An intelligent management method and system for potassium blood data of renal dialysis patients

Abstract

The present invention provides an intelligent management method and system for potassium blood data of renal dialysis patients, belonging to the technical field of medical management. The method includes: obtaining the potassium blood data of renal dialysis patients uploaded through the upload channel for preliminary quality analysis and determining the quality analysis result; when the quality analysis result is determined to be qualified, retrieving the individual information of the renal dialysis patients from the potassium blood data of the renal dialysis patients; counting the information of each management queue in the potassium blood data management center and processing it in combination with the individual information of the renal dialysis patients to confirm the management queue of the renal dialysis patients; according to the management queue of the renal dialysis patients, processing to obtain the sub-management mode under the management queue where the potassium blood data of the renal dialysis patients is located. The present invention achieves the effect of refined management of the potassium blood data of renal dialysis patients by matching appropriate management queues and sub-management modes to the potassium blood data of renal dialysis patients.

Description

Technical Field

[0001] The present invention relates to the technical field of medical management, and particularly to an intelligent management method and system for blood potassium data of renal dialysis patients. Background Art

[0002] The kidney plays a crucial role in the body's electrolyte balance, especially in the regulation of blood potassium. The kidney maintains the normal blood potassium concentration in the body by filtering, reabsorbing, and excreting potassium ions. Blood potassium is one of the important electrolytes in the body. Potassium ions are directly involved in metabolic activities inside and outside cells, including maintaining cell metabolism, regulating body fluid osmotic pressure, maintaining acid-base balance, and maintaining cell stress function, etc. For end-stage renal disease patients undergoing renal dialysis, abnormal blood potassium levels can significantly increase the risk of adverse cardiovascular events in patients, such as arrhythmia, cardiac arrest, and cardiovascular events. Therefore, during the chronic disease management of dialysis patients, it is necessary to closely monitor the blood potassium index to ensure that it remains within the normal range. For renal dialysis medical staff, ensuring the balance of blood potassium levels is a very important part of the daily management of renal dialysis patients. They need to adjust the chronic disease management plan of patients according to the specific situation of patients, conduct risk management of blood potassium for patients, and prevent adverse consequences caused by abnormal blood potassium. For dialysis patients, blood potassium is one of the biochemical indexes routinely detected monthly, and it is greatly affected by individualization, which results in an extremely large volume of blood potassium data, making it complex to manage, and thus the demand for blood potassium data management is also increasing day by day.

[0003] The existing management of blood potassium data of renal dialysis patients usually monitors and manages the blood potassium data in a single way based on preset algorithms and rules. The unified management mode may not meet the blood potassium data characteristics of different renal dialysis patients, which will not only cause great difficulty in data management, but also affect the access and use of blood potassium data by personnel. Therefore, there is a problem that it is difficult to conduct refined management of the blood potassium data of renal dialysis patients. Summary of the Invention

[0004] The present invention provides an intelligent management method and system for blood potassium data of renal dialysis patients, which solves the problem in the prior art that it is difficult to conduct personalized management of the blood potassium data of renal dialysis patients, and realizes effective management of the blood potassium data of renal dialysis patients.

[0005] To achieve the above-mentioned invention objectives, the technical solutions provided by the present invention are as follows:

[0006] An intelligent management method and system for potassium blood data of renal dialysis patients, comprising: obtaining the potassium blood data of renal dialysis patients uploaded through an upload channel for preliminary quality analysis, and determining a quality analysis result, where the quality analysis result is qualified or unqualified; when the quality analysis result is determined to be qualified, retrieving the individual information of the renal dialysis patient from the potassium blood data of the renal dialysis patient; counting the information of each management queue in the potassium blood data management center, and processing it in combination with the individual information of the renal dialysis patient to confirm the potassium blood data management queue of the renal dialysis patient; and obtaining the potassium blood data management constraint parameters of the renal dialysis patient according to the potassium blood data management queue of the renal dialysis patient and performing processing.

[0007] Optionally, the specific process of obtaining the potassium blood data of renal dialysis patients uploaded through an upload channel for preliminary quality analysis is as follows: extracting data upload channel parameters from the upload channel, where the data upload channel parameters include: data upload delay time, data upload average rate, and peak channel upload data volume; extracting data feature parameters and image feature parameters from the uploaded potassium blood data of renal dialysis patients, where the data feature parameters include: number of missing field fills, data field fill density, and cumulative data format error value, and the image feature parameters include: average image resolution, average image contrast, and average image signal-to-noise ratio; and performing comprehensive processing based on the data upload channel parameters, data feature parameters, and image feature parameters to obtain the data quality analysis value of the potassium blood data.

[0008] Optionally, the specific method for obtaining the data quality analysis value of the potassium blood data is as follows:

[0009] ;

[0010] In the formula, represents the data quality analysis value of the potassium blood data, represents the data upload delay time, represents the preset data upload delay time threshold, represents the data upload average rate, represents the preset data upload average rate threshold, represents the peak channel upload data volume, represents the preset channel upload data volume threshold, represents the number of missing field fills, represents the preset number of missing field fills threshold, represents the data field fill density, represents the preset data field fill density reference value, represents the cumulative data format error value, represents the preset cumulative data format error value threshold, represents the average image resolution, represents a preset reference value of the average image resolution, represents the average image contrast, represents a preset reference value of the average image contrast, represents the average signal-to-noise ratio of the image, represents a preset threshold of the average signal-to-noise ratio of the image, is the natural constant.

[0011] Optionally, the determination obtains a quality analysis result, and the specific process is as follows: obtain a preset data quality analysis threshold, compare the data quality analysis value of the blood potassium data with the data quality analysis threshold. When the data quality analysis value of the blood potassium data is less than the data quality analysis threshold, the quality analysis result of the blood potassium data of the hemodialysis patient is determined to be unqualified. When the data quality analysis value of the blood potassium data is greater than or equal to the data quality analysis threshold, the quality analysis result of the blood potassium data of the hemodialysis patient is determined to be qualified.

[0012] Optionally, the process of confirming the management queue of the blood potassium data of the hemodialysis patient is as follows: based on the management queue information of the blood potassium data management center, the management queue information includes the individual sample information of each management queue and the dialysis information parameters of each existing data packet in each management queue; the individual sample information of each management queue includes: age reference value, height reference value, and weight reference value; based on the dialysis information parameters of each existing data packet in each management queue, where the dialysis information parameters include the cumulative dialysis times, dialysis frequency, and initial dialysis interval duration, perform a mean process on the dialysis information parameters of each existing data packet one by one to obtain the mean value of the dialysis information parameters of the existing data packets in each management queue, and the mean value of the dialysis information parameters includes the mean value of the cumulative dialysis times, dialysis frequency, and initial dialysis interval duration of the existing data packets in each management queue; retrieve the individual information of the hemodialysis patient from the blood potassium data of the hemodialysis patient, specifically including the age, height, weight, cumulative dialysis times, dialysis frequency, and initial dialysis interval duration of the hemodialysis patient; based on the individual information of the hemodialysis patient, and synchronously combine the individual sample information of each management queue and the mean value of the dialysis information parameters of the existing data packets in each management queue for comprehensive processing to obtain the storage embedding value between the blood potassium data of the hemodialysis patient and each management queue, and match the target management queue of the blood potassium data of the hemodialysis patient according to the storage embedding value, and use it as the management queue of the blood potassium data of the hemodialysis patient; the storage embedding value between the blood potassium data of the hemodialysis patient and each management queue is used to represent the matching degree of the blood potassium data of the hemodialysis patient stored in each management queue.

[0013] Optionally, the process of obtaining the target management queue for the potassium blood level data of the hemodialysis patient according to the stored embedding value is as follows: Obtain the stored embedding values between the potassium blood level data of the hemodialysis patient and each management queue, sort the stored embedding values between the potassium blood level data of the hemodialysis patient and each management queue from largest to smallest, and select the management queue corresponding to the largest stored embedding value as the target management queue for the potassium blood level data of the hemodialysis patient.

[0014] Optionally, the process of obtaining the management constraint parameter for the potassium blood level data of the hemodialysis patient is as follows: Extract the potassium blood level change curves for each hemodialysis of the hemodialysis patient from the potassium blood level data of the hemodialysis patient, and statistically process the characteristic parameters of the potassium blood level change curves for each hemodialysis of the hemodialysis patient to obtain the first characteristic parameter of the potassium blood level change curve of the hemodialysis patient; Based on the information of each management queue in the potassium blood level data management center, obtain the potassium blood level characteristic curve set of each existing data packet in the target management queue and extract the data quality analysis values of each existing data packet. The potassium blood level characteristic curve set includes the peak value, valley value, maximum pulse width, and change rate of the potassium blood level characteristic curve. Perform mean processing on the potassium blood level characteristic curve sets of each existing data packet to obtain the potassium blood level characteristic curve comparison set of the data packets in the target management queue; Based on the first characteristic parameter of the potassium blood level change curve of the hemodialysis patient, the potassium blood level characteristic curve comparison set, the data quality analysis value of the potassium blood level data, and the data quality analysis values of each existing data packet, process to obtain the deep aggregation value between the potassium blood level data of the hemodialysis patient and the target management queue. The deep aggregation value between the potassium blood level data of the hemodialysis patient and the target management queue is used to represent the data fitting degree between the potassium blood level data of the hemodialysis patient and the existing data packets, and determine the management constraint parameter for the potassium blood level data of the hemodialysis patient through the deep aggregation value between the potassium blood level data of the hemodialysis patient and the target management queue.

[0015] Optionally, the first characteristic parameter of the potassium blood level change curve includes: the first peak value, the first valley value, the first maximum pulse width, and the first change rate of the potassium blood level change curve of the hemodialysis patient; The potassium blood level characteristic curve set specifically includes the average peak value, average valley value, average maximum pulse width, and average change rate of the potassium blood level characteristic curve of the data packets in the target management queue.

[0016] Optionally, the process of obtaining the potassium blood data management constraint parameters for renal dialysis patients is as follows: Based on the deep aggregation value between the potassium blood data of renal dialysis patients and the target management cohort, and obtaining the branch cohorts corresponding to each preset deep aggregation value interval, map the deep aggregation value between the potassium blood data of renal dialysis patients and the target management cohort to the branch cohorts corresponding to each preset deep aggregation value interval, obtain the branch cohort corresponding to the interval where the deep aggregation value between the potassium blood data of renal dialysis patients and the target management cohort is located, and mark it as the target sub-cohort of the potassium blood data of renal dialysis patients; statistically analyze the data quality analysis value of the potassium blood data of renal dialysis patients, match it with the adaptive inspection period corresponding to each preset data quality analysis value interval, obtain the adaptive inspection period of the potassium blood data of renal dialysis patients, and record it as the target adaptive inspection period of the potassium blood data of renal dialysis patients; jointly mark the potassium blood data management cohort of renal dialysis patients, the target sub-cohort of the potassium blood data of renal dialysis patients, and the adaptive inspection period of the potassium blood data as the potassium blood data management constraint parameters.

[0017] The embodiment of the present invention provides a system for an intelligent management method of potassium blood data for renal dialysis patients, including: a quality analysis module: used to obtain the potassium blood data of renal dialysis patients uploaded through the upload channel for preliminary quality analysis, and determine the quality analysis result, where the quality analysis result is qualified or unqualified; an information retrieval module: used to retrieve the individual information of renal dialysis patients from the potassium blood data of renal dialysis patients when the quality analysis result is determined to be qualified; a management cohort matching module: used to count the information of each management cohort in the potassium blood data management center, and process it in combination with the individual information of renal dialysis patients to confirm the potassium blood data management cohort of renal dialysis patients; a management constraint parameter acquisition module: used to process according to the potassium blood data management cohort of renal dialysis patients to obtain the potassium blood data management constraint parameters of renal dialysis patients.

[0018] The above technical solution has at least the following beneficial effects compared with the prior art:

[0019] In the above solution, by retrieving the individual information of renal dialysis patients with a qualified quality analysis result and combining the individual information reference value of the management cohort, the renal dialysis patients are accurately assigned to the appropriate management cohort, and according to the deep aggregation value between the potassium blood data of renal dialysis patients and the target management cohort, the target sub-cohort of the potassium blood data of renal dialysis patients is matched, so that the potassium blood data of renal dialysis patients obtains a management sub-cohort suitable for their situation, realizing personalized management services and effectively automating the management of potassium blood data.

[0020] By conducting a preliminary quality analysis on the potassium blood level data of renal dialysis patients, it is possible to effectively determine whether the uploaded potassium blood level data is qualified, avoid misallocation of the management queue caused by poor quality of potassium blood level data, promptly detect quality problems in the potassium blood level data, ensure the accuracy and reliability of the potassium blood level data of renal dialysis patients through multi-level data quality analysis, and effectively improve the management quality of potassium blood level data.

[0021] By analyzing the curve characteristic parameters of the potassium blood level change curve of the patient and the potassium blood level characteristic curve sets of each existing data packet in the target management queue, it is possible to accurately match the target sub-queue where the potassium blood level data of the renal dialysis patient is more similar, and accurately and efficiently manage the potassium blood level data of the renal dialysis patient.

[0022] By matching the data quality analysis value of the potassium blood level data of the renal dialysis patient with the adaptive inspection period corresponding to each preset data quality analysis value interval, the adaptive inspection period of the potassium blood level data of the renal dialysis patient is accurately determined, realizing regular inspection of the management queue of the potassium blood level data of the renal dialysis patient. When the potassium blood level data of the renal dialysis patient does not match the currently affiliated management queue, it can be replaced in a timely manner, realizing dynamic management of the potassium blood level data of the renal dialysis patient, and enabling more efficient management of the potassium blood level data of the renal dialysis patient. Description of the Drawings

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following-described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0024] Figure 1 It is a schematic flowchart of the method according to the embodiment of the present invention;

[0025] Figure 2 It is a schematic diagram of the system module according to the embodiment of the present invention. Detailed Embodiments

[0026] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions of the embodiments of the present invention in conjunction with the drawings of the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the described embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0027] Unless otherwise defined, the technical terms or scientific terms used in the present invention shall have the ordinary meanings as understood by those of ordinary skill in the field to which the present invention pertains. The terms "first", "second" and similar terms used in the present invention do not denote any order, quantity or importance, but are only used to distinguish different components. Similarly, the terms such as "a", "an" or "the" do not denote a quantity limitation, but mean that there is at least one. The terms such as "comprising" or "including" mean that the elements or objects appearing before the term cover the elements or objects listed after the term and their equivalents, without excluding other elements or objects. The terms such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect.

[0028] It should be noted that the terms "upper", "lower", "left", "right", "front", "rear", etc. used in the present invention are only used to represent relative positional relationships. When the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0029] In view of the problem that it is difficult to perform refined management on the blood potassium data of renal dialysis patients in the prior art, the present invention provides a method and system for intelligent management of blood potassium data of renal dialysis patients, which can effectively manage the blood potassium data of renal dialysis patients.

[0030] As Figure 1 shown, an embodiment of the present invention provides a method for intelligent management of blood potassium data of renal dialysis patients, including: obtaining the blood potassium data of renal dialysis patients uploaded through an upload channel for preliminary quality analysis, and determining a quality analysis result, where the quality analysis result is qualified or unqualified; when the quality analysis result is determined to be qualified, retrieving the individual information of the renal dialysis patients from the blood potassium data of the renal dialysis patients; counting the information of each management queue in the blood potassium data management center, and processing it in combination with the individual information of the renal dialysis patients to confirm the blood potassium data management queue of the renal dialysis patients; and obtaining the blood potassium data management constraint parameters of the renal dialysis patients according to the blood potassium data management queue of the renal dialysis patients and performing processing.

[0031] In this embodiment, for the potassium blood level data of hemodialysis patients obtained, in order to ensure the security and privacy protection of the potassium blood level data of hemodialysis patients, it is necessary to keep the potassium blood level data of hemodialysis patients confidential and encrypted, and the potassium blood level data of hemodialysis patients is encrypted using the Advanced Encryption Standard (such as the AES-256-bit encryption algorithm) during the transmission and storage processes. It should be noted that the potassium blood level data of hemodialysis patients includes the basic information of hemodialysis patients (such as age and weight, etc.), the basic dialysis information of hemodialysis patients, and the potassium blood level-related information of hemodialysis patients, as well as the potassium blood level concentration data of each hemodialysis of hemodialysis patients and other related data. The potassium blood level data of hemodialysis patients uploaded through the upload channel may include image data, and doctors or patients may upload image data related to hemodialysis patients. The obtained information is integrated to obtain the potassium blood level data of hemodialysis patients, and data quality analysis is performed on the potassium blood level data of this hemodialysis patient. It should be noted that the potassium blood level data management center is a place for centrally storing, processing, managing, and analyzing data. The potassium blood level data management center includes multiple management queues, and each management queue contains various branch queues. The management queue is a queue that combines the basic information of similar patients, comprehensively manages data packets with similar basic information of a certain type of patients, and the basic information of patients includes patient individual information and dialysis information. The branch queue is a refinement of the management queue and is a queue that manages similar characteristic parameters of the potassium blood level change curve.

[0032] Among them, the preliminary quality analysis is performed on the potassium blood level data of hemodialysis patients uploaded through the upload channel. The specific process is as follows: Extract the data upload channel parameters from the upload channel. The data upload channel parameters include: data upload delay time, average data upload rate, and peak channel upload data volume; Extract the data characteristic parameters and image characteristic parameters from the uploaded potassium blood level data of hemodialysis patients. The data characteristic parameters include: number of missing field fills, data field fill density, and cumulative data format error value. The image characteristic parameters include: average image resolution, average image contrast, and average image signal-to-noise ratio; Based on the data upload channel parameters, data characteristic parameters, and image characteristic parameters, comprehensive processing is performed to obtain the data quality analysis value of the potassium blood level data.

[0033] In this embodiment, the data upload delay time is the time required from the start of data upload to the completion of upload. The average data upload rate is the average of the overall data upload rate, and the peak channel upload data volume refers to the maximum transmission volume of data uploaded through the channel. The data upload delay time, average data upload rate, and peak channel upload data volume are obtained through network performance monitoring software.

[0034] In this embodiment, the data characteristic parameter is a parameter used to represent the perfection degree of the blood potassium data of renal dialysis patients. The number of missing field fills is the number of data fields with missing values. The data field fill density is the ratio of the filled fields to the total fields. The cumulative data format error value is the total number of data uploaded that does not meet the predetermined format requirements. The number of missing field fills, the data field fill density, and the cumulative data format error value are obtained through data analysis and processing software.

[0035] In this embodiment, the average image resolution refers to the clarity of details in the image, which is the average number of pixel points per unit area in the image. The average image contrast is the average value of the brightness difference between the brightest and darkest regions in the image. The average image signal-to-noise ratio is the average value of the ratio of the useful signal to the background noise in the image. The average image resolution, the average image contrast, and the average image signal-to-noise ratio are obtained through image processing software.

[0036] Among them, the specific method for obtaining the data quality analysis value of the blood potassium data is as follows:

[0037] ;

[0038] In the formula, represents the data quality analysis value of the blood potassium data, represents the data upload delay time, represents the preset data upload delay time threshold, represents the average data upload rate, represents the preset average data upload rate threshold, represents the peak value of the data volume uploaded through the channel, represents the preset data volume threshold for channel upload, represents the number of missing field fills, represents the preset threshold for the number of missing field fills, represents the data field fill density, represents the preset reference value for the data field fill density, represents the cumulative data format error value, represents the preset threshold for the cumulative data format error value, represents the average image resolution, represents the preset reference value for the average image resolution, represents the average image contrast, represents the preset reference value for the average image contrast, represents the average image signal-to-noise ratio, represents the preset threshold for the average image signal-to-noise ratio, is the natural constant.

[0039] In this embodiment, the data upload delay time threshold, the data upload average rate threshold, the channel upload data volume threshold, the field filling missing number threshold, the data field filling density reference value, the cumulative data format error value threshold, the image average resolution reference value, the image average contrast reference value, and the image average signal-to-noise ratio threshold are obtained from the database.

[0040] In this embodiment, the data upload channel parameters, the data feature parameters, and the image feature parameters are interrelated and interact with each other, and together they also reflect the quality of the blood potassium data of renal dialysis patients. The data upload delay time is related to the data upload average rate and the peak value of the channel upload data volume. When the delay is high, the data transmission efficiency is low, and the data upload average rate may become low. If the data upload delay time is too high, the upload may fail, resulting in an increase in the peak value of the channel upload data volume. When the data upload average rate is high, the corresponding data upload delay time will be lower. At the same time, the data transmission process is faster, and the peak value of the channel upload data volume may also be relatively low. A too large peak value of the channel upload data volume will increase the data upload delay and may cause data packet loss or transmission errors, affecting the overall quality of the blood potassium data. The larger the number of missing field fillings usually means poorer data integrity. A low field filling density usually reflects incomplete data with more missing fields, affecting data quality. When the number of missing field fillings is large, the data field filling density is usually low. A long data delay time or a low data upload average rate may cause a delay in the field filling process, possibly resulting in an increase in the number of missing field fillings. When there are format errors in data upload, it may cause some fields to be unable to be correctly recognized and filled, thereby increasing the number of missing fillings, that is, a larger cumulative data format error value may lead to an increase in the number of missing field fillings. This results in a lower data field filling density. The number of missing field fillings and the cumulative data format error value are closely related. A large number of missing field fillings will cause the upload to fail, thus increasing the peak value of the channel upload data volume. More field types may increase the probability of format errors. Images with a higher average image resolution usually require a longer upload time because of the large amount of data, which may lead to a higher delay. A higher average image contrast usually means a stronger image signal and relatively less noise, so the average image signal-to-noise ratio is higher. Images with a high average image resolution can better present the differences in average image contrast. Images with a higher average image resolution and a higher average image contrast usually have a higher signal-to-noise ratio. Images with a low signal-to-noise ratio may cause errors during upload due to quality problems, resulting in repeated uploads, thereby increasing the peak value of the channel upload data volume. In short, the data upload channel parameters, the data feature parameters, and the image feature parameters all affect the quality of the blood potassium data. This embodiment synthesizes the above factors and effectively improves the quality of the blood potassium data.

[0041] In this embodiment, the quality of blood potassium data is closely related to the stability and reliability of data transmission. If the average data upload rate is too low, it may cause packet loss, transmission errors or delays during data transmission, thus affecting the quality of blood potassium data. If the average data upload rate is unstable or insufficient, it may lead to some blood potassium data failing to be successfully uploaded, or the uploaded data being incomplete, thus reducing the accuracy and integrity of the data. A relatively long data upload delay time may be related to problems such as unstable network connection and complex data processing. These factors will all affect the quality of blood potassium data. If the peak value of the data volume uploaded through the channel is too high, it may cause network congestion or bandwidth overload, resulting in data loss or delay during data transmission, thus affecting the quality of blood potassium data.

[0042] Among them, to determine the quality analysis result, the specific process is as follows: Obtain the preset data quality analysis threshold, compare the data quality analysis value of the blood potassium data with the data quality analysis threshold. When the data quality analysis value of the blood potassium data is less than the data quality analysis threshold, the quality analysis result of the blood potassium data of the renal dialysis patient is determined to be unqualified. When the data quality analysis value of the blood potassium data is greater than or equal to the data quality analysis threshold, the quality analysis result of the blood potassium data of the renal dialysis patient is determined to be qualified.

[0043] In this embodiment, when the quality analysis result is determined to be qualified, retrieve the individual information of the renal dialysis patient from the blood potassium data of the renal dialysis patient, and allocate a management queue for the individual information of the renal dialysis patient.

[0044] Among them, the blood potassium data management queue of renal dialysis patients is confirmed, and the specific process is: based on the management queue information of the blood potassium data management center, the information of each management queue includes the individual sample information of each management queue and the dialysis information parameters of each existing data packet in each management queue; the individual sample information of each management queue includes: age reference value, height reference value and weight reference value; based on the dialysis information parameters of each existing data packet in each management queue, wherein the dialysis information parameters include the cumulative number of dialysis sessions, the dialysis frequency and the initial dialysis interval, the dialysis information parameters of each existing data packet are averaged one by one to obtain the mean of the dialysis information parameters of the existing data packets in each management queue, and the mean of the dialysis information parameters includes the mean of the cumulative number of dialysis sessions, the mean of the dialysis frequency and the initial dialysis interval of the existing data packets in each management queue. The mean duration of the dialysis interval; the individual information of the renal dialysis patients is retrieved from the blood potassium data of the renal dialysis patients, specifically including the age, height, weight, cumulative number of dialysis sessions, dialysis frequency and duration of the first dialysis interval of the renal dialysis patients; based on the individual information of the renal dialysis patients, the individual sample information of each management cohort and the mean value of the dialysis information parameters of the existing data packets in each management cohort are synchronously processed to obtain the storage embedding value between the blood potassium data of the renal dialysis patients and each management cohort, and the target management cohort of the blood potassium data of the renal dialysis patients is obtained according to the matching of the storage embedding value, and is used as the management cohort of the blood potassium data of the renal dialysis patients; the storage embedding value between the blood potassium data of the renal dialysis patients and each management cohort is used to characterize the matching degree of the blood potassium data of the renal dialysis patients stored in each management cohort.

[0045] In this embodiment, when matching the blood potassium data management queue of renal dialysis patients, the hyperkalemia risk screening scale score of renal dialysis patients can be added. Each management queue is provided with a standard hyperkalemia risk screening scale score interval. For example, the standard hyperkalemia risk screening scale score interval of renal dialysis patients in a certain management queue is 4-6 points. The above is just a simple example. The standard hyperkalemia risk screening scale score interval of each management queue is determined according to the actual situation. The middle value of the standard hyperkalemia risk screening scale score interval of each management queue is taken as the standard hyperkalemia risk screening scale score of each management queue. Before the renal dialysis patients are assigned to the management queue, the hyperkalemia risk screening scale score of the renal dialysis patients can be obtained. It can be obtained by filling out the hyperkalemia risk screening scale for maintenance hemodialysis patients and calculating it, or by calculating it according to the information provided by the renal dialysis patients. The hyperkalemia risk screening scale for maintenance hemodialysis patients provided in this embodiment is shown in Table 1:

[0046] Table 1 Hyperkalemia risk screening scale for maintenance hemodialysis patients

[0047]

[0048]

[0049] In this embodiment, the specific method for obtaining the stored embedding values between the blood potassium data of renal dialysis patients and each management queue is as follows:

[0050] ;

[0051] In the formula, represents the stored embedding value between the blood potassium data of renal dialysis patients and the th management queue, , is the total number of management queues, represents the age of renal dialysis patients, represents the age reference value of the existing data packets in the th management queue, represents the height of renal dialysis patients, represents the height reference value of the existing data packets in the th management queue, represents the weight of renal dialysis patients, represents the weight reference value of the existing data packets in the th management queue, represents the cumulative dialysis times of renal dialysis patients, represents the average value of the cumulative dialysis times of the existing data packets in the th management queue, represents the dialysis frequency of renal dialysis patients, represents the average value of the dialysis frequencies of the existing data packets in the th management queue, represents the initial dialysis interval duration of renal dialysis patients, represents the average value of the initial dialysis interval durations of the existing data packets in the th management queue, represents the score of the hyperkalemia risk screening scale for renal dialysis patients, represents the standard hyperkalemia risk screening scale score of the th management queue, is the natural constant.

[0052] In this embodiment, the individual sample information of each management queue is the sample reference value set for the existing data packets in the comprehensive management queue of each management queue. The setting of the individual sample information of each management queue is used to judge the matching degree between the individual information of renal dialysis patients and the individual sample information of this management queue.

[0053] In this embodiment, the cumulative dialysis times refer to the cumulative number of times a renal dialysis patient undergoes renal dialysis, the dialysis frequency refers to the frequency of renal dialysis for a renal dialysis patient, the duration between the first dialysis and the time of obtaining the potassium blood data of the renal dialysis patient is the initial dialysis interval duration, and the age, height, weight, cumulative dialysis times, dialysis frequency, and initial dialysis interval duration are extracted from the potassium blood data of the renal dialysis patient.

[0054] In this embodiment, there is a certain association and an inseparable relationship among the individual information-related parameters, the reference values of individual sample information, and the reference values of dialysis information parameters. The closer the age, height, weight, cumulative dialysis times, dialysis frequency, and initial dialysis interval duration of a renal dialysis patient are to the age reference value, height reference value, weight reference value, average cumulative dialysis times, average dialysis frequency, and average initial dialysis interval duration, the higher the matching degree of the renal dialysis patient with this management cohort. There is a certain association between the age, height, and weight of a renal dialysis patient and the cumulative dialysis times, dialysis frequency, and initial dialysis interval duration. The age, height, and weight of a renal dialysis patient affect the dialysis frequency and dialysis effect. An increase in dialysis frequency is usually accompanied by an increase in cumulative dialysis times. A higher cumulative dialysis times and a shorter initial dialysis interval duration mean a higher dialysis frequency. The greater the dialysis frequency and the initial dialysis interval duration, the smaller the cumulative dialysis times. The age, height, and weight of a renal dialysis patient all reflect the physiological characteristics of the human body. Elderly patients usually suffer from chronic kidney disease for a longer time and often require dialysis treatment for a longer time. Therefore, as the age increases, the cumulative dialysis times of the patient tend to be more. Taller people may need more dialysis to maintain electrolyte balance in the body and excrete waste. Heavier patients have more fluids and metabolic waste in their bodies, so their dialysis needs are usually greater and they may need to increase the dialysis frequency.

[0055] Among them, the specific process of obtaining the target management cohort of the potassium blood data of a renal dialysis patient according to the stored embedding value is as follows: obtain the stored embedding values between the potassium blood data of the renal dialysis patient and each management cohort, sort the stored embedding values between the potassium blood data of the renal dialysis patient and each management cohort from largest to smallest, and select the management cohort corresponding to the largest stored embedding value as the target management cohort of the potassium blood data of the renal dialysis patient.

[0056] In this embodiment, the stored embedding values between the blood potassium data of the renal dialysis patient and each management queue characterize the matching degree of the individual information of the renal dialysis patient, the individual sample information of each management queue, and the dialysis information parameters of the existing data packets in each management queue. The larger the stored embedding value, the closer the relevant parameters of the individual information of the renal dialysis patient are to the individual sample information of the management queue and the dialysis information parameters of the existing data packets in the management queue, that is, the higher the matching degree with the management queue. Therefore, the management queue corresponding to the largest stored embedding value is selected as the target management queue for the blood potassium data of the renal dialysis patient.

[0057] Among them, the process of obtaining the management constraint parameters for the blood potassium data of the renal dialysis patient is as follows: extract the blood potassium concentration change curves of each renal dialysis of the renal dialysis patient from the blood potassium data of the renal dialysis patient, and statistically process the characteristic parameters of the blood potassium concentration change curves of each renal dialysis of the renal dialysis patient to obtain the first characteristic parameter of the blood potassium concentration change curve of the renal dialysis patient; based on the information of each management queue in the blood potassium data management center, obtain the blood potassium characteristic curve sets of each existing data packet in the target management queue and extract the data quality analysis values of each existing data packet. The blood potassium characteristic curve set includes the peak value, valley value, maximum pulse width, and change rate of the blood potassium characteristic curve. Perform mean processing on the blood potassium characteristic curve sets of each existing data packet to obtain the blood potassium characteristic curve comparison set of the data packets in the target management queue; based on the first characteristic parameter of the blood potassium concentration change curve of the renal dialysis patient, the blood potassium characteristic curve comparison set, the data quality analysis value of the blood potassium data, and the data quality analysis values of each existing data packet, process to obtain the deep aggregation value between the blood potassium data of the renal dialysis patient and the target management queue. The deep aggregation value between the blood potassium data of the renal dialysis patient and the target management queue is used to characterize the data embedding degree between the blood potassium data of the renal dialysis patient and the existing data packets, and determine the management constraint parameters for the blood potassium data of the renal dialysis patient through the deep aggregation value between the blood potassium data of the renal dialysis patient and the target management queue.

[0058] In this embodiment, the specific method for obtaining the deep aggregation value between the blood potassium data of the renal dialysis patient and the target management queue is as follows:

[0059] ;

[0060] In the formula, represents the deep aggregation value between the blood potassium data of the renal dialysis patient and the target management queue, represents the data quality analysis value of the blood potassium data, represents the data quality analysis value of the th data packet in the target management queue, , is the total number of data packets, represents the first peak value of the blood potassium concentration change curve of the renal dialysis patient, Represents the average peak value of the potassium blood level characteristic curve of the data packets in the target management queue, Represents the first trough value of the potassium blood level change curve of the renal dialysis patient, Represents the average trough value of the potassium blood level characteristic curve of the data packets in the target management queue, Represents the first maximum pulse width of the potassium blood level change curve of the renal dialysis patient, Represents the average maximum pulse width of the potassium blood level characteristic curve of the data packets in the target management queue, Represents the first change rate of the potassium blood level change curve of the renal dialysis patient, Represents the average change rate of the potassium blood level characteristic curve of the data packets in the target management queue, Is the natural constant, and the data quality analysis value of the th data packet in the target management queue is obtained from the database.

[0061] In this embodiment, the potassium blood level change curves of each renal dialysis of the renal dialysis patient reflect the change of the potassium blood level during the dialysis process. For many renal dialysis patients, the potassium blood level before dialysis is usually on the high side. When dialysis starts, the excess potassium in the patient's body will be removed from the blood, and the potassium blood level usually drops rapidly. At the end of dialysis, the patient's potassium blood level usually drops significantly. It should be noted that each existing data packet is the potassium blood level data packet of each historical doctor-patient in the target management queue of the renal dialysis patient. The characteristic parameters of the potassium blood level change curve are the peak value, trough value, maximum pulse width and change rate of the potassium blood level change curve. The characteristic parameters of the potassium blood level change curve of each renal dialysis of the renal dialysis patient are averaged to obtain the first characteristic parameter of the potassium blood level change curve of the renal dialysis patient.

[0062] Among them, the first characteristic parameter of the potassium blood level change curve includes: the first peak value, the first trough value, the first maximum pulse width and the first change rate of the potassium blood level change curve of the renal dialysis patient; the potassium blood level characteristic curve set specifically includes the average peak value, the average trough value, the average maximum pulse width and the average change rate of the potassium blood level characteristic curve of the data packets in the target management queue.

[0063] In this embodiment, the first peak value is the mean of the peak values of the potassium ion concentration change curves for each renal dialysis of renal dialysis patients. The peak value is the maximum value of the potassium ion concentration change curve. The first trough value is the mean of the trough values of the potassium ion concentration change curves for each renal dialysis of renal dialysis patients. The trough value is the minimum value of the potassium ion concentration change curve. The first maximum pulse width is the mean of the maximum pulse widths of the potassium ion concentration change curves for each renal dialysis of renal dialysis patients. The maximum pulse width is the maximum continuous duration in the potassium ion concentration curve. The first change rate is the mean of the change rates of the potassium ion concentration change curves for each renal dialysis of renal dialysis patients. The change rate is the rate of the largest change in potassium ion concentration. The peak value, trough value, change amplitude, and change rate can be obtained through Python software.

[0064] Among them, the process of obtaining the management constraint parameters for the potassium ion data of renal dialysis patients is as follows: Based on the deep aggregation value between the potassium ion data of renal dialysis patients and the target management queue, and obtaining the branch queues corresponding to each preset deep aggregation value interval, map the deep aggregation value between the potassium ion data of renal dialysis patients and the target management queue to the branch queues corresponding to each preset deep aggregation value interval, obtain the branch queue corresponding to the interval where the deep aggregation value between the potassium ion data of renal dialysis patients and the target management queue is located, and mark it as the target sub-queue of the potassium ion data of renal dialysis patients; count the data quality analysis value of the potassium ion data of renal dialysis patients, match it with the adaptive inspection period corresponding to each preset data quality analysis value interval, obtain the adaptive inspection period of the potassium ion data of renal dialysis patients, and record it as the target adaptive inspection period of the potassium ion data of renal dialysis patients; jointly mark the potassium ion data management queue of renal dialysis patients, the target sub-queue of the potassium ion data of renal dialysis patients, and the adaptive inspection period of potassium ion data as the management constraint parameters of potassium ion data.

[0065] In this embodiment, each preset deep aggregation value interval corresponds to a different branch queue. It should be noted that the branch queue is a branch queue under the management queue, and each branch queue stores corresponding potassium ion data. Map the deep aggregation value between the potassium ion data of renal dialysis patients and the target management queue to each preset deep aggregation value interval, and find the branch queue corresponding to the deep aggregation value between the potassium ion data of renal dialysis patients and the target management queue. Define this branch queue as the target sub-queue of the potassium ion data of renal dialysis patients, allocate the potassium ion data of renal dialysis patients to this target sub-queue, and execute the management measures of this target sub-queue.

[0066] In this embodiment, the deep aggregation value between the blood potassium data of renal dialysis patients and the target management queue is used to characterize the degree of data chimerism between the blood potassium data of renal dialysis patients and each existing data packet. Through the deep chimerism value, the branch queue where the data packet most similar to the blood potassium data of renal dialysis patients is located can be obtained, and the blood potassium data of renal dialysis patients can be effectively managed automatically. In addition, the target adaptive inspection period of the blood potassium data of renal dialysis patients is the adaptive inspection period of the target sub-queue of the blood potassium data of renal dialysis patients. According to the target adaptive inspection period of the blood potassium data of renal dialysis patients, the target management queue and the target sub-queue are regularly re-checked and replaced to achieve dynamic management of the blood potassium data of renal dialysis patients.

[0067] An embodiment of the present invention provides a system for an intelligent management method of blood potassium data of renal dialysis patients, including: a quality analysis module: used to obtain the blood potassium data of renal dialysis patients uploaded through the upload channel for preliminary quality analysis and determine the quality analysis result, and the quality analysis result is qualified or unqualified; an information retrieval module: used to retrieve the individual information of renal dialysis patients from the blood potassium data of renal dialysis patients when the quality analysis result is determined to be qualified; a management queue matching module: used to count the information of each management queue in the blood potassium data management center and process it in combination with the individual information of renal dialysis patients to confirm the blood potassium data management queue of renal dialysis patients; a management constraint parameter acquisition module: used to process according to the blood potassium data management queue of renal dialysis patients to obtain the blood potassium data management constraint parameters of renal dialysis patients. The following points need to be explained:

[0068] (1) The drawings of the embodiments of the present invention only relate to the structures involved in the embodiments of the present invention, and other structures can refer to the general design.

[0069] (2) For clarity, in the drawings used to describe the embodiments of the present invention, the thickness of layers or regions is enlarged or reduced, that is, these drawings are not drawn according to the actual scale. It can be understood that when an element such as a layer, film, region, or substrate is referred to as being "on" or "under" another element, the element can be "directly" on or under another element or there can be intermediate elements.

[0070] (3) Without conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other to obtain new embodiments.

[0071] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for intelligent management of blood potassium data for renal dialysis patients, characterized in that: include: Obtaining the blood potassium data of the renal dialysis patient uploaded by the upload channel for preliminary quality analysis, and determining the quality analysis result, wherein the quality analysis result is qualified or unqualified; The blood potassium data of the renal dialysis patients uploaded by the upload channel is obtained and a preliminary quality analysis is performed, and the specific process is as follows: Extracting data upload channel parameters from the upload channel, the data upload channel parameters including: data upload delay time, data upload average rate and channel upload data volume peak value; extracting data feature parameters and image feature parameters from the uploaded blood potassium data of renal dialysis patients, the data feature parameters including: field filling missing number, data field filling density and cumulative data format error value, the image feature parameters including: image average resolution, image average contrast and image average signal-to-noise ratio; performing comprehensive processing based on the data upload channel parameters, data feature parameters and image feature parameters to obtain the data quality analysis value of the blood potassium data; When the quality analysis result is judged as qualified, the individual information of the renal dialysis patient is retrieved from the blood potassium data of the renal dialysis patient; Collect the information of each management cohort of the blood potassium data management center, and process it in combination with the individual information of renal dialysis patients to confirm the blood potassium data management cohort of renal dialysis patients; A queue is managed according to the blood potassium data of renal dialysis patients, and the blood potassium data management constraint parameters of renal dialysis patients are obtained by processing; The processing to obtain the blood potassium data management constraint parameters of the renal dialysis patient is specifically performed as follows: Extracting the blood potassium concentration change curve of each renal dialysis of the renal dialysis patient from the blood potassium data of the renal dialysis patient, and statistically analyzing the characteristic parameters of the blood potassium concentration change curve of each renal dialysis of the renal dialysis patient for mean processing to obtain the first characteristic parameter of the blood potassium concentration change curve of the renal dialysis patient; Based on the information of each management queue of the blood potassium data management center, the blood potassium characteristic curve set of each existing data packet in the target management queue is obtained and the data quality analysis value of each existing data packet is extracted. The blood potassium characteristic curve set includes the peak value, valley value, maximum pulse width and change rate of the blood potassium characteristic curve. The blood potassium characteristic curve set of each existing data packet is averaged to obtain the blood potassium characteristic curve control set of the data packet in the target management queue; Based on the first characteristic parameter of the blood potassium concentration change curve of the renal dialysis patient and the control set of the blood potassium characteristic curve, the data quality analysis value of the blood potassium data and the data quality analysis value of each existing data packet, the deep aggregation value between the blood potassium data of the renal dialysis patient and the target management queue is processed to obtain the deep aggregation value between the blood potassium data of the renal dialysis patient and the target management queue. The deep aggregation value between the blood potassium data of the renal dialysis patient and the target management queue is used to characterize the degree of data chimerism between the blood potassium data of the renal dialysis patient and the existing data packets, and the blood potassium data management constraint parameters of the renal dialysis patient are determined through the deep aggregation value between the blood potassium data of the renal dialysis patient and the target management queue.

2. The intelligent management method for blood potassium data of renal dialysis patients according to claim 1, characterized in that: The specific method for obtaining the data quality analysis value of the blood potassium data is: ； In the formula, Represents the data quality analysis value of blood potassium data, Represents the data upload delay time, Represents the preset data upload delay time threshold. Represents the average data upload rate, Represents the preset average data upload rate threshold. Represents the peak value of the channel uploaded data. Represents the preset channel upload data volume threshold. Represents the number of missing fields to be filled. Represents the preset field filling missing number threshold, Represents the data field filling density, Represents the preset data field filling density reference value, Represents the cumulative data format error value, Represents the preset cumulative data format error value threshold, Represents the average image resolution, Represents the preset average image resolution reference value. represents the average contrast of the image, Represents the preset image average contrast reference value, represents the average signal-to-noise ratio of the image, Represents the preset image average signal-to-noise ratio threshold, is a natural constant.

3. The intelligent management method for blood potassium data of renal dialysis patients according to claim 1, characterized in that: The determination results in quality analysis, and the specific process is as follows: A preset data quality analysis threshold is obtained, and the data quality analysis value of the blood potassium data is compared with the data quality analysis threshold. When the data quality analysis value of the blood potassium data is less than the data quality analysis threshold, the quality analysis result of the blood potassium data of the renal dialysis patient is judged to be unqualified; when the data quality analysis value of the blood potassium data is greater than or equal to the data quality analysis threshold, the quality analysis result of the blood potassium data of the renal dialysis patient is judged to be qualified.

4. The intelligent management method for blood potassium data of renal dialysis patients according to claim 1, characterized in that: The specific process of confirming the blood potassium data management cohort of renal dialysis patients is as follows: Based on the management queue information of the blood potassium data management center, the management queue information includes the individual sample information of each management queue and the dialysis information parameters of each existing data packet in each management queue; The individual sample information of each management cohort includes: age reference value, height reference value and weight reference value; Based on the dialysis information parameters of each existing data packet in each management queue, wherein the dialysis information parameters include the cumulative number of dialysis sessions, the dialysis frequency, and the initial dialysis interval duration, the dialysis information parameters of each existing data packet are averaged one by one to obtain the average of the dialysis information parameters of the existing data packets in each management queue, wherein the average of the dialysis information parameters includes the average of the cumulative number of dialysis sessions, the average of the dialysis frequency, and the initial dialysis interval duration of the existing data packets in each management queue; Retrieving individual information of renal dialysis patients from their blood potassium data, including age, height, weight, cumulative number of dialysis sessions, dialysis frequency, and duration of the first dialysis session; Based on the individual information of renal dialysis patients, the individual sample information of each management queue and the mean value of the dialysis information parameters of the existing data packets in each management queue are synchronously processed to obtain the storage embedding value between the blood potassium data of renal dialysis patients and each management queue, and the target management queue of the blood potassium data of renal dialysis patients is obtained according to the matching of the storage embedding value, and used as the blood potassium data management queue of renal dialysis patients; The storage embedding value between the blood potassium data of the renal dialysis patient and each management cohort is used to characterize the matching degree of the blood potassium data of the renal dialysis patient stored in each management cohort.

5. The intelligent management method for blood potassium data of renal dialysis patients according to claim 4, characterized in that: The target management queue of the blood potassium data of the renal dialysis patients is obtained by matching the stored embedded values, and the specific process is as follows: The storage embedding values ​​between the blood potassium data of renal dialysis patients and each management queue are obtained, the storage embedding values ​​between the blood potassium data of renal dialysis patients and each management queue are sorted from large to small, and the management queue corresponding to the maximum storage embedding value is selected as the target management queue for the blood potassium data of renal dialysis patients.

6. The intelligent management method for blood potassium data of renal dialysis patients according to claim 1, characterized in that: The first characteristic parameter of the blood potassium concentration change curve includes: a first peak value, a first valley value, a first maximum pulse width and a first change rate of the blood potassium concentration change curve of the renal dialysis patient; The blood potassium characteristic curve set specifically includes an average peak value, an average valley value, an average maximum pulse width, and an average change rate of the blood potassium characteristic curves of the data packets in the target management queue.

7. The intelligent management method for blood potassium data of renal dialysis patients according to claim 1, characterized in that: The specific process of obtaining the blood potassium data management constraint parameters of the renal dialysis patient is as follows: Based on the deep aggregation value between the blood potassium data of the renal dialysis patient and the target management cohort, the branch cohorts corresponding to the preset intervals of each deep aggregation value are obtained, and the deep aggregation value between the blood potassium data of the renal dialysis patient and the target management cohort is mapped with the branch cohorts corresponding to the preset intervals of each deep aggregation value, so as to obtain the branch cohort corresponding to the interval where the deep aggregation value between the blood potassium data of the renal dialysis patient and the target management cohort is located, and the branch cohort is marked as the target sub-cohort of the blood potassium data of the renal dialysis patient; The data quality analysis values ​​of the blood potassium data of the renal dialysis patients are counted, and matched with the adaptive inspection cycles corresponding to the preset data quality analysis value intervals to obtain the adaptive inspection cycle of the blood potassium data of the renal dialysis patients, which is recorded as the target adaptive inspection cycle of the blood potassium data of the renal dialysis patients; The blood potassium data management queue of renal dialysis patients, the blood potassium data target sub-queue of renal dialysis patients, and the blood potassium data adaptive inspection period are collectively marked as blood potassium data management constraint parameters.

8. A system using the method for intelligent management of blood potassium data of renal dialysis patients as claimed in any one of claims 1 to 7, characterized in that: include: Quality analysis module: used to obtain the blood potassium data of the renal dialysis patients uploaded by the upload channel for preliminary quality analysis, and determine the quality analysis result, which is qualified or unqualified; Information retrieval module: used to retrieve individual information of renal dialysis patients from their blood potassium data when the quality analysis result is determined to be qualified; Management queue matching module: used to collect statistics on the management queue information of the blood potassium data management center, and process it in combination with the individual information of renal dialysis patients to confirm the blood potassium data management queue of renal dialysis patients; Management constraint parameter acquisition module: used to manage the queue according to the blood potassium data of the renal dialysis patients, and process and obtain the blood potassium data management constraint parameters of the renal dialysis patients.

Images