Medical record migration model training method and medical record migration method based on same

By encoding and mapping the source medical records and processing them with a clinical manifestation knowledge graph, and combining this with training a large language model to generate a standardized medical record migration model, the problem of migration between electronic medical record systems and inconsistencies in clinical logic has been solved, achieving efficient and accurate medical record migration and writing.

CN122245582APending Publication Date: 2026-06-19HANGZHOU QUANXIAN MEDICAL TECH CO LTD
0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
HANGZHOU QUANXIAN MEDICAL TECH CO LTD
Filing Date
2026-03-17
Publication Date
2026-06-19

AI Technical Summary

⚠Technical Problem

Migration challenges arise between electronic medical record systems due to inconsistent data structure standards, and inconsistencies in clinical logic exist in large models during medical record conversion.

⚗Method used

By encoding and mapping the diagnostic text of the source medical record, a simplified source medical record is constructed. A list of strongly constrained elements is obtained using a clinical manifestation knowledge graph. The medical record generation model is trained by combining a large language model, and then validated and optimized to finally generate a medical record transfer model that conforms to clinical standards.

🎯Benefits of technology

The generated medical records are accurate and complete, conform to clinical expression standards, improve the efficiency and quality of medical record writing, reduce omissions and errors, have good generalization ability, and solve the migration problems and inconsistencies in clinical logic caused by the lack of uniform data structure standards between electronic medical record systems.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
Patent Text Reader

Abstract

This application relates to the field of medical informatics and data processing technology, and discloses a method for training a medical record transfer model and a method for transferring medical records based thereon. The method includes: acquiring the diagnostic text of the source medical record; encoding and mapping the chief complaint information in the diagnostic text to obtain the corresponding anchor code; and constructing a simplified source medical record based on the chief complaint information; acquiring a pre-constructed clinical manifestation knowledge graph; inputting the anchor code into the clinical manifestation knowledge graph to obtain a list of strongly constrained elements; inputting the anchor code, the list of constrained elements, and the simplified source medical record as training samples into a large language model to obtain a medical record generation model; validating the medical record generation model based on the diagnostic text, and updating the medical record generation model based on the validation results to obtain a medical record transfer model. The technical solution provided by this application solves the transfer problem caused by inconsistent data structure standards between electronic medical record systems, and the problem of inconsistent clinical logic in large models during medical record conversion.
Need to check novelty before this filing date? Find Prior Art