Medical record identification method and device based on natural language processing
Through natural language processing-based methods, the risk index parameters in the medical records are extracted and analyzed, and the problem of low accuracy in medical records recognition in the prior art is solved, and more efficient medical record information extraction and analysis is achieved.
CN120220942APending Publication Date: 2025-06-27RENMIN HOSPITAL OF WUHAN UNIVERSITY (HUBEI GENERAL HOSPITAL)
0 Cites 1 Cited by
Patent Information
- Application Number
- CN202510383322.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-28
- Publication Date
- 2025-06-27
AI Technical Summary
Technical Problem
In the prior art, the accuracy of medical record recognition is low, and it is difficult to effectively extract specific information in electronic medical records.
Method used
Using a natural language processing method, by obtaining the medical record text to be predicted, inputting the risk index feature extraction model, filtering out the second and third risk index parameters, and conducting risk predictions separately to finally determine the target risk prediction results.
Benefits of technology
It improves the accuracy of medical record identification and can more effectively extract and analyze key information in medical records.
✦ Generated by Eureka AI based on patent content.
Abstract
The invention discloses a medical record recognition method and device based on natural language processing, and the method comprises the steps: obtaining a to-be-predicted medical record text; inputting a to-be-predicted medical record text into the risk index feature extraction model to obtain a plurality of first risk index parameters; screening a plurality of second risk index parameters and a plurality of third risk index parameters from the plurality of first risk index parameters; inputting the plurality of second risk index parameters into a first risk prediction model for risk prediction to obtain a first risk prediction result; inputting the plurality of third risk index parameters into a second risk prediction model for risk prediction to obtain a second risk prediction result; and determining a target risk prediction result based on the first risk prediction result and the second risk prediction result. The accuracy of medical record identification can be improved.
Need to check novelty before this filing date? Find Prior Art