Structural processing method for a thyroid ultrasound report based on a tree structure

Abstract

The invention relates to a tree-shaped structured template established according to a part-of-speech dictionary and a dependency relationship tree, and a method for structuring a thyroid ultrasound report by referring to the template. The overall process mainly comprises a part-of-speech dictionary establishing module, a tree structure template establishing module and a tree template calling structuring stage. And the part-of-speech dictionary establishing module is used for carrying out short sentence segmentation on the report and carrying out short sentence clustering. And then a complete part-of-speech dictionary is established by using a named entity recognition technology according to the organ words ORG, the position words LOC, the attribute words ATT and the attribute names. And the tree template establishing module is used for analyzing by using a dependency syntactic to obtain a semantic relationship of each short sentence and obtaining a part-of-speech of each word by usinga part-of-speech dictionary. And a tree template establishment process is provided by combining the two steps. And the tree template calling module is used for carrying out text structuring by using atree template.

Description

technical field [0001] The invention relates to a structured system based on a tree structure model, which belongs to the technical field of medical equipment. Background technique [0002] With the rapid development of medical informatization, medical institutions have produced a large amount of original electronic medical record data in the process of clinical diagnosis. These electronic medical records are important information for recording the process of patient diagnosis and treatment, and contain rich knowledge. Since electronic medical records are mostly unstructured and narrative texts, the clinical information in medical records cannot be well stored, organized and managed. Therefore, it is difficult to make full use of unstructured electronic medical records. Therefore, the current research on the analysis of electronic medical records is mainly focused on the structural aspects of electronic medical records. Data, and finally the use of artificial intelligence a...

AI Technical Summary

Problems solved by technology

[0006] (1) Dictionary-based methods cannot match complex semantic structures

The medical text structuring method using medical dictionaries has a clear process and high extraction accuracy, but the structure of clinical medical documents is diverse. If only the method based on medical dictionaries can not record the intrinsic semantic relationship between each word, such as in the thyroid ultrasound report In , there are two description forms of the attribute name "echo", which are similar to "echo distribution uniform" after the descriptor, and similar to "dense medium echo" in the front, only by matching "echo" from the dictionary One word cannot determine the position before and after the descriptor that needs to be structured

[0007] (2) Constructing a medical professional dictionary consumes a lot of manpower and time

Especially when determining the relationship between classification concepts and definition concepts and attribute labeling, it takes a lot of manpower and time, and it is inevitable that there will be missing concepts during the construction process, and updating the dictionary also requires a lot of work

[0008] (3) Simply using dependency parsing cannot segment the text into finer grains

Such key value results are not completely segmented, and the key still contains rich information that has not been extracted

[0009] (4) The structured result is just a simple key-value form, without a hierarchical structure, which is not easy to understand

Images