Medical big data access control method and device and computer readable storage medium
An access control and big data technology, applied in the field of medical data privacy protection, which can solve problems such as difficult application, ignoring uncertainty and big data environment, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0181] S1. Preprocessing of historical visit data: Divide doctors into different departments, and code the historical medical records visited by each doctor in the same department within a period of time according to ICD-10 codes; In the corresponding disease code, it is marked with "1". If the code in the historical visit record of a doctor is not in the corresponding disease code of the department, it is marked with "0", and then the labels of all doctors in the same department are converted into one Boolean matrix, the different columns in the matrix represent the historical records of doctors' visits, and the rows represent the collection of medical records of a single doctor's visits in the same department;
[0182] S2. Construct doctor matrix:
[0183] The doctor's similarity matrix is composed of the similarity of historical visit records between doctors, let s ij is the similarity between the i-th doctor and the j-th doctor, then the doctor similarity matrix S is ex...
Embodiment 2
[0210] S1. Preprocessing of historical visit data: Divide doctors into different departments, and code the historical medical records visited by each doctor in the same department within a period of time according to ICD-10 codes; In the corresponding disease code, it is marked with "1". If the code in the historical visit record of a doctor is not in the corresponding disease code of the department, it is marked with "0", and then the labels of all doctors in the same department are converted into one Boolean matrix, the different columns in the matrix represent the historical records of doctors' visits, and the rows represent the collection of medical records of a single doctor's visits in the same department; after obtaining the Boolean matrix, the same historical visits records of different doctors in the same department are merged to obtain the deduplication Matrix of historical access records;
[0211] S2. Construct doctor matrix:
[0212] The doctor's similarity matrix...
Embodiment 3
[0264] Embodiment 3: simulation test experiment
[0265] Obtain experimental data from a hospital, and the data types include text data, image data, and video data. According to the requirements of the experimental test of the method of the present invention, only part of the data is extracted from the data for experimentation;
[0266] Experimental setup: Divide doctors into two categories according to the method of the present invention, then simulate the visit requests of the two types of doctors, calculate and compare the average risk value of the two types of doctors, and observe whether the risk value of honest doctors is much lower than that of malicious doctors ;
[0267] In the simulation experiment, we divided doctors in the same department into honest doctors and malicious doctors according to their historical visit records, set doctors without visit history as honest doctors, and used Z, z i Represents the hierarchy of ICD-10 disease codes, where Z represents t...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap