CN-121687357-B - Intelligent management method for health data of neurosurgery patient

CN121687357BCN 121687357 BCN121687357 BCN 121687357BCN-121687357-B

Abstract

The invention relates to the technical field of electronic medical record data management, in particular to an intelligent management method for health data of neurosurgical patients. The method comprises the steps of firstly obtaining an electronic medical record of a current patient, further obtaining a physical state score of the patient at each time point according to deviation characteristics of health data of each data dimension, further obtaining importance parameters of each treatment node according to change characteristics of the physical state score, screening important nodes, further obtaining correction association coefficients of each important node and each data dimension, further obtaining value coefficients of the health data of each dimension at each time point according to time intervals of each important node and the current time point and combining the corresponding correction association coefficients and the importance parameters and the deviation characteristics of the health data of each dimension, storing the health data based on the value coefficients, optimizing a storage mode of the health data, and relieving management pressure.

Inventors

ZHAO HUWEI
TIE JIA
DU XIN
YANG DAWEI
ZHAO KE
SU HAIDONG
LIU QINYI
SU YU
Ren Yingjuan
PU XIAOLI
ZHAO YUE
Xu Xuanle
MA SHUYIN
LIU SHUYAN
LIN LIZHEN
LI YANNI

Assignees

咸阳市第一人民医院

Dates

Publication Date: 20260512
Application Date: 20260209

Claims (8)

1. An intelligent management method for health data of a neurosurgical patient, which is characterized by comprising the following steps: Acquiring an electronic medical record of a current patient, wherein the electronic medical record comprises multidimensional health data of a plurality of time points, records of a plurality of treatment nodes and corresponding operation labels; at each time point, according to the deviation characteristics of the health data of each data dimension compared with a preset standard range, acquiring the physical state score of the patient at each time point; according to the change characteristics of the physical state scores, the importance parameters of each treatment node are obtained; According to the interval characteristics among the important nodes, combining the importance parameters of each important node to obtain a judgment time domain interval of each important node; in the judging time domain interval of each important node, acquiring the association coefficient of each important node and each data dimension according to the fluctuation intense characteristic of the health data of each data dimension; according to the association coefficients of all important nodes and each data dimension under each type of operation label, the correction association coefficients of each important node and each data dimension are obtained by combining the corresponding association coefficients; According to the time interval between each important node and the current time point, the corresponding correction association coefficient and importance parameter are combined, and the deviation characteristics of the health data of each dimension are obtained, so that the value coefficient of the health data of each dimension of each time point is obtained; the value coefficient acquisition method comprises the following steps: obtaining a reference coefficient of each health data of each data dimension in a judging time domain interval of each treatment node through a reference coefficient calculation formula, wherein the reference coefficient calculation formula comprises the following steps: ; Wherein, the J represents the sequence number of the data dimension, k represents the sequence number of the health data; Represent the first In a judging time domain interval of the important nodes, the reference coefficient of the kth health data in the jth data dimension; Represent the first Time intervals between the important nodes and the current time point; Represent the first Importance parameters of the important nodes; Represent the first Correction association coefficients of the important nodes and the jth data dimension; Represent the first In the judging time domain interval of the important nodes, the data value of the kth health data in the jth data dimension; representing a linear normalization function; taking the maximum reference coefficient corresponding to the health data of each dimension of each time point as the value coefficient of the health data of each dimension of each time point; Based on the value coefficient, storing the health data, cold storing the health data with the value coefficient smaller than the preset value threshold, and directly storing the health data with the value coefficient larger than or equal to the preset value threshold.
2. The method for intelligently managing health data of a neurosurgical patient according to claim 1, wherein the method for acquiring the physical state score comprises: The physical state score is obtained through a physical state score calculation formula, wherein the physical state score calculation formula comprises the following steps: ; wherein t represents the sequence number of the time point; a physical state score representing a t-th time point, J representing the number of data dimensions, J representing the sequence number of the data dimensions; representing the maximum value of a preset standard range of the jth data dimension; representing the minimum value of a preset standard range of the jth data dimension; representing the median value of a preset standard range of the jth data dimension; a data value representing a jth data dimension of a t-th point in time; The representation takes absolute value.
3. The method for intelligently managing health data of a neurosurgical patient according to claim 1, wherein the method for acquiring importance parameters comprises the steps of: taking the absolute value of the difference value of the physical state scores of the adjacent time points on two sides of the time domain of each treatment node as the physical change degree of each treatment node; the importance parameters of each treatment node are obtained through an importance parameter calculation formula, wherein the importance parameter calculation formula comprises the following steps: ; wherein i represents the time sequence number of the treatment node; an importance parameter representing an ith treatment node; Representing a time interval between the i-1 th treatment node and the i-th treatment node; representing the degree of physical change of the i-1 th treatment node; Representing a time interval between the (i+1) th treatment node and the (i) th treatment node; representing the degree of physical change of the (i+1) th treatment node; representing a linear normalization function.
4. The method for intelligently managing health data of a neurosurgical patient according to claim 3, wherein the method for acquiring the important nodes comprises the steps of: And marking the treatment nodes with importance parameters larger than a preset importance threshold as important nodes.
5. The method for intelligently managing health data of a neurosurgical patient according to claim 1, wherein the method for acquiring the decision time domain interval comprises: acquiring an average value of time intervals between all adjacent two important nodes as an interval basic value; taking the product of the importance parameter and the interval basic value of each important node and the sum of the interval basic value as the interval range length of each important node, taking the recording time point of each important node as the center, and constructing the judgment time domain interval of each important node by taking the interval range length as the center.
6. The method for intelligently managing health data of a neurosurgical patient according to claim 1, wherein the method for acquiring the association coefficients comprises: The method comprises the steps of selecting any important node as a target node, selecting any data dimension as a target dimension, acquiring a data sequence formed by health data of the target dimension in a judging time domain interval of the target node, and arranging the health data in the data sequence according to a time sequence; and normalizing the product of the average absolute deviation and the average frequency of the data sequence to obtain the association coefficient of the target node and the target dimension.
7. The method for intelligently managing health data of a neurosurgical patient according to claim 6, wherein the method for acquiring the correction association coefficient comprises: when the association coefficient of the target node and the target dimension is larger than a preset association threshold, judging that the association is strong; the method comprises the steps that in all treatment nodes of the same class operation label of a target node, the probability that the target dimension is judged to be strongly associated is obtained as association probability; And taking the product of the association probability corresponding to the target node and the association coefficient as a corrected association coefficient of the target node.
8. The method for intelligently managing health data of a neurosurgical patient according to claim 1, wherein when a patient has a plurality of electronic medical records, a value coefficient of health data of each dimension at each time point is acquired respectively in each electronic medical record, and the health data is stored based on the value coefficients.

Description

Intelligent management method for health data of neurosurgery patient Technical Field The invention relates to the technical field of electronic medical record data management, in particular to an intelligent management method for health data of neurosurgical patients. Background The existing method for managing the health data of the patient is usually realized by utilizing an electronic medical record, namely, the medical record, the operation record, the laboratory examination result, the medication record and other health data of the patient are summarized through digital records, and the sharing among medical institutions can be realized, so that the health data of the patient can be ensured to be accessed by a proper medical provider anytime and anywhere. However, since neurosurgical diseases require a long time from the start of treatment to the complete rehabilitation, the amount of health data corresponding to each patient increases with time, and as the number of patients increases simultaneously, the pressure on patient health data management in the medical system increases continuously. Meanwhile, a large amount of data generated in the long-term treatment process can cause excessive data analysis processing pressure, and the transmission and access of a large amount of data can generate pressure on network bandwidth. Disclosure of Invention In order to solve the technical problem of overlarge data management pressure of health data of a neurosurgical patient, the invention aims to provide an intelligent management method of the health data of the neurosurgical patient, and the adopted technical scheme is as follows: Acquiring an electronic medical record of a current patient, wherein the electronic medical record comprises multidimensional health data of a plurality of time points, records of a plurality of treatment nodes and corresponding operation labels; at each time point, acquiring a physical state score of the patient at each time point according to the deviation characteristics of the health data of each data dimension compared with a preset standard range; according to the change characteristics of the physical state scores, the importance parameters of each treatment node are obtained; According to the interval characteristics among the important nodes, combining the importance parameters of each important node to acquire a judgment time domain interval of each important node; acquiring association coefficients of each important node and each data dimension according to the fluctuation intense characteristic of the health data of each data dimension in the judging time domain interval of each important node; acquiring correction association coefficients of each important node and each data dimension according to the association coefficients of all important nodes and each data dimension under each operation label by combining the corresponding association coefficients; and according to the time interval between each important node and the current time point, acquiring a value coefficient of the health data of each dimension of each time point by combining the corresponding correction association coefficient, the corresponding importance parameter and the deviation characteristic of the health data of each dimension, and storing the health data based on the value coefficient. Further, the method for acquiring the physical state score comprises the following steps: The physical state score is obtained through a physical state score calculation formula, wherein the physical state score calculation formula comprises the following steps: ; wherein t represents the sequence number of the time point; a physical state score representing a t-th time point, J representing the number of data dimensions, J representing the sequence number of the data dimensions; representing the maximum value of a preset standard range of the jth data dimension; representing the minimum value of a preset standard range of the jth data dimension; representing the median value of a preset standard range of the jth data dimension; a data value representing a jth data dimension of a t-th point in time; The representation takes absolute value. Further, the method for acquiring the importance parameter comprises the following steps: taking the absolute value of the difference value of the physical state scores of the time points adjacent to the two sides of the time domain of each treatment node as the physical change degree of each treatment node; Obtaining importance parameters of each treatment node through a calculation formula of the importance parameters, wherein the calculation formula of the importance parameters comprises the following steps: ; wherein i represents the time sequence number of the treatment node; an importance parameter representing an ith treatment node; Representing a time interval between the i-1 th treatment node and the i-th treatment node; representing the degree of physical chan