Predictive Business Analytics For Reducing Healthcare Costs And Enhancing Patient Outcomes Across U.S. Public Health Systems

Abstract

The increasing healthcare expenses, especially in U.S. government-funded health systems, are a significant burden to policymakers and medical practitioners. Although the issue of predictive analytics as an intervention in enhancing patient outcomes and cost reduction has gained traction as a concept, there is a knowledge gap in the area of how such technologies can be systematized in large-scale public health environments. The aim of the research was to assess the role of predictive business analytics in terms of healthcare costs and patient outcomes in the U.S. public health systems. The research employed a mixed-methods design, which involved both quantitative analyses of the data on costs and patient outcomes from 50 public health facilities, as well as qualitative analyses of the effectiveness of predictive models. The data were gathered in the electronic health records (EHRs) and examined with the help of regression models, t-tests, and correlation. The results showed that the healthcare costs reduced significantly (mean reduction of 8.5% p < 0.05) and that patient outcomes also improved, with a 12% decline in hospital readmission rates and a 15-point increase in patient satisfaction scores (p < 0.01). These findings highlight the possible opportunities of predictive analytics in streamlining health care delivery and minimizing expenses. The study multiplies the existing literature in the field of application of data-driven decision-making to the field of healthcare, providing empirical evidence of its effectiveness in the public health systems. This study opens the possibilities of wider implementation of predictive analytics tools to improve cost-efficiency and patient care in the field of public health.