BUSINESS INTELLIGENCE AND PREDICTIVE ANALYTICS FOR IMPROVING PUBLIC HEALTHCARE OPERATIONS: A SYSTEMATIC LITERATURE REVIEW

Abstract

Public healthcare systems worldwide face mounting pressure to deliver safe, timely, and cost-efficient services under conditions of constrained budgets, workforce shortages, and rising patient demand. Business intelligence (BI) and predictive analytics have emerged as central enablers of data-driven decision-making in this environment, transforming fragmented operational, clinical, and financial data into actionable insight. This paper presents a systematic narrative review of the peer-reviewed literature published between 2015 and 2025 on the application of BI and predictive analytics to public healthcare operations. Following a structured search of Google Scholar and allied academic databases, forty studies were selected and synthesized around four themes: (1) the conceptual architecture of healthcare BI systems, including data warehousing, extract-transform-load pipelines, and visualization layers; (2) predictive analytics techniques, ranging from classical statistical forecasting to ensemble machine learning and deep learning; (3) operational application domains, namely patient flow and bed management, workforce and staffing optimization, supply chain and inventory management, disease surveillance, financial and fraud analytics, and clinical performance dashboards; and (4) the organizational, technical, and ethical barriers that constrain adoption, particularly in resource-limited and public-sector settings. The review finds consistent evidence that BI-enabled predictive analytics improves forecasting accuracy for admissions and resource demand, reduces preventable readmissions, shortens waiting times, and strengthens managerial decision-making, while also revealing persistent challenges around data quality, interoperability, governance, workforce analytics literacy, and equitable access to these technologies in low- and middle-income health systems. The paper concludes with an integrated conceptual framework linking data infrastructure, analytic capability, and organizational readiness, and proposes an agenda for future research emphasizing explainable artificial intelligence, real-time analytics, and governance frameworks tailored to public healthcare operations.