Intelligent health management method and system for chronic disease patient

Abstract

The invention provides an intelligent health management method and system for chronic disease patients. The system comprises a physical sign abnormity module, a common disease association module, a common disease repulsion association module and a strategy module. The physical sign abnormity module can collect physical sign data, judge abnormal risk conditions of chronic diseases, and obtain abnormal physical sign data of the chronic diseases when judging that the chronic diseases have abnormal risks; the co-disease association module comprises associated diseases associated with chronic diseases, and the association degree of the chronic diseases with abnormal risks and the associated diseases is obtained; the co-disease exclusion association module comprises exclusion diseases with treatment counteracting effects with chronic diseases, and the chronic diseases with abnormal risks and the exclusion association degree of the exclusion diseases are obtained; and the strategy module allocates a corresponding common disease treatment strategy according to the association degree between the chronic disease with the abnormal risk and the associated disease and the exclusion association degree between the chronic disease and the exclusion associated disease. According to the invention, the system optimization is improved.

Description

Technical Field

[0001] This application relates to the field of intelligent health management methods, and particularly to an intelligent health management method and system for chronic disease patients. Background Art

[0002] Chronic diseases refer to a group of diseases with a long course and slow progression, often lasting for months or years, and even difficult to eradicate throughout life (such as hypertension, diabetes, heart disease, chronic obstructive pulmonary disease, arthritis, tumors, etc.). Due to the long duration and diverse and complex conditions of the diseases, more dimensions, more levels, and longer-term physical sign observations and health management are often required compared to other diseases. Currently, as a booming emerging technology in the medical industry, the intelligent health care model is seeking new breakthroughs and reforms for chronic disease management and showing significant advantages. Currently, patients can choose to conduct real-time monitoring through intelligent wearable devices outside the medical platform system, such as wearing a heart rate detection device, a blood glucose detection device, a blood pressure detection device, etc. The data collected by these devices can provide basic data for the medical health management system to evaluate and predict the disease condition. In the existing applications of intelligent systems, generally, a trained medical data model is used to obtain the patient's physical sign data through peripheral devices to judge the development of the patient's chronic diseases. When a deteriorating condition is found, an early warning can be given for the deteriorating condition.

[0003] However, the big data models of the existing technologies often use qualitative models, that is, single-judgment models, which can often only give judgments on whether the physical sign values are normal, and often simply evaluate the patient's current situation based on the current monitoring situation, lacking stability, pertinence, preventive ability, and sensitivity. Since each patient has a different constitution, and chronic diseases often last for a long time, patients often suffer from many chronic diseases. Among these co-existing diseases, some will have a mutually promoting effect, some will mask the manifestations of the disease, and there will be problems of mutual cancellation and exclusion between the treatment plans of some other chronic diseases. Therefore, in the case of co-existing diseases, the methods for judging the malignant changes of chronic diseases and selecting health treatment plans are very complex, and it is difficult for a simple qualitative system to give accurate judgments. Therefore, a method that can comprehensively consider the patient's individual disease characteristics, comprehensively evaluate the disease condition, and give a more reasonable health treatment plan according to the trend of the disease condition changes is needed. Summary of the Invention

[0004] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variants. The basic principles defined in the following description can be applied to other implementation schemes, variant schemes, improvement schemes, equivalent schemes, and other technical schemes that do not deviate from the spirit and scope of the present invention.

[0005] To solve the technical problems, the present application provides an intelligent health management system for chronic disease patients, including a physical sign abnormality module, a comorbidity association module, a comorbidity exclusion association module, and a strategy module; The physical sign abnormality module includes a monitoring module and an abnormality module. The monitoring module can collect physical sign data, and the abnormality module can judge the abnormal risk situation of chronic diseases according to the collected physical sign data. When it is judged that a chronic disease has an abnormal risk, the abnormal physical sign data of the chronic disease is obtained; The comorbidity association module includes associated diseases that are associated with the onset of chronic diseases, and obtains the association degree between the chronic disease with abnormal risk and its associated diseases; The comorbidity exclusion association module includes exclusion diseases that have a treatment offset effect on chronic diseases, and obtains the exclusion association degree between the chronic disease with abnormal risk and its exclusion diseases; The strategy module allocates corresponding comorbidity treatment strategies according to the association degree between the chronic disease with abnormal risk and its associated diseases and the exclusion association degree with its exclusion diseases.

[0006] Among them, the monitoring standard threshold is set according to the patient's personal health characteristics. When the monitoring value exceeds the standard threshold, this monitoring is used as an abnormal node of the physical sign; the personal health characteristics include age, gender, height, weight, medical history, and medical record.

[0007] Among them, the monitoring value is recorded as the abnormal value of the abnormal node, the difference between the monitoring value and the monitoring standard threshold is recorded as the node amplitude of the abnormal node, and an abnormal physical sign list of chronic diseases is obtained according to the data of the abnormal node and the amplitude threshold of the physical sign. When it is judged that a chronic disease has an abnormal risk, a risk alarm is sent to the patient and the abnormal physical sign list is displayed.

[0008] The present application also provides a method for using the intelligent health management system for chronic disease patients as described above. The steps include: S1, the system provides health management for n types of chronic diseases M, M = [M1, M2, M3,..., M n , where the monitoring module is set to monitor p types of physical sign categories IT for the i-th type of chronic disease M i IT = [IT1, IT2, IT3,..., IT p , where the monitoring frequency of the j-th type of physical sign IT j is θ; the monitoring standard threshold of the j-th type of physical sign IT j is set to UJ0; S2, obtain the monitoring value UJ j of the physical sign IT h , when the monitoring value UJ hWhen it exceeds the standard threshold range UJ0, this monitoring is regarded as the physical sign IT j For the abnormal node, the monitoring value UJ h is recorded as the abnormal value of the abnormal node, and the monitoring value UJ h The difference from the monitoring standard threshold UJ0 is recorded as the node amplitude of the abnormal node, and the amplitude threshold △U0 of the physical sign IT j is set; S3, set the physical sign IT j to include b abnormal monitoring nodes Q, Q = [Q1, Q2, Q3, …, Q b , where the node amplitude corresponding to the h-th abnormal monitoring node Q h is △U h , Obtain the abnormal amplitude δ j of the physical sign IT j = ; S4, according to the amplitude threshold △U0 of the physical sign IT j , obtain the abnormal deviation degree j of the physical sign IT ; When ρ j ≥ρ0, regard the physical sign IT j as the abnormal physical sign of the chronic disease M i ; S5, obtain d abnormal physical signs of the chronic disease M i , and establish an abnormal physical sign list YTJ = [YTJ1, YTJ2, YTJ3, …, YTJ d in descending order, where the abnormal deviation degree of the z-th abnormal physical sign YTJ z is ρ z ; S6, according to the p physical sign categories IT that need to be monitored for the chronic disease M i , obtain the total abnormal degree ε i of the chronic disease M i = ; S7, set the abnormal degree threshold ε0 of the chronic disease M i , and when the total abnormal degree ε i of the obtained chronic disease M i ≥ε0, judge that the chronic disease M i has an abnormal risk; S8, set the chronic disease with a morbidity correlation with M i as the associated disease of M i , and set the associated diseases PI of M i to include b kinds, PI = [PI1, PI2, PI3, …, PI b, where the k-th associated disease is PI k , set the chronic disease M i and the associated disease PI k has a correlation coefficient of R ki , obtain PI k and M i 's association score F ki ; According to the obtained association score F ki execute the corresponding comorbidity strategy; S9, set the chronic disease with a treatment offset effect on M i as the repellent disease of M i , set the repellent diseases QI of M i include c kinds, QI = [QI1, QI2, QI3,..., QI c , where the r-th repellent disease is QI r , set the treatment plans AQI of QI r have g kinds, AQI = [AQI1, AQI2, AQI3,..., AQI g , where the s-th treatment plan AQI s 's treatment effect time period △st = [t, t + △T], where t is the treatment occurrence time and △T is the treatment effect duration; obtain the treatment plan AQI s and the chronic disease M i 's repellent association score FW i ; According to the obtained repellent association score FW i execute the corresponding comorbidity strategy.

[0009] Among them, step S8 includes: set PI k needs to monitor f kinds of physical sign categories KT, and among the physical sign categories KT includes m abnormal physical signs of M i ; According to the d abnormal physical signs YTJ of the chronic disease M i , the z-th abnormal physical sign YTJ z 's abnormal deviation degree ρ z , obtain PI k and M i 's association score .

[0010] Among them, step S9 includes: according to the abnormal physical sign list YTJ = [YTJ1, YTJ2, YTJ3,..., YTJ d , obtain the time point TZ of the z-th abnormal physical sign YTJ z ; Whenever TZ ∈ △st occurs once, add 1 to the association count of the abnormal physical sign YTJ z and the treatment plan AQI s , according to all abnormal physical signs YTJ zData to obtain abnormal physical signs YTJ z And treatment plan AQI s Exclusive association count NUM z ; Obtain treatment plan AQI s And chronic disease M i Exclusive association score .

[0011] Among them, obtain the association score between chronic disease M i And its associated diseases. The higher the association score, the greater the impact of the associated disease on the abnormal risk of the chronic disease. When pushing the push strategy plan, preferentially select the treatment plan that can take both sides into account.

[0012] Among them, obtain the exclusive association score between chronic disease M i And the treatment plan of its exclusive disease. The higher the exclusive association score, the greater the impact of the treatment plan on the abnormal risk of the chronic disease. When pushing the treatment plan, preferentially select the plan with a lower exclusive association score.

[0013] The beneficial effects achieved by this application are as follows: This application is for the application of the intelligent health management method and system for chronic disease patients, realizing comprehensive and efficient management of chronic diseases. This application can monitor the patient's vital signs in real time, and through algorithm analysis, timely capture abnormal indicators while warning of potential health crises in advance, helping doctors more accurately evaluate the disease progress and adjust the treatment plan, truly achieving "early detection, early intervention". Patients can use health management devices to scientifically set goals, make plans, and conduct self-monitoring and adjustment according to their own health conditions. This active participation management mode can greatly enhance the patient's self-management ability and promote the effective control of chronic diseases.

[0014] In addition, this application can comprehensively consider the evaluation of the association degree of associated diseases associated with the onset of chronic diseases and the evaluation of the exclusive association degree of exclusive diseases with treatment offset effects for chronic diseases, allocate corresponding comorbidity treatment strategies, reasonably avoid risk plans, and give optimized solutions. Description of the Drawings

[0015] In order to more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in this application. For those skilled in the art, other drawings can also be obtained according to these drawings.

[0016] Figure 1 It is the step flow chart of the intelligent health management system for chronic disease patients of this application. Detailed Embodiments

[0017] Combined with the accompanying drawings in the embodiments of the present application, the technical solutions in the embodiments of the present application are clearly and completely described. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application. It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above accompanying drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0018] The present application provides an intelligent health management system for chronic disease patients, including a physical sign abnormality module, a comorbidity association module, and a comorbidity exclusion association module; The physical sign abnormality module includes a monitoring module and an abnormality module. The monitoring module can collect physical sign data at a set frequency, and the abnormality module can judge the abnormal risk situation of chronic diseases based on the collected physical sign data. When it is judged that a chronic disease has an abnormal risk, the abnormal physical sign data of the chronic disease is obtained; The comorbidity association module includes associated diseases that are associated with the onset of chronic diseases, obtains the association degree between the chronic diseases with abnormal risks and their associated diseases, and assigns corresponding comorbidity treatment strategies according to the association degree; The comorbidity exclusion association module includes exclusion diseases that have a treatment offset effect on chronic diseases, obtains the exclusion association degree between the chronic diseases with abnormal risks and their exclusion diseases, and assigns corresponding comorbidity treatment strategies according to the exclusion association degree.

[0019] Specifically, in some embodiments of the present application, the system provides health management for n types of chronic diseases M, M = [M1, M2, M3,..., M n , where the monitoring module is set to monitor p types of physical sign categories IT for the i-th type of chronic disease M i , IT = [IT1, IT2, IT3,..., IT p , where the monitoring frequency of the monitoring module for the j-th type of physical sign IT j is θ; Set the j-th type of physical sign IT jThe monitoring standard threshold for it is UJ0, where the monitoring standard threshold is set according to the patient's personal health characteristics, and the personal health characteristics include age, gender, height, weight, medical history and medical records. Based on the above personal health characteristics, the physical sign IT can be set for the patient through a data model j The monitoring standard threshold UJ0 of it. For example, due to differences in age and medical history, the normal blood pressure of a normal adult is generally between 90 - 139 mmHg, but if the patient is an 85-year-old elderly person with a history of hypertension who has been taking antihypertensive drugs all year round, it is more appropriate to set the monitoring standard threshold UJ0 to 80 - 150 mmHg.

[0020] Monitor the physical sign IT at the monitoring frequency θ j and obtain the monitoring value UJ of the physical sign IT at the monitoring time TH j h When the monitoring value UJ h exceeds the range of the standard threshold UJ0, this monitoring is regarded as an abnormal node of the physical sign IT j Record the monitoring value UJ h as the abnormal value of the abnormal node, record the difference between the monitoring value UJ h and the monitoring standard threshold UJ0 as the node amplitude of the abnormal node, and set the amplitude threshold △U0 of the physical sign IT j ; Based on the data obtained by the monitoring module, the abnormal module judges the abnormal risk of chronic diseases. Among them, it is known that the physical sign IT j includes b abnormal monitoring nodes Q, Q = [Q1, Q2, Q3,..., Q b , where the node amplitude corresponding to the hth abnormal monitoring node Q h is △U h ; Obtain the abnormal amplitude δ j of the physical sign IT j = ; Based on the amplitude threshold △U0 of the physical sign IT j , obtain the abnormal deviation degree j of the physical sign IT ; When ρ j ≥ ρ0, regard the physical sign IT j as the abnormal physical sign of the chronic disease M i ; Obtain d abnormal physical signs of the chronic disease M i and establish an abnormal physical sign list YTJ = [YTJ1, YTJ2, YTJ3,..., YTJ d ​], the order of the list expresses the dominant role in the risk of this chronic disease, among which the zth abnormal sign YTJ z The degree of abnormal deviation is ρ z .

[0021] According to chronic disease i p types of signs that need to be monitored IT, get chronic disease M i The total abnormality of i = ; According to chronic disease i The abnormality threshold ε0, when the chronic disease M i The total abnormality of i When ≥ε0, it is judged that the chronic disease M i If there is a risk of abnormal deterioration, the system should alert the patient to the condition and display a list of abnormal signs to the patient, prompting the patient to adopt healthy diets and medication methods that can alleviate the above signs. For example, the patient monitored blood pressure, heart rate, blood sugar, blood oxygen and other signs on September 12. According to the monitoring data, the system judged that the risk of chronic disease "heart disease" was abnormal. At this time, the system alerted the user, indicating that the risk of "heart disease" was on the rise, and displayed a list of abnormal signs of this risk to the patient, with blood pressure and blood sugar ranked first and second respectively, and showing that the blood pressure values ​​on September 7, September 9, September 10 and September 12 were all too high, and the blood sugar values ​​on September 7, September 9 and September 11 were all too high. In other words, the risk abnormality this time was mainly caused by the abnormality of these two signs, and the corresponding healthy diet strategy, exercise strategy and drug improvement strategy were prompted at the same time.

[0022] In the comorbidity association module, set i The chronic diseases associated with the occurrence of M i The associated disease, set M i The associated disease PI includes b types, PI = [PI1, PI2, PI3, ..., PI b ], where the kth associated disease is PI k , chronic disease M i PI k The correlation coefficient is R ki ; Setting up the Pi k f types of signs of category KT need to be monitored, including M i m kinds of abnormal signs; According to chronic disease i The zth abnormal sign YTJ among the d abnormal signs YTJ z The degree of abnormal deviation ρ z , obtain PI kThe association score with M i ; ; Obtain the association scores corresponding to all associated diseases according to the above method. The higher the association score, the greater the impact of the associated disease on the abnormal risk of chronic diseases. When pushing the treatment strategy plan, a treatment plan that can take into account both parties should be preferred, or a plan for simultaneous treatment should be selected.

[0023] According to medical data, there are often significant associations between hypertension, diabetes, and coronary heart disease among chronic diseases, which may be related to the common pathophysiological mechanisms of these diseases. In addition, there is also a high comorbidity rate between chronic obstructive pulmonary disease (COPD) and arthritis, which may be related to the lifestyle and environmental factors of the elderly. There is a mutually promoting effect among these chronic diseases. For example, the vascular lesions in diabetic patients can promote the occurrence of cardiovascular diseases, and the long-term hypoxia state in patients with chronic obstructive pulmonary disease may also lead to the occurrence of cardiovascular diseases. Therefore, these associated diseases are recorded as associated diseases in the system. Specifically, in one implementation, among the multiple chronic diseases monitored by the patient, there are "heart disease", "arthritis", and "diabetes". The risk of occurrence of "heart disease" is abnormal this time. Since "diabetes" and "heart disease" are associated diseases, the degree of correlation between the two for this risk is evaluated. If the obtained evaluation score exceeds the association baseline score, it indicates that the abnormality of "heart disease" this time is very likely related to "diabetes". Therefore, the risk-associated diseases need to be shown to the patient, and a healthy diet plan and drug combination plan are given for multiple risk-associated diseases.

[0024] In the comorbidity repulsion association module, set the chronic disease M i with a treatment offset effect on the i-th type of chronic disease as the repulsion disease QI of M i . Set the repulsion disease QI of M i to include c types, QI = [QI1, QI2, QI3,..., QI c , where the r-th type of repulsion disease with a treatment offset effect on M i is QI r .

[0025] Set the treatment plan AQI of QI r to have g types, where the treatment effect time period △st of the s-th treatment plan AQI s is [t, t + △T], where t is the occurrence time of the treatment plan and △T is the duration of the treatment plan effect.

[0026] According to the abnormal sign list YTJ = [YTJ1, YTJ2, YTJ3,..., YTJ d , obtain the time point TZ of the z-th abnormal sign YTJ z ; Whenever TZ ∈ △st occurs, the abnormal physical sign YTJ z and the treatment plan AQI s associated count is incremented by 1. Based on all the data of the abnormal physical signs YTJ z , the exclusive association count NUM z between the abnormal physical sign YTJ s and the treatment plan AQI z is obtained; The exclusive association score FW s between the treatment plan AQI i and the chronic disease M i is obtained; ; According to the above method, the exclusive association scores corresponding to g treatment plans AQI of QI r are obtained. The higher the exclusive association score, the greater the impact of the treatment plan on the abnormal risk of chronic diseases. When implementing the push of the comorbidity strategy, it is recommended to preferentially select the treatment plan with a lower exclusive association score.

[0027] Specifically, in one embodiment, among the multiple chronic diseases monitored by the patient, there are "hypertension" and "diabetes". Since the treatment plan for "hypertension" (antihypertensive drugs) contains beta-blockers and diuretics, it may cause a decrease in insulin sensitivity, inhibit the release and metabolism of insulin after medication, and thus lead to an increase in blood sugar. Therefore, "hypertension" is set as the exclusive disease of "diabetes". When it is found through monitoring and calculation that the risk of "diabetes" in the patient is abnormal, it is necessary to calculate the exclusive association score between "diabetes" and its exclusive disease "hypertension". During the calculation process, according to the time when the patient takes antihypertensive drugs and the efficacy time of the antihypertensive drugs, whenever the abnormal physical sign of "diabetes", "hyperglycemia", occurs within the antihypertensive efficacy time, the exclusive association count is incremented by 1 time to obtain the total count, and then the exclusive association score is calculated.

[0028] Furthermore, the present invention also provides a computer-readable storage medium, which includes a stored program. Among them, when the program runs, it executes the method described in the above method embodiment.

[0029] Furthermore, the present invention also provides an electronic device, which includes a memory and a processor. A computer program is stored in the memory, and the processor is configured to execute the method described in the above method embodiment through the computer program.

[0030] Furthermore, it should be understood that since the setting of each module is only to illustrate the functional units of the device of the present invention, the physical devices corresponding to these modules can be the processor itself, or a part of the software in the processor, a part of the hardware, or a part of the combination of software and hardware. Therefore, the number of each module in the figure is only illustrative.

[0031] Those skilled in the art can understand that all or part of the processes in the methods of the above embodiments of the present invention can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable storage medium can include: any entity or device, medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal, and software distribution medium that can carry the computer program code, etc.

[0032] The computer device can be a terminal. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is implemented by network, NFC (Near Field Communication) or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0033] Those skilled in the art can understand that the various modules in the device can be adaptively split or combined. Such splitting or combination of specific modules will not cause the technical solution to deviate from the principle of the present invention. Therefore, the technical solutions after splitting or combination will all fall within the protection scope of the present invention.

Claims

1. An intelligent health management system for chronic disease patients, characterized in that, It includes a physical sign abnormality module, a comorbidity association module, a comorbidity exclusion association module, and a strategy module; The physical sign abnormality module includes a monitoring module and an abnormality module. The monitoring module can collect physical sign data, and the abnormality module can judge the abnormal risk situation of chronic diseases based on the collected physical sign data. When it is judged that a chronic disease has an abnormal risk, the abnormal physical sign data of the chronic disease is obtained; The comorbidity association module includes associated diseases that are associated with the onset of chronic diseases, and obtains the association degree between the chronic disease with abnormal risk and its associated diseases; The comorbidity exclusion association module includes exclusion diseases that have a treatment offset effect on chronic diseases, and obtains the exclusion association degree between the chronic disease with abnormal risk and its exclusion diseases; The strategy module allocates corresponding comorbidity treatment strategies according to the association degree between the chronic disease with abnormal risk and its associated diseases and the exclusion association degree with its exclusion diseases.

2. The intelligent health management system for chronic disease patients according to claim 1, wherein, The monitoring standard threshold is set according to the patient's personal health characteristics. When the monitoring value exceeds the monitoring standard threshold, this monitoring is regarded as an abnormal node of the physical signs; the personal health characteristics include age, gender, height, weight, medical history, and medical records.

3. The intelligent health management system for chronic disease patients according to claim 2, wherein, The monitoring value is recorded as the abnormal value of the abnormal node, and the difference between the monitoring value and the monitoring standard threshold is recorded as the node amplitude of the abnormal node. According to the data of the abnormal node and the amplitude threshold of the physical signs, a list of abnormal physical signs of the chronic disease is obtained. When it is judged that a chronic disease has an abnormal risk, a risk alarm is sent to the patient and the list of abnormal physical signs is displayed.

4. A method of using the intelligent health management system for chronic disease patients as described in claims 1-3, characterized in that the steps It includes: S1, the system provides health management for n types of chronic diseases M, M = [M1, M2, M3, …, M n , where the monitoring module is set to monitor the physical sign categories IT of the i-th type of chronic disease M i including p kinds, IT = [IT1, IT2, IT3, …, IT p , where the monitoring frequency of the j-th type of physical sign IT j is θ; the monitoring standard threshold of the j-th type of physical sign IT j is set to UJ0; S2, obtain the physical sign IT j of the monitored value UJ h , when the monitored value UJ h exceeds the standard threshold UJ0 range, regard this monitoring as an abnormal node of the physical sign IT j , record the monitored value UJ h as the abnormal value of the abnormal node, record the difference between the monitored value UJ h and the monitoring standard threshold UJ0 as the node amplitude of the abnormal node, and set the amplitude threshold △U0 of the physical sign IT j ; S3, Set the physical sign IT j It includes b abnormal monitoring nodes Q, Q = [Q1, Q2, Q3, …, Q b , where the node amplitude corresponding to the h-th abnormal monitoring node Q h is △U h , Obtain physical sign IT j Abnormal amplitude δ j = ; S4, according to the amplitude threshold ΔU0 of the physical sign IT j obtain the abnormal deviation degree of the physical sign IT j ; ; When ρ j ≥ ρ0, the physical sign IT j is taken as the abnormal physical sign of the chronic disease M i ; S5, obtain chronic disease M i of d kinds of abnormal signs, and establish an abnormal sign list YTJ = [YTJ1, YTJ2, YTJ3, …, YTJ d , where the abnormal deviation degree of the z-th abnormal sign YTJ z is ρ z ; S6, according to chronic disease M i The p types of physical sign categories IT to be monitored, obtain the total abnormality degree ε i of chronic disease M i = ; S7, set the abnormality degree threshold ε0 of chronic disease M. When the total abnormality degree ε of the obtained chronic disease M i ≥ ε0, it is determined that the chronic disease M i has an abnormal risk; i i ​​ S8, set up with M i The chronic disease with onset relevance is M i 's associated disease, set up M i 's associated disease PI includes b types, PI = [PI1, PI2, PI3, …, PI b , where the k-th type of associated disease is PI k , set up the chronic disease M i and the associated disease PI k 's correlation coefficient is R ki , obtain PI k and M i 's association score F ki ; According to the obtained association score F ki Execute the corresponding comorbidity strategy; S9, set to be related to M i The chronic disease with a treatment offset effect is M i For the disease repulsion related to M, set M i There are c types of disease repulsion QI related to M, QI = [QI1, QI2, QI3,..., QI c r], where the r-th type of disease repulsion is QIr r , set QI r There are g types of treatment plans AQI for QI, AQI = [AQI1, AQI2, AQI3,..., AQI g g], where the s-th treatment plan is AQIs s The treatment effect time period △st = [t, t + △T] of the treatment plan AQIs, where t is the treatment occurrence time and △T is the treatment effect duration; obtain the treatment plan AQIs s and the chronic disease M i the repulsion correlation score FW i ; According to the obtained repulsion correlation score FW i Execute the corresponding comorbidity strategy.

5. The method of the intelligent health management system for chronic disease patients according to claim 4, characterized in that, Step S8 includes: setting PI k It is necessary to monitor f types of physical sign categories KT, and m abnormal physical signs are included in the physical sign category KT i ; according to the m abnormal physical signs of chronic disease M i The z-th abnormal physical sign YTJ among the d abnormal physical signs YTJ of z The abnormal deviation degree ρ z , PI is obtained k The correlation score with M i .​ 6. The method of the intelligent health management system for chronic disease patients according to claim 4, characterized in that, Step S9 includes: according to the list of abnormal signs YTJ = [YTJ1, YTJ2, YTJ3,..., YTJ d , obtaining the time point TZ of the z-th abnormal sign YTJ z ; whenever TZ ∈ △st occurs, incrementing the association count of the abnormal sign YTJ z with the treatment plan AQI s by 1, and obtaining the exclusion association count NUM z of the abnormal sign YTJ z with the treatment plan AQI s based on the data of all abnormal signs YTJ z ; Obtain treatment plan AQI s and chronic disease M i repulsion correlation score .

7. The method of the intelligent health management system for chronic disease patients according to claim 5, characterized in that Obtaining Chronic Disease M i The association score with its associated disease. The higher the association score, the greater the impact of the associated disease on the abnormal risk of the chronic disease. When pushing the treatment strategy plan, a treatment plan that can take both into account is preferably selected.

8. The method of the intelligent health management system for chronic disease patients according to claim 6, wherein, Obtaining chronic disease M i The anti-correlation score of the treatment plan for the anti-disease. The higher the anti-correlation score, the greater the impact of the treatment plan on the abnormal risk of chronic diseases. When pushing treatment plans, give priority to selecting plans with lower anti-correlation scores.

Images