A method for estimating disease prevalence based on medical insurance big data

Abstract

The invention discloses a method for calculating the prevalence of diseases based on medical insurance big data. The number of new and old cases of a certain disease in the total population within a specific time is used as the molecule for calculating the prevalence, and the total population within a specific time As the denominator for calculating the prevalence rate; by summarizing multiple key parameters of monthly medical insurance data, including: the total number of insured individuals per month, the number of newly insured individuals per month, the total number of monthly medical records, and the lack of diagnosis of monthly medical records The total number; obtain the numerator and denominator information of the prevalence rate calculation, and then calculate the prevalence rate. The method of the present invention is based on medical insurance big data, which is simple, fast and effective, and can replace the existing epidemiological population survey that consumes human resources and property, transform the prevalence calculation strategy based on panel data, and optimize the execution efficiency of data storage and calculation. Reduce the risk of privacy leakage and the threshold of data sharing, and promote the transformation and application of medical insurance big data.

Description

technical field [0001] The present invention relates to data processing technology, and in particular to a method for measuring and calculating disease prevalence based on medical insurance big data, specifically performing statistical operations on the corresponding numerator and denominator of highly efficient counting prevalence in a summary data format. Background technique [0002] Medical insurance data (Claims data) is the data obtained during the medical insurance business process. Since it does not require sampling surveys, it naturally covers a large-scale population and records the medical information of the population within a certain period of time. It is increasingly used Mostly used in disease prevalence studies. [0003] In conventional epidemiological studies, the calculation of prevalence requires the population size of the denominator to be determined and the number of cases corresponding to a certain period of time to be counted. However, for the huge am...

AI Technical Summary

Problems solved by technology

Foreign research is based on individual raw data, and the amount of data matches the performance of computing resources. However, my country's medical insurance population exceeds 1.3 billion, and under the scenario of massive data with many times and years, the traditional computing strategy of building individual panel data will lead to data sparseness, Problems such as information redundancy, storage and computing difficulties

Images