Outpatient hemodialysis infection event monitoring system and monitoring method

Abstract

The invention provides an outpatient hemodialysis infection event monitoring system and monitoring method, and is applied to the technical field of data processing. The method comprises the following steps: processing vascular access information of a target patient and an outpatient hemodialysis intubation record of the target patient to generate a hemodialysis event influence factor; processing the dialysis physiological parameter information of the target patient within the preset time to generate hemodialysis monitoring parameter information of the target patient; processing the historical infection data of the hemodialysis target patient to generate a hemodialysis prediction monitoring feature vector; and processing the hemodialysis event influence factor, the hemodialysis monitoring parameter information of the target patient, the hemodialysis prediction monitoring feature vector and the infection examination result information of the target patient based on the target hemodialysis event early warning model to generate hemodialysis infection event early warning information.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a monitoring system and method for outpatient hemodialysis infection events. Background Art

[0002] Hemodialysis is an important treatment method for maintaining the life of patients with end-stage renal disease, and there are a large number of outpatient hemodialysis patients. However, currently, outpatient hemodialysis patients face a relatively high risk of infection, and the infection problem has become a key factor affecting the health of patients and the effect of dialysis treatment.

[0003] Traditional monitoring methods are difficult to comprehensively, timely, and accurately monitor the infection risk of patients. Existing monitoring means often rely only on a single indicator or simply observe the physical signs of patients, and cannot comprehensively consider various complex factors. For example, only focusing on the change in the patient's body temperature and ignoring factors such as the vascular access condition, dialysis equipment-related factors, and the patient's own historical infection situation, etc., resulting in the inability to detect potential infection risks in advance, making it difficult for patients to receive timely intervention and treatment in the initial stage of infection.

[0004] Clinically, there is an urgent need for a more effective monitoring model for outpatient hemodialysis infection events to achieve accurate monitoring and early warning of the infection risk of outpatient hemodialysis patients, reduce the infection incidence rate, and ensure the dialysis safety of patients.

[0005] It should be noted that the information disclosed in the above background art section is only used to enhance the understanding of the background of the present disclosure, and therefore includes information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] The purpose of the present application is to provide a monitoring system and method for outpatient hemodialysis infection events, which at least to a certain extent overcome the problems existing in the prior art. By obtaining multi-faceted data of target patients, processing the vascular access and outpatient hemodialysis catheterization records to generate hemodialysis event impact factors; processing dialysis physiological parameters to obtain hemodialysis monitoring parameter information; analyzing historical infection data to generate hemodialysis prediction monitoring feature vectors, providing a multi-dimensional basis for subsequent infection risk assessment, realizing effective monitoring and early warning of the infection risk of outpatient hemodialysis patients, and helping to timely discover potential infection risks.

[0007] Other characteristics and advantages of the present application will become apparent through the following detailed description, or will be learned in part through the practice of the present invention.

[0008] According to one aspect of the present application, a method for monitoring outpatient hemodialysis infection events is provided, including: obtaining the hemodialysis physiological parameter information of a target patient undergoing maintenance hemodialysis within a preset time, the vascular access information of the target patient, the outpatient hemodialysis intubation record of the target patient, the infection examination result information of the target patient, and the historical infection data of the hemodialysis target patient; processing the vascular access information of the target patient and the outpatient hemodialysis intubation record of the target patient to generate a hemodialysis event impact factor; processing the hemodialysis physiological parameter information of the target patient within a preset time to generate the hemodialysis monitoring parameter information of the target patient; processing the historical infection data of the hemodialysis target patient to generate a hemodialysis prediction monitoring feature vector; and processing the hemodialysis event impact factor, the hemodialysis monitoring parameter information of the target patient, the hemodialysis prediction monitoring feature vector, and the infection examination result information of the target patient based on the target hemodialysis event warning model to generate a hemodialysis infection event warning information.

[0009] According to another aspect of the present application, a monitoring device for outpatient hemodialysis infection events is provided, characterized by including: an acquisition module for obtaining the hemodialysis physiological parameter information of a target patient undergoing maintenance hemodialysis within a preset time, the vascular access information of the target patient, the outpatient hemodialysis intubation record of the target patient, the infection examination result information of the target patient, and the historical infection data of the hemodialysis target patient; a processing module for processing the vascular access information of the target patient and the outpatient hemodialysis intubation record of the target patient to generate a hemodialysis event impact factor; processing the hemodialysis physiological parameter information of the target patient within a preset time to generate the hemodialysis monitoring parameter information of the target patient; processing the historical infection data of the hemodialysis target patient to generate a hemodialysis prediction monitoring feature vector; and processing the hemodialysis event impact factor, the hemodialysis monitoring parameter information of the target patient, the hemodialysis prediction monitoring feature vector, and the infection examination result information of the target patient based on the target hemodialysis event warning model to generate a hemodialysis infection event warning information.

[0010] According to still another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a second processor, the above-mentioned method for monitoring outpatient hemodialysis infection events is implemented.

[0011] For the outpatient hemodialysis infection event monitoring system and monitoring method provided by the present application, the server obtains various data of the target patient, such as hemodialysis physiological parameters, vascular access information, etc. By processing the vascular access and outpatient hemodialysis intubation record, a hemodialysis event impact factor is generated; processing the hemodialysis physiological parameters to obtain the hemodialysis monitoring parameter information; analyzing the historical infection data to generate a hemodialysis prediction monitoring feature vector. These data processing steps provide a multi-dimensional basis for subsequent infection risk assessment. Using the model to comprehensively generate an infection risk score for various types of data, further determining the infection risk level, and issuing a hemodialysis infection event warning information according to a preset threshold.

[0012] Deeply analyze the warning information to determine the source and transmission route of the infectious pathogen, such as judging whether the infection is caused by catheterization operations, dialysis equipment, etc. Generate target triage information and response cause priority information based on this information to provide guidance for subsequent targeted measures. Finally, formulate hemodialysis infection warning measures according to the above information, such as adjusting the treatment plan, strengthening equipment disinfection, etc., to reduce the infection risk. Through comprehensive data processing and multi-step analysis and evaluation, the effective monitoring and warning of the infection risk of outpatient hemodialysis patients are realized, which helps to timely discover potential infection risks, provides strong support for medical staff to take corresponding measures, and is of great significance for ensuring the safety of patient dialysis and reducing the infection incidence rate.

[0013] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 The flowchart showing a method for monitoring an outpatient hemodialysis infection event provided by an embodiment of the present application;

[0015] Figure 2 The structural schematic diagram showing a device for monitoring an outpatient hemodialysis infection event provided by an embodiment of the present application. DETAILED DESCRIPTION

[0016] The following describes the preferred embodiments of the present invention with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only for the purpose of illustration and explanation of the present invention, and are not used to limit the present invention.

[0017] The following combines Figure 1 to describe a method for monitoring an outpatient hemodialysis infection event according to an exemplary embodiment of the present application. In one embodiment, the present application also proposes a monitoring system and a monitoring method for an outpatient hemodialysis infection event. Figure 1 Schematically shows a flowchart of a method for monitoring an outpatient hemodialysis infection event according to an embodiment of the present application. As Figure 1 shown, this method is applied to a server and includes:

[0018] S101, obtaining the dialysis physiological parameter information of a target patient undergoing maintenance hemodialysis within a preset time, the vascular access information of the target patient, the outpatient hemodialysis catheterization record of the target patient, the infection examination result information of the target patient, and the historical infection data of the hemodialysis target patient.

[0019] In one implementation, in the outpatient hemodialysis center of a certain hospital, there is a complete monitoring system for comprehensively monitoring patients undergoing maintenance hemodialysis. Taking patient Mr. Li as an example, let's detail how to obtain various types of data: The dialysis equipment is connected to the hospital information system in real-time. During each dialysis session of Mr. Li, the system automatically collects multiple physiological parameters. For example, during a dialysis process, at the start of dialysis, the blood flow rate stabilizes at 250 ml / min, the dialysis fluid flow rate is 500 ml / min, the venous pressure is maintained at around 150 mmHg, and the body temperature is 36.5°C. As dialysis progresses, these parameters change in real-time, and the system continuously records them. After each dialysis session, all the physiological parameter data during this dialysis process, together with a time stamp accurate to the second, such as "blood flow rate, dialysis fluid flow rate, venous pressure, and body temperature data during the period from 10:00:00 on October 15, 2024, to 12:30:00 on October 15, 2024", are stored in the long-term monitoring database. These data not only record the current dialysis situation but also provide a basis for subsequent analysis, facilitating medical staff to observe the changing trends of various physiological indicators of Mr. Li during different dialysis periods.

[0020] Mr. Li uses a tunneled cuffed central venous catheter (TCC) as the vascular access. This information is detailedly recorded in the system, including the catheter placement location (such as the right internal jugular vein) and the catheter placement time (August 10, 2024). In addition, medical staff regularly check the condition of the vascular access, such as whether the blood vessels are unobstructed, and signs of stenosis, thrombosis, etc. These inspection results are also promptly entered into the system. For example, during an inspection in October 2024, it was found that the blood flow rate of Mr. Li's vascular access was slightly lower than the normal range, and this information was recorded, providing a reference for subsequent infection risk assessment. Mr. Li's outpatient hemodialysis catheterization records detail all the relevant information about his each catheterization. Recently, due to treatment needs, Mr. Li had a catheter replacement operation on October 5, 2024, changing from the original long-term catheter (TCC) to a temporary catheter (ECC), and the information on the change in catheter type was accurately recorded. Before and after each dialysis, medical staff evaluate the catheter, and the evaluation results are also recorded. For example, during the pre-dialysis evaluation on October 15, 2024, it was found that the skin around the catheter puncture site was slightly red, but there was no bleeding or secretion. These catheter evaluation results provide an important basis for judging the infection risk.

[0021] Mr. Li undergoes regular screening for bloodborne pathogens, namely the eight preoperative immunity tests. The most recent test was on October 10, 2024, and the test results showed negative for hepatitis B surface antigen, negative for hepatitis C antibody, negative for HIV antibody, negative for syphilis blood specific antibody, etc. The previous test results are also stored in the system for convenient comparison and analysis. If an abnormality appears in a certain test result, such as the hepatitis B surface antigen turning from negative to positive, the system will immediately detect this change and further evaluate the infection risk in combination with other data. The system stores Mr. Li's past infection-related data. In the past year, Mr. Li had a fever symptom due to vascular access infection in March 2024, with a body temperature reaching 37.8°C. The blood culture result showed a Staphylococcus aureus infection. Antibacterial treatment was carried out at that time, using cephalosporin antibiotics, and the treatment lasted for 10 days. These historical infection data, including the infection time, infection symptoms, infectious pathogens, treatment measures, and treatment duration, are of great significance for analyzing Mr. Li's current infection risk, and can help medical staff understand his infection pattern and susceptibility, so as to more accurately evaluate the current infection risk.

[0022] In another implementation, obtaining a target hemodialysis event warning model includes obtaining a training sample set and a preset hemodialysis event warning model. Among them, the training sample set includes the dialysis physiological parameter information, vascular access information, outpatient hemodialysis catheterization records, infection test result information, and historical infection data of other patients undergoing maintenance hemodialysis within a preset time. Specifically, various data of numerous patients undergoing maintenance hemodialysis are stored in the hospital information system. The relevant data of 1000 patients in the past 12 months are selected as the training sample set. These data cover dialysis physiological parameter information, such as the blood flow rate of patient A being 280 ml / min, the dialysis fluid flow rate being 500 ml / min, the venous pressure being 160 mmHg, and the body temperature being 36.8°C during a certain dialysis; vascular access information, like patient B using a temporary catheter (ECC) with the catheterization position in the femoral vein; outpatient hemodialysis catheterization records, for example, patient C had two catheterizations within 30 days, and the catheterization type changed from a long-term catheter (TCC) to a temporary catheter (ECC); infection test result information, such as the hepatitis B surface antigen in the eight preoperative immunity tests of patient D being positive; historical infection data of hemodialysis patients, such as patient E had an infection due to hemodialysis half a year ago, with symptoms of fever and Escherichia coli found in the blood culture. At the same time, a logistic regression model is selected as the preset hemodialysis event warning model, and this model has a framework for initially analyzing data and predicting infection risk.

[0023] Count the quantity of each data feature in the training sample set, and generate a sampling ratio based on these quantities. The hemodialysis physiological parameter information includes 4 main features: blood flow rate, dialysate flow rate, venous pressure, and body temperature; the vascular access information includes 3 features such as catheterization type and catheterization location; the outpatient hemodialysis catheterization record has 4 features such as catheterization times and changes in catheterization type; the infection test result information involves 8 features of the eight preoperative immunity tests; the historical infection data of hemodialysis patients includes 5 features such as the number of infections and types of infectious pathogens. According to these feature quantities, considering the importance of different features and the data distribution, generate the sampling ratio according to the proportion of the feature quantity in the total feature quantity. Suppose the feature quantity of the hemodialysis physiological parameter information accounts for 20% of the total feature quantity, then its sampling ratio is set to 0.2.

[0024] Perform sampling processing on the training sample set based on the sampling ratio to generate a preset number of sampled features. From the data of 1000 patients, according to the sampling ratio of 0.2 for the hemodialysis physiological parameter information, randomly select the hemodialysis physiological parameter data of 200 patients; according to the sampling ratio of the vascular access information, extract the vascular access data of the corresponding number of patients, and so on. Sample each data type, and finally generate a preset number of sampled features. These sampled features form a new data set, which contains representative data extracted from the original training sample set.

[0025] Process any data feature with each sampled feature, and divide the data into a response group and a poor response group. Among them, each group contains a preset number of data samples, and at least one data sample has identification information. For example, select the data feature of "body temperature" in the hemodialysis physiological parameters and process it with each sampled feature. Taking 37.3°C as the boundary, divide the patient data in the sampled features with a body temperature higher than or equal to 37.3°C and accompanied by other infection-related signs (such as positive blood culture, abnormal white blood cell count, etc.) into the poor response group; divide the patient data with a body temperature lower than 37.3°C and no other obvious infection signs into the response group. Each group is set to contain 200 data samples, and add the patient ID as identification information to each data sample for subsequent tracking and analysis.

[0026] Process the preset hemodialysis event warning model based on the response group and the poor response group to generate a trained hemodialysis event warning model and training results. If the data samples containing identification information in the training results are factors characterizing the hemodialysis infection risk, then the trained hemodialysis event warning model is used as the target hemodialysis event warning model. The model analyzes the relationships between various features and the infection risk in the two groups of data and continuously adjusts its own parameters (such as regression coefficients). During the training process, the model learns the associations between factors such as increased body temperature, frequent changes in catheter types, and positive screening for bloodborne pathogens and the hemodialysis infection risk. After the training is completed, a trained hemodialysis event warning model and training results are obtained. The training results include the model's evaluation of the relationships between various data features and the infection risk. Check the data samples with identification information in the training results to determine which factors have a significant impact on the hemodialysis infection risk. If it is found that in the training results, data samples containing identification information such as "body temperature higher than 37.3°C", "catheter type changed more than twice within three months", and "a certain index in the eight items of surgical immunity is positive" can effectively characterize the factors of hemodialysis infection risk, then the trained logistic regression model is determined as the target hemodialysis event warning model. This model can be used for subsequent more accurate prediction and warning of the infection risk of other outpatient hemodialysis patients.

[0027] S102. Process the vascular access information of the target patient and the outpatient hemodialysis catheterization record of the target patient to generate a hemodialysis event influencing factor.

[0028] In one implementation, process the outpatient hemodialysis catheterization record of the target patient to obtain catheter type change information and catheter evaluation results. Mr. Li's outpatient hemodialysis catheterization record details the relevant information of each of his catheterizations. Over a period of time, Mr. Li initially used a long-term catheter (TCC), which was inserted on August 10, 2024, at the right internal jugular vein. On October 5, 2024, due to treatment needs, Mr. Li had a catheter replacement and changed to a temporary catheter (ECC). This change in catheter type was accurately recorded by the system and became the catheter type change information. Before and after each dialysis, medical staff would evaluate Mr. Li's catheter and record the evaluation results in the system. For example, during the pre-dialysis evaluation on October 15, 2024, it was found that the skin around the catheter puncture site was slightly red, but there was no bleeding, secretion, or hematoma, and the fixation was good. These evaluation information are the catheter evaluation results.

[0029] Process the information on the change of catheter types to generate catheter types for different time periods. During the period from August 10, 2024 to October 4, 2024, Mr. Li's catheter type was long-term catheterization (TCC); starting from October 5, 2024, the catheter type changed to temporary catheterization (ECC). Through such processing, Mr. Li's catheter types in different time periods are clearly presented, facilitating subsequent analysis of the impact of different catheter types on the infection risk. Process the catheter assessment results to generate information on hematoma conditions and bleeding conditions. In Mr. Li's catheter assessment on October 15, 2024, it was clearly recorded that there was no hematoma, so the information on hematoma conditions was "no hematoma". At the same time, the assessment results showed no bleeding, so the information on bleeding conditions was "no bleeding". These information will be one of the important bases for assessing the infection risk.

[0030] Process the catheter types, information on hematoma conditions and information on bleeding conditions for different time periods to generate information on the degree of impact. Among them, the information on the degree of imaging is used to characterize the change situations of different catheter types and the corresponding impact weights of catheter assessment results. The change of catheter type from long-term catheterization (TCC) to temporary catheterization (ECC) may increase the infection risk, so a relatively high impact weight is assigned to this change; while the situations of no hematoma and no bleeding have relatively less impact on the infection risk, and lower impact weights are assigned. For example, through a certain algorithm or expert experience, the impact weight of the change of catheter type (from TCC to ECC) is set to 0.8, the impact weight of no hematoma is set to 0.1, and the impact weight of no bleeding is set to 0.1. The information composed of these weight values is the information on the degree of impact, which is used to quantify the impact degree of different situations on the hemodialysis infection risk.

[0031] Process the vascular access information and information on the degree of imaging of the target patient to generate the impact factor of hemodialysis events. In the process of assessing Mr. Li's hemodialysis infection risk, the impact factor of hemodialysis events is a key indicator, which comprehensively considers various factors related to the infection risk. When calculating this factor, factors such as the change of catheter type, hematoma conditions, bleeding conditions, and vascular access location information need to be considered, and corresponding impact weights are assigned to each factor. Let the impact factor of hemodialysis events be I, and the impact weight of the change of catheter type be ω 1 ,set to 0.8; the impact weight of hematoma conditions is ω 2 ,taking the value of 0.1; the impact weight of bleeding conditions is ω 3 ,being 0.1; the impact weight of vascular access location information is ω 4 ,assuming that when the vascular access location is the right internal jugular vein, its impact weight is ω 4 being 0.3.

[0032] Regarding the change of catheter type, Mr. Li changed from long-term catheterization (TCC) to temporary catheterization (ECC), and this change has a greater impact on the infection risk. Use x1 Indicates the degree of influence of the change in catheterization type. When there is a change, x 1 = 1. In terms of the hematoma situation, Mr. Li's catheter evaluation result is no hematoma, and x 2 is used to represent the degree of influence of the hematoma situation. When there is no hematoma, x 2 = 0. Similarly for the bleeding situation, Mr. Li has no bleeding, so the degree of influence of the bleeding situation x 3 = 0. For the vascular access location, Mr. Li's catheterization location is the right internal jugular vein. It is set that the degree of influence of the vascular access location at this time x 4 = 1.

[0033] According to the formula I = ω 1 x 1 + ω 2 x 2 + ω 3 x 3 + ω 4 x 4 , substitute the above values for calculation:

[0034] I = 0.8×1 + 0.1×0 + 0.1×0 + 0.3×1 = 1.1.

[0035] The current hemodialysis event impact factor for Mr. Li is obtained as 1.1. This hemodialysis event impact factor will be combined with other information (such as dialysis physiological parameters, infection test results, etc.) in subsequent evaluations to assess Mr. Li's hemodialysis infection risk. The higher the impact factor, the greater the possible risk of Mr. Li having a hemodialysis infection. Based on this factor, the infection status of Mr. Li can be judged more scientifically, and corresponding measures can be taken in a timely manner, such as strengthening monitoring or adjusting the treatment plan, etc.

[0036] S103. Process the dialysis physiological parameter information of the target patient within a preset time to generate the hemodialysis monitoring parameter information of the target patient.

[0037] In one implementation, the dialysis physiological parameter information of a target patient within a preset time is processed to generate the dialysis data for each time and the corresponding timestamps. When Mr. Li undergoes hemodialysis in the hospital, the dialysis equipment is connected to the hospital information system in real time. During a dialysis process, the system automatically collects various physiological parameters from the start of dialysis. For example, at the start of dialysis, the blood flow rate is 250 ml / min, the dialysis fluid flow rate is 500 ml / min, the venous pressure is 150 mmHg, and the body temperature is 36.5°C. At this time, the time is 9:00 am on November 1, 2024. These data, together with the time accurate to seconds, "November 1, 2024 09:00:00", are recorded. As dialysis progresses, at regular intervals (such as every minute), the system records a new set of parameter data and the corresponding time. For example, at 9:01 am, the blood flow rate changes to 245 ml / min, and other parameters also change accordingly. All these data are completely recorded. After dialysis ends, all the data collected during this dialysis process, such as "November 1, 2024 09:00:00 - blood flow rate 250 ml / min, dialysis fluid flow rate 500 ml / min, venous pressure 150 mmHg, body temperature 36.5°C; November 1, 2024 09:01:00 - blood flow rate 245 ml / min..." etc., are organized into the dialysis data for each time and corresponding timestamps, and stored in the long-term monitoring database.

[0038] Noise filtering and normalization processing are performed on the dialysis data for each time to generate the dialysis parameter sequence information of the target patient. The raw data collected may be subject to noise interference, which affects the accuracy of the data and subsequent analysis. For example, occasionally due to momentary fluctuations in the equipment, an abnormal value of a certain parameter may occur. The system uses a specific algorithm to perform noise filtering on the dialysis data for each time. Suppose the moving average method is used to process the blood flow rate data to remove the abnormal values that deviate significantly from the normal fluctuation range.

[0039] After noise filtering, since the dimensions and value ranges of different parameters are different, in order to facilitate unified analysis, normalization processing is also required. Taking the blood flow rate and venous pressure as an example, the blood flow rate is generally between 100 - 300 ml / min, and the venous pressure is between 50 - 300 mmHg. Their value ranges and dimensions are different. Using the normalization formula (such as where X is the raw data, X max and X min(That is, the maximum and minimum values of the parameter within a certain period of time), parameters such as blood flow rate and venous pressure are all transformed into the range of 0 - 1. After such processing, all the parameters of Mr. Li's each dialysis are transformed into data of a unified scale, forming the dialysis parameter sequence information of the target patient. For example, the processed data of a certain dialysis may be presented as "[0.5 (normalized value of blood flow rate), 0.6 (normalized value of dialysis fluid flow rate), 0.4 (normalized value of venous pressure), 0.3 (normalized value of body temperature)]", and arranged in the order of dialysis time, it constitutes the parameter sequence information of Mr. Li's this dialysis.

[0040] Based on the preset threshold ranges of each parameter and the monitoring purpose, dynamic analysis and correlation analysis are performed on the dialysis parameter sequence information of the target patient to generate the hemodialysis monitoring parameter information of the target patient. According to clinical experience and medical research, preset threshold ranges are set for each parameter. For example, the threshold range of normal blood flow rate is set at 200 - 280 ml / min, and the threshold range of venous pressure is set at 80 - 200 mmHg, etc. At the same time, based on the monitoring purpose of whether there is an infection risk during Mr. Li's dialysis process, the system performs dynamic analysis and correlation analysis on his dialysis parameter sequence information.

[0041] In terms of dynamic analysis, the system will observe the changing trend of parameters over time in real time. For example, if during Mr. Li's dialysis, the blood flow rate was originally fluctuating stably within the normal range, but suddenly continued to decline and was lower than 200 ml / min for a period of time, this belongs to abnormal fluctuation, and the system will record this change situation. In terms of correlation analysis, the system will study the mutual relationship between different parameters. For example, when the venous pressure rises, observe whether the blood flow rate will decrease accordingly, or whether there is a certain correlation between the body temperature change and other parameters. If it is found that while the venous pressure rises, the blood flow rate continues to decrease, and the body temperature has an upward trend, this implies that there are some potential problems.

[0042] Based on the results of comprehensive dynamic analysis and correlation analysis, the hemodialysis monitoring parameter information of the target patient is generated. If Mr. Li's dialysis parameters fluctuate within the normal threshold range, and the correlation between each parameter also conforms to the normal law, then the hemodialysis monitoring parameter information may be displayed as "normal"; but if there are situations such as parameters exceeding the threshold range, abnormal fluctuations, or abnormal correlations between parameters, the hemodialysis monitoring parameter information will record these abnormal situations in detail, such as "the blood flow rate was lower than the normal threshold during [specific time period], and there was an abnormal negative correlation between the venous pressure and the blood flow rate", etc. These hemodialysis monitoring parameter information will be used to evaluate Mr. Li's dialysis condition and infection risk, etc. in the follow-up, helping doctors to detect potential problems in time and take corresponding measures.

[0043] S104, process the historical infection data of the hemodialysis target patient to generate the hemodialysis prediction monitoring feature vector.

[0044] In one implementation, physiological parameters of each dialysis and a target historical time period are obtained. Mr. Li regularly undergoes hemodialysis in the hospital, and the hospital's monitoring system automatically records the detailed physiological parameters of each dialysis. For example, during the dialysis on November 1, 2024, the blood flow rate at the start of dialysis was 250 ml / min, the dialysate flow rate was 500 ml / min, the venous pressure was 150 mmHg, and the body temperature was 36.5°C. As dialysis progresses, the system records a new set of parameter data every certain period (such as 1 minute). At the same time, to analyze the changing trend of Mr. Li's dialysis parameters, the system selects the dialysis data within the past 3 months of Mr. Li as the data for the target historical time period. Mr. Li had 12 hemodialysis sessions within these 3 months, and the physiological parameters and corresponding times of each dialysis are completely recorded in the system.

[0045] The physiological parameters of each dialysis and the target historical time period are processed to generate the deviation values of the parameters of each dialysis from the historical data. Taking the dialysis on November 1, 2024 as an example, the system compares the parameters during this dialysis with the parameters at the corresponding time points within the target historical time period. For example, at 15 minutes into dialysis, the blood flow rate during this dialysis was 240 ml / min, while the average blood flow rate at the same dialysis time period (around 15 minutes) within the past 3 months was 255 ml / min. Then the deviation value of the blood flow rate from the historical data is 240 - 255 = -15 ml / min. In the same way, the deviation values of other parameters such as the dialysate flow rate, venous pressure, and body temperature from the historical data at each time point are calculated. In this way, the changes of each parameter in this dialysis compared with the historical situation are comprehensively reflected.

[0046] Based on the deviation values of the parameters of each dialysis from the historical data, the fluctuation range and the degree of abnormality of the parameter deviation values are obtained. The deviation values of the parameters obtained from each dialysis are further analyzed. Taking the blood flow rate as an example, during the dialysis on November 1, 2024, from the start to the end, the deviation value of the blood flow rate fluctuated between -20 ml / min and 10 ml / min, and this range is the fluctuation range of the blood flow rate deviation value for this dialysis. To evaluate the degree of abnormality, the system sets a threshold for the normal fluctuation range based on the statistical analysis of historical data. Assuming that based on past experience, the normal fluctuation range of the blood flow rate deviation value is between -10 ml / min and 10 ml / min, then the deviation value of the blood flow rate in this dialysis exceeds the lower limit of the normal range, indicating that there is a certain degree of abnormality in the change of the blood flow rate. For other parameters such as the dialysate flow rate, venous pressure, and body temperature, the fluctuation range is calculated and the degree of abnormality is evaluated in the same way.

[0047] Based on correlation analysis and regression analysis, the fluctuation range and abnormal degree of parameter deviation values are processed to generate the correlation degree between each dialysis parameter and the prediction value range of each parameter. The methods of correlation analysis and regression analysis are used to process the fluctuation range and abnormal degree of parameter deviation values. Correlation analysis can discover the internal relationship between different parameters. For example, through analysis, it is found that when the venous pressure deviation value of Mr. Li shows an abnormal increase, the blood flow rate deviation value often shows an abnormal decrease at the same time, which indicates that there is a strong negative correlation between venous pressure and blood flow rate. Regression analysis is used to predict the future change trend of parameters. Based on a large amount of historical data and the current deviation value situation, the system can predict that during the next dialysis process, if other conditions remain unchanged, the blood flow rate of Mr. Li may fluctuate within a certain range. Suppose the predicted value range of the blood flow rate in the next 10 minutes is 230 - 250 ml / min. Similarly, similar analyses are carried out on other parameters such as dialysis fluid flow rate and body temperature to obtain their correlation degrees and respective prediction value ranges.

[0048] Process the correlation degree between each dialysis parameter and the prediction value range of each parameter to generate a hemodialysis prediction and monitoring feature vector. The hemodialysis prediction and monitoring feature vector is a multi-dimensional data structure that integrates the dynamic change information of each parameter during Mr. Li's dialysis process and their mutual relationship. For example, the hemodialysis prediction and monitoring feature vector may be expressed as [(correlation degree between blood flow rate and venous pressure: -0.8), (prediction value range of blood flow rate: 230 - 250 ml / min), (correlation degree between dialysis fluid flow rate and body temperature: 0.3), (prediction value range of dialysis fluid flow rate: 480 - 520 ml / min)……]. This feature vector can comprehensively reflect Mr. Li's current dialysis state and future possible change trends, providing an important basis for evaluating the infection risk based on the target hemodialysis event warning model. Medical staff can discover potential problems in advance based on this feature vector and adjust the treatment plan in time to reduce the risk of adverse events such as infection for Mr. Li.

[0049] S105, based on the target hemodialysis event warning model, process the hemodialysis event impact factors, the hemodialysis monitoring parameter information of the target patient, the hemodialysis prediction and monitoring feature vector, and the target patient's infection examination result information to generate hemodialysis infection event warning information.

[0050] In one implementation, based on the target hemodialysis event warning model, the impact factors of hemodialysis events, the hemodialysis monitoring parameter information of the target patient, the hemodialysis prediction monitoring feature vector, and the infection test result information of the target patient are processed to generate the infection risk score of the target patient. The monitoring system of the hospital has collected the impact factors of hemodialysis events, the hemodialysis monitoring parameter information, the hemodialysis prediction monitoring feature vector, and the infection test result information of Mr. Li. Suppose the impact factor of Mr. Li's hemodialysis event is 1.1 (this factor comprehensively considers factors such as catheter type change, catheter assessment, and vascular access location), the hemodialysis monitoring parameter information shows that the blood flow rate during his recent dialysis is occasionally lower than the normal threshold, and the venous pressure shows an abnormal negative correlation with the blood flow rate; the hemodialysis prediction monitoring feature vector indicates that the correlation degree between the blood flow rate and the venous pressure is -0.8, and the predicted future blood flow rate fluctuation range is 230 - 250 ml / min; the infection test result shows that all the results of Mr. Li's last preoperative eight - item test are negative.

[0051] These information are input into the target hemodialysis event warning model. The model assigns different weights according to the correlation degree between each piece of information and the infection risk. Suppose the weight of the impact factor of hemodialysis events is 0.4, the weight of the hemodialysis monitoring parameter information is 0.3, the weight of the hemodialysis prediction monitoring feature vector is 0.2, and the weight of the infection test result information is 0.1. After calculation, the infection risk score of Mr. Li is obtained as 0.6 (the specific calculation method is

[0052] S = F×v 1 +P 1 ×v 2 +P 2 ×v 3 +P 3 ×v 4 . Among them, S is the infection risk score, F is the impact factor of hemodialysis events, v 1 is the weight of the impact factor of hemodialysis events, P 1 is the score of blood flow rate abnormality and correlation factors, v 2 is the weight of the hemodialysis monitoring parameter information, P 2 is the score of the prediction feature vector, v 3 is the weight of the hemodialysis prediction monitoring feature vector, P 3 is the score of the infection detection result, v 4 is the weight of the infection test result information).

[0053] Process the infection risk score of the target patient to generate the current infection risk level of the target patient. The infection risk score is divided into different intervals corresponding to different infection risk levels. It is set that the infection risk score of 0 - 0.4 is a low risk level, 0.4 - 0.7 is a medium risk level, and 0.7 - 1 is a high risk level. Mr. Li's infection risk score is 0.6, which is in the interval of 0.4 - 0.7. Therefore, Mr. Li's current infection risk level is determined to be medium risk. This means that Mr. Li has a certain possibility of infection and needs to be closely monitored by medical staff.

[0054] Based on a preset warning threshold, process the current infection risk level of the target patient to generate a hemodialysis infection event warning message. The hospital has preset a warning threshold. If the infection risk level reaches or exceeds a certain threshold, the system will trigger a warning. Suppose the preset warning threshold is the medium risk level (i.e., the infection risk score reaches 0.4). Since Mr. Li's infection risk level is medium risk and has reached the warning threshold, the system generates a hemodialysis infection event warning message. This warning message will be displayed on the monitoring system interface of the hospital, showing that Mr. Li may have an infection risk, and at the same time, displaying relevant risk factors, such as a relatively high hemodialysis event impact factor (indicating that factors such as changes in catheter types may increase the infection risk), abnormal blood flow volume and abnormal associations between parameters in hemodialysis monitoring parameters, and potential risks reflected by the hemodialysis prediction monitoring feature vector. After seeing the warning message, medical staff will further combine Mr. Li's specific situation, such as checking his recent dialysis records, physical symptoms, etc., to determine whether corresponding measures need to be taken, such as increasing the monitoring frequency during dialysis, further examining Mr. Li, or adjusting the treatment plan to reduce the infection risk.

[0055] In addition, in another aspect of the present application, based on the target hemodialysis event warning model, process the hemodialysis event impact factor, the hemodialysis monitoring parameter information of the target patient, the hemodialysis prediction monitoring feature vector, and the target patient's infection examination result information to generate a hemodialysis infection event warning message. After that, it further includes:

[0056] Process the hemodialysis infection event warning message to generate information on the source and transmission route of the infectious pathogen;

[0057] Based on the information on the source and transmission route of the infectious pathogen and the target patient's infection examination result information, process to generate target triage information and response factor priority information;

[0058] Process the target triage information and response factor priority information to generate hemodialysis infection warning measures.

[0059] In one implementation, assuming that the early warning information of Mr. Li's hemodialysis infection event indicates a relatively high infection risk, the system first analyzes the possible sources and transmission routes of the infectious pathogen from various types of data. From Mr. Li's dialysis history records, it is found that he recently changed his temporary catheter (ECC), and the catheterization operation may increase the infection risk. Combining with the catheter assessment results, if the skin around the puncture site has shown redness, and although the pathogen has not been identified in the blood culture during this period, the inflammatory indicators have increased, it is speculated that the infectious pathogen may originate from contact infection during the catheterization operation, and the bacteria invade from the puncture site. At the same time, reviewing the hospital environmental monitoring data, if it is found that there are abnormalities in the cleaning and disinfection records of the dialysis equipment, and similar infection early warnings also occur in other patients during the same period, the possibility of pathogen transmission caused by incomplete disinfection of the dialysis equipment cannot be excluded. Combining these pieces of information, it is preliminarily judged that the infectious pathogen may be Staphylococcus, the source may be contamination during the catheterization operation or incomplete disinfection of the dialysis equipment, and the transmission route is contact transmission.

[0060] Based on the above information about the source and transmission route of the infectious pathogen, as well as Mr. Li's infection examination results (such as inflammatory indicators, bloodborne pathogen screening results, etc.), target triage information and response cause priority information are generated. Since Mr. Li has a relatively high infection risk and may have a blood infection risk, he is first considered to be triaged to the infection isolation area for further examination and treatment to avoid cross-infection. In terms of the response cause priority, the catheter-related infection risk is ranked first because the catheterization operation is closely related to the current infection symptoms, and if the catheter infection is not treated in a timely manner, it may lead to serious complications. The second is the problem of dialysis equipment disinfection, which involves the infection prevention and control safety of the entire dialysis center and needs to be investigated and rectified in a timely manner. Therefore, the target triage information is to transfer Mr. Li to the infection isolation area, and the response cause priority information is: first, deal with the catheter-related infection risk, and second, solve the problem of dialysis equipment disinfection.

[0061] Regarding the catheter-related infection risk, immediately arrange medical staff to re-evaluate Mr. Li's catheter, including replacing the catheter or strengthening catheter care. Collect catheter tip samples for bacterial culture and drug sensitivity testing to more accurately identify the pathogen and select sensitive antibacterial drugs for treatment. At the same time, closely monitor Mr. Li's vital signs and infection indicators, such as body temperature, white blood cell count, etc. For the problem of dialysis equipment disinfection, notify the logistics department to conduct a comprehensive and in-depth disinfection of the dialysis equipment and related accessories used by Mr. Li, strengthen the supervision and inspection of the daily disinfection management process of the dialysis equipment to ensure that the disinfection operation complies with the specifications. Conduct an infection risk investigation on other patients who used this batch of dialysis equipment during the same period and monitor their health conditions. In addition, strengthen the infection prevention and control training for medical staff, emphasize the standard procedures for catheterization operations and equipment disinfection, and prevent similar infection events from occurring again.

[0062] Obtain various data of the target patient from the server, such as dialysis physiological parameters, vascular access information, etc. Generate hemodialysis event impact factors by processing vascular access and outpatient hemodialysis catheterization records; process dialysis physiological parameters to obtain hemodialysis monitoring parameter information; analyze historical infection data to generate hemodialysis prediction monitoring feature vectors. These data processing steps provide a multi-dimensional basis for subsequent infection risk assessment. Obtain a training sample set and a preset model, train the model through operations such as statistics, sampling, and data group division, and screen out an effective target hemodialysis event warning model. Use this model to generate an infection risk score by integrating various types of data, further determine the infection risk level, and issue a warning message for hemodialysis infection events based on a preset threshold.

[0063] Deeply analyze the warning information to determine the source and transmission route of the infectious pathogen, such as judging whether the infection is caused by catheterization operations, dialysis equipment, etc. Generate target triage information and response factor priority information based on this information to provide guidance for subsequent targeted measures. Finally, formulate hemodialysis infection warning measures based on the above information, such as adjusting the treatment plan, strengthening equipment disinfection, etc., to reduce the infection risk.

[0064] Through comprehensive data processing and multi-step analysis and evaluation, the effective monitoring and warning of the infection risk of outpatient hemodialysis patients are realized, which helps to timely detect potential infection risks, provides strong support for medical staff to take corresponding measures, and is of great significance for ensuring the safety of patient dialysis and reducing the infection incidence.

[0065] In one implementation, as Figure 2 shown, the present application also provides a monitoring device for outpatient hemodialysis infection events, including:

[0066] An acquisition module 201, configured to acquire the dialysis physiological parameter information of the target patient undergoing maintenance hemodialysis within a preset time, the vascular access information of the target patient, the outpatient hemodialysis catheterization record of the target patient, the infection examination result information of the target patient, and the historical infection data of the hemodialysis target patient;

[0067] A processing module 202, configured to process the vascular access information of the target patient and the outpatient hemodialysis catheterization record of the target patient to generate a hemodialysis event impact factor; process the dialysis physiological parameter information of the target patient within a preset time to generate the hemodialysis monitoring parameter information of the target patient; process the historical infection data of the hemodialysis target patient to generate a hemodialysis prediction monitoring feature vector; process the hemodialysis event impact factor, the hemodialysis monitoring parameter information of the target patient, the hemodialysis prediction monitoring feature vector, and the infection examination result information of the target patient based on the target hemodialysis event warning model to generate a hemodialysis infection event warning message.

[0068] Each embodiment in this application is described in a related manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the monitoring method, electronic device, electronic equipment, and readable storage medium for evaluating outpatient hemodialysis infection events, since they are basically similar to the embodiments of the monitoring method for outpatient hemodialysis infection events described above, the description is relatively simple, and reference can be made to the relevant parts of the embodiments of the monitoring method for outpatient hemodialysis infection events described above.

Claims

1. A method for monitoring outpatient hemodialysis infection events, characterized in that: include: Obtaining the target patient's dialysis physiological parameter information within a preset time for maintenance hemodialysis, the target patient's vascular access information, the target patient's outpatient hemodialysis cannulation record, the target patient's infection test result information, and the target hemodialysis patient's historical infection data; The vascular access information of the target patient and the outpatient hemodialysis cannulation record of the target patient are processed to generate the hemodialysis event influencing factors; Processing the target patient's dialysis physiological parameter information within a preset time to generate the target patient's hemodialysis monitoring parameter information; Process the historical infection data of hemodialysis target patients to generate hemodialysis prediction monitoring feature vectors; Based on the target hemodialysis event warning model, the hemodialysis event influencing factors, the hemodialysis monitoring parameter information of the target patient, the hemodialysis prediction monitoring feature vector and the target patient infection examination result information are processed to generate hemodialysis infection event warning information.

2. The method according to claim 1, characterized in that Obtain the target hemodialysis event warning model, including: Obtaining a training sample set and a preset hemodialysis event warning model, wherein the training sample set includes dialysis physiological parameter information, vascular access information, outpatient hemodialysis cannulation records, infection examination result information, and historical infection data of other hemodialysis patients within a preset time period of other patients undergoing maintenance hemodialysis; Count the number of each data feature in the training sample set and generate a sampling ratio based on these numbers; Sampling the training sample set based on the sampling ratio to generate a preset number of sampling features; Based on any data feature and each sampling feature, the data is divided into a response group and a poor response group, wherein each group contains a preset number of data samples and at least one data sample carries identification information; Processing the preset hemodialysis event warning model based on the response group and the poor response group to generate a trained hemodialysis event warning model and training results; If the data sample containing identification information in the training result is a factor characterizing the risk of hemodialysis infection, the trained hemodialysis event warning model is used as the target hemodialysis event warning model.

3. The method according to claim 1, characterized in that The vascular access information of the target patient and the outpatient hemodialysis cannulation record of the target patient are processed to generate the influencing factors of hemodialysis events, including: Process the outpatient hemodialysis catheterization records of target patients to obtain information on changes in catheter type and catheter evaluation results; Process the catheter type change information to generate catheter types in different time periods; Processing the catheter assessment results to generate hematoma information and bleeding information; Process the catheterization type, hematoma information and bleeding information in different time periods to generate impact degree information, where the image degree information is used to characterize the impact weights corresponding to the changes in different catheterization types and catheter evaluation results; The vascular access information and imaging degree information of the target patient are processed to generate the influencing factors of hemodialysis events.

4. The method according to claim 1, characterized in that The target patient's hemodialysis physiological parameter information within a preset time is processed to generate the target patient's hemodialysis monitoring parameter information, including: Process the target patient's dialysis physiological parameter information within a preset time to generate each dialysis data and corresponding timestamp; Perform noise filtering and normalization on each dialysis data to generate dialysis parameter sequence information of the target patient; Based on the preset threshold range of each parameter and the monitoring purpose, the dialysis parameter sequence information of the target patient is dynamically analyzed and correlated to generate the hemodialysis monitoring parameter information of the target patient.

5. The method according to claim 1, characterized in that The historical infection data of hemodialysis target patients are processed to generate hemodialysis prediction monitoring feature vectors, including: Obtain physiological parameters and target historical time periods for each dialysis session; Processing the physiological parameters of each dialysis session and the target historical time period to generate deviation values ​​between each dialysis parameter and historical data; Obtaining the fluctuation range and abnormality of the parameter deviation value based on the deviation value of each dialysis parameter and the historical data; Based on correlation analysis and regression analysis, the fluctuation range and abnormality of parameter deviation values ​​are processed to generate the correlation degree between various dialysis parameters and the predicted value range of each parameter; The correlation degree between each dialysis parameter and the predicted value range of each parameter are processed to generate a hemodialysis prediction monitoring feature vector.

6. The method according to claim 5, characterized in that Based on the target hemodialysis event early warning model, the hemodialysis event influencing factors, the hemodialysis monitoring parameter information of the target patient, the hemodialysis prediction monitoring feature vector and the target patient infection examination result information are processed to generate the hemodialysis infection event early warning information, including: Based on the target hemodialysis event early warning model, the hemodialysis event influencing factors, the hemodialysis monitoring parameter information of the target patient, the hemodialysis prediction monitoring feature vector and the target patient infection examination result information are processed to generate the infection risk score of the target patient; Processing the infection risk score of the target patient to generate the current infection risk level of the target patient; The target patient's current infection risk level is processed based on the preset warning threshold to generate hemodialysis infection event warning information.

7. The method according to claim 1, characterized in that Based on the target hemodialysis event early warning model, the hemodialysis event influencing factors, the hemodialysis monitoring parameter information of the target patient, the hemodialysis prediction monitoring feature vector and the target patient infection examination result information are processed to generate the hemodialysis infection event early warning information, and then, it also includes: Process the early warning information of hemodialysis infection events to generate information on the source and transmission pathway of the infectious pathogen; Based on the source information of the infectious pathogen, the transmission route information and the infection test result information of the target patient, target triage information and response priority information are generated; The target triage information and response priority information are processed to generate early warning measures for hemodialysis infection.

8. A monitoring device for outpatient hemodialysis infection events, characterized in that: The device comprises: An acquisition module is used to obtain the dialysis physiological parameter information of the target patient undergoing maintenance hemodialysis within a preset time, the vascular access information of the target patient, the outpatient hemodialysis cannulation record of the target patient, the infection examination result information of the target patient, and the historical infection data of the hemodialysis target patient; The processing module is used to process the vascular access information of the target patient and the outpatient hemodialysis catheterization record of the target patient to generate the hemodialysis event influencing factor; process the dialysis physiological parameter information of the target patient within a preset time to generate the hemodialysis monitoring parameter information of the target patient; process the historical infection data of the hemodialysis target patient to generate the hemodialysis prediction monitoring feature vector; based on the target hemodialysis event early warning model, process the hemodialysis event influencing factor, the hemodialysis monitoring parameter information of the target patient, the hemodialysis prediction monitoring feature vector and the target patient infection examination result information to generate the hemodialysis infection event early warning information.

9. An electronic device, characterized in that: include: a first processor; and a memory for storing executable instructions of the first processor; Wherein, the first processor is configured to execute the method for monitoring outpatient hemodialysis infection events as described in any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the second processor, the method for monitoring outpatient hemodialysis infection events according to any one of claims 1 to 7 is implemented.

Images