Intelligent dialysis service method and system

Abstract

The invention discloses an intelligent dialysis service method and system, and provides an intelligent dialysis service system capable of monitoring physiological information of a patient in real time, judging the dialysis effect, establishing a dialysis model, performing risk assessment and optimizing a treatment scheme. Firstly, physiological information of a patient is monitored in real time through a physiological parameter monitoring module, and data is fed back to a server. The dialysis scheme generation module is used for judging the dialysis effect according to the physiological information after dialysis, generating corresponding dialysis effect description data, establishing a dialysis model based on the generated data, analyzing the physiological information before and after dialysis, obtaining dialysis condition data, generating warning information through the dialysis condition analysis module, and assisting a doctor in judging the state of a patient. According to patient monitoring data analysis and dialysis effect description, abnormal conditions are found in time through an abnormal monitoring and early warning module, risk assessment is carried out, and early warning standards of different levels are set, so that medical staff can carry out corresponding processing.

Description

Technical Field

[0001] The present invention belongs to the field of dialysis technology, and in particular relates to an intelligent dialysis service method and system. Background Art

[0002] There are many problems in hemodialysis treatment. First, due to the time-consuming operation of blood testing technology, there is a certain lag in the acquisition of hemodialysis parameters, which makes it difficult to carry out timely management and regulation during the dialysis process. Secondly, the existing systems are usually designed according to the average user needs, lacking flexibility and personalized services, and cannot meet the specific needs of each patient. For example, the dialysis parameters of different patients may vary, but the existing system is difficult to adjust according to individual differences. In addition, because the existing system finds it difficult to predict and warn of possible complications and problems by analyzing the patient's physiological indicators and parameter changes during the dialysis process, the safety of the dialysis process and the efficiency of data processing are insufficient. Therefore, it is necessary to introduce intelligent systems and technologies to solve these problems and improve the effect of hemodialysis treatment and patient experience. Summary of the Invention

[0003] An intelligent dialysis service method comprises the following steps: S1: Data collection and real-time monitoring: Use the monitoring terminal to monitor the patient's physiological information in real time and feed the data back to the server; S2: Dialysis effect description and database management: The dialysis effect description module automatically determines the dialysis effect based on the patient's physiological information after dialysis, generates corresponding dialysis effect description data, and stores the patient information, physiological information at different times, and dialysis effect description data in the database module; S3: Dialysis model establishment: A dialysis model is established based on the data stored in the database module, physiological information before and after dialysis is analyzed, dialysis condition data is obtained, and it is determined whether the set dialysis conditions need to be adjusted. The dialysis condition analysis module uses historical data to determine whether the conditions for dialysis are suitable and generates warning information to assist doctors in judging the patient's condition. S4: Early warning system and risk assessment: Based on the analysis of patient monitoring data and description of dialysis effects, abnormal situations are detected in a timely manner and risk assessment is conducted. Different levels of early warning standards are set so that medical staff can respond accordingly based on the degree of urgency. S5: Dialysis timing determination and feedback: The dialysis timing determination module compares the patient's real-time monitored physiological information with the set dialysis conditions to determine whether the patient needs dialysis and whether the dialysis conditions are met. Feedback is provided based on the warning information of the physiological indicators and the second threshold is adjusted to more accurately assess the patient's dialysis condition. S6: Practical application and continuous optimization: Carry out practical application and combine data mining technology to analyze large amounts of patient data to discover potential patterns and trends, provide more in-depth guidance for dialysis treatment, continuously optimize intelligent systems, and continuously improve algorithms and models to adapt to changing clinical needs and patient conditions.

[0004] Furthermore, an intelligent dialysis service method, In step S3, a dialysis model is established based on the data stored in the database module. The specific steps for adding specific dialysis-related parameters are as follows: S31: Data collection: Collect the patient's physiological information data before and after dialysis: blood pressure, heart rate, blood composition, weight, and collect data during dialysis: dialysate composition, dialysis time, dialysis rate, to ensure the accuracy and completeness of the data and avoid data loss or errors; S32: Data preprocessing: Clean the data, handle missing values and outliers, perform feature selection, select features related to dialysis effect, standardize and normalize the data for model training; S33: Model training: Divide the processed dataset into a training set and a test set, use the training set to train the linear regression model, adjust the model parameters to maximize the prediction accuracy, use the test set to evaluate the model performance, and adjust the model structure to improve the generalization ability; S34: Model evaluation and optimization: Use evaluation indicators (such as accuracy, recall, F1 value, etc.) to evaluate model performance, optimize the model based on the evaluation results, adjust feature selection, adjust model parameters, and iterate the above steps until satisfactory model performance is achieved; S35: Model application and interpretation: Apply the optimized model to new data, predict dialysis effects, analyze model results, explain the relationship between features and dialysis effects, discover patterns and characteristics, and propose further adjustment suggestions and optimization plans based on model results.

[0005] Furthermore, an intelligent dialysis service method, In the specific step S3, based on the analysis of patient monitoring data and the description of dialysis effect, abnormal situations are discovered in time and risk assessment is performed, and different levels of early warning standards are set. The specific early warnings are as follows Weight change warning: If the weight change exceeds 1kg per week, the warning standard is: if the weight change exceeds 1kg, the warning will be triggered, indicating water retention or changes in nutritional status; Dialysis effect warning: Kt / V value is lower than 1.2. Warning standard: A warning is triggered when the Kt / V value is lower than 1.2, which may indicate insufficient dialysis or poor clearance effect.

[0006] Blood biochemistry warning: blood potassium exceeds 5.5 mmol / L, blood phosphorus exceeds 1.78 mmol / L, and blood calcium is less than 2.1 mmol / L. Warning standard: A warning is triggered when blood potassium exceeds 5.5 mmol / L, blood phosphorus exceeds 1.78 mmol / L, or blood calcium is less than 2.1 mmol / L; Comprehensive indicator warning of dialysis process: The above factors are combined for warning, and the weighted average method is used to integrate and obtain the warning formula in: Indicates weight change warning. When the weight change exceeds 1kg, The value is 1, otherwise it is 0. Indicates dialysis effect warning. When the Kt / V value is lower than 1.2, The value is 1, otherwise it is 0. Indicates blood biochemistry warning. When blood potassium exceeds 5.5 mmol / L, blood phosphorus exceeds 1.78 mmol / L, or blood calcium is lower than 2.1 mmol / L, The value is 1, otherwise it is 0. When the result of the warning formula is greater than 0, a comprehensive warning is triggered, warning of abnormal pressure and flow during the dialysis process. Abnormal pressure or flow during the dialysis process will trigger a warning, which may indicate a dialyzer failure or pipeline problem.

[0007] Furthermore, an intelligent dialysis service system is provided, wherein the intelligent dialysis service system is used to implement any one of the intelligent dialysis service methods described above, and the intelligent dialysis service system comprises: a patient information management module, a physiological parameter monitoring module, a dialysis plan generation module, a dialysis process control module, an abnormality monitoring and early warning module, a data analysis and reporting module, a remote monitoring and management module, and a patient education and support module; The patient information management module is used to enter and manage the patient's basic information, dialysis history, dialysis plan, etc.

[0008] Physiological parameter monitoring module: used to monitor the patient's physiological parameters during dialysis, such as blood pressure, weight, and hemodialysis parameters; Dialysis plan generation module: Generates a suitable dialysis plan based on the patient's individual situation and medical guidelines, including dialysis frequency, dialysis time, and dialysate composition; Dialysis process control module: monitors key parameters during the dialysis process, such as dialysate flow rate and dialysis membrane permeability, to ensure the safety and effectiveness of the dialysis process; Abnormal monitoring and early warning module: monitors abnormal conditions that occur during dialysis and issues early warnings to alert medical staff to intervene; Data analysis and reporting module: Analyzes patients' dialysis data, generates dialysis effect evaluation reports, and assists medical staff in adjusting dialysis plans and management strategies; Remote monitoring and management module: supports medical staff to remotely monitor and manage patients, monitor patients' dialysis conditions anytime and anywhere, and provide timely intervention and guidance; Patient Education and Support Module: Provides patients with dialysis-related knowledge education and support to help patients better understand and manage the dialysis process.

[0009] The beneficial effects of the present invention are as follows: by monitoring the patient's physiological information in real time through the monitoring terminal, changes in the patient's status can be captured in time, improving the real-time and accuracy of the treatment. Through the dialysis effect description module and database management, the patient's dialysis effect can be objectively evaluated and recorded, providing a reference basis for doctors. The establishment of a dialysis model can better analyze the physiological information before and after dialysis, helping doctors to determine whether the dialysis conditions need to be adjusted, thereby improving the personalization and accuracy of dialysis treatment. The early warning system can detect abnormal situations in a timely manner and conduct risk assessments, thereby improving the safety and controllability of the treatment process. According to the judgment of the dialysis timing determination module, whether the patient needs dialysis and the timing of dialysis can be determined more accurately, providing decision support for doctors. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A flowchart of an intelligent dialysis service method; DETAILED DESCRIPTION

[0011] An intelligent dialysis service method comprises the following steps: S1: Data collection and real-time monitoring: Use the monitoring terminal to monitor the patient's physiological information in real time and feed the data back to the server; S2: Dialysis effect description and database management: The dialysis effect description module automatically determines the dialysis effect based on the patient's physiological information after dialysis, generates corresponding dialysis effect description data, and stores the patient information, physiological information at different times, and dialysis effect description data in the database module; S3: Dialysis model establishment: A dialysis model is established based on the data stored in the database module, physiological information before and after dialysis is analyzed, dialysis condition data is obtained, and it is determined whether the set dialysis conditions need to be adjusted. The dialysis condition analysis module uses historical data to determine whether the conditions for dialysis are suitable and generates warning information to assist doctors in judging the patient's condition. S4: Early warning system and risk assessment: Based on the analysis of patient monitoring data and description of dialysis effects, abnormal situations are detected in a timely manner and risk assessment is conducted. Different levels of early warning standards are set so that medical staff can respond accordingly based on the degree of urgency. S5: Dialysis timing determination and feedback: The dialysis timing determination module compares the patient's real-time monitored physiological information with the set dialysis conditions to determine whether the patient needs dialysis and whether the dialysis conditions are met. Feedback is provided based on the warning information of the physiological indicators and the second threshold is adjusted to more accurately assess the patient's dialysis condition. S6: Practical application and continuous optimization: Carry out practical application and combine data mining technology to analyze large amounts of patient data to discover potential patterns and trends, provide more in-depth guidance for dialysis treatment, continuously optimize intelligent systems, and continuously improve algorithms and models to adapt to changing clinical needs and patient conditions.

[0012] Furthermore, an intelligent dialysis service method, In step S3, a dialysis model is established based on the data stored in the database module. The specific steps for adding specific dialysis-related parameters are as follows: S31: Data collection: Collect the patient's physiological information data before and after dialysis: blood pressure, heart rate, blood composition, weight, and collect data during dialysis: dialysate composition, dialysis time, dialysis rate, to ensure the accuracy and completeness of the data and avoid data loss or errors; S32: Data preprocessing: Clean the data, handle missing values and outliers, perform feature selection, and select features related to dialysis effect. Standardize and normalize the data for model training; S33: Model training: Divide the processed dataset into a training set and a test set, use the training set to train the linear regression model, adjust the model parameters to maximize the prediction accuracy, use the test set to evaluate the model performance, and adjust the model structure to improve the generalization ability; S34: Model evaluation and optimization: Use evaluation indicators (such as accuracy, recall, F1 value, etc.) to evaluate model performance, optimize the model based on the evaluation results, adjust feature selection, adjust model parameters, and iterate the above steps until satisfactory model performance is achieved; S35: Model application and interpretation: Apply the optimized model to new data, predict dialysis effects, analyze model results, explain the relationship between features and dialysis effects, discover patterns and characteristics, and propose further adjustment suggestions and optimization plans based on model results.

[0013] Furthermore, an intelligent dialysis service method, In the specific step S3, based on the analysis of patient monitoring data and the description of dialysis effect, abnormal situations are discovered in time and risk assessment is performed, and different levels of early warning standards are set. The specific early warnings are as follows Weight change warning: If the weight change exceeds 1kg per week, the warning standard is: if the weight change exceeds 1kg, the warning will be triggered, indicating water retention or changes in nutritional status; Dialysis effect warning: Kt / V value is lower than 1.2. Warning standard: A warning is triggered when the Kt / V value is lower than 1.2, which may indicate insufficient dialysis or poor clearance effect.

[0014] Blood biochemistry warning: blood potassium exceeds 5.5 mmol / L, blood phosphorus exceeds 1.78 mmol / L, and blood calcium is less than 2.1 mmol / L. Warning standard: A warning is triggered when blood potassium exceeds 5.5 mmol / L, blood phosphorus exceeds 1.78 mmol / L, or blood calcium is less than 2.1 mmol / L; Comprehensive indicator warning of dialysis process: The above factors are combined for warning, and the weighted average method is used to integrate and obtain the warning formula in: Indicates weight change warning. When the weight change exceeds 1kg, The value is 1, otherwise it is 0. Indicates dialysis effect warning. When the Kt / V value is lower than 1.2, The value is 1, otherwise it is 0. Indicates blood biochemistry warning. When blood potassium exceeds 5.5 mmol / L, blood phosphorus exceeds 1.78 mmol / L, or blood calcium is lower than 2.1 mmol / L, The value is 1, otherwise it is 0. When the result of the warning formula is greater than 0, a comprehensive warning is triggered, warning of abnormal pressure and flow during the dialysis process. Abnormal pressure or flow during the dialysis process will trigger a warning, which may indicate a dialyzer failure or pipeline problem.

[0015] Furthermore, an intelligent dialysis service system is provided, wherein the intelligent dialysis service system is used to implement any one of the intelligent dialysis service methods described above, and the intelligent dialysis service system comprises: a patient information management module, a physiological parameter monitoring module, a dialysis plan generation module, a dialysis process control module, an abnormality monitoring and early warning module, a data analysis and reporting module, a remote monitoring and management module, and a patient education and support module; The patient information management module is used to enter and manage the patient's basic information, dialysis history, dialysis plan, etc.

[0016] Physiological parameter monitoring module: used to monitor the patient's physiological parameters during dialysis, such as blood pressure, weight, and hemodialysis parameters; Dialysis plan generation module: Generates a suitable dialysis plan based on the patient's individual situation and medical guidelines, including dialysis frequency, dialysis time, and dialysate composition; Dialysis process control module: monitors key parameters during the dialysis process, such as dialysate flow rate and dialysis membrane permeability, to ensure the safety and effectiveness of the dialysis process; Abnormal monitoring and early warning module: monitors abnormal conditions that occur during dialysis and issues early warnings to alert medical staff to intervene; Data analysis and reporting module: Analyzes patients' dialysis data, generates dialysis effect evaluation reports, and assists medical staff in adjusting dialysis plans and management strategies; Remote monitoring and management module: supports medical staff to remotely monitor and manage patients, monitor patients' dialysis conditions anytime and anywhere, and provide timely intervention and guidance; Patient Education and Support Module: Provides patients with dialysis-related knowledge education and support to help patients better understand and manage the dialysis process.

Claims

1. An intelligent dialysis service method, characterized in that: The following steps are involved: S1: Data collection and real-time monitoring: Use the monitoring terminal to monitor the patient's physiological information in real time and feed the data back to the server; S2: Dialysis effect description and database management: The dialysis effect description module automatically determines the dialysis effect based on the patient's physiological information after dialysis, generates corresponding dialysis effect description data, and stores the patient information, physiological information at different times, and dialysis effect description data in the database module; S3: Dialysis model establishment: A dialysis model is established based on the data stored in the database module, physiological information before and after dialysis is analyzed, dialysis condition data is obtained, and it is determined whether the set dialysis conditions need to be adjusted. The dialysis condition analysis module uses historical data to determine whether the conditions for dialysis are suitable and generates warning information to assist doctors in judging the patient's condition. S4: Early warning system and risk assessment: Based on the analysis of patient monitoring data and description of dialysis effects, abnormal situations are detected in a timely manner and risk assessment is conducted. Different levels of early warning standards are set so that medical staff can respond accordingly based on the degree of urgency. S5: Dialysis timing determination and feedback: The dialysis timing determination module compares the patient's real-time monitored physiological information with the set dialysis conditions to determine whether the patient needs dialysis and whether the dialysis conditions are met. Feedback is provided based on the warning information of the physiological indicators and the second threshold is adjusted to more accurately assess the patient's dialysis condition. S6: Practical application and continuous optimization: Carry out practical application and combine data mining technology to analyze large amounts of patient data to discover potential patterns and trends, provide more in-depth guidance for dialysis treatment, continuously optimize intelligent systems, and continuously improve algorithms and models to adapt to changing clinical needs and patient conditions.

2. The intelligent dialysis service method according to claim 1, characterized in that: In step S3, a dialysis model is established based on the data stored in the database module. The specific steps for adding specific dialysis-related parameters are as follows: S31: Data collection: Collect the patient's physiological information data before and after dialysis: blood pressure, heart rate, blood composition, weight, and collect data during dialysis: dialysate composition, dialysis time, dialysis rate, to ensure the accuracy and completeness of the data and avoid data loss or errors; S32: Data preprocessing: Clean the data, handle missing values and outliers, perform feature selection, and select features related to dialysis effect. Standardize and normalize the data for model training; S33: Model training: Divide the processed dataset into a training set and a test set, use the training set to train the linear regression model, adjust the model parameters to maximize the prediction accuracy, use the test set to evaluate the model performance, and adjust the model structure to improve the generalization ability; S34: Model evaluation and optimization: Use evaluation indicators such as accuracy, recall rate, and F1 value to evaluate model performance. Optimize the model based on the evaluation results, adjust feature selection, adjust model parameters, and iterate the above steps until satisfactory model performance is achieved. S35: Model application and interpretation: Apply the optimized model to new data, predict dialysis effects, analyze model results, explain the relationship between features and dialysis effects, discover patterns and characteristics, and propose further adjustment suggestions and optimization plans based on model results.

3. The intelligent dialysis service method according to claim 1, wherein: In the specific step S3, based on the analysis of patient monitoring data and the description of dialysis effects, abnormal conditions are discovered in a timely manner and risk assessment is performed, and different levels of warning standards are set. The specific warnings are as follows; Weight change warning: If the weight change exceeds 1kg per week, the warning standard is: if the weight change exceeds 1kg, the warning will be triggered, indicating water retention and changes in nutritional status; Dialysis effect warning: Kt / V value is lower than 1.

2. Warning standard: Kt / V value lower than 1.2 will trigger a warning, indicating insufficient dialysis and poor clearance effect; Blood biochemistry warning: blood potassium exceeds 5.5 mmol / L, blood phosphorus exceeds 1.78 mmol / L, and blood calcium is less than 2.1 mmol / L. Warning standard: A warning is triggered when blood potassium exceeds 5.5 mmol / L, blood phosphorus exceeds 1.78 mmol / L, or blood calcium is less than 2.1 mmol / L; Comprehensive indicator warning of dialysis process: The above factors are combined for warning, and the weighted average method is used to integrate and obtain the warning formula in: Indicates weight change warning, Indicates dialysis effect warning, It indicates blood biochemistry warning, warning of abnormal pressure and flow during dialysis. Abnormal pressure and flow during dialysis will trigger the warning, indicating dialyzer failure and pipeline problems.

4. An intelligent dialysis service system, characterized in that: The intelligent dialysis service system is used to implement the intelligent dialysis service method according to any one of claims 1 to 3, and the intelligent dialysis service system includes: a patient information management module, a physiological parameter monitoring module, a dialysis plan generation module, a dialysis process control module, an abnormality monitoring and early warning module, a data analysis and reporting module, a remote monitoring and management module, and a patient education and support module; The patient information management module is used to input and manage the patient's basic information, dialysis history, dialysis plan, etc. Physiological parameter monitoring module: used to monitor the patient's physiological parameters during dialysis, such as blood pressure, weight, and hemodialysis parameters; Dialysis plan generation module: Generates a suitable dialysis plan based on the patient's individual situation and medical guidelines, including dialysis frequency, dialysis time, and dialysate composition; Dialysis process control module: monitors key parameters during the dialysis process, such as dialysate flow rate and dialysis membrane permeability, to ensure the safety and effectiveness of the dialysis process; Abnormal monitoring and early warning module: monitors abnormal conditions that occur during dialysis and issues early warnings to alert medical staff to intervene; Data analysis and reporting module: Analyzes patients' dialysis data, generates dialysis effect evaluation reports, and assists medical staff in adjusting dialysis plans and management strategies; Remote monitoring and management module: supports medical staff to remotely monitor and manage patients, monitor patients' dialysis conditions anytime and anywhere, and provide timely intervention and guidance; Patient Education and Support Module: Provides patients with dialysis-related knowledge education and support to help patients better understand and manage the dialysis process.

Images