Method and system for managing chronic disease follow-up nursing service

Abstract

The invention discloses a chronic disease follow-up visit nursing service management method, and particularly relates to the technical field of follow-up visit nursing service, and the method comprises the steps: obtaining the family address information of a patient, and recommending a follow-up visit path according to the family address information of the patient; according to the relevancy and the adaptation degree of each nursing item, calculating the weight of each nursing item by using a superior sequence diagram; determining the nursing time of each patient and the weight of each nursing item, and determining the nursing scheme with the highest weight as a recommended scheme; recording the nursing item duration, the unnursed items and the weight of the patient, and recording the body data of the patient. When the second follow-up visit is carried out, the nursing items which are not carried out by each patient in the last follow-up visit, the weight sum of the nursing items and the address information of each patient are determined, the follow-up visit path is recommended again for follow-up visit, and comprehensive follow-up visit nursing can be better carried out on the patient within limited time.

Description

Technical Field

[0001] The present invention relates to the technical field of follow-up nursing services, and more specifically, to a management method and system for chronic disease follow-up nursing services. Background Art

[0002] Chronic diseases are one of the major health problems worldwide. Their treatment and management are usually long-term and continuous, involving the participation of patients, medical service providers, family caregivers, etc. In order to improve the treatment effect of chronic disease patients, reduce the occurrence of complications, and optimize the allocation of medical resources, chronic disease follow-up nursing services have become an important means of health management.

[0003] The core goal of the chronic disease follow-up care service management method and system is to ensure that patients can receive treatment on time, control their condition, and improve their quality of life through continuous and regular monitoring, care, and intervention. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a management method and system for chronic disease follow-up nursing services to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A management method for chronic disease follow-up nursing services comprises the following steps:

[0007] Step S1: Obtain the patient's home address information and recommend a follow-up path based on the patient's home address information;

[0008] Step S2: Calculate the weight of each nursing item using a priority diagram according to the relevance and suitability of each nursing item;

[0009] Step S3: Screen out a batch of nursing plans according to the nursing time of each patient and the time taken by each nursing item; determine the weight of each nursing item, sum the weights of the nursing items in each nursing plan, and find the nursing plan with the largest weight as the recommended plan output;

[0010] Step S4: Record the duration of the patient's nursing items, uncared items and weights, and record the patient's physical data.

[0011] In a preferred embodiment, in step S1, a path is planned to connect all patients and the headquarters according to the patient address information and the headquarters location;

[0012] Then filter the paths based on the following criteria:

[0013] The time spent by the nursing staff on the follow-up journey plus the average time of caring for a single patient multiplied by the number of patients on the follow-up path is not greater than the working hours of the nursing staff; the screened path is output as the follow-up path.

[0014] In a preferred embodiment, in step S2, the correlation is calculated based on the historical condition data and each nursing item data: Collect patient symptom change data, compare it with the nursing items in the historical database, and recommend the suitability of each nursing item.

[0015] In a preferred embodiment, in step S2, the relevance and the nursing item suitability are determined and the weight of each nursing item is calculated according to the priority diagram method.

[0016] In a preferred embodiment, in step S3, the nursing time of each patient is determined, the nursing time of the first patient is the average nursing time, which fluctuates up and down by 20% of the average nursing time; the nursing time of the second patient is the total nursing time minus the nursing time of the first patient divided by the number of remaining patients, and the value fluctuates up and down by 20%; specifically, the range of fluctuation can be set according to actual needs; the total nursing time is equal to the working time of the nursing staff minus the travel time to each patient's residence; and so on, the nursing time of each patient is calculated one by one;

[0017] Determine the nursing time for each patient. The nursing time for each nursing item is obtained by averaging the nursing time for each nursing item in history. The nursing items are randomly combined, and the sum of the nursing time of each nursing item in the combination is less than the patient's nursing time.

[0018] Obtain multiple nursing item combinations, determine the nursing items in the combination, calculate the sum of the weights of the nursing items in the combination, and select the combination with the largest sum of weights as the nursing plan.

[0019] In a preferred embodiment, in step S4, after the patient completes the nursing items, the duration of the patient's nursing items, the unnursed items and their weights are recorded, and the patient's physical data is recorded.

[0020] In a preferred embodiment, during the second follow-up, the nursing items that were not performed on each patient during the previous follow-up and their weights and the address information of each patient are determined, and a random forest algorithm is selected to determine the follow-up path; the specific steps are as follows:

[0021] The data set includes the nursing items that each patient did not perform during the last follow-up, their weights and addresses, and the address information of each patient. The data set is set to D, which contains m samples, and each sample j has k features cj1, cj2, cj3...cjk; and the target variable is set to Tj, where Tj is the path label;

[0022] The dataset D is randomly divided into a training set Dtrain and a test set Dtest. The training set is used to build the model, and the test set is used to verify the model. The training set contains p samples, and the test set contains q samples, where p+q=m.

[0023] Construct W decision trees, each tree Uw is constructed independently; for each tree, extract a sample set of size p from the training set Dtrain by bootstrap sampling; at each split node, instead of using all k features, randomly select the square root of k features from the k features to find the best split;

[0024] Each tree Uw generates a model Kw based on its training data; for a given test sample c, each tree Uw will output a prediction result Tw(c);

[0025] Output all tree prediction outputs The average of all tree prediction outputs is taken as the prediction result.

[0026] In a preferred embodiment, the access path is determined, the nursing time of each patient is confirmed, and the nursing items that were not performed last time are combined, and the sum of the nursing time of each nursing item in the combination is less than the patient's nursing time; multiple nursing item combinations are taken, the nursing items in the combination are determined, the sum of the weights of the nursing items in the combination is calculated, and the combination with the largest sum of weights is selected as the nursing plan.

[0027] In a preferred embodiment, after the patient completes the nursing items, the duration of the nursing items, the missed nursing items and their weights are recorded, and the patient's physical data is recorded.

[0028] In a preferred embodiment, it includes a path generation module, a positioning module, a nursing plan recommendation module, a display module, an input module, and a storage module;

[0029] A path generation module generates a follow-up path and sends the follow-up path to a display module;

[0030] Positioning module, locates the real-time position of the nursing staff and sends the position information to the display module;

[0031] A nursing plan recommendation module recommends nursing plans and sends the nursing plans to the display module;

[0032] A display module, which displays information transmitted from a path generation module, a positioning module, and a nursing plan recommendation module;

[0033] The input module inputs the patient's symptom change data, medical history review data, and nursing plan recommendation module, and inputs the patient's physical data into the storage module;

[0034] The storage module records the duration of patient care items, uncared items and weights, and records the patient's physical data.

[0035] Technical effects and advantages of the present invention:

[0036] The present invention obtains the patient's home address information and recommends a follow-up route based on the patient's home address information; calculates the weight of each nursing item using a priority diagram based on the relevance and suitability of each nursing item; determines the time used for each patient's care and the weight of each nursing item, and determines the nursing plan with the highest weight as the recommended nursing plan; the recommended nursing plan is closer to the patient's actual situation; records the duration of the patient's nursing items, uncared items and weights, and records the patient's physical data.

[0037] During the second follow-up, the nursing items that were not performed on each patient during the previous follow-up and their weights and the address information of each patient are determined, and the follow-up path is re-recommended for follow-up, so as to better provide comprehensive follow-up care for patients within a limited time. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0039] Figure 1 A flowchart of a management method for chronic disease follow-up nursing services according to the present invention;

[0040] Figure 2 This is a structural schematic diagram of a management system for chronic disease follow-up nursing services according to the present invention. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] The present invention obtains the patient's home address information and recommends a follow-up route based on the patient's home address information; calculates the weight of each nursing item using a priority diagram based on the relevance and suitability of each nursing item; determines the time used for each patient's care and the weight of each nursing item, and determines the nursing plan with the highest weight as the recommended plan; records the duration of the patient's care items, uncared items and weights, and records the patient's physical data.

[0043] During the second follow-up, the nursing items that were not performed on each patient during the previous follow-up and their weights and the address information of each patient are determined, and the follow-up path is re-recommended for follow-up, so as to better provide comprehensive follow-up care for patients within a limited time.

[0044] Example 1

[0045] A method for managing chronic disease follow-up care services, such as Figure 1 As shown, the following steps are included:

[0046] Step S1: Obtain the patient's home address information and recommend a follow-up path based on the patient's home address information;

[0047] Step S2: Calculate the weight of each nursing item using a priority diagram according to the relevance and suitability of each nursing item;

[0048] Step S3: Screen out a batch of nursing plans according to the nursing time of each patient and the time taken by each nursing item; determine the weight of each nursing item, sum the weights of the nursing items in each nursing plan, and find the nursing plan with the largest weight as the recommended plan output;

[0049] Step S4: Record the duration of the patient's nursing items, uncared items and weights, and record the patient's physical data.

[0050] Specifically, in step S1, the patient's family uploads the patient's address information. Based on the patient's address information, the address information includes the distance between the patient's location and the headquarters and the distance between the patient's locations, as well as the location coordinates of each patient and the headquarters location coordinates; based on the patient's address information, the time spent by the nursing staff on the follow-up journey, the average time for caring for a single patient, the number of patients on the follow-up route, and the working hours of the nursing staff, a route is planned to connect all patients and the headquarters.

[0051] First, generate all possible paths that can connect patients to the headquarters, and then filter the paths based on the following conditions:

[0052] The time spent by the nursing staff on the follow-up route plus the average time of caring for a single patient multiplied by the number of patients on the follow-up route shall not be greater than the nursing staff's working hours. The average time of caring for a single patient is obtained from historical records, and the time of caring for all patients is divided by the number of patients cared for; the number of patients on the route and the nursing staff's working hours are entered by the staff as required.

[0053] The filtered paths are output as follow-up paths.

[0054] In step S2, the historical condition of the patient to be followed up is determined. The historical condition includes the disease type and the patient's age, etc. The data of each nursing item includes the nursing item number, the age group suitable for the nursing item, etc. The corresponding nursing item number can be matched according to the disease type, which is obtained according to the historical data and can also be input by relevant experts. The correlation is calculated based on the historical condition data and the data of each nursing item: Where r represents the correlation, X i and Y i Represent historical medical data and nursing project data respectively. and is its mean value.

[0055] Collect patient symptom change data: During follow-up, we must first understand whether the patient has new symptoms or aggravation of existing symptoms; for example, whether there is headache, impaired consciousness, memory loss, language problems, limb weakness, unsteady walking, etc.; medical history review data: check whether there are new changes in the patient's medical history, such as hospitalization, acute attack, medication, etc.; symptom change data and medical history review data are obtained by simply asking the patient's family and observing the patient's condition. The nursing staff will record the collected patient symptom changes and medical history review records into the system. The system will compare the input information with the information in the patient database and recommend the suitability of each nursing project; the more recommended nursing projects are, the higher the suitability is. The suitability of nursing projects is obtained according to the proportion of the number of times the nursing project has been used in history. The higher the proportion, the higher the suitability is; the patient database stores historical patient symptom changes and medical history review records, and the relevant nursing projects can be queried by comparing them one by one.

[0056] After determining the relevance and fitness of each nursing item, each nursing item is evaluated. First, linear normalization is used to map the relevance and fitness of each nursing item to the interval [0,1], and the formula is: In the formula, is the normalized value, X is the original data point, and X min is the minimum value in the data set, X max is the maximum value in the data set.

[0057] In this embodiment, an example of calculating the recommended score of each nursing item is as follows:

[0058] Determine the normalized correlation and the suitability of each nursing item, marked as X and S respectively; then the recommended score calculation formula for each nursing item is: P = X + S, where P represents the recommended score of each nursing item.

[0059] Determine the recommended score of each nursing item. The higher the relevance and suitability of each nursing item, the more the patient needs the nursing item. The more important it is, the greater the consideration weight should be. The recommended score of each nursing item is weighted according to the priority diagram method to determine the weight value of each nursing item. Specifically, the recommended score of each nursing item is weighted according to the priority diagram method as shown in Table 1 below:

[0060]

[0061]

[0062] Table 1

[0063] In the table, item A, item B, item C, item D, item E, and item F correspond to the six nursing items in this embodiment one by one. After sorting the nursing items according to the size of the recommended score, they correspond to item A, item B, item C, item D, item E, and item F in descending order. Among them, item A, item B, item C, item D, item E, and item F respectively include the following specific nursing services:

[0064] Project A: Neurological function examination includes: Cognitive function: Evaluate the patient's cognitive ability through a simple mental state examination (such as MMSE or MOCA) to determine whether there is further decline in cognitive function, especially in patients with Alzheimer's disease. Motor function: For patients with motor dysfunction such as Parkinson's disease, regularly evaluate their motor symptoms, including tremor, stiffness, bradykinesia, etc. Gait and balance examination: Detect whether the patient has abnormal gait and risk of falling, and provide corresponding rehabilitation guidance.

[0065] Project B: Imaging examination: Regular brain imaging examinations, such as CT, MRI or MRA, are performed to monitor changes in brain diseases, especially for patients after cerebral infarction or stroke, to observe whether there are new cerebrovascular problems or brain atrophy, etc. For patients with epilepsy, electroencephalogram (EEG) examinations can assess the frequency and type of epileptic seizures and adjust drug treatment.

[0066] Project C: Physiological index monitoring: Blood pressure monitoring: Hypertension is an important risk factor for many chronic brain diseases (such as stroke and cerebrovascular disease). Blood pressure needs to be measured regularly during follow-up. Blood sugar and blood lipid monitoring: For patients with diabetes or hyperlipidemia, blood sugar and blood lipid levels should be checked regularly to prevent complications. Weight and nutritional status: Patients who are bedridden for a long time or have decreased exercise capacity need to pay attention to their weight changes and the risk of malnutrition.

[0067] Project D: Drug use and treatment assessment: Drug compliance: During follow-up, assess whether the patient takes the medication on time, and whether there are any side effects or drug resistance. Adjust the treatment plan: Adjust the treatment plan in a timely manner according to the patient's condition, drug reaction and side effects. For example, adjust anti-epileptic drugs, anti-Parkinson's drugs, etc. Drug side effect monitoring: Regularly check the effects of drugs on liver and kidney function, blood system, etc.

[0068] Project E: Mental health assessment: Emotional and psychological state: Patients with chronic brain diseases, especially elderly patients, are prone to emotional problems such as depression, anxiety, and loneliness. Regularly assess their mental health and provide psychological support or referral for psychotherapy when necessary. Cognitive impairment: Assess whether the patient has cognitive decline, especially elderly patients, who may have early symptoms of Alzheimer's disease or other dementia.

[0069] Project F: Rehabilitation and exercise guidance: Motor function rehabilitation: For patients with limited motor ability (such as sequelae of stroke and Parkinson's disease), develop personalized rehabilitation plans and carry out appropriate physical therapy and exercise training. Balance and coordination training: Help patients improve their balance ability and reduce the risk of falling, especially for elderly patients. Rehabilitation assessment: Regularly assess the patient's rehabilitation progress and make adjustments when necessary.

[0070] In step S3, the nursing time of each patient is determined. The nursing time of the first patient is the average nursing time plus or minus 20% of the average nursing time; the nursing time of the second patient is the total nursing time minus the nursing time of the first patient divided by the number of remaining patients, with a value of 20% plus or minus; specifically, the range of fluctuation can be set according to actual needs. The total nursing time is equal to the working time of the nursing staff minus the travel time to each patient's residence. And so on, the nursing time of each patient is calculated one by one.

[0071] Determine the nursing time for each patient. The nursing time for each nursing item is obtained by averaging the nursing time of each nursing item in history. The nursing items are randomly combined, and the sum of the nursing time of each nursing item in the combination is less than the patient's nursing time.

[0072] Obtain multiple nursing item combinations, determine the nursing items in the combination, calculate the sum of the weights of the nursing items in the combination, and select the combination with the largest sum of weights as the nursing plan; the larger the sum of weights, the more important the nursing items contained in the combination.

[0073] In step S4, after the patient completes the nursing items, the duration of the patient's nursing items, the un-nursed items and their weights are recorded, and the patient's physical data is recorded.

[0074] Example 2

[0075] When the second follow-up is conducted, the nursing items that were not performed on each patient at the previous follow-up and their weights and the address information of each patient are determined.

[0076] At the last follow-up, the smaller the sum of the weights of the remaining nursing items that have not been cared for, it means that the patient has completed most of the nursing items in the last care and the completion rate is high. Otherwise, it means that the patient has not completed the last care at a high level.

[0077] Re-plan the follow-up path;

[0078] Determine the nursing items that each patient did not perform during the last follow-up, their weights and addresses, and select the random forest algorithm to determine the follow-up path; the specific steps are as follows:

[0079] The data set includes the nursing items that were not performed by each patient during the last follow-up, their weights and address information, and the data set is set to D, which contains m samples, and each sample j has k features cj1, cj2, cj3...cjk; and the target variable is set to Tj, where Tj is the path label.

[0080] The dataset D is randomly divided into a training set Dtrain and a test set Dtest. The training set is used to build the model, and the test set is used to verify the model. The training set contains p samples, and the test set contains q samples, where p+q=m.

[0081] Construct W decision trees, each tree Uw is constructed independently. For each tree, a sample set of size p is extracted from the training set Dtrain by bootstrap sampling. At each split node, instead of using all k features, the square root of k features are randomly selected from the k features to find the best split.

[0082] Each tree Uw generates a model Kw based on its training data. For a given test sample c, each tree Uw outputs a prediction result Tw(c).

[0083] Output all tree prediction outputs The average of all tree prediction outputs is taken as the prediction result.

[0084] Specifically, in this embodiment, the data set includes the following fields:

[0085] The nursing items that the patient did not receive and their weights and sums: The nursing items that the patient did not receive and their weights and sums;

[0086] Patient address information: the distance between the patient's location and the headquarters' location, the distance between the patient's locations, and the location coordinates of each patient and the headquarters' location coordinates;

[0087] Path: The path connecting the addresses of various patients;

[0088] D consists of m samples, each sample j has the features described above and a path label, namely:

[0089] Among them, for each sample j:

[0090] c j1 represents the care items that the patient did not receive and their weights and;

[0091] c j2 Represents the patient's address information;

[0092] T j is the path label, which is a number.

[0093] It should be noted that all the above data do not have units. Random Forest (RF) is a machine learning algorithm based on ensemble learning and belongs to the ensemble method of decision trees. It improves the accuracy and stability of the model by constructing multiple decision trees and summarizing their prediction results. Random Forest is widely used in tasks such as classification, regression, and feature selection.

[0094] The output path label is compared with the path database, and the follow-up path is output. The nursing staff follows the follow-up path for follow-up.

[0095] The path database contains all paths between the patient headquarters, and each path corresponds to a unique path label.

[0096] Visit according to the planned route; first confirm the nursing time of each patient, the calculation method is the same as above, combine the nursing items that were not performed last time, and the sum of the nursing time of each nursing item in the combination is less than the patient's nursing time; take multiple nursing item combinations, determine the nursing items in the combination, calculate the sum of the weights of the nursing items in the combination, and select the combination with the largest sum of weights as the nursing plan; the combination with a larger sum of weights represents more important nursing items included in the combination.

[0097] After the patient completes the nursing program, record the duration of the nursing program, the missed nursing items and the weight, and record the patient's physical data.

[0098] Example 3

[0099] The present invention provides Figure 2The management system for chronic disease follow-up nursing services shown includes: a path generation module, a positioning module, a nursing plan recommendation module, a display module, an input module, and a storage module.

[0100] A path generation module generates a follow-up path and sends the follow-up path to a display module;

[0101] Positioning module, locates the real-time position of the nursing staff and sends the position information to the display module;

[0102] A nursing plan recommendation module recommends nursing plans and sends the nursing plans to the display module;

[0103] A display module, which displays information transmitted from a path generation module, a positioning module, and a nursing plan recommendation module;

[0104] The input module inputs the patient's symptom change data, medical history review data, and nursing plan recommendation module, and inputs the patient's physical data into the storage module;

[0105] The storage module records the duration of patient care items, uncared items and weights, and records the patient's physical data.

[0106] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0107] In the several embodiments provided in the present application, 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 only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0108] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0109] In addition, each functional unit in each embodiment of the present application 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.

[0110] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A management method for chronic disease follow-up nursing services, characterized in that: The following steps are involved: Step S1: Obtain the patient's home address information and recommend a follow-up path based on the patient's home address information; Step S2: Calculate the weight of each nursing item using a priority diagram according to the relevance and suitability of each nursing item; Step S3: Screening out a batch of nursing plans according to the nursing time of each patient and the time of each nursing item; Determine the weight of each nursing item, sum the weights of the nursing items in each nursing plan, and find the nursing plan with the largest weight as the recommended plan output; Step S4: Record the duration of the patient's nursing items, uncared items and weights, and record the patient's physical data.

2. A management method for chronic disease follow-up nursing services according to claim 1, characterized in that: In step S1, a path is planned to connect all patients and the headquarters according to the patient address information and the headquarters location; Then filter the paths based on the following criteria: The time spent by the nursing staff on the follow-up journey plus the average time of caring for a single patient multiplied by the number of patients on the follow-up path is not greater than the working hours of the nursing staff; the screened path is output as the follow-up path.

3. A management method for chronic disease follow-up nursing services according to claim 1, characterized in that: In step S2, the correlation is calculated based on the historical condition data and each nursing item data: Collect patient symptom change data, compare it with the nursing items in the historical database, and recommend the suitability of each nursing item.

4. A management method for chronic disease follow-up nursing services according to claim 3, characterized in that: In step S2, the relevance and nursing item suitability are determined and the weight of each nursing item is calculated according to the priority diagram method.

5. The management method of chronic disease follow-up nursing service according to claim 1, characterized in that: In step S3, the nursing time of each patient is determined. The nursing time of the first patient is the average nursing time plus or minus 20% of the average nursing time; the nursing time of the second patient is the total nursing time minus the nursing time of the first patient divided by the number of remaining patients, and the value fluctuates by 20%; specifically, the range of fluctuation can be set according to actual needs; the total nursing time is equal to the working time of the nursing staff minus the travel time to each patient's residence; and so on, the nursing time of each patient is calculated one by one; Determine the nursing time for each patient. The nursing time for each nursing item is obtained by averaging the nursing time for each nursing item in history. The nursing items are randomly combined, and the sum of the nursing time of each nursing item in the combination is less than the patient's nursing time. Obtain multiple nursing item combinations, determine the nursing items in the combination, calculate the sum of the weights of the nursing items in the combination, and select the combination with the largest sum of weights as the nursing plan.

6. A management method for chronic disease follow-up nursing services according to claim 1, characterized in that: In step S4, after the patient completes the nursing items, the duration of the patient's nursing items, the un-nursed items and their weights are recorded, and the patient's physical data is recorded.

7. The management method of chronic disease follow-up nursing service according to claim 1, characterized in that: During the second follow-up, determine the nursing items that were not performed by each patient during the previous follow-up, their weights and addresses, and select the random forest algorithm to determine the follow-up path; the specific steps are as follows: The data set includes the nursing items that each patient did not perform during the last follow-up, their weights and addresses, and the address information of each patient. The data set is set to D, which contains m samples, and each sample j has k features cj1, cj2, cj3...cjk; and the target variable is set to Tj, where Tj is the path label; The dataset D is randomly divided into a training set Dtrain and a test set Dtest. The training set is used to build the model, and the test set is used to verify the model. The training set contains p samples, and the test set contains q samples, where p+q=m. Construct W decision trees, each tree Uw is constructed independently; for each tree, extract a sample set of size p from the training set Dtrain by bootstrap sampling; at each split node, instead of using all k features, randomly select the square root of k features from the k features to find the best split; Each tree Uw generates a model Kw based on its training data; for a given test sample c, each tree Uw will output a prediction result Tw(c); Output all tree prediction outputs The average of all tree prediction outputs is taken as the prediction result.

8. The management method of chronic disease follow-up nursing service according to claim 1, characterized in that: Determine the access path, confirm the nursing time of each patient, and combine the nursing items that were not performed last time. The sum of the nursing time of each nursing item in the combination is less than the patient's nursing time. Take multiple nursing item combinations, determine the nursing items in the combination, calculate the sum of the weights of the nursing items in the combination, and select the combination with the largest sum of weights as the nursing plan.

9. A management method for chronic disease follow-up nursing services according to claim 1, characterized in that: After the patient completes the nursing program, record the duration of the nursing program, the missed nursing items and the weight, and record the patient's physical data.

10. A management system for chronic disease follow-up nursing services, used to implement a management method for chronic disease follow-up nursing services as claimed in any one of claims 1 to 9, characterized in that: It includes a path generation module, a positioning module, a nursing plan recommendation module, a display module, an input module, and a storage module; A path generation module generates a follow-up path and sends the follow-up path to a display module; Positioning module, locates the real-time position of the nursing staff and sends the position information to the display module; A nursing plan recommendation module recommends nursing plans and sends the nursing plans to the display module; A display module, which displays information transmitted from a path generation module, a positioning module, and a nursing plan recommendation module; The input module inputs the patient's symptom change data, medical history review data, and nursing plan recommendation module, and inputs the patient's physical data into the storage module; The storage module records the duration of patient care items, uncared items and weights, and records the patient's physical data.

Images