CN115050449A - Theophylline guiding medication device based on weighted regression - Google Patents
Theophylline guiding medication device based on weighted regression Download PDFInfo
- Publication number
- CN115050449A CN115050449A CN202210554834.1A CN202210554834A CN115050449A CN 115050449 A CN115050449 A CN 115050449A CN 202210554834 A CN202210554834 A CN 202210554834A CN 115050449 A CN115050449 A CN 115050449A
- Authority
- CN
- China
- Prior art keywords
- regression model
- theophylline
- regression
- model
- training set
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- ZFXYFBGIUFBOJW-UHFFFAOYSA-N theophylline Chemical compound O=C1N(C)C(=O)N(C)C2=C1NC=N2 ZFXYFBGIUFBOJW-UHFFFAOYSA-N 0.000 title claims abstract description 78
- 229960000278 theophylline Drugs 0.000 title claims abstract description 39
- 239000003814 drug Substances 0.000 title claims abstract description 24
- 229940079593 drug Drugs 0.000 title claims abstract description 18
- 238000012549 training Methods 0.000 claims abstract description 44
- 238000012360 testing method Methods 0.000 claims abstract description 36
- 210000002966 serum Anatomy 0.000 claims abstract description 10
- 238000010276 construction Methods 0.000 claims abstract description 7
- 238000012417 linear regression Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000000034 method Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 6
- 206010007522 Cardiac asthma Diseases 0.000 description 3
- 208000004327 Paroxysmal Dyspnea Diseases 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 210000002460 smooth muscle Anatomy 0.000 description 3
- BHPQYMZQTOCNFJ-UHFFFAOYSA-N Calcium cation Chemical compound [Ca+2] BHPQYMZQTOCNFJ-UHFFFAOYSA-N 0.000 description 2
- UCTWMZQNUQWSLP-UHFFFAOYSA-N adrenaline Chemical compound CNCC(O)C1=CC=C(O)C(O)=C1 UCTWMZQNUQWSLP-UHFFFAOYSA-N 0.000 description 2
- 208000006673 asthma Diseases 0.000 description 2
- 229910001424 calcium ion Inorganic materials 0.000 description 2
- 210000002345 respiratory system Anatomy 0.000 description 2
- SFLSHLFXELFNJZ-QMMMGPOBSA-N (-)-norepinephrine Chemical compound NC[C@H](O)C1=CC=C(O)C(O)=C1 SFLSHLFXELFNJZ-QMMMGPOBSA-N 0.000 description 1
- 206010049816 Muscle tightness Diseases 0.000 description 1
- 208000005374 Poisoning Diseases 0.000 description 1
- 210000005091 airway smooth muscle Anatomy 0.000 description 1
- 230000001269 cardiogenic effect Effects 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 208000023819 chronic asthma Diseases 0.000 description 1
- 210000002472 endoplasmic reticulum Anatomy 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 208000030603 inherited susceptibility to asthma Diseases 0.000 description 1
- 229960002748 norepinephrine Drugs 0.000 description 1
- SFLSHLFXELFNJZ-UHFFFAOYSA-N norepinephrine Natural products NCC(O)C1=CC=C(O)C(O)=C1 SFLSHLFXELFNJZ-UHFFFAOYSA-N 0.000 description 1
- 231100000572 poisoning Toxicity 0.000 description 1
- 230000000607 poisoning effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
- 231100000331 toxic Toxicity 0.000 description 1
- 230000002588 toxic effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Epidemiology (AREA)
- Biomedical Technology (AREA)
- Primary Health Care (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medicinal Chemistry (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to a theophylline medication guiding device based on weighted regression, which comprises: a dataset acquisition module: the data set is used for acquiring data sets, wherein the data sets are the theophylline concentrations in serum collected by different patients at different time after taking different doses of theophylline; a classification module: for dividing the data set into a training set and a test set; a model construction module: the regression model is used for constructing a regression model, training a training set by using the regression model to obtain a trained regression model, and testing the trained regression model by using the test set to obtain a fitted regression model; a prediction module: and predicting the serum theophylline concentration of the patient needing medication guidance through the fitted regression model. The invention can realize accurate theophylline medication guidance for patients.
Description
Technical Field
The invention relates to the technical field of auxiliary medical treatment, in particular to a theophylline medication guiding device based on weighted regression.
Background
Theophylline (Theophylline) can reduce smooth muscle tension and dilate respiratory tract; can promote the release of endogenous adrenaline and noradrenaline and the relaxation of airway smooth muscle; inhibit the release of calcium ions from smooth muscle endoplasmic reticulum, and reduce the concentration of calcium ions in cells to generate respiratory tract expansion effect. Theophylline has strong relaxation effect on smooth muscle.
Theophylline is a commonly used medicine for treating bronchial asthma and cardiogenic asthma, and the traditional medicine scheme is guided by doctors according to experience to achieve the purpose of treatment. It is difficult to quantitatively administer the drug according to the condition of each patient. The judgment is often inaccurate by an artificial judgment method, negative effects can be brought to the treatment of the cardiac asthma if the dosage is too large, and the aim of treating the cardiac asthma cannot be achieved if the dosage is too small.
Clinically, in order to control the attack of chronic asthma patients, the serum theophylline concentration must reach 8-20 mug/ml, and over 20 mug/ml can cause toxic reaction. However, the serum theophylline concentration has a plurality of influencing factors and large individual difference, and the individual quantitative administration according to the clinical manifestations of patients is difficult in the actual administration scene, thus causing irreparable consequences.
Therefore, there is a need to find a suitable method for providing theophylline to patients suffering from cardiac asthma, which is suitable for the condition of the patients, so as to achieve the therapeutic effect.
Disclosure of Invention
The invention aims to provide a theophylline medication guidance device based on weighted regression, which can realize accurate theophylline medication guidance for patients.
The technical scheme adopted by the invention for solving the technical problems is as follows: provided is a theophylline medication guiding device based on weighted regression, comprising:
a dataset acquisition module: the data set is used for acquiring data sets, wherein the data sets are the theophylline concentrations in serum collected by different patients at different time after taking different doses of theophylline;
a classification module: for dividing the data set into a training set and a test set;
a model construction module: the regression model is used for constructing a regression model, training a training set by using the regression model to obtain a trained regression model, and testing the trained regression model by using the test set to obtain a fitted regression model;
a prediction module: and predicting the serum theophylline concentration of the patient needing medication guidance through the fitted regression model.
The classification module divides the data set into a training set and a testing set, and specifically comprises the following steps: the data set was divided into 80% training set and 20% testing set.
The regression model in the model construction module is a weighted linear regression model.
The method comprises the following steps of constructing a regression model in the model construction module, training a training set by using the regression model to obtain a trained regression model, and further comprising the following steps of: when the regression model is used for training a training set, different weights are given to data points of different offset values in the training set, wherein the offset value is the distance between the data point in the training set and a line or a plane corresponding to the regression model.
The data points with different deviation values in the training set are given different weights, and the formula is as follows:
where ω represents the ith data point x in the training set i M represents the number of data points in the training set, μ represents the mean of the M data points, S represents the covariance matrix of the M data points, and k represents a constant.
The model building module tests the trained regression model through the test set to obtain a fitted regression model, and the method specifically comprises the following steps: testing the trained regression model by using the test set to obtain a test result, and comparing the test result with a real result to calculate a decision coefficient R ^2 of the trained regression model;
if the decision coefficient R2 is larger than a preset value, taking the trained regression model as a fitted regression model, and outputting the fitted regression model;
if the decision is that R2 is smaller than a preset value, the weight of the trained regression model is adjusted until the decision coefficient R2 is larger than the preset value.
The preset value is 0.7.
Advantageous effects
Due to the adoption of the technical scheme, compared with the prior art, the invention has the following advantages and positive effects: compared with the traditional linear regression method, the method has the advantages that the standard error of the regression coefficient estimated by the weighted linear regression is smaller (more stable and less variable), and the model fitting is better; the invention combines the traditional medicine and the modern computer technology to realize an accurate and personalized medication guidance scheme; the patient does not need to go to a hospital to obtain a medication guiding scheme, so that the medical cost is reduced, and the treatment efficiency is improved.
Drawings
FIG. 1 is a flow chart of an embodiment of the present invention.
Detailed Description
The invention will be further illustrated with reference to the following specific examples. It should be understood that these examples are for illustrative purposes only and are not intended to limit the scope of the present invention. Further, it should be understood that various changes or modifications of the present invention may be made by those skilled in the art after reading the teaching of the present invention, and such equivalents may fall within the scope of the present invention as defined in the appended claims.
The embodiment of the present invention relates to a theophylline medication guiding device based on weighted regression, referring to fig. 1, including:
a dataset acquisition module: for obtaining data sets of the theophylline concentrations in serum collected at different times after different patients took different doses of theophylline.
A classification module: for separating the data set into a training set and a test set.
The classification module divides the data set into a training set and a testing set, and specifically comprises the following steps: the data set was divided into 80% training set and 20% testing set.
A model construction module: the method is used for constructing a regression model, training a training set by using the regression model to obtain a trained regression model, and testing the trained regression model by using the test set to obtain a fitted regression model.
Further, the regression model in the model construction module is a weighted linear regression model.
In the conventional linear regression, a common least square method is adopted to fit a regression model to obtain a residual error, and a regression equation is obtained by performing regression on a proper interpretation variable by using the square of the residual error (or the absolute value of the residual error). However, the data points with different offset values are subjected to a unification process, which affects the fitting effect of the model. Therefore, the present embodiment improves the data points with different offset values, specifically as follows:
further, the constructing a regression model in the model constructing module, and training a training set by using the regression model to obtain a trained regression model, further includes: when the regression model is used for training a training set, different weights are given to data points of different offset values in the training set, wherein the offset value is the distance between the data point in the training set and a line or a plane corresponding to the regression model. Here, the line or the plane (a two-dimensional space corresponds to a line, and a multi-dimensional space corresponds to a plane) is the line or the plane when the regression problem is solved, that is, a visualization result of the regression model in the present embodiment.
Different weights are given to the data points with different offset values in the training set, and the formula is as follows:
where ω represents the ith data point x in the training set i M represents the number of data points in the training set, μ represents the mean of the M data points, S represents the covariance matrix of the M data points, and k represents a constant.
Further, the model building module tests the trained regression model through the test set to obtain a fitted regression model, specifically: testing the trained regression model by using the test set to obtain a test result, and comparing the test result with a real result to calculate a decision coefficient R ^2 of the trained regression model;
if the decision coefficient R2 is larger than a preset value, taking the trained regression model as a fitted regression model, and outputting the fitted regression model;
if the decision is that R2 is smaller than a preset value, the weight of the trained regression model is adjusted until the decision coefficient R2 is larger than the preset value. The preset value is 0.7.
A prediction module: the method is used for predicting the serum theophylline concentration of a patient needing medication guidance through the fitted regression model, and when the theophylline concentration is less than 8 mug/ml, the patient needs to take the medicine, and when the theophylline concentration is 8-20 mug/ml, the theophylline exerts the medicine effect and does not need to take the medicine; when the theophylline concentration is more than 20 mug/ml, the patient is indicated to have too large dosage or too short dosage interval and poisoning risk, and needs to seek medical advice in time for further examination.
The foregoing descriptions of specific exemplary embodiments of the present invention have been presented for purposes of illustration and description. It is not intended to limit the invention to the precise form disclosed, and obviously many modifications and variations are possible in light of the above teaching. The exemplary embodiments were chosen and described in order to explain certain principles of the invention and its practical application to enable one skilled in the art to make and use various exemplary embodiments of the invention and various alternatives and modifications as are suited to the particular use contemplated. It is intended that the scope of the invention be defined by the claims and their equivalents.
Claims (7)
1. A theophylline guidance medication device based on weighted regression, comprising:
a dataset acquisition module: the data set is used for acquiring data sets, wherein the data sets are the theophylline concentrations in serum collected by different patients at different time after taking different doses of theophylline;
a classification module: for dividing the data set into a training set and a test set;
a model construction module: the regression model is used for constructing a regression model, training a training set by using the regression model to obtain a trained regression model, and testing the trained regression model by using the test set to obtain a fitted regression model;
a prediction module: and predicting the serum theophylline concentration of the patient needing medication guidance through the fitted regression model.
2. The theophylline guidance dosing device based on weighted regression as claimed in claim 1, wherein the classification module divides the data set into a training set and a test set, specifically: the data set was divided into 80% training set and 20% testing set.
3. The theophylline guidance dosing device based on weighted regression of claim 1, wherein the regression model in the model building module is a weighted linear regression model.
4. The theophylline guidance dosing device based on weighted regression as claimed in claim 3, wherein the model building module builds a regression model, and the regression model is used to train a training set to obtain a trained regression model, further comprising: when the regression model is used for training a training set, different weights are given to data points of different offset values in the training set, wherein the offset value is the distance between the data point in the training set and a line or a plane corresponding to the regression model.
5. The weighted regression-based theophylline guidance dosing device of claim 4, wherein different weights are assigned to the data points for different bias values in the training set according to the formula:
where ω represents the ith data point x in the training set i M represents the number of data points in the training set, μ represents the mean of the M data points, S represents the covariance matrix of the M data points, and k represents a constant.
6. The theophylline guidance medication device based on weighted regression as claimed in claim 4, wherein the model building module tests the trained regression model through the test set to obtain a fitted regression model, specifically: testing the trained regression model by using the test set to obtain a test result, and comparing the test result with a real result to calculate a decision coefficient R ^2 of the trained regression model;
if the decision coefficient R2 is larger than a preset value, taking the trained regression model as a fitted regression model, and outputting the fitted regression model;
if the decision is that R2 is smaller than a preset value, the weight of the trained regression model is adjusted until the decision coefficient R2 is larger than the preset value.
7. The weighted regression-based theophylline guidance dosing device of claim 5, wherein the preset value is 0.7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210554834.1A CN115050449A (en) | 2022-05-19 | 2022-05-19 | Theophylline guiding medication device based on weighted regression |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210554834.1A CN115050449A (en) | 2022-05-19 | 2022-05-19 | Theophylline guiding medication device based on weighted regression |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115050449A true CN115050449A (en) | 2022-09-13 |
Family
ID=83159382
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210554834.1A Pending CN115050449A (en) | 2022-05-19 | 2022-05-19 | Theophylline guiding medication device based on weighted regression |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115050449A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050187445A1 (en) * | 2004-02-11 | 2005-08-25 | Han Sang-Joon | Method of determining a weighted regression model and method of predicting a component concentration of mixture using the weighted regression model |
| CN113555079A (en) * | 2021-09-16 | 2021-10-26 | 台州市中心医院（台州学院附属医院） | Medication prediction system based on neural network |
-
2022
- 2022-05-19 CN CN202210554834.1A patent/CN115050449A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050187445A1 (en) * | 2004-02-11 | 2005-08-25 | Han Sang-Joon | Method of determining a weighted regression model and method of predicting a component concentration of mixture using the weighted regression model |
| CN113555079A (en) * | 2021-09-16 | 2021-10-26 | 台州市中心医院（台州学院附属医院） | Medication prediction system based on neural network |
Non-Patent Citations (2)
| Title |
|---|
| 张懋;蒋昆谕;韩龙;赵妍;王欣;孟胜男;: "茶碱在正常及肝纤维化大鼠体内的药物动力学", 中国生化药物杂志, no. 06, 20 December 2012 (2012-12-20), pages 747 - 753 * |
| 黄露;熊欣;郭源源;熊桂斌;: "复方胆氨胶囊中氨茶碱在健康人体的生物等效性研究", 中国药师, no. 09, 5 September 2020 (2020-09-05), pages 1873 - 1875 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Delsoglio et al. | Indirect calorimetry in clinical practice | |
| Barrea et al. | Phase angle as an easy diagnostic tool of meta-inflammation for the nutritionist | |
| Crawley et al. | Assessment of clinical and social characteristics that distinguish presbylaryngis from pathologic presbyphonia in elderly individuals | |
| Hooshmand Moghadam et al. | The effects of high-intensity interval training vs. moderate-intensity continuous training on inflammatory markers, body composition, and physical fitness in overweight/obese survivors of breast cancer: a randomized controlled clinical trial | |
| Dzierzewski et al. | Adherence to continuous positive airway pressure in existing users: self-efficacy enhances the association between continuous positive airway pressure and adherence | |
| Campa et al. | Effects of different resistance training frequencies on body composition, cardiometabolic risk factors, and handgrip strength in overweight and obese women: A randomized controlled trial | |
| Löser et al. | Changes of exhaled volatile organic compounds in postoperative patients undergoing analgesic treatment: a prospective observational study | |
| Vandemoortele et al. | General purpose pharmacokinetic-pharmacodynamic models for target-controlled infusion of anaesthetic drugs: a narrative review | |
| Sesbreno et al. | Elite male volleyball players are at risk of insufficient energy and carbohydrate intake | |
| Bland | When Is a Disease a “Disease”? | |
| Heredia-Elvar et al. | Reproducibility and applicability of traditional strength training prescription recommendations | |
| Lee et al. | The Effect of Deep and Slow Breathing on Retention and Cognitive Function in the Elderly Population | |
| Wasyluk et al. | Methodological aspects of indirect calorimetry in patients with sepsis—possibilities and limitations | |
| Bell et al. | Stubborn exercise responders–where to next? | |
| Cuadrado-Peñafiel et al. | Microdosing sprint distribution as an alternative to achieve better sprint performance in field hockey players | |
| Mosiołek et al. | Brain-derived neurotrophic factor (BDNF) as an indicator for effects of cognitive behavioral therapy (CBT): A systematic review | |
| US11728017B2 (en) | Methods and systems for physiologically informed therapeutic provisions | |
| Militello et al. | Redox homeostasis and metabolic profile in young female basketball players during in-season training | |
| Rasmussen et al. | Early gastrointestinal neuropathy assessed by wireless motility capsules in adolescents with type 1 diabetes | |
| CN115050449A (en) | Theophylline guiding medication device based on weighted regression | |
| Czerwińska-Ledwig et al. | Effect of a 6-Week Cycle of Nordic Walking Training on Vitamin 25 (OH) D3, Calcium-Phosphate Metabolism and Muscle Damage in Multiple Myeloma Patients–Randomized Controlled Trial | |
| Sarlabous et al. | Development and validation of a sample entropy-based method to identify complex patient-ventilator interactions during mechanical ventilation | |
| Buch et al. | Comparison of equations estimating resting metabolic rate in older adults with type 2 diabetes | |
| Chang et al. | The Effectiveness of Home-Based Inspiratory Muscle Training on Small Airway Function and Disease-Associated Symptoms in Patients with Chronic Obstructive Pulmonary Disease | |
| Hamarat et al. | Can the treatment of normal-pressure hydrocephalus induce normal-tension glaucoma? A narrative review of a current knowledge |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |