A method and system for monitoring and evaluating elderly health based on big data
The method and system leverage big data analysis to analyze physical data dimensions, create data change curves, and calculate risk indices, addressing inefficiencies and inaccuracies in elderly health monitoring by accurately assessing chronic disease risks.
Patent Information
- Application Number
- CN202411113441.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-14
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-08-14
AI Technical Summary
Existing methods for monitoring and evaluating the health of the elderly fail to analyze the deep connections between physical data of different dimensions and lack historical data screening, leading to inefficiency and low accuracy in identifying chronic diseases.
A method and system that utilizes big data to obtain and analyze physical data of different dimensions, create normal and abnormal data change curves, determine disease dominance, and calculate a disease risk index to accurately assess health status.
Enhances the accuracy of health monitoring and evaluation by comparing current data with historical data, identifying abnormal factors, and determining disease risk indices, thereby providing precise health assessments.
Smart Images

Figure CN118629659B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of medical care data processing, and in particular to a method and system for monitoring and evaluating the health of the elderly based on big data. Background Art
[0002] In the field of medical health, how to provide comprehensive and intelligent health management services for the elderly to protect their health has always been an important research topic. In actual situations, wearable health monitoring systems can be used to collect 24-hour physical information of the elderly, and computer communication technology can be used to achieve continuous remote health monitoring, so as to provide real-time warnings for possible abnormal situations and predict potential health problems in advance.
[0003] In the process of health monitoring and evaluation of the elderly, their physical data are usually analyzed to identify possible chronic disease risks. When identifying the chronic disease risks of the elderly, the existing methods monitor whether the changes in their various physical indicators are normal, and compare them with historical big data to determine whether the elderly have chronic diseases. However, this evaluation method does not analyze the deep relationship between physical data of different dimensions and each chronic disease of the elderly, and lacks the screening of historical data when comparing data, resulting in inefficiency and lack of accuracy in data analysis, which in turn makes it impossible to accurately monitor and evaluate the health of the elderly. Summary of the invention
[0004] In order to solve the technical problem that the existing methods for identifying chronic diseases in the elderly ignore the deep connection between physical data of different dimensions and each chronic disease in the elderly, and lack the screening of historical big data when comparing data, resulting in low efficiency and insufficient precision in data analysis, and thus unable to accurately monitor and evaluate the health of the elderly, the purpose of the present invention is to provide a method and system for health monitoring and evaluation of the elderly based on big data, and the technical scheme adopted is as follows: a method for health monitoring and evaluation of the elderly based on big data, the method comprising: obtaining physical data of different dimensions of each elderly person at the current sampling moment and the historical sampling moments; obtaining the types of chronic diseases suffered by each elderly person; selecting any chronic disease in the elderly as the target chronic disease, and obtaining the normal health of the elderly in each dimension according to the physical data fluctuation characteristics of all elderly people who do not suffer from the target chronic disease at all historical sampling moments in each dimension. Data change curve; obtaining the abnormal physical factors of each elderly person with the target chronic disease in each dimension according to the difference between the physical data of each elderly person with the target chronic disease at all historical sampling moments in each dimension and the normal data change curve; obtaining the degree of dominance of the physical data in each dimension for the target chronic disease according to the change characteristics of the abnormal physical factors of all elderly people with the target chronic disease; screening all elderly people with the target chronic disease according to the abnormal physical factors of all elderly people with the target chronic disease in each dimension to obtain the target elderly patient group; obtaining the disease risk index of each elderly person with the target chronic disease according to the difference in physical data of each elderly person and the target elderly patient group in each dimension and the disease dominance of each dimension; conducting a health assessment on each elderly person according to the disease risk index of each elderly person for each elderly chronic disease.
[0005] Furthermore, the method for obtaining the normal data change curve includes: averaging the physical data of each dimension of all elderly people who do not suffer from the target chronic disease at each historical sampling moment to obtain standard data of each dimension at each historical sampling moment; fitting the standard data of each dimension at all historical sampling moments into the normal data change curve of the elderly in each dimension.
[0006] Furthermore, the method for obtaining the abnormal body factor includes: selecting an elderly person suffering from a target chronic disease as a target elderly person, and selecting a dimension as a target dimension; fitting the physical data of the target elderly person in the target dimension into a target physical data curve; and obtaining the abnormal body factor according to a calculation formula for the abnormal body factor, wherein the calculation formula for the abnormal body factor is as follows: In the formula, Indicates the physical abnormality factor of the target elderly in the target dimension; Indicates the number of body data of the target dimension; The target body data curve The slope of the location of the body data; The first one represents the normal data change curve of the target dimension The slope of the location of the standard data; The target body data curve The data value of each body data; The first one represents the normal data change curve of the target dimension The data value of the standard data; represents an exponential function with a natural constant as base; Represents a symbolic function.
[0007] Furthermore, the method for obtaining the disease dominance degree includes: obtaining the disease dominance degree according to a disease dominance degree calculation formula, and the disease dominance degree calculation formula is as follows: In the formula, Indicates the ordinal number of the target dimension; Indicates the degree of dominance of the physical data of the target dimension for the target chronic disease; indicates the number of older adults with the target chronic condition; Indicates the first Physical abnormality factors of the elderly in the target dimension; Indicates the first The average physical abnormality factor of all dimensions in the elderly; Represents the maximum value function.
[0008] Furthermore, the method for obtaining the target elderly patient group includes: obtaining the data preference degree of each elderly person suffering from the target chronic disease according to the physical abnormality factors in all dimensions of each elderly person suffering from the target chronic disease; and selecting a preset number of elderly people with the highest data preference degree as the target elderly patient group.
[0009] Furthermore, the method for obtaining the data preference degree includes: averaging the square of the physical abnormality factor of each elderly person suffering from the target chronic disease in each dimension to obtain the data preference degree of each elderly person suffering from the target chronic disease.
[0010] Furthermore, the method for obtaining the disease risk index of each elderly person suffering from the target chronic disease includes: obtaining the disease risk index according to a disease risk index calculation formula, and the disease risk index calculation formula is as follows: In the formula, Indicates the risk index of each elderly person suffering from the target chronic disease; represents the number of elderly people in the target elderly patient group; Indicates the number of dimensions; Represents the number of body data in each dimension, where the number of bodies in each dimension is the same; Indicates that every elderly person In the dimension The data value of each body data; Indicates the first The elderly in In the dimension The data value of each body data; Indicates The degree to which each dimension of physical data is dominant in the prevalence of the target chronic disease; Represents the normalization function.
[0011] Furthermore, the derivative of each data of the target body data curve and the normal data change curve is used as the slope of the position where each data of the target body data curve and the normal data change curve is located.
[0012] Furthermore, a health assessment is conducted on each elderly person based on his or her risk index for each chronic disease of the elderly, including: calculating the risk index of each elderly person for each chronic disease of the elderly; when the risk index of any chronic disease of the elderly is greater than a preset first threshold, it is considered that the current elderly person is at a greater risk of disease.
[0013] A big data-based elderly health monitoring and assessment system, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the above methods when executing the computer program.
[0014] The present invention has the following beneficial effects: since the present invention needs to obtain historical big data of the elderly as standard data to compare with the physical data of the elderly being monitored at the current sampling moment in each dimension, the physical data of each elderly person at the current sampling moment and the historical sampling moments in different dimensions are obtained; since the influence of the physical data of each dimension on each chronic disease of the elderly needs to be analyzed later, the type of chronic disease of the elderly suffered by each elderly person is obtained; since the physical data of the elderly suffering from the target chronic disease are abnormal compared with other elderly people who do not suffer from the target chronic disease, the normal data change curve of the elderly in each dimension is first obtained; then, according to the difference between the physical data of each elderly person suffering from the target chronic disease at all historical sampling moments in each dimension and the normal data change curve, the physical abnormality factor of each elderly person suffering from the target chronic disease in each dimension is obtained; Because the influence of different dimensions of body data on different elderly chronic diseases is different, the dominant degree of the body data of each dimension on the target chronic disease is analyzed; because in reality, not every elderly person with the target chronic disease has precursors or abnormalities in the early stage of the disease, the reference value of the body data of these elderly people in the comparison is smaller, so the body data of the elderly with the target chronic disease should be screened to obtain the target elderly patient group; in order to analyze the risk of each elderly person suffering from the target chronic disease, the risk index of each elderly person suffering from the target chronic disease is obtained according to the difference in body data of each elderly person and the target elderly patient group in each dimension and the dominant degree of the disease in each dimension, reflecting the risk of each elderly person suffering from each chronic disease; according to the risk index of each elderly person for each elderly chronic disease, each elderly person is evaluated for health. The present invention compares the connection between body data and chronic diseases in all dimensions, selects the most valuable body data for analysis, thereby obtaining a health assessment model for the elderly with higher accuracy, and then more accurately performs health monitoring and assessment on the elderly. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0016] Figure 1 A flow chart of a method for monitoring and evaluating the health of the elderly based on big data is provided in accordance with an embodiment of the present invention. DETAILED DESCRIPTION
[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, characteristics and effects of a method and system for monitoring and evaluating the health of the elderly based on big data proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.
[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
[0019] The following is a detailed description of a big data-based elderly health monitoring and assessment method and system provided by the present invention in conjunction with the accompanying drawings.
[0020] See also Figure 1 , which shows a method for monitoring and evaluating the health of the elderly based on big data provided by an embodiment of the present invention, the method comprising: step S1: obtaining the physical data of each elderly person in different dimensions at the current sampling time and the historical sampling time; obtaining the types of chronic diseases suffered by each elderly person.
[0021] The embodiment of the present invention is mainly used in the scenario of monitoring and evaluating chronic diseases of the elderly. In order to evaluate the health status of each elderly person, it is first necessary to obtain the historical big data of the elderly as standard data to compare with the physical data of each dimension of the elderly being monitored at the current sampling time, and perform subsequent analysis. Therefore, in the embodiment of the present invention, the physical data of each elderly person in different dimensions at the current sampling time and the historical sampling time are obtained; because the impact of the physical data of each dimension on each chronic disease of the elderly is to be analyzed later, it is necessary to obtain the type of chronic disease suffered by each elderly person, and analyze the physical data of each dimension of the elderly suffering from a certain chronic disease of the elderly to obtain the impact of the physical data of each dimension on the chronic disease of the elderly. For specific analysis, please refer to the subsequent embodiments.
[0022] In one embodiment of the present invention, the dimensions of the body data include: heart rate, blood pressure, body temperature, blood sugar, etc. It should be noted that in other embodiments of the present invention, body data of other dimensions may also be collected, which is not limited here.
[0023] The sampling frequency of the body data is once every 10 minutes, that is, in the embodiment of the present invention, the time difference between two adjacent sampling moments is 10 minutes. It should be noted that the sampling frequency can be set by oneself and is not limited here.
[0024] Step S2: Select any chronic disease of the elderly as the target chronic disease, and obtain the normal data change curve of the elderly in each dimension based on the physical data fluctuation characteristics of all elderly people who do not suffer from the target chronic disease at all historical sampling moments in each dimension; obtain the physical abnormality factor of each elderly person with the target chronic disease in each dimension based on the difference between the physical data of each elderly person with the target chronic disease at all historical sampling moments in each dimension and the normal data change curve.
[0025] Since the physical data abnormalities caused by each chronic disease of the elderly are different, each chronic disease of the elderly is analyzed separately. And for the elderly with the target chronic disease, their physical data are abnormal relative to the physical data of other elderly people who do not have the target chronic disease, so it is extracted from the historical big data, and the physical data of other elderly people who do not have the target chronic disease in each dimension at all historical sampling moments are used as standard samples, and compared with the physical data of each elderly person with the target chronic disease in each dimension, that is, in the embodiment of the present invention, according to the physical data fluctuation characteristics of all elderly people who do not have the target chronic disease at all historical sampling moments in each dimension, the normal data change curve of the elderly in each dimension is obtained.
[0026] Preferably, in one embodiment of the present invention, the method for obtaining the normal data change curve includes: averaging the physical data of each dimension of all elderly people who do not suffer from the target chronic disease at each historical sampling moment to obtain the standard data of each dimension at each historical sampling moment; fitting the standard data of each dimension at all historical sampling moments into the normal data change curve of the elderly in each dimension.
[0027] In one embodiment of the present invention, the least square method is used to fit the standard data of each dimension at all historical sampling moments into the normal data change curve of the elderly in each dimension. It should be noted that the fitting can also be performed using a machine learning method, and both the least square method and machine learning are technical means well known to those skilled in the art, and will not be described in detail here.
[0028] After obtaining the normal data change curve of the elderly in each dimension, the physical data of the elderly suffering from the target chronic disease are compared with the normal data, so as to analyze in which dimensions the physical data of the elderly suffering from the target chronic disease will produce greater abnormalities compared with the normal data. Therefore, in the embodiment of the present invention, the physical abnormality factor of each elderly suffering from the target chronic disease in each dimension is obtained according to the difference between the physical data of each elderly suffering from the target chronic disease at all historical sampling moments in each dimension and the normal data change curve.
[0029] Preferably, in one embodiment of the present invention, the method for acquiring abnormal body factors includes: selecting any elderly person suffering from a target chronic disease as a target elderly person, and selecting any dimension as a target dimension.
[0030] The body data of the target elderly in the target dimension are fitted into a target body data curve using the least square method. It should be noted that a linear regression method can also be used to fit the target body data curve, which is not limited here.
[0031] Obtain the body abnormality factor according to the body abnormality factor calculation formula, which is as follows: In the formula, Indicates the physical abnormality factor of the target elderly in the target dimension; Indicates the number of body data of the target dimension; The target body data curve The slope of the position of the body data, where the slope passes through the first The derivative of the body data is obtained; The first one represents the normal data change curve of the target dimension The slope of the position of the standard data, where the slope passes through the normal data change curve The derivative of standard data is obtained; The target body data curve The data value of each body data; The first one represents the normal data change curve of the target dimension The data value of the standard data; represents an exponential function with a natural constant as base; Represents a symbolic function.
[0032] In the calculation formula of physical abnormality factor, the symbol function To reflect the target body data curve The curve of body data and normal data change The consistency of the change direction of the standard data, among which, The smaller it is, the weaker the consistency between the target body data curve and the normal data change curve. The larger the value, the more abnormal the target elderly's physical data in the target dimension is, and the larger the target elderly's physical factor in the target dimension is; and the overall deviation between the target elderly's physical data in the target dimension and the normal data change curve of the target dimension The larger it is, the more abnormal the physical data of the target elderly person in the target dimension is, that is, the larger the physical abnormality factor is.
[0033] Step S3: According to the change characteristics of the abnormal physical factors in each dimension of all elderly people suffering from the target chronic disease, the degree of dominance of the physical data in each dimension for the target chronic disease is obtained; according to the abnormal physical factors in each dimension of all elderly people suffering from the target chronic disease, all elderly people suffering from the target chronic disease are screened to obtain the target elderly patient group; according to the difference in physical data in each dimension between each elderly person and the target elderly patient group and the degree of dominance of each dimension, the disease risk index of each elderly person suffering from the target chronic disease is obtained.
[0034] In reality, physical data of different dimensions have different degrees of influence on different chronic diseases of the elderly. For example, sudden changes in blood pressure data of the elderly are the main cause of hypertension in the elderly. In order to analyze the influence of physical data of each dimension on the target chronic disease, the degree of dominance of each dimension on the target chronic disease is calculated. As can be seen from the above process, the larger the physical abnormality factor of a certain dimension, the more likely it is that the chronic disease of the elderly is caused by the physical data of this dimension. Therefore, in an embodiment of the present invention, the degree of dominance of physical data of each dimension on the target chronic disease is obtained according to the change characteristics of physical abnormality factors in each dimension of all elderly people suffering from the target chronic disease.
[0035] Preferably, in one embodiment of the present invention, the method for obtaining the disease dominance degree includes: obtaining the disease dominance degree according to a disease dominance degree calculation formula, and the disease dominance degree calculation formula is as follows: In the formula, Indicates the ordinal number of the target dimension; Indicates the degree of dominance of the physical data of the target dimension for the target chronic disease; indicates the number of older adults with the target chronic condition; Indicates the first Physical abnormality factors of the elderly in the target dimension; Indicates the first The average physical abnormality factor of all dimensions in the elderly; Represents the maximum value function.
[0036] In the calculation formula of disease predominance, will be less than the first The average physical abnormality factor of all elderly people in all dimensions is used to screen out the elderly people with the target chronic disease. Among them, the greater the abnormal prominence of the physical abnormality factor of all elderly people with the target chronic disease in the target dimension relative to the average physical abnormality factor, the more dominant the target dimension is in the target chronic disease; and the larger the mean value of the physical abnormality factor of all elderly people with the target chronic disease in the target dimension, the greater the overall abnormality of all elderly people with the target chronic disease in the target dimension, and at this time, the more dominant the target dimension is in the target chronic disease.
[0037] Since in reality not every elderly person with the target chronic disease has precursors or abnormalities in the early stage of the disease, the reference value of the physical data of these elderly people in the comparison is smaller at this time, so the physical data of the elderly people with the target chronic disease should be screened. Since the larger the physical abnormality factor of the elderly people with the target chronic disease in each dimension, the more representative the physical data of the elderly people are in the subsequent data comparison, so in the embodiment of the present invention, all the elderly people with the target chronic disease are screened according to the physical abnormality factor of all the elderly people with the target chronic disease in each dimension to obtain the target elderly patient group.
[0038] Preferably, in one embodiment of the present invention, the method for obtaining the target elderly patient group includes: averaging the square of the physical abnormality factor of each elderly person suffering from the target chronic disease in each dimension to obtain the data preference degree of each elderly person suffering from the target chronic disease. In one embodiment of the present invention, the data preference degree calculation formula is as follows: In the formula, Represents the data preference for each older adult with the target chronic condition; The number of dimensions representing the body data; Each elderly person with the target chronic disease in Dimensions of physical abnormalities.
[0039] In the data priority calculation formula, the greater the overall physical abnormality factor in all dimensions of each elderly person suffering from the target chronic disease, the greater the data priority of the elderly person suffering from the target chronic disease.
[0040] A preset number of elderly people with the highest data preference is selected as the target elderly patient group. In one embodiment of the present invention, the preset number is set to 20, that is, 20 elderly people with the highest data preference are obtained as the target elderly patient group.
[0041] The more similar the physical data changes of each elderly person are to those of the target elderly patient group, and the greater the dominance of the dimension in which the similar physical data resides for the target chronic disease, the greater the possibility that the elderly person suffers from the target chronic disease. In order to analyze the risk of each elderly person suffering from the target chronic disease, in an embodiment of the present invention, the disease risk index of each elderly person suffering from the target chronic disease is obtained based on the difference in physical data between each elderly person and the target elderly patient group in each dimension and the degree of disease dominance in each dimension.
[0042] Preferably, in one embodiment of the present invention, the method for obtaining the disease risk index of each elderly person suffering from a target chronic disease includes: obtaining the disease risk index according to a disease risk index calculation formula, and the disease risk index calculation formula is as follows: In the formula, Indicates the risk index of each elderly person suffering from the target chronic disease; represents the number of elderly people in the target elderly patient group; Indicates the number of dimensions; Represents the number of body data in each dimension, where the number of bodies in each dimension is the same; Indicates that every elderly person In the dimension The data value of each body data; Indicates the first The elderly in In the dimension The data value of each body data; Indicates The degree to which each dimension of physical data is dominant in the prevalence of the target chronic disease; Represents the normalization function.
[0043] In the disease risk index calculation formula, the elderly being monitored are taken as the elderly to be analyzed, and the difference between the physical data of the elderly to be analyzed in each dimension and the corresponding physical data of each elderly in the target elderly patient group in the same dimension is calculated. The smaller the difference, the higher the risk of disease. Each sampling moment in the dimension is similar to the physical data of each elderly person in the target elderly patient group. The ratio of the dominance of the dimension for the target chronic disease to the dominance of all dimensions for the target chronic disease As body data difference The weight of As the elderly to be analyzed and the target elderly patient group The elderly in The dimension The degree of difference in physical data between the individual physical data; the average of the degree of difference in physical data of the elderly to be analyzed and each elderly person in the target elderly patient group at each sampling moment in each dimension. The smaller the mean, the more similar the physical data of the elderly to be analyzed is to that of the elderly in the target elderly patient group, that is, the more likely they are to suffer from the target chronic disease.
[0044] At this point, the disease risk index of each elderly person suffering from the target chronic disease is obtained.
[0045] Step S4: Conduct a health assessment on each elderly person based on their risk index for each chronic disease.
[0046] According to the above process, the risk index of all chronic diseases for each elderly person can be obtained.
[0047] In one embodiment of the present invention, real-time physical data monitoring is performed on each elderly person, and the risk index of all elderly chronic diseases is calculated at a fixed time every day; when the risk index of any elderly chronic disease is greater than a preset first threshold, it is considered that the current elderly person has a greater risk of disease, and an early warning is immediately issued to relevant personnel. Among them, the preset first threshold is set to 0.65. It should be noted that in other embodiments of the present invention, the preset first threshold can be set by itself and is not limited here.
[0048] At this point, the health assessment of the elderly is completed.
[0049] An embodiment of the present invention provides a big data-based elderly health monitoring and assessment system, which includes a memory, a processor and a computer program, wherein the memory is used to store the corresponding computer program, and the processor is used to run the corresponding computer program. When the computer program runs in the processor, it can implement the method described in steps S1-S4.
[0050] In summary, the physical data of each elderly person in different dimensions at the current sampling moment and the historical sampling moments are obtained; the types of chronic diseases suffered by each elderly person are obtained; one chronic disease of the elderly is selected as the target chronic disease, and the normal data change curve of the elderly person in each dimension is obtained according to the fluctuation characteristics of the physical data of all elderly people who do not suffer from the target chronic disease at all historical sampling moments in each dimension; the physical abnormality factor of each elderly person with the target chronic disease in each dimension is obtained according to the difference between the physical data of each elderly person with the target chronic disease at all historical sampling moments and the normal data change curve; the degree of dominance of the physical data of each dimension for the target chronic disease is obtained according to the change characteristics of the physical abnormality factors of all elderly people with the target chronic disease in each dimension; all elderly people with the target chronic disease are screened according to the physical abnormality factors of all elderly people with the target chronic disease in each dimension to obtain the target elderly patient group; the disease risk index of each elderly person suffering from the target chronic disease is obtained according to the difference in physical data between each elderly person and the target elderly patient group in each dimension and the disease dominance of each dimension; and the health assessment of each elderly person is performed according to the disease risk index of each elderly person for each chronic disease.
[0051] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0052] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.
Claims
1. A method for monitoring and evaluating elderly health based on big data. It is characterized in that The method comprises: Obtain the physical data of each elderly person in different dimensions at the current sampling time and historical sampling time; obtain the types of chronic diseases suffered by each elderly person; Select any chronic disease of the elderly as the target chronic disease, and obtain the normal data change curve of the elderly in each dimension according to the fluctuation characteristics of the body data of all the elderly people who do not suffer from the target chronic disease at all historical sampling moments in each dimension; obtain the abnormal body factor of each elderly person suffering from the target chronic disease in each dimension according to the difference between the body data of each elderly person suffering from the target chronic disease at all historical sampling moments in each dimension and the normal data change curve; According to the change characteristics of the abnormal physical factors in each dimension of all elderly people suffering from the target chronic disease, the degree of dominance of the physical data in each dimension for the target chronic disease is obtained; according to the abnormal physical factors in each dimension of all elderly people suffering from the target chronic disease, all elderly people suffering from the target chronic disease are screened to obtain the target elderly patient group; according to the difference in physical data in each dimension between each elderly person and the target elderly patient group and the degree of dominance of each dimension, the disease risk index of each elderly person suffering from the target chronic disease is obtained; Conduct a health assessment for each elderly person based on their risk index for each chronic disease; The method for obtaining the abnormal body factor comprises: Choose any elderly person with the target chronic disease as the target elderly person, and choose any dimension as the target dimension; Fitting the body data of the target elderly in the target dimension into a target body data curve; The body abnormality factor is obtained according to the body abnormality factor calculation formula, and the body abnormality factor calculation formula is as follows: In the formula, Indicates the physical abnormality factor of the target elderly in the target dimension; Indicates the number of body data of the target dimension; The target body data curve The slope of the location of the body data; The first one represents the normal data change curve of the target dimension The slope of the location of the standard data; The target body data curve The data value of each body data; The first one represents the normal data change curve of the target dimension The data value of the standard data; represents an exponential function with a natural constant as base; represents a symbolic function; The method for obtaining the disease predominance degree includes: The disease dominance degree is obtained according to the disease dominance degree calculation formula, and the disease dominance degree calculation formula is as follows: In the formula, Indicates the ordinal number of the target dimension; Indicates the degree of dominance of the physical data of the target dimension for the target chronic disease; indicates the number of older adults with the target chronic condition; Indicates the first Physical abnormality factors of the elderly in the target dimension; Indicates the first The average physical abnormality factor of all dimensions in the elderly; represents the maximum value function; The method for obtaining the risk index of each elderly person suffering from a target chronic disease includes: The disease risk index is obtained according to the disease risk index calculation formula, and the disease risk index calculation formula is as follows: In the formula, Indicates the risk index of each elderly person suffering from the target chronic disease; represents the number of elderly people in the target elderly patient group; Indicates the number of dimensions; Represents the number of body data in each dimension, where the number of bodies in each dimension is the same; Indicates that every elderly person In the dimension The data value of each body data; Indicates the first The elderly in In the dimension The data value of each body data; Indicates The degree to which each dimension of physical data is dominant in the prevalence of the target chronic disease; represents the normalization function; The derivative of each data of the target body data curve and the normal data change curve is used as the slope of the position where each data of the target body data curve and the normal data change curve is located.
2. According to the big data-based elderly health monitoring and evaluation method of claim 1, It is characterized in that The method for obtaining the normal data change curve includes: The physical data of each dimension of all elderly people who do not suffer from the target chronic disease at each historical sampling moment are averaged to obtain the standard data of each dimension at each historical sampling moment; The standard data of each dimension at all historical sampling moments are fitted into the normal data change curve of each dimension for the elderly.
3. According to the big data-based elderly health monitoring and evaluation method of claim 1, It is characterized in that The method for obtaining the target elderly patient group comprises: According to the physical abnormal factors in all dimensions of each elderly person suffering from the target chronic disease, obtaining the data preference degree of each elderly person suffering from the target chronic disease; A preset number of elderly people with the highest data preference are selected as the target elderly patient group.
4. According to the big data-based elderly health monitoring and evaluation method of claim 3, It is characterized in that The method for obtaining the data preference degree includes: The squares of the physical abnormality factors in each dimension of each elderly person suffering from the target chronic disease are averaged to obtain the data preference degree of each elderly person suffering from the target chronic disease.
5. According to the big data-based elderly health monitoring and evaluation method of claim 1, It is characterized in that Conduct a health assessment for each elderly person based on their risk index for each chronic disease, including: Calculate the risk index of each elderly person for each chronic disease; When the risk index of any chronic disease in the elderly is greater than a preset first threshold, it is considered that the elderly are currently at greater risk of developing the disease.
6. A big data-based elderly health monitoring and assessment system, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.
Citation Information
Cited By
Multi-mode AI fusion senile non-inductive assessment method and system and electronic equipment
CN121148701A
