Medical record data prediction method and device and electronic equipment
A data prediction and data technology, which is applied in patient-specific data, medical data mining, instruments, etc., can solve problems such as poor interpretability and ignoring the time and sequence characteristics of medical visit records
Pending Publication Date: 2020-06-19
SHENZHEN INST OF ADVANCED TECH
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Traditional machine learning tools simply gather high-dimensional clinical variable statistics together, ignoring the characteristics of medical visit records in time and sequence, and the interpretability of traditional medical record data prediction results is poor.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0047]A method for predicting medical record data provided by an embodiment of the present invention includes such as figure 1 S100~S400 shown in the following combination figure 1 S100 to S400 will be explained.
[0048] S100: Acquire the patient's medical record data, the medical record data includes at least one visit vector, and one visit vector represents the consultation result of the patient at time t. Among them, t is a positive integer.
[0049] S200: Obtain forward sequence data and reverse sequence data based on time and access vectors in the medical record data.
[0050] S300: Obtain positive sequence attention data based on the positive sequence data, and obtain reverse sequence attention data based on the reverse sequence data.
[0051] Among them, the positive sequence attention data represents the importance of the access vector in the medical record data based on the positive sequence of time, and the reverse sequence attention data represents the importanc...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a medical record data prediction method and device and electronic equipment, and the method comprises the steps: obtaining the medical record data of a patient, wherein the medical record data comprise at least one access vector, and one access vector represents an inquiry result of the patient at the t-th time; obtaining positive sequence data and negative sequence data based on the time and the access vector in the medical record data; obtaining positive sequence attention data based on the positive sequence data, and obtaining reverse sequence attention data based onthe reverse sequence data; and based on the medical record data, the positive sequence attention data and the negative sequence attention data, obtaining an illness state prediction result of the patient. The technical problem of poor interpretability of the medical record data prediction result in the prior art is solved, and the technical effect of improving the interpretability of the illnessstate prediction result is achieved.
Description
technical field [0001] The field of electronic information processing of the present invention, in particular, relates to a medical record data prediction method, device and electronic equipment. Background technique [0002] With the widespread adoption of electronic medical record systems, accurate predictions of medical record data can improve the quality of medical care. An electronic medical record can be a time series of high-dimensional clinical variables (e.g., diagnosis, medication, treatment), where each time series contains a medical visit record for a patient. Traditional machine learning tools simply aggregate high-dimensional clinical variable statistics together, ignoring the time and sequence characteristics of medical visit records, and the predictive results of traditional medical record data are poorly interpretable. Contents of the invention [0003] The purpose of the present invention is to provide a medical record data prediction method, device and ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G16H10/60G16H50/70G06N20/00
CPCG16H10/60G16H50/70
Inventor 张建业殷鹏
Owner SHENZHEN INST OF ADVANCED TECH