RANDOM FOREST ALGORITHMS IN HEALTH CARE SECTORS: A REVIEW OF APPLICATIONS

Abstract

Safety culture is a multidimensional phrase in healthcare delivery systems that have been linked to medical errors and patient safety incidents. Despite this, there is little evidence to suggest that safety culture characteristics have an impact on overall patient safety. Aside from that, complex statistical analysis has only been applied sparingly in previous data studies on safety culture practices. In healthcare, there is a centralized organization delivery systems is a multifaceted issue that is linked to medical errors and patient safety concerns. Using health facility aggregate data from the United States, this study investigates the communication between recognized organizational safety components and patient security grade to address these safety concerns. Random forests computer vision program based on trees technique, researchers use to predict accurate and stable relationships between variables. Amidst this, there is little information available about which aspects of patient safety culture are most important. Furthermore, advanced statistical analysis in previous reviews of data on safety culture has been limited, as previously mentioned. Additionally, random forests, a machine learning technique based on trees, estimate precise and stable associations between variables. As a result, researchers used data from a study in collective US hospitals to investigate the relationship between identified safety culture components and patient safety grades. As a result of the findings, the scientists found that healthcare quality knowledge, organizational factors, and top management objectives all play a crucial influence in determining patient safety grades. Security concerns in the work unit, as well as the work environment created by hospital management, have an impact on patient safety outcomes