Big data analytics in healthcare: current practices, innovations, and future prospects

Abstract

Healthcare is one of the most important sectors, and the potential for improvement through the application of data and analytics is tremendous. The study aimed to identify the current approaches, innovations, and future directions in the healthcare industry based on big data analytics. A systematic literature review was applied to address the study’s objectives. Required studies were explored through ten digital databases that included Scopus, Web of Science, PubMed, Ovid Medline, Medline, PLOS, Global Health, Emerald, Wiley Inter Science, and Pro Quest. Thirty-five peer-reviewed research papers published in key digital databases from 2014 to 2025 were selected to conduct the study. This study has addressed a specific gap in the literature that is the lack of a consolidated and up-to-date synthesis of technological advancements and implementation challenges related to big data analytics in healthcare. While various studies have examined individual aspects of big data in healthcare, there is a critical need for a holistic and integrative review that maps out current practices, emerging innovations, and persistent barriers. This research addresses that gap through a comprehensive overview of big data analytics across various dimensions of the healthcare sector. Findings of the study revealed that big data analytics assisted in clinical decision support, population health management, healthcare industry improvement, and electronic health data transformation. The study revealed that machine learning and artificial intelligence, blockchain technology, and cloud computing are the most important technological innovations in health information analysis tools. It also indicated that data privacy, technical complications, and expertise and resources caused challenges for the adoption of big data analytics in the healthcare industry. Robust privacy and security measures need to be developed for ensuring confidentiality of sensitive medical data. Sufficient financial resources should be provided for the implementation of big data analytics in healthcare organizations to ensure compatibility. Staff training should be ensured to cultivate required skills to efficiently manage health systems based on big data analytics. Data standards should be established to address challenges related to complex variables and differences in data entry preferences. Documented policies, procedures, and clear guidelines should be developed to manage sensitive patients’ information. The study’s original contributions include: (1) a categorized synthesis of enabling technologies (AI/ML, blockchain, cloud computing); (2) a structured classification of implementation challenges (data privacy, technical complexity, lack of expertise and resources); and (3) strategic recommendations for addressing these challenges through workforce training, policy frameworks, data governance, and collaborative ecosystems. These contributions are grounded in a comprehensive synthesis of existing literature and offer clear direction for future research, implementation efforts, and policy development. This work has offered a comprehensive synthesis of the state-of-the-art in big data analytics for healthcare through key approaches, innovations, and prospective developments.

Ähnliche Arbeiten