Alzheimer's disease intelligent follow-up visit management method and system

Abstract

The invention relates to the technical field of health management, in particular to an intelligent follow-up visit management method and system for Alzheimer's disease, and the method comprises the steps: collecting physiological characteristic attribute features of a plurality of aspects of behaviors and physiological characteristics of a patient; receiving the Alzheimer's disease correlation degree of the physiological characteristic attribute characteristics in different aspects, and outputting an Alzheimer's disease risk assessment result in combination with the aspect number of patient behaviors; outputting gene characteristics of the physiological characteristics based on the associated conditions of the physiological characteristics; receiving associated behavior information of the to-be-associated patient behavior based on the gene characteristics of the physiological characteristics and the difference between the physiological characteristic attribute characteristics of the physiological characteristics and the physiological characteristic attribute characteristics of the to-be-associated patient behavior, and outputting a forgetting prediction sequence of the to-be-associated patient behaviors in combination with the occurrence frequency deviation so as to perform sequential forgetting prediction on the to-be-associated patient behaviors. According to the invention, the abnormal forgetting assessment can be carried out from the aspect of combining the source with the congenital gene and the acquired environment, so that the Alzheimer's disease of the patient is controlled.

Description

Technical Field

[0001] The present invention relates to the field of health management technology, and in particular to an intelligent follow-up management method and system for Alzheimer's disease. Background Art

[0002] Alzheimer's disease (AD) is a progressive neurodegenerative disease characterized by cognitive decline, behavioral abnormalities, and decreased ability to function. With the accelerating global aging population, the number of AD patients continues to grow, placing a heavy burden on families and society. Currently, the clinical management of AD faces the following key challenges: There is insufficient integration of multi-dimensional data, lack of dynamic risk assessment, delayed personalized intervention, blank gene-behavior association analysis, bottlenecks in real-time data processing, and low efficiency of traditional methods in processing multi-source heterogeneous data (such as physiological indicators collected by wearable devices and electronic medical record data).

[0003] In response to the above problems, the present invention proposes an intelligent follow-up management method, which achieves technical breakthroughs through the following innovations: Construct a multi-dimensional feature fusion model, integrate behavioral, physiological and genetic data, develop a dynamic correlation evaluation algorithm, quantify the real-time correlation between behavioral characteristics and AD progression, design a personalized intervention mechanism based on the forgetting prediction sequence, establish a gene-behavioral feature mapping relationship, achieve accurate risk assessment, and use multi-level response linked list technology to improve real-time data processing efficiency. Summary of the Invention

[0004] To achieve the above object, the present invention provides the following technical solutions: According to a first aspect of the present invention, the present invention claims protection for an intelligent follow-up management method for Alzheimer's disease, the method comprising the following steps: Collect physiological attribute characteristics of multiple aspects of each patient's behavior and physiological characteristics; receiving the Alzheimer's disease correlations of different aspects of physiological trait attribute characteristics; outputting the Alzheimer's disease risk assessment results of each patient behavior based on the Alzheimer's disease correlations of the different aspects of physiological trait attribute characteristics and the number of aspects of each patient behavior; Outputting the gene characteristics of each physiological trait based on the associated conditions of each physiological trait; receiving the associated behavior information of each patient behavior to be associated based on the difference between the gene characteristics of each physiological trait and the physiological trait attribute characteristics of each physiological trait and the physiological trait attribute characteristics of each patient behavior to be associated; outputting a predicted forgetting order of each patient behavior to be associated based on associated behavior information and occurrence frequency deviation of each patient behavior to be associated; Based on the forgetting prediction order of each patient behavior to be associated, sequential forgetting prediction is performed on each patient behavior to be associated.

[0005] Furthermore, the physiological attribute characteristics of various aspects of each patient's behavior and physiological characteristics are collected, including the following specific steps: The original indicators and occurrence frequencies of various physiological traits and various patient behaviors in the real-time forgetting prediction network are collected; each indicator in the original indicators of various physiological traits and various patient behaviors is used as an aspect to constitute multiple behavioral features, and the multiple behavioral features of all physiological traits and patient behaviors are normalized using the range normalization algorithm, and the physiological trait attribute features of multiple aspects of each patient behavior and each physiological trait are received.

[0006] Furthermore, receiving the correlation between different aspects of physiological characteristics and attributes of Alzheimer's disease includes the following specific steps: All physiological trait attribute features are input into the trained deep learning model to collect the correlation between various aspects of the patient's behavior and Alzheimer's disease.

[0007] Furthermore, based on the correlation degree and number of aspects of physiological trait attribute characteristics, the Alzheimer's disease risk assessment results of each patient's behavior are output. The specific steps include the following: , Where, represents the Alzheimer's disease risk assessment result of the kth patient behavior; The number of aspects representing the physiological trait attributes of the kth patient's behavior; represents the Alzheimer's disease relevance of the i-th aspect of the physiological trait attribute characteristics of the k-th patient's behavior; Represents the i-th aspect data of the physiological characteristic attribute characteristics of the k-th patient's behavior; The number of all key behavioral features representing the behavior of the kth patient.

[0008] Furthermore, based on the correlation of each physiological trait, the gene signature of each physiological trait is outputted, including the following specific steps: , Where, represents the genetic characteristics of the jth physiological trait; represents the number of parsed genes for the jth physiological trait; This represents the Alzheimer's disease risk assessment result for the g-th patient behavior in the analyzed gene for the j-th physiological trait.

[0009] Furthermore, the specific method for collecting the number of analyzed genes is as follows: The number of patient behaviors to be analyzed and being analyzed for each physiological trait is counted and recorded as the number of analyzed genes for each physiological trait.

[0010] Furthermore, receiving the associated behavior information of each patient behavior to be associated includes the following specific steps: , Where, represents the genetic characteristics of the jth physiological trait; represents the Alzheimer's disease risk assessment result of the d-th patient behavior to be associated; represents the associated behavior information of the dth patient behavior to be associated; n represents the number of physiological traits; f(x) is a non-negative function; represents the data mean of all aspects of the physiological trait attribute characteristics of the jth physiological trait; Represents the data mean of all aspects of the physiological trait attribute characteristics of the d-th patient behavior to be associated.

[0011] Furthermore, based on the associated behavior information and occurrence frequency of each patient behavior to be associated, the forgetting prediction order of each patient behavior to be associated is output, and the specific steps included are as follows: , represents the forgetting prediction order of the dth patient behavior to be associated, represents the association order feature of the d-th patient behavior to be associated, Represents the difference between the real-time frequency and the occurrence frequency of the d-th patient behavior to be associated.

[0012] Furthermore, based on the forgetting prediction order of each patient behavior to be associated, each patient behavior to be associated is processed, including the following specific steps: Based on the multi-level response linked list forgetting prediction algorithm, several preparation linked lists are created, and the number and length of the linked lists are set; the patient behaviors to be associated are associated to each preparation linked list from high to low according to the forgetting prediction order of each patient behavior, and the time-sharing technology in the multi-level response linked list forgetting prediction algorithm is used to associate the frequency slices from short to long to each preparation linked list, and sequential forgetting prediction is performed on different patient behaviors based on the response linked list forgetting prediction algorithm.

[0013] According to the second aspect of the present invention, the present invention seeks protection for an intelligent follow-up management system for Alzheimer's disease, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the computer program implements the steps of an intelligent follow-up management method for Alzheimer's disease when executed by the processor.

[0014] The present invention relates to the field of health management technology, and in particular to an intelligent follow-up management method and system for Alzheimer's disease, which collects physiological trait attribute characteristics of multiple aspects of patient behavior and physiological traits; receives the Alzheimer's disease correlation of physiological trait attribute characteristics of different aspects, and outputs Alzheimer's disease risk assessment results in combination with the number of aspects of patient behavior; outputs the genetic characteristics of physiological traits based on the associated situation of physiological traits; based on the difference between the genetic characteristics of physiological traits and the physiological trait attribute characteristics of physiological traits and the physiological trait attribute characteristics of the patient behavior to be associated, receives the associated behavior information of the patient behavior to be associated, and outputs the forgetting prediction sequence of the patient behavior to be associated in combination with the occurrence frequency deviation, thereby performing sequential forgetting prediction on the patient behavior to be associated. The present invention can evaluate forgetting abnormalities from the source by combining the aspects of innate genes and acquired environment, and thus control the patient's Alzheimer's disease. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flow chart of an intelligent follow-up management method for Alzheimer's disease claimed in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments accepted by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0017] The terms "first," "second," and "third" in this disclosure are used for descriptive purposes only and should not be construed as indicating or implying a relative degree of relevance to Alzheimer's disease or implicitly specifying the number of technical features identified. Therefore, features identified as "first," "second," or "third" may explicitly or implicitly include at least one such feature. In the description of this disclosure, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined. All directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of this disclosure are intended only to illustrate the relative positional relationships and movement of components in a specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications will also change accordingly. Furthermore, the terms "including," "having," and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements, but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0018] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0019] The specific scheme of the intelligent follow-up management method and system for Alzheimer's disease provided by the present invention is described in detail below with reference to the accompanying drawings.

[0020] See also Figure 1 , which shows a flowchart of a method for intelligent follow-up management of Alzheimer's disease provided by one embodiment of the present invention, the method comprising the following steps: Step S001: Acquire physiological trait attribute characteristics of various physiological traits and physiological trait attribute characteristics of various patient behaviors.

[0021] The purpose of this embodiment is to achieve automated forgetting prediction of massive amounts of data by optimizing the forgetting prediction configuration of physiological characteristics for different patient behaviors in the forgetting prediction network. Therefore, the original indicators and occurrence frequencies of each physiological characteristic and each patient behavior in the real-time forgetting prediction network are collected. Other embodiments may select other indicators as original indicators, and this embodiment does not specifically limit them. Each indicator in the original indicators of each physiological characteristic and each patient behavior is used as an aspect to constitute multiple behavioral features. The multiple behavioral features of all physiological characteristics and patient behaviors are normalized using the range normalization algorithm, and the physiological characteristic attribute characteristics of multiple aspects of each patient behavior and each physiological characteristic are received.

[0022] Furthermore, the number of patient behaviors to be analyzed and being analyzed for each physiological trait is counted and recorded as the number of analyzed genes for each physiological trait.

[0023] Step S002: receiving the Alzheimer's disease correlation of different physiological trait attribute characteristics based on the normalized multidimensional physiological trait attribute characteristics; outputting the Alzheimer's disease risk assessment result of each patient behavior based on the Alzheimer's disease correlation and the number of aspects of the different physiological trait attribute characteristics.

[0024] It should be noted that when realizing automated forgetting prediction for massive data processing, the core lies in processing the configuration forgetting prediction problem of physiological characteristics and patient behavior. In order to maximize processing efficiency and reduce the blocking of parsing resources caused by excessive patient behavior data, in the process of optimizing forgetting prediction of the parsing order, it is necessary to analyze the order of patient behavior in combination with the Alzheimer's disease risk assessment results of different patient behaviors.

[0025] Among the multiple behavioral characteristics related to physiological trait attributes, the forgetting information represented by different aspects of the data in the multiple behavioral characteristics has different relevance to the patient's behavior for Alzheimer's disease. Therefore, to analyze the Alzheimer's disease risk assessment results of different patient behaviors, it is first necessary to evaluate the relevance of different aspects of the physiological trait attributes in each patient's behavior to the real-time patient behavior for Alzheimer's disease. Then, based on the differences between the different aspects of the physiological trait attributes and the different aspects of the physiological trait attributes of the patient's behavior, as well as the amount of data on forgetting needs, analyze the Alzheimer's disease risk assessment results of the patient's behavior. For patient behaviors with massive amounts of data, calculating their Alzheimer's disease risk assessment results solely based on their forgetting needs ignores the impact of data volume on the analysis process, so the Alzheimer's disease risk assessment results of the patient's behavior also need to be analyzed in combination with the size of the data.

[0026] In this embodiment, physiological characteristics include at least: physical characteristics, appearance characteristics and natural reactions; Among the physical characteristics mentioned above, those with a higher degree of correlation with Alzheimer's disease include the effects of exercise on weight loss and difficulty in deep sleep; Among the physical characteristics, those with a higher correlation with Alzheimer's disease include BMI index and genetic height; Characteristics of natural responses that were more strongly associated with Alzheimer's disease included pain sensitivity; Specifically, in the embodiments of the present invention: Example 1: Multi-dimensional data collection and feature extraction; Data collection: The patients' daily physiological indicators were collected through a smart bracelet: sleep duration (6.5±1.2h), resting heart rate (72±5bpm), and number of steps (3520±1200 steps); Behavioral characteristics were recorded using home monitoring equipment: number of repeated questions (3.2 ± 1.5 times / day), incidents of misplacing items (1.8 ± 0.7 times / day); Genetic testing data: APOE-ε4 carrier status (ε3 / ε4), BDNF Val66Met polymorphism Feature normalization processing: Using the range normalization algorithm: For example, the daily step count [800, 6000] is mapped to the interval [0, 1]; Example 2: Deep learning correlation evaluation; Model construction: Use a 3D-CNN network architecture (input layer → 3 convolutional blocks → LSTM layer → fully connected layer); Training data: Multimodal data of 500 patients in the ADNI database; Output the correlation degree of each feature: sleep fragmentation: 0.72 (strong association); Spatial navigation error: 0.68; Short-term memory test: 0.65; Example 3 Multi-level linked list prediction system System Configuration: Processor: Intel Xeon Gold 6248R Memory: 128GB DDR4 Storage: 2TB NVMe SSD Prediction process: Python: # Create a three-level response list chain_levels = [ {"length": 10, "interval": 1h}, # High frequency behavior {"length": 30, "interval": 6h}, # IF behavior {“length”: 50, “interval”: 24h} # Low-frequency behavior ]; # Behavior prediction sorting prediction_order = { “Repeated questions”: 0.82, "Time and space confusion": 0.79, "Personal hygiene negligence": 0.68 } Example 4: Clinical validation; Experimental Design: Participants: 100 patients with MCI (MMSE 20-26 points) Control group: traditional questionnaire follow-up Experimental group: This system management The results are shown in Table 1; Table 1 Experimental results

[0027] Example 5: System interface implementation; Doctor's panel: Real-time risk heat map: displays the risk value of each behavior using HSV color space; Prediction trajectory curve: shows the probability of cognitive decline in the next 3 months; Emergency warning module: triggers a red alarm when the R value > 0.8; Patient-side APP: Daily cognitive training reminders; Vibration prompt for abnormal behavior; Family sharing report generation; This example demonstrates that the system can achieve: The accuracy of early risk identification increased by 37.2%; The speed of generating personalized intervention plans increased by 8 times; Medical resource consumption decreased by 42.5%; This causes the body's adrenaline levels to remain relatively high, making it more sensitive to stimuli such as pain.

[0028] Specifically, all physiological trait attribute features are input into the trained deep learning model to collect the Alzheimer's disease correlation of various aspects of the patient's behavior; the deep learning model used in this embodiment is DNN deep learning, and the method for collecting the data set for training the deep learning is: collecting a number of historical physiological trait attribute features, and scoring each historical physiological trait attribute feature by manual scoring, and the score values ​​are preset as: 0.1, 0.2, 0.3, ... 1, a total of 10 score types, corresponding to 10 Alzheimer's disease correlation levels; the historical physiological trait attribute features and their corresponding score values ​​constitute a data set; the deep learning is trained using the data set, and the loss function used in the training process is the cross entropy function; the specific training process is a well-known content of deep learning, and the specific training process will not be repeated in this embodiment.

[0029] Then the Alzheimer's disease risk assessment result of the kth patient behavior in the forgetting prediction network is calculated as: , Where, represents the Alzheimer's disease risk assessment result of the kth patient behavior; The number of aspects representing the physiological trait attributes of the kth patient's behavior; represents the Alzheimer's disease relevance of the i-th aspect of the physiological trait attribute characteristics of the k-th patient's behavior; Represents the i-th aspect data of the physiological characteristic attribute characteristics of the k-th patient's behavior; The number of all key behavioral features representing the behavior of the kth patient.

[0030] By normalizing the Alzheimer's disease correlation q of different aspects of physiological trait attribute characteristics and using it as the weight, the weighted mean of the real-time patient behavior corresponding to the forgetting demand is calculated. The larger the value, the higher the real-time patient behavior's requirements for analytical resources, and the greater the corresponding Alzheimer's disease risk assessment result. It represents the product of the weighted mean of forgetting demand and the amount of real-time patient behavior data. The larger the value, the greater the impact of the data volume on the analysis process, and the greater the Alzheimer's disease risk assessment result.

[0031] Step S003: outputting the gene characteristics of each physiological trait based on the associated status of each physiological trait; receiving the associated behavior information of each patient behavior to be associated based on the gene characteristics and physiological trait attribute characteristics of each physiological trait and the physiological trait attribute characteristics of each patient behavior to be associated.

[0032] It should be noted that when optimizing the forgetting prediction process of the forgetting prediction network and achieving automated forgetting prediction, after collecting the Alzheimer's disease risk assessment results for each patient's behavior, the physiological trait information and transport status in the real-time forgetting prediction network should also be combined to determine the applicability of the physiological traits to the patient's behavior. The physiological trait attribute characteristics that are suitable for the physiological characteristics of the patient's behavior should not be lower than the physiological trait attribute characteristics proposed in the patient's behavior. To avoid wasting resources, physiological traits should be associated with patient behaviors that match their physiological trait attribute characteristics as much as possible. Therefore, it is necessary to combine the physiological traits and patient behavior information in the forgetting prediction network to comprehensively analyze the correlation order characteristics of different patient behaviors.

[0033] Specifically, the genetic characteristics of the jth physiological trait are calculated as follows: , The calculation method of the associated behavior information of the d-th patient behavior to be associated is: , Where, represents the genetic characteristics of the jth physiological trait; represents the number of parsed genes for the jth physiological trait; represents the Alzheimer's disease risk assessment result of the d-th patient behavior to be associated; The Alzheimer's disease risk assessment result of the g-th patient behavior in the parsed gene of the j-th physiological trait; represents the associated behavior information of the dth patient behavior to be associated; n represents the number of physiological characteristics; f(x) is a non-negative function, where x is the input of the non-negative function. When the input is a non-negative number, the output is , where the The model only shows negative correlation and the output of the constraint model is in In the interval, As the input of this model, it can be replaced by other models with the same purpose in specific implementation. This embodiment is just based on The model is used as an example for description without any specific limitation. represents the data mean of all aspects of the physiological trait attribute characteristics of the jth physiological trait; Represents the data mean of all aspects of the physiological trait attribute characteristics of the d-th patient behavior to be associated.

[0034] Represents the mean of the Alzheimer's disease risk assessment results of the patient behavior associated with the jth physiological trait. The larger the mean, the greater the carrying burden of the jth physiological trait and the greater the genetic characteristics of the jth physiological trait. For a patient's behavior, the more suitable physiological traits there are, the more obvious their correlation order characteristics should be in order to improve the operating efficiency of the forgetting prediction network. The non-negative function value representing the difference between the physiological trait attribute feature data of the j-th physiological trait and the physiological trait attribute feature data of the patient behavior to be associated, The smaller the value, the lower the associated behavior information contributed by the jth physiological trait to the dth patient behavior to be associated. The purpose is to reduce the waste of parsing resources. When the jth physiological trait is exactly the same as the forgetting requirement of the dth patient behavior to be associated, The output is the maximum value 1; then This indicates that the more idle the real-time carrying situation of the j-th physiological trait is, the more obvious the correlation order characteristics that the j-th physiological trait can provide are.

[0035] Step S004: outputting the forgetting prediction order of each patient behavior to be associated based on the associated behavior information and the occurrence frequency of each patient behavior to be associated.

[0036] It should be noted that the correlation order characteristics of patient behavior are forgetting prediction characteristics output by combining real-time physiological characteristics and forgetting demand analysis. Finally, it is necessary to analyze the forgetting prediction order of patient behavior in combination with the frequency of occurrence of patient behavior to meet the "first come, first served" principle as much as possible.

[0037] Specifically, the calculation method for the forgetting prediction order of the d-th patient behavior to be associated is: , represents the forgetting prediction order of the dth patient behavior to be associated, represents the association order feature of the d-th patient behavior to be associated, Represents the difference between the real-time frequency and the occurrence frequency of the d-th patient behavior to be associated.

[0038] The larger the value, the more obvious the correlation order characteristics of the forgotten demand are and the earlier the demand appears, the higher the forgetting prediction order of the real-time forgotten demand should be.

[0039] Similarly, receive the forgotten predicted order of all patient behaviors.

[0040] Step S005: Process each patient behavior to be associated based on the forgetting prediction order of each patient behavior to be associated.

[0041] It should be noted that this embodiment uses a multi-level response linked list forgetting prediction algorithm, combined with the forgetting prediction order of patient behavior, to perform forgetting prediction and adjustment on patient behavior in the forgetting prediction network. The specific process is as follows: creating a number of preparation linked lists. Since this number is related to the number of physiological characteristics in the real-time forgetting prediction network, the number of linked lists created in this embodiment is 50, and the length of each linked list is 10. This is described as an example. Other embodiments can set other numbers of linked lists and lengths of linked lists; the patient behavior to be associated is sequentially associated with each preparation linked list from high to low according to the forgetting prediction order of each patient behavior, and the frequency slices from short to long are associated with each preparation linked list using time-sharing technology. Different patient behaviors are processed based on the multi-level response linked list forgetting prediction algorithm. By analyzing different patient behaviors and performing different orders of analysis, automatic forgetting prediction is achieved in the face of massive data processing. It should be noted that the multi-level response linked list forgetting prediction algorithm and time-sharing technology used in this embodiment are well-known technologies and will not be described in detail in this embodiment.

[0042] According to a second embodiment of the present invention, the present invention seeks protection for an intelligent follow-up management system for Alzheimer's disease, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the intelligent follow-up management method for Alzheimer's disease when executed by the processor.

[0043] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0044] In addition, the functional units in the various embodiments of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware or in the form of software functional units. The above is only an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

[0045] The above detailed description of the specific embodiments of the invention is intended to be illustrative only, and the present invention is not limited to the specific embodiments described above. For those skilled in the art, any equivalent modifications or substitutions to the invention are also within the scope of the present invention. Therefore, equivalent changes, modifications, and improvements made without departing from the spirit and scope of the present invention are also encompassed within the scope of the present invention.

Claims

1. An intelligent follow-up management method for Alzheimer's disease, characterized by: The method comprises the following steps: Collect physiological attribute characteristics of multiple aspects of each patient's behavior and physiological characteristics; receiving the Alzheimer's disease correlations of different aspects of physiological trait attribute characteristics; outputting the Alzheimer's disease risk assessment results of each patient behavior based on the Alzheimer's disease correlations of the different aspects of physiological trait attribute characteristics and the number of aspects of each patient behavior; Outputting the gene characteristics of each physiological trait based on the associated conditions of each physiological trait; receiving the associated behavior information of each patient behavior to be associated based on the difference between the gene characteristics of each physiological trait and the physiological trait attribute characteristics of each physiological trait and the physiological trait attribute characteristics of each patient behavior to be associated; outputting a predicted forgetting order of each patient behavior to be associated based on associated behavior information and occurrence frequency deviation of each patient behavior to be associated; Based on the forgetting prediction order of each patient behavior to be associated, sequential forgetting prediction is performed on each patient behavior to be associated.

2. The intelligent follow-up management method for Alzheimer's disease according to claim 1, characterized in that: The specific steps of collecting physiological attribute characteristics of multiple aspects of each patient's behavior and physiological characteristics are as follows: The original indicators and occurrence frequencies of various physiological traits and various patient behaviors in the real-time forgetting prediction network are collected; each indicator in the original indicators of various physiological traits and various patient behaviors is used as an aspect to constitute multiple behavioral features, and the multiple behavioral features of all physiological traits and patient behaviors are normalized using the range normalization algorithm, and the physiological trait attribute features of multiple aspects of each patient behavior and each physiological trait are received.

3. The intelligent follow-up management method for Alzheimer's disease according to claim 1, characterized in that: The receiving of the correlation between physiological characteristics and attributes of different aspects of Alzheimer's disease includes the following specific steps: All physiological trait attribute features are input into the trained deep learning model to collect the correlation between various aspects of the patient's behavior and Alzheimer's disease.

4. The intelligent follow-up management method for Alzheimer's disease according to claim 1, characterized in that: The Alzheimer's disease correlation degree based on the physiological characteristics of different aspects and the number of aspects of each patient's behavior is outputted based on the Alzheimer's disease risk assessment result of each patient's behavior, and the specific steps include the following: ， Where, represents the Alzheimer's disease risk assessment result of the kth patient behavior; The number of aspects representing the physiological trait attributes of the kth patient's behavior; represents the Alzheimer's disease relevance of the i-th aspect of the physiological trait attribute characteristics of the k-th patient's behavior; Represents the i-th aspect data of the physiological characteristic attribute characteristics of the k-th patient's behavior; The number of all key behavioral features representing the behavior of the kth patient.

5. The intelligent follow-up management method for Alzheimer's disease according to claim 1, characterized in that: The specific steps of outputting the gene features of each physiological trait based on the associated conditions of each physiological trait are as follows: ， Where, represents the genetic characteristics of the jth physiological trait; represents the number of parsed genes for the jth physiological trait; This represents the Alzheimer's disease risk assessment result for the g-th patient behavior in the analyzed gene for the j-th physiological trait.

6. The intelligent follow-up management method for Alzheimer's disease according to claim 5, characterized in that: The specific method for collecting the number of analyzed genes is as follows: The number of patient behaviors to be analyzed and being analyzed for each physiological trait is counted and recorded as the number of analyzed genes for each physiological trait.

7. The intelligent follow-up management method for Alzheimer's disease according to claim 1, characterized in that: The receiving of the associated behavior information of each patient behavior to be associated includes the following specific steps: ， Where, represents the genetic characteristics of the jth physiological trait; represents the Alzheimer's disease risk assessment result of the d-th patient behavior to be associated; represents the associated behavior information of the dth patient behavior to be associated; n represents the number of physiological traits; f(x) is a non-negative function; represents the data mean of all aspects of the physiological trait attribute characteristics of the jth physiological trait; Represents the data mean of all aspects of the physiological trait attribute characteristics of the d-th patient behavior to be associated.

8. The intelligent follow-up management method for Alzheimer's disease according to claim 1, characterized in that: The method of outputting the forgetting prediction order of each patient behavior to be associated based on the associated behavior information and the occurrence frequency deviation of each patient behavior to be associated includes the following specific steps: ， represents the forgetting prediction order of the dth patient behavior to be associated, represents the association order feature of the d-th patient behavior to be associated, Represents the difference between the real-time frequency and the occurrence frequency of the d-th patient behavior to be associated.

9. The intelligent follow-up management method for Alzheimer's disease according to claim 1, characterized in that: The sequential forgetting prediction of each patient behavior to be associated is performed based on the forgetting prediction order of each patient behavior to be associated, and the specific steps include the following: Based on the multi-level response linked list forgetting prediction algorithm, several preparation linked lists are created, and the number and length of the linked lists are set; the patient behaviors to be associated are associated to each preparation linked list from high to low according to the forgetting prediction order of each patient behavior, and the time-sharing technology in the multi-level response linked list forgetting prediction algorithm is used to associate the frequency slices from short to long to each preparation linked list, and sequential forgetting prediction is performed on different patient behaviors based on the response linked list forgetting prediction algorithm.

10. An intelligent follow-up management system for Alzheimer's disease, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the computer program is executed by a processor, the steps of the intelligent follow-up management method for Alzheimer's disease as described in any one of claims 1 to 9 are implemented.

Images