Medical information data item name standardization method and system, equipment and medium

Abstract

The invention relates to data standardization of medical data sources, in particular to a medical information data item name standardization method and system, equipment and a medium, which can automatically standardize data of a plurality of data sources from a literal description level, is reasonable in design, simple in processing and high in adaptability, greatly liberates manpower and improves efficiency. The method comprises the following steps: unifying and de-duplicating acquired initial data item names of a plurality of medical information data sources in a character level to obtain data items with different names; constructing an n-gram feature set of each data item according to the number of characters of the name of each data item; according to the n-gram feature set of each data item, obtaining a character level-based name similarity between every two data items, and constructing a similar matrix; and clustering the data items greater than a similarity threshold in the similar matrix, and assigning the same standardization name for all the data items in each cluster for standardization.

Description

technical field [0001] The invention relates to data standardization of medical data sources, in particular to a method, system, device and medium for standardizing names of medical information data items. Background technique [0002] With the advancement of informatization construction in various industries, massive amounts of data are stored electronically. For example, in the medical industry, more and more medical institutions use a Hospital Information System (Hospital Information System, HIS system) to manage collected data. This type of information system improves the ability of data collection and management, but also brings about the problem of data standardization from different data sources. [0003] The HIS system of each medical institution has a set of data standard methods. However, the data standardization methods of different medical institutions are usually different, and it is very difficult to implement data standardization in multiple medical institut...

AI Technical Summary

Problems solved by technology

This brings difficulties to the fusion of data from multiple data sources. Unified standardization of data from multiple data sources requires a lot of labor, time-consuming and labor-intensive. The existing standardization methods, on the one hand, vectorize the names and compare them, and the amount of calculation Large, and different vectorization will bring deviations in the results, it is impossible to unify, and standard adjustment is also difficult. On the other hand, it will establish a standard library and then standardize it after comparison, which has poor adaptability. The requirements are high, and the update is slow, and it is easy to encounter problems that cannot be matched, resulting in incomplete standardization

Images