Sage Journals: Discover world-class research

Abstract

Background: Despite the ongoing efforts to digitalize the healthcare sector in developing countries, the full adoption of big data analytics in healthcare settings is yet to be attained Exploring opportunities and challenges encountered is essential for designing and implementing effective interventional strategies. Objective: Exploring opportunities and challenges towards integrating big data analytics technologies in the healthcare industry in developing countries. Methodology: This was a narrative review study design. A literature search on different databases was conducted including PubMed, ScienceDirect, MEDLINE, Scopus, and Google Scholar. Articles with predetermined keywords and written in English were included. Results: Big data analytics finds its application in population health management and clinical decision-support systems even in developing countries. The major challenges towards the integration of big data analytics in the healthcare sector in developing countries include fragmentation of healthcare data and lack of interoperability, data security, privacy and confidentiality concerns, limited resources and inadequate regulatory and policy frameworks for governing big data analytics technologies and limited reliable power and internet infrastructures. Conclusion: Digitalization of healthcare delivery in developing countries faces several significant challenges. However, the integration of big data analytics can potentially open new avenues for enhancing healthcare delivery with cost-effective benefits.

Keywords

big data analytics developing countries health information system healthcare sector

Summary of the key findings

• The application of big data analytics in the healthcare industry, particularly in developing countries, faces various challenges, such as a lack of evidence for its practical benefits, inadequate skilled personnel, a lack of appropriate policy and regulatory frameworks, and the required substantial financial investment.

• The available literature focuses only on the qualitative benefits of applying big data analytics to the healthcare industry. Future studies should quantitatively assess the practical benefits and analyze the implementation costs of integrating big data analytics technologies in the healthcare sector, particularly in developing countries with competing priorities and limited resources.

• By leveraging the potential benefits of digitization of healthcare data, the healthcare industry in developing countries can harness the power of big data analytics to improve the quality of care and health outcomes.

Introduction

“Big data” refers to data that can neither be managed with traditional software or hardware nor easily handled with traditional data management tools and techniques due to their high complexity and heterogeneity.^1,2,3 Big data has been classically defined based on its volume, variety, velocity, veracity, and value.^4,5,6,7 Volume, as applied to big data, refers to the quantity of data measured by petabyte, exabyte, zettabyte, or yottabyte.^2,6,8,9 The variety implies that big data occur in different types and forms and have heterogeneous characteristics.^10,11 The speed at which data is generated is known as the velocity, encompassing static and real-time, dynamic data.^2,11,12 Veracity, as applied to big data, refers to the completeness, consistency, accuracy, reliability, credibility, and certainty of information.¹³ It is usually influenced by fraud, ambiguities, and missing values.¹⁴ The veracity as applied to big data is determined by how accurately and consistently data is collected, and this is of the most significant concern because informed decisions depend on high-quality and accurate data.^2,14 The value of data refers to how valuable the insights extracted from the data are in informing decisions and policymakers.¹ These characteristics make the traditional management and utilization of healthcare data overwhelming,^14,15 not only because of its vast volume¹⁶ but also because of its complexity, heterogeneity, and the rate at which they are generated.^15,17

The field of big data analytics focuses on gaining an in-depth understanding of a massive volume of data by applying algorithms for analyzing and extracting valuable information from complex datasets.^13,18,19 With the swift transition to digital technologies across various sectors, big data analytics has gained attention in recent years due to its wide range of applications. In the healthcare context, where data are highly complex and heterogeneous,^2,13,20 applying big data analytics tools and techniques ensures the conversion of raw data into actionable information by discovering hidden patterns, trends, correlations, and associations within these complex datasets.^2,21,22 This eventually leads to developing specific, insightful, data-driven interventions to improve overall health outcomes.²³

In developed countries, big data analytics technologies have been widely used to assist clinical decision support in targeted drug therapy, medical signalling analytics, disease surveillance, and bioinformatics.^{1,10,12,13,24} On the contrary, big data analytics in healthcare settings in developing countries has yet to be integrated, leaving a significant percentage of healthcare data unstructured and underutilized.^13,25 Exploring the opportunities and challenges of applying big data analytics in the healthcare industry in developing countries is crucial for developing effective strategies for implementing and counteracting related challenges.

This article reviews the concept of big data in healthcare and its sources. It points out potential applications of big data analytics technologies in the context of developing countries in terms of challenges and opportunities. It further identifies what can be implemented to address the existing challenges.

Methodology

This was a narrative review study design. A comprehensive literature search was conducted in different databases, including PubMed, ScienceDirect, MEDLINE, Scopus, and Google Scholar. Relevant references cited in recent articles were also reviewed. The literature review included all articles in full text and written in English. Key findings were summarised and discussed.

A search strategy with the search strings “Big Data,” “Bioinformatics,” “Data Analytics,” “Data Mining,” “Machine Learning,” “Artificial Intelligence,” “Healthcare,” “Health Sector,” “Medical,” “Hospital,” “Health Information Systems,” “Developing Countries,” “Low—and Middle-Income Countries,” “LMIC,” “Emerging Economies,” and “Third World Countries” were performed.

A comprehensive search across mentioned databases was done using predefined search strings. The selected studies were critically reviewed to identify recurring topics related to the integration of big data analytics in healthcare, particularly in developing countries. These recurring topics were grouped into key thematic areas, such as sources of healthcare big data, potential applications of big data analytics, challenges of application of big data in the healthcare sector in developing countries, and mitigation measures for the application of big data analytics in developing countries. Themes were refined based on their repetitiveness and their relevance to the research objectives, ensuring a comprehensive representation of the literature’s findings.

Findings

We found different challenges to integrating big data analytics technologies in the healthcare industry in developing countries, along with possible opportunities (Table 1).

Table 1.

Summary of the key findings from the review of the literature.

Category	Key findings
Sources of big data in the healthcare sector	• Demographic characteristics • Medical images • Clinical notes • Electronic health records • Laboratory information systems • Administrative and clinical databases
Potential applications of big data analytics in the healthcare sector	• Medical image processing and analysis: Improving the accuracy of diagnostic services through imaging modalities such as ultrasound, X-rays, CT-scan, MRI, and PET scan • Population health management: Predicting, monitoring, and diagnosing diseases using data from internet search queries, social media, and crowdsourcing • Clinical informatics: Organizing unstructured clinical information into structured datasets to inform clinical decisions • Bioinformatics: Analysis of biological datasets for precision medicine, disease risk stratification, and individualized treatment strategies • Clinical decision support: Providing evidence-based insights, predictive analytics, and prescriptive analytics to inform and optimize patient care decisions
Challenges in developing countries	• Fragmentation of healthcare data and lack of interoperability • Data security, patient privacy, and confidentiality concerns • Limited resources for implementing big data analytics and training health professionals • Inadequate regulatory and policy frameworks for governing big data analytics technologies • Limited reliable power and internet infrastructure
Mitigation measures	• Providing training and awareness on the potential applications of big data analytics in the healthcare sector to health professionals through optional modules in academic curriculums and short courses • Implementing big data governance and policy frameworks • Develop a data-sharing culture between stakeholders and facilities • Implementing robust data security measures such as encryption, source data verification, and access control • Incorporating cloud computing for efficient data storage and management

The sources of healthcare data

As one of the world’s largest and fastest-growing industries, the healthcare sector generates massive, complex and heterogeneous data.^2,20 The generation of healthcare data is driven by record keeping, compliance with regulatory requirements, and the need to improve the quality of care.²⁰ These data are generated from different sources and occur in different structures and formats.²⁶ They include demographic characteristics, medical images, clinical notes, administrative databases, clinical databases, electronic health records, and laboratory information systems.^27,28,29 Others include biometric data from wearable and smart devices, data from social media, biomarkers, and genetic data.^30,31,32 Healthcare data occur in different types, from unstructured and semi-structured to structured datasets, which may also be discrete or continuous.¹ While these data are primarily stored in hard copies, especially in developing countries, there has been a recent digitization trend of healthcare data through electronic medical records and health information management systems.^2,13 As the quest for evidence-based medicine continues, these vast quantities of complex data have the potential to improve the quality of care at a lower cost²² through their wide range of insightful applications, such as clinical decision support, disease surveillance, and population health management.^{8,10,19,33,34,35,36}

Potential applications of big data analytics in the healthcare sector in developing countries

Medical image processing and analysis

Medical Image Processing and Imaging Informatics have revolutionized the aspects of disease screening and diagnosis.¹² The introduction of imaging modalities such as Ultrasound, X-rays, Computed Tomography Scanning (CT-scan), Magnetic Resonance Imaging (MRI), and Positron Emission Tomography (PET scan) have by far improved the accuracy of diagnostic services in developing countries. These imaging modalities are widely used for screening and diagnosis of cancers,^37,38,39 cardiovascular diseases,^29,40 neurological conditions,^41,42 and some prevailing infectious diseases such as pulmonary tuberculosis.^43,44 The domain of medical imaging informatics also encompasses digitized cytopathological and histopathological images, which are used to detect different types of cancers. With the ongoing digitization of the healthcare sector in developing countries, medical image processing and imaging informatics can create a huge repository of big data, which can be used to train algorithms for computer-assisted image analysis and interpretation.^{2,12,19,44,45,46,47,48} This will result in the early detection of diseases and improved efficiency and accuracy, improving the treatment and survival outcomes. For example, an algorithm developed from massive datasets of chest radiographs could accurately detect pulmonary tuberculosis in India, Nepal, and Cameroon.^43,44 Although these breakthroughs are yet to be fully integrated into clinical practice, they have proved to be potentially valuable for increasing diagnostic accuracy and efficiency, enabling early detection of diseases in resource-limited settings.

Population health management and disease surveillance

Traditionally, disease surveillance and population health management are achieved by collecting epidemiological data to study how frequently diseases occur in a particular age group and geographical area.¹² This information is used to formulate and evaluate disease prevention interventions and provide guidelines for managing patients.^12,49 The presence of laboratory-based detection tools has drastically reduced the time to accurate diagnosis in limited-resource and crisis settings, as observed during the 2014 West African Ebola virus outbreak and Zika virus epidemic.^50,51,52,53 Furthermore, the availability of rapid immunologically-based diagnostic tests has ensured the near-real-time detection of emerging viral threats.⁵⁴ In addition to the increasing sophistication of these conventional disease surveillance systems, surveillance systems have rapidly developed using big data streams.^55,56 These novel surveillance systems can incorporate big data streams from Internet search queries, social media data, and crowdsourcing to provide useful information about public health threats at a particular time and locale, a discipline known as public health informatics.^12,55 The big streams of public or social media information can be used to predict, monitor, and diagnose different disease conditions.^51,57 For example, Young et al., 2014⁵⁷ obtained a positive correlation between HIV-related tweets and HIV cases after extracting over 9800 keywords and geographical annotations that contain HIV risk words from 553,186,016 tweets from Twitter.

In another study, Nambisan et al., 2015⁵⁸ used big data analytics tools to extract hidden insightful patterns from messages and tweets on social media to detect depression. They concluded that the behavioural and emotional patterns in messages depicted symptoms of depression. During the COVID-19 pandemic in December 2020, the UNDP accelerator laboratory extracted over 20,422 related tweets in four consecutive days, which were used to determine the level of misinformation about the pandemic in one of the districts in Tanzania.⁵⁹ Although the study involved one district, it provided theoretical evidence on using big data analytics techniques to extract valuable information from social media data. In the order of these ideas, and with the increase in internet use, big data analytics in population health management seems essential in real-time disease surveillance and understanding real-time situational awareness about public health.^33,55

Clinical informatics

Unstructured clinical information such as clinical documents, laboratory investigation results, medical images, and patient discharge summaries are the major sources of healthcare data, accounting for over 80% of data concerning patient health and wellbeing.^12,60 Despite the rapid digitization of these data, a large portion still needs to be more structured and utilized.²⁵ The unstructured format renders it ineffective in informing data-driven decisions. The unstructured data must be converted into structured datasets to extract valuable insights and discover trends and patterns within the data.^12,61 Big data analytics tools can be effectively deployed to organize patients’ clinical data, laboratory tests, and reports into structured and computerized forms to increase data retrieval and extraction and inform clinical decision-making.^60,61,62

Clinical informatics is, however, not implemented in developing countries, partly due to limited resources. If fully implemented, clinical informatics can transform the healthcare sector by ensuring maximum utilization of healthcare data through the extraction of trends, patterns, associations, and correlations within various datasets and, therefore, provide actionable information to inform evidence-based clinical practice and policy making.

Bioinformatics

The concept of precision medicine has been gaining attention in recent years.⁶³ This entails tailoring preventive and curative interventions to a small group of people or even individual patients based on their genetic makeup, environmental exposure, and lifestyle.^63,64,65 Bioinformatics is becoming increasingly valuable due to its vitality in achieving precision medicine. Bioinformatics is an interdisciplinary area involving molecular biology, computer science, mathematics, and statistics, focusing on the computational analysis of biological datasets.^63,66 Bioinformatics has been widely used to understand disease processes at a molecular level, enabling disease risk stratification and early detection, developing individualized treatment strategies, and predicting treatment outcomes and patient response to therapy.^66,67,68

The field of bioinformatics involves the analysis of a huge volume of data, which has been growing dramatically.⁶⁸ For example, a single sequenced human genome is approximately 200 gigabytes.⁶⁹ Although the availability of this enormous volume of data is essential for accurate analysis, it also poses significant analytical challenges, especially in developing countries where big data analytics and cloud computing tools have not been effectively integrated.^66,68 Furthermore, the heterogeneous nature and the ethnic and geographical variations of these data increase the complexity of their analysis.⁶⁸ Applying big data analytics in organizing and analyzing biological data will ensure the maximum realization of the power of bioinformatics in disease risk stratification, targeted therapy, disease prevention, treatment, and cure.

Challenges to implementation of healthcare big data analytics in developing countries

Despite the potential benefits and opportunities for big data analytics in the healthcare sector, developing countries still lag in adopting big data analytics in the healthcare sector.¹³ With the substantial available repository, it becomes difficult to understand which data will be used and for what purpose.⁷⁰ The healthcare sector also needs more appropriate infrastructure, such as storage facilities and a reliable internet connection, which is essential for the management and analysis of big streams of data.^19,71,72 Despite the ongoing digitization of healthcare data, most patient-related data are paper-based, posing challenges of inconsistency, validity, incompleteness, and unreliability, rendering them incompatible with big data analytics tools.^6,73 Therefore, healthcare systems must be redesigned using distributed data processing.^74,75

The resistance to incorporating digitized healthcare systems^15,76 and the need for massive investment⁷⁷ make it more challenging to utilize big data technologies in developing countries with existing competing priorities.^27,78,79 Studies have further shown that due to a lack of technical knowledge about the best algorithms to be used⁷⁰ and the unavailability of trained health data scientists and big data managers,^22,28,72,79 most developing countries are far from realizing the potential benefits of big data analytics in the healthcare sector. Another big concern that has been raised regarding the application of big data analytics in the healthcare sector is the processing of information without human supervision, which can lead to erroneous conclusions and false-positive associations.^80,81,82 Therefore, it becomes imperative to develop simple, convenient, and transparent big data analytics algorithms that can be utilized for real-time cases.² Integration and interoperability challenges are also among the setbacks for applying big data analytics in healthcare industries.^3,73,75 This might be because healthcare data are fragmented,^70,83 arise from different sources,²⁸ and occur in different forms and structures.²⁶ Lastly, data security, patient privacy, and confidentiality are paramount. Integrating big data analytics in the healthcare sector may involve sharing patients’ data between stakeholders and facilities.^76,81 With the lack of data protocols and regulatory frameworks, informed consent and privacy have become critical areas of concern.^25,78

Discussion

This review provides a comprehensive narrative of the opportunities and challenges of adopting big data analytics in healthcare, specifically in developing countries. It bridges a critical knowledge gap by synthesizing existing literature and highlighting potential applications and obstacles. It further identifies unique issues such as data fragmentation, regulatory challenges, and limited infrastructure, particularly prevalent in developing countries, while proposing solutions for healthcare transformation through big data. These insights are crucial for policymakers, healthcare practitioners, and researchers advancing digital health in resource-limited settings.

The concept of big data encompasses various definitions, ranging from data that is challenging to handle using conventional analytical tools and methods to describing it as having an immense volume, high speed, diverse variety, and varying accuracy.^1,2,3,11 While most studies defined big data based on the mentioned characteristics, one study characterized big healthcare data as having energy and lifespan.³ The lack of consensus definition of “big data” indicates that despite the term “big data” being widely known, its objective definition is still unclear. This may affect the implementation of these technologies since it has not been objectively defined as what data is really “big data”. Furthermore, defining “big data” based on the fact that it cannot be analyzed by traditional data analytics software is somewhat subjective because the sophistication and capacity of this “traditional” software vary according to the level of technological advancement in a particular region. Moreover, it has not been objectively stated as to what software is considered “traditional”. These controversies must be addressed to facilitate the adoption of big data analytics technologies in developing countries.

It has also been demonstrated that big data analytics techniques are distinct from traditional data analysis approaches. While conventional analysis typically utilizes deductive reasoning to monitor care and quality outcomes retrospectively, big data analytics relies on inductive reasoning for prospective data analysis.⁷⁷ This approach generates hypotheses rather than testing by identifying associations and correlations within observational data without focusing on the causal relationships between variables.¹³ Nonetheless, validating these hypotheses through hypothesis testing is crucial before implementing the findings into clinical practice. The implementation of big data analytics in the healthcare sector should, therefore, focus on testing and validating hypotheses rather than just generating them.

Literature on applying big data analytics in the healthcare industry revealed that big data analytics technologies could be helpful in clinical decision support, personalized medicine, and disease surveillance. Big data analytics techniques can be integrated into different healthcare domains, including medical image analysis and imaging informatics,^{38,39,40,41,42,43,44,45} population health management,^{55,56,57,58,59} clinical informatics,^60,62 and bioinformatics.^66,68,71 Integrating big data technologies in healthcare can enhance the quality of care and identify high-risk patients early through real-time analytics, optimising clinical operations and saving lives at a lower cost.^1,13,84 Studies on applying big data analytics technologies in cardiovascular diseases, diabetes, oncology, infectious diseases, mental health, and clinical research have shown that they can improve timely care delivery and reduce cost.^22,52,55 Few studies, however, suggested that it is essential to incorporate human judgment and supervision in interpreting insights obtained through big data analytics algorithms.^80,81,82 This is necessary to mitigate the potential occurrence of adverse events that may arise from relying solely on the results generated by big data analytics algorithms. Despite the qualitative description of the application of big data analytics technologies in healthcare in developing countries, none of the literature reviewed here presented a quantitative assessment of the practical impact, cost implications, and operational efficiency. We believe that assessing the impact and cost analysis for integrating big data technology in healthcare through large-scale implementation studies would provide strong evidence for large-scale adoption. Therefore, future research should focus on assessing the quantitative impacts of big data analytics technologies in the healthcare sector and their cost implications. This will better inform decision-makers on integrating big data technologies in the healthcare sector, especially in developing countries with limited resources.

Despite the significant value that big data analytical tools can add to the healthcare industry in developing countries,⁸⁵ the adoption of this technology has been limited due to various challenges. These include inadequate IT infrastructure, high implementation costs, data privacy and security concerns, fragmented data ownership, lack of sustainable and reliable internet connection, and technical challenges such as data quality and multidimensionality.^19,79 Additionally, the lack of evidence regarding the practical benefits of big data analytics in healthcare, the shortage of skilled big data analysts with healthcare knowledge, and the complexity of the analytical systems have also contributed to the limited integration of this technology.^22,28 To fully realize its potential, strategies such as proper governance and regulatory frameworks, promoting health information exchange, training key health personnel, developing simple and transparent big data systems, utilizing cloud storage and distributed data processing, and strengthening IT security are some of the measures that have been proposed to harness the potential of big data analytics technologies in the healthcare sector in developing countries.^{19,76,83,86,87}

Recommendations

Several challenges exist when applying big data analytics in the healthcare sector, particularly for developing countries. The following measures might be useful in addressing such challenges when applicable;

• Provision of necessary training in big data analytics to health professionals: To extract meaningful insights and valuable information from large sets of healthcare data, health professionals should be trained with big data analytics competencies.¹³ This training is critical because incorrect analysis and interpretation could lead to unforeseen outcomes.¹⁹ This can be achieved by introducing optional modules within the academic curriculums, introducing short courses on the application of big data analytics in healthcare for health professionals, and increasing the awareness and engagement of health professionals in understanding the potential applications of big data analytics in the healthcare sector, especially in developing countries.

• Implementing big data governance as well as policy and regulatory frameworks: Inadequate management of healthcare data and a lack of regulatory and policy frameworks for big data analytics result in significant expenses related to big data infrastructure.³⁵ Implementing appropriate governance will lead to effective utilization of healthcare data, provided that proper policy and regulatory frameworks are in place.^76,79

• Creating a data-sharing culture: Developing an information-sharing culture between stakeholders and facilities in developing countries is crucial in addressing the interoperability challenges and maximizing the predictive and prescriptive potentials of big data analytics in the healthcare industry.^26,83 By sharing consolidated healthcare data, stakeholders can effectively utilize these resources to improve health outcomes.

• Implementing data security measures: To address the concern of data security, measures such as robust data encryption, source data verification, data access control, authentication, de-anonymization, and de-identification can be effectively used to ensure data security and confidentiality.^86,87 These measures are crucial in protecting sensitive information from unauthorized access.

• Incorporating Cloud Computing in Healthcare Data Storage: To address the enormous volume of healthcare data, healthcare organizations in developing countries can incorporate cloud computing in their data storage and management strategy.¹³ This would allow even small healthcare organizations to overcome storage challenges and reduce data storage-related costs.¹⁹ Integration of cloud computing in data storage and management will enable healthcare organizations in developing countries to store and manage large volumes of healthcare data efficiently.

Limitations

The exclusion of non-English literature from the data synthesis of this review might have limited the extent of potential information included in this study, hence its discussion, conclusion, and recommendations. Moreover, the study might be limited by the inconsistent availability and data quality across different developing countries. Data fragmentation and lack of standardization may have led to incomplete or inaccurate data synthesis. Furthermore, this study’s findings and conclusion might only be generalized to some developing countries due to possible differences in healthcare infrastructures, policies, and socio-economic conditions.

Conclusion

Integrating big data analytics in developing countries’ healthcare industry can open new avenues for enhancing healthcare delivery. By leveraging the potential benefits of digitization of healthcare data, the healthcare industry in developing countries can harness the power of big data analytics to improve quality and outcomes while reducing costs. Big data analytics’ predictive nature and pattern recognition capabilities can revolutionize the healthcare sector’s quest for transformation from an experience-based approach to evidence-based practice. Despite the benefits big data analytics can have in the healthcare industry of developing countries, highlighted strategies should be implemented to address a number of challenges these countries encounter towards using this technology.

Moreover, political will among developing countries is essential to ensure the sustainability and effectiveness of big data analytics technology in developing countries. Furthermore, since most of the currently available literature focuses more on the qualitative benefits of the application of big data analytics in the healthcare industry in developing countries, this review further emphasizes the need for quantitatively assessing the practical impacts and implementation cost of integrating big data technology in the healthcare sector, where resources are limited, and priorities are competing.

Footnotes

Acknowledgements

We acknowledge Professor Muhammad Bakari for reviewing the first draft of the manuscript and provide constructive comments.

Author contributions

Project Supervision and Administration: Harold L. Mashauri. Study conceptualization and design: David Muhunzi, Lucy Kitambala and Harold L. Mashauri. Acquisition of data: David Muhunzi, Harold L. Mashauri and Lucy Kitambala. Analysis and interpretation of findings: David Muhunzi. Drafting of the manuscript: David Muhunzi. Critical review: Lucy Kitambala and Harold L. Mashauri. Approval of manuscript: David Muhunzi, Harold L. Mashauri and Lucy Kitambala.

Declaration of conflicting interests

The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Funding

The author(s) received no financial support for the research, authorship, and/or publication of this article.

Declaration of generative AI and AI-assisted technologies in the writing process

No generative AI or AI-assisted technology was used in the preparation of this manuscript.

ORCID iDs

David Muhunzi

Harold L Mashauri

Data availability statement

Data sharing does not apply to this article as no datasets were generated or analyzed during the current study.*

References

Ristevski

Chen

. Big data analytics in medicine and healthcare. J Integr Bioinform 2018; 15(3): 1–5.

Raghupathi

. Big data analytics in healthcare: promise and potential. Health Inf Sci Syst 2014; 2(1): 3.

Dinov

. Volume and value of big healthcare data. J Med Stat Inform 2016; 4(1): 3.

Andreu-Perez

Poon

CCY

Merrifield

, et al. Big data for health. IEEE J Biomed Health Inform 2015; 19(4): 1193–1208.

Archenaa

Mary Anita

. A survey of big data analytics in healthcare and government. Procedia Computer Science 2015; 50: 408–413. DOI: 10.1016/j.procs.2015.04.021.

Kruse

Goswamy

Raval

, et al. Challenges and opportunities of big data in health care: a systematic review. JMIR Med Inform 2016; 4(4): e38.

Liyanage

de Lusignan

Liaw

, et al. Big data usage patterns in the health care domain: a use case driven approach applied to the assessment of vaccination benefits and risks. Contribution of the IMIA primary healthcare working group. Yearb Med Inform 2014; 9: 27–35.

Trends

Benefits

Backhaul

. White paper. 2008. Big data and healthcare payers.

Gui

Zheng

, et al., An Architecture for Healthcare Big Data Management and Analysis, In Yin, X., Geller, J., Li, Y., Zhou, R., Wang, H., Zhang, Y., (eds). Health Information Science. HIS 2016 Lecture Notes in Computer Science, Cham: Springer, 2016.

10.

Kumar

Singh

. Big data analytics for healthcare industry: impact, applications, and tools. Big Data Mining and Analytics 2019; 2(1): 48–57.

11.

Cyganek

Graña

Krawczyk

, et al. A survey of big data issues in electronic health record analysis. Appl Artif Intell 2016; 30(6): 497–520.

12.

Rehman

Naz

Razzak

. Leveraging big data analytics in healthcare enhancement: trends, challenges and opportunities. Multimedia Systems 2020; 28: 1339–1371.

13.

Mehta

Pandit

. Concurrence of big data analytics and healthcare: a systematic review. Int J Med Inf 2018; 114: 57–65.

14.

Sukumar

Natarajan

Ferrell

. Quality of big data in health care. Int J Health Care Qual Assur 2015; 28(6): 621–634.

15.

Khalili

. Drowning in Big Data? Reducing Information Technology Complexities and Costs for Healthcare Organizations. Frost & Sullivan White Paper [Internet]. Frost & Sullivan, 2011. https://www.academia.edu/6563567/A_Frost_and_Sullivan_White_Paper_Drowning_in_Big_Data_Reducing_Information_Technology_Complexities_and_Costs_For_Healthcare_Organizations_CONTENTS.

16.

Kraft

Desouza

Androwich

. Data Mining in Healthcare Information Systems: Case Study of a Veterans? Administration Spinal Cord Injury Population. HICSS: IEEE Computer Society, 2003, p. 159.

17.

Dash

Shakyawar

Sharma

, et al. Big data in healthcare: management, analysis and future prospects. J Big Data 2019; 6(1): 54.

18.

Jain

Bhatnagar

. Crime Data Analysis Using Pig with Hadoop. Procedia Computer Science. 2016; 78: 571–578.

19.

Wang

Kung

Byrd

. Big data analytics: understanding its capabilities and potential benefits for healthcare organizations. Technol Forecast Soc Change 2018; 126: 3–13. DOI: 10.1016/j.techfore.2015.12.019.

20.

Raghupathi

. Data mining in healthcare. In Healthcare informatics: improving efficiency and productivity. 2010, pp. 211.

21.

Goli-Malekabadi

Sargolzaei-Javan

Akbari

. An effective model for store and retrieve big health data in cloud computing. Comput Methods Progr Biomed 2016; 132: 75–82.

22.

Asante-Korang

Jacobs

. Big Data and paediatric cardiovascular disease in the era of transparency in healthcare. Cardiol Young 2016; 26: 1597–1602.

23.

Boutayeb

. The double burden of communicable and non-communicable diseases in developing countries. Trans R Soc Trop Med Hyg 2006; 100: 191–199.

24.

Nambiar

Bhardwaj

Sethi

, et al. A look at challenges and opportunities of Big Data analytics in healthcare. In: Proceedings - 2013 IEEE International Conference on Big Data, Big Data 2013, CA, USA: Silicon Valley, 2013, pp. 17–22.

25.

Belle

Thiagarajan

Soroushmehr

SMR

, et al. Big data analytics in healthcare. BioMed Res Int 2015; 2015: 370194.

26.

Rouse

Serban

. Data in Healthcare. Understanding and Managing the Complexity of Healthcare. The MIT Press, 2014, pp. 183–204. http://www.jstor.org/stable/j.ctt9qf9g5.13.

27.

Mohammed

Far

Naugler

. Applications of the MapReduce programming framework to clinical big data analysis: current landscape and future trends. BioData Min 2014; 7: 22.

28.

Auffray

Balling

Barroso

, et al. Making sense of big data in health research: towards an EU action plan. Genome Med 2016; 8(1): 71.

29.

Rumsfeld

Joynt

Maddox

. Big data analytics to improve cardiovascular care: promise and challenges. Nat Rev Cardiol 2016; 13: 350–359.

30.

Weng

Kahn

. Clinical research informatics for big data and precision medicine. Yearb Med Inform 2016; 10: 211–218.

31.

Viceconti

Hunter

Hose

. Big data, big knowledge: big data for personalized healthcare. IEEE J Biomed Health Inform 2015; 19(4): 1209–1215.

32.

Chung Chow

. On big-data analytics in biomedical research. J Biometrics Biostat 2015; 06(03): 1000236.

33.

Bradley

. Implications of big data analytics on population health management. Big Data 2013; 1(3): 152–159.

34.

Hernandez

Zhang

. Using predictive analytics and big data to optimize pharmaceutical outcomes. Am J Health Syst Pharm 2017; 74(18): 1494–1500.

35.

Feldman

Martin

Skotnes

. Big data in healthcare - hype and hope. DrBonnie 360 degree (Business Development for Digital Health) 2012; 2013(1): 25.

36.

Fernandes

O’Connor

Weaver

. Big data, bigger outcomes. J AHIMA (Am Health Inf Manag Assoc) 2012; 83(10): 38–43.

37.

Sun

, et al. High energy X-ray radiation sensitive scintillating materials for medical imaging, cancer diagnosis and therapy. Nano Energy 2021; 79: 105437.

38.

Bagheri

Ahlman

Lindenberg

, et al. Advances in medical imaging for the diagnosis and management of common genitourinary cancers. Urol Oncol 2017; 35: 473–491.

39.

Bankman

. Handbook of medical image processing and analysis. Handbook of medical image processing and analysis. Academic Press, 2009, pp. 973–984.

40.

Dilsizian

Siegel

. Artificial intelligence in medicine and cardiac imaging: harnessing big data and advanced computing to provide personalized medical diagnosis and treatment. Curr Cardiol Rep 2014; 16(1): 441.

41.

Chen

Cockrell

Ward

, et al. Intracranial pressure level prediction in traumatic brain injury by extracting features from multiple sources and using machine learning methods. In: Proceedings - 2010 IEEE International Conference on Bioinformatics and Biomedicine. BIBM 2010, 2010.

42.

Yao

Zheng

, et al. Massive medical images retrieval system based on hadoop. J Multimed 2014; 9(2): 216–222.

43.

Piccazzo

Paparo

Garlaschi

. Diagnostic accuracy of chest radiography for the diagnosis of tuberculosis (tb) and its role in the detection of latent TB infection: a systematic review. J Rheumatol 2014; 41(SUPPL. 91): 32–40.

44.

Nash

Kadavigere

Andrade

, et al. Deep learning, computer-aided radiography reading for tuberculosis: a diagnostic accuracy study from a tertiary hospital in India. Sci Rep 2020; 10(1): 210.

45.

Panayides

Amini

Filipovic

, et al. AI in medical imaging informatics: current challenges and future directions. IEEE J Biomed Health Inform 2020; 24: 1837–1857.

46.

Bao

Sun

Zhang

, et al. The artificial intelligence-assisted cytology diagnostic system in large-scale cervical cancer screening: a population-based cohort study of 0.7 million women. Cancer Med 2020; 9(18): 6896–6906.

47.

Wang

Yang

Rong

, et al. Artificial intelligence in lung cancer pathology image analysis. Cancers 2019; 11: 1673.

48.

Zhu

Isikman

Mudanyali

, et al. Optical imaging techniques for point-of-care diagnostics. Lab Chip 2013; 13: 51–67.

49.

Valleron

Bouvet

Garnerin

, et al. A computer network for the surveillance of communicable diseases: the French experiment. Am J Publ Health 1986; 76(11): 1289–1292.

50.

Kuehnert

Basavaraju

Moseley

, et al. Screening of blood donations for zika virus infection — Puerto Rico, april 3–june 11, 2016. MMWR Morb Mortal Wkly Rep 2016; 65(24): 627–628.

51.

Zhang

Ibaraki

Schwartz

. Disease surveillance using online news: dengue and zika in tropical countries. J Biomed Inf 2020; 102: 103374.

52.

Woolhouse

MEJ

Rambaut

Kellam

. Lessons from Ebola: improving infectious disease surveillance to inform outbreak management. Sci Transl Med 2015; 7: 307rv5.

53.

Quick

Loman

Duraffour

, et al. Real-time, portable genome sequencing for Ebola surveillance. Nature 2016; 530(7589): 228–232.

54.

Van Kerkhove

Hirve

Koukounari

, et al. Estimating age-specific cumulative incidence for the 2009 influenza pandemic: a meta-analysis of A(H1N1)pdm09 serological studies from 19 countries. Influenza Other Respir Viruses 2013; 7: 872–886.

55.

Simonsen

Gog

Olson

, et al. Infectious disease surveillance in the big data era: towards faster and locally relevant systems. J Infect Dis 2016; 214: S380–S385.

56.

Herland

Khoshgoftaar

Wald

. A review of data mining using big data in health informatics. J Big Data 2014; 1(1): 2.

57.

Young

Rivers

Lewis

. Methods of using real-time social media technologies for detection and remote monitoring of HIV outcomes. Prev Med 2014; 63: 112–115.

58.

Nambisan

Luo

Kapoor

Patrick

Cisler

RA.

“Social Media, Big Data, and Public Health Informatics: Ruminating Behavior of Depression Revealed through Twitter,” 2015 48th Hawaii International Conference on System Sciences, Kauai, HI, USA, 2015, pp. 2906-2913, DOI: 10.1109/HICSS.2015.351.

59.

NyandaUnited Nations Development Peter.Programme. Using artificial intelligence to tackle infodemic in Tanzania . 2020. [cited 2023 Mar 15] Available from: https://www.undp.org/tanzania/blog/using-artificial-intelligence-tackle-infodemic-tanzania.

60.

Pramanik

Lau

RYK

Azad

MAK

, et al. Healthcare informatics and analytics in big data. Expert Syst Appl 2020; 152: 113388.

61.

Simpao

Ahumada

Gálvez

, et al. A review of analytics and clinical informatics in health care. J Med Syst 2014; 38: 45.

62.

Subrahmanya

SVG

Shetty

Patil

, et al. The role of data science in healthcare advancements: applications, benefits, and future prospects. Ir J Med Sci 2022; 191(4): 1473. DOI: 10.1007/s11845-021-02730-z.

63.

Azad

Shulaev

. Metabolomics technology and bioinformatics for precision medicine. Briefings Bioinf 2019; 20(6): 1957.

64.

Thomas

. What does “precision medicine” have to say about prevention? Epidemiology 2017; 28: 479–483.

65.

Gillman

Hammond

. Precision treatment and precision prevention: integrating “below and above the skin”. JAMA Pediatr 2016; 170: 9–10.

66.

Sandhya

. Big Data Analytics and Deep Learning in Bioinformatics With Hadoop, (eds) Arun Kumar Sangaiah, Deep Learning and Parallel Computing Environment for Bioengineering Systems, Academic Press, 2019, Pages 17-36, ISBN 9780128167182, DOI: 10.1016/B978-0-12-816718-2.00009-9.

67.

Gulilat

Lamb

Teft

, et al. Targeted next generation sequencing as a tool for precision medicine. BMC Med Genom 2019; 12(1): 81.

68.

Kashyap

Ahmed

Hoque

, et al. Big data analytics in bioinformatics: a machine learning perspective. ArXiv 2015; 13(9): 1–20. Available from: https://arxiv.org/abs/1506.05101.

69.

Hood

Rowen

. The human genome project: big science transforms biology and medicine. Genome Med 2013; 5(9): 79.

70.

Szlezák

Evers

Wang

, et al. The role of big data and advanced analytics in drug discovery, development, and commercialization. Clin Pharmacol Ther 2014; 95(5): 492–495.

71.

Costa

. Big data in biomedicine. Drug Discov Today 2014; 19: 433–440.

72.

Fodeh

Zeng

. Mining Big Data in biomedicine and health care. J Biomed Inf 2016; 63: 400–403.

73.

Salas-Vega

Haimann

Mossialos

. Big data and health care: challenges and opportunities for coordinated policy development in the EU. Health Syst Reform 2015; 1(4): 285–300.

74.

Zhang

Cao

Khan

, et al. A task-level adaptive MapReduce framework for real-time streaming data in healthcare applications. Future Generat Comput Syst 2015; 7: 43–44.

75.

Peek

Holmes

Sun

. Technical challenges for big data in biomedicine and health: data sources, infrastructure, and analytics. Yearb Med Inform 2014; 9: 42.

76.

Huang

Mulyasasmita

Rajagopal

. The path from big data to precision medicine. Expert Review of Precision Medicine and Drug Development, 2016, vol 1, pp. 129.

77.

Lee

Yoon

. Medical big data: promise and challenges. Kidney Res Clin Pract 2017; 36(1): 3–11.

78.

Wang

Kung

Wang

WYC

, et al. An integrated big data analytics-enabled transformation model: application to health care. Inf Manag 2018; 55(1): 64–79.

79.

Cheng

, et al. The promising future of healthcare services: when big data analytics meets wearable technology. Inf Manag 2016; 53(8): 1020–1033.

80.

Asokan

. Leveraging “big data” to enhance the effectiveness of “one health” in an era of health informatics. J Epidemiol Glob Health 2015; 5(4): 311.

81.

Grossglauser

Saner

. Data-driven healthcare: from patterns to actions. Eur J Prev Cardiol 2014; 21: 14.

82.

McNutt

Moore

Quon

. Needs and challenges for big data in radiation oncology. Int J Radiat Oncol Biol Phys 2016; 95(3): 909.

83.

Dimitrov

. Medical Internet of things and big data in healthcare. Healthc Inform Res 2016; 22: 156.

84.

Manikandan

Gokul

Abirami

, et al. Big data analytics in healthcare. Big data analytics for healthcare: datasets, techniques, life cycles. Management, and Applications 2022; 2015: 3–11.

85.

Wyber

Vaillancourt

Perry

, et al. Big data in global health: improving health in low- and middle-income countries. Bull World Health Organ 2015; 93(3): 203–208.

86.

Naydenov

Liveri

Dupre

Chalvatzi

Skouloudi

. Big Data Security Good Practices and Recommendations on the Security of Big Data Systems [Internet]. European Union Agency for Cybersecurity. Heraklion; 2015. Available from: https://www.enisa.europa.eu/publications/big-data-security/at_download/%0AfullReport.

87.

Adler-Milstein

Jha

. Healthcare’s “big data” challenge. Am J Manag Care. 2013 Jul; 19(7): 537–8.

Big data analytics in the healthcare sector: Opportunities and challenges in developing countries. A literature review

Abstract

Keywords

Summary of the key findings

Introduction

Methodology

Findings

The sources of healthcare data

Potential applications of big data analytics in the healthcare sector in developing countries

Medical image processing and analysis

Population health management and disease surveillance

Clinical informatics

Bioinformatics

Challenges to implementation of healthcare big data analytics in developing countries

Discussion

Recommendations

Limitations

Conclusion

Footnotes

Acknowledgements

Author contributions

Declaration of conflicting interests

Funding

Declaration of generative AI and AI-assisted technologies in the writing process

ORCID iDs

Data availability statement

References