Apparatus and method for predicting cardiopulmonary fitness of individual
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Filing Date
- 2025-12-04
- Publication Date
- 2026-08-06
Smart Images
Figure KR2025020781_06082026_PF_FP_ABST
Abstract
Description
Device and method for predicting the cardiorespiratory fitness of an individual
[0001] The present invention relates to a device and method for predicting the cardiorespiratory fitness of an individual.
[0002] Cardiorespiratory fitness refers to the ability of the respiratory or circulatory systems to sustain prolonged exercise or activity by ensuring a smooth supply of oxygen to the energy-generating muscles. While it is the most reliable measure used to assess the cardiorespiratory capacity of the general public, including athletes, it is also closely related to the likelihood of developing cardiovascular disease and mortality rates from all diseases.
[0003] Existing methods for measuring an individual's cardiorespiratory fitness require treadmills / stationary bicycles and ergometers capable of performing exercise, as well as respiratory gas metabolism analyzers for measuring cardiorespiratory function, and necessitate a sufficient space to operate and measure these devices. Furthermore, experts capable of handling the equipment and skilled personnel capable of managing the risk of accidents during measurements are always required. A respiratory gas analyzer is a device that measures cardiorespiratory function during exercise by analyzing the concentrations of oxygen and carbon dioxide, respiratory volume, respiratory exchange ratio, maximum oxygen uptake, and calorie expenditure that occur during respiratory activity during exercise.
[0004] When measuring cardiorespiratory fitness using the method described above, cardiorespiratory capacity is assessed by providing the exerciser with an appropriate exercise load under the supervision of a professional and measuring maximum oxygen uptake and maximum heart rate at maximum exercise intensity, a state in which the exerciser does not become exhausted. By using this measurement method, each individual's cardiorespiratory level can be identified, and based on this, an exercise prescription suitable for the individual can be provided.
[0005] Measuring an individual's cardiorespiratory fitness forms the basis for personalized aerobic exercise prescriptions; however, as previously explained, the measurement method is cumbersome and uneconomical. To address this issue, a simple formula—'Maximum Heart Rate = 220 - Age'—is used to determine the maximum heart rate based on one's age, allowing for the setting of an appropriate aerobic exercise intensity. However, this method only provides a rough range of exercise intensity and is not a means to evaluate an individual's actual level of cardiorespiratory fitness.
[0006] Recently, there has been active development of algorithms based on big data that can conveniently measure an individual's health status. In line with these technological advancements, there is a need for a method to measure an individual's cardiorespiratory fitness status by utilizing personal health and lifestyle information, without the need for specific locations or equipment.
[0007]
[0008] Cardiorespiratory fitness is defined as the body's ability to adapt to prolonged, continuous exercise and is one of the key factors in health-related physical fitness. Good cardiorespiratory function implies a high capacity for oxygen utilization; by maintaining robust organs—including the heart, lungs, and muscles—one can perform tasks for extended periods, thereby preventing fatigue, increasing resistance to stress, and helping to prevent cardiovascular diseases and cancer. Cardiorespiratory fitness can be assessed by determining whether one can consistently perform aerobic exercises, such as running, cycling, and swimming, or climb stairs without strain.
[0009] The standard measurement method for cardiorespiratory fitness is maximum oxygen uptake ( Maximal oxygen uptake is a term representing the amount of oxygen that can be consumed per unit of time when exercise intensity reaches its maximum, and it is determined by an individual's aerobic capacity, that is, oxygen transport capacity and tissue oxygen utilization capacity. Maximal oxygen uptake can be measured through exercise stress tests using a treadmill or cycle ergometer and a gas analyzer; however, this method has disadvantages due to issues of convenience and cost-effectiveness. Therefore, an alternative method is needed to assess an individual's cardiorespiratory fitness based on various physical information.
[0010] Therefore, the purpose of this institution is to overcome the difficulties of such inaccessible methods and to present a method for evaluating an individual's cardiorespiratory fitness level by utilizing simple anthropometric measurements and health checkup indicators.
[0011]
[0012] The present invention provides a device for evaluating the cardiorespiratory fitness of an individual, comprising at least one processor and at least one memory including computer program code, wherein the at least one memory and the computer program code are configured such that the cardiorespiratory fitness evaluation device acquires health information of a plurality of individuals through the at least one processor, derives a plurality of cardiorespiratory fitness evaluation variables from the health information through a machine learning model, derives a cardiorespiratory fitness evaluation formula considering the weights of each of the plurality of cardiorespiratory fitness evaluation variables, acquires information on the plurality of cardiorespiratory fitness evaluation variables of a specific individual, and evaluates the cardiorespiratory fitness of the specific individual using the information on the plurality of cardiorespiratory fitness evaluation variables of the specific individual and the cardiorespiratory fitness evaluation formula.
[0013] Furthermore, the present invention provides a method for evaluating cardiorespiratory fitness performed in a device for evaluating cardiorespiratory fitness, comprising the steps of: acquiring health information of a plurality of individuals; deriving a plurality of cardiorespiratory fitness evaluation variables from the health information through a machine learning model; deriving a cardiorespiratory fitness evaluation formula by considering the weights of each of the plurality of cardiorespiratory fitness evaluation variables; acquiring information on the plurality of cardiorespiratory fitness evaluation variables of a specific individual; and evaluating the cardiorespiratory fitness of the specific individual using the information on the plurality of cardiorespiratory fitness evaluation variables of the specific individual and the cardiorespiratory fitness evaluation formula.
[0014]
[0015] Through this facility, an individual's cardiorespiratory fitness can be predicted by utilizing simple anthropometric measurements or health checkup indicators.
[0016]
[0017] FIG. 1 shows a block diagram of an apparatus according to the present invention.
[0018] Figure 2 shows a flowchart of the method according to the present invention.
[0019] Figure 3a shows the health and physical fitness standards for Koreans (adults / elderly).
[0020] Fig. 3b is It shows the correlation between the waist circumference value relative to body weight.
[0021] Figure 3c shows the median and 3rd quartiles of waist circumference relative to body weight.
[0022] FIG. 4 is a diagram illustrating the training process of a machine learning modeling process according to one embodiment of the present invention.
[0023] FIG. 5 is a diagram illustrating the training process of a machine learning modeling process according to one embodiment of the present invention.
[0024] Figure 6 shows the result of calculating a cardiopulmonary score using an evaluation formula derived according to one embodiment of the present invention.
[0025] Figure 7 shows the AUC-ROC results of a development dataset according to one embodiment of the present invention.
[0026] Figure 8 shows the AUC-ROC results of a verification dataset according to one embodiment of the present invention.
[0027]
[0028] Embodiments of the present invention are described below with reference to the attached drawings so that those skilled in the art can easily implement them. However, the present invention may be embodied in various different forms and is not limited to the embodiments described herein. Furthermore, in order to clearly explain the present invention in the drawings, parts unrelated to the explanation have been omitted, and similar parts throughout the specification are denoted by similar reference numerals.
[0029] Throughout this specification, when a part is described as "comprising" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.
[0030] The terms “step” or “step of” used throughout this specification do not mean “step for”.
[0031] Throughout this specification, the term “combination(s) of these” included in the Markush-type expression means one or more mixtures or combinations selected from the group consisting of the components described in the Markush-type expression, and means including one or more selected from the group consisting of said components.
[0032] Throughout this specification, the description "A and / or B" means "A or B, or A and B".
[0033] Throughout the entire specification, the term “part” includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more hardware, and two or more units may be realized by one hardware.
[0034] Throughout this specification, the term "object" refers to a subject for which cardiorespiratory fitness is to be predicted, and is preferably a person. Here, the term "person" may include Koreans of other groups, or foreigners such as Chinese, Japanese, and American nationals, although the present embodiment used data obtained from a specific group of Koreans.
[0035] The functions realized by the components described herein may be implemented in a general-purpose processor, a specific-purpose processor, an integrated circuit, an Application Specific Integrated Circuit (ASIC), a Central Processing Unit (CPU), a circuit, and / or a combination thereof, which are programmed to realize the described functions. A processor may include transistors or other circuits and is considered to be a circuit or a processing circuit. A processor may be a programmed processor that executes a program stored in memory.
[0036] In this specification, circuits, parts, units, and means are hardware programmed to realize or perform the described functions. Such hardware may be any hardware disclosed in this specification or any hardware known to be programmed or perform the described functions.
[0037] If the hardware is a processor considered to be of a circuit type, the circuit, the part, means, or unit is a combination of the hardware and the software used to constitute the hardware and / or processor.
[0038] Hereinafter, embodiments and examples of the present invention will be described in detail with reference to the attached drawings. However, the present invention may not be limited to these embodiments and examples and the drawings.
[0039] FIG. 1 shows a block diagram of a device according to the present invention. Referring to FIG. 1, the cardiorespiratory fitness evaluation device (1) of the present invention may include at least one processor (10) and at least one memory (20) (storage device / storage) containing computer program code.
[0040] At least one memory (20) and computer program code allow the cardiorespiratory fitness evaluation device (1) to evaluate the cardiorespiratory fitness of a specific individual through at least one processor (10).
[0041] The cardiorespiratory fitness evaluation device (1) can derive cardiorespiratory fitness evaluation variables that can evaluate the cardiorespiratory fitness of a specific individual using health information of multiple individuals, and can derive a cardiorespiratory fitness evaluation formula through this.
[0042] For example, the cardiorespiratory fitness evaluation device (1) can acquire health information of multiple individuals for the training of a machine learning model and train the machine learning model so that the machine learning model derives multiple cardiorespiratory fitness evaluation variables from the health information.
[0043] According to one embodiment of the present invention, the term "multiple entities" means "multiple Koreans" when, for example, the entity is a Korean, and in this case, the term "health information of multiple entities" means "health information of multiple Koreans." Specifically, according to the embodiment below, the health information of multiple entities may be data from the "National Fitness 100 Project," but is not limited thereto.
[0044] According to one embodiment of the present invention, the health information includes information that can be a variable for evaluating cardiorespiratory fitness, and for example, the health information may include, but is not limited to, systolic blood pressure (mmHg), diastolic blood pressure (mmHg), gender (male / female), total cholesterol (mg / dL), fasting blood glucose (mmol / L), body fat mass (kg), triglycerides (mg / dL), age (years), HDL cholesterol (mg / dL), BMI, drinking status (abstinence, 0; drinking, 1), and skeletal muscle mass (kg).
[0045] According to one embodiment of the present invention, the machine learning model is a generalized linear model, and a plurality of cardiorespiratory fitness evaluation variables may additionally be derived from the health information through an Elastic net algorithm or a Lasso algorithm.
[0046] Regression analysis refers to a technique for modeling the correlation between multiple independent variables and a single dependent variable. Generalized linear regression, used in generalized linear models, refers to modeling f(y), which is obtained by transforming the dependent variable into an appropriate function, as a linear combination of independent variables and regression coefficients.
[0047] Multiple cardiorespiratory fitness evaluation variables may be derived by setting health information as the independent variable and the cardiorespiratory fitness levels of multiple individuals as the dependent variable and using a generalized linear regression algorithm.
[0048] The Elastic Net and Lasso algorithms are regularization techniques used to exclude variables with low weights. Multiple cardiorespiratory fitness assessment variables may be derived by applying a generalized linear regression algorithm followed by removing variables with low weights using the Elastic Net and Lasso algorithms.
[0049] The cardiorespiratory fitness evaluation device (1) can derive a cardiorespiratory fitness evaluation formula by considering the weights of each of the multiple cardiorespiratory fitness evaluation variables. Here, the weight may refer to the degree of correlation (slope) between the independent variable and the dependent variable in regression analysis.
[0050] That is, as described above, in the regression analysis in which health information is the independent variable and the cardiorespiratory fitness level of the multiple individuals is the dependent variable, the weights can be derived based on the degree of correlation between the health information, which is the independent variable, and the cardiorespiratory fitness level of the multiple individuals, which is the dependent variable.
[0051]
[0052] The cardiorespiratory fitness evaluation device (1) can evaluate the cardiorespiratory fitness of a specific individual using the derived cardiorespiratory fitness evaluation formula.
[0053] According to one embodiment of the present invention, a cardiorespiratory fitness evaluation device (1) can obtain a plurality of cardiorespiratory fitness evaluation variable information of a specific individual and evaluate the cardiorespiratory fitness of a specific individual using the plurality of cardiorespiratory fitness evaluation variable information of the specific individual and a cardiorespiratory fitness evaluation formula.
[0054] The features of the cardiorespiratory fitness evaluation device (1) described above also apply to the cardiorespiratory fitness evaluation method (Fig. 2) according to the present invention.
[0055] Example 1. Derivation of Cardiorespiratory Fitness Evaluation Formula
[0056] To derive the cardiorespiratory fitness assessment formula, data from the 'National Fitness 100 Project' organized by the Ministry of Health and Welfare and the Korea Sports Promotion Foundation was obtained.
[0057] The 'National Fitness 100 Project' is a project that measures the diverse physical fitness and health status of Koreans to present fitness levels reflecting health characteristics by life cycle, aiming to prevent disease and improve mental health and quality of life. It involves conducting demographic surveys, blood and body composition tests, cardiorespiratory fitness tests, and flexibility tests.
[0058] Regarding the project data, initial data was obtained for 2,887 individuals, excluding missing values, out of a total of 3,782 adult and elderly men and women aged 19 or older who visited national physical fitness certification centers and completed physical fitness measurements and health checkups / surveys.
[0059] Oxygen intake and waist circumference relative to body weight were selected as indicators to evaluate cardiorespiratory fitness. The individual's oxygen intake was calculated using the VO₂max item from the database, and waist circumference relative to body weight was calculated by dividing the waist circumference (cm) by the square root of the body weight (kg).
[0060] More specifically, VO₂max was applied according to the criteria in Fig. 3a, and waist circumference relative to body weight was verified for correlation with VO₂max (R=-0.619, p<0.001) based on the database (see Fig. 3b). Then, using the median and 3rd quartiles of waist circumference relative to body weight, the subjects were divided into a high-income group (1156 people), a middle-income group (768 people), and a low-income group (963 people) of cardiorespiratory fitness (see Fig. 3c).
[0061] Based on the previously defined judgment criteria, the proportions of combinations of the subgroup and uppergroup of cardiorespiratory fitness indicators were examined. For the application of logistic regression analysis, individuals judged to have both indicators as normal were classified into the upper cardiorespiratory function group (n=1156), and those judged to have two or more indicators as insufficient were classified into the subgroup (n=963). These extreme values were used to develop a machine learning algorithm.
[0062] The final data of a total of 2,119 people was divided into a development dataset (training set; 70% of the total data, 1,484 people) and a verification dataset (test set; 30% of the total data, 635 people). Then, the development dataset was used as health information of multiple individuals to derive a cardiorespiratory fitness evaluation formula, and the performance of the cardiorespiratory fitness evaluation device (1) or method according to the present invention was evaluated in Example 2 below through ROC curve analysis using the verification dataset.
[0063] Specific information on the health of multiple individuals is as shown in Table 1 below.
[0064] Systolic Blood Pressure (mmHg) Diastolic Blood Pressure (mmHg) Gender (Male / Female) Total Cholesterol (mg / dL) Fasting Blood Glucose (mmol / L) Body Fat Mass (kg) Triglycerides (mg / dL) Age (years) HDL Cholesterol (mg / dL) BMI Alcohol Consumption (Abstinence, 0; Drinking, 1) Skeletal Muscle Mass (kg)
[0065] Using a generalized linear model, a regression model among machine learning algorithms, the health information in Table 1 above was set as independent variables, and modeling was performed to verify the correlation between two or more independent variables and the dependent variable, cardiorespiratory fitness. Subsequently, the Elastic net (selecting or removing multiple variables with high correlation) and Lasso (randomly selecting one of multiple correlated variables to reduce the coefficient (a constant multiplied in front of the equation)) methods were applied, and the most suitable model among them was selected (Figs. 4, 5).
[0066] Considering the multiple cardiorespiratory fitness evaluation variables derived through the above process and the weights of each variable, the following cardiorespiratory fitness evaluation formula was derived.
[0067] At this time, it can be seen that multiple cardiorespiratory fitness evaluation variables include age, gender, BMI, skeletal muscle mass, fasting blood glucose, alcohol consumption, body fat mass, systolic blood pressure, diastolic blood pressure, total cholesterol, triglycerides, and HDL cholesterol.
[0068] Y=(0.11)+(-1.53)*Age+(0.77)*Gender+(-0.06)*BMI+(1.21)*Skeletal Muscle Mass+(-0.38)*Fasting Blood Glucose+(-0.02)*Drinking Status+(-0.96)*Body Fat Mass+(-0.419)*Systolic Blood Pressure+(0.454)*Diastolic Blood Pressure+(-0.13)*Total Cholesterol+(-0.07)*Triglycerides+(0.38)*HDL Cholesterol
[0069] Herein, the above mathematical formula is merely an example and does not limit the scope of the present invention,
[0070] It can be expressed as [Mathematical Formula 1] below.
[0071]
[0072] Y represents the cardiorespiratory fitness evaluation formula, C is a constant, x is a plurality of cardiorespiratory fitness evaluation variables, and A represents the weight of each cardiorespiratory fitness evaluation variable.
[0073] Through the final derived evaluation formula, the cardiorespiratory fitness scores of the upper, middle, and lower groups were recalculated, and it was confirmed that the upper, middle, and lower groups were clearly distinguished through these scores (Fig. 6).
[0074] Example 2. ROC curve analysis
[0075] The performance of the cardiorespiratory fitness evaluation device (1) or method according to the present invention was evaluated through ROC curve analysis using the verification dataset of Example 1 (test set; 30% of the total data, 635 people).
[0076] We applied the derived evaluation formula to the entire development dataset and the validation dataset to calculate cardiorespiratory fitness scores, and conducted an ROC curve analysis to evaluate the ability to distinguish between the upper and lower cardiorespiratory fitness groups. The AUC-ROC of the entire development dataset (training set) was derived as 0.926 (Fig. 7, sensitivity 83.9%, specificity 87.9%, accuracy 85.7%). As a result of applying the formula to the validation dataset (test set), the AUC-ROC was derived as 0.923 (Fig. 8, sensitivity 86.6%, specificity 86.3%, accuracy 86.5%). Through this, it was confirmed that the cardiorespiratory fitness evaluation device or method according to the present invention can accurately evaluate the cardiorespiratory fitness of an individual.
Claims
1. In a device for evaluating the cardiorespiratory fitness of an individual, At least one processor; and It includes at least one memory containing computer program code, and The above at least one memory and the computer program code through the above at least one processor The above cardiorespiratory fitness evaluation device Acquire health information of multiple entities, and Multiple cardiorespiratory fitness evaluation variables are derived from the above health information through a machine learning model, and A cardiorespiratory fitness evaluation formula is derived by considering the weight of each of the aforementioned multiple cardiorespiratory fitness evaluation variables, and Acquiring information on the aforementioned multiple cardiorespiratory fitness evaluation variables of a specific individual, and A cardiorespiratory fitness evaluation device configured to evaluate the cardiorespiratory fitness of a specific individual using the plurality of cardiorespiratory fitness evaluation variable information of the specific individual and the cardiorespiratory fitness evaluation formula.
2. In Paragraph 1, A cardiorespiratory fitness evaluation device in which the above health information includes systolic blood pressure (mmHg), diastolic blood pressure (mmHg), gender (male / female), total cholesterol (mg / dL), fasting blood glucose (mmol / L), body fat mass (kg), triglycerides (mg / dL), age (years), HDL cholesterol (mg / dL), BMI, alcohol consumption status (abstinence, 0; alcohol consumption, 1), and skeletal muscle mass (kg).
3. In Paragraph 1, The above machine learning model is a generalized linear model, and The above plurality of cardiorespiratory fitness evaluation variables are, Additionally, a cardiorespiratory fitness evaluation device derived from the above health information through an Elastic net algorithm or a Lasso algorithm.
4. A method for evaluating cardiorespiratory fitness performed on a device for evaluating cardiorespiratory fitness, Step of acquiring health information of multiple entities; A step of deriving a plurality of cardiorespiratory fitness evaluation variables from the above health information through a machine learning model; and A step of deriving a cardiorespiratory fitness evaluation formula by considering the weight of each of the plurality of cardiorespiratory fitness evaluation variables mentioned above; A step of obtaining information on the aforementioned plurality of cardiorespiratory fitness evaluation variables of a specific entity; A step of evaluating the cardiorespiratory fitness of the specific individual using the plurality of cardiorespiratory fitness evaluation variable information of the specific individual and the cardiorespiratory fitness evaluation formula; A method for evaluating cardiorespiratory fitness, including 5. In Paragraph 4, The above health information includes systolic blood pressure (mmHg), diastolic blood pressure (mmHg), gender (male / female), total cholesterol (mg / dL), fasting blood glucose (mmol / L), body fat mass (kg), triglycerides (mg / dL), age (years), HDL cholesterol (mg / dL), BMI, alcohol consumption status (abstinence, 0; alcohol consumption, 1), and skeletal muscle mass (kg), a method for evaluating cardiorespiratory fitness.
6. In Paragraph 4, The above machine learning model is a generalized linear model, and The step of deriving the above plurality of cardiorespiratory fitness evaluation variables is, A method for evaluating cardiorespiratory fitness, comprising the step of additionally deriving cardiorespiratory fitness evaluation variables from health information through an Elastic net algorithm or a Lasso algorithm.