardiac
patients. In the study, an electronic band is worn by the patient
and the real-time situation of health and system of e-health are
Big data for monitoring of proactive healthcare of patients of
[17] to process the obtained data from patient. The system supports
chronic diseases
the patient to take proactive process beside some of the
abnormal states in their health and further supports the doctors
to monitor the health of patient on a regular basis.
8 Journal of Healthcare Engineering

Table 1: Continued.
Citation Method Description
The research has established left ventricular volumes approach
Deep learning network in left ventricular volumes of identification without segmentation by deep learning
[18]
identification in cardiac MRI technology and the data set form large-scale cardiac MRI from
second annual data science bowl in 2016
The study offered review of the associated techniques of data
[19] Medical data mining and heart disease mining for finding of diseases classes and heart failure.
Additionally, emphasis is given on sequential mining.
The study presented summary of the fundamental notions in
[20] ML horizon in cardiac hybrid imaging
ML and its applications in standard cardiac imaging
Application of mobile for the patient of myocardial infarction
[21] Mobile heart rate monitoring system for patient of MI (MI) is presented to preserve heart rate tracking and with stress-
free pursuing for emergency support
Interviews in the two main cardiac hospitals of Sudan were led
and an exploratory study among the hospitals’ doctors was
[22] Clinical guidelines in cardiology run-through in Sudan
prepared for examining the perceptions of a huge population of
prescribers of the subject examined
Management of cardiac data and operative concept of
[23] Big health data remodelling to examine early symptoms of heart failure is
presented
The research censoriously reviewed the challenges of big data
Big health data records for early and late translational
[24] before time and after the event stages of research in translational
cardiovascular research
cardiovascular disease
The study examined the related woks on factorization of tensor
Factorization of tensor for precision medicine in failure of
[25] applications in the associated biomedical field of phenotyping
heart with preserved ejection fraction
and genotyping
The research led a study from January to April 2017 in Klang
Mobile messaging applications’ effect on knowledge of cardiac
Valley’s teaching hospital for determining the effect of mobile
[26] patients with risk of coronary artery disease and healthy
messaging applications on patients with coronary artery disease
lifestyle adherence
and observation of healthy life
The study observed the signal over digital signal processor and
then computed the blood oxygen saturation, heart rate, and
[27] SVM for classification of biomedical signal on IoT platform blood pressure. SVM was considered for the purpose of showing
the data and its classification into unhealthy, healthy, and very
unhealthy and designates accuracy of classification prediction.
Risk factors of heart failure and focus on prevention are
[28] Heart failure prevention
specified
The study presented summary of the collected works of
[29] Statistical shape models of the heart
statistical shape models in cardiac imaging
Classifying mining techniques for the accessible clarification Framework to use healthcare data for attributes based heart
[30]
for heart disease prediction disease prediction is presented in the study
Statistical based recommendation model for the patients of Smart system of recommendation is presented for patients with
[31]
heart disease heart disease in the fields of medical informatics and e-health
Modelling 4D for rapid assessment of biventricular function in The study has quantified 4D biventricular function from
[32]
congenital heart disease analysis of standard cardiac MRI
Applications of big database studies in cardiology were
[33] Big database applications and forthcomings in cardiology
presented in the study
The study presented an approach for identification of particular
[34] Approach of big data to myocyte membrane analysis pathological ion dynamics responsible for abnormal electrical
behaviour practiced through the experiment
The research inspected the patterns where the patients of heart
attack are transferred between the hospitals. The three key
factors in transferring destinations are:
Distance, quality, or relationship? Interhospital transfer of (i) The distance between sending and receiving in hospitals
[35]
patients with heart attack (ii) Widely reported quality measures of receiving hospitals as
specified by whether they are related with the same
multihospital system
(iii) The relationship between sending and receiving hospitals
Journal of Healthcare Engineering 9

Table 1: Continued.
Citation Method Description
Integrate the experimental results of the examination of ML
[36] Feature analysis and coronary artery heart disease data sets which are applied on varied data sets aiming at the coronary
artery heart disease
The paper has focused on the procedure of mapping ventricular
Mapping of ventricular tachycardia in patients with heart
[37] tachycardia; the conventional and novel technique of mapping
structural disease
and the details of some methodological tips are given
Saudi Arabian patients with HFpEF were examined with acute
Patients’ baseline characteristics with heart failure and
heart failure. The clinical characteristics, signs, and indications
[38] preserved ejection fraction during admission with acute heart
of heart failure, echocardiographic findings, and medications
failure in Saudi Arabia
during admission and at hospital discharge were determined.
The authors established a cardiovascular dysautonomias
identification system for the prediction of appropriate
Cardiovascular dysautonomias diagnosis and treatments
[39] treatments and diagnosis for patients with cardiovascular
through data mining
dysautonomias through the data set extracted from the ANS
unit of University Hospital Avicenne in Morocco
The research developed an adaptive energy resourceful
Approach of data transmission based on adaptive energy transmission system which can recognise the important events
[40]
efficiency for prediction of heart disease like myocardial infarction and reduce data transmission from
the devices
The study identified the analytics uses in big data for the
prevention and prediction of heart attack, privacy of the
[41] Analytics of big data in prediction of heart attack patients, and the challenges for the use of technology in big data.
The study analyzed the national and international databases for
the proposed study.
System of cloud-based investigation is intended for cardiac
images and link services of computation for remote sharing. A
[42] Cloud computing for myocardial fibre information in vivo
method for postprocessing of image is defined as important
service for obtaining information on in vivo myocardial fibres.
The research presented an algorithm to involuntarily identify
[43] Using big data for assessing the risks of arrhythmia
the R, S, and T wave peaks in epicardial electrogram signals
The study proposed that the cardiac biomechanics produce
ML framework and imaging based big data for rapid adequate information which can affect ML and framework of
[44]
phenotyping of left ventricular diastolic function big data analytics for function of automated left ventricular
diastolic assessment
The entity site-feature values are mined in triples in the report of
[45] Insights from echo reports of paediatric disease of heart echo and then on the ground of this prediction of the level of
risk
The technique of Bayesian belief networks is used. The approach
contains four phases; the first and second phases of the data are
preprocessed and a set of predictors are produced based on
Framework of probabilistic data driven for scoring the
[46] different variable selection method. The medically associated
preoperatives recipient-donor heart transplant survival
variables are added to the list of variables in the third phase, and
in the last phase the Bayesian belief networks technique is
applied.
The research presented a novel semiautomatically fuzzy
partition rules for facilitating an accurate and robust aspect into
cardiac arrhythmia. The approach of text mining is
Identification of heart arrhythmia through big data-based demonstrated and applied to large data set containing freely
[47]
extraction of fuzzy partition rules existing articles in the PubMed library. The information is
mined and then put to the experimental data and expert
information for facilitating robust system to tackle the issues
arising through the assessment of medical big data.
The research has established a central monitoring system for
patients of large set of health records as input. It is intended to
mine the essential information from large set of medical records
[48] Big data for prediction of heart disease through map reduction
through the method of map reduction. By using this approach, it
can be decided whether there is patient normality or
abnormality.
10 Journal of Healthcare Engineering

Table 1: Continued.
Citation Method Description
The authors studied the relations between cardiovascular risk
Cardiovascular risk clustering factors highlighted the coronary
[49] clustering and the discriminators of disease of cardiovascular
artery calcium as a strong clinical discriminator
factors
The current technological and clinical improvements
containing wearable health tracking devices, smartphone
[50] Mobile health initiatives for cardiovascular disease devices, and social media for supporting behaviour factors of
risk for cardiovascular disease in terms of smoking, physical
inactivity, and suboptimal nutrition
The study defined guidelines of what is to be required for
Sudden cardiac death with risk stratification and making the translational step, through the comparatively well
[51]
computational cardiology intended cases required or drug induced long QT as a case of
syndrome
The research presented various applications of smartphone
[52] Technology of smartphone in cardiology
based technologies in cardiology and gave a review of them
The study offered an overview of the existing associated works of
Visualization of cardiovascular MRI challenges and
[53] visualization approaches and emphasis on the visualizing
opportunities
imagery issues resulting from 2D myocardial tagging in CMR
The article’s purpose is the three encouraging big data
applications in cardiovascular care, with “proof-of-concept”
[54] Big data in cardiology
challenges to be met if the encouraging data is to be
comprehended
Cardiovascular medicine big data, health informatics, and The study offered a report on cardiovascular medicine big data,
[55]
future health informatics, and future
The objectives of the study are:
(a) to build an interactive and
(b) data visualization tool based on web MIMIC-II
Furthermore, the research mainly offered two features of
Tool for the MIMIC-II database, a web-based data exploration and comparison. The first feature helps the patient
[56]
visualization cohort within MIMIC-II and visualized the distribution of
various variables including administrative, clinical, and
demographic variables within the selected cohort. The second
feature helps the users in selection of two patient cohorts and
visual comparison with other variables.
The study designated various sources of big data in cardiology
[57] Connecting the dots: from big data to healthy heart followed by talk over the possibilities of building the best use of
data-driven knowledge production models
A web portal is employed for improved communications of
Libraries implementation of open-source data visualization of diabetes patients with doctors for the process of identification
[58]
web portal for patients of diabetes and handling of diabetes. Medical data are offered on the portal
based on open-source libraries.
The research discusses the details of diverse applications of
[52] Technology of smartphone in cardiology
technologies of smartphone in cardiology
SVM and Osuna were used for detecting the ischemic disease of
Machine learning approaches in detection of ischemic heart
[59] heart. The principal component analysis algorithm was also
disease
used.
The research offered a review on analytics of big data impact in
Paediatric cardiovascular disease in the era of transparency in
[60] paediatric cardiovascular disease and its possible issues of
healthcare using big data
transparency in distribution of care
[61] Data visualization: science on the map A tool box for data visualization
The paper discussed the following:
(i) Report on big data science research
[62] Harnessing the heart of big data (ii) Potential of data science to support examinations of
cardiovascular diseases
(iii) Challenges and opportunities
The chapter emphasizes on numerous existing solutions and
[63] 4D OCT in developmental cardiology gives review of the perspective in the evaluation of 4D OCT
imaging for cardiovascular system in the past several years
Journal of Healthcare Engineering 11

Table 1: Continued.
Citation Method Description
The research aims to offer a virtual human heart from medical
Kinect-based gesture prediction in volumetric visualization of
[64] imaging data with incorporation of collaborating interface using
heart from CMR imaging
visual 3D holographic, haptic, and sonic feedback
The research presented the existing data visualization uses and
[65] Feast for the eyes reviewed the probable issues, benefits, and applications of
libraries
Overview of the technological developments for volumetric
[66] Cardiac 4D ultrasound imaging
imaging of the heart beat with the support of ultrasound is given
The study presented Bayesian belief network containing four
phases. The data is preprocessed in the first two phases and
Probabilistic data-driven framework for scoring the
[67] produces a candidate set of predictors. Medical related variables
preoperative recipient-donor heart transplant survival
are added in the third phase and, finally, the model of Bayesian
belief network is applied.
The chapter discussed the visualization, analysis, and mining of
healthcare data and concludes the way in which data can be
[68] Health analytics
proficiently accomplished which further improves the ability of
organization to control risk, yield revenue, and cost
The paper presented cardiac electrical excitation propagation
model based on the data of human cardia cross-sectional to
discover the cardiac electrical activities. After that, biophysical
visualization method is applied for the biophysical integration
Electrophysiology-morphous merging of human heart based
[69] of cardiac anatomy and electrophysiological properties, which
on composite visualization approach
provide the equivalent position, spatial relationship, and the
whole process in 3D space with the context of anatomical
structure for giving the details of biophysical and
electrophysiological activity.
The paper determined the encouraging data sets for finding of
[70] Big data for cardiology: novel discovery? science and the impact on the approaches used in science in
general and explicitly in cardiology
The uses of algorithms and intelligent approaches of visualizing
[71] Visualization of medical volume though intelligent approaches medical big data are presented. The article discusses the existing
software and toolkits for visualization of medical volume.

Big data are considered to be the main asset of the Data Availability
organization for its successful operations and future en-
deavour [72–77]. No data were used to support this study.

4. Conclusion Conflicts of Interest

The authors declare no conflicts of interest.
Healthcare system facilitates the patients with the support of
wearable devices, smart devices, handheld devices, and many
other devices. These devices are producing a huge bulk of data References
that need to be moulded for extracting expressive insights from
them for the useful use of researchers and practitioners. Various [1] W. Raghupathi and V. Raghupathi, “Big data analytics in
healthcare: promise and potential,” Health Information Sci-
approaches, methods, and tools are in use for doing so and to
ence and Systems, vol. 2, no. 1, 2014.
extract meaningful information in the field of healthcare. This [2] D. W. Bates, S. Saria, L. Ohno-Machado, A. Shah, and
information is being used as evidence to further analyze the data G. Escobar, “Big data in health care: using analytics to identify
for the early care of patients and to devise treatment. Early care and manage high-risk and high-cost patients,” Health Affairs,
and treatment can facilitate healthcare and patient and can have vol. 33, no. 7, pp. 1123–1131, 2014.
immense potentiality of quality refining of care and lessen care [3] E. A. Mohammed, B. H. Far, and C. Naugler, “Applications of
cost and can decrease waste and chances of error. To facilitate the MapReduce programming framework to clinical big data
healthcare in general and cardiology in specific, the proposed analysis: current landscape and future trends,” BioData
study presents an overview of the existing literature associated Mining, vol. 7, no. 1, 2014.
with big data, its insights, and analytics. The presented report [4] Y. Wang and N. Hajli, “Exploring the path to big data ana-
will help practitioners and researchers to devise new solutions lytics success in healthcare,” Journal of Business Research,
for early care in healthcare and in cardiology. vol. 70, pp. 287–299, 2017.
12 Journal of Healthcare Engineering

[5] B. Kayyali, D. Knott, and S. V. Kuiken, “The big-data revo- [21] M. F. B. Mustapha and D. T. Anw, “Mobile heart rate monitor
lution in us health care: accelerating value and innovation,” for myocardial infarction patients,” in Proceedings of the 2017
McKinsey Co., pp. 1–6, 2013. 6th ICT International Student Project Conference (ICT-ISPC),
[6] J. M. Pevnick, K. Birkeland, R. Zimmer, Y. Elad, and I. Kedan, Skudai, Malaysia, May 2017.
“Wearable technology for cardiology: an update and frame- [22] H. Elsadig, M. Weiss, J. Scott, and R. Laaksonen, “Use of
work for the future,” Trends in Cardiovascular Medicine, clinical guidelines in cardiology practice inSudan,” Journal of
vol. 28, no. 2, pp. 144–150, 2018. Evaluation in Clinical Practice, vol. 24, no. 1, pp. 127–134,
[7] N. Mehta, A. Pandit, and S. Shukla, “Transforming healthcare 2018.
with big data analytics and artificial intelligence: a systematic [23] D. Seth, N. Biswas, and D. Ghosh, “Big health data: cardiac
mapping study,” Journal of Biomedical Informatics, vol. 100, remodelling and functional interactions of big brain based
p. 103311, 2019. implications in body sensor networks,” in Proceedings of the
[8] S. B. Atitallah, M. Driss, W. Boulila, and H. B. Ghézala, 2017 7th International Conference on Communication Systems
“Leveraging Deep Learning and IoT big data analytics to and Network Technologies, Nagpur, India, November 2017.
support the smart cities development: review and future di- [24] H. Hemingway, F. W. Asselbergs, J. Danesh et al., “Big data
rections,” Computer Science Review, vol. 38, Article ID from electronic health records for early and late translational
100303, 2020. cardiovascular research: challenges and potential,” European
[9] J. Kazmierska, “From multisource data to clinical decision Heart Journal, vol. 39, no. 16, pp. 1481–1495, 2018.
aids in radiation oncology: the need for a clinical data science [25] Y. Luo, F. S. Ahmad, and S. J. Shah, “Tensor factorization for
community,” Radiotherapy and Oncology, vol. 153, pp. 43–54, precision medicine in heart failure with preserved ejection
2020. fraction,” Journal of Cardiovascular Translational Research,
[10] O. Ben-Assuli, T. Heart, N. Shlomo, and R. Klempfner, vol. 10, no. 3, pp. 305–312, 2017.
“Bringing big data analytics closer to practice: a methodo- [26] Y. H. Tang, M. C. Chong, Y. P. Chua, P. L. Chui, L. Y. Tang,
logical explanation and demonstration of classification al- and N. Rahmat, “The effect of mobile messaging apps on
gorithms,” Health Policy and Technology, vol. 8, no. 1, cardiac patient knowledge of coronary artery disease risk
pp. 7–13, 2019. factors and adherence to a healthy lifestyle,” Journal of Clinical
[11] D. Itchhaporia, “Artificial intelligence in cardiology,” Trends Nursing, vol. 27, pp. 4311–4320, 2018.
in Cardiovascular Medicine, 2020, In press. [27] S.-W. Liou, D. Kurniadi, B.-R. Zheng, W.-Q. Xie, C.-J. Tien,
[12] S. Nazir, M. Nawaz, A. Adnan, S. Shahzad, and S. Asadi, “Big
and G.-J. Jong, “Classification of biomedical signal on IoT
data features, applications, and analytics in cardiology-A
platform using support vector machine,” in Proceedings of
systematic literature review,” IEEE Access, vol. 7,
IEEE International Conference on Applied System Innovation,
pp. 143742–143771, 2019.
Chiba, Japan, April 2018.
[13] S. Nazir, M. Nawaz Khan, S. Anwar et al., “Big data visual-
[28] Z. Taimeh, D. Duprez, and D. J. Garry, “Heart failure pre-
ization in cardiology-A systematic review and future direc-
vention,” Proceedings of the Congestive Heart Failure and
tions,” IEEE Access, vol. 7, pp. 115945–115958, 2019.
Cardiac Transplantation, vol. 6, no. 8, pp. 1120–1128, 2017.
[14] P. Bizopoulos and D. Koutsouris, “Deep learning in cardi-
[29] C. Piazzese, M. ChiaraCarminati, and E. G. Caiani, “Statistical
ology,” IEEE Reviews in Biomedical Engineering, vol. 12,
shape models of the heart: applications to cardiac imaging,” in
pp. 168–193, 2019.
[15] H. D. Cannière, “The progression of heart rate variability Statistical Shape and Deformation Analysis Methods,
parameters throughout cardiac rehabilitation,” Computing in pp. 445–480, Elseiver, Amsterdam, Netherlands, 2017.
Cardiology, vol. 8–11, pp. 1–4, 2019. [30] R. G. Saboji and P. K. Ramesh, “A scalable solution for heart
[16] R. W. Treskes, E. T. Van der Velde, J. W. Schoones, and disease prediction using classification mining technique,” in
M. J. Schalij, “Implementation of smart technology to im- Proceedings of the International Conference on Energy,
prove medication adherence in patients with cardiovascular Communication, Data Analytics and Soft Computing
disease: is it effective?” Expert Review of Medical Devices, (ICECDS-2017), Chennai, India, August 2017.
vol. 15, no. 2, pp. 119–126, 2018. [31] A. Mustaqeem, S. M. Anwar, A. R. Khan, and M. Majid, “A
[17] A. Naseer, B. Y. Alkazemi, and E. U. Waraich, “A big data statistical analysis based recommender model for heart dis-
approach for proactive healthcare monitoring of chronic ease patients,” International Journal of Medical Informatics,
patients,” in Proceedings of the 2016 Eighth International vol. 108, pp. 134–145, 2017.
Conference on Ubiquitous and Future Networks (ICUFN), [32] K. Gilbert, B. Pontre, C. J. Occleshaw, B. R. Cowan,
Vienna, Austria, July 2016. A. Suinesiaputra, and A. A. Young, “4D modelling for rapid
[18] G. Luo, G. Sun, K. Wang, S. Dong, and H. Zhang, “A novel left assessment of biventricular function in congenital heart
ventricular volumes prediction method based on deep disease,” The International Journal of Cardiovascular Imaging,
learning network in cardiac MRI,” in Proceedings of the 2016 vol. 34, no. 3, pp. 407–417, 2018.
Computing in Cardiology Conference (CinC), Vancouver, [33] K. T. Lee, A. L. Hour, B. C. Shia, and P. H. Chu, “The ap-
Canada, 2016. plication and future of big database studies in cardiology: a
[19] C. B. Rjeily, G. Badr, A. H. E. Hassani, and E. Andres, single-center experience,” Acta Cardiologica Sinica, vol. 33,
“Medical data mining for heart diseases and the future of no. 6, pp. 581–587, 2017.
sequential mining in medical field (machine learning para- [34] C. A. Ledezma, “A big data approach to myocyte membrane
digms),” Machine Learning Paradigms,Intelligent Systems analysis: using populations of models to understand the
Reference Library, vol. 149, pp. 71–99, 2018. cellular causes of heart failure,” in Proceedings of the Com-
[20] L. E. Juarez-Orozco, O. Martinez-Manzanera, S. V. Nesterov, puting in Cardiology, Vancouver, Canada, September 2017.
S. Kajander, and a. J. Knuuti, “The machine learning horizon [35] L. X. Lu and S. F. Lu, “Distance, quality, or relationship?
in cardiac hybrid imaging,” European Journal of Hybrid Interhospital transfer of heart attack patients,” Production and
Imaging, vol. 2, no. 15, pp. 1–15, 2018. Operations Management, vol. 27, no. 12, pp. 2251–2269, 2017.
Journal of Healthcare Engineering 13

[36] R. El-Bialy, M. A. Salamay, O. H. Karam, and M. E. Khalifa, calcium as a strong clinical discriminator,” Health and
“Feature analysis of coronary artery heart disease data sets,” in Technology, vol. 6, no. 3, pp. 159–165, 2016.
Proceedings of the International Conference on Communica- [50] B. Urrea, “Mobile health initiatives to improve outcomes in
tion, Management and Information Technology (ICCMIT primary prevention of cardiovascular disease,” Current
2015), Prague, Czech Republic, April 2015. Treatment Options in Cardiovascular Medicine, vol. 17, no. 12,
[37] H. Mizuno, “Mapping of ventricular tachycardia in patients pp. 1–12, 2015.
with structural heart disease,” Journal of Arrhythmia, vol. 30, [51] A. P. Hill, M. D. Perry, N. Abi-Gerges et al., “Computational
no. 4, pp. 283–291, 2014. cardiology and risk stratification for sudden cardiac death:
[38] S. Abohammar, M. A. ElSaidy, D. Fathalla, and M. Aldosarri, one of the grand challenges for cardiology in the 21st century,”
“Baseline characteristics of patients with heart failure and The Journal of Physiology, vol. 594, no. 23, pp. 6893–6908,
preserved ejection fraction at admission with acute heart 2016.
failure in Saudi Arabia,” The Egyptian Heart Journal, vol. 69, [52] H. H. Nguyen and J. N. A. A. Silva, “Use of smartphone
no. 1, pp. 21–28, 2017. technology in cardiology,” Trends in Cardiovascular Medicine,
[39] A. Idri and I. Kadi, “A data mining-based approach for vol. 26, no. 4, pp. 376–386, 2016.
cardiovascular dysautonomias diagnosis and treatment,” in [53] S. Walton, K. Berger, J. Thiyagalingam et al., “Visualizing
Proceedings of the 2017 IEEE International Conference on cardiovascular magnetic resonance (CMR) imagery: chal-
Computer and Information Technology, Helsinki, Finland, lenges and opportunities,” Progress in Biophysics and Mo-
August 2017. lecular Biology, vol. 115, no. 2-3, pp. 349–358, 2014.
[40] A. B. Christian, L. Sharma, and S.-L. Wu, “AED: adaptive [54] R. U. Shah and J. S. Rumsfeld, “Big data in cardiology,”
energy-efficient data transmission scheme for heart disease European Heart Journal, vol. 38, no. 24, pp. 1865–1867, 2017.
detection,” in Proceedings of the 2017 IEEE 15th International [55] J. Kim, “Big data, health informatics, and the future of car-
Conference on Dependable, Autonomic and Secure Computing, diovascular medicine,” Journal of the American College of
15th International Conference on Pervasive Intelligence and Cardiology, vol. 69, no. 7, pp. 899–902, 2017.
Computing, 3rd International Conference on Big Data Intel- [56] J. Lee, E. Ribey, and J. R. Wallace, “A web-based data visu-
ligence and Computing and Cyber Science and Technology alization tool for the MIMIC-II database,” BMC Medical
Congress, Orlando, FL, USA, November 2017. Informatics and Decision Making, vol. 16, no. 15, pp. 1–8, 2016.
[41] C. A. Alexander and a. L. Wang, “Big data analytics in heart [57] E. Lau, K. E. Watson, and P. Ping, “Connecting the dots,”
attack prediction,” Journal of Nursing and Care, vol. 6, no. 2, Circulation, vol. 134, no. 5, pp. 362–364, 2016.
pp. 1–9, 2017. [58] G. Kopanitsa, A. Karpov, G. Lakovenko, and A. Laskovenko,
[42] Q. Wang, W. Xiong, Y. Zhang et al., “Remote analysis of “Implementation of a web portal for diabetes patients using
myocardial fiber information in vivo assisted by cloud open source data visualization libraries,” Studies in Health
computing,” Future Generation Computer Systems, vol. 85, Technology and Informatics, vol. 224, pp. 189–194, 2016.
pp. 146–159, 2018. [59] M. Ciecholewski, “Ischemic heart disease detection using
[43] C. A. Ledezma, “Evaluating the risks of arrhythmia through selected machine learning methods,” International Journal of
big data: automatic processing and neural networks to classify Computer Mathematics, vol. 90, no. 8, pp. 1734–1759, 2013.
epicardial electrograms,” in Proceedings of the Computing in [60] A. Asante-Korang and J. P. Jacobs, “Big Data and paediatric
Cardiology 2017, Rennes, France, September 2017. cardiovascular disease in the era of transparency in health-
[44] A. M. S. Omar, “Imaging based big data and machine learning care,” Cardiology in the Young, vol. 26, no. 8, pp. 1597–1602,
framework for rapid phenotyping OF left ventricular diastolic 2016.
function,” Journal of the American College of Cardiology, [61] M. Zastrow, “Data visualization: science on the map, Easy-to-
vol. 67, no. 13, p. 1614, 2016. use mapping tools give researchers the power to create
[45] Y. Shi, “Automatic knowledge extraction and data mining beautiful visualizations of geographic data,” Nature Inter-
from echo reports of pediatric heart disease: application on national Weekly Journal of Science, vol. 519, no. 7541, pp. 1-2,
clinical decision support,” in Proceedings of the Chinese 2015.
Computational Linguistics and Natural Language Processing [62] S. B. Scruggs, “Harnessing the heart of big data,” Circulation
Based on Naturally Annotated Big Data, Changsha, China, Research, pp. 1–11, 2015.
October 2015. [63] M. W. Jenkins and A. M. Rollins, “4-D OCT in developmental
[46] A. Dag, K. Topuz, A. Oztekin, S. Bulur, and F. M. Megahed, “A cardiology,” Optical Coherence Tomography, vol. 116,
probabilistic data-driven framework for scoring the preop- pp. 2003–2023, 2015.
erative recipient-donor heart transplant survival,” Decision [64] A. H. Basori, M. R. B. D. A. Kadir, R. M. Ali, F. Mohamed, and
Support Systems, vol. 86, pp. 1–12, 2016. S. Kadiman, “Kinect-based gesture recognition in volumetric
[47] O. Behadada, M. Trovati, M. Chikh, and N. Bessis, “Big data- visualisation of heart from cardiac magnetic resonance
based extraction of fuzzy partition rules for heart arrhythmia (CMR) imaging,” Virtual, Augmented Reality and Serious
detection: a semi-automated approach,” Concurrency and Games for Healthcare 1, Intelligent Systems Reference Library,
Computation: Practice and Experience, vol. 28, no. 2, vol. 68, pp. 79–92, 2014.
pp. 360–373, 2016. [65] T. J. Brigham, “Feast for the eyes: an introduction to data
[48] G. Vaishali and V. Kalaivani, “Big data analysis for heart visualization,” Medical Reference Services Quarterly, vol. 35,
disease detection system using map reduce technique,” in no. 2, pp. 215–223, 2016.
Proceedings of the 2016 International Conference on Com- [66] J. D’hooge, “Cardiac 4D ultrasound imaging,” in Biomedical
puting Technologies and Intelligent Data Engineering Image Processing, Biological and Medical Physics, Biomedical
(ICCTIDE’16), Kovilpatti, India, January 2016. Engineering, pp. 81–104, Springer, Berlin, Germany, 2011.
[49] C. M. Bucci, W. E. Legnani, and R. L. Armentano, “Clustering [67] A. Dag, K. Topuz, A. Oztekin, S. Bulur, and F. M. Megahed, “A
of cardiovascular risk factors highlighted the coronary artery probabilistic data-driven framework for scoring the
14 Journal of Healthcare Engineering

preoperative recipient-donor heart transplant survival,” De-

cision Support Systems, vol. 86, pp. 1–12, 2018.
[68] P. M. Griffin, H. B. Nembhard, C. J. DeFlitch, N. D. Bastian,
H. Kang, and D. A. Muñoz, “Health analytics,” in Healthcare
Systems EngineeringEuropian society of cardiology, Sophia
Antipolis, France, 2016.
[69] F. Yang, “A composite visualization method for electro-
physiology-morphous merging of human heart,” BioMed Eng
OnLine, vol. 16, no. 70, pp. 1–16, 2017.
[70] V. Mayer-Schönberger, “Big Data for cardiology: novel dis-
covery?” European Heart Journal, vol. 37, no. 12,
pp. 996–1001, 2016.
[71] Y. Abdallah, A. Abdelhamid, T. Elarif, and A.-B. M. Salem,
“Intelligent techniques in medical volume visualization,”
Procedia Computer Science, vol. 65, pp. 546–555, 2015.
[72] S. Nazir, S. Khan, H. U. K. S. Ali, I. Garcı́a-Magariño,
R. B. Atan, and M. Nawaz, “A comprehensive analysis of
healthcare big data management, analytics and scientific
programming,” IEEE Access, vol. 8, 2020.
[73] A. U. Haq, “Intelligent machine learning approach for ef-
fective recognition of diabetes in the e-healthcare using
clinical data,” Sensors, vol. 20, no. 9, p. 2649, 2020.
[74] S. Khan, S. Nazir, I. Garcı́a-Magariño, and A. Hussain, “Deep
learning based urban big data fusion in smart cities: towards
traffic monitoring and flow-preserving fusion,” Computers &
Electrical Engineering, vol. 89, Article ID 106906, 2020.
[75] X. Liao, S. Nazir, Y. zhou, M. Shafiq, and X. Qi, “User
knowledge, data modelling and visualization- handling
through fuzzy logic based approach,” Journal of Structural
Geology, vol. 141, 2020.
[76] S. Nazir, S. Ali, M. Yang, and Q. Xu, “Deep learning algo-
rithms and multi-criteria decision making used in big data- a
systematic literature review,” Complexity, vol. 2020, Article ID
2836064, 18 pages, 2020.
[77] J. Chi, Y. Li, J. Huang et al., “A secure and efficient data
sharing scheme based on blockchain in industrial Internet of
things,” Journal of Network and Computer Applications,
vol. 167, p. 102710, 2020.