Research on Anomaly Analysis and Judgment Method of Healthcare Based on Data-drive

Abstract

With the rapid development of social healthcare, the number of insured individuals is gradually increasing, and information technology is gradually developing. Some unreasonable medical reporting behaviors that deceive large amounts of medical insurance funds from national medical insurance institutions, hospitals, and other medical industry institutions by fabricating physical conditions and concealing real situations are seriously endangering the construction of the social health development system. At the same time, the scale of the Cyber Physical System (CPS) for medical information is constantly increasing, and the inconsistency and inefficient utilization of existing medical information standards have led to a rapid increase in the overall complexity of the system. Ordinary real-time processing systems are unable to meet the computational needs of geometrically increasing data volumes. After years of medical informatization and the application of various medical information systems, it is difficult to achieve data sharing, mapping, and fusion based on medical insurance analysis, which includes a large amount of medical visit records and electronic data covering medical treatment time, treatment costs, and other contents. This study explores the new technological innovations sought by the medical field and proposes to conduct research and analysis on healthcare service datasets in the context of big data, focusing on the relevant methods of medical insurance anomaly analysis and big data mining techniques. Methods such as medical information standardization, relationship extraction, machine learning, and big data analysis are introduced to study the structuring of medical insurance data, big data assisted medical insurance case coding, medical insurance abnormal behavior mining, and active medical insurance judgment methods. It has important practical significance and value in promoting the standardization and structuring of medical insurance data, improving the efficiency of medical insurance anomaly analysis and detection, mining medical insurance quality, and assisting medical insurance research and judgment.