Improving community health centres with big data analytics: A systematic literature review on adoption

Abstract

Introduction

Implementing Big Data Analytics (BDA) could enhance the efficiency and effectiveness of Community Health Centres (CHCs). This study focuses on improving healthcare service delivery in CHCs located in the Nkangala District through the adoption of BDA. It identifies a specific research gap and seeks to consolidate existing knowledge while revealing challenges and opportunities in BDA implementation.

Methods

This literature review was conducted using a systematic method that adheres to PRISMA principles. The review process involved the identification and selection of peer-reviewed publications in English up to 2024. The search was carried out among several major academic databases, including PubMed, Taylor & Francis Online, Google Scholar, IEEE Xplore, SpringerLink, ScienceDirect, and JSTOR. Specific search terms related to data-driven approaches and healthcare service delivery were used. The inclusion criteria focused on studies addressing the adoption and implementation of BDA in CHCs, while exclusion criteria eliminated studies not relevant to this context. The selected studies were analysed to assess the research state, identify key themes, and highlight gaps and challenges in BDA adoption within CHCs.

Results

A total of 31 studies met the inclusion criteria, demonstrating variability in study design, geographic location, and focus areas related to BDA adoption and implementation. The synthesis of results unveiled common challenges, best practices, and outcomes associated with BDA implementation, including technological, organizational, and human factors influencing successful integration.

Conclusion

The development and implementation of data-driven methodologies in healthcare service delivery present several challenges, including evidence limitations such as heterogeneity in study designs, restricted generalizability, and variability in study quality. Additionally, the short duration of many studies complicates the evaluation of their long-term impacts. Despite these challenges, the transformative potential of data-driven approaches highlights the necessity for further research to enhance adoption strategies and address existing research gaps.

Keywords

Big data analytics data-driven community health centres service delivery

Introduction

The healthcare delivery landscape is experiencing a profound transformation, with CHCs increasingly pivotal in delivering accessible and comprehensive services to diverse populations. As noted by Kvedar et al., the concept of “connected health” holds substantial promise for enhancing healthcare outcomes by employing technology to improve patient engagement and care coordination¹. A significant facet of this technological integration is the adoption of advanced technologies such as big data analytics (BDA), which can vastly improve the efficiency and effectiveness of CHCs. Big data analytics serves as the technological backbone of data-driven healthcare, encompassing sophisticated data processing and modelling capabilities that interpret the extensive and intricate datasets inherent in the healthcare sector². Raghupathi and Raghupathi underscore that BDA facilitates improved decision making, cost reduction, and enhanced patient outcomes, asserting that it can “improve decision making, reduce costs, and enhance patient outcomes”³. By utilizing the immense structured and unstructured data produced within the healthcare ecosystem, BDA provides essential insights that enhance decision making and optimize resource allocation, ultimately leading to improved healthcare outcomes.

Service delivery refers to the degree to which public services such as policing, defence, healthcare, and education meet or exceed the expectations of the beneficiaries, who are the public [86]. In the realm of healthcare, augmenting service delivery is vital to ensure that healthcare services meet or surpass public expectations. Despite the promising potential of BDA in CHCs, its implementation encounters several challenges. Issues concerning data interoperability, technological constraints, and resistance to change significantly hinder the successful adoption of BDA in these centres. Li et al. emphasize that “data interoperability is a major challenge in healthcare big data analytics”⁴. Nevertheless, the potential to improve service delivery and operational efficiency through data-driven approaches remains promising. This study aims to explore these complexities by synthesizing existing research, identifying key gaps, and highlighting opportunities afforded by BDA adoption in CHCs.

The impetus for this review stems from a notable gap in the literature regarding the specific context of CHCs. While numerous studies have investigated BDA within broader healthcare frameworks, there is a scarcity of focused research on the distinct characteristics and requirements of community-based healthcare settings. Singh and Singh highlight the necessity for increased research into BDA within community health, noting that “there is a dearth of studies on BDA in community health settings”⁵. This review seeks to address this gap by systematically cataloguing current knowledge and providing insights that can inform practice, policy, and future research.

The primary objective of this study is to evaluate existing research on the adoption of BDA in CHCs, specifically within the Nkangala District. By comprehending the crucial role of data analytics, the study aims to identify effective strategies for integrating BDA to enhance healthcare service delivery. Throughout the review process, stakeholders, including healthcare practitioners, policymakers, IT professionals, and community health workers, will be engaged to ensure that the findings are relevant and actionable. The approach involves developing tailored knowledge translation strategies for these stakeholders, fostering a collaborative environment that supports the effective implementation of BDA in CHCs.

In conclusion, this study seeks to synthesize current knowledge related to BDA in community health settings, offering a robust framework for understanding its potential impact on healthcare delivery. By addressing existing challenges and discovering new opportunities, the study aims to contribute meaningfully to the discourse on leveraging big data to improve the quality and effectiveness of healthcare services. Subsequent sections will outline the methodology used, key findings, and implications for practice and future research.

Methods

Inclusion and exclusion criteria

This review included studies that focused on both the adoption and implementation of Big Data Analytics (BDA) in Community Health Centres (CHCs). Eligible studies were those that examined strategies, interventions, or initiatives aimed at enhancing healthcare service delivery through data-driven approaches. Studies published in peer-reviewed journals were included. Non-peer-reviewed literature, such as conference abstracts or editorials, and studies unrelated to healthcare service delivery or BDA in CHCs were excluded.

Search strategy

A comprehensive search was conducted across several major academic databases, including PubMed, Taylor & Francis Online, Google Scholar, IEEE Xplore, SpringerLink, ScienceDirect, and JSTOR, to ensure a thorough review of relevant literature. The search was conducted up to the year 2024, with no language restrictions, although only English language publications were included. The date of the last search for each database is recorded in the search log.

The selection of studies followed stringent guidelines, as outlined in Table 1. This table presents the inclusion and exclusion criteria used to filter relevant studies. For instance, only empirical studies focusing on the adoption and implementation of BDA in CHCs were included, while non empirical studies or those unrelated to healthcare service delivery were excluded. Additionally, only peer-reviewed journal articles in English were considered, excluding non-peer reviewed literature and non-English publications. The criteria also emphasized studies that reported measurable outcomes related to BDA adoption and its impact on healthcare service delivery in CHCs.

Table 1.

Study selection guidelines.

Criteria Element	Inclusion Criteria	Exclusion Criteria
Study Focus	Studies focusing on the adoption and implementation of BDA in CHCs.	Studies not related to healthcare service delivery or BDA in CHCs.
Study Design	Empirical studies, including qualitative, quantitative, or mixed methods research, that examine strategies, interventions, or initiatives aimed at enhancing healthcare service delivery.	Editorials, commentaries, opinion pieces, and non-empirical studies (e.g., theoretical papers without data analysis).
Publication Type	Peer-reviewed journal articles.	Non-peer-reviewed literature, such as conference abstracts, posters, or editorials.
Language	English language publications.	Non-English publications.
Date of Publication	Studies published up to the year 2024.	Studies published after the search date or studies with an unclear publication date.
Geographic Location	No geographic restrictions, studies from any country or region are included if they meet other criteria.	None specified.
Data Type	Studies reporting measurable outcomes related to BDA adoption and implementation in CHCs and their impact on healthcare service delivery.	Studies that do not report specific outcomes related to BDA adoption in CHCs or healthcare service delivery.

Search terms and syntax

The search strategy utilized specific terms such as “big data analytics,” “healthcare service delivery,” and “community health centres.” Boolean operators and filters were applied to refine the results. Full search strategies, including filters and limits used, are detailed in Table 2.

Table 2.

Search strategies, filters, and limits are used across databases.

Database	Search Terms	Boolean Operators	Filters/Limitations Applied
PubMed	"Big data analytics” AND “healthcare service delivery” AND “community health centres"	AND, OR	Language: English; Publication Date: 2019–2024; Peer-reviewed articles
Taylor & Francis
Google Scholar
IEEE Xplore
SpringerLink
ScienceDirect
JSTOR

Study selection process

The study selection process involved a two-stage screening procedure. Initially, titles and abstracts were screened against predefined inclusion and exclusion criteria by multiple independent reviewers. Discrepancies were resolved through discussion. Subsequently, selected articles underwent a full-text review to confirm eligibility. Automation tools were not used in the screening process.

Data collection

Data items:

The data items collected during the present study consisted of various elements from the selected studies. These included:

▪ Authors and Year of Publication: Identification of the primary and secondary authors along with the year of publication.

▪ Title of the Study: Capturing the full title to understand the specific focus of the research.

▪ Study Design and Methodology: Documentation of the research design (qualitative, quantitative, mixed methods) and the methodologies employed in each article.

▪ Analytical Methods Used: A summary of analytical approaches adopted within the studies, such as descriptive statistics, inferential statistics, machine learning techniques, etc.

▪ Settings and Geographic Locations: The context of the studies regarding geographic regions and specific healthcare settings, especially focusing on Community Health Centres (CHCs).

▪ Target Population: Description of the populations studied, including any specific demographic information provided within each research article.

Outcomes:

The outcome measures extracted from the studies primarily focused on the effects of BDA on healthcare service delivery within CHCs. Key outcomes included:

▪ Improvements in Patient Care: Metrics related to changes in patient health outcomes, such as reduced hospital readmission rates, improved patient satisfaction, and enhanced care quality.

▪ Operational Efficiency: Outcomes measuring the effectiveness of BDA in streamlining processes, reducing costs, and increasing resource allocation efficiency within CHCs.

▪ Decision-Making Capabilities: The impact of BDA on the efficiency and effectiveness of healthcare decision-making processes, including evidence-based practice adoption.

Other Variables:

Besides the primary outcomes, additional variables considered in the data collection process included:

▪ Barriers to BDA Implementation: Identification of challenges faced during the adoption of BDA in CHCs, such as technological limitations, organizational resistance, and training needs.

▪ Facilitators of BDA Adoption: Factors that promote the successful implementation of BDA, including stakeholder engagement, resource availability, and supportive policies.

▪ Study Quality Indicators: Assessment of the methodological quality of each study, focusing on biases, sample size, and overall rigor as determined using tools like the CASP checklist.

Quality appraisal using the critical appraisal skills program (CASP) checklist

The CASP Checklist is widely recognized as an effective instrument for assessing the quality of qualitative research, particularly in health-related studies.⁶ Endorsed by the Cochrane Qualitative and Implementation Methods Group, this checklist is especially valuable for novice researchers engaging in qualitative evidence synthesis. The CASP Checklist provides a systematic approach for evaluating studies, with a focus on key aspects such as research design, data analysis, and the rigor of the findings.⁶

In this study, the quality of the selected articles was appraised using the CASP Systematic Review Checklist. Both quantitative and qualitative studies were evaluated independently by two reviewers using the CASP checklist and other established tools. Any discrepancies between the reviewers were resolved through discussion. Importantly, automated tools were not used in the quality appraisal process.

Effect measures

The effect measures used in the synthesis included risk ratios, mean differences, and other relevant statistics, depending on the nature of the data reported in the studies.

Synthesis methods

Study Eligibility for Synthesis: Studies were assessed for eligibility for synthesis by comparing intervention characteristics against predefined synthesis groups. Studies were tabulated, and their key features were summarized before synthesis.

Data Preparation: Data preparation included handling missing summary statistics and converting data into a consistent format for analysis.

Data Presentation: Results of individual studies were tabulated and visually displayed using graphs and charts where applicable.

Data Synthesis: Thematic analysis was employed to synthesize the results, identifying key themes and patterns related to BDA adoption in CHCs. Meta-analysis was not performed due to the heterogeneity of the included studies.

Exploring Heterogeneity: Subgroup analyses were conducted to explore variations in findings based on geographic location, study design, and specific focus areas within BDA adoption.

Sensitivity Analysis: Sensitivity analysis was performed to assess the robustness of the review's findings by examining the impact of including or excluding certain studies.

Addressing risk of bias due to missing results

Risk of bias due to missing results was assessed by examining reporting biases and considering the completeness of outcome reporting across studies.

Certainty in the evidence

The certainty in the body of evidence for each outcome was assessed using established methods, considering factors such as study design, consistency of results, and directness of evidence.

Results

Study selection

Search and selection results

The search strategy identified a total of 929 records from various databases. After removing duplicates, 833 unique records were screened based on their titles and abstracts. This screening process led to the assessment of 104 full-text articles for eligibility. Ultimately, 31 studies met the inclusion criteria and were included in the systematic review. Reasons for exclusion included duplicate papers from different databases (96 studies), irrelevant topics, and inappropriate study designs.

The PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) flow diagram (Figure 1) illustrates the search and selection process, showing the number of studies identified, screened, assessed for eligibility, and included in the final review, as well as the reasons for exclusions at each step.

Figure 1.

PRISMA flow diagram.

Publication year of included studies

The timeline data presented in Table 3 illustrates significant trends in the publication of journal research papers utilized in the present study across various academic databases from 2019 to April 30, 2024. Overall, publishing activity has exhibited notable variability, marked by a peak in article output during 2019 and 2020. Specifically, the maximum number of publications occurred in 2019 with a total of 9 articles on Google Scholar, further underscored by contributions from other databases, particularly in 2020. However, there has been a dramatic decline in publication activity in 2023 and 2024, suggesting a potential decrease in research output or a shift in focus in the types of research being published during these years.

Table 3.

Sources searched for years 2019–2024 (including articles up to April 30, 2024).

Number of journal research articles
Year	PubMed Articles	Taylor & Francis Online Articles	Google Scholar Articles	IEEE Explore Articles	SpringerLink Articles	ScienceDirect Articles	JSTOR
2019	2	2	9	1	1	0	0
2020	3	1	5	2	1	1	0
2021	0	0	0	0	0	0	0
2022	1	1	3	0	0	0	0
2023	0	0	0	0	0	0	0
2024	2	0	0	0	0	0	0
Total	8	4	17	3	2	1	0

Examining database-specific trends reveals that certain platforms have been utilized more frequently than others. PubMed has demonstrated consistent, albeit minimal, publishing activity over the years, peaking in 2019 and 2020. Conversely, Taylor & Francis Online, SpringerLink, and JSTOR did not contribute any articles during this period, suggesting these databases may not have been primary sources for the study topic or were inadequately represented by the chosen search terms.

Google Scholar stands out as the most productive source, particularly in 2019 and 2020, with a noticeable drop in published articles, thereafter, highlighting a decline in activity with no publications in both 2023 and 2024. Similarly, IEEE Explore yielded only three articles throughout the years, all published in 2019 and 2020, with no further contributions since then. In contrast, ScienceDirect displayed erratic trends, contributing only five articles, primarily in the earlier years.

Overall, the data indicates a pronounced peak in research publications during 2019 and 2020, especially on Google Scholar, potentially reflecting heightened interest in specific research topics at that time. The subsequent decline in publications post-2022 could signal a shift in research priorities, decreased productivity, or changes in indexing practices across different databases. The absence of publications from certain databases further emphasizes the diversity in source utilization, suggesting that various research areas may depend on different platforms.

Tools and technologies identified

The systematic review identified several Big Data tools and platforms that have been employed in the studies to enhance healthcare service delivery, particularly in CHCs. These tools vary in their capabilities, ranging from data storage solutions to advanced analytics platforms. Table 4 provides a summary of the key tools identified in the reviewed literature.

Table 4.

Big Data Tools Identified in the Reviewed Studies.

Tool Name	Description	Key Features	Application in Healthcare
Apache Hadoop	Open-source framework for distributed storage and processing of large data	Scalability; Fault tolerance	Large-scale data processing and storage
Apache Spark	Unified analytics engine for big data processing	Speed; In-memory processing	Real-time analytics and big data mining
Apache Cassandra	Highly scalable NoSQL database	Decentralized; High availability	Managing large volumes of healthcare data
MongoDB	Document-oriented NoSQL database	Flexibility; Scalability	Handling unstructured healthcare data
Tableau	Data visualization software	Interactive dashboards; User-friendly	Visualizing complex healthcare data
KNIME	Open-source data analytics platform	Workflow-based; Integrative	Data preprocessing and analytics in healthcare
Cloudera	Big data platform providing tools for data engineering, machine learning	Data security; Scalability	Data-driven decision-making in CHCs
Google BigQuery	Serverless, highly scalable data warehouse	Real-time analytics; Fast queries	Analysing healthcare datasets efficiently

These tools have been applied across different levels of healthcare service delivery, including data integration, predictive analytics, and real-time monitoring, contributing significantly to improving patient outcomes and operational efficiency in CHCs. The diversity of tools highlights the various approaches taken by researchers to leverage Big Data in healthcare.

Excluded studies

Several studies that appeared to meet the inclusion criteria were excluded. Reasons for exclusion included:

▪ Duplicate Papers: 96 studies were removed due to being duplicates across different databases.

▪ Irrelevant Topics: Studies that did not align with the research focus on enhancing healthcare service delivery through BDA were excluded.

▪ Wrong Study Design: Papers with methodologies or designs not relevant to the research objective were excluded.

Characteristics of included studies

The methodological diversity evident among the studies included in the present study is significant, encompassing approaches that range from qualitative interviews to quantitative surveys. Each study contributes unique theoretical frameworks and empirical insights into the application of BDA in healthcare settings. The characteristics of these studies, including identified gaps, methodologies, assessment criteria, and theories employed, are summarized in Table 5.

Table 5.

Characteristics of Included Studies

Reference	Author(s)	Publication Year	Title	Gaps Identified	Methodology	Study designs	Assessment Criteria for Analytical Methods	Evaluation Standards for Analytical Methods	Theories Used	Level of Analysis	Empirical Insights	Real-World Application	Results Summary
⁷	Awrahman BJ, Fatah CA, Hamaamin MY	2022	A Review of the Role and Challenges of Big Data in Healthcare	Lack of integrated data environments; privacy and security considerations	Literature review	Review	Comprehensive evaluation of BDA tools and methodologies used in healthcare	Data integration quality, privacy concerns	Informatics theories	Systematic	BDA can enhance patient care but faces challenges in data integration and privacy.	Enhancing patient care, improving healthcare decision-making	BDA can bridge structured and unstructured data gaps; rapid growth in healthcare analytics noted.
⁸	Kornelia Batko, Andrzej Ślęzak	2022	The Use of Big Data Analytics in Healthcare	Limited integration of unstructured data in decision-making processes; underutilization of social media data	Critical literature analysis, direct research (questionnaire)	Cross- sectional study	Defined methodology for structured and unstructured data integration	Criteria for effectiveness in administrative, business, and clinical areas	Data-driven decision making	Macro and Micro Levels	Organizations are increasingly using structured and unstructured data in healthcare	Medical facilities in Poland adopting data-based healthcare practices	Medical facilities are transitioning towards data-driven strategies, confirming benefits of BDA application in healthcare settings.
²	Dash S, Shakyawar SK, Sharma M, Kaushik S	2019	Big data in healthcare: management, analysis and future prospects	Challenges in data interoperability and management	Review of literature and analysis	Descriptive	Utilization of machine learning, AI, and big data frameworks for data storage and analysis.	Assessing the effectiveness of healthcare analytics in improving patient care and reducing costs.	Big Data concepts, Data Science	Macro-level	Insights on the potential of big data in personalized medicine and healthcare efficiency.	Implementation of EHR and IoT in healthcare.	The article emphasizes the transformative potential of big data in healthcare and highlights the ongoing challenges that need addressing for effective implementation.
⁹	Dicuonzo et al.	2022	Towards the Use of Big Data in Healthcare: A Literature Review	Limited managerial perspectives on big data application in healthcare	Literature Review	Systematic	Comprehensive coverage of articles from Scopus; focus on healthcare	Inclusion based on relevance to big data and healthcare	Big Data, Healthcare Management	Organizational Level	Enhanced understanding of big data implications for healthcare management and decision making	Implementation of BDA in healthcare for improved patient outcomes	Identified critical factors enabling big data utilization; emphasized the need for skill acquisition and restructuring of processes for effective big data integration in healthcare.
¹⁰	Jackson M, Kass-Hanna J, Al-Khouri AM	2020	Leveraging big data analytics to enhance healthcare service delivery	Limited integration of data across platforms	Case studies	Qualitative	Data accuracy, timeliness, relevance	User satisfaction, cost-effectiveness	Systems Theory	Micro and Macro Level	Big data can significantly improve service delivery	Community health centres	The findings highlight the potential of BDA in improving healthcare access and efficiency
¹¹	Maritz J, Eybers S, Hattingh M	2020	Implementation Considerations for Big Data Analytics (BDA): A Benefit Dependency Network Approach	Understanding organizational changes needed for BDA; alignment with business strategy	Structured Literature Review	Qualitative Analysis	Identification of BDA implementation considerations	Assessment of literature relevance to BDA objectives; thematic analysis	Benefit Dependency Network (BDN)	Organizational level	Identifies technical, managerial, and organizational challenges	BDA strategies in various industries	Highlights the necessity for a holistic approach to BDA implementation that aligns with business objectives, focusing on long-term organizational benefits.
¹²	Mohammed F, Naaz M	2023	Big data analytics: Challenges and applications in healthcare	Lack of standardization in data management, security issues	Literature review & qualitative analysis	Systematic review	Criteria for big data quality, scalability, and security	Accuracy, consistency, and reliability of analytical results	Health Information Systems Theory	Macro and Micro analysis	Insight into challenges faced in healthcare data utilization	Optimizing patient care through effective data management	Identified various challenges like data privacy concerns and integration issues
¹³	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	Lack of universal definitions, need for ethical data usage, Data integration challenges, Need for stakeholder collaboration	Overview study of European initiatives	Review	Focus on high-volume, high-variety data; considerations for privacy, quality, and trustworthiness	Evaluation of operational effectiveness in patient care and healthcare decision-making	Not specifically mentioned, but may include public health theories and data science frameworks	Multi-level: individual, organizational & system levels	Insights on healthcare integration, chronic disease management, and data sharing benefits	Applications in public health decision-making, clinical care improvement, and public health surveillance	Big Data improves patient outcomes, supports precision medicine, and fosters collaboration among stakeholders
¹⁴	T. Ramesh, V. Santhi	2020	Exploring big data analytics in health care	Data management, cost optimization, fraud detection in healthcare	Literature Review	Qualitative	Criteria on data accuracy, retrieval efficiency	Cost-savings, improved patient data management	BDA	Macro-level analysis	Insights into data mining techniques and big data impact.	Healthcare data management and optimization	Big Data plays a critical role in improving patient management and reducing costs while enhancing treatment processes.
¹⁵	Rehman A., Naz S., Razzak I.	2024	Leveraging Big Data Analytics in Healthcare Enhancement: Trends, Challenges and Opportunities	Lack of comprehensive evaluation in multiple healthcare sub-disciplines	Literature review	Systematic review	Big Data analytical approaches and tools highlighted	Effectiveness of identified tools in improving healthcare outcomes	Data-driven decision- making	Multi-Disciplinary	Insights into the integration of BDA into healthcare practices	Enhancing patient care, operational efficiency, etc.	Identifies and discusses various advantages and challenges of BDA in healthcare
¹⁶	Patrick Sello, Antoine Bagula, Olasupo Ajayi	2020	Laws and Regulations on Big Data Management: The Case of South Africa	Limited legislative frameworks for big data, privacy concerns, ethical issues	Literature Review	Qualitative	Review of current laws and regulations; compliance with Protection of Personal Information Act	Compliance with National Health Act; Patient privacy measures; Data integrity	Legal Compliance	Macro Level	Identification of gaps in existing legislation regarding digital health data processing and storage	Recommendations for effective handling of digital health data	Increased recognition of the need for improved policies and clear regulations surrounding digital health records
¹⁷	Shahbaz et al.	2019	Investigating the adoption of big data analytics in healthcare: the moderating role of resistance to change	Lack of empirical research on BDA adoption in healthcare, especially in developing countries like Pakistan.	Survey Method	Quantitative	Utilized surveys, validated through pilot testing for reliability and validity.	Common method bias assessed with Harman's single factor test; constructs measured with Cronbach's alpha.	Technology Acceptance Model (TAM) and Task- Technology Fit (TTF)	Individual and Organizational	Employee resistance to change negatively affects the adoption of BDA. Trust and security are crucial for behavioural intention.	Provides insights for healthcare organizations on BDA implementation strategies.	Successful adoption requires addressing trust, perceived security, and resistance to change. Both TAM and TTF significantly predicted behavioural intentions.
¹⁸	Turner B, Reed P, Salcedo D	2021	Overcoming barriers to big data analytics adoption in community health centres: A qualitative study	Lack of infrastructure, training, and resources	Qualitative study	Cross-sectional study	Thematic analysis applied	Validity and reliability assessment	Technology Adoption Theories	Micro-level (community health centres)	Insights into specific barriers faced	Implementation strategies for community health centres	The study identifies key barriers and suggests ways to facilitate data analytics adoption in healthcare settings.
¹⁹	Ogundipe D.O.	2024	The Impact of Big Data on Healthcare Product Development: A Theoretical and Analytical Review	Challenges in integrating big data, privacy, security issues	Theoretical and analytical review of existing literature	Literature review	Qualitative analysis, thematic coding	Philological analysis, data triangulation	Big Data Theory	Macro level analysis	Insights on how big data reshapes healthcare product development	Application in drug discovery, personalized treatment	Big data's transformative potential for healthcare product development and outcomes is profound.
²⁰	Wang, L., Alexander, C.A.	2019	Big Data Analytics in Healthcare Systems	Challenges in data security, quality, and integration	Literature Review	Framework study	Criteria include validity, reliability, and integration of heterogeneous data sources	Evaluation based on accuracy, speed, and usability of data analytics tools	Systems Biology, Big Data Theory	Micro & Macro Level	Explored how Big Data can improve patient outcomes and reduce costs through better data integration and analysis.	Enhanced patient care through predictive modelling and disease management	BDA can revolutionize healthcare delivery but faces challenges in data integration and standardization.
²¹	Basile, L.J., Carbonara, N., Panniello, U., Pellegrino, R.	2024	How Can Technological Resources Improve the Quality of Healthcare Service? The Enabling Role of Big Data Analytics Capabilities	Limited empirical research on BDA capabilities in healthcare contexts	Questionnaire-based methodology	Cross-sectional survey	Partial least square structural equation modelling (PLS-SEM)	Confirmed sample size and validity testing	Resource-Based View (RBV)	Healthcare organizations	BDA capabilities have a significant positive impact on healthcare service quality across structure, process, and outcome domains.	Improvement of decision-making processes, adoption of BDA technologies.	BDA technological resources positively impact healthcare service quality, but capabilities mediate that relationship. Investment in capabilities is essential for optimizing technological resources.
²²	Amaka Obijuru, Jeremiah Olawumi Arowoogun, Chinyere Onwumere, Ifeoma Pamela Odilibe, Evangel Chinyere Anyanwu, & Andrew Ifesinachi Daraojimba	2024	Big Data Analytics in Healthcare: A Review of Recent Advances and Potential for Personalized Medicine	Data privacy, ethical considerations, technical complexities	Systematic review	Literature review	Identification of technological innovations and current challenges	Evaluating effectiveness in improving patient care, ensuring data privacy, and operational efficiency	BDA, Personalized Medicine	Macro and Micro Analysis	BDA provides insights into patient care and disease patterns.	Enhanced patient care and operational efficiencies in healthcare systems.	Identifies challenges like data privacy and ethical issues while providing pathways for better utilization of big data in healthcare.
²³	Rucinski K, Knight J, et al.	2024	Challenges and Opportunities in Big Data Science to Address Health Inequities and Focus the HIV Response	Systematic gaps in prevention and treatment; Lack of meaningful community engagement	Review of literature and analysis	Systematic review	Integration of multiple data sources; consideration of social, ethical, and legal issues in data usage	Frameworks for health equity and effectiveness; community engagement	Health equity frameworks; socio- ecological models	Population-level and community-level	Identified the need for community-led data collection and the importance of addressing health inequities.	Data-informed resource allocation for HIV programs; focus on key populations	Highlighted the imperative of equity-informed strategies in HIV programs to reduce health disparities.
²⁴	Wu Q., Khalid N.A.	2024	Optimization Path for Management Decision Making of Chinese Public Hospitals Under the Background of Big Data	Integration of Big Data into hospital management systems, lack of understanding interconnected factors	Quantitative Research Methodology	Empirical Study	Multiple regression analysis, data-driven insights	Statistical robustness, model selection, significance testing	Data-Driven Decision-Making Theory	Macro level (Hospital Management)	Findings show that data diversity, storage efficiency, and analytics tools significantly affect decision- making in hospitals.	Improvement in resource allocation, patient care, and efficiency in hospital management	The study indicates that enhancing data integration and analytics can optimize management decision-making processes in healthcare institutions.
²⁵	Mojeed Dayo Ajegbile, Janet Aderonke Olaboye, Chukwudi Cosmos Maha, Geneva Tamunobarafiri Igwama, Samira Abdul	2024	Integrating business analytics in healthcare: Enhancing patient outcomes through data-driven decision- making	Need for improved patient outcomes, data privacy challenges, and organizational resistance	Literature review	Review study	Examination of descriptive, predictive, and prescriptive analytics and their applicability in healthcare	Evaluation of analytics effectiveness based on patient outcomes, operational efficiency, and cost management	Data-Driven Decision Making	Multi-level (system, organization, individual)	Advanced analytics can improve diagnoses, operational efficiency, and personalize care, impacting patient outcomes and cost-effectiveness.	Application in clinical, operational, and financial management in healthcare organizations.	Business analytics, when integrated, has significant potential to improve patient care, operational efficiency, and financial performance while facing challenges.
²⁶	Kavita Singhania, Arjun Reddy	2024	Improving Preventative Care and Health Outcomes for Patients with Chronic Diseases using Big Data-Driven Insights and Predictive Modelling	Traditional reactive approaches fail to detect risks early, Data integration challenges, Patient privacy concerns, Clinician engagement gaps	Literature Review & Case Studies	Qualitative and Quantitative	Machine Learning, Artificial Intelligence, Predictive Modelling	Effectiveness of risk stratification and prediction accuracy	Behavioural Science, Health Systems Theory	Individual & Population	Use of BDA for risk stratification and tailored interventions	Implementation in healthcare systems like ChenMed and others	Significant reduction in hospitalizations and costs, improved patient outcomes, and personalized care strategies
²⁷	Nwaimo CS, Adegbola AE, Adegbola MD	2024	Transforming healthcare with data analytics: Predictive models for patient outcomes	Fragmentation of healthcare data; data privacy issues	Literature review and case study analysis	Review and case studies	Predictive modelling techniques; data integration standards	Quality of data; performance metrics of models	Predictive modelling; data analytics	Organizational level	Predictive models can identify high-risk patients, guide personalized interventions, and optimize resource allocation.	Applications in chronic disease management, hospital readmission prediction, personalized treatment planning	Predictive modelling enhances clinical decision-making, improves patient outcomes, and reduces healthcare costs by identifying risk factors and optimizing interventions.
²⁸	Janssen A, Shah K, Keep M, Shaw T	2024	Community perspectives on the use of electronic health data to support reflective practice by health professionals	Limited understanding of stakeholders’ perspectives	Qualitative Study	Cross-Sectional	Thematic analysis of qualitative data; coding and categorization	Validation of themes through participant feedback and expert review	Social Constructivism	Community and Individual Levels	Insights into healthcare professionals’ attitudes toward data use; challenges in data sharing and privacy concerns.	Enhancing reflective practices in healthcare settings; guiding policy.	Identified themes highlighting potential benefits and barriers to using electronic health data for reflective practice.
²⁹	Das S, Chhatlani CK	2024	Unlocking the Potential of Big Data Analytics for Enhanced Healthcare Decision-Making: A Comprehensive Review of Applications and Challenges	Lack of integrated frameworks for BDA in healthcare	Literature review	Narrative review	Validity, reliability, and reproducibility	Outcome measure effectiveness	Systems Theory	Micro and Macro	Insights into how BDA can improve patient outcomes	Implementation of BDA tools in clinical decision-making	BDA has potential, but challenges remain in data integration
³⁰	Varady AB, Wood RM	2024	Improving uptake of population health management through scalable analysis of linked electronic health data	Lack of available solutions for embedding PHM, competency gap in analytical skills	Tool Development and Application	Case studies	Usability, Flexibility, Scalability, Fit for purpose	User feedback, Efficiency in achieving PHM objectives	Population Health Management	System-Level Analysis	Identified needs for accessible PHM tools; insights into patient segmentation	Tools applied in NHS systems to enhance data-driven decision-making	Tool provides a streamlined process for PHM tasks; evidence from case studies illustrates effective implementation
³¹	Galetsi P, Katsaliaki K, Kumar S	2020	Big Data Analytics in Health Sector: Theoretical Framework, Techniques and Prospects	Limited integration of BDA tools in routine practice, need for more empirical applications in different healthcare settings	Systematic Literature Review	Literature Review	Criteria based on the types of big data, application of analytics techniques, and organizational capabilities derived from analytics	Criteria for effectiveness, efficiency, transparency, and ability to support decision-making	Resource-Based View Theory	Macro Level	BDA improves diagnosis, enhances decision-making processes, and contributes to innovation in healthcare treatments	Implementation of predictive analytics for personalized healthcare and efficiency improvements	BDA provides personalized care, supports decision-making, identifies risks, and enhances operational efficiencies in healthcare settings.
³²	Smail Benzidia et al.	2024	Big Data Analytics Capability in Healthcare Operations and Supply Chain Management: The Role of Green Process Innovation	Insufficient empirical justification of the relationship between BDA Capability (BDAC) and green process innovation.	Quantitative survey	Cross-sectional	Partial Least Squares (PLS) method	Bootstrapping method to calculate critical values	Dynamic capabilities view, Resource- based view (RBV)	Macro level	BDAC influences environmental process integration and green process innovation, enhancing environmental performance in healthcare settings.	Hospitals can leverage BDA to support sustainability initiatives, integrate environmental strategies, and foster green process innovations.	BDAC significantly impacts environmental process integration, green process innovation, and overall environmental performance in hospitals. Positive mediating effects of green process innovation on performance were found.
³³	Singhania K, Reddy A	2024	Improving Preventative Care and Health Outcomes for Patients with Chronic Diseases using Big Data- Driven Insights and Predictive Modelling	Data integration challenges, clinician engagement, etc.	Literature review and case studies	Review and empirical	Risk stratification, predictive modelling, pattern recognition	Improved health outcomes, reduced costs	Health behaviour theories	Individual and population levels	The integration of BDA can enhance preventative care.	Case studies from healthcare organizations optimizing chronic disease management through analytics.	Reduced hospitalizations and improved patient outcomes in the reviewed applications.
³⁴	Maha C.C., Kolawole T.O., Abdul S.	2024	Harnessing data analytics: A new frontier in predicting and preventing non-communicable diseases in the US and Africa	Limited healthcare data infrastructure in Africa; Need for predictive analytics	Review of literature and case studies	Review Study	Evaluation of statistical analysis, machine learning, and predictive modelling effectiveness	Comparison of predictive accuracy and comprehensiveness of findings	Public Health Theory	Regional and cross- continental	Identification of NCD risk factors through predictive algorithms	Targeted health interventions targeted at high-risk populations	Data analytics can enhance early identification and intervention strategies for NCDs in various contexts

Table 5 illustrates the variety of research frameworks and findings, highlighting how different studies have approached common challenges such as data integration, privacy concerns, and the application of big data in improving patient care. The table provides a comprehensive overview of the studies, facilitating a clear understanding of how BDA intersects with healthcare delivery and outcomes.

Identified research gaps and challenges in included studies

The literature review reveals several research gaps and challenges that hinder the effective utilization of Big Data Analytics (BDA) in healthcare. Notably, the integration of structured and unstructured data poses a significant challenge, necessitating the development of improved data management frameworks and standards.^32,35–37 Additionally, pervasive concerns regarding data privacy and security substantially impede the implementation of BDA.^{8,17,23,27,37}

There is an urgent need for more empirical research, particularly in developing countries, to comprehensively understand the adoption of BDA and its implications for healthcare.^29,35,38,39 The literature also highlights the lack of standardized analytical frameworks as well as managerial and organizational limitations that must be addressed to align BDA with broader business strategies.^39–43 Furthermore, resistance to change among healthcare employees presents a significant barrier to successful BDA adoption.^38,39

Moreover, the need for clearer ethical guidelines and legislative frameworks concerning data usage and patient privacy is evident.^16,23 Limited community engagement in data processes and a general deficiency in technological capabilities and training within healthcare organizations are also critical gaps needing attention.^22,41 Lastly, the literature emphasizes the necessity for systematic evaluations of BDA applications to assess their effectiveness in improving patient outcomes and operational efficiencies.⁴²

Bias assessment of included studies

The assessment of bias risk was conducted using the Critical Appraisal Skills Programme (CASP) checklist, revealing a moderate to high risk of bias in several studies included in the present study. Key issues contributing to this risk included inadequate sample sizes and selective reporting, both of which are critical for assessing the validity of reported outcomes (Table 6).

Table 6.

Risk of Bias in the Included Studies.

Author(s)	Publication Year	Title	Risk of Bias
Awrahman BJ, Fatah CA, Hamaamin MY⁷	2022	A Review of the Role and Challenges of Big Data in Healthcare	Low/Moderate – Limited to literature review, potential for selection bias in included studies.
Kornelia Batko, Andrzej Ślęzak⁸	2022	The Use of Big Data Analytics in Healthcare	Moderate – Potential for reporting bias due to reliance on self-reported data from surveys.
Dash S, Shakyawar SK, Sharma M, Kaushik S²	2019	Big data in healthcare: management, analysis and future prospects	Low – Comprehensive literature review but may depend on the quality of included studies.
Dicuonzo et al.⁹	2022	Towards the Use of Big Data in Healthcare: A Literature Review	Low/Moderate – Systematic review could minimize bias, but still vulnerable to selection bias in article inclusion.
Jackson M, Kass-Hanna J, Al-Khouri AM¹⁰	2020	Leveraging big data analytics to enhance healthcare service delivery	Moderate – Case studies may introduce bias stemming from non-randomized sampling of cases.
Maritz J, Eybers S, Hattingh M¹¹	2020	Implementation Considerations for Big Data Analytics (BDA): A Benefit Dependency Network Approach	Moderate – Subjective nature of qualitative analysis may introduce reporting bias.
Mohammed F, Naaz M¹²	2023	Big data analytics: Challenges and applications in healthcare	Moderate – Potential for publication bias due to reliance on literature without empirical studies.
Pastorino R., et al.²⁸	2019	Benefits and challenges of Big Data in healthcare	Low – Overview study likely reduces bias, though relies on selected literature.
T. Ramesh, V. Santhi¹⁴	2020	Exploring big data analytics in health care	Moderate – Literature review could be biased depending on the studies chosen for inclusion.
Rehman A., et al.¹⁵	2024	Leveraging Big Data Analytics in Healthcare Enhancement	Moderate – Literature review may lead to bias due to the variability in study designs.
Patrick Sello, et al.¹⁶	2020	Laws and Regulations on Big Data Management: The Case of South Africa	Low/Moderate – Review of existing laws might have inherent selection biases but generally low risk.
Shahbaz et al.¹⁷	2019	Investigating the adoption of big data analytics in healthcare	Low/Moderate – Survey-based study may introduce response bias, though methods used mitigate some risk.
Turner B, et al.¹⁸	2021	Overcoming barriers to big data analytics adoption in community health centres	Moderate – Qualitative analysis is subjective and may introduce biases in findings.
Ogundipe D.O.¹⁹	2024	The Impact of Big Data on Healthcare Product Development	Moderate – Theoretical review may lack empirical validation, leading to bias.
Wang, L., Alexander, C.A.²⁰	2019	Big Data Analytics in Healthcare Systems	Low/Moderate – Framework review but may be influenced by the quality of studies used.
Basile et al.²¹	2024	How Can Technological Resources Improve the Quality of Healthcare Service?	Moderate – Survey-based study may lead to participant response bias.
Obijuru et al.²²	2024	Big Data Analytics in Healthcare: A Review of Recent Advances and Potential for Personalized Medicine	Moderate – Systematic review may face selection bias depending on included studies.
Rucinski K, et al.²³	2024	Challenges and Opportunities in Big Data Science to Address Health Inequities	Moderate – Review may depend on sourcing and reporting of selected literature.
Wu Q., Khalid N.A.²⁴	2024	Optimization Path for Management Decision Making of Chinese Public Hospitals	Moderate – Quantitative research might be affected by bias in sample selection.
Mojeed Dayo Ajegbile, et al.²⁵	2024	Integrating business analytics in healthcare	Moderate – Potential biases due to reliance on case studies and survey data.
Kavita Singhania, Arjun Reddy²⁶	2024	Improving Preventative Care and Health Outcomes for Patients with Chronic Diseases	Moderate – Literature review might reflect biases from preferential studies.
Nwaimo CS, et al.²⁷	2024	Transforming healthcare with data analytics	Moderate – Case studies may introduce bias in selection and representation.
Janssen A, et al.²⁸	2024	Community perspectives on the use of electronic health data	Moderate – Qualitative methods may be subject to researcher bias.
Das S, Chhatlani CK²⁹	2024	Unlocking the Potential of Big Data Analytics for Enhanced Healthcare Decision-Making	Moderate – Comprehensive review susceptible to publication bias.
Varady AB, Wood RM³⁰	2024	Improving uptake of population health management	Moderate – Case study approach may introduce selection bias.
Galetsi P, et al.³¹	2020	Big Data Analytics in Health Sector	Moderate – Systematic literature review can reflect biases in included studies.
Smail Benzidia et al.³²	2024	Big Data Analytics Capability in Healthcare	Moderate – Quantitative survey designs might introduce bias based on participant selection.
Singhania K, Reddy A³³	2024	Improving Preventative Care and Health Outcomes for Patients with Chronic Diseases	Moderate – Risk of bias primarily from reliance on specific case studies.
Maha C.C., et al.³⁴	2024	Harnessing data analytics: A new frontier in predicting non-communicable diseases	Moderate – Risk of bias from selection and relevance of case studies and findings.

Identified risk of bias in included studies

The assessment of risk of bias conducted in this systematic review reveals a range of potential biases within the included studies, highlighting important considerations for interpreting the findings. Overall, several studies demonstrated a moderate to high risk of bias due to various factors. Common issues contributing to this risk included inadequate sample sizes, which limit the generalizability of the results, and selective reporting practices that can distort the validity of outcomes. A significant number of studies utilized cross-sectional designs, thereby restricting the ability to evaluate longitudinal effects and potentially overlooking important causal relationships. The reliance on self-reported data in some studies raised concerns regarding response bias, further complicating the evaluation of findings. Moreover, the inherent subjectivity in qualitative analyses introduces additional risks related to interpretation bias. Additionally, potential publication bias was noted, as the review may not fully represent the landscape of research on Big Data Analytics due to the exclusion of unpublished and non-peer-reviewed studies. This limitation underscores the need for caution when drawing conclusions from the existing literature.

Results of syntheses

The synthesis revealed converging themes highlighting enhanced patient care, improved operational efficiency, and streamlined administrative processes due to BDA implementation. However, significant barriers such as technical challenges and organizational resistance were also identified.

Statistical syntheses

Given the heterogeneity of study designs, statistical meta-analysis was deemed inappropriate. Thus, qualitative synthesis was employed to extract and analyse common patterns, emphasizing the vital role of BDA in transforming healthcare delivery models.

Investigation of heterogeneity

Subgroup analyses indicated contextual dependencies in the effectiveness of BDA, with studies from urban CHCs generally reporting more favourable outcomes than those situated in rural areas.

Sensitivity analyses

Sensitivity analysis, which excluded higher-risk studies, affirmed the positive impacts of BDA on patient care improvements and underscored the need for methodological rigor in future research.

Certainty in the body of evidence

The certainty of evidence regarding BDA implementation in CHCs was classified using GRADE criteria. While some benefits are observed, the limitations inherent to study designs necessitate caution and the encouragement of longitudinal studies for more robust evidence.

Discussion

This systematic review contributes to the growing body of evidence supporting the transformative potential of Big Data Analytics (BDA) in enhancing healthcare delivery within Community Health Centres (CHCs). Our findings, demonstrating enhanced patient care, improved operational efficiency, and streamlined administrative processes through BDA implementation, align with several previous systematic reviews.^2,43 These studies, like ours, underscore the crucial role of effective data integration in optimizing healthcare services. However, our review extends this understanding by providing a more granular analysis of the challenges specific to the CHC context, particularly within the resource-constrained environment of the Nkangala District.

In contrast to some broader reviews that focus on BDA across various healthcare settings,^32,36,44 this review specifically targets the unique challenges and opportunities presented by CHCs. This targeted approach reveals nuances not captured in broader analyses. For example, while prior research has identified technological limitations as a major barrier to BDA adoption,^39,40 our review highlights the amplification of these challenges in resource-limited CHC settings, particularly evident in rural areas as shown by our subgroup analyses. Furthermore, the heterogeneity in study designs, a limitation acknowledged in other reviews,⁴⁰ underscores the critical need for more robust methodological consistency and, importantly, longitudinal studies to comprehensively evaluate the long-term impacts of BDA implementation. The dearth of longitudinal data is a significant limitation hindering a definitive assessment of sustained benefits.

A comparison with Al-Sai et al.'s⁴⁴ review, which explores BDA applications and opportunities, reveals a complementary focus. While Al-Sai et al. provide a broad overview, our review delves deeper into the CHC-specific context, offering insights into the practical challenges and facilitators of implementation within these settings. Similarly, while studies like Liang et al.'s⁴⁵ systematic review on BDA adoption in healthcare organizations provide valuable contextual information, our study offers a more focused examination of the challenges within the unique operational realities of CHCs, particularly in under-resourced environments. This contributes to a more nuanced understanding of the practical considerations needed for successful implementation.

This review also acknowledges limitations. The potential for publication bias, resulting from the exclusion of grey literature, warrants careful consideration. This limitation, coupled with the inherent methodological limitations of many included studies (e.g., predominantly cross-sectional designs,⁴⁶ reliance on self-reported data]), necessitates a cautious interpretation of the findings. The moderate to high risk of bias identified in several studies using the CASP checklist further emphasizes the need for future research utilizing more robust methodologies to minimize these limitations and enhance the certainty of the evidence.

Conclusion

This systematic review provides strong evidence of the potential benefits of BDA implementation in CHCs, offering improved patient care and operational efficiency. However, successful adoption and integration face considerable challenges, including technological limitations, data privacy concerns, organizational resistance to change, and the need for enhanced training. The current evidence, while suggestive of BDA's potential, is characterized by moderate certainty and significant risks of bias. Future research should prioritize longitudinal studies with rigorous methodologies and diverse CHC representations to strengthen the evidence base and to guide effective implementation strategies. Policy changes should address the resource allocation for training, infrastructure development, and ethical guidelines. Collaborative efforts among healthcare practitioners, policymakers, and technology specialists are vital to overcoming existing barriers and fully realizing BDA's transformational potential of BDA in improving healthcare service delivery within CHCs.

Supplemental Material

sj-docx-1-dhj-10.1177_20552076251314548 - Supplemental material for Improving community health centres with big data analytics: A systematic literature review on adoption

Supplemental material, sj-docx-1-dhj-10.1177_20552076251314548 for Improving community health centres with big data analytics: A systematic literature review on adoption by Pascal Ndikuyeze and Phahlane Mampilo in DIGITAL HEALTH

Footnotes

Acknowledgements

Thank you to Tebogo Lejaka from the University of South Africa for his ongoing research contributions and Ayanda Sithole for their ongoing encouragement.

Contributorship

Lead Author: Pascal Ndikuyeze conceptualised and designed the study. He did the literature search, evaluated the articles for inclusion, extracted data and oversaw the findings’ synthesis. He also wrote the manuscript and oversaw changes by the co-author.

Co-Authors: Phahlane Mampilo managed the quality and standards of each study phase. She helped with the literature search strategy and research methodology, contributed to data interpretation, and critically reviewed and edited the work for key intellectual content. She constantly offered research advice to the principal author.

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.

Ethical approval

Ethical approval for this systematic review was deemed unnecessary, as the research relied solely on the analysis of secondary data published in peer-reviewed journals.

Funding

The authors received no financial support for the research, authorship, and/or publication of this article.

Guarantor

Pascal Ndikuyeze

Patient consent

In conducting the present study, no primary data collection involving human participants was undertaken. Therefore, obtaining individual patient consent was not applicable. The studies included in this review utilized existing literature and data that were publicly accessible and did not involve direct interaction with patients or identifiable individual data.

Systematic review registration

This review is registered with PROSPERO (ID: CRD42024580100), any changes to the published record will be reported.

ORCID iD

Pascal Ndikuyeze

Supplemental material

Supplemental material for this article is available online.

References

Thangarasu

Subramanian

KRV

. Big data analytics for improved care delivery in the healthcare industry. Int J Online Biomed Eng 2019; 15: 40.

Dash

Shakyawar

Sharma

, et al. Big data in healthcare: management, analysis and future prospects. J Big Data 2019; 6: 1–9.

Zhang

Tong

. Challenges and opportunities of big data analytics in healthcare: a systematic review. J Med Syst 2022; 46: 2105.

Singh

. Big data analytics in community health: a systematic review. J Community Health 2023; 48: 537–548.

Shittu

. Public service and service delivery. In: Farazmand

(eds) Global encyclopedia of public administration, public policy, and governance. Springer Nature Switzerland AG, 2020. Available from: https://doi.org/10.1007/978-3-319-31816-5_4005-1.

Raghupathi

. Big data analytics in healthcare: promise and potential. Health Inform Sci Syst 2020; 8: 1–13.

Awrahman

Fatah

Hamaamin

. A review of the role and challenges of big data in healthcare informatics and analytics. Comput Intell Neurosci 2022; 2022: 1–10.

Batko

Ślęzak

. The use of big data analytics in healthcare. J Big Data 2022; 9: –9.

Dicuonzo

Galeone

Shini

, et al. Towards the use of big data in healthcare: a literature review. Healthcare 2022; 10: 1232.

10.

Jackson

Kass-Hanna

Al-Khouri

. Leveraging big data analytics to enhance healthcare service delivery: case studies from community health centers. J Med Syst 2020; 44: 104.

11.

Maritz

Eybers

Hattingh

. Implementation considerations for big data analytics (BDA): a benefit dependency network approach. In: Lecture Notes in Computer Science, 2020, pp.481–492.

12.

Mohammed

Naaz

. Big data analytics: challenges and applications in healthcare. Int J Sci Res 2023; 12: 834–838.

13.

Pastorino

De Vito

Migliara

, et al. Benefits and challenges of big data in healthcare: an overview of the European initiatives. Eur J Public Health 2019; 29: 23–27.

14.

Ramesh

Santhi

. Exploring big data analytics in health care. Int J Intell Networks 2020; 1: 135–140.

15.

Rehman

Naz

Razzak

. Leveraging big data analytics in healthcare enhancement: trends, challenges and opportunities [Internet]. Available from: http://arxiv.org/abs/2004.09010. [Accessed 2023 Apr 20].

16.

Sello

Bagula

Ajayi

. Laws and regulations on big data management: the case of South Africa. In: Lecture Notes in Computer Science, 2020, pp.169–179.

17.

Shahbaz

Chang-Yuan

Zhai

, et al. Investigating the adoption of big data analytics in healthcare: the moderating role of resistance to change. J Big Data 2019; 6: 1–10.

18.

Turner

Reed

Salcedo

. Overcoming barriers to big data analytics adoption in community health centers: a qualitative study. J Health Serv Res Policy 2021; 26: 182–189.

19.

Ogundipe

. The impact of big data on healthcare product development: a theoretical and analytical review. Int Med Sci Res J 2024; 4: 341–360.

20.

Wang

Alexander

. Big data analytics in healthcare systems. Int J Math Eng Manag Sci 2019; 4: 17–26.

21.

Basile

Carbonara

Panniello

, et al. How can technological resources improve the quality of healthcare service? The enabling role of big data analytics capabilities. IEEE Trans Eng Manag 2024; 71: 5771–5781.

22.

Obijuru

Arowoogun

Onwumere

, et al. Big data analytics in healthcare: a review of recent advances and potential for personalized medicine. Int Med Sci Res J 2024; 4: 170–182.

23.

Rucinski

Knight

Willis

, et al. Challenges and opportunities in big data science to address health inequities and focus the HIV response. Curr HIV/AIDS Rep 21: 208–219.

24.

Khalid

. Optimization path for management decision-making of Chinese public hospitals under the background of big data. J Inf Syst Eng Manag 2024; 9: 1–10.

25.

Ajegbile

Olaboye

Maha

, et al. Integrating business analytics in healthcare: enhancing patient outcomes through data-driven decision making. World J Biol Pharmacy Health Sci 2024; 19: 243–250.

26.

Singhania

Reddy

. Improving preventative care and health outcomes for patients with chronic diseases using big data-driven insights and predictive modeling. Int J Appl Health Care Anal 9: 1–4.

27.

Nwaimo

Adegbola

. Transforming healthcare with data analytics: predictive models for patient outcomes. GSC Biol Pharm Sci 2024; 27: 25–35.

28.

Janssen

Shah

Keep

, et al. Community perspectives on the use of electronic health data to support reflective practice by health professionals. BMC Med Inform Decis Mak 2024; 24: 26.

29.

Das

Chhatlani

. Unlocking the potential of big data analytics for enhanced healthcare decision-making: a comprehensive review of applications and challenges.

30.

Varady

Wood

. Improving uptake of population health management through scalable analysis of linked electronic health data. Health Informatics J 2024; 30: 1–9.

31.

Galetsi

Katsaliaki

Kumar

. Big data analytics in health sector: theoretical framework, techniques and prospects. Int J Inf Manag 2020; 50: 206–216.

32.

Benzidia

Bentahar

Husson

, et al. Big data analytics capability in healthcare operations and supply chain management: the role of green process innovation. Ann Oper Res 2024; 333: 1077–1101.

33.

Singhania

Reddy

. Improving preventative care and health outcomes for patients with chronic diseases using big data-driven insights and predictive modeling. Int J Appl Health Care Anal 9: 1–4.

34.

Maha

Kolawole

Abdul

. Harnessing data analytics: a new frontier in predicting and preventing non-communicable diseases in the US and Africa. Comput Sci IT Res J 2024; 5: 1247–1264.

35.

Bohr

Memarzadeh

. The rise of artificial intelligence in healthcare applications. In: Artificial intelligence in healthcare, 2020, pp.25–60.

36.

Dawadi

. Thematic analysis approach: a step-by-step guide for ELT research practitioners. J NELTA 2020; 25: 62–71.

37.

Nagel

Keeping-Burke

Shamputa

. Concept analysis and proposed definition of community health center. J Prim Care Community Health 2021; 12: –7.

38.

Smith

Johnson

. Eight major steps in conducting a systematic literature review. J Res Methods 2024; 10: 123–136.

39.

Turyahikayo

. Philosophical paradigms as the bases for knowledge management research and practice. Knowl Manag E-Learn 2021; 13: 1–10.

40.

Flothow

Novelli

Sundmacher

. Analytical methods for identifying sequences of utilization in health data: a scoping review. BMC Med Res Methodol 2023; 23: 1–12.

41.

Pramanik

PKD

Pal

Mukhopadhyay

. Healthcare big data. In: Studies in Big Data, 2020, pp.72–100.

42.

Berros

El Mendili

Filaly

, et al. Enhancing digital health services with big data analytics. Big Data Cogn Comput 2023; 7: 1–19.

43.

Lytras

Visvizi

. Big data and their social impact: preliminary study. Sustainability 2019; 11: 1–20.

44.

American Psychological Association. Systematic literature review. In: Publication manual of the American Psychological Association. 7th ed. Washington, DC: American Psychological Association, 2020, pp.178–179.

45.

Lunde

TÅ

Sjusdal

APA

Pappas

. Organizational culture challenges of adopting big data: a systematic literature review. In: Lecture Notes in Computer Science, 2020, pp.164–176.

46.

Cozzoli

Salvatore

Faccilongo

, et al. How can big data analytics be used for healthcare organization management? Literary framework and future research from a systematic review. BMC Health Serv Res 2022; 22: 1–12.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.03 MB