阅读说明：本技术 一种基于大数据的慢性病病情预测方法、系统及存储介质 (Big data-based chronic disease condition prediction method and system and storage medium ) 是由 于大千 于 2021-08-27 设计创作，主要内容包括：本发明公开了一种基于大数据的慢性病病情预测方法、系统及存储介质,其中一种基于大数据的慢性病病情预测方法包括：采集目标对象的体征数据信息、历史诊断信息及个人生活环境信息,根据所获取的信息提取可能影响慢性病发展的影响因素,生成影响因素集合；建立重要因素遴选模型。将所述影响因素集合导入所述重要因素遴选模型,生成最终重要影响因素并确定其权重信息；根据所述最终重要影响因素及权重信息对目标对象病情进行分析预测,生成注意事项及医学建议；引入概率模型,根据目标对象病情信息对慢性病并发症进行预测；将目标对象病情信息以及注意事项、医学建议按照预设显示方式进行显示。(The invention discloses a chronic disease prediction method, a system and a storage medium based on big data, wherein the chronic disease prediction method based on the big data comprises the following steps: acquiring physical sign data information, historical diagnosis information and personal living environment information of a target object, extracting influence factors possibly influencing the development of chronic diseases according to the acquired information, and generating an influence factor set; and establishing an important factor selection model. Importing the influence factor set into the important factor selection model, generating a final important influence factor and determining weight information of the final important influence factor; analyzing and predicting the disease condition of the target object according to the final important influence factors and the weight information to generate notice items and medical suggestions; introducing a probability model, and predicting chronic disease complications according to the disease information of the target object; and displaying the disease condition information, the notice and the medical advice of the target object according to a preset display mode.)

1. A chronic disease condition prediction method based on big data is characterized by comprising the following steps:

acquiring physical sign data information, historical diagnosis information, living habits and environmental information of a target object, extracting influence factors possibly influencing the development of chronic diseases according to the acquired information, and generating an influence factor set;

establishing an important factor selection model, importing the influence factor set into the important factor selection model, generating a final important influence factor and determining weight information of the final important influence factor;

analyzing and predicting the disease condition of the target object according to the final important influence factors and the weight information to generate notice items and medical suggestions;

introducing a probability model, and predicting chronic disease complications according to the disease information of the target object;

and displaying the disease condition information, the notice and the medical advice of the target object according to a preset display mode.

2. The big data-based chronic disease condition prediction method according to claim 1, wherein the vital sign data information, the historical diagnosis information, the living habits and the environmental information of the target subject are collected, wherein the vital sign data information comprises one or a combination of more than two of height, weight, blood pressure, blood sugar and blood fat; the historical diagnosis information comprises one or more than two of the history, smoking history, drinking history and genetic history; the living habit and environment information comprises one or more than two combinations of eating habit information, local area information, regional climate information and working environment information.

3. The big data-based chronic disease condition prediction method according to claim 1, wherein the establishing of an important factor selection model, the importing of the influence factor set into the important factor selection model, the generating of the final important influence factors and the determination of the weight information thereof specifically comprise:

establishing an important factor selection model, importing an influence factor set into the important factor selection model, and carrying out cluster analysis on each influence factor in the influence factor set;

comparing the relationship between any two influencing factors, constructing an adjacency matrix of the influencing factors, wherein the two influencing factors take 1 when the relationship exists, the two influencing factors take 0 when the relationship does not exist,

calculating and generating a reachable matrix according to the adjacency matrix, extracting each influence factor through the reachable matrix, and determining a hierarchical structure;

acquiring influence factors corresponding to a front k layer in the hierarchical structure according to preset information to generate final important influence factors, wherein k is a non-zero integer and is less than or equal to the total number of layers of the hierarchical structure;

and obtaining a weight vector corresponding to the front k level in the hierarchical structure by a fuzzy analytic hierarchy process, and determining the weight information of the final important influence factor according to the weight vector.

4. The big data-based chronic disease condition prediction method according to claim 1, wherein the target object condition is analyzed and predicted according to the final important influence factors and the weight information to generate cautionary matters and medical suggestions, specifically:

presetting a chronic disease risk grade, and dividing the chronic disease condition into low risk, medium risk and high risk;

calculating a risk index according to a preset calculation mode through the final important influence factors and the weight information, and presetting a first threshold and a second threshold of the risk index;

comparing and judging the risk index with preset threshold information;

if the risk index is smaller than the first threshold, the chronic disease condition of the target object is proved to be low risk, and the generated related notice is displayed according to a preset mode;

if the risk index is larger than or equal to the first threshold and smaller than the second threshold, the chronic disease condition of the target object is proved to be medium risk, and related notice and medical advice are generated and displayed according to a preset mode;

if the risk index is larger than the second threshold, the chronic disease condition of the target object is proved to be high risk, and the related notice and the medical suggestion are generated and displayed according to a preset mode.

5. The big data-based chronic disease condition prediction method according to claim 1, wherein the probabilistic model is introduced to predict chronic disease complications according to the condition information of the target object, and specifically comprises:

extracting data information corresponding to the final important influence factors, and preprocessing the acquired data to generate a data set;

and establishing a probability model, performing initialization training, and importing the data set into the probability model to generate the conditional probability density of the chronic disease complications.

Calculating the predicted occurrence value of each complication through most conditional probability densities;

and setting a confidence interval to carry out pre-estimation correction on the predicted occurrence value to obtain a corrected predicted occurrence value, and outputting the predicted occurrence value.

6. The big data-based chronic disease condition prediction method according to claim 5, further comprising establishing a personal health status database, and verifying the evaluation of the chronic disease condition of the target user according to the historical sign data in the personal health status database, specifically:

establishing a personal health condition database, and extracting a historical sign data time sequence through the personal health condition database;

extracting the ith-year sign data of the target user according to the historical sign data time sequence;

preprocessing the extracted sign data to evaluate the chronic disease condition to obtain the prediction condition of the chronic disease condition in the ith year;

acquiring the actual condition of the chronic disease condition of the ith year from the personal health condition database;

comparing the chronic disease state prediction state with the chronic disease state actual state to obtain a deviation rate;

judging whether the deviation rate is greater than a preset deviation rate threshold value or not;

and if so, generating correction information, and correcting the evaluation of the chronic disease condition of the target user through the correction information.

7. A big data based chronic disease prediction system, the system comprising: the device comprises a memory and a processor, wherein the memory comprises a big data-based chronic disease prediction method program, and when the processor executes the big data-based chronic disease prediction method program, the following steps are realized:

acquiring physical sign data information, historical diagnosis information, living habits and environmental information of a target object, extracting influence factors possibly influencing the development of chronic diseases according to the acquired information, and generating an influence factor set;

establishing an important factor selection model, importing the influence factor set into the important factor selection model, generating a final important influence factor and determining weight information of the final important influence factor;

analyzing and predicting the disease condition of the target object according to the final important influence factors and the weight information to generate notice items and medical suggestions;

introducing a probability model, and predicting chronic disease complications according to the disease information of the target object;

and displaying the disease condition information, the notice and the medical advice of the target object according to a preset display mode.

8. The big data-based chronic disease situation prediction system according to claim 7, wherein the establishing of an important factor selection model, the importing of the influence factor set into the important factor selection model, the generating of the final important influence factors and the determination of the weight information thereof specifically comprise:

establishing an important factor selection model, importing an influence factor set into the important factor selection model, and carrying out cluster analysis on each influence factor in the influence factor set;

comparing the relationship between any two influencing factors, constructing an adjacency matrix of the influencing factors, wherein the two influencing factors take 1 when the relationship exists, the two influencing factors take 0 when the relationship does not exist,

calculating and generating a reachable matrix according to the adjacency matrix, extracting each influence factor through the reachable matrix, and determining a hierarchical structure;

acquiring influence factors corresponding to a front k layer in the hierarchical structure according to preset information to generate final important influence factors, wherein k is a non-zero integer and is less than or equal to the total number of layers of the hierarchical structure;

and obtaining a weight vector corresponding to the front k level in the hierarchical structure by a fuzzy analytic hierarchy process, and determining the weight information of the final important influence factor according to the weight vector.

9. The big data-based chronic disease condition prediction system according to claim 7, wherein the probabilistic model is introduced to predict chronic disease complications according to the condition information of the target object, and specifically comprises:

extracting data information corresponding to the final important influence factors, and preprocessing the acquired data to generate a data set;

and establishing a probability model, performing initialization training, and importing the data set into the probability model to generate the conditional probability density of the chronic disease complications.

Calculating the predicted occurrence value of each complication through most conditional probability densities;

and setting a confidence interval to carry out pre-estimation correction on the predicted occurrence value to obtain a corrected predicted occurrence value, and outputting the predicted occurrence value.

10. A computer-readable storage medium, wherein the computer-readable storage medium includes a big data-based chronic disease prediction method program, and when the big data-based chronic disease prediction method program is executed by a processor, the steps of the big data-based chronic disease prediction method according to any one of claims 1 to 6 are implemented.

Technical Field

The invention relates to the field of chronic disease management, in particular to a chronic disease condition prediction method and system based on big data and a storage medium.

Background

In the context of the new era, health has become an important aspect of the ever-increasing need for a nice life for people. However, health problems are increasingly prominent, which seriously threatens the health of people, especially the 'well-spraying' growth of patients with chronic diseases and brings heavy burden to the medical health industry. Chronic non-infectious diseases such as cardiovascular and cerebrovascular diseases, diabetes and the like which are closely related to life style of people become main killers of health and life. Chronic diseases have the characteristics of long course of disease, complex etiology, serious health damage and social harm and the like, are mostly lifelong diseases, have poor prognosis and are often accompanied with various complications. The prevalence rate of chronic diseases in China is in a continuous rising trend, and the risk factors of chronic diseases are severe in prevalence. Meanwhile, the aging trend of the population of China is accelerating rapidly, and the increase of the aging population promotes the prevention and treatment of chronic diseases to be more urgent and difficult. At present, the demand for risk prediction and management of chronic diseases is increasingly strong.

In order to monitor and manage the chronic diseases, a system needs to be developed and matched with the chronic diseases, and the system extracts influence factors possibly influencing the development of the chronic diseases according to the acquired information by acquiring data information of a target object to generate an influence factor set; establishing an important factor selection model, importing an influence factor set into a generated final important influence factor and determining weight information of the final important influence factor; analyzing and predicting the disease condition of the target object according to the final important influence factors and the weight information to generate notice items and medical suggestions; and introducing a probability model, and predicting chronic disease complications according to the disease information of the target object. In the implementation process of the system, how to establish an important factor selection model and how to analyze the state of an illness through the final important influencing factors and weight information are all problems which need to be solved urgently.

Disclosure of Invention

In order to solve at least one technical problem, the invention provides a chronic disease condition prediction method, a system and a storage medium based on big data.

The invention provides a chronic disease condition prediction method based on big data, which comprises the following steps:

acquiring physical sign data information, historical diagnosis information, living habits and environmental information of a target object, extracting influence factors possibly influencing the development of chronic diseases according to the acquired information, and generating an influence factor set;

establishing an important factor selection model, importing the influence factor set into the important factor selection model, generating a final important influence factor and determining weight information of the final important influence factor;

analyzing and predicting the disease condition of the target object according to the final important influence factors and the weight information to generate notice items and medical suggestions;

introducing a probability model, and predicting chronic disease complications according to the disease information of the target object;

and displaying the disease condition information, the notice and the medical advice of the target object according to a preset display mode.

In the scheme, the physical sign data information, the historical diagnosis information, the living habits and the environmental information of the target object are collected, wherein the physical sign data information comprises one or the combination of more than two of height, weight, blood pressure, blood sugar and blood fat; the historical diagnosis information comprises one or more than two of the history, smoking history, drinking history and genetic history; the living habit and environment information comprises one or more than two combinations of eating habit information, local area information, regional climate information and working environment information.

In this scheme, the establishment of an important factor selection model imports the influence factor set into the important factor selection model, generates a final important influence factor and determines weight information thereof, specifically:

establishing an important factor selection model, importing an influence factor set into the important factor selection model, and carrying out cluster analysis on each influence factor in the influence factor set;

comparing the relationship between any two influencing factors, constructing an adjacency matrix of the influencing factors, wherein the two influencing factors take 1 when the relationship exists, the two influencing factors take 0 when the relationship does not exist,

calculating and generating a reachable matrix according to the adjacency matrix, extracting each influence factor through the reachable matrix, and determining a hierarchical structure;

acquiring influence factors corresponding to a front k layer in the hierarchical structure according to preset information to generate final important influence factors, wherein k is a non-zero integer and is less than or equal to the total number of layers of the hierarchical structure;

and obtaining a weight vector corresponding to the front k level in the hierarchical structure by a fuzzy analytic hierarchy process, and determining the weight information of the final important influence factor according to the weight vector.

In the scheme, the condition of the target object is analyzed and predicted according to the final important influence factors and the weight information, and the notice and medical advice are generated, specifically:

presetting a chronic disease risk grade, and dividing the chronic disease condition into low risk, medium risk and high risk;

calculating a risk index according to a preset calculation mode through the final important influence factors and the weight information, and presetting a first threshold and a second threshold of the risk index;

comparing and judging the risk index with preset threshold information;

if the risk index is smaller than the first threshold, the chronic disease condition of the target object is proved to be low risk, and the generated related notice is displayed according to a preset mode;

if the risk index is larger than or equal to the first threshold and smaller than the second threshold, the chronic disease condition of the target object is proved to be medium risk, and related notice and medical advice are generated and displayed according to a preset mode;

if the risk index is larger than the second threshold, the chronic disease condition of the target object is proved to be high risk, and the related notice and the medical suggestion are generated and displayed according to a preset mode.

In the scheme, the probability model is introduced to predict chronic disease complications according to the disease condition information of the target object, and the method specifically comprises the following steps:

extracting data information corresponding to the final important influence factors, and preprocessing the acquired data to generate a data set;

and establishing a probability model, performing initialization training, and importing the data set into the probability model to generate the conditional probability density of the chronic disease complications.

Calculating the predicted occurrence value of each complication through most conditional probability densities;

and setting a confidence interval to carry out pre-estimation correction on the predicted occurrence value to obtain a corrected predicted occurrence value, and outputting the predicted occurrence value.

In the scheme, the method further comprises the steps of establishing a personal health condition database, and verifying the evaluation of the chronic disease condition of the target user according to historical sign data in the personal health condition database, wherein the specific steps are as follows:

establishing a personal health condition database, and extracting a historical sign data time sequence through the personal health condition database;

extracting the ith-year sign data of the target user according to the historical sign data time sequence;

preprocessing the extracted sign data to evaluate the chronic disease condition to obtain the prediction condition of the chronic disease condition in the ith year;

acquiring the actual condition of the chronic disease condition of the ith year from the personal health condition database;

comparing the chronic disease state prediction state with the chronic disease state actual state to obtain a deviation rate;

judging whether the deviation rate is greater than a preset deviation rate threshold value or not;

and if so, generating correction information, and correcting the evaluation of the chronic disease condition of the target user through the correction information.

The second aspect of the present invention also provides a system for predicting chronic disease conditions based on big data, the system comprising: the device comprises a memory and a processor, wherein the memory comprises a big data-based chronic disease prediction method program, and when the processor executes the big data-based chronic disease prediction method program, the following steps are realized:

acquiring physical sign data information, historical diagnosis information, living habits and environmental information of a target object, extracting influence factors possibly influencing the development of chronic diseases according to the acquired information, and generating an influence factor set;

establishing an important factor selection model, importing the influence factor set into the important factor selection model, generating a final important influence factor and determining weight information of the final important influence factor;

analyzing and predicting the disease condition of the target object according to the final important influence factors and the weight information to generate notice items and medical suggestions;

introducing a probability model, and predicting chronic disease complications according to the disease information of the target object;

and displaying the disease condition information, the notice and the medical advice of the target object according to a preset display mode.

In the scheme, the physical sign data information, the historical diagnosis information, the living habits and the environmental information of the target object are collected, wherein the physical sign data information comprises one or the combination of more than two of height, weight, blood pressure, blood sugar and blood fat; the historical diagnosis information comprises one or more than two of the history, smoking history, drinking history and genetic history; the living habit and environment information comprises one or more than two combinations of eating habit information, local area information, regional climate information and working environment information.

In this scheme, the establishment of an important factor selection model imports the influence factor set into the important factor selection model, generates a final important influence factor and determines weight information thereof, specifically:

establishing an important factor selection model, importing an influence factor set into the important factor selection model, and carrying out cluster analysis on each influence factor in the influence factor set;

comparing the relationship between any two influencing factors, constructing an adjacency matrix of the influencing factors, wherein the two influencing factors take 1 when the relationship exists, the two influencing factors take 0 when the relationship does not exist,

calculating and generating a reachable matrix according to the adjacency matrix, extracting each influence factor through the reachable matrix, and determining a hierarchical structure;

acquiring influence factors corresponding to a front k layer in the hierarchical structure according to preset information to generate final important influence factors, wherein k is a non-zero integer and is less than or equal to the total number of layers of the hierarchical structure;

and obtaining a weight vector corresponding to the front k level in the hierarchical structure by a fuzzy analytic hierarchy process, and determining the weight information of the final important influence factor according to the weight vector.

In the scheme, the condition of the target object is analyzed and predicted according to the final important influence factors and the weight information, and the notice and medical advice are generated, specifically:

presetting a chronic disease risk grade, and dividing the chronic disease condition into low risk, medium risk and high risk;

calculating a risk index according to a preset calculation mode through the final important influence factors and the weight information, and presetting a first threshold and a second threshold of the risk index;

comparing and judging the risk index with preset threshold information;

if the risk index is smaller than the first threshold, the chronic disease condition of the target object is proved to be low risk, and the generated related notice is displayed according to a preset mode;

if the risk index is larger than or equal to the first threshold and smaller than the second threshold, the chronic disease condition of the target object is proved to be medium risk, and related notice and medical advice are generated and displayed according to a preset mode;

if the risk index is larger than the second threshold, the chronic disease condition of the target object is proved to be high risk, and the related notice and the medical suggestion are generated and displayed according to a preset mode.

In the scheme, the probability model is introduced to predict chronic disease complications according to the disease condition information of the target object, and the method specifically comprises the following steps:

extracting data information corresponding to the final important influence factors, and preprocessing the acquired data to generate a data set;

and establishing a probability model, performing initialization training, and importing the data set into the probability model to generate the conditional probability density of the chronic disease complications.

Calculating the predicted occurrence value of each complication through most conditional probability densities;

and setting a confidence interval to carry out pre-estimation correction on the predicted occurrence value to obtain a corrected predicted occurrence value, and outputting the predicted occurrence value.

In the scheme, the method further comprises the steps of establishing a personal health condition database, and verifying the evaluation of the chronic disease condition of the target user according to historical sign data in the personal health condition database, wherein the specific steps are as follows:

establishing a personal health condition database, and extracting a historical sign data time sequence through the personal health condition database;

extracting the ith-year sign data of the target user according to the historical sign data time sequence;

preprocessing the extracted sign data to evaluate the chronic disease condition to obtain the prediction condition of the chronic disease condition in the ith year;

acquiring the actual condition of the chronic disease condition of the ith year from the personal health condition database;

comparing the chronic disease state prediction state with the chronic disease state actual state to obtain a deviation rate;

judging whether the deviation rate is greater than a preset deviation rate threshold value or not;

and if so, generating correction information, and correcting the evaluation of the chronic disease condition of the target user through the correction information.

The third aspect of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium includes a big data-based chronic disease prediction method program, and when the big data-based chronic disease prediction method program is executed by a processor, the steps of the big data-based chronic disease prediction method are implemented.

The invention discloses a chronic disease condition prediction method, a system and a storage medium based on big data, wherein the chronic disease condition prediction method based on the big data comprises the following steps: acquiring physical sign data information, historical diagnosis information and personal living environment information of a target object, extracting influence factors possibly influencing the development of chronic diseases according to the acquired information, and generating an influence factor set; and establishing an important factor selection model. Importing the influence factor set into the important factor selection model, generating a final important influence factor and determining weight information of the final important influence factor; analyzing and predicting the disease condition of the target object according to the final important influence factors and the weight information to generate notice items and medical suggestions; introducing a probability model, and predicting chronic disease complications according to the disease information of the target object; and displaying the disease condition information, the notice and the medical advice of the target object according to a preset display mode. According to the method, important influence factors are selected from possible influence factors by constructing an important influence factor selection model, the hierarchical relation of each important influence factor is analyzed, the weight of each important influence factor in the development process of the chronic disease is determined, the influence degree of each important influence factor on the development of the chronic disease is determined, and meanwhile, a basis is provided for the condition evaluation and complication prediction of the chronic disease.

Drawings

FIG. 1 is a flow chart of a big data based chronic disease prediction method of the present invention;

FIG. 2 is a flow chart of a method for establishing an importance factor selection model according to the present invention;

FIG. 3 is a flow chart of a method for introducing a probabilistic model for complication prediction according to the present invention;

FIG. 4 shows a block diagram of a big data based chronic disease prediction system of the present invention.

Detailed Description

In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.

FIG. 1 is a flow chart of a big data-based chronic disease prediction method according to the present invention.

As shown in fig. 1, a first aspect of the present invention provides a big data-based chronic disease prediction method, including:

s102, collecting sign data information, historical diagnosis information, living habits and environmental information of a target object, extracting influence factors possibly influencing the development of chronic diseases according to the obtained information, and generating an influence factor set;

s104, establishing an important factor selection model, importing the influence factor set into the important factor selection model, generating a final important influence factor and determining weight information of the final important influence factor;

s106, analyzing and predicting the disease condition of the target object according to the final important influence factors and the weight information to generate notice items and medical suggestions;

s108, introducing a probability model, and predicting chronic disease complications according to the disease information of the target object;

and S110, displaying the disease condition information, the notice and the medical suggestion of the target object according to a preset display mode.

It should be noted that the physical sign data information, the historical diagnosis information, the living habits and the environmental information of the target object are acquired, wherein the physical sign data information comprises one or a combination of more than two of height, weight, blood pressure, blood sugar and blood fat; the historical diagnosis information comprises one or more than two of the history, smoking history, drinking history and genetic history; the living habit and environment information comprises one or more than two combinations of eating habit information, local area information, regional climate information and working environment information.

FIG. 2 is a flow chart of the method for establishing the importance factor selection model according to the present invention.

According to the embodiment of the invention, an important factor selection model is established, the influence factor set is imported into the important factor selection model, the final important influence factor is generated, and the weight information of the final important influence factor is determined, which specifically comprises the following steps:

s202, establishing an important factor selection model, importing an influence factor set into the important factor selection model, and carrying out cluster analysis on each influence factor in the influence factor set;

s204, comparing the relationship between any two influence factors, constructing an adjacency matrix of the influence factors, wherein the two influence factors take 1 when the relationship exists, the two influence factors take 0 when the relationship does not exist,

s206, calculating and generating a reachable matrix according to the adjacent matrix, extracting each influence factor through the reachable matrix, and determining a hierarchical structure;

s208, acquiring influence factors corresponding to a front k layer in the hierarchical structure according to preset information, and generating final important influence factors, wherein k is a non-zero integer and is less than or equal to the total layer number of the hierarchical structure;

s210, obtaining a weight vector corresponding to the front k level in the hierarchical structure through a fuzzy analytic hierarchy process, and determining the weight information of the final important influence factor according to the weight vector.

It should be noted that, the analysis and prediction of the disease condition of the target object is performed according to the final important influence factors and the weight information, and the cautionary matters and the medical suggestions are generated, specifically:

presetting a chronic disease risk grade, and dividing the chronic disease condition into low risk, medium risk and high risk;

calculating a risk index according to a preset calculation mode through the final important influence factors and the weight information, and presetting a first threshold and a second threshold of the risk index;

comparing and judging the risk index with preset threshold information;

if the risk index is smaller than the first threshold, the chronic disease condition of the target object is proved to be low risk, and the generated related notice is displayed according to a preset mode;

if the risk index is larger than or equal to the first threshold and smaller than the second threshold, the chronic disease condition of the target object is proved to be medium risk, and related notice and medical advice are generated and displayed according to a preset mode;

if the risk index is larger than the second threshold, the chronic disease condition of the target object is proved to be high risk, and the related notice and the medical suggestion are generated and displayed according to a preset mode.

Fig. 3 shows a flowchart of a method for introducing a probabilistic model for complication prediction according to the present invention.

According to the embodiment of the invention, a probability model is introduced, and chronic disease complications are predicted according to the disease information of the target object, specifically:

s302, extracting data information corresponding to the final important influence factors, and preprocessing the acquired data to generate a data set;

s304, establishing a probability model, performing initialization training, and importing the data set into the probability model to generate the conditional probability density of the chronic disease complications.

S306, calculating the predicted occurrence value of each complication through most conditional probability densities;

and S308, setting a confidence interval to carry out estimation correction on the predicted occurrence value to obtain a corrected predicted occurrence value, and outputting the predicted occurrence value.

According to the embodiment of the invention, a personal health condition database is established, and the evaluation of the chronic disease condition of the target user is verified according to historical sign data in the personal health condition database, which specifically comprises the following steps:

establishing a personal health condition database, and extracting a historical sign data time sequence through the personal health condition database;

extracting the ith-year sign data of the target user according to the historical sign data time sequence;

preprocessing the extracted sign data to evaluate the chronic disease condition to obtain the prediction condition of the chronic disease condition in the ith year;

acquiring the actual condition of the chronic disease condition of the ith year from the personal health condition database;

comparing the chronic disease state prediction state with the chronic disease state actual state to obtain a deviation rate;

judging whether the deviation rate is greater than a preset deviation rate threshold value or not;

and if so, generating correction information, and correcting the evaluation of the chronic disease condition of the target user through the correction information.

According to the embodiment of the invention, physical sign data of a target user are collected in real time by a body health state monitoring device, and the physical sign data are monitored and analyzed by a cloud platform, specifically:

the method comprises the steps that physical health state monitoring equipment is used for collecting target user sign data in real time, and the physical health state monitoring equipment is connected with route access equipment;

the route access equipment transmits data to the cloud platform, and the cloud platform generates physical health condition parameters from the acquired physical sign data in a preset calculation mode;

judging whether the physical health condition parameter is smaller than a preset threshold value;

if the current time is less than the preset time, the system can give an alarm through the body health state monitoring equipment and immediately remind the target object of the relative through a short message or a call.

According to the embodiment of the present invention, after the alarm information is generated, the cloud platform generates a preliminary judgment through the personal health status database and the physical health status parameters of the target user, specifically:

performing feature extraction on the body health condition parameters of the target user to generate parameter features, and performing comparative analysis on the parameter features and normal thresholds corresponding to all the parameters to generate medical features;

importing historical monitoring data and historical diagnosis data of the target user in the medical characteristic matching personal health condition database into a medical knowledge base of a cloud platform;

performing preliminary judgment through the medical knowledge base to generate an auxiliary diagnosis result;

performing feature matching on the auxiliary diagnosis result in an electronic case database through big data processing to generate a matching result;

sorting the matching results, determining similar historical case samples according to the sorting results, and generating an emergency processing method and cautions through the similar historical case samples;

and pushing the emergency processing method and the notice along with the alarm information, and displaying the emergency processing method and the notice according to a preset mode.

FIG. 4 shows a block diagram of a big data based chronic disease prediction system of the present invention.

The second aspect of the present invention also provides a big data-based chronic disease prediction system 4, which includes: a memory 41 and a processor 42, wherein the memory includes a big data-based chronic disease prediction method program, and when the processor executes the big data-based chronic disease prediction method program, the following steps are implemented:

acquiring physical sign data information, historical diagnosis information, living habits and environmental information of a target object, extracting influence factors possibly influencing the development of chronic diseases according to the acquired information, and generating an influence factor set;

establishing an important factor selection model, importing the influence factor set into the important factor selection model, generating a final important influence factor and determining weight information of the final important influence factor;

analyzing and predicting the disease condition of the target object according to the final important influence factors and the weight information to generate notice items and medical suggestions;

introducing a probability model, and predicting chronic disease complications according to the disease information of the target object;

and displaying the disease condition information, the notice and the medical advice of the target object according to a preset display mode.

It should be noted that the physical sign data information, the historical diagnosis information, the living habits and the environmental information of the target object are acquired, wherein the physical sign data information comprises one or a combination of more than two of height, weight, blood pressure, blood sugar and blood fat; the historical diagnosis information comprises one or more than two of the history, smoking history, drinking history and genetic history; the living habit and environment information comprises one or more than two combinations of eating habit information, local area information, regional climate information and working environment information.

According to the embodiment of the invention, an important factor selection model is established, the influence factor set is imported into the important factor selection model, the final important influence factor is generated, and the weight information of the final important influence factor is determined, which specifically comprises the following steps:

establishing an important factor selection model, importing an influence factor set into the important factor selection model, and carrying out cluster analysis on each influence factor in the influence factor set;

comparing the relationship between any two influencing factors, constructing an adjacency matrix of the influencing factors, wherein the two influencing factors take 1 when the relationship exists, the two influencing factors take 0 when the relationship does not exist,

calculating and generating a reachable matrix according to the adjacency matrix, extracting each influence factor through the reachable matrix, and determining a hierarchical structure;

acquiring influence factors corresponding to a front k layer in the hierarchical structure according to preset information to generate final important influence factors, wherein k is a non-zero integer and is less than or equal to the total number of layers of the hierarchical structure;

and obtaining a weight vector corresponding to the front k level in the hierarchical structure by a fuzzy analytic hierarchy process, and determining the weight information of the final important influence factor according to the weight vector.

It should be noted that, the analysis and prediction of the disease condition of the target object is performed according to the final important influence factors and the weight information, and the cautionary matters and the medical suggestions are generated, specifically:

presetting a chronic disease risk grade, and dividing the chronic disease condition into low risk, medium risk and high risk;

calculating a risk index according to a preset calculation mode through the final important influence factors and the weight information, and presetting a first threshold and a second threshold of the risk index;

comparing and judging the risk index with preset threshold information;

if the risk index is smaller than the first threshold, the chronic disease condition of the target object is proved to be low risk, and the generated related notice is displayed according to a preset mode;

if the risk index is larger than or equal to the first threshold and smaller than the second threshold, the chronic disease condition of the target object is proved to be medium risk, and related notice and medical advice are generated and displayed according to a preset mode;

if the risk index is larger than the second threshold, the chronic disease condition of the target object is proved to be high risk, and the related notice and the medical suggestion are generated and displayed according to a preset mode.

According to the embodiment of the invention, a probability model is introduced, and chronic disease complications are predicted according to the disease information of the target object, specifically:

extracting data information corresponding to the final important influence factors, and preprocessing the acquired data to generate a data set;

and establishing a probability model, performing initialization training, and importing the data set into the probability model to generate the conditional probability density of the chronic disease complications.

Calculating the predicted occurrence value of each complication through most conditional probability densities;

and setting a confidence interval to carry out pre-estimation correction on the predicted occurrence value to obtain a corrected predicted occurrence value, and outputting the predicted occurrence value.

According to the embodiment of the invention, a personal health condition database is established, and the evaluation of the chronic disease condition of the target user is verified according to historical sign data in the personal health condition database, which specifically comprises the following steps:

establishing a personal health condition database, and extracting a historical sign data time sequence through the personal health condition database;

extracting the ith-year sign data of the target user according to the historical sign data time sequence;

preprocessing the extracted sign data to evaluate the chronic disease condition to obtain the prediction condition of the chronic disease condition in the ith year;

acquiring the actual condition of the chronic disease condition of the ith year from the personal health condition database;

comparing the chronic disease state prediction state with the chronic disease state actual state to obtain a deviation rate;

judging whether the deviation rate is greater than a preset deviation rate threshold value or not;

and if so, generating correction information, and correcting the evaluation of the chronic disease condition of the target user through the correction information.

According to the embodiment of the invention, physical sign data of a target user are collected in real time by a body health state monitoring device, and the physical sign data are monitored and analyzed by a cloud platform, specifically:

the method comprises the steps that physical health state monitoring equipment is used for collecting target user sign data in real time, and the physical health state monitoring equipment is connected with route access equipment;

the route access equipment transmits data to the cloud platform, and the cloud platform generates physical health condition parameters from the acquired physical sign data in a preset calculation mode;

judging whether the physical health condition parameter is smaller than a preset threshold value;

if the current time is less than the preset time, the system can give an alarm through the body health state monitoring equipment and immediately remind the target object of the relative through a short message or a call.

According to the embodiment of the present invention, after the alarm information is generated, the cloud platform generates a preliminary judgment through the personal health status database and the physical health status parameters of the target user, specifically:

performing feature extraction on the body health condition parameters of the target user to generate parameter features, and performing comparative analysis on the parameter features and normal thresholds corresponding to all the parameters to generate medical features;

importing historical monitoring data and historical diagnosis data of the target user in the medical characteristic matching personal health condition database into a medical knowledge base of a cloud platform;

performing preliminary judgment through the medical knowledge base to generate an auxiliary diagnosis result;

performing feature matching on the auxiliary diagnosis result in an electronic case database through big data processing to generate a matching result;

sorting the matching results, determining similar historical case samples according to the sorting results, and generating an emergency processing method and cautions through the similar historical case samples;

and pushing the emergency processing method and the notice along with the alarm information, and displaying the emergency processing method and the notice according to a preset mode.

The third aspect of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium includes a big data-based chronic disease prediction method program, and when the big data-based chronic disease prediction method program is executed by a processor, the steps of the big data-based chronic disease prediction method are implemented.

The invention discloses a chronic disease prediction method, a system and a storage medium based on big data, wherein the chronic disease prediction method based on the big data comprises the following steps: acquiring physical sign data information, historical diagnosis information and personal living environment information of a target object, extracting influence factors possibly influencing the development of chronic diseases according to the acquired information, and generating an influence factor set; and establishing an important factor selection model. Importing the influence factor set into the important factor selection model, generating a final important influence factor and determining weight information of the final important influence factor; analyzing and predicting the disease condition of the target object according to the final important influence factors and the weight information to generate notice items and medical suggestions; introducing a probability model, and predicting chronic disease complications according to the disease information of the target object; and displaying the disease condition information, the notice and the medical advice of the target object according to a preset display mode. According to the method, important influence factors are selected from possible influence factors by constructing an important influence factor selection model, the hierarchical relation of each important influence factor is analyzed, the weight of each important influence factor in the development process of the chronic disease is determined, the influence degree of each important influence factor on the development of the chronic disease is determined, and meanwhile, a basis is provided for the condition evaluation and complication prediction of the chronic disease.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, all the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.

Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a RAM, a magnetic or optical disk, or various other media that can store program code.

The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.