Investigating the Impact of Healthcare Restructuring on Patient Experience through Data Mining

Abstract

This paper examines the consequences of healthcare mergers and acquisitions on patient experiences through a comprehensive data mining approach, combining both traditional and innovative methodologies. Utilizing web scraping techniques and machine learning algorithms, we compiled a national dataset, analyzing reviews and ratings from Google and Yelp to gauge patient perspectives pre and post healthcare restructuring. Our analysis included 10 healthcare centers, with a focus on a six-month period before and after mergers or acquisitions took effect. The study identified 35 merger events and 60 acquisition events within the dataset after refining data set, highlighting significant variations in patient experiences post-restructuring. Our two-way ANOVA revealed significant main effects for restructure type (F(1, 661) = 211.77, p < 2e-16) and time period (F(1, 661) = 29.74, p < 6.99e-08), along with a significant interaction between these factors (F(1, 661) = 201.85, p < 2e-16). This significant interaction suggests a differential impact of mergers and acquisitions on patient experience review ratings, dependent on the timing relative to the restructuring event. This decline underscores the nuanced impact of healthcare consolidation on patient care quality and access, particularly among vulnerable populations. Our findings contribute to the ongoing discourse on healthcare restructuring, demonstrating the potential of data mining in uncovering the intricate dynamics of healthcare service delivery and patient satisfaction in the context of organizational changes.