Hypertension drug recommendation model based on recursive partition calculation and its construction method

A construction method and high blood pressure technology, applied in the field of medicine, can solve the problems of increasing adverse events, ignoring differences in curative effect and adverse reactions, affecting the treatment effect of patients, etc., and achieve the effect of rapid selection

Active Publication Date: 2020-12-15
ZHEJIANG UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Drug therapy is currently recognized as the basic method for the treatment of hypertension, but the current drug regimen is mostly based on the clinical experience of physicians and guided by guidelines, ignoring the differences in efficacy and adverse reactions between individuals, thus affecting the treatment effect of patients and leading to an increase in adverse events

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Hypertension drug recommendation model based on recursive partition calculation and its construction method
  • Hypertension drug recommendation model based on recursive partition calculation and its construction method
  • Hypertension drug recommendation model based on recursive partition calculation and its construction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] Passed the ICD-10 diagnosis code of hypertension (I10.X00, I10.X01, I10.X02, I10.X03, I10.X04, I10.X05, I10.X06, I11.900, I12.903, I15.000) Matching is automatically obtained through the data analysis set, and the data structure of the data analysis set can be seen in Table 1.

[0056]

[0057]

[0058] Table 1 The model building analysis data set obtained by grabbing the ICD diagnostic code

[0059] The data is automatically divided into a test set and a validation set by a stratified sampling function, wherein the test set contains 148 samples, and the validation set contains 63 samples; for the test data set, the two regimens of single drug and combined drug are used as dependent variables. Age, gender, body mass index (BMI index), height, weight, and whether the diagnosis is accompanied by (diabetes, chronic kidney disease, atherosclerosis or cerebral infarction) are used to select nodes for classification, and the BMI index is obtained by height and weight ,...

Embodiment 2

[0064] The original data set is automatically divided into a test set and a validation set by a stratified sampling function. The validation set contains 63 samples, including 39 samples of the single drug regimen and 24 samples of the combined drug regimen group; whether the samples are elderly patients, Whether it is accompanied by diabetes, whether it is accompanied by atherosclerosis, whether it is accompanied by chronic kidney disease, BMI index and gender, six parameters are used to automatically judge a hypertension drug recommendation model, and realize the prediction of the patient's medication plan. As a result, 16 patients were predicted to be in the combined drug group, and 47 patients were predicted to be in the single drug group (Table 3), and the model judgment error probability was only 22%.

[0065]

[0066]

[0067] Table 3 Comparison between the prediction results of the hypertension drug recommendation model and the actual results

Embodiment 3

[0069] By the method of the present invention, select corresponding suitable 2-3 items variable among a plurality of classification variables, draw the following concrete medication recommendation example, specific as Figure 4 shown.

[0070] 1: The newly diagnosed hypertensive patient A is 75 years old and does not have diabetes. He can be classified into category 1 according to the hypertension drug recommendation model, and combined medication is recommended.

[0071] 2: The newly diagnosed hypertensive patient B is 35 years old and has diabetes, and can be classified into category 2 according to the hypertension drug recommendation model, and combined medication is recommended.

[0072] 3: Newly diagnosed hypertensive patient B is 42 years old and does not have diabetes, but he is found to have complications of hyperlipidemia, he can be classified into category 2 according to the hypertension drug recommendation model, and combined medication is recommended.

[0073] 4: ...

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

No PUM Login to view more

Abstract

The invention discloses a hypertension medication recommendation model based on recursive partitioning calculation and a construction method thereof. The method comprises the steps: obtaining a hypertension data set through ICD coding, and analyzing and processing the data set to be in a standardized text medical record format; formatting a text medical record into a classification variable containing hypertension medication characteristics, and defining a model framework; dividing the data set into a test sample set and a verification sample set through an age stratified sampling method; based on the test sample set, calculating the fitting degree of the model and judging the complexity of medication nodes by using a recursive partitioning algorithm; establishing a model parameter pool, and setting parameter composition; and solving optimal model parameters based on the verification sample set to realize construction and optimization of the hypertension medication recommendation model. By means of big data analysis, recognition methods of different medication schemes in individualized application of hypertension patients are analyzed, and rapid selection of a single medication scheme or a combined medication scheme is achieved according to treatment classification characteristics of the patients.

Description

technical field [0001] The invention relates to the field of medicine, in particular to a drug recommendation model for hypertension based on recursive partition calculation and a construction method thereof. Background technique [0002] The burden of disease caused by hypertension in my country is becoming more and more serious. About 62% of stroke events and 49% of coronary heart disease are closely related to hypertension, and the death from cardiovascular and cerebrovascular diseases has accounted for more than 40% of the total deaths. At the same time, with the changes in the spectrum of diseases in China, the burden of hypertension and its complications on society is bound to increase further. Drug therapy is currently recognized as the basic method for the treatment of hypertension, but the current drug regimen is mostly based on the clinical experience of physicians and guided by guidelines, ignoring the differences in efficacy and adverse reactions between individu...

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
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G16H10/60G16H50/70G16H70/40G16H20/10
CPCG16H10/60G16H20/10G16H50/70G16H70/40
Inventor 洪东升刘晓健倪剑羊红玉卢晓阳李秀央李鲁
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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