A follow-up system for peritoneal dialysis patients and a method for remote monitoring of patient information

Abstract

The present invention relates to the technical field of peritoneal dialysis, and particularly relates to a follow-up system for peritoneal dialysis patients and a method for remotely monitoring patient information. In the neighborhood range of each examination, for the examination sample space or any symptom sample space, according to the position distribution of different data points in the sample space, the overall health of the patient corresponding to the examination sample space in each examination is obtained, as well as the local health corresponding to each symptom sample space, and the degree of self-control of the patient for each symptom in each examination is obtained; furthermore, the degree of drug intervention of the patient for each symptom in each examination is obtained; by combining the difference in the local health of the corresponding symptom sample space between each examination and the previous adjacent examination, follow-up of the patient is carried out. The present invention improves the effectiveness of patient follow-up by obtaining the accurate degree of drug intervention of the patient for each symptom in each examination.

Description

Technical Field

[0001] The present invention relates to the technical field of peritoneal dialysis, and specifically relates to a follow-up system for peritoneal dialysis patients and a method for remotely monitoring patient information. Background Art

[0002] Long-term peritoneal dialysis can cause symptoms such as elevated blood lipids, increased cholesterol, malnutrition, and high blood sugar in peritoneal dialysis patients. Therefore, it is necessary to examine peritoneal dialysis patients to improve their physical condition. In the prior art, the threshold set according to experience is used to analyze the physical sign data obtained by patients during each examination. However, since the physical condition and living habits of each patient are different, the traditional method lacks a relatively standard judgment on whether drug injection intervention should be carried out for symptoms such as malnutrition and high blood sugar caused by long-term dialysis in peritoneal dialysis patients, resulting in inaccurate follow-up arrangements. Summary of the Invention

[0003] In order to solve the technical problems of lack of relatively standard judgment for drug intervention and inaccurate follow-up arrangements, the purpose of the present invention is to provide a follow-up system for peritoneal dialysis patients and a method for remotely monitoring patient information. The specific technical solutions adopted are as follows:

[0004] The present invention proposes a method for remotely monitoring peritoneal dialysis patient information, and the method includes:

[0005] Obtain various physical sign data of peritoneal dialysis patients during each examination, as well as various physical sign symptom data for each symptom, to form data points in the examination sample space and each symptom sample space. The sample space includes data points of a healthy control population.

[0006] Within the neighborhood range of each examination, for the examination sample space or any symptom sample space, according to the position distribution of different data points in the sample space, obtain the overall health of the patient corresponding to the examination sample space during each examination, and the local health corresponding to each symptom sample space, and obtain the degree of self-control of the patient for each symptom during each examination.

[0007] According to the overall health distribution of the corresponding examination sample space in different examinations within the neighborhood range of each examination of the patient, and the local health corresponding to each symptom sample space in each examination, obtain the degree of drug intervention of the patient for each symptom during each examination; according to the degree of self-control of the patient for each symptom during each examination, the degree of drug intervention, and the difference in the local health of the corresponding symptom sample space between each examination and the previous adjacent examination, obtain the degree of drug intervention correction of the patient for each symptom during each examination.

[0008] Follow up the patient according to the degree of drug intervention correction.

[0009] Further, obtaining the overall health of the patient corresponding to each examination in the examination sample space and the local health corresponding to each symptom sample space includes:

[0010] Within the neighborhood range of each examination, for the examination sample space or any symptom sample space, according to the position distribution of different data points in the sample space, obtain multiple data clustering clusters for each examination, and screen out the healthy core clustering cluster;

[0011] Obtain the relative distance between the center points of the data clustering cluster where the data point corresponding to each examination of the patient is located and the healthy core clustering cluster; select the maximum value of the corresponding relative distances in all examinations, and calculate the ratio between the relative distance corresponding to each examination and the maximum value of the relative distances as the first ratio;

[0012] Count the number of examinations in which the first ratio is less than the preset ratio in all examinations as the number of healthy examinations; obtain the ratio of the number of healthy examinations to the total number of all examinations as the health of the corresponding sample space; the health of the sample space includes the overall health of the examination sample space or the local health of each symptom sample space.

[0013] Further, the method for obtaining the data clustering cluster includes:

[0014] Within the neighborhood range of each examination, for the examination sample space or any symptom sample space, perform DBSCAN clustering on all data points according to the position distribution of different data points in the sample space to obtain multiple data clustering clusters for each examination.

[0015] Further, the method for obtaining the healthy core clustering cluster includes:

[0016] Select the data clustering cluster with the most data points corresponding to the healthy control population, and use the corresponding data clustering cluster as the healthy core clustering cluster.

[0017] Further, the method for obtaining the degree of self-control includes:

[0018] For each symptom sample space, obtain the relative distance between each data point in the data clustering cluster where the data point corresponding to each examination of the patient is located and the center point of the corresponding healthy core clustering cluster, and select the data point with the smallest relative distance as the reference data point;

[0019] Obtain the ratio of the relative distance between the data point corresponding to each examination of the patient and the center point of the data clustering cluster where it is located to the maximum value of the relative distances between the data points corresponding to other examinations before each examination and the center points of the data clustering clusters where they are located as the first control coefficient;

[0020] Construct a first connection line from the corresponding data point of the patient's previous adjacent examination to the corresponding data point of each examination, and a second connection line from the reference data point to the center point of the healthy core clustering cluster; obtain the patient's self-control degree for each symptom at each examination according to the cosine value of the angle between the first connection line and the second connection line and the first control coefficient, and both the cosine value of the angle and the first control coefficient are positively correlated with the self-control degree.

[0021] Further, the method for obtaining the drug intervention degree includes:

[0022] Obtain the maximum value of the overall health of the corresponding examination sample spaces of different examinations within the neighborhood range of each examination of the patient, and calculate the difference between the maximum value of the overall health and the overall health corresponding to each examination of the patient as the first difference;

[0023] Obtain the ratio of the first difference to the local health of each symptom sample space corresponding to each examination as the drug intervention degree of the patient for each symptom at each examination.

[0024] Further, the method for obtaining the drug intervention correction degree includes:

[0025] Obtain the difference in the local health of the corresponding symptom sample spaces between the patient's previous adjacent examination and each examination as the local health difference;

[0026] Obtain the ratio between the patient's self-control degree for each symptom at each examination and the local health difference, and perform normalization as the adjustment parameter;

[0027] Obtain the drug intervention correction degree of the patient for each symptom at each examination according to the adjustment parameter and the drug intervention degree of the patient for each symptom at each examination.

[0028] Further, the method for obtaining the drug intervention correction degree includes:

[0029] Obtain the sum of the positive integer 1 and the adjustment parameter as the weighting value; obtain the product of the weighting value and the drug intervention degree of the patient for each symptom at each examination as the drug intervention correction degree of the patient for each symptom at each examination.

[0030] Further, the preset ratio is 0.5.

[0031] The present invention also proposes a remote monitoring method for peritoneal dialysis patient information, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of any one of the remote monitoring methods for peritoneal dialysis patient information are implemented.

[0032] The present invention has the following beneficial effects:

[0033] In the neighborhood range of each examination of the present invention, for the examination sample space or any symptom sample space, according to the position distribution of different data points in the sample space, the overall health of the patient corresponding to the examination sample space in each examination is obtained, as well as the local health corresponding to each symptom sample space, reflecting the overall health status of the patient at each examination and the health status under each symptom, obtaining the degree of self-control of the patient for each symptom at each examination, evaluating the initiative and ability of the patient in disease management; according to the distribution of the overall health of the examination sample space corresponding to different examinations in the neighborhood range of each examination of the patient, and the local health corresponding to each symptom sample space in each examination, the degree of drug intervention of the patient for each symptom at each examination is obtained, evaluating the degree of drug demand of the patient under each symptom; according to the degree of self-control of the patient for each symptom at each examination, the degree of drug intervention, and the difference in the local health of the corresponding symptom sample space between each examination and the previous adjacent examination, the degree of drug intervention correction of the patient for each symptom at each examination is obtained, which can dynamically monitor the changes in the health status of the patient, helping to obtain a more accurate degree of intervention demand; follow up the patient. By obtaining the accurate degree of drug intervention of the patient for each symptom at each examination, the present invention improves the effectiveness of patient follow-up. Description of the Drawings

[0034] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0035] Figure 1 It is a flowchart of a method for remotely monitoring peritoneal dialysis patient information provided by an embodiment of the present invention;

[0036] Figure 2 It is a flowchart of a method for obtaining the degree of self-control provided by an embodiment of the present invention;

[0037] Figure 3 It is a flowchart of a method for obtaining the degree of drug intervention correction provided by an embodiment of the present invention. Detailed Embodiments

[0038] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following specifically describes, with reference to the accompanying drawings and preferred embodiments, a follow-up system for peritoneal dialysis patients and a remote monitoring method for patient information, including its specific implementation manner, structure, features, and effects. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0039] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this invention belongs.

[0040] The following specifically describes the specific solutions of a follow-up system for peritoneal dialysis patients and a remote monitoring method for patient information provided by the present invention with reference to the accompanying drawings.

[0041] Please refer to Figure 1 , which shows a flowchart of a method for remotely monitoring peritoneal dialysis patient information provided by an embodiment of the present invention, specifically including:

[0042] Step S1: Obtain various physical sign data of peritoneal dialysis patients during each examination, as well as various physical sign symptom data for each symptom, to form data points in the examination sample space and each symptom sample space. The sample space includes data points of a healthy control population.

[0043] In an embodiment of the present invention, in order to timely intervene in the poor physical state of peritoneal dialysis patients, it is necessary to process the patient information of the patients and analyze the physical sign data after each examination. First, through the fixed time requirement for peritoneal dialysis patients to upload data such as weight, blood sugar, blood pressure, and heart rate that can be monitored at home, and remind peritoneal dialysis patients to go to the hospital on time to check and upload data such as blood calcium, uric acid, serum protein, and blood lipids. In peritoneal dialysis, various symptoms such as increased blood lipid, increased cholesterol, malnutrition, and high blood sugar may occur. Analyze the physical sign changes of each symptom during each examination. For example, the symptom of high or low blood sugar in peritoneal dialysis patients is related to multiple physical sign data such as blood sugar measurement, glucose tolerance test, glycated hemoglobin measurement, and glycated plasma protein measurement.

[0044] Obtain various physical sign data of peritoneal dialysis patients during each examination, as well as various physical sign symptom data for each symptom, to form data points in the examination sample space and each symptom sample space. Among them, the examination sample space contains data points composed of all physical sign data of the patient during each examination, while the symptom sample space contains data points composed of relevant physical sign symptom data of a certain symptom.

[0045] It should be noted that, in an embodiment of the present invention, in order to more accurately judge the health status of a patient, the data points of healthy people can be used as a normal reference standard. Therefore, the data points of the healthy control population are included in the sample space, and 30 healthy people without diseases are selected as the healthy control population of the patient; in other embodiments of the present invention, the number of the healthy control population can be specifically set according to specific circumstances, which will not be limited and elaborated herein.

[0046] It should be noted that, in an embodiment of the present invention, in order to facilitate the subsequent data processing, various physical sign data and physical sign symptom data are standardized to eliminate the dimension in the data, so that indicators with different units or magnitudes can be comprehensively analyzed and compared. The standardization can adopt existing methods such as Z-score standardization and min-max transformation. The specific means are well-known technical means to those skilled in the art and will not be elaborated herein.

[0047] Step S2: In the neighborhood range of each examination, for the examination sample space or any symptom sample space, according to the position distribution of different data points in the sample space, obtain the overall health degree of the patient corresponding to the examination sample space in each examination, and the local health degree corresponding to each symptom sample space, and obtain the degree of self-control of the patient for each symptom in each examination.

[0048] In order to accurately evaluate the health status of a patient, selecting the neighborhood range of each examination helps to focus on different data points before each examination, ensuring the accuracy and relevance of the analysis, so as to more accurately reflect the change of the patient's health status. In the neighborhood range of each examination, for the examination sample space or any symptom sample space, according to the position distribution of different data points in the sample space, obtain the overall health degree of the patient corresponding to the examination sample space in each examination, and the local health degree corresponding to each symptom sample space.

[0049] Preferably, in an embodiment of the present invention, obtaining the overall health degree of the patient corresponding to the examination sample space in each examination, and the local health degree corresponding to each symptom sample space includes:

[0050] In the neighborhood range of each examination, for the examination sample space or any symptom sample space, according to the position distribution of different data points in the sample space, obtain multiple data clustering clusters for each examination, and screen out the healthy core clustering clusters;

[0051] Preferably, in an embodiment of the present invention, the method for obtaining the data clustering clusters includes:

[0052] In the neighborhood range of each examination, for the examination sample space or any symptom sample space, according to the position distribution of different data points in the sample space, perform DBSCAN clustering on all data points to obtain multiple data clustering clusters for each examination.

[0053] The DBSCAN clustering algorithm can effectively identify the data points within the neighborhood radius and classify them into clusters, while excluding the influence of noise points. It should be noted that, in an embodiment of the present invention, the parameter settings for DBSCAN clustering are as follows: the size of the neighborhood radius parameter determines the clustering density, the neighborhood radius is 5, and the minimum number of data point sets is 3, that is, only when the cluster corresponding to the data point contains at least 3 data points does it meet the clustering condition for clustering; in other embodiments of the present invention, the clustering parameters can be specifically set according to specific situations, which will not be limited and elaborated herein.

[0054] It should be noted that, in an embodiment of the present invention, the neighborhood range for each inspection is based on each inspection and forms a range with all historical inspections; in other embodiments of the present invention, the size of the neighborhood range can be specifically set according to specific situations, which will not be limited and elaborated herein.

[0055] Preferably, in an embodiment of the present invention, the method for obtaining the healthy core clustering cluster includes:

[0056] Select the data clustering cluster with the most data points corresponding to the healthy control population, and use the corresponding data clustering cluster as the healthy core clustering cluster. The more data points corresponding to the healthy control population, the more the corresponding data clustering cluster approaches the normal physical sign performance, reflecting the distribution of data points when the physical signs are healthy.

[0057] Obtain the relative distance between the center points of the data clustering cluster where the data points corresponding to each patient's inspection are located and the healthy core clustering cluster; select the maximum value of the corresponding relative distances in all inspections, and calculate the ratio between the relative distance corresponding to each inspection and the maximum value of the relative distances as the first ratio;

[0058] Count the number of inspections in which the first ratio is less than the preset ratio in all inspections as the number of healthy inspections; obtain the ratio of the number of healthy inspections to the total number of all inspections as the health degree of the corresponding sample space; the health degree of the sample space includes the overall health degree of the inspection sample space or the local health degree of each symptom sample space.

[0059] It should be noted that, in an embodiment of the present invention, the preset ratio is 0.5, and in other embodiments of the present invention, the size of the preset ratio can be specifically set according to specific situations, which will not be limited and elaborated herein.

[0060] It should be noted that the method for obtaining the center point is to calculate the mean value of the corresponding position coordinates of all data points in the data clustering cluster to obtain the center point position coordinates, and then analyze the relative distance therebetween; in some embodiments of the present invention, the relative distance can be calculated by using existing distance methods such as calculating the Euclidean distance or the Manhattan distance. The specific means are well-known technical means to those skilled in the art and will not be elaborated herein.

[0061] The symptoms caused by peritoneal dialysis itself can be adjusted through the living habits of peritoneal dialysis patients. For example, if the blood sugar is high, the intake of foods with high sugar content can be controlled, etc. Under each symptom, the higher the control degree of living habits, the more the self-management ability of the patient's health status is understood. Obtain the patient's own control degree for each symptom in each examination.

[0062] Preferably, in an embodiment of the present invention, for the method for obtaining the self-control degree, please refer to Figure 2 , which shows a flowchart of a method for obtaining the self-control degree, including:

[0063] Step S201: For each symptom sample space, obtain the relative distance between each data point in the data clustering cluster where the data point corresponding to the patient in each examination is located and the center point of the corresponding healthy core clustering cluster, and select the data point when the relative distance is the smallest as the reference data point.

[0064] The healthy core clustering cluster represents an ideal or healthy state. Selecting the data point with the smallest relative distance from the center point of the healthy core clustering cluster as the reference data point can better represent the degree to which the patient is close to the healthy state in this examination.

[0065] Step S202: Obtain the ratio of the relative distance between the data point corresponding to the patient in each examination and the center point of the data clustering cluster where it is located to the maximum value of the relative distance between the data points corresponding to other examinations before each examination and the center point of the data clustering cluster where they are located, as the first control coefficient.

[0066] The greater the relative distance between the data point corresponding to the patient in each examination and the center point of the data clustering cluster where it is located, the farther the physical signs performance under the corresponding examination is from the center point, and the better the control, and the greater the first control coefficient.

[0067] Step S203: Construct a first connection line from the data point corresponding to the previous adjacent examination of the patient to the data point corresponding to each examination, and a second connection line from the reference data point to the center point of the healthy core clustering cluster; according to the cosine value of the angle between the first connection line and the second connection line and the first control coefficient, obtain the patient's self-control degree for each symptom in each examination. The cosine value of the angle and the first control coefficient are both positively correlated with the self-control degree.

[0068] In one embodiment of the present invention, for any symptom sample space, the formula for the degree of self-control is expressed as:

[0069] ;

[0070] wherein, represents the degree of self-control of the patient for each symptom in the th examination; represents the relative distance between the data point corresponding to the patient in the th examination and the center point of the data clustering cluster where it is located; represents the maximum value of the relative distances between the data points corresponding to other examinations before the th examination of the patient and the center point of the data clustering cluster where they are located; represents the included angle between the first connection line from the data point corresponding to the adjacent previous examination of the patient to the data point corresponding to each examination, and the second connection line from the reference data point to the center point of the healthy core clustering cluster.

[0071] In the formula for the degree of self-control, represents taking the cosine value of the included angle. The smaller the included angle, the closer the positions of the data clustering cluster where the data corresponding to the th examination is located and the healthy core clustering cluster are to those in the adjacent previous examination, and the healthier the physical state shown in the th examination. The larger the cosine value of the included angle, the greater the degree of self-control; represents the ratio between the relative distance between the data point corresponding to the patient in the th examination and the center point of the data clustering cluster where it is located, and the maximum value of the relative distances between the data points corresponding to other examinations before the th examination and the center point of the data clustering cluster where they are located, that is, the first control coefficient. The larger the ratio, the larger the relative distance between the data point corresponding to the patient in the th examination and the center point of the data clustering cluster where it is located, reflecting a greater degree of self-control.

[0072] Step S3: Obtain the degree of drug intervention of the patient for each symptom in each examination according to the overall health degree distribution of different examination corresponding examination sample spaces within the neighborhood range of each examination of the patient, and the local health degree of each symptom sample space corresponding to each examination; obtain the degree of drug intervention correction of the patient for each symptom in each examination according to the degree of self-control, the degree of drug intervention of the patient for each symptom in each examination, and the difference in the local health degree of the corresponding symptom sample space between each examination and the adjacent previous examination.

[0073] Health status changes over time. The overall health degree distribution reflects the general trend of the patient's health status within the neighborhood range, and the local health degree reflects the health status of specific symptoms. Combining the analysis helps to comprehensively evaluate the patient's physical health during each examination and quantify the degree of drug intervention. Based on the overall health degree distribution of the corresponding examination sample spaces for different examinations within the neighborhood range of each patient examination, and the local health degree of each symptom sample space corresponding to each examination, the degree of drug intervention for each symptom of the patient during each examination is obtained.

[0074] Preferably, in an embodiment of the present invention, the method for obtaining the degree of drug intervention includes:

[0075] Obtain the maximum value of the overall health degree of the corresponding examination sample spaces for different examinations within the neighborhood range of each patient examination, and calculate the difference between the maximum value of the overall health degree and the overall health degree corresponding to each patient examination as the first difference;

[0076] Obtain the ratio of the first difference to the local health degree of each symptom sample space corresponding to each examination as the degree of drug intervention for each symptom of the patient during each examination.

[0077] In an embodiment of the present invention, the formula for the degree of drug intervention is expressed as:

[0078] ;

[0079] Wherein, represents the degree of drug intervention for the rd symptom of the patient during the th examination; represents the overall health degree corresponding to the th examination of the patient; represents the maximum value of the overall health degree corresponding to different examinations within the neighborhood range of the th examination of the patient; represents the local health degree of the th examination corresponding to the th symptom state space of the patient.

[0080] In the formula for the degree of drug intervention, represents the difference between the maximum value of the overall health degree and the overall health degree corresponding to the th examination of the patient, that is, the first difference. The larger the difference, the smaller the overall health degree corresponding to the th examination of the patient, and the worse the overall physical state of the patient during this examination. The more drug intervention is needed. The th examination of the patient corresponds to the The smaller the local health of a symptom state space, the worse the physical state of the patient corresponding to the symptom, and the worse the degree of drug intervention.

[0081] The degree of self-control of a patient reflects their initiative and ability in symptom management, and directly affects the effect of drug intervention. Patients with a high degree of self-control can delay drug intervention through their own good control; the degree of drug intervention directly reflects the intensity of the drug's demand for the patient's symptoms; the difference in local health reflects the change in the patient's symptoms between two adjacent examinations. The greater the change, the greater the possibility of drug intervention; according to the patient's degree of self-control for each symptom in each examination, the degree of drug intervention, and the difference in the local health of the corresponding symptom sample space between each examination and the previous adjacent examination, the degree of drug intervention correction for each symptom in each examination is obtained.

[0082] Preferably, in an embodiment of the present invention, for the method of obtaining the degree of drug intervention correction, please refer to Figure 3 which shows a flowchart of a method for obtaining the degree of drug intervention correction, including:

[0083] Step S301: Obtain the difference in the local health of the corresponding symptom sample space between the previous adjacent examination and each examination of the patient as the local health difference.

[0084] To quantify the change in the patient's health status between two examinations, it is necessary to calculate the difference in local health. The greater the difference, the greater the change in health status.

[0085] Step S302: Obtain the ratio between the degree of self-control of the patient for each symptom in each examination and the local health difference, and perform normalization as the adjustment parameter.

[0086] The degree of self-control of the patient has an important impact on the health status. The better the self-control, that is, the better the state of living habits, etc., the greater the possibility of changes between examinations. At this time, the greater the local health difference, the greater the health change, and the greater the adjustment parameter.

[0087] Step S303: Obtain the degree of drug intervention correction for each symptom in each examination of the patient according to the adjustment parameter and the degree of drug intervention for each symptom in each examination of the patient.

[0088] Preferably, in an embodiment of the present invention, the method for obtaining the degree of drug intervention correction includes:

[0089] Obtain the sum of the positive integer 1 and the adjustment parameter as the weighting value; obtain the product of the weighting value and the degree of drug intervention for each symptom in each examination of the patient as the degree of drug intervention correction for each symptom in each examination of the patient.

[0090] In one embodiment of the present invention, the formula for the degree of drug intervention correction is expressed as:

[0091] ;

[0092] Wherein, represents the degree of drug intervention correction for the th symptom during the th examination of the patient; represents the degree of drug intervention for the th symptom during the th examination of the patient; represents the degree of self-control for the th symptom during the th examination of the patient; represents the local health degree of the th examination corresponding to the th symptom state space of the patient; represents the local health degree of the th examination corresponding to the th symptom state space of the patient; represents the hyperbolic tangent function.

[0093] In the formula for the degree of drug intervention correction, represents the difference in the local health degree between the th examination and the th examination corresponding to the th symptom state space of the patient, that is, the local health difference. The larger the difference, the greater the local health degree of the th examination corresponding to the th symptom state space of the patient, and the worse the health state of the patient for the corresponding symptom. The larger the local health difference, the more drug intervention is needed; represents the ratio between the degree of self-control for each symptom and the local health difference during the th examination of the patient, and is normalized by as a regulation parameter. The larger the regulation parameter, the greater the degree of self-control, the greater the credibility of the local health difference, the greater the local health degree, the greater the degree of drug intervention correction, and the smaller the local health degree, the smaller the degree of drug intervention correction.

[0094] To more comprehensively analyze the overall physical condition of the patient during each examination, the degree of drug intervention correction for each symptom is summarized to obtain the degree of drug intervention correction of the patient during each examination, which helps to integrate the correction degrees of different symptoms into an overall evaluation value. Obtain the degree of drug intervention correction of the patient during each examination.

[0095] Step S4: Follow up the patients according to the degree of drug intervention correction.

[0096] The health status, disease type, and severity of each patient are different, so the degree of need for drug intervention will also vary. Following up according to the degree of drug intervention correction can formulate personalized follow-up plans for different patients' specific conditions, which helps to observe patients more timely.

[0097] It should be noted that in another embodiment of the present invention, to follow up the patients by obtaining the degree of drug intervention correction for all symptoms in each examination of the patients, it includes: selecting the maximum value of the degree of drug intervention correction for all symptoms in each examination of different patients as the drug intervention reference degree, and arranging the follow-up of the patients in descending order of the drug intervention reference degree. The greater the drug intervention reference degree, the worse the patient's physical condition, and the more urgent it is to observe as early as possible, which helps to monitor the patient's physical condition more timely and accurately.

[0098] In summary, in the neighborhood range of each examination of the present invention, for the examination sample space or any symptom sample space, according to the position distribution of different data points in the sample space, the overall health degree of the patient corresponding to the examination sample space in each examination, and the local health degree corresponding to each symptom sample space are obtained, and the self-control degree of the patient for each symptom in each examination is obtained; furthermore, the drug intervention degree of the patient for each symptom in each examination is obtained; by combining the difference in the local health degree of the corresponding symptom sample space between each examination and the previous adjacent examination, the drug intervention correction degree of the patient in each examination is obtained; and the patients are followed up. The present invention improves the rationality of patient follow-up by obtaining the accurate drug intervention degree of the patient for each symptom in each examination.

[0099] The present invention also proposes a follow-up system for peritoneal dialysis patients, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the computer program, the steps of any one of the remote monitoring methods for peritoneal dialysis patient information are implemented.

[0100] It should be noted that: the above sequence of embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0101] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key points of each embodiment are the differences from other embodiments.

Claims

1. A remote monitoring method for peritoneal dialysis patient information, characterized in that, The method includes: Obtaining various physical sign data of peritoneal dialysis patients during each examination, as well as various physical sign symptom data for each symptom, to form data points within the examination sample space and each symptom sample space, where the sample space includes data points of the healthy control population; Within the neighborhood range of each examination, for the examination sample space or any symptom sample space, based on the position distribution of different data points within the sample space, obtaining the overall health of the patient corresponding to the examination sample space during each examination, as well as the local health corresponding to each symptom sample space, and obtaining the patient's self-control degree for each symptom during each examination; Based on the overall health distribution of the examination sample space corresponding to different examinations within the neighborhood range of each examination of the patient, and the local health corresponding to each symptom sample space during each examination, obtaining the drug intervention degree of the patient for each symptom during each examination; based on the patient's self-control degree for each symptom during each examination, the drug intervention degree, and the difference in the local health of the corresponding symptom sample space between each examination and the previous adjacent examination, obtaining the drug intervention correction degree of the patient for each symptom during each examination; Following up on the patient according to the drug intervention correction degree; The method for obtaining the drug intervention correction degree includes: Obtaining the difference in the local health of the corresponding symptom sample space between the previous adjacent examination and each examination of the patient as the local health difference; Obtaining the ratio between the patient's self-control degree for each symptom during each examination and the local health difference, and normalizing it as the adjustment parameter; Based on the adjustment parameter and the patient's drug intervention degree for each symptom during each examination, obtaining the drug intervention correction degree of the patient for each symptom during each examination; Obtaining the sum of the positive integer 1 and the adjustment parameter as the weighting value; obtaining the product of the weighting value and the patient's drug intervention degree for each symptom during each examination as the drug intervention correction degree of the patient for each symptom during each examination.

2. The remote monitoring method for peritoneal dialysis patient information according to claim 1, characterized in that, The obtaining of the overall health of the patient corresponding to the examination sample space during each examination, as well as the local health corresponding to each symptom sample space, includes: Within the neighborhood range of each examination, for the examination sample space or any symptom sample space, based on the position distribution of different data points within the sample space, obtaining multiple data clustering clusters for each examination, and screening out the healthy core clustering cluster; Obtaining the relative distance between the center points of the data clustering cluster where the data point corresponding to each examination of the patient is located and the healthy core clustering cluster; selecting the maximum value of the corresponding relative distances in all examinations, and calculating the ratio between the relative distance corresponding to each examination and the maximum value of the relative distances as the first ratio; Counting the number of examinations corresponding to the first ratio less than the preset ratio in all examinations as the number of healthy examinations; obtaining the ratio of the number of healthy examinations to the total number of all examinations as the health degree of the corresponding sample space; the health degree of the sample space includes the overall health degree of the examination sample space or the local health degree of each symptom sample space.

3. The remote monitoring method for peritoneal dialysis patient information according to claim 2, characterized in that, The method for obtaining the data clustering cluster includes: Within the neighborhood range of each inspection, for the inspection sample space or any symptom sample space, according to the position distribution of different data points within the sample space, perform DBSCAN clustering on all data points to obtain multiple data clustering clusters for each inspection.

4. A remote monitoring method for peritoneal dialysis patient information according to claim 3, characterized in that, The method for obtaining the healthy core clustering cluster includes: Select the data clustering cluster with the most corresponding data points of the healthy control population, and use the corresponding data clustering cluster as the healthy core clustering cluster.

5. The remote monitoring method for peritoneal dialysis patient information according to claim 4, wherein The method for obtaining the degree of self-control includes: For each symptom sample space, obtain the relative distance between each data point within the data clustering cluster where the data point corresponding to the patient in each inspection is located and the center point of the corresponding healthy core clustering cluster, and select the data point when the relative distance is the smallest as the reference data point; Obtain the ratio of the relative distance between the data point corresponding to the patient in each inspection and the center point of the data clustering cluster where it is located to the maximum value of the relative distance between the data points corresponding to other inspections before each inspection and the center point of the data clustering cluster where they are located, as the first control coefficient; Construct a first connection line from the data point corresponding to the patient in the previous adjacent inspection to the data point corresponding to each inspection, and a second connection line from the reference data point to the center point of the healthy core clustering cluster; according to the cosine value of the angle between the first connection line and the second connection line and the first control coefficient, obtain the degree of self-control of the patient for each symptom in each inspection, and both the cosine value of the angle and the first control coefficient are positively correlated with the degree of self-control.

6. The remote monitoring method for peritoneal dialysis patient information according to claim 1, wherein, The method for obtaining the degree of drug intervention includes: Obtain the maximum value of the overall health of the corresponding inspection sample space for different inspections within the neighborhood range of each inspection of the patient, and calculate the difference between the maximum value of the overall health and the overall health corresponding to the patient in each inspection as the first difference; Obtain the ratio of the first difference to the local health of each symptom sample space corresponding to each inspection as the degree of drug intervention of the patient for each symptom in each inspection.

7. A remote monitoring method for peritoneal dialysis patient information according to claim 2, characterized in that, The preset ratio is 0.

5.

8. A follow-up system for peritoneal dialysis patients, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method for remotely monitoring peritoneal dialysis patient information according to any one of claims 1 to 7.

Images