Simulation text medical record generation method and system

Abstract

The invention provides a simulation text medical record generation method and system. The original medical record is applied to generate positive samples, the word vector and the disease tag vector outputted by the generator in each cycle act as inputs, a new word vector is outputted and a sentence composed of multiple word vectors is generated by repetition for many times. As each word vector isgenerated, the generated word vector sequence is taken as the initial state, generator sampling is repeatedly operated to generate multiple sentences, and the discriminator takes an average of the reward values of all the sentence as the reward value of the present word vector, the generator is updated according to the obtained reward values of the sentences and the word vector and the process isrepeated until convergence. The convergent generator generates negative samples and the negative samples and the positive samples form a mixed medical record data set. The disease tag vector and the word vector sequence act as the input, the probability of each medical record coming from the real medical record is obtained and the discriminator is updated and the process is repeated until convergence. The patient privacy is involved and the simulated text medical record can assist other machine learning tasks so as to facilitate the research on the disease.

Description

technical field [0001] The invention relates to the technical field of machine learning, in particular to a method and a system for generating medical records of simulated text. Background technique [0002] With the development of the times and the continuous improvement of informatization, the use of electronic medical records is becoming more and more extensive. At the same time, with the rapid development of machine learning and deep learning in recent years, people have begun to try to use machine learning to solve problems in the medical field and have achieved some results. However, the acquisition and use of electronic medical record data, on the one hand, may be restricted by the patient's personal wishes and laws and regulations due to issues such as patient privacy, which restricts the use of related algorithms such as machine learning based on big data; on the other hand Due to the large differences in the medical record data itself, there may be an imbalance of...

AI Technical Summary

Problems solved by technology

However, the acquisition and use of electronic medical record data, on the one hand, may be restricted by the patient's personal wishes and laws and regulations due to issues such as patient privacy, which restricts the use of related algorithms such as machine learning based on big data; on the other hand Due to the large differences in the medical record data itself, there may be an imbalance of positive and negative samples (disease samples and non-disease samples) for certain types of diseases, which will affect the effect of machine learning related algorithms

In view of the above problems, it is an effective solution to generate simulated medical record data that restores the distribution of real medical record samples as much as possible. However, few technologies currently try to solve this problem.

A small number of medical record generation and text generation related technologies also have the following problems: 1. The role is only to assist in the generation of formatted medical records to meet the needs of standard formats, reducing the work of doctors' handwriting and typesetting, and does not involve automatic generation of simulated medical records

2. It can merge existing texts to generate new texts, but it does not involve machine learning-related algorithms, and the diversity of generated texts is also very limited

3. The relevant artificial intelligence-based text generation methods have limited scope of action (only text expansion, but cannot generate full text), and the scope of application is not clear, and it is not closely integrated with the medical field

Images