Diagnosis and treatment plan prediction method and device

Abstract

The present invention provides a method and device for predicting a diagnosis and treatment plan. The feature vector of the medical entity included in the medical record text to be predicted is obtained to obtain the medical entity vector, and at the same time, the text feature vector of the medical record text to be predicted is obtained. Then, input the medical entity vector and text feature vector corresponding to the medical record text to be predicted into the pre-trained diagnosis and treatment plan prediction model, and predict the diagnosis and treatment plan that matches the medical record text to be predicted, wherein the diagnosis and treatment plan includes diagnosis and treatment drugs, At least one of surgery and inspection items. It can be seen from the above that when the present invention extracts features from the medical records to be predicted, it not only extracts the feature vectors of medical entities and their associations, but also extracts the contextual information of the medical records, which reduces information loss and improves the accuracy of the medical records to be predicted. The accuracy of the feature vector of the text improves the prediction accuracy of the diagnosis and treatment plan.

Description

technical field [0001] The invention belongs to the technical field of medical diagnosis, and in particular relates to a method and a device for predicting a diagnosis and treatment plan. Background technique [0002] At present, clinically, the diagnosis and treatment plan given by the doctor depends entirely on the doctor's own experience. In order to speed up the doctor's clinical decision-making speed, a diagnosis and treatment plan prediction system is proposed to assist the doctor to quickly give an effective diagnosis and treatment plan and reduce the patient's waiting time. . [0003] The current diagnosis and treatment plan prediction system mainly sorts out clinical rules based on the clinical experience and clinical guidelines of medical experts, and then uses the ontology reasoning machine to reason, and then predicts the corresponding diagnosis and treatment plan. However, this method needs to artificially extract clinical rules from clinical expert experience ...

AI Technical Summary

Problems solved by technology

[0004] In view of this, the object of the present invention is to provide a method and device for predicting a diagnosis and treatment plan to solve the technical problems of low accuracy and low efficiency of the current diagnosis and treatment plan prediction method. The specific technical solutions are as follows:

Images