Published at : 31 Oct 2023
Volume : IJtech
Vol 14, No 6 (2023)
DOI : https://doi.org/10.14716/ijtech.v14i6.6643
Laila Baloch | Department of Computer Engineering, Balochistan University of Information, Technology, Engineering and Management Sciences, Quetta 87650, Pakistan |
Sibghat Ullah Bazai | Department of Computer Engineering, Balochistan University of Information, Technology, Engineering and Management Sciences, Quetta 87650, Pakistan |
Shah Marjan | Department of Software Engineering, Balochistan University of Information, Technology, Engineering and Management Sciences, Quetta 87650, Pakistan |
Farhan Aftab | Department of Computer Engineering, Balochistan University of Information, Technology, Engineering and Management Sciences, Quetta 87650, Pakistan |
Saad Aslam | Department of Computing and Information Systems, School of Engineering and Technology, Sunway University, Selangor 47500, Malaysia |
Tse-Kian Neo | CAMELOT, Faculty of Creative Multimedia, Multimedia University, Cyberjaya 63100, Selangor, Malaysia |
Angela Amphawan | Department of Computing and Information Systems, School of Engineering and Technology, Sunway University, Selangor 47500, Malaysia |
The healthcare sector produces an enormous amount of
complicated data from several sources, such as health monitoring systems,
medical devices, and electronic health records. Big data analytics may improve
healthcare by enabling more effective decision-making, improving patient
outcomes, and reducing costs. To improve the operational efficiency of
healthcare organizations, scientific studies must search for the
standardization and integration of data analysis equipment and methods. This
systematic literature review aims to provide current insights on the topic by
analyzing a total of 60 relevant articles published between 2017 and 2023. The
review explores the challenges and opportunities in using big data in
healthcare, including data security, privacy, data quality, interoperability,
and ethical considerations. The article also explores big data analytics'
potential uses in healthcare, such as personalized treatment, disease
prediction and prevention, and population health management. It provides significant
insights for healthcare providers, researchers, and practitioners to make
evidence-based decisions, as well as underlines the need for more research in
this area to fully realize the promise of big data in healthcare.
Artificial Intelligence; Big data analysis; Big data in healthcare; Healthcare
The amount of data generated by several public and
private sector industries have grown exponentially. As more individuals
participate in the generation of Big Data (BD), it becomes essential to
establish a clear definition of BD and comprehend its implications. According
to (Dash et al., 2019), BD refers to a massive amount of information
generated, stored, and analyzed by diverse industries to enhance the services
they offer. This data contains structured, semi-structured, and unstructured
forms and originates from a multitude of sources, showing an increasing
frequency and size. Due to the size and complexity of this BD, traditional data
processing systems are inadequate for handling it, requiring the use of
specialized tools and techniques to extract valuable insights from it. BD has
become increasingly relevant in healthcare as it can improve patient outcomes,
incre- ase efficiency, reduce costs and facilitate medical research. To achieve
ethical data use, its implementation must be properly planned and
executed
Big data is categorized using various "Vs,"
with three core ones being size, speed, and diversity. Gartner defines big data
as information assets with substantial volume, velocity, and/or variety. These
aspects demand cost-efficient and inventive approaches to information handling,
enhancing understanding, decision-making, and process automation (Abdalla, 2022). The
collection of "Vs" related to big data includes the following:
Healthcare big data (BD) can be categorized into four
primary sources. Firstly, medical data includes individual patient health
information obtained from records, often collected from public health and
medical records. Secondly, public health data encompasses publicly available
health-related information and lifelong health records. Thirdly, medical images
provide visual insights into the body's interior, while electrocardiogram
recordings offer graphical representations of heart activity. Lastly, data from
medical experiments and literature supports the evaluation of new treatments
through research articles. Figure 1 provides a visual overview of these
healthcare big data types (Roham, Gabrielyan, and
Archer, 2021).
Big data analytics (BDA) uncovers
patient data patterns for personalized treatment and population health
monitoring, aiding disease detection. However, ethical, privacy and technical
issues in BDA pose challenges. Addressing them is vital for healthcare improvement.
Protecting patient data is essential. Despite challenges, BDA enhances patient
care (Jayasri and Aruna, 2022; Imamalieva, 2022; Khanra et
al., 2020; Hassan et al., 2019; Dash et al., 2019).
Research
concerning the use of BDA in healthcare often addresses common matters but
lacks an in-depth analysis from high-quality studies. While many studies assess
sources, technologies, benefits, and challenges, few evaluate the quality of
the examined documents (Khanra et al., 2020). Further
investigation is required to identify common contexts where BDA finds
application in healthcare. This study aims to provide comprehensive summaries
of research topics, trends, challenges, and potential solutions related to the
impact of big data on global healthcare.
The following section presents the detailed literature review, whereas section 3 discusses methodology and analysis procedure, sources of big data papers, phases of systematic literature, and protocol for systematic literature review. Section 4 presents the quality assessment. The next section answers our research questions and the latest trends/ innovations that can be used to address big data needs. Section 6 provides a comprehensive discussion of the findings, while the last section concludes this article.
Figure 1 Illustrates the major types of BD in the healthcare industry
2. Literature Review
Big data analytics has numerous
applications in healthcare with the expanding volume of big data in this
context (Hassan et al., 2019).
BDA can be used to monitor the spread of diseases and predict outbreaks by
analyzing large datasets from a variety of sources, including social media,
public health monitoring systems, and electronic health records. BD can assist
medical professionals in creating customized treatment strategies by analyzing
data from genetic tests, medical history, lifestyle factors, and other sources
to identify the most effective treatments for individual patients (Hassan
et al., 2022). Healthcare providers with
real-time decision support by analyzing patient data and providing
recommendations based on evidence-based medicine. To identify and stop
healthcare fraud through the analysis of BD and identifying patterns that may
indicate fraudulent activities.
2.1. Impact of big data on healthcare
The significance of BD in the healthcare system is immense, as it could
change the way healthcare is managed, evaluated, and delivered. Here are some
key reasons why big data is significant in healthcare (Cozzoli et al., 2022).
Improving Patient Outcomes: BD aids healthcare practitioners in devising more
efficient treatment plans and predicting potential health risks. Cloud-based
remote patient monitoring models enable real-time health tracking, which is
particularly beneficial for elderly patients living alone
(Hassan et al., 2019).
Improving Population Health: BD analysis of large datasets helps uncover trends
and patterns that inform public health strategies and policies. It supports
rapid decision-making during crises, such as tracking movements during the
COVID-19 pandemic.
Optimizing Resource Allocation: BD optimizes resource usage, enhancing
healthcare delivery by efficiently managing staff, facilities, and equipment.
This leads to cost savings and improved effectiveness.
Personalizing Medicine: BD enables the creation of personalized treatment plans by analyzing
patient data, including genetics and lifestyle factors. It guides
individualized medical assessments and treatment strategies, improving outcomes
and reducing risks (Hassan et al., 2022).
Supporting Clinical Decision-Making: Real-time BD enhances clinical decisions, improving
patient care. Integrating BD into healthcare is vital (Karatas
et al., 2022). BD, AI, and IoT
aided COVID-19 tracking and health monitoring (Ahmed et
al., 2021). BD's impact spans personalized
treatment, resource optimization, and real-time insights (Bag et al., 2023).
2.2. Big Data management and
analysis
Efficient
big data analysis and decision-making require effective data management,
particularly in critical fields like healthcare. In this context, three
prominent platforms play significant roles: Hadoop, Apache Spark, and Apache
Kafka. Hadoop, an open-source distributed application, excels at managing
massive data across multiple machines, making it invaluable during
data-intensive events such as pandemics (Harb et al., 2020; Yuvaraj and SriPreethaa, 2019). Apache Spark is a versatile computing platform capable
of handling vast datasets across various sectors, offering support for a wide
range of data processing tasks. On the other hand, Apache Kafka is a
distributed streaming platform that constructs real-time data pipelines and is
crucial for real-time data processing and data exchange among different
systems. These platforms collectively address the challenges of data management
and computation in the era of big data (Harb et al., 2020; Liang et al., 2020; Dash et al.,
2019; Harerimana et al., 2018).
An SLR technique built on
Kitchenham's concepts is applied to the proposed research (Kitchenham et al., 2009). The process of the
systematic literature review method is outlined in the following sections.
3.1. Research Questions
This review article addresses the
following research questions:
RQ1. What is the significance of big data in healthcare?
RQ2. What are the research areas or trends that have emerged since 2017?
RQ3. What are the challenges and possible solutions to address these
challenges?
3.2. Selection and analysis procedure
A snowballing approach is used as a starting point for conducting a literature study. Uses references and citations to identify additional sources, also known as backward and forward snowballing. Figure 2 illustrates the snowballing procedure.
Figure 2
Snowballing procedure
3.3. Research Process
The
analysis procedure is a manual search of conference proceedings and journal
publications since 2017. 60 journals and conferences have been selected. Subsequently,
we analyzed papers that addressed the literature survey questions, including
the exclusion and inclusion of certain papers during this stage.
3.4. Sources of articles
Various
academic databases, including Google
Scholar, IEEE Xplore, ResearchGate, and Scopus, were utilized to
search for relevant articles.
3.5. Inclusion criteria
We
conducted a study focusing on healthcare-related articles pertaining to big
data, data analytics, ML, and AI.
Following the PRISMA guidelines (Rahmadian, Feitosa,
and Zwitter, 2022), we
filtered results from 2017 to 2023, specifically focusing on articles in the
English language.
3.6. Exclusion criteria
·
Studies that were not
peer-reviewed or were not available in full text.
·
Articles not written in the English language.
3.7. PRISMA flow diagram and
Phases of systematic literature review
The
PRISMA procedure was followed, as depicted in Figure 3, and the publications
were filtered based on the following criteria:
1. During the 'Identification' stage, journal and conference papers
relevant to the topic of big data were identified and subsequently included.
2. The screening step filtered out publications based on the titles and
abstracts.
3. In the eligibility step, publications were excluded based on the whole
text.
The result has a total of over 60 articles and proceedings available for analysis.
Figure 3 PRISMA flow diagram
3.8. Research Criteria
Analyze only scholarly works with
healthcare and big data in title, abstract, or keywords. Focus on four aspects:
data sources, approaches, purposes, and applications.
3.9. Protocol
for systematic literature review
A standardized data extraction form collected author(s),
publication year, title, thesis, method, results, and limitations. Data was
synthesized and analyzed to identify recurring themes and patterns.
4. Quality
Assessment
The studies' quality was assessed by considering factors like research
question clarity, methodology appropriateness, and findings validity. This
process aimed to identify unbiased studies to ensure reliable conclusions. The
selected items were evaluated for transparency and impartiality, with a quality
score calculated for each article using criteria from (Behera,
Bala, and Dhir, 2019) and (Tandon et al., 2020).
Table 1 Criteria for Quality Evaluation (QE)
QE# |
Criteria |
QE1 |
Analyses categorized as: quantitative
= "+2", qualitative = "+1.5", no evidence =
"+0". |
QE2 |
Discussing advantages and
challenges: Yes = "+2", Partial = "+1.5", No =
"+0". |
QE3 |
Results alignment
with methodology: Yes = "+2", Partial = "+1.5", No =
"+0". Note: Partial explanation means inadequate
method justification. |
QE4 |
Source reliability
and peer review: "+2" if
citations + H Index > 100. "+1.5" if
citations + H Index between 50 and 99. "+1.0" if
citations + H Index between 1 and 49. "+0" if citations + H Index = 0. |
QE5 |
Comparison with prior
methods: Yes (+1), No (+0). |
Initially, 55 articles were found via
keyword search, reduced to 45 after removing duplicates. Quality was assessed
using a score (QS) from Table 2, with 12 studies scoring 9. Additional articles
were found through citations. Those above 4.5 were relevant, while 9 and 8
scores were highly reliable for inclusion in the literature. (Behera, Bala, and Dhir, 2019).
Table 2 Computation of Quality Score (QS)
S.# |
Reference |
Total Citations |
Quality Evaluation (QE)
|
Average citations | |||||
QE1 |
QE2 |
QE3 |
QE4 |
QE5 |
QS | ||||
1 |
(Jayasri and Aruna, 2022) |
9 |
2 |
1.5 |
2 |
1 |
1 |
7.5 |
4.5 |
2 |
(Batko and ?l?zak, 2022) |
32 |
2 |
2 |
2 |
1 |
0 |
7 |
32 |
3 |
(Liang et
al., 2020) |
11 |
2 |
1.5 |
1.5 |
1 |
0 |
6 |
5.7 |
4 |
(Kim and Chung, 2019) |
56 |
2 |
2 |
2 |
1.5 |
1 |
8.5 |
14 |
5 |
(Pham et
al., 2020) |
226 |
2 |
1.5 |
2 |
2 |
0 |
7.5 |
75.3 |
6 |
(Deepa et
al., 2022) |
237 |
2 |
2 |
2 |
2 |
1 |
9 |
237 |
7 |
(Wang et
al., 2023) |
0 |
2 |
2 |
2 |
0 |
1 |
7 |
0 |
8 |
(Xing and Bei, 2020) |
139 |
2 |
2 |
2 |
2 |
1 |
9 |
34.7 |
9 |
(Demirbaga and Aujla, 2022) |
3 |
2 |
2 |
2 |
1 |
1 |
8 |
3 |
10 |
(Ghayvat et
al., 2022) |
62 |
2 |
1.5 |
2 |
1.5 |
1 |
8 |
31 |
11 |
(Puthal, 2019) |
28 |
2 |
1.5 |
2 |
1 |
1 |
7.5 |
5.6 |
12 |
(Zhou et
al., 2020) |
17 |
2 |
2 |
1.5 |
1.5 |
1 |
8 |
5.6 |
13 |
(Li et al., 2022) |
23 |
2 |
2 |
2 |
1.5 |
1 |
8.5 |
23 |
14 |
(Nazir et
al., 2020) |
66 |
2 |
2 |
1.5 |
1.5 |
0 |
7 |
22 |
15 |
(Kumar and Singh, 2019) |
154 |
1.5 |
2 |
1.5 |
2 |
0 |
7 |
30 |
16 |
(Yan et
al., 2021) |
6 |
2 |
1.5 |
2 |
1 |
1 |
7.5 |
1.5 |
17 |
(Sodagari, 2022) |
0 |
2 |
1.5 |
1.5 |
0 |
1 |
6 |
0 |
18 |
(Imamalieva, 2022) |
9 |
2 |
1.5 |
2 |
1 |
1 |
7.5 |
1.8 |
19 |
(Alexandru, Radu, and Bizon, 2018) |
35 |
2 |
1.5 |
1.5 |
1 |
0 |
6 |
1.8 |
20 |
(Roham, Gabrielyan, and Archer, 2021) |
4 |
2 |
2 |
1.5 |
1 |
1 |
7.5 |
0.75 |
21 |
(Adibuzzaman et
al., 2017) |
52 |
2 |
1.5 |
2 |
1 |
1 |
7.5 |
10.4 |
22 |
(Hong et
al., 2018) |
78 |
2 |
2 |
2 |
1.5 |
0 |
7.5 |
8.2 |
23 |
(Stylianou and Talias, 2017) |
34 |
2 |
1.5 |
1.5 |
1 |
0 |
6 |
3.33 |
24 |
(Pastorino et
al., 2019) |
153 |
2 |
2 |
2 |
2 |
1 |
9 |
22.25 |
25 |
(Lee and Yoon, 2017) |
346 |
2 |
2 |
2 |
2 |
1 |
9 |
57.67 |
26 |
(Saggi and Jain, 2018) |
242 |
2 |
2 |
2 |
2 |
1 |
8 |
48.4 |
27 |
(Hemingway et
al., 2018) |
179 |
2 |
2 |
2 |
2 |
1 |
9 |
35.8 |
28 |
(Shilo, Rossman, and Segal, 2020) |
220 |
2 |
2 |
2 |
2 |
1 |
9 |
73.33 |
29 |
(Zhang
et
al. 2017) |
150 |
2 |
2 |
2 |
1.5 |
1 |
8.5 |
25 |
30 |
(Awrahman, Aziz-Fatah, and Hamaamin, 2022) |
2 |
2 |
2 |
2 |
1 |
1 |
8 |
2 |
31 |
(Adnan et
al., 2020) |
31 |
2 |
2 |
2 |
1 |
1 |
8 |
10.33 |
32 |
(Adnan and Akbar, 2019a) |
136 |
2 |
2 |
2 |
2 |
1 |
9 |
34 |
33 |
(Adnan and Akbar, 2019b) |
57 |
2 |
2 |
1.5 |
1.5 |
1 |
8 |
14.25 |
34 |
(Khanra et
al., 2020) |
114 |
2 |
2 |
2 |
2 |
1 |
9 |
38 |
35 |
(Tandon et
al., 2020) |
237 |
2 |
2 |
2 |
2 |
1 |
9 |
79 |
36 |
(Cozzoli et
al., 2022) |
8 |
2 |
1.5 |
2 |
1 |
1 |
7.5 |
8 |
37 |
(Hassan et
al., 2022) |
17 |
2 |
1.5 |
2 |
2 |
1 |
8.5 |
17 |
38 |
(Dash et
al., 2019) |
771 |
2 |
2 |
2 |
2 |
1 |
9 |
192.75 |
39 |
(Al-Jaroodi, Mohamed, and Abukhousa, 2020) |
65 |
2 |
1.5 |
1.5 |
1 |
1 |
7 |
21.67 |
40 |
(Khanna et
al., 2022) |
2 |
2 |
2 |
1.5 |
1 |
1 |
7.5 |
2 |
41 |
(Yang et
al., 2020) |
256 |
2 |
2 |
2 |
2 |
1 |
9 |
85.33 |
42 |
(Do-Nascimento et al., 2021) |
31 |
2 |
2 |
1.5 |
1 |
1 |
7.5 |
15.5 |
43 |
(Harerimana et
al., 2018) |
75 |
2 |
2 |
2 |
1 |
1 |
8 |
15 |
44 |
(Ahmed et
al., 2021) |
70 |
2 |
1.5 |
2 |
1 |
1 |
7.5 |
35 |
45 |
(Renugadevi,
Saravanan, and Sudha, 2021) |
10 |
2 |
2 |
2 |
1 |
1 |
8 |
5 |
46 |
(Syed et
al., 2019) |
39 |
2 |
1.5 |
2 |
1 |
1 |
7.5 |
9.75 |
47 |
(Prosperi et
al., 2018) |
138 |
2 |
2 |
2 |
2 |
1 |
9 |
27.6 |
48 |
(Boyapati et
al., 2020) |
0 |
2 |
1.5 |
1.5 |
0 |
0 |
5 |
1.67 |
49 |
(Parimi and Chakraborty, 2020) |
5 |
2 |
1.5 |
1.5 |
1 |
1 |
7 |
3 |
50 |
(Kuila et
al., 2019) |
12 |
2 |
1.5 |
1.5 |
1 |
1 |
7 |
5 |
The number of yearly publications related to the topic has shown an upward trend from 2017 to 2020, as depicted in the chart (refer to Figure 4), particularly with increased academic interest in big data in 2020. Notably, a significant portion of the articles were published between 2018 and 2020. In both 2019 and 2022, there was an equal level of research interest.
Figure 4 Yearly
distribution of publications
5.1.
Challenges and solutions
Big Data in
healthcare holds immense potential but is confronted with issues such as data
quality, privacy, governance, workforce shortages, and costs. Addressing these
challenges can lead to improved patient outcomes, personalized healthcare, and
more effective responses to public health crises, such as COVID-19.
5.1.1. Gap between costs and outcomes
A major challenge is the growing healthcare cost-outcome
gap. Initiatives aim to address this by better managing research insights and
evidence, reducing resource waste, and enhancing patient care through a
"continuous learning healthcare system" (Lee and Yoon, 2017).
5.1.2 Unstructured Big Data in Healthcare
Unstructured big data from sources like social media and
IoT devices lacks defined structure, making traditional processing challenging.
Healthcare relies heavily on this data, but its complexity hinders accurate
analysis. Information extraction (IE) tech is essential for distilling
insights, and improved IE approaches are crucial, aided by advanced analytics
like NLP, ML, and DL (Adnan et al., 2020; Adnan et al.,
2019; Adnan and Akbar, 2019a).
5.2. Bigdata trends in healthcare
Predictions suggest that maintaining current healthcare
delivery will become more challenging in the next two decades. The COVID-19
pandemic exposed issues with data analysis and prediction accuracy (Batko and Slezak,
2022). A text mining method is proposed to extract linked
features from health data, improving value creation and data management (Kim and Chung,
2019).
5.2.1. Blockchain technology and AI
Blockchain technology in big data covers data management,
secure sharing, provenance, and auditing, with future research focusing on
efficient systems, AI/ML integration, and new use cases (Deepa et al.,
2022). Its applications include telemedicine, clinical trials,
supply chain, and patient-centric healthcare, but challenges like scalability
and governance persist (Wang et al., 2023; Tandon et al.,
2020). The study highlights AI and big data's role in
COVID-19, aiming to enhance predictions, diagnostics, tracking, drug discovery,
and vaccine development (Pham et al., 2020). Data
mining, involving preparation, mining, and analysis, extract insights from extensive
datasets (Yang
et al., 2020; Berawi, 2020).
5.2.2. Internet of Things
Wearable IoT generates extensive health data, requiring
real-time security measures to prevent breaches. An unsynchronized sensor data
analytics model is proposed (Jonny and Toshio, 2021; Puthal, 2019) using
Storm and Spark to monitor health data (Renugadevi, Saravanan, and
Sudha, 2021). IoT devices lack biological data but use big data
analytics and ML to predict activities (Syed et al., 2019),
benefiting elder care, rehabilitation, and chronic disease management. Health
4.0, using techs like IoHT, medical CPS, cloud, BDA, ML, blockchain, and smart
algorithms, faces privacy and security challenges (Naruetharadhol et al.,
2022; Al-Jaroodi, Mohamed, and Abukhousa, 2020). Table 3
summarizes the findings, highlighting privacy concerns and ongoing challenges.
Table 3 Literature Summaries are
included in this review
Ref |
Opportunities |
Challenges |
Findings |
(Adibuzzaman et al., 2017) |
· Integrate
smart infusion pumps. · Collaborate with stakeholders. |
· Data quality, · privacy, and regulatory
policies. |
· Sharing data broadly. · Enhancing scientific research. · Improving drug interaction analysis. |
(Alexandru, Radu, and Bizon, 2018) |
· Improved quality of care. · Enhanced fraud detection. · Reduction in expenses. · Decreased waiting times for medical treatments. |
· Privacy
concerns alongside the replacement of medical professionals. · challenges
in addressing privacy matters |
· Identified the most
important factors for using big data in healthcare. |
(Hong et
al., 2018)
|
· Improved patient treatment. · Cost reduction. |
· Data storage. · Data mining. · Data exchange. · Advancing medical research. |
· Features of big data in healthcare. · Applications of big data in healthcare. · Analytic techniques used
in healthcare big data. |
(Stylianou
and Talias, 2017) |
· Cancer research. · Climate change.
|
· Privacy and ethical
dilemmas. · Inadequate support for
data transmission and visibility. · Market share loss. |
· Three-dimensional model. · Obstacles and ethical issues. · Individuals impacted. |
(Pastorino et al., 2019) |
· Enhancing early diagnosis. · Disease prevention. · Improving pharmacovigilance and patient safety. · Advancing precision medicine. · Reducing inefficiencies
and improving cost-effectiveness. |
· Ethical challenges:
Privacy concerns, Personal autonomy implications, Impact on public
expectations of transparency, trust, and fairness. · Legal challenges related
to data access and analysis. |
· Report on best practice initiatives in Europe. · Aim: Providing fresh data for clinical care and
expediting public health surveillance. · Sectors: Cancer and
public health. |
(Hemingway et al., 2018) |
· Richer profiles of health and disease. · Accelerated disease understanding. · Discovery of new disease subtypes. · Holistic population and health system understanding. |
• Data quality. • Knowledge of available
data. • Legal and ethical
framework. • Data sharing. • Disease definition
standards. • Scalable science tools. • Multidisciplinary workforce. |
· Identifying obstacles: data quality, available data
knowledge. · Legal and ethical framework for data use. · Data sharing challenges. · Establishing and maintaining public trust. · Creating standards for
disease definition. |
(Awrahman,
Aziz-Fatah and Hamaamin, 2022) |
· Personalized
care. · Strengthened
patient-provider relationships. · Reduced hospital
expenses. |
· Real-time
processing. · Data
quality and security. · Privacy of
healthcare data. · Heterogeneity
of data. · Healthcare
data standards. |
· Significance
of big data (BD) in healthcare. · Addressed challenges associated with BD utilization. · Focused on
data aggregation challenges in healthcare. |
6. Discussion
The literature review on
big data (BD) in healthcare underscores the increasing importance of
data-driven approaches for enhancing patient care, public health, and medical
research. The utilization of big data analytics has led to significant
advancements in patient outcomes and cost reduction. Technological advancements
such as AI, IoT, ML, deep learning, and wearable sensors have amplified the
application of big data analytics in the medical domain. Precision medicine
could transform healthcare by customizing treatments according to an
individual's genetic traits, unlocking significant potential for personalized
care. Wearable technology aids real-time remote patient monitoring and early
detection of potential health issues. Challenges associated with big data in
healthcare encompass data quality, privacy concerns, interoperability, and
ethical considerations. Blockchain integration is identified to enhance patient
care, privacy, decision-making, and management efficiency. The quality and
interoperability of healthcare data are pivotal, as inaccurate information
could lead to incorrect diagnoses and treatment plans. Future research should
concentrate on developing digital platforms and specialized applications based
on big data analytics, including those dedicated to managing diagnostic images.
This study employs a systematic literature review
to assess BD in healthcare and outline future directions. Articles are
critically evaluated for their understandability, effectiveness, and
scalability. Key areas of focus emerge from analyzing BD trends and challenges
in healthcare. Future research directions include more efficient and scalable
blockchain-based systems, integrating blockchain with AI and ML, and exploring
novel blockchain applications. Current implementations of blockchain may not be
able to handle the increasing volumes of data, but they do offer a secure and
immutable ledger for healthcare records. Wearable
devices are assisting in the monitoring of patients in a timely and continuous
manner. Using blockchain technology, these devices are capable of securely
transmitting real-time health data to healthcare providers, enabling early
detection of health issues and more proactive treatment. Despite BD's benefits,
concerns include data privacy, security, and quality, necessitating proper
measures. Interoperability is vital for seamless data exchange among healthcare
professionals. BD has the potential to improve patient outcomes and reduce
costs. Future efforts will likely focus on machine learning, data mining, and
blockchain to enhance decision-making, patient outcomes, and cost efficiency.
This work is being conducted at the Balochistan
University of Information Technology, Engineering, and Management Sciences
(BUITEMS) in Quetta, Pakistan. It is with great appreciation that we
acknowledge the invaluable support received from Dr. Sibghat Ullah Bazai, Dr.
Shah Marjan and all authers during the review process.
We
would also like to thank the members of the Sunway Contactless Health
Monitoring Project (STR-RCGS-E-CITIES[S]-004-2021) for their contribution and
collaboration.
Abdalla, H.B., 2022. A
Brief Survey on Big Data: Technologies, Terminologies and Data-Intensive
Applications. Journal of Big Data, Volume 9(1), pp. 1–36
Adibuzzaman, M., DeLaurentis, P., Hill, J., Benneyworth,
B.D., 2017. Big Data in Healthcare – The Promises, Challenges and Opportunities
from A Research Perspective: A Case Study with a Model Database. In: AMIA
Annual Symposium Proceedings, Volume 2017, p. 384
Adnan, K., Akbar, R., 2019a. An Analytical
Study of Information Extraction from Unstructured and Multidimensional Big
Data. Journal of Big Data, Volume 6(1), pp. 1–38
Adnan, K., Akbar, R., 2019b. Limitations of
Information Extraction Methods and Techniques For Heterogeneous Unstructured
Big Data. International Journal of Engineering Business Management, Volume
11, p. 1847979019890771
Adnan, K., Akbar, R., Khor, S.W., Ali, A.B.A.,
2019. Role and Challenges of Unstructured Big Data in Healthcare. In: Data
Management, Analytics and Innovation. Singapore: Springer
Adnan, K., Akbar, R., Khor, S.W., Ali,
A.B.A., 2020. Role and Challenges of Unstructured Big Data in Healthcare. Advances
in Intelligent Systems and Computing, Volume 1042, pp. 301–323
Ahmed, I., Ahmad, M., Jeon, G., Piccialli,
F., 2021. A Framework for Pandemic Prediction Using Big Data Analytics. Big
Data Research, Volume 25, p. 100190
Alexandru, A.G., Radu, I.M., Bizon, M.L.,
2018. Big Data in Healthcare-Opportunities and Challenges. Informatica
Economica, Volume 22(2), pp. 43–54
Al-Jaroodi, J., Mohamed, N., Abukhousa, E.,
2020. Health 4.0: On the Way to Realizing the Healthcare of the Future. IEEE
Access, Volume 8, pp. 211189–211210
Awrahman, B.J., Aziz-Fatah, C., Hamaamin,
M.Y., 2022. A Review of the Role and Challenges of Big Data in Healthcare
Informatics and Analytics. Computational Intelligence and Neuroscience, Volume
2022, p. 5317760
Bag, S., Dhamija, P., Singh, R.K., Rahman,
M.S., Sreedharan, V.R., 2023. Big Data Analytics and Artificial Intelligence
Technologies Based Collaborative Platform Empowering Absorptive Capacity in
Health Care Supply Chain: An Empirical Study. Journal of Business Research,
Volume 154, p. 113315
Batko, K., ?l?zak, A., 2022. The Use of Big
Data Analytics in Healthcare. Journal of Big Data, Volume 9(1), p. 3
Behera, R.K., Bala, P.K., Dhir, A., 2019. The
Emerging Role of Cognitive Computing In Healthcare: A Systematic Literature
Review. International Journal of Medical Informatics, Volume 129, pp.
154–166
Berawi, M.A., 2020. Managing Artificial
Intelligence Technology for Added Value. International Journal of
Technology, Volume 11(1), pp. 1–4
Boyapati, S., Swarna, S.R., Sharma, S., Agrawal,
R., 2020. A Review of Bigdata and Machine Learning Techniques in Healthcare.
In: Proceedings of the 3rd International Conference on Intelligent
Sustainable Systems, ICISS 2020. Institute of Electrical and Electronics
Engineers Inc, pp. 756–761
Cozzoli, N., Salvatore, F.P., Faccilongo, N.,
Milone, M., 2022. How Can Big Data Analytics Be Used for Healthcare
Organization Management? Literary Framework and Future Research from A
Systematic Review. BMC Health Services Research, Volume 22(1), pp. 1–14
Dash, S., Shakyawar, S.K., Sharma, M., Kaushik,
S., 2019. Big Data in Healthcare: Management, Analysis and Future Prospects. Journal
of Big Data, Volume 6(1), pp. 1–25
Deepa, N., Pham, Q.V., Nguyen, D.C.,
Bhattacharya, S., Prabadevi, B., Gadekallu, T.R., Maddikunta, P.K.R., Fang, F.,
Pathirana, P.N., 2022. A Survey on Blockchain for Big Data: Approaches,
Opportunities, And Future Directions. Future Generation Computer Systems, Volume
131, pp. 209–226
Demirbaga, U., Aujla, G.S., 2022. MapChain: A
Blockchain-Based Verifiable Healthcare Service Management in IoT-Based Big Data
Ecosystem. IEEE Transactions on Network and Service Management, Volume 19(4),
pp. 3896–3907
Do-Nascimento, I.J.B., Marcolino, M.S.,
Abdulazeem, H.M., Weerasekara, I., Azzopardi-Muscat, N., Goncalves, M.A., Novillo-Ortiz,
D., 2021. Impact of Big Data Analytics on People’s Health: Overview of
Systematic Reviews and Recommendations for Future Studies. Journal of
Medical Internet Research, Volume 23(4), p. e27275
Ghayvat, H., Pandya, S., Bhattacharya, P.,
Zuhair, M., Rashid, M., Hakak, S., Dev, K., 2022. CP-BDHCA: Blockchain-Based
Confidentiality-Privacy Preserving Big Data Scheme for Healthcare Clouds and
Applications. IEEE Journal of Biomedical and Health Informatics, Volume 26(5),
pp. 1937–1948
Harb, H., Mroue, H., Mansour, A., Nasser, A.,
Cruz, E.M., 2020. A Hadoop-Based Platform for Patient Classification and
Disease Diagnosis in Healthcare Applications. Sensors, Volume 20(7), p.
1931
Harerimana, G., Jang, B., Kim, J.W., Park,
H.K., 2018. Health Big Data Analytics: A Technology Survey. IEEE Access,
Volume 6, pp. 65661–65678
Hassan, M., Awan, F.M., Naz, A.,
Deandrés-Galiana, E.J., Alvarez, O., Cernea, A., Fernández-Brillet, L.,
Fernández-Martínez, J.L., Kloczkowski, A., 2022. Innovations in Genomics and
Big Data Analytics for Personalized Medicine and Health Care: A Review. International
Journal of Molecular Sciences, Volume 23(9), p. 4645
Hassan, M.K., El Desouky, A.I., Elghamrawy, S.M.,
Sarhan, A.M., 2019. Big Data Challenges and Opportunities in Healthcare
Informatics and Smart Hospitals. In: Security in Smart Cities: Models,
Applications, and Challenges, pp. 3–26
Hemingway, H., Asselbergs, F.W., Danesh, J.,
Dobson, R., Maniadakis, N., Maggioni, A., Van Thiel, G.J.M., Cronin, M.,
Brobert, G., Vardas, P., Anker, S.D., Grobbee, Di.E., Denaxas, S., 2018. Big
Data from Electronic Health Records for Early and Late Translational
Cardiovascular Research: Challenges and Potential. European Heart Journal,
Volume 39(16), pp. 1481–1495
Hong, L., Luo, M., Wang, R., Lu, P., Lu, W., Lu,
L., 2018. Big Data in Health Care: Applications and Challenges. Data and
Information Management, Volume 2(3), pp. 175–197
Imamalieva, D., 2022. Recent Challenges of
Big Data Application in Healthcare System. In: International Conference
on Multidimensional Research and Innovative Technological Analyses, Volume
2012, pp.121–124
Jayasri, N.P., Aruna, R., 2022. Big Data
Analytics in Health Care by Data Mining and Classification Techniques. ICT
Express, Volume 8(2), pp. 250–257
Jonny, K., Toshio, M., 2021. Building an
Implementation Model of IoT and Big Data and Its Improvement. International
Journal of Technology, Volume 12(5), pp. 1000–1008
Karatas, M., Eriskin, L., Deveci, M., Pamucar,
D., Garg, H., 2022. Big Data for Healthcare Industry 4.0: Applications,
Challenges and Future Perspectives. Expert Systems with Applications, Volume
200, p. 116912
Khanna, D., Jindal, N., Singh, H., Rana,
P.S., 2022. Applications and Challenges in Healthcare Big Data: A Strategic
Review. Current Medical Imaging Reviews, Volume 19(1), pp. 27–36
Khanra, S., Dhir, A., Islam, A.N., Mäntymäki,
M., 2020. Big Data Analytics in Healthcare: A Systematic Literature Review. Enterprise
Information Systems, Volume 14(1), pp. 878–912
Kim, J.C., Chung, K., 2019. Associative
Feature Information Extraction Using Text Mining from Health Big Data. Wireless
Personal Communications, Volume 105(2), pp. 691–707
Kitchenham, B., Brereton, O.P., Budgen, D.,
Turner, M., Bailey, J., Linkman, S., 2009. Systematic Literature Reviews in
Software Engineering - A Systematic Literature Review. Information and
Software Technology, Volume 51(1), pp. 7–15
Kuila, S., Dhanda, N., Joardar, S., Neogy, S.,
Kuila, J., 2019. A Generic Survey on Medical Big Data Analysis Using Internet of
Things. Advances in Intelligent Systems and Computing, Volume 815, pp. 265–276
Kumar, S., Singh, M., 2019. Big Data
Analytics for Healthcare Industry: Impact, Applications, and Tools. Big Data
Mining and Analytics, Volume 2(1), pp. 48–57
Lee, C.H., Yoon, H.J., 2017. Medical Big
Data: Promise and Challenges. Kidney Research and Clinical Practice, Volume
36(1), pp. 3–11
Li, C., Dong, M., Li, J., Xu, G., Chen, X.B.,
Liu, W., Ota, K., 2022. Efficient Medical Big Data Management with
Keyword-Searchable Encryption in Healthchain. IEEE Systems Journal, Volume
16(4), pp. 5521–5532
Liang, Y., Quan, D., Wang, F., Jia, X., Li,
M., Li, T., 2020. Financial Big Data Analysis and Early Warning Platform: A
Case Study. IEEE Access, Volume 8, pp. 36515–36526
Naruetharadhol, P., Srisathan, W.A.,
Gebsombut, N., Wongthahan, P., Ketkaew, C., 2022. Industry 4.0 for Thai SMEs:
Implementing Open Innovation as Innovation Capability Management. International
Journal of Technology, Volume 13(1), pp. 48–57
Nazir, S., Khan, S., Khan, H.U., Ali, S.,
Garcia-Magarino, I., Atan, R.B., Nawaz, M., 2020. A Comprehensive Analysis of
Healthcare Big Data Management, Analytics and Scientific Programming. IEEE
Access, Volume 8, pp. 95714–95733
Parimi, S., Chakraborty, S., 2020. Application
of Big Data & Iot on Personalized Healthcare Services Article in. International
Journal of Scientific & Technology Research, Volume 9(3), pp. 1107–1111
Pastorino, R., De-Vito, C., Migliara, G.,
Glocker, K., Binenbaum, I., Ricciardi, W., Boccia, S., 2019. Benefits and
Challenges of Big Data in Healthcare: An Overview of The European Initiatives. European
Journal of Public Health, Volume 29, pp. 23–27
Pham, Q.V., Nguyen, D.C., Huynh-The, T.,
Hwang, W.J., Pathirana, P.N., 2020. Artificial Intelligence (AI) and Big Data
for Coronavirus (COVID-19) Pandemic: A Survey on the State-of-the-Arts. IEEE
Access, Volume 8, pp. 130820–130839
Prosperi, M., Min, J.S., Bian, J., Modave,
F., 2018. Big Data Hurdles in Precision Medicine and Precision Public Health. BMC
Medical Informatics and Decision Making, Volume 18(1), pp. 1–15
Puthal, D., 2019. Lattice-Modeled Information
Flow Control of Big Sensing Data Streams for Smart Health Application. IEEE
Internet of Things Journal, Volume 6(2), pp. 1312–1320
Rahmadian, E., Feitosa, D., Zwitter, A.,
2022. A Systematic Literature Review on The Use of Big Data for Sustainable
Tourism. Current Issues in Tourism, Volume 25(11), pp. 1711–1730
Renugadevi, N., Saravanan, S., Sudha, C.M.N.,
2021. Revolution of Smart Healthcare Materials in Big Data Analytics. In: Materials
Today: Proceedings, Volume 81(2), pp. 87–1176
Roham, M., Gabrielyan, A.R., Archer, N.,
2021. A Systematic Review of Knowledge Visualization Approaches Using Big Data
Methodology for Clinical Decision Support. Recent Advances in Digital System
Diagnosis and Management of Healthcare
Saggi, M.K., Jain, S., 2018. A Survey Towards
an Integration of Big Data Analytics to Big Insights for Value-Creation. Information
Processing and Management, Volume 54(5), pp. 758–790
Shilo, S., Rossman, H., Segal, E., 2020. Axes
of a Revolution: Challenges and Promises of Big Data in Healthcare. Nature Medicine,
Volume 26(1), pp. 29–38
Sodagari, S., 2022. Trends for Mobile IoT
Crowdsourcing Privacy and Security in the Big Data Era. IEEE Transactions on
Technology and Society, Volume 3(3), pp. 199–225
Stylianou, A., Talias, M.A., 2017. Big Data
in Healthcare: A Discussion on The Big Challenges. Health and Technology,
Volume 7(1), pp. 97–107
Syed, L., Jabeen, S., Manimala, S., Elsayed,
H.A., 2019. Data Science Algorithms and Techniques for Smart Healthcare Using
IoT and Big Data Analytics. Smart Techniques for a Smarter Planet: Towards
Smarter Algorithms, pp.211–241
Tandon, A., Dhir, A., Islam, A.N., Mäntymäki,
M., 2020. Blockchain In Healthcare: A Systematic Literature Review,
Synthesizing Framework and Future Research Agenda. Computers in Industry,
Volume 122, p. 103290
Wang, R., Xu, C., Dong, R., Luo, Z., Zheng,
R., Zhang, X., 2023. A Secured Big-Data Sharing Platform for Materials Genome
Engineering: State-Of-The-Art, Challenges and Architecture. Future
Generation Computer Systems, Volume 142, pp. 59–74
Xing, W., Bei, Y., 2020. Medical Health Big
Data Classification Based on KNN Classification Algorithm. IEEE Access, Volume
8, pp. 28808–28819
Yan, L., Huang, W., Wang, L., Feng, S., Peng,
Y., Peng, J., 2021. Data-Enabled Digestive Medicine: A New Big Data Analytics
Platform. IEEE/ACM Transactions on Computational Biology and Bioinformatics,
Volume 18(3), pp. 922–931
Yang, J., Li, Y., Liu, Q., Li, L., Feng, A.,
Wang, T., Zheng, S., Xu, A., Lyu, J., 2020. Brief Introduction of Medical
Database and Data Mining Technology in Big Data Era. Journal of
Evidence-Based Medicine, Volume 13(1), pp. 57–69
Yuvaraj, N., SriPreethaa, K.R., 2019.
Diabetes Prediction in Healthcare Systems Using Machine Learning Algorithms on
Hadoop Cluster, Cluster Computing, Volume 22, pp. 1–9
Zhang, X., Pérez-Stable, E.J., Bourne, P. E., Peprah, E., Duru, O.K.,
Breen, N., Berrigan, D., Wood, F., Jackson, J.S., Wong, D.W.S., Denny, J., 2017.
Big Data Science: Opportunities And Challenges To Address Minority Health And
Health Disparities In The 21st Century. Ethnicity and Disease,
Volume 27(2), pp. 95–106
Zhou, S., He, J., Yang, H., Chen, D., Zhang,
R., 2020. Big Data-Driven Abnormal Behavior Detection in Healthcare Based on
Association Rules. IEEE Access, Volume 8, pp. 129002–129011