Data analysis method and system for old people with multiple diseases

Abstract

The invention provides a data analysis method and system for old people with multiple diseases, and belongs to the field of data analysis. The problem of complex data analysis is solved; the method specifically comprises the following steps: S1, acquiring age and disease information of old people to obtain a disease table; acquiring life information of the elderly; s2, obtaining confidence coefficients among the diseases according to the disease information, and calculating to obtain influence values of the diseases; sorting the diseases according to the influence values, and obtaining a case matrix according to a disease table of the old; calculating to obtain a disease proportion and a disease value of a single disease; s3, obtaining an association model according to the age and the disease value of the elderly, classifying the disease value, and obtaining an association relationship between the life information and the disease value of the elderly in combination with the life information of the elderly; s4, the illness condition of the old people is predicted, and diseases are prevented and treated; by analyzing the data, the incidence relation between the living habits of the old people and the diseases is obtained, and suggestions are provided for disease prevention and treatment of the old people.

Description

Technical Field

[0001] A data analysis method and system for the elderly with multiple co-existing diseases of the present invention relate to the field of data analysis. Background Art

[0002] The existing data analysis methods and systems for the elderly with multiple co-existing diseases have the following deficiencies:

[0003] Problem of unrepresentative data analysis: Most of the existing data analysis on the elderly with multiple co-existing diseases analyzes the elderly through anthropometrics, which is unrepresentative and cannot reflect specific differences;

[0004] Single analysis process: The existing data analysis on the elderly with multiple co-existing diseases mainly analyzes the population characteristics of the interviewees and the correlation between diseases, and the analysis results are mostly the occurrence probability of a certain type of disease in the population;

[0005] Lack of prevention and treatment information: After processing the data, the existing analysis only conducts simple analysis and cannot predict and prevent diseases. Summary of the Invention

[0006] Aiming at the deficiencies of the existing technology, the purpose of the present invention is to provide a data analysis method and system for the elderly with multiple co-existing diseases, aiming to solve the problem of complex data analysis.

[0007] To achieve the above purpose, the present invention is realized through the following technical solutions: A data analysis method for the elderly with multiple co-existing diseases includes:

[0008] Step S1: Obtain the age and disease information of the elderly to obtain a disease table; obtain the diet information, work and rest information, and entertainment information of the elderly to obtain life information;

[0009] Step S2: Obtain the disease table of the elderly, process the disease information in the disease table to obtain the confidence level between diseases, calculate the influence value of each disease; sort the diseases according to the influence value, and matrix the disease table of the elderly according to the sorted disease order to obtain a case matrix; calculate the rows of the case matrix to obtain the prevalence proportion of a single disease, and calculate the columns of the case matrix to obtain the disease value of the elderly;

[0010] Step S3: According to the age and disease value of the elderly, obtain an association model between the age and the disease value. According to the association model, classify the disease value, and combine the life information of the elderly to obtain the association relationship between the diet information, work and rest information, entertainment information of the elderly and the disease value;

[0011] Step S4: Predict the disease condition of the elderly according to the prevalence proportion of a single disease and the confidence level between diseases, and prevent and treat the diseases in combination with the diet information, work and rest information, and entertainment information of the elderly.

[0012] Further, the specific steps of step S1 are as follows:

[0013] Step S11: Conduct a random sampling survey on the elderly to obtain the age and disease information of t elderly people, save the age and disease information, and obtain the disease table of t elderly people;

[0014] Step S12: Conduct a questionnaire survey to obtain the daily diet of the elderly to obtain the diet information of the elderly, obtain the wake-up time and rest time of the elderly to obtain the work and rest information of the elderly, and obtain the choice of the elderly for personal entertainment or group activities to obtain the entertainment information of the elderly; The diet information, work and rest information, and entertainment information constitute the living information.

[0015] Further, the specific steps of step S2 are as follows:

[0016] Step S21: Obtain the disease table of the elderly, process the disease information in the disease table through the apriori algorithm, and obtain the confidence level p between diseases mn ; p mn represents the confidence level between the m-th disease and the n-th disease in the disease table. If p mn ≥50%, it is determined that there is an association between the m-th disease and the n-th disease, and the number of associations g between the m-th disease and other diseases is counted m ; According to the number of associations g m and the confidence level p mn , the influence value of the disease is calculated and denoted as yx m ;

[0017] The influence value yx m The specific process is as follows:

[0018]

[0019] Where: s represents the number of disease types, 1 ≤ m ≤ s, 1 ≤ n ≤ s;

[0020] Step S22: Sort the diseases in ascending order according to the influence value yx m , and denote the s diseases as b1 to bs according to the sorting order; Denote the t elderly people as L1 to Lt respectively, and matrixize the disease table of the elderly according to the sorted disease order to obtain a case matrix A with s rows and c columns; The elements in the case matrix A are represented by A(bi, Lj).

[0021]

[0022] Where: A(bi, Lj) = 1 means that the j-th elderly person has the i-th disease, where c = t, 1 ≤ i ≤ s, 1 ≤ j ≤ t;

[0023] Step S23: Define the function F1(x) = x i -x i-1 , F2(x) = (x i-1 +x i-2 ) - x i . For any number i, F1(x) > 0 and F2(x) > 0, obtaining the weight x; Calculate in combination with the diseases suffered by each elderly person and the impact of the diseases to obtain the disease value hj of the elderly person;

[0024] The specific calculation process of the disease value hj is as follows:

[0025]

[0026] The value range of x is (1, 1.6];

[0027] Step S24: Count the number of cases of a single disease and calculate the prevalence ratio hi of the single disease;

[0028] The specific calculation process of the prevalence ratio hi of a single disease is as follows:

[0029]

[0030] Where: t is the number of elderly people.

[0031] Furthermore, the specific steps of the said Step S3 are as follows:

[0032] Step S31: Obtain the age LNj and disease value hj of the elderly person, obtaining t data pairs (LNj, hj). According to the data pairs, construct a correlation model; Classify the elderly people according to the correlation model to obtain the high-risk elderly person set GW and the low-risk elderly person set DW;

[0033] Step S32: Obtain the living information of the elderly people, compare the living information of the elderly people in the high-risk elderly person set with the living information of the elderly people in the low-risk elderly person set, and judge the impact of the living information of the elderly people on the disease;

[0034] Step S33: According to the impact of the living information of the elderly people on the disease, combined with the living information of the elderly people in the low-risk elderly person set, obtain the eating habits, work and rest habits, and entertainment habits with a low probability of disease occurrence; Enter Step S4.

[0035] Furthermore, the specific steps of the said Step S31 are as follows:

[0036] Step S311: Obtain the data pairs (LNj, hj), and obtain the correlation model parameters k and parameter v by least squares;

[0037] Step S312: Construct a correlation model according to the parameters k and parameter v; The specific correlation model is as follows:

[0038] h = k × LN + v;

[0039] Where: h refers to the disease value, LN refers to age, and the association model represents the correlation between the disease value and age;

[0040] Step S313: Obtain the disease values corresponding to each age according to the association model. Combine the age LNj and disease value hj of the elderly, compare the disease value of the elderly with the disease value corresponding to this age, and classify the elderly;

[0041] Count the elderly with hj > h, obtain the disease table and living information of the corresponding elderly, and form a high-risk elderly set GW,

[0042] Count the elderly with hj ≤ h, obtain the disease table and living information of the corresponding elderly, and form a low-risk elderly set DW.

[0043] Furthermore, the specific steps of step S32 are as follows:

[0044] Step S321: Obtain the living information of the elderly to get the diet information, work and rest information, and entertainment information of the elderly; Quantify the diet information, work and rest information, and entertainment information to obtain the diet value ys, work and rest value zx, and entertainment value yl of the elderly;

[0045] Step S322: Obtain the high-risk elderly set GW, and get the number of elderly gt in the high-risk elderly set GW; Obtain the diet value ys, work and rest value zx, and entertainment value yl corresponding to the elderly in the high-risk elderly set GW; Calculate the average diet value Gys of the high-risk elderly set according to the diet value ys: Calculate the average work and rest value Gzx of the high-risk elderly set according to the work and rest value zx: Calculate the average entertainment value Gyl of the high-risk elderly set according to the entertainment value yl; The specific calculation process is as follows:

[0046]

[0047] Where: ys(GW) refers to the diet value ys corresponding to the elderly in the set GW; zx(GW) refers to the work and rest value zx corresponding to the elderly in the set GW; yl(GW) refers to the entertainment value yl corresponding to the elderly in the set GW;

[0048] Step S323: Obtain the low-risk elderly set DW, and get the number of elderly dt in the low-risk elderly set DW; Obtain the diet value ys, work and rest value zx, and entertainment value yl corresponding to the elderly in the low-risk elderly set DW; Calculate the average diet value Dys of the low-risk elderly set according to the diet value ys: Calculate the average work and rest value Dzx of the low-risk elderly set according to the work and rest value zx: Calculate the average entertainment value Dyl of the low-risk elderly set according to the entertainment value yl; The specific calculation process is as follows:

[0049]

[0050] Among them: ys(DW) refers to the dietary value ys corresponding to the elderly in the set DW; ys(DW) refers to the daily routine value zx corresponding to the elderly in the set DW; yl(DW) refers to the entertainment value yl corresponding to the elderly in the set DW.

[0051] Furthermore, the step S32 further includes:

[0052] Step S324: Obtain the comparative dietary value Bys according to the average dietary value Gys of the high-risk elderly set and the average dietary value Dys of the low-risk elderly set:

[0053]

[0054] Obtain the comparative daily routine value Bzx according to the average daily routine value Gzx of the high-risk elderly set and the average daily routine value Dzx of the low-risk elderly set:

[0055]

[0056] Obtain the comparative entertainment value Byl according to the average entertainment value Gyl of the high-risk elderly set and the average entertainment value Dyl of the low-risk elderly set:

[0057]

[0058] Step S325: Make a judgment according to the comparative dietary value Bys, the comparative daily routine value Bzx, and the comparative entertainment value Byl. If Bys < 0.5, it is considered that diet has no impact on the disease; if Bys >= 0.5, it is considered that diet has an impact on the disease. If Bzx < 0.5, it is considered that the daily routine has no impact on the disease; if Bys >= 0.5, it is considered that the daily routine has an impact on the disease. If Byl < 0.5, it is considered that entertainment has no impact on the disease; if Byl >= 0.5, it is considered that entertainment has an impact on the disease.

[0059] Furthermore, the specific steps of the step S321 are as follows:

[0060] Step S3211: Judge the diet of the elderly according to the diet information of the elderly and the recommended daily food intake for the elderly aged 65, and classify it into three levels, namely: first level, second level, and third level; obtain the corresponding dietary value ys according to the level;

[0061] Step S3212: Quantify the daily routine information of the elderly. According to the recommended sleep duration, divide the daily routine of the elderly into three categories: less than the recommended duration, meeting the recommended duration, and exceeding the recommended duration; count the sleep duration to obtain the daily routine value zx;

[0062] Step S3213: Classify the elderly's entertainment information into personal entertainment preferences and group activity preferences, analyze the personal entertainment preferences and group activity preferences to obtain the entertainment value yl.

[0063] Further, the subsequent steps of step S4 are as follows:

[0064] Step S41: Obtain the prevalence rate of a single disease and the confidence level between diseases, combine the elderly's disease information to calculate the probability of the elderly having other diseases, and obtain the probability value gli;

[0065] The specific process of calculating the probability value gli is as follows:

[0066]

[0067] p mn represents the confidence level between diseases, n = i; A(bm, Lj) represents the value in the m-th row and j-th column of the case matrix;

[0068] If gli > 50%, it is determined that the probability of the elderly having the i-th disease is greater than 50%; targeted prevention and control of this disease are required;

[0069] Step S42: Intervene in the elderly's living habits, formulate eating habits, work and rest habits, and entertainment habits that can reduce the probability of disease occurrence, and prevent and control diseases.

[0070] A data analysis system for the elderly with multiple co-existing diseases includes:

[0071] Data acquisition module: used to acquire the age and disease information of the elderly to obtain a disease table; acquire the eating information, work and rest information, and entertainment information of the elderly to obtain living information;

[0072] Data processing module: used to acquire the disease table of the elderly, process the disease information in the disease table to obtain the confidence level between diseases, calculate the influence value of each disease; sort the diseases according to the influence value, matrixize the disease table of the elderly according to the sorted disease order to obtain a case matrix; calculate the rows of the case matrix to obtain the prevalence rate of a single disease, and calculate the columns of the case matrix to obtain the disease value of the elderly;

[0073] Data analysis module: used to obtain the association model between age and disease value according to the age and disease value of the elderly, classify the disease value according to the association model, and combine the living information of the elderly to obtain the association relationship between the eating information, work and rest information, entertainment information of the elderly and the disease value;

[0074] Data prediction module: used to predict the disease situation of the elderly based on the prevalence rate of a single disease and the confidence level between diseases, and prevent and treat diseases by combining the diet information, work and rest information, and entertainment information of the elderly.

[0075] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0076] Refined data analysis: The present invention ensures the randomness of data through random sampling, and obtains the living information of the elderly through questionnaire surveys of the elderly or their families; the data is more specific than human characteristic data.

[0077] Specific analysis content: By analyzing the correlation between diseases, sort the influence values of diseases, and conduct specific analysis on the elderly based on the influence values of diseases; at the same time, by analyzing the living information of the elderly, judge the influence of living information on diseases;

[0078] Optimized analysis results: Predict the disease situation of the elderly through the correlation between diseases, prevent and treat in advance, and provide living habits that can reduce the probability of disease occurrence based on the analysis results of the living information of the elderly to prevent diseases. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] By reading the following detailed description of the non-limiting embodiments with reference to the accompanying drawings, other features, objects, and advantages of the present invention will become more apparent:

[0080] Figure 1 It is a schematic diagram of the method of the present invention;

[0081] Figure 2 It is a schematic diagram of the main data processing of the present invention;

[0082] Figure 3 It is a schematic diagram of the system of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0083] To make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0084] Embodiment 1

[0085] Please refer to Figure 1 , a data analysis method for the elderly with multiple co-existing diseases includes:

[0086] It should be noted that the diseases in the coexistence of multiple diseases mainly refer to 14 common chronic diseases, namely hypertension, dyslipidemia (hyperlipidemia or hypolipidemia), diabetes or elevated blood sugar (including impaired glucose tolerance and elevated fasting blood sugar), malignant tumors (excluding mild skin cancer), chronic pulmonary diseases (including chronic bronchitis or emphysema, cor pulmonale, but excluding tumors or cancers), liver diseases (except fatty liver, tumors or cancers), heart diseases (including myocardial infarction, coronary heart disease, angina pectoris, congestive heart failure and other heart diseases), stroke, kidney diseases (excluding tumors or cancers), gastric diseases (excluding tumors or cancers), emotional and mental problems, memory-related diseases (including Alzheimer's disease, brain atrophy, Parkinson's disease), arthritis or rheumatism, asthma. In the present invention, these common chronic diseases are represented by "diseases", and s represents the number of disease types;

[0087] It should be noted that the elderly in the coexistence of multiple diseases refer to those aged over 65;

[0088] Step S1: Obtain the age and disease information of the elderly to get a disease table; obtain the diet information, work and rest information, and entertainment information of the elderly to get life information;

[0089] Step S11: Conduct a random sampling survey on the elderly (the number of surveyed people is not less than 10,000), obtain the age and disease information of t elderly people, save the age and disease information, and get the disease table of t elderly people.

[0090] It should be noted that the disease information refers to the specific diseases suffered by the elderly.

[0091] Step S12: Conduct a questionnaire survey, obtain the daily diet of the elderly to get the diet information of the elderly, obtain the wake-up time and rest time of the elderly to get the work and rest information of the elderly, obtain the choice of personal entertainment or group activities of the elderly to get the entertainment information of the elderly; the diet information, work and rest information, and entertainment information constitute the life information.

[0092] Step S2: Process the disease table of the elderly, obtain the confidence level between diseases, calculate and obtain the influence value of each disease; sort the diseases according to the influence value, matrixize the disease table of the elderly according to the sorted disease order to get a case matrix; calculate the rows of the case matrix to obtain the prevalence proportion of a single disease, and calculate the columns of the case matrix to obtain the disease value of the elderly;

[0093] The specific steps are as follows:

[0094] Step S21: Process the disease table of the elderly through the apriori algorithm to obtain the confidence level p between diseases mn ; p mn represents the confidence level between the m-th disease and the n-th disease in the disease table, pmn If it is ≥ 50%, it is determined that there is an association between the m-th disease and the n-th disease, and the number of associations g between the m-th disease and other diseases is counted. m ; According to the number of associations g m and the confidence level p mn , the influence value of the disease is calculated and denoted as yx. m ;

[0095] The influence value yx m The specific process is as follows:

[0096]

[0097] Where: s represents the number of disease types, 1 ≤ m ≤ s, 1 ≤ n ≤ s.

[0098] Step S22: According to the influence value yx m sort the diseases in ascending order. According to the sorting order, the s diseases are respectively denoted as b1 to bs; the t elderly people are respectively denoted as L1 to Lt. Matrixize the disease table of the elderly through the sorted disease order to obtain a case matrix A with s rows and c columns; the elements in the case matrix A are represented by A(bi, Lj).

[0099]

[0100] It should be noted that: Matrixization means representing data through a matrix.

[0101] It should be noted that: A(bi, Lj) = 1 means that the j-th elderly person has the i-th disease, where c = t, 1 ≤ i ≤ s, 1 ≤ j ≤ t.

[0102] Please refer to Figure 2 ; Step S23: Obtain the weight x; Combine the diseases suffered by each elderly person with the influence of the disease to calculate the disease value hj of the elderly person.

[0103] The specific calculation process of the disease value hj is as follows:

[0104]

[0105] Where: for any i, there is x i > x i-1 , and at the same time x i < x i-1 + x i-2 , and the value range of x is (1, 1.6].

[0106] For example, for the first elderly person, his disease value is calculated as follows:

[0107] h1 = A(b1, L1) × x1 +A(b2, L1) × x 2 + …… + A(bs, L1) × x s ;

[0108] For the second elderly person, the disease value is calculated as follows:

[0109] h2 = A(b1, L2) × x 1 +A(b2, L2) × x 2 + …… + A(bs, L2) × x s ;

[0110] For the t-th elderly person, the disease value is calculated as follows:

[0111] ht = A(b1, Lt) × x 1 +A(b2, Lt) × x 2 + …… + A(bs, Lt) × x s ;

[0112] Step S24: Count the number of cases of a single disease and calculate the disease proportion hi of the single disease;

[0113] The specific calculation process of the disease proportion hi of a single disease is as follows:

[0114]

[0115] Step S3: Based on the age and the disease value, obtain the association model between the age and the disease value. According to the association model, classify the disease values, and combine with the living information of the elderly to obtain the association relationship between the diet information, work and rest information, entertainment information of the elderly and the disease value;

[0116] Step S31: Obtain the age LNj and the disease value hj of the elderly to get t data pairs (LNj, hj). According to the data pairs, construct an association model; classify the elderly according to the association model;

[0117] The specific construction process is as follows:

[0118] Step S311: Obtain the data pairs (LNj, hj), and obtain the association model parameters k and v by least squares;

[0119] The specific obtaining process is as follows:

[0120] Step S3111: Calculate the parameter k according to the age LNj and the disease value hj of the elderly;

[0121] The specific calculation process is as follows:

[0122]

[0123] Step S3112: Calculate and obtain parameter v based on the age Lj of the elderly person, the disease value hj, and in combination with parameter k;

[0124] The specific calculation process is as follows:

[0125]

[0126] Step S312: Construct an association model based on parameter k and parameter v; The association model is specifically as follows:

[0127] h = k × LN + v;

[0128] Where: h refers to the disease value, LN refers to the age, and the association model represents the correlation between the disease value and the age;

[0129] Step S313: Obtain the disease values corresponding to each age according to the association model, and in combination with the age LNj and disease value hj of the elderly person, compare the disease value of the elderly person with the disease value corresponding to this age, and classify the elderly person;

[0130] Statistically analyze the elderly with hj > h, obtain the disease table and living information of the corresponding elderly, and form a high-risk elderly set GW,

[0131] Statistically analyze the elderly with hj ≤ h, obtain the disease table and living information of the corresponding elderly, and form a low-risk elderly set DW.

[0132] Step S32: Obtain the living information of the elderly, compare the living information of the elderly in the high-risk elderly set GW with the living information of the elderly in the low-risk elderly set DW, and judge the impact of the living information of the elderly on the disease;

[0133] Step S321: Obtain the living information of the elderly to obtain the diet information, work and rest information, and entertainment information of the elderly; Quantify the diet information, work and rest information, and entertainment information to obtain the diet value ys, work and rest value zx, and entertainment value yl of the elderly;

[0134] The specific quantification process is as follows:

[0135] Step S3211: Judge the diet of the elderly according to the diet information of the elderly and the daily food recommended intake for 65-year-old elderly people, and classify it into three levels, namely: level one (meeting the daily food recommended intake for 65-year-old elderly people), level two (partially meeting the daily food recommended intake for 65-year-old elderly people), and level three (not meeting the daily food recommended intake for 65-year-old elderly people); Obtain the corresponding diet value ys according to the level; If it is level one, then ys = 1;

[0136] It should be noted that "partially meeting" means meeting the recommended intake of some foods. For example, an elderly person consumes 220 grams of grains (the recommended intake is 200 - 250 grams) and 30 grams of eggs (the recommended intake is 40 - 50 grams). In this case, the grain intake meets the requirement while the egg intake does not. Then the diet level of this elderly person is level two.

[0137] Step S3212: Quantify the rest information of the elderly. According to the recommended sleep duration, divide the rest of the elderly into three categories: less than the recommended duration, meeting the recommended duration, and exceeding the recommended duration; obtain the rest value zx.

[0138] It should be noted that if it is less than the recommended duration, then zx = -1; if it meets the recommended duration, then zx = 0; if it is higher than the recommended duration, then zx = 1.

[0139] Step S3213: Quantify the entertainment information of the elderly, which is divided into two categories: liking personal entertainment or group activities, and obtain the entertainment value yl.

[0140] It should be noted that if one likes personal entertainment, then yl = -1; if one likes group activities, then yl = 1.

[0141] Step S322: Obtain the set GW of high-risk elderly people and the number gt of elderly people in the set GW of high-risk elderly people; obtain the diet value ys, rest value zx, and entertainment value yl corresponding to the elderly people in the set GW of high-risk elderly people.

[0142] Calculate the average diet value Gys of the set of high-risk elderly people according to the diet value ys; the specific calculation process is as follows:

[0143]

[0144] Among them: ys(GW) refers to the diet value ys corresponding to the elderly people in the set GW.

[0145] Calculate the average rest value Gzx of the set of high-risk elderly people according to the rest value zx; the specific calculation process is as follows:

[0146]

[0147] Among them: zx(GW) refers to the rest value zx corresponding to the elderly people in the set GW.

[0148] Calculate the average entertainment value Gyl of the set of high-risk elderly people according to the entertainment value yl; the specific calculation process is as follows:

[0149]

[0150] Among them: yl(GW) refers to the entertainment value yl corresponding to the elderly people in the set GW.

[0151] Step S323: Obtain the set DW of low-risk elderly people, and get the number dt of elderly people in the set DW of low-risk elderly people; obtain the diet value ys, work and rest value zx, and entertainment value yl corresponding to the elderly people in the set DW of low-risk elderly people.

[0152] Calculate the average diet value Dys of the set of low-risk elderly people according to the diet value ys; the specific calculation process is as follows:

[0153]

[0154] Among them: ys(DW) refers to the diet value ys corresponding to the elderly people in the set DW.

[0155] Calculate the average work and rest value Dzx of the set of low-risk elderly people according to the work and rest value zx; the specific calculation process is as follows:

[0156]

[0157] Among them: ys(DW) refers to the work and rest value zx corresponding to the elderly people in the set DW.

[0158] Calculate the average entertainment value Dyl of the set of low-risk elderly people according to the entertainment value yl; the specific calculation process is as follows:

[0159]

[0160] Among them: yl(DW) refers to the entertainment value yl corresponding to the elderly people in the set DW.

[0161] Step S324: Obtain the comparative diet value Bys based on the average diet value Gys of the set of high-risk elderly people and the average diet value Dys of the set of low-risk elderly people.

[0162] The specific calculation process of the comparative diet value Bys is as follows:

[0163]

[0164] Obtain the comparative work and rest value Bzx based on the average work and rest value Gzx of the set of high-risk elderly people and the average work and rest value Dzx of the set of low-risk elderly people.

[0165] The specific calculation process of the comparative work and rest value Bzx is as follows:

[0166]

[0167] Obtain the comparative entertainment value Byl based on the average entertainment value Gyl of the set of high-risk elderly people and the average entertainment value Dyl of the set of low-risk elderly people.

[0168] The specific calculation process of the comparative entertainment value Byl is as follows:

[0169]

[0170] Step S325: Make a judgment based on the comparison diet value Bys, the comparison work and rest value Bzx, and the comparison entertainment value Byl. If Bys < 0.5, it is considered that diet has no impact on the disease; if Bys >= 0.5, it is considered that diet has an impact on the disease. If Bzx < 0.5, it is considered that work and rest have no impact on the disease; if Bys >= 0.5, it is considered that work and rest have an impact on the disease. If Byl < 0.5, it is considered that entertainment has no impact on the disease; if Byl >= 0.5, it is considered that entertainment has an impact on the disease.

[0171] Step S33: If diet has an impact on the disease, obtain the eating habits of the corresponding level according to Dys as the eating habits that can reduce the probability of the disease occurrence. If work and rest have an impact on the disease, obtain the similar work and rest category according to Dzx as the work and rest habits that can reduce the probability of the disease occurrence. If entertainment has an impact on the disease, obtain the corresponding entertainment habits according to Dyl as the entertainment habits that can reduce the probability of the disease occurrence. Then enter Step S4.

[0172] Step S4: Predict the disease situation of the elderly according to the prevalence rate of a single disease and the confidence level between diseases, and prevent and treat the disease by combining the diet information, work and rest information, and entertainment information of the elderly.

[0173] Step S41: Obtain the prevalence rate of a single disease and the confidence level between diseases, and calculate the probability of the elderly suffering from other diseases by combining the disease information of the elderly to obtain the probability value gli.

[0174] The specific calculation process of the probability value gli is as follows:

[0175]

[0176] It should be noted that: p mn represents the confidence level between diseases. In the above formula, n = i; A(bm, Lj) represents the value in the m-th row and j-th column of the case matrix.

[0177] If gli > 50%, it is judged that the probability of the elderly suffering from the i-th disease is high, and targeted prevention and control of this disease are required.

[0178] Step S42: Intervene in the living habits of the elderly, formulate eating habits, work and rest habits, and entertainment habits that can reduce the probability of the disease occurrence, and prevent and treat the disease.

[0179] Embodiment 2

[0180] Please refer to Figure 3, A data analysis system for the elderly with multiple co-existing diseases includes: a data acquisition module, a data processing module, a data analysis module, a data prediction module, and a database; the data acquisition module, the data processing module, the data analysis module, and the data prediction module are respectively connected to the database.

[0181] The data acquisition module: is used to obtain the age and disease information of the elderly to obtain a disease table; obtain the diet information, work and rest information, and entertainment information of the elderly to obtain life information;

[0182] The data processing module: is used to obtain the disease table of the elderly, process the disease information in the disease table to obtain the confidence level between diseases, calculate the influence value of each disease; sort the diseases according to the influence value, and matrixize the disease table of the elderly according to the sorted disease order to obtain a case matrix; calculate the rows of the case matrix to obtain the prevalence ratio of a single disease, and calculate the columns of the case matrix to obtain the disease value of the elderly;

[0183] The data analysis module: is used to obtain the association model between age and disease value according to the age and disease value of the elderly, classify the disease value according to the association model, and combine the life information of the elderly to obtain the association relationship between the diet information, work and rest information, entertainment information of the elderly and the disease value;

[0184] The data prediction module: is used to predict the disease situation of the elderly according to the prevalence ratio of a single disease and the confidence level between diseases, and prevent and treat diseases in combination with the diet information, work and rest information, and entertainment information of the elderly;

[0185] The above formulas are all dimensionless and take their numerical values for calculation. The formula is obtained by collecting a large amount of data for software simulation to get a formula closest to the real situation. The preset parameters in the formula are set by those skilled in the art according to the actual situation. For example, if there are weight coefficients and proportionality coefficients, the values set are for quantifying each parameter to obtain a specific value, which is convenient for subsequent comparison. Regarding the magnitudes of the weight coefficients and proportionality coefficients, as long as they do not affect the proportional relationship between the parameters and the quantified values.

[0186] Finally, it should be noted that the above-described embodiments are only specific embodiments of the present invention, used to illustrate the technical solutions of the present invention, rather than limiting it. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that any person skilled in the technical field of the present invention can still modify the technical solutions described in the foregoing embodiments, or can easily think of changes, or perform equivalent replacements on some of the technical features; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims described herein.

Claims

1. A data analysis method for the elderly with multiple co-existing diseases, characterized in that, The analysis method includes: Step S1: Obtain the age and disease information of the elderly to get a disease table; obtain the diet information, work and rest information, and entertainment information of the elderly to get life information; Step S2: Obtain the disease table of the elderly, process the disease information in the disease table to obtain the confidence levels between diseases, calculate the influence values of each disease; sort the diseases according to the influence values, and matrixize the disease table of the elderly according to the sorted disease order to obtain a case matrix; calculate the rows of the case matrix to obtain the prevalence ratio of a single disease, and calculate the columns of the case matrix to obtain the disease value of the elderly; Step S3: According to the age and disease value of the elderly, obtain an association model between age and disease value, classify the disease values according to the association model, and combine the life information of the elderly to obtain the association relationship between the diet information, work and rest information, entertainment information of the elderly and the disease value; Step S4: Predict the disease situation of the elderly according to the prevalence ratio of a single disease and the confidence levels between diseases, and prevent and treat diseases by combining the diet information, work and rest information, and entertainment information of the elderly.

2. The data analysis method for the elderly with multiple co-existing diseases according to claim 1, characterized in that The specific steps of step S1 are as follows: Step S11: Conduct a random sampling survey on the elderly, obtain the age and disease information of t elderly people, save the age and disease information, and obtain the disease table of t elderly people; Step S12: Conduct a questionnaire survey to obtain the daily diet of the elderly to get the diet information of the elderly, obtain the wake-up time and rest time of the elderly to get the work and rest information of the elderly, obtain the choice of personal entertainment or group activities of the elderly to get the entertainment information of the elderly; the diet information, work and rest information, and entertainment information constitute the life information.

3. A data analysis method for the elderly with multiple co-existing diseases according to claim 1, characterized in that, The specific steps of step S2 are as follows: Step S21: Obtain the disease list of the elderly, and process the disease information in the disease list through the Apriori algorithm to obtain the confidence p between diseases mn ; p mn represents the confidence between the m-th disease and the n-th disease in the disease list If p mn ≥ 50%, it is determined that there is an association between the m-th disease and the n-th disease, and the number of associations g between the m-th disease and other diseases is counted m ; According to the number of associations g m and the confidence level p mn , the influence value of the disease is calculated and denoted as yx m : Where: s represents the number of disease types, 1 ≤ m ≤ s, 1 ≤ n ≤ s; Step S22: According to the influence value yx m Sort the diseases in ascending order. Denote the s diseases as b1 to bs respectively according to the sorting order; Denote the t elderly people as L1 to Lt respectively. Matrixize the disease tables of the elderly according to the sorted disease order to obtain a case matrix A with s rows and c columns. The elements in the case matrix A are represented by A(bi, Lj); Where: A(bi, Lj) = 1 means that the jth elderly person has the ith disease, where c = t, 1 ≤ i ≤ s, 1 ≤ j ≤ t; Step S23: Define the function F1(x) = x i -x i-1 , F2(x) = (x i-1 +x i-2 )-x i , for any number i, F1(x) > 0 and F2(x) > 0 always hold, and the weight x is obtained; calculate in combination with the diseases suffered by each elderly person and the impacts of the diseases to obtain the morbidity value hj of the elderly person: Step S24: Count the number of cases of a single disease and calculate the prevalence ratio hi of a single disease; The specific calculation process of the prevalence ratio hi of a single disease is as follows: Where: t is the number of elderly people.

4. A data analysis method for the elderly with multiple coexisting diseases according to claim 1, characterized in that, The specific steps of step S3 are as follows: Step S31: Obtain the age LNj and disease value hj of the elderly to get t data pairs (LNj, hj), and construct an association model according to the data pairs; classify the elderly according to the association model to obtain a high-risk elderly set GW and a low-risk elderly set DW; Step S32: Obtain the life information of the elderly, compare the life information of the elderly in the high-risk elderly set with the life information of the elderly in the low-risk elderly set, and judge the influence of the life information of the elderly on diseases; Step S33: According to the influence of the life information of the elderly on diseases, combine the life information of the elderly in the low-risk elderly set to obtain eating habits, work and rest habits, and entertainment habits with a low probability of disease occurrence; Proceed to step S4.

5. The data analysis method and system for the elderly with multiple co-existing diseases according to claim 4, characterized in that, The specific steps of step S31 are as follows: Step S311: Obtain the data pair (LNj, hj), and obtain the association model parameters k and parameter v by least squares method; Step S312: Construct an association model based on parameter k and parameter v. The specific association model is as follows: h = k × LN + v; where: h refers to the disease value, LN refers to age, and the association model represents the correlation between the disease value and age; Step S313: Obtain the disease values corresponding to each age according to the association model. Combine the age LNj and disease value hj of the elderly, compare the disease value of the elderly with the disease value corresponding to this age, and classify the elderly; Statistically analyze the disease table and living information of the elderly with hj > h to form a high-risk elderly set GW, Statistically analyze the disease table and living information of the elderly with hj ≤ h to form a low-risk elderly set DW.

6. A data analysis method for the elderly with multiple co-existing diseases according to claim 4, characterized in that, The specific steps of the said Step S32 are as follows: Step S321: Obtain the living information of the elderly to get the diet information, work and rest information, and entertainment information of the elderly. Quantify the diet information, work and rest information, and entertainment information to obtain the diet value ys, work and rest value zx, and entertainment value yl of the elderly; Step S322: Obtain the high-risk elderly set GW and get the number of elderly gt in the high-risk elderly set GW. Obtain the diet value ys, work and rest value zx, and entertainment value yl corresponding to the elderly in the high-risk elderly set GW. Calculate the average diet value Gys of the high-risk elderly set according to the diet value ys: Calculate the average work and rest value Gzx of the high-risk elderly set according to the work and rest value zx: Calculate the average entertainment value Gyl of the high-risk elderly set according to the entertainment value yl. The specific calculation process is as follows: where: ys(GW) refers to the diet value ys corresponding to the elderly in the set GW; zx(GW) refers to the work and rest value zx corresponding to the elderly in the set GW; yl(GW) refers to the entertainment value yl corresponding to the elderly in the set GW; Step S323: Obtain the low-risk elderly set DW and get the number of elderly dt in the low-risk elderly set DW. Obtain the diet value ys, work and rest value zx, and entertainment value yl corresponding to the elderly in the low-risk elderly set DW. Calculate the average diet value Dys of the low-risk elderly set according to the diet value ys: Calculate the average work and rest value Dzx of the low-risk elderly set according to the work and rest value zx: Calculate the average entertainment value Dyl of the low-risk elderly set according to the entertainment value yl. The specific calculation process is as follows: where: ys(DW) refers to the diet value ys corresponding to the elderly in the set DW; ys(DW) refers to the work and rest value zx corresponding to the elderly in the set DW; yl(DW) refers to the entertainment value yl corresponding to the elderly in the set DW.

7. A data analysis method for the elderly with multiple coexisting diseases according to claim 4, characterized in that, The said Step S32 also includes: Step S324: Obtain the comparison diet value Bys according to the average diet value Gys of the high-risk elderly set and the average diet value Dys of the low-risk elderly set; Obtain the comparison work and rest value Bzx according to the average work and rest value Gzx of the high-risk elderly set and the average work and rest value Dzx of the low-risk elderly set; Obtain the comparison entertainment value Byl according to the average entertainment value Gyl of the high-risk elderly set and the average entertainment value Dyl of the low-risk elderly set; Step S325: Make a judgment based on the comparison diet value Bys, the comparison work and rest value Bzx, and the comparison entertainment value Byl. If Bys < 0.5, it is considered that diet has no impact on the disease; if Bys >= 0.5, it is considered that diet has an impact on the disease. If Bzx < 0.5, it is considered that work and rest have no impact on the disease; if Bys >= 0.5, it is considered that work and rest have an impact on the disease. If Byl < 0.5, it is considered that entertainment has no impact on the disease; if Byl >= 0.5, it is considered that entertainment has an impact on the disease.

8. A data analysis method for the elderly with multiple co-existing diseases according to claim 6, characterized in that, The specific steps of the said step S321 are as follows: Make a judgment on the diet of the elderly according to the diet information of the elderly and the daily food recommended intake for the elderly aged 65, and classify it into three levels, namely: first level, second level, and third level; obtain the corresponding diet value ys according to the level; Quantify the work and rest information of the elderly. According to the recommended sleep duration, classify the work and rest of the elderly into three categories: less than the recommended duration, meeting the recommended duration, and exceeding the recommended duration; Count the sleep duration to obtain the work and rest value zx; Classify the entertainment information of the elderly into those who like personal entertainment and those who like group activities, and analyze it to obtain the entertainment value yl.

9. A data analysis method for the elderly with multiple co-existing diseases according to claim 1, characterized in that, The subsequent steps of the said step S4 are as follows: Step S41: Obtain the prevalence rate of a single disease and the confidence level between diseases, and calculate the probability of the elderly suffering from other diseases in combination with the disease information of the elderly to obtain the probability value gli; The specific calculation process is as follows: p mn represents the confidence level between diseases, n = i; A(bm, Lj) represents the value in the m-th row and j-th column of the case matrix; If gli > 50%, it is judged that the probability of the elderly suffering from the i-th disease is greater than 50%; targeted prevention of this disease is required; Step S42: Intervene in the living habits of the elderly, formulate eating habits, work and rest habits, and entertainment habits that can reduce the probability of disease occurrence, and prevent and treat the disease.

10. An analysis system for the data of the elderly with multiple co-existing diseases, applicable to any one of the analysis methods for the data of the elderly with multiple co-existing diseases in claims 1-9, characterized in that, Including: Data acquisition module: used to obtain the age and disease information of the elderly to obtain a disease table; Obtain the diet information, work and rest information, and entertainment information of the elderly to obtain living information; Data processing module: used to obtain the disease table of the elderly, process the disease information in the disease table to obtain the confidence level between diseases, calculate the influence value of each disease; sort the diseases according to the influence value, and matrixize the disease table of the elderly through the sorted disease order to obtain a case matrix; calculate the rows of the case matrix to obtain the prevalence rate of a single disease, and calculate the columns of the case matrix to obtain the disease value of the elderly; Data analysis module: used to obtain the association model between age and disease value according to the age and disease value of the elderly, classify the disease value according to the association model, and combine the living information of the elderly to obtain the association relationship between the diet information, work and rest information, entertainment information and disease value of the elderly; Data prediction module: used to predict the disease situation of the elderly according to the prevalence rate of a single disease and the confidence level between diseases, and prevent and treat the disease in combination with the diet information, work and rest information, and entertainment information of the elderly.

Images