A method, device and storage medium for full-process health monitoring of hemodialysis patients

Abstract

This application relates to the field of health monitoring technology, and discloses a method, device, and storage medium for full-process health monitoring of hemodialysis patients. The method includes: acquiring the patient's historical dialysis data, basic information, and initial physiological data, and inputting them into a first preset model to predict dialysis parameters; during dialysis, collecting human dynamic parameters, physiological state data, and hemodialysis data according to a preset cycle; statistically analyzing the collected data to determine whether dialysis parameters need adjustment; if so, generating new dialysis parameters and continuing the dialysis process; after dialysis, generating a phased purification assessment value based on historical dialysis data and dialysis monitoring data, and generating reminder information in conjunction with historical behavioral habit data; and sending the assessment value and reminder information to the patient's terminal. This application's technical solution achieves accurate monitoring and personalized management throughout the dialysis process, improving the level of intelligence in health monitoring.

Description

Technical Field

[0001] This application relates to the field of health monitoring technology, and in particular to a method, device and storage medium for full-process health monitoring of hemodialysis patients. Background Technology

[0002] With an aging population and an increase in chronic diseases, the number of hemodialysis patients is rising year by year. Hemodialysis is one of the main treatment methods for patients with end-stage renal disease (ESRD), aiming to replace the filtration function of the kidneys and remove metabolic waste and excess water from the body. During dialysis treatment, the patient's physiological state undergoes dynamic changes, and real-time monitoring of these changes is crucial for timely detection of potential problems and optimization of treatment plans. Meanwhile, hemodialysis patients require long-term treatment, and issues such as poor treatment adherence and low self-management levels exist, making information management and patient education during treatment essential. With the development of artificial intelligence, big data, and Internet of Things technologies, the medical field has begun to explore the application of these technologies to the health management of hemodialysis patients.

[0003] A similar prior art is disclosed in Chinese patent application CN118749932A, which discloses a method and system for monitoring patient health data during hemodialysis. This method acquires blood pressure data at a first monitoring time point, issues an alarm and implements abnormal blood pressure management measures when abnormalities are detected. It also acquires heart rate data at a second monitoring time point, and issues an alarm and implements abnormal heart rate management measures when an abnormality is detected within the current analysis time period at a preset analysis time point. For each analysis time point, it calculates short-term and long-term heart rate fluctuation values, and sets a first and second adjustment threshold based on the long-term heart rate fluctuation value. If the short-term heart rate fluctuation value is greater than the first adjustment threshold but less than the second adjustment threshold, it implements frequency adjustment measures. If the short-term heart rate fluctuation value is greater than the second adjustment threshold, it acquires a heart rate prediction set based on the frequency adjustment measures, inputs the prediction set into a heart rate prediction model to obtain a predicted heart rate dataset, and issues an alarm and implements abnormal heart rate management measures when an anomaly is found in the predicted heart rate dataset. This method only monitors blood pressure and heart rate, does not cover comprehensive physiological data, and lacks dynamic adjustment of dialysis parameters and comprehensive health management. Another Chinese patent application, CN118737473A, discloses a method and system for patient health monitoring based on hemodialysis data analysis. This method collects patient body data and hemodialysis data, analyzes the correlation values ​​between the data to construct a correlation dataset, performs clustering calculations using a clustering algorithm based on the patient correlation dataset, analyzes patient feature sets in different clusters, analyzes patient body data based on the patient feature sets in different clusters, calculates improvement values, predicts patient health scores, analyzes improvement values ​​to determine the patient's physical condition, and adjusts improvement suggestions based on the patient's physical condition; and encrypts and transmits data based on different patient clusters, generates reports, and sends the reports. However, this method does not provide precise analysis of nutritional intake and lacks personalized guidance for patients.

[0004] Therefore, providing a method, device, and storage medium for comprehensive health monitoring of hemodialysis patients to improve the comprehensiveness, accuracy, and personalization of health monitoring is an urgent problem to be solved. Summary of the Invention

[0005] This application provides a method, device, and storage medium for full-process health monitoring of hemodialysis patients. By real-time monitoring and dynamic adjustment of dialysis parameters, combined with patient behavior data, it achieves accurate monitoring and personalized management throughout the dialysis process. While improving the accuracy of dialysis, it also enhances the comprehensiveness and personalization of health monitoring, realizing intelligent and full-process management and improving the treatment experience.

[0006] In a first aspect, this application provides a method for full-process health monitoring of hemodialysis patients, the method comprising:

[0007] Step 1: Obtain the patient's historical dialysis data, basic information, and initial physiological data. Input the historical dialysis data, basic information, and initial physiological data into the first preset model to predict the patient's dialysis parameters and obtain the dialysis parameters.

[0008] Step 2: Perform the dialysis process based on the dialysis parameters, and collect the human dynamic parameters, physiological status data and hemodialysis data during the dialysis process according to the preset cycle;

[0009] Step 3: Perform statistical analysis on the hemodialysis data collected at each time point within the first preset time period to determine whether the dialysis parameters need to be adjusted. If so, generate new dialysis parameters and return to step 2. If not, proceed to step 4.

[0010] Step 4: Determine whether the amount of physiological state data collected in the current monitoring phase has reached the first preset value. If not, return to step 2. If yes, perform statistical analysis on the physiological state data and hemodialysis data to determine whether the dialysis parameters need to be adjusted. If yes, generate new dialysis parameters and return to step 2, while starting the next monitoring phase. If not, return to step 2.

[0011] Step 5: After dialysis is completed, obtain the dialysis monitoring data for the current treatment course, generate a phased purification assessment value based on historical dialysis data and dialysis monitoring data, and obtain historical behavioral habit data within a second preset time period. Generate reminder information based on initial physiological data and historical behavioral habit data. The dialysis monitoring data includes basic information, initial physiological data, physiological state data, and hemodialysis data.

[0012] Step 6: Send the interim purification assessment values ​​and reminder information to the patient's terminal.

[0013] In conjunction with the first aspect, in the first implementation of the first aspect of this application, the physiological state data includes directly obtainable first-type state data and indirectly obtainable second-type state data. The steps for obtaining the second-type state data include:

[0014] For any second-class state data, extract the first-class state data related to any second-class state data and define it as reference state data. Preprocess the reference state data and input the preprocessing result into the corresponding second preset model to obtain the initial value of any second-class state data. Then determine whether the human dynamic parameters are greater than the preset threshold. If so, extract the historical state data within a third preset time period and use the average value of the historical state data as the value of any second-class state data. If not, use the initial value as the value of any second-class state data.

[0015] In conjunction with the first aspect, in the second implementation of the first aspect of this application, the hemodialysis data includes the volume of body fluid flowing into the dialysis device within a preset cycle, and step 3 includes:

[0016] The difference between the body fluid volume at the current time point and the body fluid volume at the first time point is calculated and defined as the flow rate difference. The ratio of the flow rate difference to the preset cycle is calculated and defined as the first ratio. Then, the difference between the first ratio at the current time point and the first ratio at the first time point is calculated and defined as the first change. When the first change exceeds the preset range, the dialysis parameters are adjusted. The first time point is the previous collection time point of the current time point.

[0017] In conjunction with the first aspect, in the third implementation of the first aspect of this application, step 4 includes:

[0018] The difference between the body fluid volume at any time point and the second time point within the current monitoring phase is defined as the flow difference, where the second time point is the previous collection time point of any given time point;

[0019] Extract any physiological state data, calculate the difference between the state values ​​of any physiological state data at any time point and the second time point within the current monitoring phase, and define it as the state difference;

[0020] Extract all flow differences and all state differences within the current monitoring phase, combine the flow differences and state differences at the same collection time point to form a data point in the state-flow space, and calculate the geometric center of all data points in the state-flow space.

[0021] Based on the similarity between data points, all data points are divided into multiple arrays. Data points in an array are defined as array data points. Any array is extracted, the average position of all array data points in any array is calculated, and the first relative distance from any array data point in any array to the average position is calculated. The maximum value of the first relative distance is defined as the first distance.

[0022] After traversing all arrays, calculate the second relative distance between each average position and the geometric center point. Then determine whether all first distances are less than or equal to the second preset value and all second relative distances are less than or equal to the third preset value. If not, it is determined that the dialysis parameters need to be adjusted; if so, it is determined that the dialysis parameters do not need to be adjusted.

[0023] In conjunction with the first aspect, in the fourth implementation of the first aspect of this application, the hemodialysis data includes the volume of body fluid flowing into the dialysis device within a preset cycle, and the historical dialysis data and dialysis monitoring data include the first and second solute concentrations of the preset solute before and after dialysis treatment, the single run time of the dialysis device, and the dialysis treatment time. Step 5, generating the phased purification assessment value, includes:

[0024] Historical dialysis data within a fourth preset time period is extracted and defined as the first dialysis data. The dialysis monitoring data and the dialysis treatment process corresponding to the first dialysis data are defined as the reference treatment process.

[0025] Extract any reference treatment process, calculate the total body fluid volume during the entire treatment process, define the ratio of the total body fluid volume to the single run time as the second ratio, execute the first predetermined algorithm on the first solute concentration, the second solute concentration and the second ratio to generate renal function index values, and then generate the feature vector of any reference treatment process, the feature vector including renal function index values, single run time, dialysis treatment time and basic information;

[0026] A third preset model is constructed to describe the absorption, distribution, metabolism and excretion of solutes in the body. All feature vectors are input into the third preset model to obtain the maximum solute concentration. A second preset algorithm is then executed on the maximum solute concentration to generate a phased purification assessment value.

[0027] In conjunction with the first aspect, in the fifth implementation of the first aspect of this application, the basic information includes body weight, and the second predetermined algorithm is applied to the maximum solute concentration to generate a phased purification assessment value, including:

[0028] The interval between any two adjacent reference treatment sessions is calculated based on the dialysis treatment time. Then, the first, second, and third standard deviations of the single run time, interval time, and body weight during the reference treatment sessions are calculated respectively.

[0029] A weighted average of the first, second, and third standard deviations is used to obtain the comprehensive volatility assessment value.

[0030] A negative correlation function is constructed, and the comprehensive fluctuation assessment value is input into the negative correlation function to obtain the compensation parameter. Based on the compensation parameter, the assessment value obtained by executing the second predetermined algorithm is adjusted to generate a phased purification assessment value.

[0031] In conjunction with the first aspect, in the sixth implementation of the first aspect of this application, generating reminder information based on initial physiological data and historical behavioral habit data includes:

[0032] Extract the component type and total intake of each nutrient consumed by the patient within a second preset time period from historical behavioral data. Compare the total intake of each nutrient with the corresponding recommended total intake to identify nutrient components that are insufficient or excessively consumed and define them as components to be analyzed.

[0033] Biochemical indicators are extracted from the initial physiological data, compared with the corresponding standard ranges, and the degree of kidney damage is calculated based on the comparison results. Then, a third predetermined algorithm is executed on the degree of kidney damage to generate body indicator values.

[0034] Obtain the historical contribution rate of all components to be analyzed, and accumulate all historical contribution rates to obtain the accumulated value. Update the historical contribution rate of any component to be analyzed based on the accumulated value, obtain the current contribution rate, and use the product of the current contribution rate and the body indicator value as the current contribution value of any component to be analyzed.

[0035] Obtain the current contribution value of any nutrient and all historical contribution values ​​within a fifth preset time period, and define the average of all historical contribution values ​​and the current contribution value as the comprehensive contribution value of any nutrient.

[0036] A reminder message is generated based on the current contribution value and contribution indicator value.

[0037] Secondly, this application provides a device for monitoring the health of hemodialysis patients throughout their treatment process, the device comprising:

[0038] The parameter setting module is used to acquire the patient's historical dialysis data, basic information and initial physiological data, and input the historical dialysis data, basic information and initial physiological data into the first preset model to predict the patient's dialysis parameters and obtain the dialysis parameters;

[0039] The data acquisition module is used to execute the dialysis process according to the dialysis parameters and to collect the human dynamic parameters, physiological status data and hemodialysis data during the dialysis process according to the preset cycle.

[0040] The first judgment module is used to perform statistical analysis on the hemodialysis data collected at each time point within the first preset time period to determine whether the dialysis parameters need to be adjusted. If so, new dialysis parameters are generated and returned to the data acquisition module; otherwise, the second judgment module is entered.

[0041] The second judgment module is used to determine whether the amount of physiological state data collected in the current monitoring stage has reached the first preset value. If not, it returns to the data acquisition module. If yes, it performs statistical analysis on the physiological state data and hemodialysis data to determine whether the dialysis parameters need to be adjusted. If yes, it generates new dialysis parameters and returns to the data acquisition module, while starting the next monitoring stage. If not, it returns to the data acquisition module.

[0042] The notification generation module is used to obtain dialysis monitoring data for the current treatment course after dialysis is completed, generate a phased purification assessment value based on historical dialysis data and dialysis monitoring data, obtain historical behavioral habit data within a second preset time period, and generate reminder information based on initial physiological data and historical behavioral habit data. The dialysis monitoring data includes basic information, initial physiological data, physiological state data, and hemodialysis data.

[0043] The notification sending module is used to send interim purification assessment values ​​and reminder information to the patient's terminal.

[0044] A third aspect of this application provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the aforementioned method for monitoring the health of hemodialysis patients throughout their treatment process.

[0045] Compared with the prior art, the beneficial effects of the technical solution of this application are at least as follows:

[0046] 1. During dialysis, a phased dynamic adjustment mechanism including short-term and medium-term measures is set up. Short-term assessment can quickly respond to emergencies and avoid acute adverse reactions in patients during dialysis. Medium-term assessment, based on more comprehensive data analysis, ensures the rationality of dialysis parameters throughout the monitoring phase, reducing the risk of chronic complications. Through dual assessment of short-term and medium-term measures, the physiological changes of patients during dialysis can be captured more accurately, avoiding inaccurate parameter adjustments due to short-term fluctuations or failure to capture long-term trends in a timely manner. This ensures that the dialysis process is more in line with the individual needs of patients, improving the purification effect of dialysis and the overall treatment effect.

[0047] 2. Based on historical dialysis data and dialysis monitoring data, a phased purification assessment value is generated, which can comprehensively and objectively reflect the purification effect of patients during the dialysis process, provide more accurate feedback on treatment effect for patients and medical staff, and provide a scientific basis for subsequent treatment and health management.

[0048] 3. By analyzing patients' historical behavioral habits and initial physiological data, we can identify unhealthy habits that may lead to health problems and generate reminder messages. These reminders, based on individual patient behavior, can help patients better manage their habits, improve treatment adherence, thereby improving their quality of life and long-term prognosis, preventing potential health risks, and reducing the occurrence of complications. Attached Figure Description

[0049] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a schematic diagram of an embodiment of a method for monitoring the health of hemodialysis patients throughout the entire process, as described in this application.

[0051] Figure 2 This is a schematic diagram of one embodiment of the dialysis parameter adjustment judgment in this application.

[0052] Figure 3 This is a schematic diagram of an embodiment of the method for generating phased purification assessment values ​​in this application.

[0053] Figure 4 This is a schematic diagram of one embodiment of a hemodialysis patient's full-process health monitoring device according to the present application. Detailed Implementation

[0054] This application provides a method, device, and storage medium for comprehensive health monitoring of hemodialysis patients. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" or "having" and any variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0055] For ease of understanding, the specific process of the embodiments of this application is described below. Please refer to [link / reference]. Figure 1 One embodiment of a method for full-process health monitoring of hemodialysis patients in this application includes:

[0056] Step 1: Obtain the patient's historical dialysis data, basic information, and initial physiological data. Input the historical dialysis data, basic information, and initial physiological data into the first preset model to predict the patient's dialysis parameters and obtain the dialysis parameters.

[0057] Specifically, historical dialysis data includes basic information and physiological data before previous dialysis, as well as various indicators and parameters during previous dialysis processes, including dialysis treatment time, blood flow rate, dialysate flow rate, dialysis duration, dialysis dose and / or dialysate composition, etc.; basic information includes the patient's age, gender, weight, height and / or medical history, etc.; initial physiological data includes the patient's total body water, blood electrolyte levels (such as potassium, sodium, calcium, etc.), serum creatinine, urea concentration, blood pressure, heart rate, blood oxygen saturation, electrocardiogram data and / or body temperature, etc.

[0058] The first preset model is built on big data analysis, machine learning algorithms or other advanced prediction technologies. This model analyzes various input data and comprehensively considers the interrelationships between various factors to accurately predict the dialysis parameters suitable for patients. It is more scientific and accurate, can better adapt to individual differences, and improve dialysis results.

[0059] Step 2: Perform the dialysis process based on the dialysis parameters, and collect the human body's dynamic parameters, physiological status data and hemodialysis data during the dialysis process according to the preset cycle.

[0060] The preset period can be set based on the experience of those skilled in the art or according to the actual application scenario, and this application embodiment is not limited in this respect. For example, the preset period is 5 minutes, but it can also be dynamically adjusted according to the specific situation of the patient. For example, a shorter data collection period can be set for patients with more serious conditions.

[0061] Specifically, the human dynamic parameters include body movement speed and the time for collecting the body movement speed; the data type of the physiological state data is consistent with the initial state data mentioned above; the hemodialysis data includes various indicators and parameters during the dialysis process, including dialysis treatment time, blood flow rate, dialysate flow rate, dialysis dose, dialysate composition and / or the operating status of the dialysis equipment.

[0062] Step 3: Perform statistical analysis on the hemodialysis data collected at each time point within the first preset time period to determine whether the dialysis parameters need to be adjusted. If so, generate new dialysis parameters and return to step 2. If not, proceed to step 4.

[0063] The first preset time is the current time and a period of time before it. It is set according to the experience of those skilled in the art or according to the actual application scenario. This application embodiment does not limit this.

[0064] Specifically, by analyzing hemodialysis data in real time, potential problems during dialysis can be identified promptly, such as excessive or insufficient removal of intravascular fluid. Adjusting dialysis parameters in a timely manner can prevent these problems, improve the purification effect of dialysis, and reduce complications during the dialysis process.

[0065] Step 4: Determine whether the amount of physiological state data collected in the current monitoring phase has reached the first preset value. If not, return to step 2. If yes, perform statistical analysis on the physiological state data and hemodialysis data to determine whether the dialysis parameters need to be adjusted. If yes, generate new dialysis parameters and return to step 2, while starting the next monitoring phase. If not, return to step 2.

[0066] Specifically, a monitoring phase refers to different time periods during dialysis, divided according to time or specific conditions. For example, the dialysis process can be divided into three phases: initial, intermediate, and final. Alternatively, different monitoring phases can be set based on changes in the patient's physiological state. The first preset value refers to the amount of physiological state data that needs to be collected within the current monitoring phase. This value can be fixed (e.g., collecting 100 data points for any physiological state in each phase) or dynamically adjusted according to the patient's specific situation. The first preset value for the amount of data collected in each monitoring phase can be the same or different, and can be set based on the experience of those skilled in the art or according to the actual application scenario. This application embodiment does not limit this.

[0067] By conducting phased monitoring, physiological status data and hemodialysis data can be comprehensively analyzed over a longer period of time to assess the patient's overall physiological status during the current monitoring phase. This helps to identify long-term trends in the patient's physiological status and dialysis effectiveness, enabling preventative measures to be taken in advance to avoid the deterioration of problems, ensuring the safety and effectiveness of the dialysis process, and providing a more comprehensive assessment of the patient's health status.

[0068] Step 5: After dialysis is completed, obtain the dialysis monitoring data for the current treatment course, generate a phased purification assessment value based on historical dialysis data and dialysis monitoring data, and obtain historical behavioral habit data within a second preset time period. Generate reminder information based on initial physiological data and historical behavioral habit data. The dialysis monitoring data includes basic information, initial physiological data, physiological state data, and hemodialysis data.

[0069] Specifically, based on historical dialysis data and dialysis monitoring data, a phased purification assessment value is generated, which can comprehensively and objectively reflect the purification effect of the patient in the current dialysis process, providing more accurate feedback on treatment effectiveness for patients and medical staff. Initial physiological data refers to the physiological state data before the start of current dialysis treatment. Behavioral habit data includes dietary records (such as sodium, potassium, and protein intake), fluid intake, exercise status, and / or medication use, reflecting the patient's daily behavioral habits. Statistical analysis is performed on the initial physiological data and historical behavioral habit data within a second preset time period to identify the impact of historical behavioral data on the initial physiological data, further extracting adverse behavioral habits that lead to health problems, and providing patients with personalized health management suggestions.

[0070] The second preset time refers to a specific time period, such as one week or one month before the initial physiological data collection. It is set according to the experience of those skilled in the art or according to the actual application scenario. This application embodiment does not limit this.

[0071] The reminders include dietary advice (such as reminding patients to control sodium and potassium intake and increase protein intake), fluid management (such as reminding patients to control fluid intake to avoid excessive weight gain), exercise advice, and medication reminders.

[0072] After dialysis monitoring is completed, the dialysis monitoring data will be stored in the historical dialysis data.

[0073] Step 6: Send the interim purification assessment values ​​and reminder information to the patient's terminal.

[0074] Specifically, after dialysis, the detection of some data in the dialysis monitoring data requires time, and the sending time of the interim purification assessment values ​​can be later than the sending time of the reminder information. Sending the assessment values ​​and reminder information to the patient's terminal allows the patient to understand their health status in a timely manner, thereby improving patient participation and compliance, and encouraging patients to adjust their lifestyle and behavioral habits according to the reminder information, so as to better cooperate with dialysis treatment.

[0075] In one specific embodiment, the physiological state data includes a first type of state data that can be directly acquired and a second type of state data that can be indirectly acquired. The steps for acquiring the second type of state data include:

[0076] For any second-class state data, extract the first-class state data related to any second-class state data and define it as reference state data. Preprocess the reference state data and input the preprocessing result into the corresponding second preset model to obtain the initial value of any second-class state data. Then determine whether the human dynamic parameters are greater than the preset threshold. If so, extract the historical state data within a third preset time period and use the average value of the historical state data as the value of any second-class state data. If not, use the initial value as the value of any second-class state data.

[0077] Specifically, the first type of status data includes electrocardiogram (ECG), pulse, respiratory rate, blood glucose, and body temperature, while the second type of status data includes blood volume, blood oxygen level, cardiac output, and / or blood pressure. Directly obtaining the second type of status data may be difficult or could affect the dialysis process. Calculating the second type of status data based on the first type of status data facilitates dialysis treatment while improving the accuracy and reliability of the data. For example, blood oxygen level can be estimated based on pulse waveform data, and blood pressure can be estimated based on both ECG and pulse waveform data.

[0078] Taking blood pressure as an example, based on the electrocardiogram (ECG) data and the pulse waveform data, the first interval time from the start of ventricular contraction (R wave of ECG) to the arrival of the pulse wave in the peripheral blood vessels (peak of pulse waveform) and the second interval time from the start of ventricular diastole (T wave of ECG) to the arrival of the pulse wave in the peripheral blood vessels (trough of pulse waveform) are calculated. Then, using the known relationship between the above interval time and blood pressure, the highest and lowest blood pressure are calculated respectively by formulas, for example, highest blood pressure = f (first interval time), lowest blood pressure = g (second interval time), where f and g are known functions, usually related to the elasticity parameters of blood vessels.

[0079] Specifically, the aforementioned human dynamic parameters refer to the changes in velocity of body parts (arms, legs, head, etc.) per unit time. Although patients are primarily lying down during dialysis, limb movements still occur, and the resulting human dynamic parameters may affect the accuracy of physiological status data. If the human dynamic parameters exceed a preset threshold, it indicates that the body's velocity changes rapidly in a short period, and the body's state is unstable, requiring correction of the second type of state data to reduce the impact of motion artifacts. If the human dynamic parameters are less than or equal to the preset threshold, it indicates that the body's velocity changes slowly in a short period, and the body's state is stable, requiring no adjustment of the second type of state data. By correcting for minute movements, the accuracy and reliability of physiological status data can be improved.

[0080] A sliding window is set up to smooth the data by averaging historical state data over a third preset time period. This reduces the impact of instantaneous fluctuations and improves the accuracy of physiological state data. The third preset time period can be set based on the experience of those skilled in the art or according to the actual application scenario. This embodiment of the application does not limit this setting. For example, when calculating blood pressure data, the third preset time period is 15 minutes. If the current time is 10:00, the system will extract blood pressure data between 9:45 and 10:00.

[0081] Preferably, the second type of state parameters can also be calculated based on the first type of state data and dialysis parameters.

[0082] In one specific embodiment, the hemodialysis data includes the amount of body fluid flowing into the dialysis device within a preset cycle, and the process of performing step 3 may specifically include the following steps:

[0083] The difference between the body fluid volume at the current time point and the body fluid volume at the first time point is calculated and defined as the flow rate difference. The ratio of the flow rate difference to the preset cycle is calculated and defined as the first ratio. Then, the difference between the first ratio at the current time point and the first ratio at the first time point is calculated and defined as the first change. When the first change exceeds the preset range, the dialysis parameters are adjusted. The first time point is the previous collection time point of the current time point.

[0084] Specifically, during hemodialysis, the dialysis device processes a certain amount of blood, removing metabolic waste and excess water. The volume of fluid flowing into the dialysis device (which can also be understood as blood) is a crucial parameter, reflecting the efficiency of dialysis and the removal of water load. By monitoring the volume of fluid flowing into the dialysis device within a preset cycle, the patient's water removal during dialysis and the operational status of the dialysis device can be assessed.

[0085] The first ratio reflects the rate at which extravascular fluid moves into the blood vessel. By calculating the first change, the change in the rate of fluid removal during dialysis can be assessed. If the first change is greater than a preset range, it indicates that intravascular fluid is being excessively removed; if the first change is less than the preset range, it indicates that intravascular fluid is being insufficiently removed. To ensure the stability and effectiveness of the dialysis process, dialysis parameters need to be adjusted to avoid complications such as hypotension and arrhythmia caused by excessively fast or slow fluid removal.

[0086] For example, the above dialysis parameter is the ultrafiltration rate. If the first change is less than the corresponding preset range, the ultrafiltration rate is reduced; if the first change is greater than the preset unit, the ultrafiltration rate is increased.

[0087] Preferably, the dialysate flow rate, dialysate pressure, and / or body fluid volume can also be adjusted.

[0088] In one specific embodiment, the process of performing step 4 may specifically include the following steps:

[0089] (1) Calculate the difference in body fluid volume between any time point and the second time point within the current monitoring phase, which is defined as the flow difference, where the second time point is the previous collection time point of any time point.

[0090] (2) Extract any physiological state data, calculate the difference between the state values ​​of any physiological state data at any time point and the second time point within the current monitoring phase, and define it as the state difference.

[0091] (3) Extract all flow differences and all state differences within the current monitoring phase, combine the flow differences and state differences at the same collection time point to form a data point in the state-flow space, and calculate the geometric center of all data points in the state-flow space.

[0092] (4) Based on the similarity between data points, all data points are divided into multiple arrays. Data points in the arrays are defined as array data points. Any array is extracted, the average position of all array data points in any array is calculated, and the first relative distance from any array data point in any array to the average position is calculated. The maximum value of the first relative distance is defined as the first distance.

[0093] (5) After traversing all arrays, calculate the second relative distance between each average position and the geometric center point. Then determine whether all first distances are less than or equal to the second preset value and all second relative distances are less than or equal to the third preset value. If not, it is determined that the dialysis parameters need to be adjusted. If yes, it is determined that the dialysis parameters do not need to be adjusted.

[0094] In this application, one embodiment of the dialysis parameter adjustment judgment method is as follows: Figure 2 As shown.

[0095] Specifically, by calculating the flow difference, the change in blood volume processed by the dialysis device at two time points is assessed; by calculating the state difference, the changes in the patient's physiological state during dialysis are assessed; a state-flow space is constructed, combining the flow difference and all state differences at the same collection time point to form a data point within the state-flow space, integrating multidimensional data into a unified framework for comprehensive analysis. Subsequently, clustering algorithms (such as K-means, hierarchical clustering, etc.) are used to divide all data points into multiple arrays. Statistical analysis is performed on the average position and first distance of each group, as well as the second relative distance between each average position and the geometric center point, to assess the distribution and anomaly degree of the data points. If all first distances are less than or equal to a second preset value, and all second relative distances are less than or equal to a third preset value, the dialysis process is considered stable, and no adjustment of dialysis parameters is required; otherwise, adjustment of dialysis parameters is necessary. The second and third preset values ​​are set based on the experience of those skilled in the art or according to the actual application scenario, and this embodiment does not limit their specific settings.

[0096] Preferably, the aforementioned physiological data is blood pressure. In this case, the state-flow space is the blood pressure-flow space, and the dialysis parameters include ultrafiltration rate. The adjustment of the dialysis parameters in step 4 is to reduce the ultrafiltration rate. That is, when a tendency for blood pressure to change is predicted, regardless of whether the blood pressure increases or decreases, the system will reduce the ultrafiltration rate. If the blood pressure tends to decrease, reducing the dehydration rate can reduce the decrease in intravascular pressure, thereby avoiding hypotension; if the blood pressure tends to increase, reducing the dehydration rate can reduce the excessive increase in intravascular pressure, thereby avoiding hypertension.

[0097] In one specific embodiment, the hemodialysis data includes the volume of body fluid flowing into the dialysis device within a preset cycle; historical dialysis data and dialysis monitoring data include the first and second solute concentrations of preset solutes before and after dialysis treatment, the single run time of the dialysis device, and the dialysis treatment time; step 5, generating the phased purification assessment value, includes:

[0098] (1) Extract historical dialysis data within the fourth preset time period and define it as the first dialysis data. Define the dialysis monitoring data and the dialysis treatment process corresponding to the first dialysis data as the reference treatment process.

[0099] (2) Extract any reference treatment process, calculate the total body fluid volume in the entire treatment process, define the ratio of the total body fluid volume to the single run time as the second ratio, execute the first predetermined algorithm on the first solute concentration, the second solute concentration and the second ratio to generate renal function index values, and then generate the feature vector of any reference treatment process. The feature vector includes renal function index values, single run time, dialysis treatment time and basic information.

[0100] (3) Construct a third preset model to describe the absorption, distribution, metabolism and excretion of solute in the body, input all feature vectors into the third preset model, obtain the maximum value of solute concentration, execute the second preset algorithm on the maximum value of solute concentration, and generate a phased purification assessment value.

[0101] In this application, one embodiment of the method for generating phased purification assessment values ​​is, for example... Figure 3 As shown.

[0102] The fourth preset time can be set based on the experience of those skilled in the art or according to the actual application scenario, and the embodiments of this application are not limited in this regard.

[0103] Specifically, solutes refer to substances dissolved in the blood, such as urea, creatinine, and β2-microglobulin. These substances are excreted in urine when kidney function is normal. However, in patients with kidney failure (end-stage renal disease, ESRD), these solutes cannot be effectively excreted and accumulate in the body, leading to the buildup of metabolic waste. Hemodialysis removes these substances. Between dialysis sessions, solutes gradually accumulate in the body, reaching peak concentrations. During dialysis, solutes are removed, but after dialysis stops, they are released back into the bloodstream from the tissues, causing a temporary rebound in concentration.

[0104] Kidney function indicators measure the ability of a dialyzer to remove certain substances (such as urea, creatinine, etc.) from the blood per unit time; their values ​​reflect the functional status of the kidneys. For example, the first predetermined algorithm is: Where FIs represents the renal function index value, Q represents the first ratio, SC1 represents the first solute concentration, and SC2 represents the first solute concentration. When multiple solutes are present, the individual index value for each solute is calculated separately, and then they are added together to obtain the above-mentioned renal function index value.

[0105] The third pre-defined model mentioned above is a mathematical model based on the principles of physics and pharmacokinetics, simulating the dynamic changes of solutes in the body. It can accurately predict changes in solute concentration. The maximum solute concentration reflects the accumulation of solutes between two dialysis sessions. If the maximum solute concentration is too high, it indicates that dialysis treatment has failed to effectively remove solutes from the body, which may lead to uremia symptoms or other complications in the patient.

[0106] For example, the second preset algorithm is: PE = SC P ×FIs or PE = SC P ×FIs×F D Where PE is the phased purification assessment value, and SC is the SC value. p F represents the maximum solute concentration. D This refers to the dialysis frequency. By generating periodic purification assessment values, the adequacy and effectiveness of dialysis treatment can be quantified, providing more accurate feedback on treatment outcomes for patients and healthcare professionals, and determining whether a patient's dialysis is sufficient.

[0107] The technical solution of this invention can comprehensively and scientifically evaluate the therapeutic effect of hemodialysis when dialysis conditions (duration of a single dialysis session, dialysis interval, weight, etc.) are unstable, providing a basis for personalized treatment and dynamic adjustment, thereby improving the dialysis effect and overall prognosis of patients.

[0108] In one specific embodiment, basic information includes body weight, and a second predetermined algorithm is executed on the maximum solute concentration to generate a phased purification assessment value, including:

[0109] (1) Calculate the interval between any two adjacent reference treatment sessions based on the dialysis treatment time, and then calculate the first standard deviation, second standard deviation and third standard deviation of the single run time, interval time and weight in the reference treatment sessions respectively.

[0110] (2) Take a weighted average of the first standard deviation, the second standard deviation and the third standard deviation to obtain the comprehensive volatility assessment value.

[0111] (3) Construct a negative correlation function, input the comprehensive fluctuation assessment value into the negative correlation function, obtain the compensation parameter, adjust the assessment value obtained by executing the second predetermined algorithm based on the compensation parameter, and generate a phased purification assessment value.

[0112] Specifically, fluctuations in dialysis conditions, such as irregularities in dialysis time, intervals, and frequency, can lead to uneven solute clearance in the body, affecting dialysis adequacy and consequently impacting interim purification assessment values. By calculating the standard deviation or variance of single-session run time, interval time, and body weight, a comprehensive fluctuation assessment value can be calculated. This quantifies the unevenness of dialysis conditions, allowing for adjustments to the calculation of interim purification assessment values ​​and a more accurate evaluation of dialysis effectiveness. A higher comprehensive fluctuation assessment value indicates poorer stability in the dialysis treatment process; therefore, the assessment value should be lowered accordingly through compensation parameters to reflect the true effectiveness of the treatment.

[0113] For example, the negative correlation function is f(SE) = 1 - α × SE or f(SE) = β × e -γ×SE Where SE is the comprehensive volatility assessment value, and α, β, and γ are weighting coefficients.

[0114] In one specific embodiment, generating reminder information based on initial physiological data and historical behavioral habit data includes:

[0115] (1) Extract the component type and total intake of each nutrient consumed by the patient within the second preset time period from historical behavioral habit data, compare the total intake of each nutrient with the corresponding recommended total intake, identify the nutrient that is insufficient or excessive, and define it as the component to be analyzed.

[0116] (2) Extract biochemical index data from the initial physiological data, compare the biochemical index data with the corresponding standard range, calculate the degree of kidney damage based on the comparison results, and then execute the third predetermined algorithm on the degree of kidney damage to generate body index values.

[0117] (3) Obtain the historical contribution rate of all components to be analyzed, and accumulate all historical contribution rates to obtain the accumulated value. Update the historical contribution rate of any component to be analyzed based on the accumulated value, obtain the current contribution rate, and use the product of the current contribution rate and the body indicator value as the current contribution value of any component to be analyzed.

[0118] (4) Obtain the current contribution value of any nutrient and all historical contribution values ​​within the fifth preset time period, and define the average of all historical contribution values ​​and current contribution values ​​as the comprehensive contribution value of any nutrient.

[0119] (5) Generate reminder information based on the current contribution value and contribution indicator value.

[0120] Specifically, patients can share their diet, exercise, and other data to a cloud platform. The system can analyze this data, extracting the composition type and total intake of each nutrient, including calcium, sodium, potassium, protein, and water. The total intake of each nutrient is compared to the corresponding recommended intake. If the intake of a nutrient is lower than the recommended intake, it is defined as insufficient; if the intake is higher than the recommended intake, it is defined as excessive. All insufficient or excessive nutrients are collectively referred to as the components to be analyzed—those that adversely affect the purification effect of the current stage.

[0121] Biochemical indicators include serum creatinine, blood urea nitrogen, serum potassium, and serum sodium, which reflect kidney function. For example, the formula for calculating the degree of kidney damage is: Among them, D B AV i Let AV be the actual value of the i-th biochemical indicator. i When below the standard range, SV i The minimum value within the above standard range, when AV i When it exceeds the standard range, SV i The maximum value within the above standard range is represented by ε, where ε is the weighting coefficient. For example, the formula for calculating the body indicator value is T. B =a1×a2×D B In this calculation, TB represents the body indicator value, a1 is a physiological indicator factor calculated based on deviations from physiological state data, and a2 is a comprehensive influencing factor calculated based on age, gender, underlying diseases, etc. The body indicator value comprehensively considers multiple factors such as the patient's kidney function, physiological state, and basic information, and can comprehensively reflect the patient's current overall health status. Since the patient's body indicators and nutritional intake change over time, regularly calculating the body indicator value allows for monitoring trends in the patient's health status.

[0122] The historical contribution rate of any nutrient reflects its contribution to the degree of kidney damage over a past period. For example, there are four components to be analyzed: A1, A2, A3, and A4, with corresponding historical contribution rates of 20%, 70%, 55%, and 30%, respectively, totaling 175%. The updated current contribution rates of components A1, A2, A3, and A4 are 31% (20% ÷ 175% + 20%), 100% (maximum value is 100%, set to 100% when the calculated contribution rate is greater than 100%), 86%, and 47%, respectively. Subsequently, the current contribution value of each component is calculated based on its current contribution rate and body indicator values. The higher the current contribution value, the greater the impact of the component on kidney health and the higher its likelihood of being a cause of kidney damage. At different assessment stages, even if the contribution rate is the same, the contribution of nutrients to kidney health will vary depending on the degree of kidney health (physical indicator values). For example, when the physical indicator values ​​are high, even if the current contribution rate of a certain nutrient is low, its current contribution value may be high, and the impact of that nutrient on health will be amplified.

[0123] The fifth preset time is a historical time within a certain period of time from the current time. For example, there are a total of 5 nutrients A1, A2, A3, A4 and A5. A total of 3 contribution value calculations were performed. The contribution values ​​of each nutrient in each calculation are A1 (0.9, 0, 2), A2 (0.8, 4.1, 6.4), A3 (2.9, 1, 5.5), A4 (0, 2.5, 3) and A5 (3.2, 1.6, 0). The combined contribution values ​​of A1, A2, A3, A4 and A5 are 1, 3.8, 3.1, 1.8 and 1.6, respectively.

[0124] Based on the current contribution value and the overall contribution value, the long-term and short-term effects of a certain nutrient on kidney health can be comprehensively assessed. Preferably, when generating reminder messages, the current contribution value and the overall contribution value are sorted according to their numerical values, and the top N1 components to be analyzed are extracted as the first reminder components (nutrients with greater short-term effects), and the top N2 components are extracted as the second reminder components (nutrients with greater long-term effects). For example, the reminder messages may be "Your sodium intake has been insufficient recently, it is recommended to appropriately increase salt intake," "Your potassium intake has been too high recently, please reduce the intake of high-potassium foods," or "Your kidney function has declined, it is recommended to control protein intake and increase water intake," etc.

[0125] According to the technical solution of the present invention, factors that have a significant impact on the patient's kidney health can be identified based on the patient's daily behavioral habits, making the patient aware of the causal relationship between daily behavioral habits and kidney health, thereby improving bad behavioral habits, improving treatment compliance, and preventing potential health risks.

[0126] The above describes a method for monitoring the health of hemodialysis patients throughout the entire process, as described in the embodiments of this application. The following describes a device for monitoring the health of hemodialysis patients throughout the entire process, as described in the embodiments of this application. Please refer to [link / reference]. Figure 4 One embodiment of a hemodialysis patient's full-process health monitoring device in this application includes:

[0127] The parameter setting module 10 is used to acquire the patient's historical dialysis data, basic information and initial physiological data, and input the historical dialysis data, basic information and initial physiological data into the first preset model to predict the patient's dialysis parameters and obtain the dialysis parameters.

[0128] The data acquisition module 20 is used to execute the dialysis process according to the dialysis parameters and to collect the human dynamic parameters, physiological state data and hemodialysis data during the dialysis process according to the preset cycle.

[0129] The first judgment module 30 is used to perform statistical analysis on the hemodialysis data collected at each time point within the first preset time period to determine whether the dialysis parameters need to be adjusted. If so, new dialysis parameters are generated and returned to the data acquisition module 20. If not, the second judgment module 40 is entered.

[0130] The second judgment module 40 is used to determine whether the amount of physiological state data collected in the current monitoring stage has reached the first preset value. If not, it returns to the data acquisition module 20. If yes, it performs statistical analysis on the physiological state data and hemodialysis data to determine whether the dialysis parameters need to be adjusted. If yes, it generates new dialysis parameters and returns to the data acquisition module 20, while starting the next monitoring stage. If no, it returns to the data acquisition module 20.

[0131] The notification generation module 50 is used to obtain dialysis monitoring data for the current treatment course after dialysis is completed, generate a phased purification assessment value based on historical dialysis data and dialysis monitoring data, obtain historical behavioral habit data within a second preset time period, and generate reminder information based on initial physiological data and historical behavioral habit data. The dialysis monitoring data includes basic information, initial physiological data, physiological state data, and hemodialysis data.

[0132] The notification sending module 60 is used to send interim purification assessment values ​​and reminder information to the patient terminal.

[0133] This application also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when the instructions are executed on a computer, cause the computer to perform the steps of the method for full-process health monitoring of hemodialysis patients.

[0134] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, equipment, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0135] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0136] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for monitoring the health of hemodialysis patients throughout the entire process, characterized in that, The method includes: Step 1: Obtain the patient's historical dialysis data, basic information, and initial physiological data. Input the historical dialysis data, basic information, and initial physiological data into a first preset model to predict the patient's dialysis parameters and obtain the dialysis parameters. Step 2: Perform the dialysis process based on the dialysis parameters, and collect human dynamic parameters, physiological state data and hemodialysis data during the dialysis process according to the preset cycle; Step 3: Perform statistical analysis on the hemodialysis data collected at each time point within the first preset time period to determine whether the dialysis parameters need to be adjusted. If so, generate new dialysis parameters and return to Step 2. If not, proceed to Step 4. Step 4: Determine whether the amount of physiological state data collected in the current monitoring stage has reached the first preset value. If not, return to step 2. If yes, perform statistical analysis on the physiological state data and the hemodialysis data to determine whether the dialysis parameters need to be adjusted. If yes, generate new dialysis parameters and return to step 2, while starting the next monitoring stage. If not, return to step 2. Step 5: After dialysis is completed, obtain the dialysis monitoring data for the current treatment course, generate a phased purification assessment value based on the historical dialysis data and the dialysis monitoring data, and obtain historical behavioral habit data within a second preset time period. Generate reminder information based on the initial physiological data and the historical behavioral habit data. The dialysis monitoring data includes the basic information, the initial physiological data, the physiological state data, and the hemodialysis data. Step 6: Send the interim purification assessment value and the reminder information to the patient's terminal; The hemodialysis data includes the volume of body fluid flowing into the dialysis device within the preset cycle, and step 3 includes: The difference between the body fluid volume at the current time point and the body fluid volume at the first time point is calculated and defined as the flow rate difference. The ratio of the flow rate difference to the preset cycle is calculated and defined as the first ratio. Then, the difference between the first ratio at the current time point and the first ratio at the first time point is calculated and defined as the first change. When the first change exceeds the preset range, the dialysis parameters are adjusted. The first time point is the previous collection time point of the current time point. Step 4 includes: The difference between the body fluid volume at any time point and the second time point within the current monitoring phase is calculated and defined as the flow difference, wherein the second time point is the previous collection time point of any of the time points; Extract any physiological state data, and calculate the difference between the state values ​​of any physiological state data at any time point and the second time point within the current monitoring phase, which is defined as the state difference; Extract all flow differences and all state differences within the current monitoring phase, combine the flow differences and state differences at the same collection time point to form a data point in the state-flow space, and calculate the geometric center of all data points in the state-flow space; Based on the similarity between data points, all data points are divided into multiple arrays, and the data points in the arrays are defined as array data points. Any array is extracted, the average position of all array data points in any array is calculated, and the first relative distance from any array data point in any array to the average position is calculated. The maximum value of the first relative distance is defined as the first distance. After traversing all arrays, calculate the second relative distance between each average position and the geometric center point. Then determine whether all first distances are less than or equal to the second preset value and all second relative distances are less than or equal to the third preset value. If not, determine that the dialysis parameters need to be adjusted; if so, determine that the dialysis parameters do not need to be adjusted.

2. The method for full-process health monitoring of hemodialysis patients according to claim 1, characterized in that, The physiological state data includes a first type of state data that can be directly obtained and a second type of state data that can be indirectly obtained. The steps for obtaining the second type of state data include: For any second-type state data, extract the first-type state data related to any second-type state data and define it as reference state data. Preprocess the reference state data and input the preprocessing result into the corresponding second preset model to obtain the initial value of any second-type state data. Then determine whether the human dynamic parameter is greater than a preset threshold. If so, extract the historical state data within a third preset time period and use the average value of the historical state data as the value of any second-type state data. If not, use the initial value as the value of any second-type state data.

3. The method for full-process health monitoring of hemodialysis patients according to claim 1, characterized in that, The hemodialysis data includes the volume of body fluid flowing into the dialysis device within the preset cycle. The historical dialysis data and the dialysis monitoring data include the first and second solute concentrations of the preset solute before and after dialysis treatment, the single run time of the dialysis device, and the dialysis treatment time. Step 5, which generates the staged purification assessment value, includes: Extract the historical dialysis data within a fourth preset time period and define it as the first dialysis data. Define the dialysis monitoring data and the dialysis treatment process corresponding to the first dialysis data as the reference treatment process. Extract any reference treatment process, calculate the total body fluid volume during the entire treatment process, define the ratio of the total body fluid volume to the single run time as the second ratio, execute a first predetermined algorithm on the first solute concentration, the second solute concentration and the second ratio to generate renal function index values, and then generate a feature vector for any of the reference treatment processes, the feature vector including the renal function index values, the single run time, the dialysis treatment time and the basic information; A third preset model is constructed to describe the absorption, distribution, metabolism and excretion process of solute in the body. All feature vectors are input into the third preset model to obtain the maximum solute concentration. A second predetermined algorithm is executed on the maximum solute concentration to generate the staged purification assessment value.

4. The method for full-process health monitoring of hemodialysis patients according to claim 3, characterized in that, The basic information includes body weight, and the process of performing a second predetermined algorithm on the maximum solute concentration to generate the phased purification assessment value includes: Based on the dialysis treatment time, the interval between any two adjacent reference treatment sessions is calculated, and then the first standard deviation, second standard deviation, and third standard deviation of the single run time, the interval time, and the body weight during the reference treatment sessions are calculated respectively. A weighted average of the first standard deviation, the second standard deviation, and the third standard deviation is used to obtain a comprehensive volatility assessment value. A negative correlation function is constructed, the comprehensive fluctuation assessment value is input into the negative correlation function, a compensation parameter is obtained, and the assessment value obtained by executing the second predetermined algorithm is adjusted based on the compensation parameter to generate the phased purification assessment value.

5. The method for full-process health monitoring of hemodialysis patients according to claim 1, characterized in that, The generation of reminder information based on the initial physiological data and the historical behavioral habit data includes: Extract the component type and total intake of each nutrient consumed by the patient within the second preset time period from the historical behavioral habit data, compare the total intake of each nutrient with the corresponding recommended total intake, identify the nutrient that is insufficient or excessive, and define it as the component to be analyzed. Biochemical index data are extracted from the initial physiological data, and the biochemical index data are compared with the corresponding standard range. The degree of kidney damage is calculated based on the comparison results. Then, a third predetermined algorithm is executed on the degree of kidney damage to generate body index values. Obtain the historical contribution rate of all components to be analyzed, and accumulate all historical contribution rates to obtain the accumulated value. Update the historical contribution rate of any component to be analyzed based on the accumulated value, obtain the current contribution rate, and use the product of the current contribution rate and the body indicator value as the current contribution value of any component to be analyzed. Obtain the current contribution value of any nutrient and all historical contribution values ​​within a fifth preset time period, and define the average of all historical contribution values ​​and the current contribution value as the comprehensive contribution value of any nutrient. The reminder message is generated based on the current contribution value and the total contribution value.

6. A device for monitoring the health of hemodialysis patients throughout the entire process, characterized in that, The device includes: The parameter setting module is used to acquire the patient's historical dialysis data, basic information and initial physiological data, and input the historical dialysis data, the basic information and the initial physiological data into the first preset model to predict the patient's dialysis parameters, thereby obtaining the dialysis parameters; The data acquisition module is used to execute the dialysis process according to the dialysis parameters and to collect human dynamic parameters, physiological state data and hemodialysis data during the dialysis process according to a preset cycle. The first judgment module is used to perform statistical analysis on the hemodialysis data collected at each time point within a first preset time period to determine whether the dialysis parameters need to be adjusted. If so, new dialysis parameters are generated and returned to the data collection module. If not, the second judgment module is entered. The second judgment module is used to determine whether the amount of physiological state data collected in the current monitoring stage has reached the first preset value. If not, it returns to the data acquisition module. If yes, it performs statistical analysis on the physiological state data and the hemodialysis data to determine whether the dialysis parameters need to be adjusted. If yes, it generates new dialysis parameters and returns to the data acquisition module, while starting the next monitoring stage. If not, it returns to the data acquisition module. The notification generation module is used to obtain dialysis monitoring data for the current treatment course after dialysis is completed, generate a phased purification assessment value based on the historical dialysis data and the dialysis monitoring data, obtain historical behavioral habit data within a second preset time period, and generate reminder information based on the initial physiological data and the historical behavioral habit data. The dialysis monitoring data includes the basic information, the initial physiological data, the physiological state data, and the hemodialysis data. The notification sending module is used to send the interim purification assessment value and the reminder information to the patient terminal; The hemodialysis data includes the volume of body fluid flowing into the dialysis device within the preset cycle. The first judgment module is further configured to: The difference between the body fluid volume at the current time point and the body fluid volume at the first time point is calculated and defined as the flow rate difference. The ratio of the flow rate difference to the preset cycle is calculated and defined as the first ratio. Then, the difference between the first ratio at the current time point and the first ratio at the first time point is calculated and defined as the first change. When the first change exceeds the preset range, the dialysis parameters are adjusted. The first time point is the previous collection time point of the current time point. The second judgment module is also used for: The difference between the body fluid volume at any time point and the second time point within the current monitoring phase is calculated and defined as the flow difference, wherein the second time point is the previous collection time point of any of the time points; Extract any physiological state data, and calculate the difference between the state values ​​of any physiological state data at any time point and the second time point within the current monitoring phase, which is defined as the state difference; Extract all flow differences and all state differences within the current monitoring phase, combine the flow differences and state differences at the same collection time point to form a data point in the state-flow space, and calculate the geometric center of all data points in the state-flow space; Based on the similarity between data points, all data points are divided into multiple arrays, and the data points in the arrays are defined as array data points. Any array is extracted, the average position of all array data points in any array is calculated, and the first relative distance from any array data point in any array to the average position is calculated. The maximum value of the first relative distance is defined as the first distance. After traversing all arrays, calculate the second relative distance between each average position and the geometric center point. Then determine whether all first distances are less than or equal to the second preset value and all second relative distances are less than or equal to the third preset value. If not, determine that the dialysis parameters need to be adjusted; if so, determine that the dialysis parameters do not need to be adjusted.

7. A computer-readable storage medium storing instructions thereon, characterized in that, When the instruction is executed by the processor, it implements a method for full-process health monitoring of hemodialysis patients as described in any one of claims 1-5.

Images