Blood purification personalized treatment planning system and method thereof

Abstract

The invention relates to the technical field of medical information systems, in particular to a blood purification personalized treatment planning system and method, and the system comprises a patient evaluation module which is used for collecting basic information, disease information and auxiliary examination information of a patient; the treatment scheme generation module is in communication connection with the patient evaluation module and is used for receiving a patient evaluation score sent by the patient evaluation module; based on the patient evaluation score, generating a personalized treatment scheme, the personalized treatment scheme including dialysis frequency, dialysis time, dialysis mode, target weight and auxiliary examination items; the effect monitoring module is in communication connection with the treatment scheme generation module and is used for acquiring monitoring data of the patient in the treatment process; the monitoring module is used for processing monitoring data and adjusting the feedback module, a multi-dimensional evaluation score generated by the patient evaluation module is directly input for the treatment scheme generation module, and real-time data of the effect monitoring module can influence an evaluation result and a treatment scheme by adjusting the feedback module.

Description

Technical Field

[0001] The present invention relates to the technical field of medical information systems, and more specifically, to a blood purification personalized treatment planning system and method thereof. Background Art

[0002] With the increasing number of patients with chronic kidney disease, blood purification therapy is increasingly used in clinical practice. Traditional hemodialysis treatment programs usually adopt a "one-size-fits-all" approach, using the same dialysis frequency, time and method for all patients. This method is difficult to meet the individual needs of each patient. In recent years, the medical community has gradually realized the importance of personalized treatment and has begun to try to adjust treatment plans according to the specific conditions of patients.

[0003] However, there are still many problems in the current process of formulating personalized treatment plans. First, the patient assessment process is often too simplistic, considering only a few indicators, such as creatinine and urea nitrogen levels, while ignoring the patient's overall health status and quality of life. Second, the formulation of treatment plans mainly relies on the experience of doctors and lacks a systematic and standardized method, which not only increases the workload of doctors, but also may lead to inconsistency in treatment plans. Furthermore, the existing treatment effect monitoring system is usually passive and can only detect problems during regular review, and cannot adjust the treatment plan in real time. Finally, most existing systems lack an effective feedback mechanism and cannot dynamically optimize the treatment plan based on the patient's treatment response.

[0004] These problems seriously restrict the effect of blood purification treatment and affect the patient's quality of life and prognosis. Therefore, there is an urgent need for an intelligent system that can comprehensively evaluate the patient's condition, formulate personalized treatment plans, monitor the treatment effect in real time and adjust it dynamically. Summary of the invention

[0005] The present invention aims to solve the above technical problems and provides a blood purification personalized treatment planning system and method. The system evaluates the patient's condition in multiple dimensions, formulates a personalized treatment plan using an intelligent algorithm, monitors the treatment effect in real time, and can dynamically adjust the plan according to the patient's response, thereby significantly improving the accuracy and effectiveness of blood purification treatment.

[0006] In order to solve the above technical problems, the present invention adopts the following technical solutions: Blood purification personalized treatment planning system, including: Patient Assessment Module for: Collect the patient's basic information, disease information and auxiliary examination information; Generate patient labels; Calculating a patient assessment score, wherein the patient assessment score includes a disease assessment score, a symptom assessment score, an age assessment score, a height assessment score, and a weight assessment score; A treatment plan generating module is communicatively connected with the patient assessment module and is used to: receiving a patient assessment score sent by the patient assessment module; Generate a personalized treatment plan based on the patient assessment score, wherein the personalized treatment plan includes dialysis frequency, dialysis time, dialysis method, target weight and auxiliary examination items; The effect monitoring module is in communication with the treatment plan generating module and is used to: Obtain monitoring data of patients during treatment; Processing the monitoring data; The adjustment feedback module is in communication with the effect monitoring module and the treatment plan generating module, and is used to: Receiving the processed monitoring data sent by the effect monitoring module; Dynamically adjusting the patient's estimated score based on the processed monitoring data; The adjusted estimated score is sent to the treatment plan generation module.

[0007] Preferably, the patient assessment module comprises: Patient information collection unit, used to collect basic patient information; Auxiliary inspection unit, used to formulate auxiliary inspection items; Health record unit, used to establish patient health records; a label generation unit for formulating patient labels; A score calculation unit is used to calculate the patient assessment score.

[0008] Preferably, the auxiliary examination items formulated by the auxiliary examination unit include routine blood test, routine urine test, fecal occult blood test, blood lipid analysis, renal function test, blood sugar test, electrocardiogram test, hepatitis B liver function test, coagulation function test, liver test, blood lipid test, blood rheology test, whole abdomen color ultrasound, kidney color ultrasound, carbohydrate tolerance test, glucose tolerance test, dynamic electrocardiogram, arterial color ultrasound and fundus examination.

[0009] Preferably, the treatment plan generating module comprises: a dialysis frequency determination unit, configured to determine the dialysis frequency according to the disease assessment score and the symptom assessment score; a dialysis time determination unit, configured to determine the dialysis time according to the height assessment score and the weight assessment score; A dialysis mode determination unit, used to determine the dialysis mode according to the degree of disease progression, patient age and weight; A target weight determination unit, used for determining a target weight according to a patient's height, age and disease; The auxiliary examination determination unit is used to determine auxiliary examination items according to the disease assessment score and the age assessment score.

[0010] As a preference, it also includes: The online access module is in communication with the patient assessment module, the treatment plan generation module, the effect monitoring module and the adjustment feedback module, and is used to: Provide evaluation of treatment effectiveness to physicians and patients; Provides online historical data viewing function.

[0011] Preferably, the online access module comprises: Expert consultation unit, for doctors and patients to consult online about treatment plans and treatment effects; Remote consultation unit, used for remote consultation between doctors and patients; The data query unit is used to query the patient's historical medical data.

[0012] As a preference, it also includes: The treatment history module is in communication with the effect monitoring module and the online access module, and is used to: Store the patient's historical treatment process and parameters; Analyze and filter historical data; Generate a treatment database.

[0013] Preferably, the effect monitoring module comprises: A data acquisition unit, used to collect monitoring data during the patient's treatment process; A data processing unit, used for cleaning, denoising and feature processing the monitoring data; The data analysis unit is used to analyze the processed data and generate a patient treatment parameter set.

[0014] Preferably, the adjustment feedback module comprises: A score adjustment unit, configured to dynamically adjust the patient's estimated score according to the processed monitoring data; A plan optimization unit, used to optimize the personalized treatment plan according to the adjusted estimated score; A feedback unit is used to feed back the optimized treatment plan to the treatment plan generation module.

[0015] A method for personalized blood purification treatment planning comprises the following steps: S1. Collect the patient's basic information, disease information and auxiliary examination information; S2. Generate patient labels; S3. Calculate the patient assessment score, wherein the patient assessment score includes a disease assessment score, a symptom assessment score, an age assessment score, a height assessment score, and a weight assessment score; S4. Generate a personalized treatment plan based on the patient assessment score, wherein the personalized treatment plan includes dialysis frequency, dialysis time, dialysis method, target weight and auxiliary examination items; S5. Obtain monitoring data of patients during treatment; S6. Processing the monitoring data; S7. Dynamically adjust the patient's estimated score based on the processed monitoring data; S8. Optimize the personalized treatment plan based on the adjusted estimated score.

[0016] The beneficial effects of the present invention are mainly reflected in the following aspects: The blood purification personalized treatment planning system and method of the present invention have significant technical advantages and clinical value. From the overall architecture, the system builds a closed-loop intelligent treatment management platform, including four core modules: patient assessment, program formulation, effect monitoring, and dynamic adjustment, realizing full-process management from assessment to treatment to optimization. This closed-loop design not only improves the accuracy of treatment, but also greatly enhances the system's adaptive ability.

[0017] In terms of module collaboration, the various functional modules are closely linked to form an organic whole. For example, the multi-dimensional evaluation scores generated by the patient evaluation module directly provide input for the treatment plan generation module, and the real-time data of the effect monitoring module can affect the evaluation results and treatment plans by adjusting the feedback module. This highly collaborative design ensures that the system can quickly respond to changes in patient status.

[0018] The present invention also cleverly resolves the contradiction between personalized treatment and standardized procedures. By introducing intelligent algorithms and dynamic adjustment mechanisms, the system can ensure the standardization of the treatment process while making personalized adjustments based on each patient's unique situation and treatment response. This not only improves the accuracy of treatment, but also reduces the workload of medical staff.

[0019] In terms of effect, the various innovative points of the present invention show significant complementarity and synergy. Multi-dimensional patient evaluation lays the foundation for precise treatment, intelligent program formulation ensures the scientific nature of treatment, and real-time monitoring and dynamic adjustment further optimize the treatment effect. These advantages are superimposed on each other to form a comprehensive effect that far exceeds traditional methods.

[0020] From a microscopic perspective, the present invention has innovations in many technical details. For example, in the patient assessment phase, the system not only considers conventional biochemical indicators, but also introduces multi-dimensional indicators such as symptom scores and quality of life assessment to fully reflect the patient's condition. In the treatment plan formulation phase, the system uses advanced machine learning algorithms to learn the best treatment strategies from massive historical data. In the effect monitoring phase, the system uses the Internet of Things technology to achieve real-time monitoring of the patient's status, greatly improving the safety of treatment.

[0021] In general, the present invention integrates multiple advanced technologies to build a highly intelligent and personalized blood purification treatment management system. This system can not only significantly improve the accuracy and effectiveness of treatment, but also reduce the workload of medical staff and reduce medical costs. More importantly, it provides a more humane and high-quality treatment experience for patients with chronic kidney disease, which is expected to significantly improve the quality of life and long-term prognosis of patients. With the promotion and application of this system, it is expected to promote the entire blood purification field to develop in a more accurate and intelligent direction, bringing revolutionary changes to medical practice. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flowchart of the overall system of the present invention.

[0023] Figure 2 It is a logical block diagram of the patient assessment module of the present invention.

[0024] Figure 3 A logical block diagram of the treatment plan generation module of the present invention.

[0025] Figure 4 It is a logic block diagram of the effect monitoring module of the present invention.

[0026] Figure 5 It is a logic block diagram of the adjustment feedback module of the present invention.

[0027] Figure 6 It is a logic block diagram of the online access module of the present invention.

[0028] Figure 7 It is a logical block diagram of the treatment history module of the present invention. DETAILED DESCRIPTION

[0029] like Figure 1-7 As shown, the present invention provides a blood purification personalized treatment planning system, and the present invention provides a blood purification personalized treatment planning system and method thereof. The system includes a patient assessment module 1, a treatment plan generation module 2, an effect monitoring module 3 and an adjustment feedback module 4.

[0030] The patient assessment module 1 is used to collect the patient's basic information, disease information and auxiliary examination information, generate patient labels, and calculate patient assessment scores. Preferably, the patient assessment score includes a disease assessment score S1, a symptom assessment score S2, an age assessment score S3, a height assessment score S4 and a weight assessment score S5. These scores can be calculated using a weighted average method, for example: ; in, is the i-th evaluation score, is the weight of the jth factor, is the standardized score of the jth factor. The weight can be determined based on expert experience and historical data analysis. For example, for the disease assessment score S1, more emphasis may be placed on renal function indicators such as creatinine and urea nitrogen levels; while for the symptom assessment score S2, more attention may be paid to the patient's subjective feelings such as fatigue and edema.

[0031] The treatment plan generation module 2 is in communication with the patient assessment module 1, and is used to receive the patient assessment scores sent by the patient assessment module 1, and generate a personalized treatment plan based on these scores. In one embodiment of the present invention, the personalized treatment plan includes dialysis frequency X1, dialysis time X2, dialysis method X3, target weight X4 and auxiliary examination items X5.

[0032] The dialysis frequency X1 can be determined based on the disease assessment score S1 and the symptom assessment score S2. For example, the following formula can be used: ; Among them, α and β are weight coefficients, which can be determined based on clinical experience. Typically, α may be between 0.6-0.8 and β between 0.2-0.4 to ensure that the severity of the disease plays a dominant role in determining the frequency of dialysis.

[0033] The dialysis time X2 is mainly determined based on the height assessment score S4 and the weight assessment score S5. The following formula can be used: ; Among them, γ and δ are weight coefficients, and ε is the basic dialysis time. γ is usually between 0.3-0.5, δ is between 0.5-0.7, and ε can be set to 3 hours as the basic value. This ensures that the effect of weight on dialysis time is slightly greater than height, while ensuring the shortest basic dialysis time.

[0034] The effect monitoring module 3 is connected to the treatment plan generation module 2 for obtaining and processing the monitoring data of the patient during the treatment process. The monitoring data may include multiple indicators such as blood pressure, heart rate, ultrafiltration volume, electrolyte levels, etc. Data processing may involve steps such as denoising and standardization to ensure data quality.

[0035] The adjustment feedback module 4 is in communication with the effect monitoring module 3 and the treatment plan generation module 2. It receives the processed monitoring data sent by the effect monitoring module 3, dynamically adjusts the patient's estimated score based on these data, and sends the adjusted estimated score to the treatment plan generation module 2. This dynamic adjustment mechanism ensures that the treatment plan can respond to changes in the patient's condition in a timely manner.

[0036] In another embodiment of the present invention, the patient assessment module 1 includes a patient information collection unit 11 , an auxiliary examination unit 12 , a health record unit 13 , a label generation unit 14 and a score calculation unit 15 .

[0037] The patient information collection unit 11 is responsible for collecting basic patient information, such as age, gender, and medical history. The auxiliary examination unit 12 is used to formulate auxiliary examination items, which may include routine blood tests, routine urine tests, fecal occult blood tests, etc. The health record unit 13 is responsible for establishing patient health records and integrating all relevant medical information. The label generation unit 14 formulates patient labels based on the collected information, which may include "chronic renal insufficiency", "hypertension", "diabetes", etc. The score calculation unit 15 is responsible for calculating the evaluation scores mentioned above.

[0038] The auxiliary examination items formulated by the auxiliary examination unit 12 may also include blood lipid analysis, renal function test, blood glucose test, electrocardiogram test, hepatitis B liver function test, coagulation function test, liver test, blood lipid test, blood rheology test, whole abdomen color Doppler ultrasound, kidney color Doppler ultrasound, carbohydrate tolerance test, glucose tolerance test, dynamic electrocardiogram, arterial color Doppler ultrasound and fundus examination. The selection of these examination items is based on the specific conditions of the patients. For example, for patients with a history of diabetes, more attention may be paid to blood glucose test and fundus examination; while for patients with cardiovascular disease risks, more attention may be paid to electrocardiogram and arterial color Doppler ultrasound.

[0039] Through this comprehensive assessment and personalized treatment plan formulation, the system of the present invention can provide more accurate and effective treatment for hemodialysis patients, improve treatment effects, and improve the quality of life of patients. At the same time, the dynamic adjustment function of the system can also respond to changes in the patient's condition in a timely manner to ensure the safety and effectiveness of treatment.

[0040] The treatment plan generating module 2 of the present invention comprises a dialysis frequency determining unit 21, a dialysis time determining unit 22, a dialysis mode determining unit 23, a target weight determining unit 24 and an auxiliary examination determining unit 25. These units work together to generate a personalized treatment plan.

[0041] The dialysis frequency determination unit 21 mainly determines the dialysis frequency according to the disease assessment score S1 and the symptom assessment score S2. In practical applications, the following formula can be used: ; in, Indicates rounding down. This formula ensures a minimum dialysis frequency of twice a week, while allowing for an appropriate increase in the number of dialysis sessions based on the severity of the patient's disease and symptoms. For example, when the value of S1+S2 is between 20 and 29, dialysis is recommended three times a week; when the value is greater than or equal to 30, a dialysis frequency of four times a week or more may need to be considered.

[0042] The dialysis time determination unit 22 mainly determines the dialysis time based on the height assessment score S3 and the weight assessment score S5. . Preferably, the following formula can be used: ; This formula sets a baseline dialysis time of 3 hours, which can be extended appropriately based on the patient's height and weight. For example, for a patient with average height and weight (assuming S3 and S5 are both 10), the calculated dialysis time is approximately 3.5 hours.

[0043] This formula sets a baseline dialysis time of 3 hours, which can be extended appropriately based on the patient's height and weight. For example, for a patient with average height and weight (assuming S3 and S5 are both 10), the calculated dialysis time is about 3.5 hours.

[0044] The dialysis mode determination unit 23 determines the dialysis mode X3 according to the degree of disease progression, the patient's age and weight. In one embodiment of the present invention, a decision tree method can be used to determine the dialysis mode. For example: 1. If the patient is <65 years old and weighs <90 kg, hemodialysis is preferred; 2. If the patient is ≥65 years old or weighs ≥90 kg and the disease progresses slowly, peritoneal dialysis may be considered; 3. If the disease progresses rapidly or there are other complications, more intensive treatments such as hemofiltration or hemodiafiltration may need to be considered.

[0045] The target weight determination unit 24 determines the target weight X4 according to the patient's height, age and disease condition. In a preferred embodiment of the present invention, a modified ideal weight calculation formula can be used: ; Where H is height (cm), A is age, and D is the disease-related weight adjustment factor.

[0046] This formula takes into account the effect of age on ideal weight and adapts to the weight requirements of different disease states through the disease adjustment factor D. For example, for patients with a significant tendency to edema, the D value may be larger, thereby reducing the target weight.

[0047] The auxiliary examination determination unit 25 mainly determines the auxiliary examination item X5 based on the disease assessment score S1 and the age assessment score S3. The present invention adopts a method for selecting auxiliary examination items based on risk score. First, the risk score R is calculated: ; Then, select different levels of auxiliary inspection items according to the R value: When R<5, basic examinations were performed, including routine blood tests, routine urine tests, and basic biochemical indicators; When 5≤R<8, additional examinations such as electrocardiogram and ultrasound were performed; When R≥8, more comprehensive examinations may need to be considered, such as dynamic electrocardiogram, whole abdominal color Doppler ultrasound, etc.

[0048] This approach can flexibly adjust auxiliary examination items according to the patient's disease severity and age-related risks, ensuring the completeness of necessary examinations while avoiding excessive examinations.

[0049] In another embodiment of the present invention, the system further comprises an online access module 5. This module maintains communication connection with the patient evaluation module 1, the treatment plan generation module 2, the effect monitoring module 3 and the adjustment feedback module 4, aiming to provide convenient remote access services for doctors and patients.

[0050] The main functions of the online access module 5 include providing doctors and patients with treatment effect evaluation and online access to historical data. For example, doctors can use this module to view the patient's treatment progress in real time, including the changing trends of various physiological indicators, the adjustment history of the treatment plan, etc. Patients can use this module to understand their own treatment status, view historical examination results, and even conduct some simple self-evaluations.

[0051] In order to achieve these functions, the online access module 5 may use a series of advanced data visualization technologies. For example, interactive charts can be used to show the changing trends of indicators such as blood pressure and weight of patients; dashboards can be used to intuitively display various parameters of the current treatment plan; and red, yellow and green three-color systems can be used to identify the status of various indicators to help users quickly identify issues that need attention.

[0052] In addition, the online access module 5 also includes an expert consultation unit 51, a remote consultation unit 52 and a data query unit 53. The expert consultation unit 51 allows doctors and patients to consult online about treatment plans and treatment effects. This function is particularly suitable for patients who are unable to move or live far away from medical centers, and can greatly improve the accessibility of medical resources.

[0053] The remote consultation unit 52 supports remote consultation between doctors. When dealing with complex cases, the attending doctor can invite other experts to have remote discussions through this unit to jointly develop the best treatment plan. This not only improves the quality of diagnosis and treatment, but also promotes the optimal allocation of medical resources.

[0054] The data query unit 53 is specifically used to query the patient's historical medical data. This unit uses an efficient data indexing and retrieval algorithm to quickly find the required information from the massive historical data. At the same time, in order to protect the privacy of patients, the data query unit 53 also implements strict access control and data desensitization measures to ensure the security of sensitive information.

[0055] Through the realization of these functions, the personalized blood purification treatment planning system of the present invention not only improves the accuracy and effect of treatment, but also greatly enhances the communication efficiency between doctors and patients, providing strong support for the development of telemedicine.

[0056] The system of the present invention also includes a treatment history module 6. This module maintains communication connection with the effect monitoring module 3 and the online access module 5, and is mainly used to store the patient's historical treatment process and parameters, analyze and screen the historical data, and generate a treatment database.

[0057] The core function of the treatment history module 6 is to establish a comprehensive patient treatment history file. After each treatment, the module will automatically record various parameters of this treatment, including but not limited to dialysis time, ultrafiltration volume, blood pressure changes, type of dialysis fluid used, etc. These data are systematically stored to form a personal treatment timeline for the patient.

[0058] In terms of data analysis, the treatment history module 6 uses advanced data mining algorithms. For example, time series analysis methods can be used to identify the long-term trend of changes in various physiological indicators of patients. Specifically, the autoregressive integrated moving average model (ARIMA) can be used to predict future indicator changes: ; Among them, p is the number of autoregressive terms, d is the number of differences, q is the number of moving average terms, and c is the constant term. is the autoregressive coefficient, is the moving average coefficient, is white noise. In this way, the system can predict the patient's future health status and provide a basis for adjusting the treatment plan.

[0059] In addition, the treatment history module 6 also includes a knowledge graph construction unit. This unit combines the patient's treatment history data with the medical knowledge base to build a personalized patient knowledge graph. This knowledge graph not only contains the patient's treatment history, but also includes relevant disease knowledge, drug interaction information, etc. Through the association analysis of the graph, the system can have a more comprehensive understanding of the patient's health status and provide deeper insights for formulating treatment plans.

[0060] The effect monitoring module 3 is another key component of the system of the present invention. The module includes a data acquisition unit 31, a data processing unit 32 and a data analysis unit 33.

[0061] The data acquisition unit 31 is responsible for collecting various monitoring data during the patient's treatment. These data may come from multiple sources, including sensors on the dialysis machine itself, wearable devices worn by patients, and manual input by medical staff. In order to ensure the integrity and accuracy of the data, the data acquisition unit 31 uses multi-source data fusion technology. For example, the Kalman filter algorithm can be used to integrate blood pressure data from different sources: ; ; in, is the current state estimate, is the observed value, is the Kalman gain, H is the observation matrix, is the estimation error covariance, and R is the observation noise covariance.

[0062] The data processing unit 32 is mainly responsible for cleaning, denoising and feature processing of the collected raw data. During the data cleaning stage, the system will detect and process problems such as outliers and missing values. For example, for missing values, multiple imputation can be used to fill them: ; in, is the final estimate, is the result of the i-th interpolation, and m is the number of interpolation times.

[0063] In the feature processing stage, the data processing unit 32 extracts some high-level features. For example, wavelet transform can be used to analyze the electrocardiogram signal to extract more meaningful features: ; in, are the wavelet transform coefficients, is the wavelet function, a is the scale parameter, and b is the translation parameter.

[0064] The data analysis unit 33 is responsible for in-depth analysis of the processed data and generating a set of patient treatment parameters. A variety of machine learning algorithms may be used here, such as support vector machine (SVM) for anomaly detection and random forest for feature importance ranking.

[0065] Finally, the adjustment feedback module 4 includes a score adjustment unit 41, a scheme optimization unit 42 and a feedback unit 43. The score adjustment unit 41 dynamically adjusts the patient's estimated score according to the processed monitoring data. This process can be regarded as an online learning problem, and the online gradient descent algorithm can be used to continuously optimize the estimation model: ; in, are model parameters, is the learning rate, L is the loss function, ( , ) is the current data sample.

[0066] The scheme optimization unit 42 optimizes the personalized treatment scheme according to the adjusted estimated score. This can be formulated as a multi-objective optimization problem, which can be solved using algorithms such as particle swarm optimization (PSO). Finally, the feedback unit 43 feeds the optimized treatment scheme back to the treatment scheme generation module 2, forming a closed-loop optimization process.

[0067] In this way, the blood purification personalized treatment planning system of the present invention can continuously learn and optimize, providing patients with increasingly accurate personalized treatment plans. The present invention also provides a blood purification personalized treatment planning method, which includes the following steps:

[0068] First, in step S1, the system collects the patient's basic information, disease information, and auxiliary examination information. This step is usually completed by medical staff when the patient first visits or during regular checkups. The collected information may include the patient's age, gender, weight, height, past medical history, current symptoms, laboratory test results, etc. Preferably, this information can be directly imported through the electronic health record system to improve the efficiency and accuracy of data collection.

[0069] Next, in step S2, the system generates patient labels based on the collected information. These labels may include disease type (such as chronic renal failure, diabetic nephropathy, etc.), complications (such as hypertension, cardiovascular disease, etc.), treatment stage (such as pre-dialysis, mid-dialysis, post-dialysis), etc. The label generation process may involve complex medical knowledge reasoning, and the present invention preferably uses a rule-based expert system to achieve this function.

[0070] In step S3, the system calculates the patient assessment score. As mentioned above, these scores include disease assessment score S1, symptom assessment score S2, age assessment score S3, height assessment score S4, and weight assessment score S5. The calculation of each score is based on specific medical assessment criteria and weight systems. For example, the disease assessment score S1 may mainly consider renal function indicators such as creatinine clearance, urea nitrogen level, etc.; the symptom assessment score S2 may focus more on the patient's subjective feelings, such as fatigue level, edema, etc.

[0071] Step S4 is the core step of the method. The system generates a personalized treatment plan based on the patient evaluation score calculated previously. The plan includes dialysis frequency X1, dialysis time X2, dialysis method X3, target weight X4 and auxiliary examination items X5. This step involves a complex medical decision-making process, and the present invention preferably adopts a method based on deep reinforcement learning to achieve it. Specifically, the patient's state can be used as the environment, the treatment parameters as the action, and the degree of improvement in the patient's health status as the reward. Through continuous simulation and learning, the optimal treatment strategy can be found.

[0072] In steps S5 and S6, the system obtains and processes the patient's monitoring data during treatment. This data may come from real-time monitoring of the dialysis machine, wearable devices worn by the patient, and regular laboratory tests. Data processing may include steps such as denoising, standardization, and feature extraction, with the aim of improving data quality and laying the foundation for subsequent analysis.

[0073] Step S7 is a dynamic adjustment step, in which the system dynamically adjusts the patient's estimated score based on the processed monitoring data. This step reflects the adaptability of the method of the present invention, and can timely adjust the evaluation results according to the patient's actual treatment response. Preferably, an online learning algorithm can be used to implement this function, so that the system can continuously learn from new data and improve the accuracy of the estimate.

[0074] Finally, in step S8, the system optimizes the personalized treatment plan based on the adjusted estimated score. This may involve fine-tuning parameters such as dialysis frequency, time, and method, or adding or removing auxiliary examination items. The optimization process needs to balance multiple goals such as treatment effect and patient quality of life, which can be achieved using a multi-objective optimization algorithm.

[0075] Through this series of steps, the method of the present invention can provide highly personalized treatment plans for hemodialysis patients, and can be dynamically adjusted according to the patient's treatment response, thereby significantly improving the treatment effect and the patient's quality of life.

[0076] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto; any person familiar with the art who, within the scope disclosed by the present invention, makes substitutions or changes based on the scheme and improved concepts of the present invention shall be covered within the protection scope of the present invention.

Claims

1. Blood purification personalized treatment planning system, characterized by: include: Patient Assessment Module for: Collect the patient's basic information, disease information and auxiliary examination information; Generate patient labels; Calculating a patient assessment score, wherein the patient assessment score includes a disease assessment score, a symptom assessment score, an age assessment score, a height assessment score, and a weight assessment score; A treatment plan generating module is communicatively connected with the patient assessment module and is used to: receiving a patient assessment score sent by the patient assessment module; Generate a personalized treatment plan based on the patient assessment score, wherein the personalized treatment plan includes dialysis frequency, dialysis time, dialysis method, target weight and auxiliary examination items; The effect monitoring module is in communication with the treatment plan generating module and is used to: Obtain monitoring data of patients during treatment; Processing the monitoring data; The adjustment feedback module is in communication with the effect monitoring module and the treatment plan generating module, and is used to: Receiving the processed monitoring data sent by the effect monitoring module; Dynamically adjusting the patient's estimated score based on the processed monitoring data; The adjusted estimated score is sent to the treatment plan generation module.

2. The blood purification personalized treatment planning system according to claim 1, characterized in that: The patient assessment module includes: Patient information collection unit, used to collect basic patient information; Auxiliary inspection unit, used to formulate auxiliary inspection items; Health record unit, used to establish patient health records; a label generation unit for formulating patient labels; A score calculation unit is used to calculate the patient assessment score.

3. The blood purification personalized treatment planning system according to claim 2, characterized in that: The auxiliary examination items formulated by the auxiliary examination unit include routine blood test, routine urine test, fecal occult blood test, blood lipid analysis, renal function test, blood sugar test, electrocardiogram, hepatitis B liver function test, coagulation function test, liver test, blood lipid test, blood rheology test, whole abdomen color ultrasound, kidney color ultrasound, carbohydrate tolerance test, glucose tolerance test, dynamic electrocardiogram, arterial color ultrasound and fundus examination.

4. The blood purification personalized treatment planning system according to claim 1, characterized in that: The treatment plan generation module includes: a dialysis frequency determination unit, configured to determine the dialysis frequency according to the disease assessment score and the symptom assessment score; a dialysis time determination unit, configured to determine the dialysis time according to the height assessment score and the weight assessment score; A dialysis mode determination unit, used to determine the dialysis mode according to the degree of disease progression, patient age and weight; A target weight determination unit, used for determining a target weight according to a patient's height, age and disease; The auxiliary examination determination unit is used to determine auxiliary examination items according to the disease assessment score and the age assessment score.

5. The blood purification personalized treatment planning system according to claim 1, characterized in that: Also includes: The online access module is in communication with the patient assessment module, the treatment plan generation module, the effect monitoring module and the adjustment feedback module, and is used to: Provide evaluation of treatment effectiveness to physicians and patients; Provides online historical data viewing function.

6. The blood purification personalized treatment planning system according to claim 5, characterized in that: The online access module includes: Expert consultation unit, for doctors and patients to consult online about treatment plans and treatment effects; Remote consultation unit, used for remote consultation between doctors and patients; The data query unit is used to query the patient's historical medical data.

7. The blood purification personalized treatment planning system according to claim 1, characterized in that: Also includes: The treatment history module is in communication with the effect monitoring module and the online access module, and is used to: Store the patient's historical treatment process and parameters; Analyze and filter historical data; Generate a treatment database.

8. The blood purification personalized treatment planning system according to claim 1, characterized in that: The effect monitoring module comprises: A data acquisition unit, used to collect monitoring data during the patient's treatment process; A data processing unit, used for cleaning, denoising and feature processing the monitoring data; The data analysis unit is used to analyze the processed data and generate a patient treatment parameter set.

9. The blood purification personalized treatment planning system according to claim 1, characterized in that: The adjustment feedback module comprises: A score adjustment unit, configured to dynamically adjust the patient's estimated score according to the processed monitoring data; A plan optimization unit, used to optimize the personalized treatment plan according to the adjusted estimated score; A feedback unit is used to feed back the optimized treatment plan to the treatment plan generation module.

10. A method for personalized blood purification treatment planning, characterized in that: The steps include: S1. Collect the patient's basic information, disease information and auxiliary examination information; S2. Generate patient labels; S3. Calculate the patient assessment score, wherein the patient assessment score includes a disease assessment score, a symptom assessment score, an age assessment score, a height assessment score, and a weight assessment score; S4. Generate a personalized treatment plan based on the patient assessment score, wherein the personalized treatment plan includes dialysis frequency, dialysis time, dialysis method, target weight and auxiliary examination items; S5. Obtain monitoring data of patients during treatment; S6. Processing the monitoring data; S7. Dynamically adjust the patient's estimated score based on the processed monitoring data; S8. Optimize the personalized treatment plan based on the adjusted estimated score.

Images