Traditional Chinese medicine urine diagnosis quantification method and classification standard and application thereof in dynamic early warning of coronary heart disease risk

Abstract

The invention provides a traditional Chinese medicine urine diagnosis quantification method and classification standard and application thereof in dynamic early warning of coronary heart disease risk. The method comprises the following steps: S1, collecting a urine sample; s2, urine color quantification and classification: extracting a urine image CIEL * a * b * color space value, and realizing objective quantification and accurate analysis of urine color; s3, urine grouping: classifying the urine samples into corresponding color groups according to a urine color value range and a characteristic set threshold value; s4, establishing a coronary heart disease risk early warning model and verifying the effect: establishing a model for accurately early warning the coronary heart disease risk based on urine and evaluating the application effect; and S5, visualizing the model: dynamically presenting the model on a webpage for online use by a user, thereby realizing real-time evaluation and long-term tracking of the coronary heart disease risk of the user. Urine can be naturally generated every day, collection is harmless, individualized early warning signals can be provided before coronary heart disease symptoms appear by dynamically monitoring urine changes, and the device is particularly suitable for areas with limited resources to achieve early intervention.

Description

Technical Field

[0001] The present invention relates to the fields of medicine and computer programming technology, and in particular to a traditional Chinese medicine urine diagnosis quantitative method and classification standard and a use thereof for dynamically warning the risk of coronary heart disease. Background Art

[0002] The high morbidity and mortality of coronary heart disease have brought a heavy burden to patients, families and society. The risk of sudden cardiac death in patients with undiagnosed or asymptomatic coronary heart disease is extremely high, accounting for 45% of the total number of sudden deaths. Therefore, accurately identifying and intervening in the potential high-risk population for coronary heart disease before symptoms appear is of vital importance to reducing the morbidity and mortality of coronary heart disease.

[0003] Invasive coronary angiography is a key means of diagnosing coronary artery obstruction. However, in clinical practice, approximately 40% to 70% of patients with ischemic symptoms or signs who undergo coronary angiography actually have no obvious stenosis on angiography. In view of this, it is recommended to use non-invasive testing methods to assess the clinical possibility of coronary heart disease in patients before invasive coronary angiography. Especially in low- and middle-income areas, due to limited resources and the high economic burden that patients may face, it is more necessary to carefully screen out patients who really need coronary angiography to improve the accuracy and efficiency of diagnosis. With the transformation of the medical model, the concept of "active health, prevention and treatment" has gradually been recognized. The construction of a coronary heart disease risk warning model for risk assessment and prediction is of great significance for delaying or preventing the progression of the disease.

[0004] Urine is filtered from blood. Its formation and composition are closely related to the blood circulation system, especially to heart function. When the heart is damaged or there is a potential risk, changes in its physiological function will directly affect blood circulation, which will then be reflected in urine. Traditional Chinese medicine believes that urine is formed by the coordination of multiple internal organs. "Treatise on Febrile Diseases" further clarified that the cold and hot nature of the disease can be determined based on the color of urine. "Ten Questions Song" also records the content of "asking about urine". In the past, urine color was often described subjectively by patients or checked by doctors in the container with the naked eye. We have pioneered a quantitative analysis method for traditional medical urine diagnosis based on CIEL*a*b* color space values, and formulated detailed classification standards. This innovation aims to develop a simple, efficient and non-invasive detection method to provide patients and medical professionals with accurate and timely early warning signals before the symptoms of coronary heart disease are obvious, so as to achieve early intervention of coronary heart disease and effectively reduce its morbidity and mortality. Summary of the invention

[0005] The purpose of the present invention is to provide a urine diagnosis quantitative method and classification standard based on traditional Chinese medicine, as well as its application in non-invasive dynamic early warning of coronary heart disease risk. The method aims to overcome the subjectivity and lack of accuracy of existing urine color judgment methods, while avoiding the high false positive rate of invasive coronary angiography in diagnosing coronary artery obstruction, especially considering the actual situation of limited resources. By accurately monitoring the changes in urine color values, the present invention can objectively assess the risk of coronary heart disease, thereby improving the efficiency and accuracy of diagnosis. In addition, the dynamic risk value is intuitively displayed using a web platform, so that users can clearly understand the current coronary heart disease risk level and corresponding medical advice. It is not only suitable for preventive monitoring of healthy people, but also suitable for real-time evaluation and long-term tracking of people and patients at risk of coronary heart disease, aiming to help people more comprehensively grasp their own cardiovascular health status, so as to take scientific and reasonable preventive measures and effectively reduce the risk of coronary heart disease.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A traditional Chinese medicine urine diagnosis quantitative method and classification standard and its use for dynamic early warning of coronary heart disease risk, comprising the following steps:

[0008] S1. Sample collection: Collect urine samples from patients with CHD and healthy subjects who meet the inclusion and exclusion criteria.

[0009] S2. Urine color quantification and classification: By collecting images of urine samples and using image processing software to extract L (brightness), a (red-green value) and b (yellow-blue value) of urine in the CIEL*a*b* color space, accurate quantification and analysis of urine color can be achieved.

[0010] S3. Urine grouping: Based on the quantitative data, the grouping criteria are set according to the specific numerical range and characteristics of urine color, and the urine samples are classified into corresponding color groups by setting thresholds.

[0011] S4. Establish a risk warning model for coronary heart disease and verify its effect: Combined with the Logistic regression model, a urine-based model that can accurately warn of the risk of coronary heart disease is constructed and its application effect is evaluated. At the same time, the ROC curve is used to evaluate the model and determine the optimal critical value of urine color to improve the prediction accuracy and practicality of the model.

[0012] S5. Visualization model: dynamically present the coronary heart disease risk warning model on the web page for users to use online.

[0013] Furthermore, the inclusion criteria for coronary heart disease in S1 are: ① age ≥ 40 years old; ② meet the diagnostic criteria for coronary heart disease and are in the stable stage of coronary heart disease. The exclusion criteria are: ① patients with severe electrolyte disorders, malignant tumors and other serious diseases; ② pregnant or lactating women; ③ patients with mental illness or a history of mental illness; ④ patients with acute or chronic urinary tract infections; ⑤ patients with infectious diseases.

[0014] Furthermore, the urine sample in S1 was collected after fasting for 12 hours the night before, and 10 ml of midstream urine was collected the next day, which was photographed and imaged within 2 hours.

[0015] Furthermore, in S2, a white box with four sides closed and one side opened is used as a photographing device. The photographing instrument is placed on the top and fixed. The urine is placed in a white container and photographed using a device that can clearly photograph and save urine images.

[0016] Furthermore, in S2, image processing software (such as Photoshop, but not limited thereto) is used to extract the value of urine in the CIEL*a*b* color space.

[0017] Furthermore, in S4, the predictive performance of the coronary heart disease risk warning model was comprehensively evaluated through the ROC curve (Receiver Operating Characteristic Curve), calibration curve (Calibration Curve) and DCA curve (Decision Curve Analysis).

[0018] Furthermore, the maximum value of the Youden index was calculated by ROC curve in S4 to determine the high risk of coronary heart disease and the optimal critical value of urine color.

[0019] Furthermore, S5 uses R language to dynamically display the prediction results of the coronary heart disease risk warning model. Users adjust the input parameter urine color value through the slider, and the webpage updates the prediction results in real time, using the predicted risk probability and confidence interval to dynamically display them to users.

[0020] The beneficial effects of the present invention are:

[0021] This invention combines the urine diagnosis theory of traditional Chinese medicine with modern image processing technology for the first time, and achieves accurate capture and analysis of urine color changes by quantifying urine color values. This innovative method avoids the uncertainty and variability of subjective judgment in traditional urine diagnosis, making the assessment of urine color more objective and reliable, and improving the accuracy and practicality of early warning of coronary heart disease risk.

[0022] Compared with traditional invasive coronary angiography, the urine diagnosis method provided by the present invention is non-invasive, simple and easy to operate. It does not require complex equipment and professional technicians, reduces medical costs, improves the popularity and accessibility of diagnosis, and is particularly suitable for areas with limited resources.

[0023] By dynamically monitoring the changes in urine color values, the present invention can provide accurate and timely early warning signals to patients and medical professionals before the symptoms of coronary heart disease become apparent. This helps to achieve early intervention of coronary heart disease, effectively reduce its morbidity and mortality, and improve the quality of life of patients.

[0024] The present invention uses a webpage platform to intuitively display dynamic risk values, so that any user with an Internet connection can access and experience this interactive coronary heart disease risk warning tool, allowing users to clearly understand the current coronary heart disease risk level and corresponding medical advice. This is not only suitable for preventive monitoring of healthy people, but also for real-time evaluation and long-term tracking of people at risk of coronary heart disease and patients, which helps people to have a more comprehensive understanding of their own cardiovascular health status.

[0025] The present invention combines the urine diagnosis theory of traditional Chinese medicine with modern medical technology, providing a new idea and method for the integration of Chinese and Western medicine. This not only helps to promote the modernization and internationalization of traditional Chinese medicine, but also provides a new strategy for the prevention and treatment of chronic diseases such as coronary heart disease. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 : Schematic diagram of urine photography device.

[0025] Figure 2 : Distribution of urine color quantification values ​​in three-dimensional space according to an embodiment of the present invention.

[0026] Figure 3 : Receiver operating characteristic (ROC) curve of the embodiment of the present invention.

[0027] Figure 4 : Calibration curve of the embodiment of the present invention.

[0028] Figure 5 : DCA curve for clinical decision making in an embodiment of the present invention.

[0029] Figure 6 : Coronary heart disease dynamic risk warning webpage. DETAILED DESCRIPTION

[0027] The following is an explanation of the implementation of the present invention through specific embodiments, and those skilled in the art can understand the advantages and effects of the present invention from the contents disclosed in this specification. The present invention can be implemented or applied through other different specific embodiments, and the details in this specification can also be modified and changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention.

[0028] The following embodiments will further explain the relevant technical contents of the present invention in detail, but the disclosed contents are not intended to limit the protection scope of the present invention. Any product identical or similar to the present invention obtained by anyone under the enlightenment of the present invention or by combining the features of the present invention with other prior arts shall fall within the protection scope of the present invention.

[0029] In the embodiment of the present invention, urine samples were randomly collected from 50 patients with coronary heart disease and 80 healthy people at the China-Japan Friendship Hospital and the Physical Examination Center of the Third Affiliated Hospital of Beijing University of Chinese Medicine according to the inclusion and exclusion criteria.

[0030] Participants were asked to fast and not drink for 12 hours at night and to collect 10 ml of midstream urine the next morning to ensure that the effects of food and drugs on urine production were minimized.

[0031] Using a high-resolution camera Figure 1 The urine sample is photographed in the stable light source device shown, ensuring that the light in the shooting environment is stable, and the urine sample is photographed and imaged within 2 hours to avoid contamination of the urine sample or color change caused by long-term storage.

[0032] The urine images were imported into Photoshop software, and the urine color values ​​were extracted using the software. A 300px×300px area in the center of the image was selected. Then, the L*a*b* values ​​of the image were extracted using the filter-blur-average-color picker in the software tool. L represents brightness, a represents red and green values, and b represents yellow and blue values. The urine samples were processed and color values ​​extracted in the above steps to ensure that the color data of all samples were consistent and comparable. The urine color distribution of patients with coronary heart disease and healthy people is shown in Table 1.

[0033] Table 1 Urine color distribution of patients with coronary heart disease and healthy people based on Lab* value

[0034] Table 2 compares the urine color values ​​of patients with coronary heart disease and healthy people and finds that, compared with healthy people, the L value of urine color in patients with coronary heart disease is significantly increased, and the a value and b value are significantly decreased. The urine color of patients with coronary heart disease becomes lighter when observed with the naked eye, indicating that urine color can be used as a risk factor for the onset of coronary heart disease.

[0035] Table 2 Comparison of urine color space values ​​between coronary heart disease and healthy subjects and one-way ANOVA

[0036] The group distribution of CIEL*a*b* values ​​of urine samples of patients with coronary heart disease and healthy people in three-dimensional space. For details, please refer to the attached Figure 2 .

[0037] The range of L value of urine color of patients with coronary heart disease is 39-59, and the range of L value of urine color of healthy people is 36-59. The group interval is set to 4, and the L value is divided into 6 groups from small to large. The grouping criteria are shown in Table 3. It is found that the distribution trend of coronary heart disease in each urine color group is opposite to that of healthy people. Coronary heart disease is mostly distributed in 52≤L<60, while healthy people are mostly distributed in 44≤L<52. In addition, the distribution percentages of coronary heart disease and healthy people in each urine color group are significantly different, which further suggests that urine color can warn the occurrence or development of coronary heart disease.

[0038] Table 3 Urine color grouping standards

[0039] The risk warning model of coronary heart disease was established by Logistic regression analysis. P = 0.000 (P < 0.001). The model was statistically significant. The fitted coronary heart disease warning regression equation The results are shown in Table 4.

[0040] The Logistic coronary heart disease early warning regression equation shows that urine color L value is a risk factor for coronary heart disease, which can significantly positively reflect the risk of coronary heart disease. The higher the urine color L value, the more likely it is to develop coronary heart disease. For every unit increase in urine color L value, the risk of coronary heart disease increases by nearly 1.235 times on average.

[0041] Table 4 Logistic regression equation for urine warning of coronary heart disease risk

[0042] The ROC curve was used to further evaluate the discrimination effect of the model and calculate the optimal critical value of urine color L value for independent warning of coronary heart disease. Figure 3 As shown in the ROC curve, the sensitivity and specificity were 0.774 and 0.856 respectively, and the area under the curve AUC was 0.810 (P=0000, 95% CI: 0.698-0.922), indicating that it has a good warning value for coronary heart disease.

[0043] Furthermore, the urine color L value is used as an independent warning indicator for coronary heart disease, and its optimal critical value is 52, which means that if the urine color L value is greater than or equal to 51.5, the individual can be diagnosed as or can be diagnosed as coronary heart disease, and is considered a high-risk group for coronary heart disease. Then, samples with urine color values ​​L<51.5 are marked as healthy, and samples with L≥51.5 are marked as coronary heart disease, verifying the accuracy of this method. The results show (Table 5) that the diagnostic accuracy of this method for non-coronary heart disease patients is as high as 85.3%, and it has the ability to effectively distinguish between people with potential coronary heart disease risk and healthy people.

[0044] Table 5 Classification of urine color L* value predicting coronary heart disease results

[0045] Draw the calibration curve to further measure the calibration of the coronary heart disease risk warning model, such as Figure 4 As shown, the curve fluctuates around the diagonal line. In each prediction probability interval, the predicted positive case proportion is very close to the actually observed positive case proportion, without any obvious deviation or trend away from the diagonal line, indicating that the risk probability predicted by the urine color L value is highly consistent with the actual risk of coronary heart disease.

[0046] Draw the DCA curve for clinical decision making to further measure the clinical applicability of the CHD risk warning model, such as Figure 5 As shown, the net benefits at different thresholds are higher than the None line of the no warning strategy and the All line of the comprehensive warning strategy. As the decision threshold increases from 0 to 1, the change trend of the net benefit is stable, and it is significantly better than the random guessing line at multiple threshold points, indicating that the present invention has high accuracy in identifying patients who need warnings and has practical application value in decision-making, which reflects the stability and reliability of the warning effect in different situations.

[0047] In order to further improve the convenience and accessibility of the early warning of coronary heart disease risk, the present invention uses the Shiny interactive data visualization tool of R language on the basis of the early warning model of coronary heart disease risk to dynamically display the prediction results of the early warning model of coronary heart disease risk. Figure 6 As shown in the figure, the left side of the webpage is a collection of input controls, and the right side is a result display area. Users adjust the input parameter urine color value through the slider, and the Shiny application captures these changes through reactive expressions, updates the prediction results in real time, and dynamically displays them to users using predicted risk probabilities and confidence intervals. Users do not need to calculate scores manually, which greatly simplifies the complex calculation steps in the traditional risk assessment process. Even those without a professional medical background can easily understand and apply it.

[0048] The above are exemplary embodiments, and the exemplary embodiments are selected for description in order to explain the specific principles and practical applications of the present invention, so that relevant personnel can understand and use them easily. Among them, the methods mentioned in the embodiments are not completely limited to such methods, and relevant personnel can make corresponding adjustments according to the principles in actual operations. The scope of protection of the present invention is intended to be defined by the claims and their equivalents.

Claims

1. A traditional Chinese medicine urine diagnosis quantitative method and classification standard and its use in dynamic early warning of coronary heart disease risk, characterized in that The following steps are involved: S1. Sample collection: urine samples from patients with coronary heart disease and healthy subjects who meet the inclusion and exclusion criteria are collected; S2. Urine color quantification and classification: By collecting images of urine samples and using image processing software to extract urine color space values, accurate quantification and analysis of urine color can be achieved; S3. Urine grouping: Based on the quantitative data, the grouping criteria are set according to the specific numerical range and characteristics of urine color, and the urine samples are classified into corresponding color groups by setting thresholds; S4. Establish a risk warning model for coronary heart disease and verify its effect: Combined with the Logistic regression model, a urine-based model that can accurately warn of the risk of coronary heart disease is constructed and its application effect is evaluated. At the same time, the optimal critical value of urine color is determined to improve the prediction accuracy and practicality of the model; S5. Visualization model: dynamically present the coronary heart disease risk warning model on the web page for users to use online.

2. The method and classification standard for urine diagnosis in traditional Chinese medicine according to claim 1 and its use for dynamic early warning of coronary heart disease risk, characterized in that: The inclusion criteria for coronary heart disease in step S1 are: ① age ≥ 40 years old; ② meet the diagnostic criteria for coronary heart disease and are in the stable stage of coronary heart disease. The exclusion criteria are: ① patients with severe electrolyte disorders, malignant tumors and other serious diseases; ② pregnant or lactating women; ③ patients with mental illness or a history of mental illness; ④ patients with acute or chronic urinary tract infections; ⑤ patients with infectious diseases.

3. The method and classification standard for urine diagnosis in traditional Chinese medicine according to claim 1 and its use for dynamic early warning of coronary heart disease risk, characterized in that: In step S1, the patient fasts for 12 hours the night before the urine sample is collected, and 10 ml of midstream urine is collected the next day, which is then photographed and imaged within 2 hours.

4. The method and classification standard for urine diagnosis in traditional Chinese medicine according to claim 1 and its use for dynamic early warning of coronary heart disease risk, characterized in that: In step S2, a white box that is closed on all sides and has an opening on one side is used as a photographing device, a photographing instrument is placed on the top and fixed, urine is placed in a white container, and photographed using a device that can clearly photograph and save urine images.

5. The method and classification standard for urine diagnosis in traditional Chinese medicine according to claim 1 and its use for dynamic early warning of coronary heart disease risk, characterized in that: In step S4, the predictive performance of the coronary heart disease risk warning model is comprehensively evaluated through the ROC curve, calibration curve and DCA curve.

6. The Chinese traditional medicine urine diagnosis quantitative method and classification standard and its use for dynamic early warning of coronary heart disease risk according to claim 1, characterized in that: In step S4, the maximum value of the Youden index is calculated by the ROC curve to determine the high risk of coronary heart disease and the optimal critical value of the urine color L* value.

7. The Chinese traditional medicine urine diagnosis quantitative method and classification standard and its use for dynamic early warning of coronary heart disease risk according to claim 1, characterized in that: In step S5, the Shiny interactive data visualization tool of R language is used to dynamically display the prediction results of the coronary heart disease risk warning model. The user adjusts the input parameter urine color L* value through the slider, and the Shiny application captures these changes through reactive expressions, updates the prediction results in real time, and dynamically displays them to the user using the predicted risk probability and confidence interval.

8. A traditional Chinese medicine urine diagnosis quantification method and classification standard and its use for dynamic early warning of coronary heart disease risk according to any one of claims 1 to 7, wherein the use is to dynamically monitor the changes in urine color values, and before the symptoms of coronary heart disease are obvious, use a web platform to intuitively display the dynamic risk value, provide accurate and timely early warning signals for patients and medical professionals, and realize non-invasive dynamic early warning of coronary heart disease risk.

Images