Treatment scheme recommendation method and device, equipment and storage medium

Abstract

The invention discloses a treatment scheme recommendation method, and the method comprises the steps: obtaining a current case symptom and a medical case database, and extracting a candidate treatment scheme corresponding to the current case symptom from the medical case database based on a self-attention mechanism; preprocessing the candidate treatment scheme to obtain a first vector set; constructing a medical knowledge graph, extracting a medical node set from the medical knowledge graph, performing characterization learning on the medical node set by adopting a heterogeneous graph neural network, screening characterization results according to the current case symptom, and obtaining a second vector set corresponding to the current case symptom; calculating the similarity between the first vector set and the second vector set; determining a target vector from the first vector set according to a similarity calculation result, and taking a candidate treatment scheme corresponding to the target vector as a recommended treatment scheme. By means of the mode, the medical knowledge graph and the candidate treatment schemes of doctors can be fully combined, and the reliability of the recommended treatment schemes is guaranteed.

Description

technical field [0001] The present invention relates to the technical field of medical information data processing, in particular to a treatment plan recommendation method, device, equipment and storage medium. Background technique [0002] The recommendation method of disease treatment plan is very complicated, and the existing recommendation method usually adopts the method of decision tree based on rules, or the method of searching for similar plans based on existing cases. [0003] After building key decision points in the rule-based decision tree, there are usually missing or incomplete features and too many complications, which make it impossible to match the original decision rules. Therefore, the rule-based decision tree recommends disease treatment options. Strong reliability, but poor personalization. [0004] The method of searching for similar schemes based on existing cases can be evidence-based for real-world cases, and a new scheme can be selected based on ev...

AI Technical Summary

Problems solved by technology

[0002] The recommendation method of disease treatment plan is very complicated. The existing recommendation method is usually carried out by means of decision tree based on rules, or by searching for similar plans based on existing cases.

[0003] After building key decision points in the rule-based decision tree, there are usually missing or incomplete features and too many complications, which make it impossible to match the original decision rules. Therefore, the rule-based decision tree recommends disease treatment options. Great reliability, but poor personalization

[0004] The method of searching for similar schemes based on existing cases can be evidence-based for real-world cases, and a new scheme can be selected based on evidence. However, the characteristics of patients are not the same, and it is impossible to find similar cases that are 100% completely matched.

Images