Search

CN-121687543-B - Urinary surgery diagnosis and treatment data intelligent processing method and system

CN121687543BCN 121687543 BCN121687543 BCN 121687543BCN-121687543-B

Abstract

The invention relates to the field of diagnosis and treatment data processing, in particular to an intelligent treatment method and system for diagnosis and treatment data of urology surgery. According to the method, diagnosis and treatment data of different dimensions of each patient in urinary surgery are firstly obtained, important evaluation factors of each dimension of each patient are obtained for the correlation of diagnosis and treatment data differences of the same dimension and diagnosis and treatment data of each dimension between each patient and other patients, the similarity degree among the patients is obtained based on the diagnosis and treatment data differences of the same dimension and the important evaluation factor differences among the patients, iterative clustering is carried out on each patient to obtain multiple clustering results, the clustering effect of each clustering result is analyzed, the optimal clustering result is selected, and then the diagnosis and treatment data of each dimension of the patient in the same clustering cluster in the optimal clustering result are stored in a database. The invention can improve the personalized classified storage effect of diagnosis and treatment data of patient groups.

Inventors

  • DONG CHUNHUI

Assignees

  • 北京拾玖益信息技术有限公司

Dates

Publication Date
20260512
Application Date
20251204

Claims (8)

  1. 1. An intelligent processing method for urinary surgery diagnosis and treatment data is characterized by comprising the following steps: Acquiring diagnosis and treatment data of different dimensions of each patient in urology surgery; Taking any one patient as a target patient, taking any one dimension as a target dimension, and obtaining an important evaluation factor of the target dimension of the target patient according to the difference of diagnosis and treatment data of the target dimension between the target patient and other patients except the target dimension and the correlation of the diagnosis and treatment data of the target dimension and the other dimensions except the target dimension; Taking any one clustering result as a target clustering result, and obtaining the preference degree of the target clustering result according to the similarity degree between each patient in each clustering cluster in the target clustering result and the corresponding patient in the clustering center and the important evaluation factors of the same dimension of each patient in each clustering cluster; Screening out optimal clustering results from all the clustering results based on the preference degree of each clustering result, and storing diagnosis and treatment data of each dimension of patients in the same clustering cluster in the optimal clustering results into a database; The method for determining the important evaluation factors comprises the following steps: taking the average value of the diagnosis and treatment data of all patients in the target dimension as first integral diagnosis and treatment data of the target dimension; Taking the absolute value of the difference value between the diagnosis and treatment data of the target dimension of the target patient and the first integral diagnosis and treatment data as a first data deviation value of the target dimension of the target patient, taking the first data deviation value of the target dimension of the target patient as a numerator, taking the accumulated value of the first data deviation values of all the dimensions of the target patient as a denominator, and taking the ratio as a first importance of the target dimension of the target patient; Taking a sequence formed by the diagnosis and treatment data of the same dimension of all patients as a diagnosis and treatment data sequence of each dimension; Taking other dimensions except the target dimension as reference dimensions, and analyzing the correlation between the diagnosis and treatment data sequences of the target dimension and the diagnosis and treatment data sequences of each reference dimension to obtain a second importance of the target dimension; Taking the product value of the first importance of the target dimension of the target patient and the second importance of the target dimension as an important evaluation factor of the target dimension of the target patient; The second importance determination method comprises the following steps: Taking the absolute value of a pearson correlation coefficient between the diagnosis and treatment data sequence of the target dimension and the diagnosis and treatment data sequence of each reference dimension as the data correlation degree between the target dimension and each reference dimension; and taking the average value of the data correlation degrees between the target dimension and all the reference dimensions as a second importance degree of the target dimension.
  2. 2. The method for intelligently processing urinary surgery diagnosis and treatment data according to claim 1, wherein the step of obtaining the similarity between any two patients comprises the steps of: Taking the important evaluation factors of the target dimension of each patient as a molecule, taking the accumulated value of the important evaluation factors of all dimensions of each patient as a denominator, and taking the ratio as the importance duty ratio of the target dimension of each patient; Arbitrarily selecting two patients as a first patient and a second patient, and performing negative correlation mapping on the absolute value of the difference value of the importance duty ratio of the target dimension between the first patient and the second patient to obtain a first similar parameter of the target dimension between the first patient and the second patient; Performing negative correlation mapping on the absolute value of the difference value of the target dimension of the diagnosis and treatment data between the first patient and the second patient to obtain a second similar parameter of the target dimension between the first patient and the second patient; Integrating the first similar parameters and the second similar parameters to obtain integrated similar parameters of target dimensions between a first patient and a second patient; and normalizing the accumulated values of the comprehensive similarity parameters of all dimensions between the first patient and the second patient to obtain the similarity degree between the first patient and the second patient.
  3. 3. The method for intelligently processing urinary surgery diagnosis and treatment data according to claim 1, wherein the step of obtaining a plurality of clustering results comprises the steps of: performing first clustering on all patients based on the similarity degree among the patients by using an iterative self-organizing clustering algorithm to obtain a first clustering result, and taking the first clustering result as a current clustering result; Selecting any one of the cluster to be tested as a patient to be tested according to the diagnosis and treatment data of each dimension of the patients in the cluster to be tested, and obtaining the weight parameters of the patients to be tested in the current cluster result according to the similarity between the patient to be tested and the cluster center patient of the cluster to be tested and the difference of the important evaluation factors of the same dimension of each patient in the cluster to be tested; And using an iterative self-organizing clustering algorithm, carrying out next clustering on all patients based on weight parameters of all patients in the current clustering result and the similarity degree among all patients to obtain a next clustering result, taking the next clustering result as the current clustering result if the ending condition of the iterative clustering is not reached, and continuing iterative clustering, otherwise, stopping iterative clustering.
  4. 4. A method for intelligently processing urinary surgery diagnosis and treatment data according to claim 3, wherein selecting a cluster center patient of a cluster to be measured from all patients in the cluster to be measured comprises: Taking the average value of the diagnosis and treatment data of the same dimension of all patients in the cluster to be tested as second integral diagnosis and treatment data of each dimension in the cluster to be tested; Taking the absolute value of the difference value between the diagnosis and treatment data of the target dimension of each patient in the cluster to be tested and the second integral diagnosis and treatment data of the target dimension as a second data deviation value of the target dimension of each patient in the cluster to be tested; taking the average value of the second data deviation values of all the dimensions of each patient in the cluster to be tested as the center deviation value of each patient in the cluster to be tested; And in the cluster to be detected, taking the patient corresponding to the minimum value of the center deviation value as the clustering center patient of the cluster to be detected.
  5. 5. The method for intelligently processing urinary surgery diagnosis and treatment data according to claim 3, wherein the step of obtaining the weight parameters of the patient to be tested in the current clustering result comprises the steps of: taking the average value of the important evaluation factors of the same dimension of all patients in the cluster to be tested as the integral important evaluation factor of each dimension of the cluster to be tested; taking the absolute value of the difference value between the important evaluation factors of each dimension of the patient to be tested and the overall important evaluation factors of each dimension of the cluster to be tested as an importance deviation value of each dimension of the patient to be tested; The similarity degree between the patient to be detected and the clustering center patient of the cluster to be detected and the classification necessity degree are comprehensively processed to obtain the weight parameter of the patient to be detected in the current clustering result, wherein the weight parameter of the patient to be detected in the current clustering result is positively correlated with the similarity degree between the patient to be detected and the clustering center patient of the cluster to be detected and inversely correlated with the classification necessity degree.
  6. 6. The method for intelligently processing urinary surgery diagnosis and treatment data according to claim 3, wherein the obtaining of the preference degree of the target clustering result comprises the following steps: taking any one cluster in the target cluster result as a target cluster, and taking the product value of the similarity degree between each patient in the target cluster and the clustering center patient of the target cluster and the weight parameter of each patient as the updating stability of each patient in the target cluster; taking the average value of the updated stability of all patients in the target cluster as the clustering effect evaluation degree of the target cluster; And taking the average value of the clustering effect evaluation degrees of all the clustering clusters in the target clustering result as the preference degree of the target clustering result.
  7. 7. The method for intelligently processing urinary surgery diagnosis and treatment data according to claim 1, wherein the step of screening out the best clustering result from all the clustering results comprises the steps of: And taking the clustering result corresponding to the maximum value of the preference degree as the optimal clustering result.
  8. 8. An intelligent processing system for urinary surgery diagnosis and treatment data, the system comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any one of claims 1-7 when executing the computer program.

Description

Urinary surgery diagnosis and treatment data intelligent processing method and system Technical Field The invention relates to the field of diagnosis and treatment data processing, in particular to an intelligent treatment method and system for diagnosis and treatment data of urology surgery. Background The urological diagnosis and treatment data can be used for evaluating and analyzing the urological system diseases of the patient, and because the diagnosis and treatment data of the urological department of the patient relate to various types and dimensions and have large and complex data volume, the urological diagnosis and treatment data of the patient are accurately classified and stored, a doctor can be assisted to formulate a personalized diagnosis and treatment scheme for the patient, diagnosis and treatment efficiency can be improved, and the urological diagnosis and treatment data has important significance for the urological diagnosis and treatment process. In the related art, patients are generally clustered based on differences of diagnosis and treatment data of the same dimension among patients, and diagnosis and treatment data of the patients in the same cluster are stored as the same class, but because the conventional clustering algorithm does not consider interaction among diagnosis and treatment data of different dimensions in the clustering process, the patients cannot be accurately clustered by the conventional clustering method, and the classification storage effect of the diagnosis and treatment data of a patient group is reduced. Disclosure of Invention In order to solve the technical problem that patients cannot be accurately clustered by the existing clustering method and the diagnosis and treatment data classification storage effect of patient groups is reduced, the invention aims to provide an intelligent treatment method and system for the diagnosis and treatment data of the urology surgery, and the adopted technical scheme is as follows: the invention provides an intelligent treatment method for diagnosis and treatment data of urinary surgery, which comprises the following steps: Acquiring diagnosis and treatment data of different dimensions of each patient in urology surgery; Taking any one patient as a target patient, taking any one dimension as a target dimension, and obtaining an important evaluation factor of the target dimension of the target patient according to the difference of diagnosis and treatment data of the target dimension between the target patient and other patients except the target dimension and the correlation of the diagnosis and treatment data of the target dimension and the other dimensions except the target dimension; Taking any one clustering result as a target clustering result, and obtaining the preference degree of the target clustering result according to the similarity degree between each patient in each clustering cluster in the target clustering result and the corresponding patient in the clustering center and the important evaluation factors of the same dimension of each patient in each clustering cluster; And screening out the optimal clustering results from all the clustering results based on the preference degree of each clustering result, and storing diagnosis and treatment data of each dimension of patients in the same clustering cluster in the optimal clustering results into a database. Further, the obtaining the important evaluation factors of the target dimension of the target patient includes: taking the average value of the diagnosis and treatment data of all patients in the target dimension as first integral diagnosis and treatment data of the target dimension; Taking the absolute value of the difference value between the diagnosis and treatment data of the target dimension of the target patient and the first integral diagnosis and treatment data as a first data deviation value of the target dimension of the target patient, taking the first data deviation value of the target dimension of the target patient as a numerator, taking the accumulated value of the first data deviation values of all the dimensions of the target patient as a denominator, and taking the ratio as a first importance of the target dimension of the target patient; Taking a sequence formed by the diagnosis and treatment data of the same dimension of all patients as a diagnosis and treatment data sequence of each dimension; Taking other dimensions except the target dimension as reference dimensions, and analyzing the correlation between the diagnosis and treatment data sequences of the target dimension and the diagnosis and treatment data sequences of each reference dimension to obtain a second importance of the target dimension; Taking the product value of the first importance of the target dimension of the target patient and the second importance of the target dimension as an important evaluation factor of the target dimension of the target patient. Further, the ob