Medical insurance big data based analysis method for measuring and calculating incidence of rare diseases

Abstract

The invention discloses a medical insurance big data based analysis method for measuring and calculating the incidence of rare diseases, and relates to medical insurance data processing and analysis technologies. Measured and calculated diseases are diseases that cannot be completely cured, so that people have to suffer from the diseases for life long time if the diseases are diagnosed. Numeratorand denominator information required by incidence calculation can be obtained by summarizing multiple key parameters of medical insurance data every month, so that the incidence can be obtained through calculation, wherein the numerator is the number of new cases of a target disease in a certain range of population within specific time, and the denominator is the number of exposed populations within the specific time, that is, people may have the target disease, but people, which have already had the disease and cannot become the new cases, need to be excluded. The incidence data can be obtained through the method, so that the development of epidemiological study of rare diseases can be promoted, and data and technology support can be provided for the reasonable making of clinical guidelines; and conversion applications of medical insurance big data can be further promoted, and the blank of epidemiological data on rare diseases in China can be filled up.

Description

technical field [0001] The invention relates to medical insurance data processing and analysis technology, in particular to an analysis method for calculating the incidence of rare diseases (Incidence) based on medical insurance big data. Background technique [0002] Rare diseases refer to a class of rare diseases with very low prevalence and incidence. At present, my country lacks information on the basic epidemic characteristics of such diseases, including incidence and prevalence. Medical insurance data (Claims data) is generally the data formed through the integration of payment information in the medical insurance administrative management system, including the basic characteristics of the insured, diagnosis, treatment and other information. Low, high operability, and longitudinal data from the real world, which is conducive to rapid and efficient epidemiological research, especially the use of national medical insurance data to provide new insights into the lack of rar...

AI Technical Summary

Problems solved by technology

In the current foreign analysis methods for the incidence of rare diseases, Raghu G and other scholars use the US Medicare medical insurance data to calculate the incidence of idiopathic pulmonary fibrosis during 2001-2011, but the calculation of these incidence rates is based on the medical insurance data. For my country's massive medical insurance data, regardless of the period, format and volume of data storage, or the span, absence, and individual out-of-insurance of data indicators, they are all different from foreign medical insurance data, so the above method cannot be directly used. In the epidemiological research of my country's medical insurance database; and looking at the research on the use of medical insurance data in China, it is found that most of them are currently focused on discovering fraud by mining medical insurance data, improving disease treatment effects, and assisting policy revisions. Data epidemiology, especially the research on the incidence and prevalence of rare diseases, makes it difficult to make full use of medical insurance big data to analyze the relevant epidemiological characteristics of rare diseases

Images