KR102602465B1 - Apparatus for displaying circulatory disease risk and method thereof - Google Patents

Abstract

One embodiment of the present invention includes a data collection step of collecting at least two of systolic blood pressure, diastolic blood pressure, pulse, and electrocardiogram measured from the user for a preset time; A modeling step of modeling a potential function that reflects the time series characteristics of the collected data; A 3D shape determination step of determining the 3D shape of the user based on the characteristic elements of the modeled potential function; And an output step of searching and outputting the circulatory system disease with the highest correlation value to the determined 3-dimensional shape, based on a table that corresponds the ratio of the 3-dimensional shape to the circulatory system disease. Outputting the potential for occurrence of circulatory system disease, including a. Disclose the method.

Description

Apparatus for displaying circulatory disease risk and method thereof}

The present invention relates to a device and method for outputting the probability of developing a circulatory disease. More specifically, it relates to a device that can quantify and output the possibility of developing a circulatory disease and a method of operating the device.

As people's interest in health increases day by day, the types of equipment that can easily measure health-related indicators are also increasing. For example, as various measuring equipment, such as blood pressure monitors, pulse meters, and blood oxygen saturation meters, become increasingly sophisticated and lightweight, people not only visit certain places to use the measuring equipment, but also conveniently carry the measuring equipment. I was able to use it while traveling.

However, most portable health indicator measurement devices are limited to the function of immediately displaying only the results of the input when the user inputs input according to a certain usage method, and do not have a function of providing highly reliable results compared with actual data. Not only are there very few portable health index measurement devices available, but the price of the device is not realistic, making user accessibility very poor.

Meanwhile, as multi-functional intelligent complex terminals equipped with various wired and wireless communication functions, such as smartphones, become widespread, various equipment that can be additionally installed and utilized on smartphones are increasing, and the advanced computational processing capabilities included in smartphones are increasing. There is an emerging need for a device that can provide accurate and useful information to users by utilizing both the display function and the accurate measurement function of a portable health indicator measuring device.

Prior Document 1 (Application No. 10-2016-0158494) discloses a device that visualizes and outputs the potential risk of developing circulatory diseases. According to the device disclosed in Prior Document 1, the user can visually know which of several circulatory diseases the user is most likely to suffer from.

Figure 1 is a diagram for explaining the principle of operation of the device disclosed in Prior Document 1.

The device according to Prior Document 1 includes a plurality of modules, and Figure 1 is a diagram showing an example of a three-dimensional user pattern calculated by a pattern calculation unit among the plurality of modules.

Referring to FIG. 1, the 3D user pattern is a pattern in which the highest user blood pressure pattern 110, the lowest user blood pressure pattern 130, and the user pulse pattern 150 are arranged in a single three-dimensional space, and next to them is a three-dimensional pattern. It can be seen that there is a comparison target pattern 170, which is a pattern compared to the user pattern. The highest user blood pressure pattern 110, the lowest user blood pressure pattern 130, and the user pulse pattern 150 are arranged in a single 3-dimensional space according to their respective 3-dimensional coordinate values.

Since the user highest blood pressure pattern 110, the lowest user blood pressure pattern 130, and the user pulse pattern 150 have significantly different values before being patterned, they are each arranged in a 3-dimensional vector form in a single 3-dimensional space after being patterned. It is common to keep them apart at regular intervals, but in cases where the user's health condition changes suddenly or the user suffers from a circulatory system disease, the highest blood pressure pattern, like the various comparison target patterns shown in Figure 1, It may be difficult to distinguish between the lowest blood pressure pattern and pulse pattern, and the overall shape itself may be an element that reflects the user's constitutional characteristics.

Figure 2 is a diagram showing an example of a similarity map output when the user data receiver receives information about the number of clusters.

Referring to Figure 2, it can be seen that multiple users, including normal people, suffering from various circulatory diseases are divided into several groups. Multiple clusters are classified according to the number of clusters entered by the user.

Like the first cluster 210 and the second cluster 230, about 10 nodes may belong to a cluster, but like the third cluster 250, numerous nodes may belong to one cluster. A person corresponding to a node belonging to cluster 3 (250) can be considered to have the most general constitution.

In Figure 2, a total of 10 people belong to the first cluster 210, and if the person indicated by 61 is considered a user, there are 7 people directly connected to the user (corresponding to nodes indicated by 44, 326, 350, 392, 1668053, and 1681300, respectively) person) can be seen as a person with a constitution similar to the user in the first cluster 210, and since the distance between nodes is the similarity, the person corresponding to the node at 1868053, which is the shortest distance from 61, is the person with the constitution most similar to the user. This happens. According to the above configuration, the smaller the number of clusters entered by the user, the more people will belong to the cluster to which the user belongs. If the user has a unique constitution, the user will be There may be only a very small number of people in the cluster to which it belongs.

According to the invention disclosed in Prior Document 1, the user does not input information about the number of clusters, but visually checks the similarity map comparing the user's constitution with all people stored in the database, and determines the user's circulatory system. The disease occurrence potential (potential risk of occurrence) can be intuitively determined.

However, the invention disclosed in Prior Document 1, when user data is entered as the final input value in the presence of various refined data, determines which group the user belongs to and which constitution is most similar to the patient. By providing it visually, it has the advantage of greatly improving intuition compared to conventional technology, but when information reflecting user characteristics is input, quantified or visualized information is provided on which circulatory system disease among various circulatory system diseases should be the most careful and prepared for. There is a limit to what cannot be done.

Republic of Korea Patent No. 10-1809149 (announced on December 14, 2017)

The technical problem to be solved by the present invention is to provide a device that quantifies and outputs which circulatory system disease the user should be most wary of when information about the user is input, and a method of implementing the device.

A method according to an embodiment of the present invention for solving the above technical problem includes a data collection step of collecting at least two of systolic blood pressure, diastolic blood pressure, pulse, and electrocardiogram measured from the user for a preset time; A modeling step of modeling a potential function that reflects the time series characteristics of the collected data; A 3D shape determination step of determining the 3D shape of the user based on the characteristic elements of the modeled potential function; and an output step of searching for and outputting the circulatory system disease with the highest correlation value to the determined 3D shape, based on a table that corresponds the ratio of the 3D shape to the circulatory system disease.

A device according to another embodiment of the present invention for solving the above technical problem includes: a first operation unit that collects at least two of high blood pressure, low blood pressure, pulse, and electrocardiogram measured from the user for a preset time; a second operation unit that models a potential function reflecting the time series characteristics of the collected data; a third operation unit that determines the three-dimensional shape of the user based on the characteristic elements of the modeled potential function; and a result output unit that searches for and outputs the circulatory system disease with the highest correlation value to the determined 3-dimensional shape, based on a table that corresponds the ratio of the 3-dimensional shape to the circulatory system disease.

One embodiment of the present invention can provide a computer-readable recording medium storing a program for executing the above method.

According to the present invention, the user can visually confirm which circulatory system disease the user should be most careful about.

Figure 1 is a diagram for explaining the principle of operation of the device disclosed in Prior Document 1.
Figure 2 is a diagram showing an example of a similarity map output when the user data receiver receives information about the number of clusters.
Figure 3 is a diagram showing an example of a block diagram of a device according to an embodiment of the present invention.
Figure 4 is a diagram showing several examples of a user's three-dimensional shape.
Figure 5 is an example of a graph for explaining a duffing oscillator.
Figure 6 is another example of a graph for explaining a duffing oscillator.
Figure 7 is a diagram showing an example of a three-dimensional shape determined by three types of biosignal data.
Figure 8 is a diagram showing another example of a three-dimensional shape determined by three types of biosignal data.
Figure 9 schematically shows an example of determining the correlation between two oscillators based on whether the slope between them is positive or negative.
Figure 10 is a flow chart showing an example of a method according to the present invention.

Since the present invention can be modified in various ways and can have various embodiments, specific embodiments will be illustrated in the drawings and described in detail in the detailed description. The effects and features of the present invention and methods for achieving them will become clear by referring to the embodiments described in detail below along with the drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various forms.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. When describing with reference to the drawings, identical or corresponding components will be assigned the same reference numerals and redundant description thereof will be omitted. .

In the following embodiments, terms such as first and second are used not in a limiting sense but for the purpose of distinguishing one component from another component.

In the following examples, singular terms include plural terms unless the context clearly dictates otherwise.

In the following embodiments, terms such as include or have mean the presence of features or components described in the specification, and do not exclude in advance the possibility of adding one or more other features or components.

In cases where an embodiment can be implemented differently, a specific process sequence may be performed differently from the described sequence. For example, two processes described in succession may be performed substantially at the same time, or may be performed in an order opposite to that in which they are described.

Figure 3 is a diagram showing an example of a block diagram of a device according to an embodiment of the present invention.

Referring to FIG. 3, the device 10 for outputting the occurrence potential of circulatory diseases includes a first operation unit 310, a second operation unit 330, a third operation unit 350, a result output unit 370, and a database ( 390). Below, in order to facilitate the explanation, the function of each module included in the device 10 for outputting the occurrence potential of circulatory diseases will be described most comprehensively, followed by a detailed explanation of how each module operates. Do this.

The first operation unit 310 collects systolic blood pressure, diastolic blood pressure, pulse, electrocardiogram test results, etc. measured from the user for a preset time.

The second operation unit 330 models a potential function that reflects the time series characteristics of the data collected in the first operation unit 310.

The third operation unit 350 determines the three-dimensional shape of the user based on the characteristic elements of the modeled potential function.

The result output unit 370 searches for the circulatory system disease that has the highest correlation value with the 3D shape determined by the third operation unit 350, based on a table that corresponds to the ratio of the 3D shape and the circulatory system disease. and print it out.

The database 390 stores data processed in the first operation unit 310, the second operation unit 330, the third operation unit 350, and the result output unit 370, or the result output unit 370 outputs the results. We are storing a reference table for this purpose.

First, the first operation unit 310 collects basic data (raw data) to determine the potential for occurrence of circulatory diseases. There can be various methods for the first operation unit 310 to collect basic data. As an example, the first operation unit 310 may collect user data from a past period stored in the database 390. As another example, the first operation unit 310 may collect information entered by the user through the input unit by converting it into basic data. Although not shown in Figure 3, in the present invention, the input unit includes not only a keyboard, mouse, and touch panel that directly receive user input, but also an HDD, SDD, and ODD that can input a large amount of data according to the user's input. It is considered a broad concept that

The data collected by the first operation unit 310 is data measured during a preset time, and here, the preset time means a time sufficient to calculate the potential for occurrence of a user's circulatory system disease. For example, the data collected by the first operation unit 310 may be biosignal data measured continuously for 40 hours from a smart watch worn by the user. The above-mentioned 40 hours is an example of a preset time, and in order to derive reasonable results, the preset time can be determined experimentally or empirically as a time to obtain the best result. For example, when data exceeding a preset time is input, the first calculation unit 310 may collect the data by dividing it into a data length that ensures optimal calculation efficiency.

Additionally, the data collected by the first operation unit 310 may be data on the user's systolic blood pressure, diastolic blood pressure, pulse, and electrocardiogram.

Measurement location, method, and time period Systolic blood pressure (mmHg) Diastolic blood pressure (mmHg) office blood pressure ≥140 ≥90 24-hour ambulatory blood pressure Average daily blood pressure ≥130 ≥80 Weekly average blood pressure ≥135 ≥85 Average night blood pressure ≥120 ≥70 home blood pressure ≥135 ≥85 Automatic blood pressure in clinic ≥135 ≥85

Table 1 is an example of a table prescribed by the Korean Society of Hypertension for diagnosing hypertension. In general, the daily average blood pressure of systolic blood pressure (BPsys) is more than 130 mmHg, the average daytime blood pressure is more than 135 mmHg, the average nighttime blood pressure is more than 120 mmHg, and the average daily blood pressure of diastolic blood pressure (BPdia) is more than 135 mmHg. People with an average daytime blood pressure of more than 80 mmHg, an average daytime blood pressure of more than 85 mmHg, or an average nighttime blood pressure of more than 70 mmHg are classified as hypertensive patients. In the present invention, systolic blood pressure and diastolic blood pressure are used with the same meaning as systolic blood pressure and diastolic blood pressure in Table 1, respectively. Considered.

The first operation unit 310 may collect at least two types of data on systolic blood pressure, diastolic blood pressure, pulse, and electrocardiogram measured during a preset time, and collecting more than two types is to output more accurate results. am.

The second operation unit 330 models a potential function that reflects the time series characteristics of the data collected by the first operation unit 310. The data collected by the first operation unit 310 is biosignal data measured over a preset period of time, and is data that has unique characteristics for each user. For example, the user's systolic blood pressure data measured for 40 hours reflects the user's unique characteristics, and in the present invention, the time series characteristics of the data refers to the systolic blood pressure value (lowest blood pressure) at a specific fixed point in time. value, pulse, ECG results), but rather the change trend of systolic blood pressure (lowest blood pressure, pulse, ECG results) that changes over time during a preset period of time.

The potential function modeled by the second operation unit 330 is derived from the physical meaning that an arbitrary force function is calculated by differentiating the potential function, and the potential function preserves the time series characteristics of the user's data as much as possible. It can be understood as a mathematical equation that reflects the function, and may be nicknamed the circulatory risk potential function to clarify its physical meaning.

Equation 1 is an equation that indicates that the force function is the result of the differentiation of the potential function, where F refers to the force function and U refers to the potential function, respectively.

The introduction of the potential function in the present invention stems from the fact that the data collected from users to determine the potential for occurrence of circulatory diseases is continuous data that continues for a preset time. Specifically, if there is a force function in a certain section, the potential function must be a continuous function for a preset time so that an indifferentiable point does not occur according to Equation 1, and this property is adopted in the present invention.

The potential function is a function that changes over time and includes an intra term and an interaction term.

Equation 2 is an equation representing the potential function. In Equation 2, Ui(intra) means an intra term, Ui(inter) means an interaction term, and i means that each term included in Equation 2 is a value (function) for circulatory disease and prodromal symptoms. do. Depending on the embodiment, the interaction term may be omitted from the potential function of the present invention.

In the potential function, the intra term is defined as the sum of the internal potentials within the circulatory oscillator, and the interaction term is defined as the sum of the interaction terms between the oscillators when there are two or more oscillators. In the present invention, the circulatory system oscillator refers to an oscillator that receives the highest blood pressure, lowest blood pressure, pulse, and electrocardiogram test results from the user and can most reliably predict the precursor symptoms of circulatory disease. As an example, There is a time-delay curve oscillator, and as another example, there is a duffing oscillator.

Equation 3 and Equation 4 express the intra term and interaction term more specifically than Equation 2. _In Equation 3 _, C _ij is _an intra term coefficient, It means each character. Additional explanations for the coefficients and expressions described in Equation 3 and Equation 4 will be provided later through Tables 2 and 3.

The third operation unit 350 determines the user's 3-dimensional shape based on the characteristic elements of the modeled potential function.

Figure 4 is a diagram showing several examples of a user's three-dimensional shape.

Referring to FIG. 4, it can be seen that the user's three-dimensional shape determined by the third operation unit 350 is one of four types: inverted cone, cylindrical, diamond, and cone.

When the potential function is determined through Equation 2 to Equation 4, the third operation unit 350 extracts the characteristic elements of the potential function, projects the extracted characteristic elements to coordinates in three-dimensional space, and calculates the projected coordinates. By connecting them in chronological order and analyzing the shape of the volume created in the 3D space, the 3D shape of the user can be determined. That is, the third operation unit 350 includes a module that receives a potential function and extracts feature elements, a module that projects the extracted feature elements onto coordinates in three-dimensional space, and a module that connects the projected coordinates of three-dimensional space in temporal order. This includes a module that creates a shape with a sense of quality within a three-dimensional space, a module that analyzes the unique irregularities, length, and thickness of the three-dimensional shape, and determines one of four three-dimensional shapes according to a pre-stored formula.

In particular, Figure 4 shows an example of a three-dimensional shape generated based on the user's systolic blood pressure data, and even for the same user, if the three-dimensional shape is generated based on the diastolic blood pressure, pulse, and electrocardiogram waveform, Figure 4 Although the shape is completely different from the three-dimensional shape shown in , the third operation unit 350 determines the shape to be one of an inverted cone, a cylinder, a diamond, and a cone.

Figure 4 (a) shows an inverted cone shape in which the overall cylindrical shape with an area narrowing from the top to the bottom is maintained, and the inverted cone including a sharp part at the bottom is tilted at an angle of 45 degrees. In addition, Figure 4 (b) shows a cone shape in which the cross-sectional areas of the top and bottom are kept constant, and Figures 4 (c) and (d) also have a three-dimensional shape to match the dictionary meanings of diamond and cone, respectively. It shows.

The third operation unit 350 extracts and analyzes the characteristic elements of the potential function to determine one of four predefined three-dimensional shapes. For a specific example, the third operation unit 350 may extract the coefficients constituting the time delay oscillator as characteristic elements of the potential function, and in this case, the interaction term in Equation 2 is considered omitted. The coefficients of the time delay oscillator will be further described later with reference to FIGS. 5 and 6.

As another embodiment, if a three-dimensional shape other than the above-described inverted cone, cone, diamond, or cylinder is defined in the third operation unit 350, the third operation unit 350 is set to determine the additionally defined three-dimensional shape. It could be.

The result output unit 370 searches for and outputs the circulatory system disease with the highest correlation value to the 3D shape determined by the third operation unit 350, based on a table that corresponds the ratio of the 3D shape to the circulatory system disease. .

Highest blood pressure type Number of patients (people) ratio(%) inverted cone 263 50.58 cylindrical 83 15.96 rhombus 76 14.62 conical 98 18.85 Sum 520 100

Table 2 is an example of a table referenced by the result output unit 370. Table 2 is reference information for creating a table that corresponds to the 3D shape and the rate of circulatory disease. When the 3D shape of the time delay oscillator was determined on 520 people, a mixture of circulatory disease patients and the general public, , It represents the relative ratio between three-dimensional shapes. Here, 520 users are users who showed characteristics that well correspond to actual results when measuring the potential for occurrence of circulatory diseases according to the present invention, and the data collected from them are considered refined user data. Referring to Table 2, when a 3D shape is created based on a time delay curve oscillator using data from patients actually suffering from circulatory diseases, it can be seen that close to half of all 3D shapes are inverted cones.

Highest blood pressure type High blood pressure(%) Coronary artery disease (%) diabetes(%) Hyperlipidemia (%) inverted cone 62.74 2.28 7.6 14.83 cylindrical 44.58 7.23 6.02 13.25 rhombus 80.26 5.26 6.58 18.42 conical 46.94 2.04 6.12 15.31 average 59.42 3.46 6.92 15.19

Table 3 is another example of a table referenced by the result output unit 370. Table 3 is a table that corresponds to the three-dimensional shape and the rate of circulatory disease, and can be generated based on Table 2. Interpreting the fourth row of Table 3, when systolic blood pressure data is used as user data and a 3D shape is created based on a time delay curve oscillator, among the diamond-shaped patients, 80.26% are suffering from high blood pressure, and 80.26% of the patients are suffering from coronary artery disease. It can be seen that 5.26% of patients are suffering from diseases, and 6.58% and 18.42% of patients are suffering from diabetes or hyperlipidemia, respectively. When further interpreting the above results, 4 out of 5 patients whose primary 3D shape for peak blood pressure is a diamond shape suffer from hypertension, which is the other 3D-shape group. This is a higher rate than that of patients suffering from high blood pressure. Likewise, it can be derived from Table 3 that patients whose 3D shape for peak blood pressure is a diamond suffer from hyperlipidemia at a higher rate than other 3D shape groups.

lowest blood pressure type High blood pressure(%) Coronary artery disease (%) diabetes(%) Hyperlipidemia (%) inverted cone 62.87 2.57 6.99 12.87 cylindrical 45.69 6.03 9.48 19.83 rhombus 63.16 5.26 2.63 15.79 conical 64.89 2.13 5.32 15.96 average 59.42 3.46 6.92 15.19

Table 4 is another example of a table referenced by the result output unit 370. Table 4 is a table that corresponds to the three-dimensional shape and the rate of circulatory disease. It is a table generated based on the user's diastolic blood pressure data, and is different from Tables 2 and 3, which are generated based on systolic blood pressure data. Interpreting the third row of Table 3, when diastolic blood pressure data was used as user data and a 3D shape was created based on a time delay curve oscillator, among patients whose 3D shape was cylindrical, the number of patients suffering from hypertension was 45.69. %, patients suffering from coronary artery disease are 6.03%, and patients suffering from diabetes or hyperlipidemia are 9.48% and 19.83%, respectively.

Comprehensively interpreting Table 3 and Table 4, if a 3D shape is created using the systolic blood pressure data of a hypertensive patient, it is most likely to be a diamond shape, and if a 3D shape is created using the diastolic blood pressure data, it is most likely to be a cone shape. You can see that it is high. In other words, the average ratio of patients with specific circulatory diseases in the total number of patients remains the same in both Tables 3 and 4 (59.42, 3.46, 6.92, and 15.19 in the order of hypertension, coronary artery disease, diabetes, and hyperlipidemia, respectively), but the four three dimensions For any one of the three-dimensional shapes, it is observed that it is much higher than the average. If Tables 3 and 4 are further expanded according to pulse and electrocardiogram, this difference appears more clearly. Ultimately, the device according to the present invention receives the user's time-series biosignal data, determines the three-dimensional shape, and determines the determined By additionally referring to the 3D shape table, it is possible to output circulatory diseases that the user has already suffered or is most likely to suffer in the future, thereby providing meaningful health information accurately and conveniently as information specialized for the user.

pulse type High blood pressure(%) Coronary artery disease (%) diabetes(%) Hyperlipidemia (%) inverted cone 59.06 3.41 4.99 15.22 cylindrical 64.29 3.57 14.29 17.86 rhombus 55.81 2.33 9.30 13.95 conical 60.00 5.00 12.50 12.50 average 59.42 3.46 6.92 15.19

Table 5 is another example of a table referenced by the result output unit 370. Table 5 is a table that corresponds to the three-dimensional shape and the rate of circulatory diseases. It is a table generated based on the user's pulse data, and is different from Tables 3 and 4, which are generated based on systolic blood pressure data or diastolic blood pressure data. In Table 5, the probability that the three-dimensional shape of a patient suffering from coronary artery disease is conical is about twice higher than that of a diamond shape, and the probability that the three-dimensional shape of a patient suffering from diabetes is a cylindrical shape is about three times higher than that of an inverted cone. It appears that

Patients with high blood pressure (%) lowest blood pressure inverted cone a cylindrical b diamond c conical d highest blood pressure Inverted conical A 64.46 54.55 58.33 70.00 Cylindrical B 50.00 25.93 66.67 60.00 Diamond C 77.50 88.89 80.00 83.33 Conical D 50.00 32.00 37.50 56.76

Table 6 is an example of a table combining Tables 3 and 4. Specifically, Table 6 shows numerically the results when two time delay curve oscillators are selected and created in a three-dimensional shape. Interpreting Table 6, if the systolic blood pressure data is diamond-shaped and the diastolic blood pressure data is cylindrical (hereinafter referred to as "Cb" type), the probability of being a hypertensive patient is close to 88.89%, while the systolic blood pressure data and diastolic blood pressure data are cylindrical (hereinafter referred to as "Cb" type). If all are cylindrical (hereinafter referred to as “Bb” type), it can be seen that the probability of being a patient with high blood pressure is only 25.93%.

According to the present invention, the result output unit 370 analyzes the user's systolic blood pressure data and diastolic blood pressure data, and if the Cb type is found, it can output a result that the user currently has high blood pressure or is likely to have high blood pressure in the future. . Meanwhile, the result output unit 370 may analyze the user's data and output, if the Bb type is found, the probability that the user does not have high blood pressure is relatively low, along with the actual probability value.

In Table 6, two time delay curve oscillators are selected, and examples are given only for systolic blood pressure data and diastolic blood pressure data, respectively. However, in the result output unit 370, a table is also provided for the user's pulse data or electrocardiogram data as described above. It can be constructed, and if an integrated table for a higher dimension than Table 6 is constructed, more accurate results can be provided to the user. It can be seen from the explanation through Table 6 that those with ordinary knowledge in this field can It will be self-evident to you.

As an optional embodiment, the second operation unit 330 may consider both intra terms and interaction terms when modeling a potential function that reflects the time series characteristics of the collected user data. In Table 6, a method of outputting the circulatory disease occurrence potential using two same types of oscillators has already been described. However, in this optional embodiment, a method of using two different types of oscillators is described. Do this.

Figure 5 is an example of a graph for explaining a duffing oscillator.

For convenience of explanation, the following will be described with reference to FIG. 3.

Figure 5(a) is a graph of two different waveforms overlaid on the same x-axis, and Figure 5(b) is the user's highest blood pressure data measured for 40 hours. The graph shown in (b) of FIG. 5 is raw data collected by the first operation unit 310, and shows how the user's systolic blood pressure changes over 40 hours. Here, it has already been explained that systolic blood pressure means systolic blood pressure.

Meanwhile, in (a) of Figure 5, two different graphs are overlapped. The left side shows the time delay curve oscillator modeled from (b) in Figure 5, and the right side shows the duffing oscillator modeled from (b) in Figure 5. it means. The time delay curve oscillator consists of a second-order differential term, a first-order differential term, a first-order term, and a third-order term, and can be modeled by repeating training and testing to have a form most similar to (b) in Figure 5. there is. At this time, the learning process is appropriate using one or more of the existing machine learning algorithms such as ANN (Artificial Neural Network), RNN (Recursive ANN), HMM (Hidden Markov Model), and SVM (Support Vector Machine). It can be used effectively.

When the second operation unit 330 completes modeling of the time delay curve oscillator, the second operation unit 330 models the modeled time delay curve oscillator and the vibration function with the smallest error, and during this modeling process, the duffing oscillator can be decided. The sum of the differences between the two graphs is defined as R ² , and the closer R ² is to 1, the more ideal the fitting is. The closer R ² is to 0, the poorer the fitting.

Referring to FIG. 5, in the modeling results of the time delay curve oscillator, the coefficient of the second-order differential term is maintained at 1, the remaining coefficients are α, β, and δ, respectively, and the maximum value of the function value in the modeling results of the duffing oscillator is γ. , it can be seen that the angular velocity is ω and the phase is θ.

Although not specified in FIG. 5 and FIG. 6 described later, (a) in FIG. 5 is the result of modeling based on systolic blood pressure data of a normal person without circulatory disease, and (a) in FIG. 6 is a result of modeling of a patient with angina pectoris. The results of modeling based on the patient's highest blood pressure data are shown. In normal people who do not have circulatory diseases, the fitting between the time delay curve oscillator and the duffing oscillator tends to be good, but in Figure 6, which will be described later, the fitting between the two oscillators tends to be poor. In other words, for normal people, R ² tends to be close to 1, and for patients with circulatory diseases, R ² tends to be close to 0.

Figure 6 is another example of a graph for explaining a duffing oscillator.

Figure 6(a) is a graph in which two different waveforms are overlapped on the same x-axis, and Figure 6(b) is peak blood pressure data of an angina patient measured over 40 hours. The graph shown in (b) of FIG. 6 is raw data collected in the first operation unit 310, and shows how the systolic blood pressure (systolic blood pressure) of an angina patient changes over 40 hours.

Since the user in FIG. 6 is a circulatory disease patient suffering from angina pectoris, the gap between the two oscillators has the characteristic of having a low R ² , and accordingly, in (a) of FIG. 6, the fitting between the time delay curve oscillator and the duffing oscillator is shown in FIG. 5 It is clearly shown that it does not work relatively well compared to (a). The y-axis in FIG. 6(a) represents the converted blood pressure value, and is scaled at a certain rate so as not to be the same as the y-axis in FIG. 6(b).

Correlation High blood pressure(%) Coronary artery disease (%) diabetes(%) Hyperlipidemia (%) Dizziness (%) High R type ² 44.12 0.00 8.82 20.59 35.29 low R type ² 60.49 3.70 6.79 14.81 27.57 average 59.42 3.46 6.92 15.19 28.08

Table 7 shows numerically the results when a time delay curve oscillator and a duffing oscillator are selected and created in a three-dimensional shape. In Table 7, the high R ² type refers to data for a normal user as shown in FIG. 5, where fitting between two different types of oscillators is easily achieved and a relatively high R ² value is calculated, and the low R ² The type refers to data on angina patients as shown in FIG. 6, where the fitting between two different types of oscillators is not good and a relatively low R ² value is calculated. Here, in order to determine whether the R ² value is relatively high or low, the result output unit 370 internally stores a reference value for comparison with the R ² value.

Interpreting Table 7, when fitting the time delay curve and Duffing oscillator on the systolic blood pressure data of 520 users, there were no patients suffering from coronary artery disease among the users with high R ² type. In the opposite interpretation, it can be said that the correlation of patients suffering from coronary artery disease is all low R ² type. Depending on the reference value for distinguishing between high R ² type and low R ² type, the ratio shown in Table 7 may vary, but if the user is determined to be high R ² type according to the present invention, the user does not suffer from coronary artery disease and , can be interpreted to mean that the risk of suffering from the disease in the future is extremely low.

Correlation High blood pressure(%) Coronary artery disease (%) diabetes(%) Hyperlipidemia (%) Dizziness (%) High R type ² 60.27 2.74 10.96 17.12 30.14 low R type ² 59.09 3.74 5.35 14.44 27.27 average 59.42 3.46 6.92 15.19 28.08

Table 8 is a table that further expands the contents of Table 7 and shows the results of fitting the time delay curve and duffing oscillator for the systolic blood pressure data and diastolic blood pressure data of 520 users. Referring to Table 8, it can be seen that the still high R ² type has a lower risk of coronary artery disease such as angina compared to the low risk R ² type.

The device according to the present invention defines the circulatory system disease oscillator through table data such as Tables 1 to 7 and Equations 1 to 4, and calculates the potential for occurrence of circulatory system diseases from the user's time-series biosignal data. You can print it out. In particular, according to the present invention, the potential function is divided into an intra term and an interaction term, and the potential for occurrence of circulatory disease is determined using only the intra term, or the potential for occurrence of a circulatory system disease is quantified by considering both the intra term and the interaction term. information can be provided to users.

For example, the device according to the present invention provides information that the potential for occurrence of high blood pressure is more than 80% to a user whose three-dimensional shape for systolic blood pressure data is a diamond, or provides information that the systolic blood pressure data is divided into two different types of oscillators. By fitting with , it is possible to provide information that the probability of occurrence of coronary artery disease is close to 0% due to the high ^R2 type. In the present invention, in order to provide users with numerical information about each disease, the three-dimensional shape of each circulatory disease oscillator is determined in three-dimensional space, the resulting analysis can be easily and accurately performed, and the number of samples is small. As the learning results increase and accumulate, more accurate results can be output.

According to a previously known invention, when user information is input, the user can be placed in the same group as specific patients, thereby providing information showing similarity to the corresponding patients. However, according to the present invention, for a preset time If there is measured biosignal data of the user, not only can the possibility of developing various circulatory diseases be directly quantified and output, but also, as a comparison group, it is possible to output whether the user is more at risk compared to other types of users.

In FIGS. 5 and 6, the modeling results of the time delay curve oscillator are limited to include only second to third order terms, but depending on the embodiment, more terms or fewer terms may be used.

Figure 7 is a diagram showing an example of a three-dimensional shape determined by three types of biosignal data.

The above-mentioned Table 6 is a numerical table showing that the potential for occurrence of circulatory diseases can be calculated in an integrated manner for the user's systolic blood pressure data and diastolic blood pressure data, and FIG. 7 is a more expanded concept than Table 6, and shows the preset time It schematically shows how to determine a unique three-dimensional shape for the user by collecting the user's systolic blood pressure data, diastolic blood pressure data, and pulse data measured during the period of time. In Figure 7, the user is a normal person who does not suffer from circulatory disease.

First, Figure 7(a) shows that when the potential function is modeled based on the user's systolic blood pressure data and diastolic blood pressure data, there is a high correlation between the two biosignal data.

Next, Figure 7(b) shows that when the potential function is modeled based on the user's highest blood pressure data and pulse data, there is no correlation between the two biosignal data.

Meanwhile, Figure 7(c) shows that when the potential function is modeled based on the user's diastolic blood pressure data and pulse data, there is no correlation between the two biosignal data.

Lastly, Figure 7(d) shows the three-dimensional shape of the user by integrating the results of Figures 7(a) to (c), as described in Figures 7(b) and (c). Although the user's pulse data is collected as biosignal data, it does not generate any correlation with the systolic and diastolic blood pressure data (the interaction term is 0), so it is a three-dimensional data in a three-dimensional space with systolic blood pressure, diastolic blood pressure, and pulse as each axis. The shape has substantially the same shape as (a) in Figure 7. The result output unit 370 can calculate and output the user's circulatory system disease occurrence potential based on (d) of FIG. 7.

Figure 8 is a diagram showing another example of a three-dimensional shape determined by three types of biosignal data.

In FIG. 8 , the user, unlike FIG. 7 , is a patient suffering from unstable angina.

First, Figure 8(a) shows that when the potential function is modeled based on the user's systolic blood pressure data and diastolic blood pressure data, there is a certain correlation between the two biosignal data. However, as explained in Table 7, (a) of FIG. 8 has a lower degree of correlation (low R ² type) than (a) of FIG. 7.

Next, Figure 8(b) shows that when the potential function is modeled based on the user's highest blood pressure data and pulse data, there is no correlation between the two biosignal data.

Meanwhile, Figure 8(c) shows that when the potential function is modeled based on the user's lowest blood pressure data and pulse data, there is a low degree of correlation between the two biosignal data.

Lastly, Figure 8(d) shows the three-dimensional shape of the user by integrating the results of Figures 8(a) to (c), and as explained in Figure 8(b), systolic blood pressure data Except for the absence of correlation with pulse data, the rest are recognized as correlations, so the three-dimensional shape in a three-dimensional space with systolic blood pressure, diastolic blood pressure, and pulse as each axis (referring to (d) in Figure 8) ) is a shape that linearly combines (a) of Figure 8 and (c) of Figure 8. The result output unit 370 can calculate and output the occurrence potential of the user's circulatory disease based on (d) of FIG. 8, and additionally provide the user with information that the user is likely to be suffering from coronary artery disease. You can.

Figure 9 schematically shows an example of determining the correlation between two oscillators based on whether the slope between them is positive or negative.

In FIGS. 7 and 8, in order to determine the correlation between oscillators, fitting as described in FIGS. 5 and 6 is performed, and the gap between the two functions for which the fitting has been completed is calculated, and the calculated square of R is close to 0 or 1. If classified into high R ² type or low R ² type based on the degree of proximity to , in Figure 9, the characteristic elements of the two oscillators are projected onto the coordinates to create a virtual plane, and the plane has an overall positive or negative slope. It can be understood as judging the correlation between oscillators.

Specifically, referring to FIG. 9, (a) of FIG. 9 shows an overall positive slope when a plane is created based on systolic blood pressure data and pulse data, so it can be called a positive type, and (b) of FIG. 9 ) represents an overall negative slope when a plane is created based on systolic blood pressure data and pulse data, so it can be called a negative type.

Correlation High blood pressure(%) Coronary artery disease (%) diabetes(%) Hyperlipidemia (%) Dizziness (%) Positive (+) 57.27 3.30 7.49 15.20 29.52 Negative type (-) 74.24 4.55 3.03 15.15 18.18 average 59.42 3.46 6.92 15.19 28.08

Table 9 shows a table of the occurrence potential of circulatory diseases corresponding to the positive and negative types described in FIG. 9. Referring to Table 9, if the result of inputting the user's systolic blood pressure data and pulse data into the device according to the present invention is negative, it can be seen that the user is likely to be a patient suffering from high blood pressure and coronary artery disease. You can.

Additionally, Table 9 is a table that can be integrated and applied to other embodiments described above. For example, if the user is type Cb in Table 6 and negative type in Table 9, the user is called type Cb-, and the probability of being a patient with high blood pressure is displayed as very high. Additionally, as another example, if the user is type Db in Table 6 and positive type in Table 9, the user is called type Db+ and has a low risk of developing coronary artery disease, but is highly likely to suffer from dizziness.

Figure 10 is a flow chart showing an example of a method according to the present invention.

Since the method according to FIG. 10 can be implemented by the device according to FIG. 3, it will be described below with reference to FIGS. 3 to 9, and descriptions that overlap with the content already described in FIG. 3 will be omitted. .

The first operation unit 310 receives and collects blood pressure, pulse, electrocardiogram data, etc. measured during a preset time (S1010).

Next, the second operation unit 330 fits the oscillator based on the received data (S1030). In step S1030, the second operation unit 330 may model a potential function that reflects the time series characteristics of the collected data.

The third operation unit 350 performs clustering based on the characteristic elements of the modeled potential function (S1050). It has already been explained through FIG. 4 that the clustered result can be expressed as a shape in three-dimensional space.

The result output unit 370 matches the clustering result with the disease-specific table and outputs the result (S1070). Specifically, the result output unit 370 searches for and outputs the circulatory system disease corresponding to the 3-dimensional shape determined in step S1050, based on a table that corresponds to the ratio of the 3-dimensional shape and the circulatory system disease, and this is shown in Table 1 This has been explained through Table 9.

Embodiments according to the present invention described above may be implemented in the form of a computer program that can be executed through various components on a computer, and such a computer program may be recorded on a computer-readable medium. At this time, the media includes magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and ROM. , RAM, flash memory, etc., may include hardware devices specifically configured to store and execute program instructions.

Meanwhile, the computer program may be designed and configured specifically for the present invention, or may be known and available to those skilled in the art of computer software. Examples of computer programs may include not only machine language code such as that created by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like.

The specific implementations described in the present invention are examples and do not limit the scope of the present invention in any way. For the sake of brevity of the specification, descriptions of conventional electronic components, control systems, software, and other functional aspects of the systems may be omitted. In addition, the connections or connection members of lines between components shown in the drawings exemplify functional connections and/or physical or circuit connections, and in actual devices, various functional connections or physical connections may be replaced or added. Can be represented as connections, or circuit connections. Additionally, if there is no specific mention such as “essential,” “important,” etc., it may not be a necessary component for the application of the present invention.

In the specification of the present invention (especially in the claims), the use of the term “above” and similar referential terms may refer to both the singular and the plural. In addition, when a range is described in the present invention, the invention includes the application of individual values within the range (unless there is a statement to the contrary), and each individual value constituting the range is described in the detailed description of the invention. It's the same. Finally, unless there is an explicit order or statement to the contrary regarding the steps constituting the method according to the invention, the steps may be performed in any suitable order. The present invention is not necessarily limited by the order of description of the above steps. The use of any examples or illustrative terms (e.g., etc.) in the present invention is merely to describe the present invention in detail, and unless limited by the claims, the scope of the present invention is limited by the examples or illustrative terms. It doesn't work. Additionally, those skilled in the art will recognize that various modifications, combinations and changes may be made according to design conditions and factors within the scope of the appended claims or their equivalents.

Claims (17)

A data collection step in which the first operation unit collects at least two of systolic blood pressure, diastolic blood pressure, pulse, and electrocardiogram measured from the user for a preset time;
A modeling step in which a second operation unit models a potential function reflecting time series characteristics of the collected data;
A 3D shape determination step in which a third operation unit determines the 3D shape of the user based on the characteristic elements of the modeled potential function; and
An output step in which the result output unit searches and outputs the circulatory system disease with the highest correlation value to the determined 3-dimensional shape, based on a table that corresponds to the ratio of the 3-dimensional shape and the circulatory system disease,
The potential function ( U _i ) derives an arbitrary force function by differentiation, and as expressed in <Equation 1> below, an intra term and an omitted interaction term are used. ), the intra term is defined as the sum of the internal potentials within the circulatory oscillator, and the interaction term is defined as the sum of the interaction terms between oscillators when there are two or more oscillators, causing circulatory disease. Potential output method.
<Equation 1>



i: Each term included in <Equation 1> is a value (function) for circulatory diseases and prodromal symptoms
C _ij: intra term coefficient
X _ij: circulatory descriptors in intra terms
C _ikl : interaction term coefficient
Y _ikl: circulatory descriptor in the interaction term According to paragraph 1,
The table is,
A circulatory system disease occurrence potential output method characterized in that it is a table that corresponds a three-dimensional shape to the ratio of at least two or more circulatory system diseases. According to paragraph 1,
The potential function is,
A method for outputting circulatory disease occurrence potential, characterized by including a second-order differential term. According to paragraph 1,
The potential function is,
A method for outputting circulatory disease occurrence potential, characterized by including a third-order term. According to paragraph 1,
The potential function is,
A method for outputting circulatory disease occurrence potential, characterized in that it is a time-delay curve including a differential term. According to paragraph 1,
The three-dimensional shape is,
A circulatory disease occurrence potential output method that includes at least two of cone, inverted cone, diamond, and cylindrical shapes. According to paragraph 1,
The circulatory system diseases are:
A method for outputting circulatory disease occurrence potential, characterized in that it includes at least one of high blood pressure, coronary artery disease, diabetes, and hyperlipidemia. According to paragraph 1,
A method for outputting a circulatory disease occurrence potential, characterized in that the number of branches of the determined three-dimensional shape is proportional to the number of branches of information collected in the data collection step. A computer-readable recording medium storing a program for executing the method according to any one of claims 1 to 8. In the circulatory system disease occurrence potential output device that performs the circulatory system disease occurrence potential output method described in claim 1,
a first operation unit that collects at least two of systolic blood pressure, diastolic blood pressure, pulse, and electrocardiogram measured from the user for a preset time;
a second operation unit that models a potential function reflecting the time series characteristics of the collected data;
a third operation unit that determines the three-dimensional shape of the user based on the characteristic elements of the modeled potential function; and
Based on a table that corresponds the ratio of the 3D shape to the circulatory system disease, a result output unit that searches for and outputs the circulatory system disease with the highest correlation value to the determined 3D shape; Outputting the potential for occurrence of circulatory system disease, including a Device. According to clause 10,
The table is,
A circulatory system disease occurrence potential output device, characterized in that it is a table that corresponds a three-dimensional shape to the ratio of at least two types of circulatory system diseases. According to clause 10,
The potential function is,
A circulatory disease occurrence potential output device comprising a second-order differential term. According to clause 10,
The potential function is,
A circulatory disease occurrence potential output device characterized by including a third-order term. According to clause 10,
The potential function is,
A circulatory disease occurrence potential output device characterized by a time-delay curve including a derivative term. According to clause 10,
The three-dimensional shape is,
A circulatory disease occurrence potential output device that includes at least two of the following shapes: conical, inverted conical, diamond, and cylindrical shapes. According to clause 10,
The circulatory system diseases are:
A circulatory disease occurrence potential output device, characterized in that it includes at least one of high blood pressure, coronary artery disease, diabetes, and hyperlipidemia. According to clause 10,
A circulatory disease occurrence potential output device, characterized in that the number of branches of the determined three-dimensional shape is proportional to the number of branches of information collected by the first operation unit.

Images