A method and system for processing vital sign monitoring data after urology surgery

Abstract

The present invention discloses a method and system for processing post-urological vital sign monitoring data, which relates to the field of medical monitoring technology. The method constructs a preliminary dehydration risk algorithm model in a cloud data processing platform to conduct a comprehensive analysis of the post-operative vital sign data of each patient and generate a preliminary dehydration risk index DS. The calculation of this indicator is based on multiple key vital sign data. Through precise modeling and analysis of these data, the dehydration risk of each patient can be quantified, and preliminary screening can be carried out based on the value of the dehydration risk index DS. In the preliminary evaluation stage, if the patient's preliminary dehydration risk index DS value is greater than or equal to 0.05, it indicates that the patient is at risk of dehydration, and a deep dehydration and edema analysis is performed on the patient. This data-based precise evaluation method can detect patients at risk of dehydration in the early postoperative period, provide an important basis for subsequent intervention and treatment, and reduce potential health risks.

Description

Technical Field

[0001] The present invention relates to the technical field of medical monitoring, and in particular to a method and system for processing post-urology vital sign monitoring data. Background Art

[0002] Urological postoperative care is an important branch of modern medicine, focusing on the recovery and health management of patients after surgery. Especially after urological surgery, the patient's water and electrolyte balance, body fluid management, and renal function monitoring are particularly critical. With the advancement of medical technology and the diversification of surgical methods, the postoperative recovery management of patients after urological surgery is becoming increasingly complex. In this process, postoperative vital sign monitoring has become an important part of medical care, including real-time monitoring of physiological parameters such as urine output, heart rate, and total body water content. Traditional manual monitoring methods, due to their reliance on the experience of medical staff, often fail to detect problems such as postoperative edema or dehydration in a timely and accurate manner.

[0003] At present, the monitoring of vital signs of patients after urological surgery mainly relies on traditional manual inspections or intermittent monitoring, which lacks continuity and real-time performance. For example, changes in body fluid status such as dehydration or edema are often discovered only when the patient's symptoms are obvious, resulting in untimely clinical intervention and the possibility of postoperative complications. Although some traditional equipment such as scales and urine analyzers can monitor the patient's urine output and urine osmotic pressure, they cannot comprehensively and comprehensively evaluate the dynamic changes in the patient's body fluids. In addition, existing monitoring equipment usually lacks integration, resulting in fragmented data, making it difficult to achieve effective real-time monitoring and intelligent analysis, increasing the workload of medical staff, and posing the risk of data analysis lags and errors. Summary of the Invention

[0004] In view of the deficiencies in the prior art, the present invention provides a method and system for processing post-urology vital sign monitoring data, which solves the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: comprising the following steps:

[0006] S1. Equip all patients after urological surgery with a sensor set to collect postoperative vital sign data of all patients in real time, build a cloud data processing platform, and transmit the collected postoperative vital sign data to the cloud data processing platform via the Internet of Things;

[0007] S2. Preprocessing the postoperative vital sign data in a cloud data processing platform to obtain standard vital sign data for each patient, labeling and numbering the standard vital sign data for each patient, and setting up a cloud database to store the standard vital sign data in the cloud database and sorting them in order of numbering;

[0008] S3. Constructing a preliminary dehydration risk algorithm model on the cloud data processing platform, extracting standard vital sign data for each patient and inputting them into the preliminary dehydration risk algorithm model, calculating and outputting a preliminary dehydration risk index DS for each patient, and performing preliminary comparative evaluation based on the output of the preliminary dehydration risk index DS to screen patients at risk of dehydration;

[0009] S4. For patients identified as at risk of dehydration through preliminary assessment, perform a deep dehydration and edema analysis. The deep dehydration and edema analysis extracts standard physical sign data and calculates and outputs a deep dehydration risk index DA and an edema risk index EA. The deep dehydration risk index DA and the edema risk index EA are then combined to output a comprehensive risk index R.

[0010] S5. Perform a secondary comparative evaluation based on the output results of the comprehensive risk index R, analyze the current patient's dehydration and edema risks, generate warning information, and send it to the client to push warning notifications.

[0011] Preferably, said S1 includes S11 and S12;

[0012] S11, equipping all patients after urological surgery with a sensor group and setting the sensor group's acquisition frame rate to once per minute, thereby collecting postoperative vital sign data of all patients after urological surgery in real time;

[0013] The sensor group includes a urine analyzer, a smart weight scale, a blood oxygen saturation detector, an electrocardiogram device, a limb dimension measuring instrument and a bioelectrical impedance analyzer;

[0014] The postoperative physical sign data include urination rate Pdi, urine osmotic pressure UOsm, heart rate variability index HRV, heart rate response coefficient RHR, total body water content TBW and limb swelling EL;

[0015] S12. Through the communication module in the sensor group, use the MQTT protocol of the Internet of Things to encapsulate the postoperative vital sign data, obtain the vital sign data packet, and generate a unique identifier for each vital sign data packet. Then, transmit the vital sign data packet to the cloud data processing platform through the wireless communication network.

[0016] Preferably, said S2 includes S21 and S22;

[0017] S21. Receive vital sign data packets in real time on the cloud data processing platform, unpack the data packets, extract postoperative vital sign data, and set up an API to integrate the cloud data processing platform with the medical record system. Match the unique identifier with the patient medical record information in the medical record database to extract the patient's initials and the last four digits of their ID card.

[0018] After matching the patient case information, preprocess the postoperative vital sign data of all patients, including abnormal data removal and data standardization, obtain standard vital sign data, and mark the standard vital sign data of each patient with a number;

[0019] The number is composed in the following format: initials of name / last four digits of ID card / year, month, day / last two digits of unique identifier;

[0020] The abnormal data elimination is carried out by using the data anomaly detection algorithm z-score on the postoperative vital sign data to eliminate sensor failure and data deviation;

[0021] The data standardization is performed by denoising, filling missing values ​​and normalizing the postoperative vital sign data;

[0022] S22. At the same time, a cloud database is set up, and an API application program interface is set up to integrate the cloud data processing platform with the cloud database, store the standard vital signs data in the cloud database, and sort them in order of number.

[0023] Preferably, said S3 includes S31 and S32;

[0024] S31. Based on the machine learning algorithm, a preliminary dehydration risk algorithm model is constructed in the cloud data processing platform. The standard vital sign data of each patient in the cloud database is extracted through the API application program interface, and the data is input into the preliminary dehydration risk algorithm model to calculate and output the preliminary dehydration risk index DS for each patient, thereby comprehensively quantifying the dehydration index of each patient.

[0025] The preliminary dehydration risk indicator DS is calculated and output by the following preliminary dehydration risk algorithm model;

[0026]

[0027] Where, DS i represents the initial dehydration risk index of the i-th patient, ln represents the natural logarithm, UOsm i represents the urine osmotic pressure of the i-th patient, Pdi i represents the urination rate of the i-th patient, TBW i represents the total body water content of the i-th patient, HRV i Represents the heart rate variability index of the i-th patient, RHR i represents the heart rate response coefficient of the i-th patient, EL i represents the limb swelling of the i-th patient.

[0028] Preferably, S32, calculating a preliminary dehydration risk index DS for each patient and performing a preliminary assessment based on an output result of the preliminary dehydration risk index DS to screen patients at risk of dehydration. The specific assessment content is as follows;

[0029] When the initial dehydration risk indicator DS of the i-th patient i When the value is ≥0.05, it indicates that the patient is at risk of dehydration, and deep dehydration and edema analysis is performed at this time;

[0030] When the initial dehydration risk indicator DS of the i-th patient i When the value is <0.05, it indicates that the patient is normal and needs to be monitored continuously.

[0031] Preferably, said S4 includes S41, S42 and S43;

[0032] S41. After preliminary screening of patients at risk of dehydration, further performing a deep dehydration and edema analysis, the deep dehydration and edema analysis including a deep dehydration analysis and a deep edema analysis;

[0033] The deep dehydration analysis is performed by combining urine osmotic pressure UOsm, total body water content TBW, urination rate Pdi, heart rate variability index HRV and limb swelling degree EL through nonlinear power function and exponential function to calculate and output the deep dehydration risk index DA for each screened patient;

[0034] The deep dehydration risk index DA is calculated and output by the following algorithm formula:

[0035]

[0036] In the formula, DA i represents the deep dehydration risk index of the i-th patient, exp represents the exponential function, and HRcrit represents the critical heart rate.

[0037] Preferably, S42, the depth edema analysis is performed by combining a nonlinear power relationship, an exponential function and standard physical sign data to calculate and output an edema risk index EA to analyze the edema risk;

[0038] The edema risk index EA is calculated and output by the following algorithm formula;

[0039]

[0040] Where Pfl represents fluid intake, EA i represents the edema risk index EA of the i-th patient, WCR represents the water clearance rate, and T represents the unit time window.

[0041] Preferably, S43, based on the acquired deep dehydration risk index DA and edema risk index EA, a comprehensive calculation is performed to obtain a comprehensive analysis index R, and the postoperative risk of the patient is analyzed;

[0042] The comprehensive analysis index R is calculated and output by the following algorithm formula:

[0043]

[0044] Where α and β represent the deep dehydration risk index DA of the i-th patient, respectively. i and the edema risk indicator EA for the i-th patient i The weight value is set by the user, and α+β=1.

[0045] Preferably, said S5 includes S51 and S52;

[0046] S51. Based on the output of the comprehensive analysis index R, conduct a secondary comparative evaluation to analyze the dehydration and edema status of the current postoperative urology patients, and generate intervention recommendations based on the secondary comparative evaluation results. The specific evaluation contents are as follows;

[0047] When the comprehensive analysis index R>1, it means that the current patient is at risk of dehydration, and the first intervention recommendation is generated;

[0048] When the comprehensive analysis index R=1, it means that the patient's current dehydration risk and edema risk are normal, and there is no need for intervention and continuous monitoring;

[0049] When the comprehensive analysis index R<1, it means that the current patient is at risk of edema, and the second intervention recommendation is generated;

[0050] S52: Based on the obtained intervention suggestions, generate warning information and push it to the client through the cloud data processing platform to prompt medical staff to intervene in the patient after urological surgery. The client includes a mobile terminal and a nursing terminal;

[0051] The specific warning information is as follows:

[0052] When the first intervention recommendation is generated, the first warning message is pushed to the medical staff, reminding them that the patient is at risk of dehydration. In this case, the patient should increase fluid intake by 30%, adjust the drug dosage, and switch to intravenous fluid replacement.

[0053] When the second intervention suggestion is generated, a second warning message is pushed to remind medical staff that the patient is at risk of edema. At this time, the medication use should be adjusted and the patient is advised to exercise.

[0054] A post-operative urology vital sign monitoring data processing system, comprising a post-operative vital sign collection module, a cloud processing module, a preliminary dehydration analysis module, a deep dehydration and edema analysis module, and a comprehensive evaluation and push module;

[0055] The postoperative vital signs collection module equips all patients after urological surgery with a sensor group to collect the postoperative vital signs data of all patients in real time, and builds a cloud data processing platform to transmit the collected postoperative vital signs data to the cloud data processing platform through the Internet of Things;

[0056] The cloud processing module pre-processes the postoperative vital sign data in a cloud data processing platform to obtain standard vital sign data of each patient, labels and numbers the standard vital sign data of each patient, and sets up a cloud database to store the standard vital sign data in the cloud database and sort them in order of numbers;

[0057] The preliminary dehydration analysis module constructs a preliminary dehydration risk algorithm model in the cloud data processing platform, extracts the standard physical sign data of each patient and inputs them into the preliminary dehydration risk algorithm model, calculates and outputs a preliminary dehydration risk index DS for each patient, and performs preliminary comparative evaluation based on the output results of the preliminary dehydration risk index DS to screen patients at risk of dehydration;

[0058] The deep dehydration and edema analysis module screens out patients at risk of dehydration through preliminary assessment and performs deep dehydration and edema analysis. The deep dehydration and edema analysis extracts standard physical sign data and calculates and outputs a deep dehydration risk index DA and an edema risk index EA. The deep dehydration risk index DA and the edema risk index EA are then comprehensively calculated to output a comprehensive risk index R.

[0059] The comprehensive assessment push module performs a secondary comparative assessment based on the output results of the comprehensive risk index R, analyzes the current patient's dehydration and edema risks, generates warning information, and sends it to the client to push warning notifications.

[0060] The present invention provides a method and system for processing post-urology vital sign monitoring data. It has the following beneficial effects:

[0061] (1) This method assembles a sensor group and uses Internet of Things technology to collect the vital sign data of all patients after urological surgery in real time, and transmits it to the cloud data processing platform through the MQTT protocol, thereby realizing real-time monitoring of postoperative vital signs. The vital sign data of each patient is automatically collected through multiple dedicated sensors to ensure the accuracy and timeliness of the data. In addition, the sensor group has its own communication module, which can encapsulate the vital sign data into a vital sign data packet and transmit it to the cloud data processing platform through a wireless network to ensure timely transmission and storage of the data. This real-time collection and processing mechanism greatly improves the accuracy of postoperative vital sign data, reduces the error of manual monitoring, helps to detect potential risk factors such as dehydration or edema as early as possible, and ensures that patients can receive more accurate and effective care after surgery.

[0062] (2) This method constructs a preliminary dehydration risk algorithm model in a cloud data processing platform, conducts a comprehensive analysis of each patient's postoperative vital signs data, and generates a preliminary dehydration risk index DS. The calculation of this index is based on multiple key vital signs data. Through precise modeling and analysis of these data, the dehydration risk of each patient can be quantified, and preliminary screening can be carried out based on the value of the dehydration risk index DS. In the preliminary assessment stage, if the patient's DS value is greater than or equal to 0.05, it indicates that the patient is at risk of dehydration, and a deep dehydration and edema analysis is performed on the patient. This data-based precise assessment method can detect patients at risk of dehydration in the early postoperative period, provide an important basis for subsequent intervention and treatment, and reduce potential health risks.

[0063] (3) After initially screening out patients at risk of dehydration, this method further performs deep dehydration and edema analysis to conduct a more refined risk assessment of the patients. Deep dehydration analysis calculates the deep dehydration risk index DA by using nonlinear power functions and exponential functions. Edema risk analysis calculates the edema risk index EA by integrating nonlinear power relationships, exponential functions and other algorithms. On this basis, the deep dehydration risk index DA and the edema risk index EA are comprehensively calculated to obtain the comprehensive risk index R. According to the different values ​​of the comprehensive risk index R, the system automatically generates intervention recommendations. If the comprehensive risk index R value is greater than 1, it indicates a high risk of dehydration. The system will recommend increasing fluid supplementation and adjusting drug treatment; if the comprehensive risk index R value is less than 1, it indicates a high risk of edema. It is recommended to adjust the drug or increase the amount of exercise for intervention. Finally, the system will push the intervention recommendations to the client of medical staff through early warning information to ensure timely intervention. This risk assessment and intervention decision-making mechanism based on comprehensive analysis has greatly improved the efficiency of patient postoperative risk management. It can quickly take effective measures when patients have problems and avoid further deterioration of potential health risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 This is a schematic diagram of the steps of a method for processing vital sign monitoring data after urology surgery according to the present invention;

[0065] Figure 2 The figure is a flow chart of a data processing system for monitoring vital signs after urological surgery according to the present invention. DETAILED DESCRIPTION

[0066] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0067] Example 1

[0068] See also Figure 1 The present invention provides a method for processing post-urology vital sign monitoring data. To achieve the above objectives, the present invention is implemented through the following technical solutions: comprising the following steps:

[0069] S1. Equip all patients after urological surgery with a sensor set to collect their postoperative vital signs data in real time. Build a cloud-based data processing platform and transmit the collected postoperative vital signs data to the cloud-based data processing platform via the Internet of Things.

[0070] S2. Preprocess the postoperative vital sign data in the cloud data processing platform to obtain the standard vital sign data of each patient, label and number the standard vital sign data of each patient, and set up a cloud database to store the standard vital sign data in the cloud database and sort them in the order of the numbers;

[0071] S3. Construct a preliminary dehydration risk algorithm model on the cloud data processing platform, extract the standard vital signs data of each patient and input them into the preliminary dehydration risk algorithm model, calculate and output a preliminary dehydration risk index DS for each patient, conduct a preliminary comparative evaluation based on the output results of the preliminary dehydration risk index DS, and screen patients at risk of dehydration;

[0072] S4. For patients identified as at risk of dehydration through preliminary assessment, perform a deep dehydration and edema analysis. The deep dehydration and edema analysis extracts standard physical sign data and calculates and outputs a deep dehydration risk index DA and an edema risk index EA. The deep dehydration risk index DA and the edema risk index EA are then combined to output a comprehensive risk index R.

[0073] S5. Perform a secondary comparative evaluation based on the output results of the comprehensive risk index R, analyze the current patient's dehydration and edema risks, generate warning information, and send it to the client to push warning notifications.

[0074] In this embodiment, the system achieves full-time real-time monitoring and risk assessment of postoperative patients through a series of precise steps, combined with Internet of Things technology, cloud data processing, and algorithm analysis. The specific implementation method includes: first, assembling a sensor group on all patients after urological surgery, collecting postoperative vital sign data in real time, and transmitting the data to the cloud platform through the Internet of Things; then, pre-processing the data on the cloud platform to obtain standard vital sign data and numbering, sorting, and storing them; then, based on the standard vital sign data of each patient, constructing a preliminary dehydration risk algorithm model, calculating and outputting a preliminary dehydration risk index DS, and screening out dehydration risk patients through preliminary comparison; next, performing deep dehydration and edema analysis on the screened high-risk patients, calculating the deep dehydration risk index DA and the edema risk index EA, and comprehensively calculating the comprehensive risk index R; finally, performing a secondary assessment based on the output of the comprehensive risk index R, generating an early warning message and pushing it to the client, and promptly notifying medical staff to take intervention measures. Through the above steps, the present invention effectively improves the efficiency of collecting, storing, and processing postoperative vital sign data, ensuring the real-time and accuracy of the data. Furthermore, through preliminary dehydration risk assessment and analysis of deep dehydration and edema, patients at risk can be accurately screened and risk assessment reports and intervention recommendations generated in real time. This approach significantly improves the accuracy and real-time responsiveness of postoperative care, enabling medical staff to promptly adjust treatment plans based on comprehensive analysis results, optimize the patient care process, reduce the incidence of postoperative complications, and improve the quality of postoperative recovery. The implementation of this system not only enhances the decision-making support capabilities of medical staff but also improves patient safety and satisfaction, thereby providing effective technical support for the health management of patients after urological surgery.

[0075] Example 2

[0076] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: S1 includes S11 and S12;

[0077] S11, equipping all patients after urological surgery with a sensor group, and setting the sensor group's acquisition frame rate to once per minute, to collect postoperative vital sign data of all patients after urological surgery in real time;

[0078] The sensor set includes a urine analyzer, a smart weight scale, a blood oxygen saturation monitor, an electrocardiogram device, a limb dimension measuring instrument, and a bioelectrical impedance analyzer;

[0079] Postoperative physical sign data included urine voiding rate Pdi, urine osmotic pressure UOsm, heart rate variability index HRV, heart rate response coefficient RHR, total body water content TBW and limb swelling EL;

[0080] The urine voiding rate Pdi and urine osmotic pressure UOsm were collected and obtained by urine analyzer;

[0081] Heart rate variability index HRV and heart rate response coefficient RHR are acquired through electrocardiogram equipment;

[0082] The limb swelling degree EL is obtained by measuring the limb dimension;

[0083] Total body water content TBW was obtained by bioelectrical impedance analyzer;

[0084] S12. Through the communication module in the sensor group, use the MQTT protocol of the Internet of Things to encapsulate the postoperative vital sign data, obtain the vital sign data packet, and generate a unique identifier for each vital sign data packet. Then, transmit the vital sign data packet to the cloud data processing platform through the wireless communication network.

[0085] In this embodiment, the method constructs an efficient and accurate system for monitoring the vital signs of patients after urological surgery. The specific implementation method includes: first, each patient after urological surgery is equipped with a complete set of sensor groups, and the acquisition frame rate is set to once per minute to collect the patient's postoperative vital sign data in real time. These sensor groups include a urine analyzer, an intelligent weight scale, a blood oxygen saturation detector, an electrocardiogram device, a limb dimension measuring instrument, and a bioelectrical impedance analyzer, each responsible for collecting postoperative vital sign data. The collection of each data provides a comprehensive and highly accurate foundation for subsequent risk assessment and patient health monitoring. Next, through the communication module built into the sensor group, the MQTT protocol of the Internet of Things is used to encapsulate the collected vital sign data, generate a vital sign data packet, and transmit it to the cloud data processing platform via a wireless communication network. This process ensures the real-time and integrity of the data, and marks each data packet by generating a unique identifier, providing an efficient management method for subsequent data storage, processing, and tracing. Through this embodiment, the present invention achieves efficient collection, real-time transmission, and precise management of postoperative vital sign data. Its beneficial effects are mainly reflected in the following aspects: on the one hand, the use of advanced sensor technology and real-time data collection methods ensures the comprehensiveness and real-time nature of postoperative patient vital sign data, providing solid data support for subsequent health assessments; on the other hand, the application of Internet of Things technology makes data transmission more efficient, avoids delays caused by human intervention, and ensures the fast and accurate transmission of data.

[0086] Example 3

[0087] This embodiment is explained in Example 2, please refer to Figure 1 , specifically: S2 includes S21 and S22;

[0088] S21. Receive vital sign data packets in real time on the cloud data processing platform, unpack the data packets, extract postoperative vital sign data, and set up an API to integrate the cloud data processing platform with the medical record system. Match the unique identifier with the patient medical record information in the medical record database to extract the patient's initials and the last four digits of their ID card.

[0089] After matching the patient medical records, all postoperative vital signs data of all patients were preprocessed. The preprocessing included removing abnormal data and standardizing the data to obtain standard vital signs data, and marking the standard vital signs data of each patient with a number.

[0090] The format of the number is: initials of name / last four digits of ID card / year, month, day / last two digits of unique identifier;

[0091] Abnormal data elimination: sensor failure and data deviation are eliminated by using the data anomaly detection algorithm z-score on the postoperative vital sign data;

[0092] Data standardization was performed by denoising, filling missing values ​​and normalizing the postoperative vital sign data;

[0093] S22. At the same time, a cloud database is set up, and an API application program interface is set up to integrate the cloud data processing platform with the cloud database, store the standard vital signs data in the cloud database, and sort them in order of number.

[0094] In this embodiment, the method is closely integrated with the cloud data processing platform and the case system, and receives and unseals the vital sign data packet of each patient in real time through the API interface to extract the postoperative vital sign data. At the same time, the patient information in the case library is matched with the unique identifier, the patient's initials and the last four digits of the ID card are extracted, and a unique identity is given to each patient's vital sign data. In terms of data preprocessing, an abnormal data elimination method is adopted, and sensor failures and data deviations are eliminated through data anomaly detection algorithms such as z-score to ensure the validity and accuracy of the data. In addition, the data is standardized, including denoising, filling missing values ​​and normalization, to further improve the consistency and comparability of the data. The cloud platform and the cloud database are integrated and connected, and the postoperative vital sign data after preprocessing and standardization are stored in the cloud database and sorted according to a preset numbering format. The vital sign data of each patient are marked with a precise numbering system, which makes the data management more standardized and facilitates subsequent query and analysis. Through this embodiment, the present invention realizes the accurate storage and standardized management of postoperative vital sign data. Its beneficial effects are mainly reflected in the following aspects: First, through data matching and labeling numbers, it ensures that the vital signs data of each patient can be accurately associated with the patient's identity information, facilitating data traceability and management; second, the anomaly elimination and standardized processing of data effectively improve the quality and reliability of the data, avoiding incorrect judgments caused by sensor failure or data deviation; finally, through the efficient storage and sorting of cloud databases, the retrieval efficiency and access convenience of data are further improved, laying a solid data foundation for subsequent risk assessment and the implementation of intervention measures.

[0095] Example 4

[0096] This embodiment is explained in Example 3, please refer to Figure 1 ,Specifically: S3 includes S31 and S32;

[0097] S31. Based on the machine learning algorithm, a preliminary dehydration risk algorithm model is constructed in the cloud data processing platform. The standard vital sign data of each patient in the cloud database is extracted through the API application program interface, and the data is input into the preliminary dehydration risk algorithm model to calculate and output the preliminary dehydration risk index DS for each patient, thereby comprehensively quantifying the dehydration index of each patient.

[0098] The preliminary dehydration risk indicator DS is calculated and output by the following preliminary dehydration risk algorithm model;

[0099]

[0100] Where, DS i represents the initial dehydration risk index of the i-th patient, ln represents the natural logarithm, UOsmi represents the urine osmotic pressure of the i-th patient, Pdi i represents the urination rate of the i-th patient, TBW i represents the total body water content of the i-th patient, HRV i Represents the heart rate variability index of the i-th patient, RHR i represents the heart rate response coefficient of the i-th patient, EL i represents the limb swelling of the i-th patient.

[0101] S32. Calculate a preliminary dehydration risk index DS for each patient and perform a preliminary assessment based on the output of the preliminary dehydration risk index DS to screen patients at risk of dehydration. The specific assessment contents are as follows;

[0102] When the initial dehydration risk indicator DS of the i-th patient i When the value is ≥0.05, it indicates that the patient is at risk of dehydration, and deep dehydration and edema analysis is performed at this time;

[0103] When the initial dehydration risk indicator DS of the i-th patient i When the value is <0.05, it indicates that the patient is normal and needs to be monitored continuously.

[0104] In this embodiment, the method first constructs a preliminary dehydration risk algorithm model in the cloud data processing platform, which combines the standard vital signs data of each patient. The standard vital signs data of each patient stored in the cloud database is extracted through the API interface, and input into the algorithm model for calculation, and finally the preliminary dehydration risk index DS of each patient is output. This indicator reflects the patient's dehydration risk level through the comprehensive quantification of multiple vital signs data. Based on the calculation results of the preliminary dehydration risk index DS, each patient is then preliminarily evaluated. When the DS value is ≥0.05, it indicates that the patient may be at risk of dehydration and further deep dehydration and edema analysis is required; when the DS value is <0.05, it indicates that the patient is in a normal state and the system will continue to monitor. This screening method based on numerical thresholds can effectively identify which patients have potential dehydration risks and take targeted measures to intervene in a timely manner. Through this embodiment, the present invention realizes the automated assessment of postoperative dehydration risk based on big data and machine learning technology. Its beneficial effects are reflected in the following aspects: First, the use of machine learning algorithms can comprehensively consider the influence of multiple vital signs data, thereby improving the accuracy and scientificity of dehydration risk assessment; second, by introducing an automated assessment process, it reduces the bias of manual judgment and improves monitoring efficiency and processing speed; in addition, the system can automatically screen out high-risk patients based on preliminary assessment results, thereby providing strong decision-making support for subsequent interventions.

[0105] Example 5

[0106] This embodiment is explained in Example 4. Please refer to Figure 1 , specifically: S4 includes S41, S42 and S43;

[0107] S41. After preliminary screening of patients at risk of dehydration, further perform a deep dehydration and edema analysis, which includes a deep dehydration analysis and a deep edema analysis;

[0108] Deep dehydration analysis uses nonlinear power functions and exponential functions, combined with urine osmotic pressure UOsm, total body water content TBW, urination rate Pdi, heart rate variability index HRV and limb swelling EL, to calculate and output the deep dehydration risk index DA for each screened patient;

[0109] The deep dehydration risk index DA is calculated and output by the following algorithm formula;

[0110]

[0111] In the formula, DA i represents the deep dehydration risk index of the i-th patient, exp represents the exponential function, and HRcrit represents the critical heart rate.

[0112] S42. Deep edema analysis: By combining nonlinear power relationships, exponential functions, and standard physical sign data, the edema risk indicator EA is calculated and output to analyze the edema risk.

[0113] The edema risk index EA is calculated and output by the following algorithm formula;

[0114]

[0115] Where Pfl represents fluid intake, EA i represents the edema risk index EA of the i-th patient, WCR represents the water clearance rate, and T represents the unit time window.

[0116] S43. Based on the obtained deep dehydration risk index DA and edema risk index EA, a comprehensive calculation is performed to obtain a comprehensive analysis index R, and the postoperative risk of the patient is analyzed;

[0117] The comprehensive analysis index R is calculated and output through the following algorithm formula;

[0118]

[0119] Where α and β represent the deep dehydration risk index DA of the i-th patient, respectively. i and the edema risk indicator EA for the i-th patient i The weight value of .

[0120] In this embodiment, the method performs a deep dehydration analysis on patients initially identified as at risk of dehydration. During this process, a nonlinear power function and exponential function model are employed to calculate a deep dehydration risk index (DA) for each patient. This index not only considers the interaction of various vital signs but also incorporates the critical heart rate (HRcrit), helping to identify patients at high risk through in-depth analysis. Furthermore, a deep edema risk index (EA) is calculated for each patient in patients at risk of dehydration. By combining a nonlinear power relationship, an exponential function, and standard vital signs such as fluid intake, the edema risk index (EA) is calculated. This analysis effectively identifies patients at risk of edema and helps healthcare professionals understand changes in their fluid status. Next, the deep dehydration risk index (DA) and the edema risk index (EA) are combined to produce a comprehensive analysis index (R). This index uses user-defined weights to weight the risks of deep dehydration and edema, providing a comprehensive assessment of the patient's overall postoperative risk. The introduction of the comprehensive analysis index (R) integrates the assessment of dehydration and edema risks, providing a more comprehensive patient risk profile. The core advantages of this implementation are: first, the combined analysis of deep dehydration and edema is more comprehensive, taking into account the multi-dimensional interaction of patients' postoperative physical signs, thereby improving the accuracy of the assessment; second, through the combination of nonlinear and exponential models, it can handle complex clinical data relationships, significantly improving the sensitivity and predictive ability of the model; finally, the calculation of the comprehensive analysis index R provides clear and intuitive risk assessment results for subsequent patient management and intervention decisions.

[0121] Example 6

[0122] This embodiment is explained in Example 5, please refer to Figure 1 ,Specifically: S5 includes S51 and S52;

[0123] S51. Based on the output of the comprehensive analysis index R, conduct a secondary comparative evaluation to analyze the dehydration and edema status of the current postoperative urology patients, and generate intervention recommendations based on the secondary comparative evaluation results. The specific evaluation contents are as follows;

[0124] When the comprehensive analysis index R>1, it means that the current patient is at risk of dehydration, and the first intervention recommendation is generated;

[0125] When the comprehensive analysis index R=1, it means that the patient's current dehydration risk and edema risk are normal, and the patient's dehydration and edema are at critical values. At this time, no intervention or continuous monitoring is required;

[0126] When the comprehensive analysis index R<1, it means that the current patient is at risk of edema, and the second intervention recommendation is generated;

[0127] S52. Based on the intervention suggestions obtained, early warning information is generated and pushed to the client through the cloud data processing platform to prompt medical staff to intervene in the patient after urological surgery. The client includes a mobile terminal and a nursing terminal;

[0128] The specific warning information is as follows:

[0129] When the first intervention recommendation is generated, the first warning message is pushed to the medical staff, reminding them that the patient is at risk of dehydration. In this case, the patient should increase fluid intake by 30%, adjust the drug dosage, and switch to intravenous fluid replacement.

[0130] When the second intervention suggestion is generated, a second warning message is pushed to remind medical staff that the patient is at risk of edema. At this time, medications such as diuretics can be adjusted and the patient is advised to exercise.

[0131] In this embodiment, the method analyzes the patient's current risk of dehydration and edema through a secondary comparative assessment based on a comprehensive analysis index, R, and generates personalized intervention recommendations for each patient. Specifically, when the comprehensive analysis index, R, is greater than 1, indicating a high risk of dehydration, a first intervention recommendation is generated, prompting increased fluid intake and adjusting medication dosage and treatment based on the patient's condition. When R = 1, the patient's risk of dehydration and edema is within the normal range, requiring no immediate intervention and requiring continued regular monitoring. When R < 1, indicating a risk of edema, a second intervention recommendation is generated, prompting medical staff to adjust diuretic use and recommending appropriate exercise. Next, an early warning message is generated based on the intervention recommendation and pushed to the client via a cloud-based data processing platform. This mechanism provides real-time notifications on mobile and nursing terminals, promptly informing medical staff of the patient's risk status and recommended intervention measures. Specifically, when the first intervention recommendation is generated, the system automatically pushes an early warning message, reminding medical staff to increase fluid intake, adjust medication regimens, and switch to intravenous fluids. The second intervention recommendation, however, suggests adjusting diuretic use and recommending exercise to effectively manage edema. This implementation not only enhances the accuracy of risk assessments but also ensures the timeliness and relevance of interventions, improving the precision of patient management. Its beneficial effects are reflected in the following aspects: First, patients' dehydration and edema risks are accurately identified and assessed, enabling medical staff to make informed intervention decisions based on real-time data; second, personalized intervention recommendations are delivered, ensuring rapid implementation of patient care measures and avoiding the risk of worsening conditions; finally, the early warning information push mechanism enables real-time interaction between medical staff and patients, optimizing postoperative management processes and improving the quality and efficiency of medical services.

[0132] Example 7

[0133] See also Figure 1and Figure 2 , a postoperative urological vital sign monitoring data processing system, including a postoperative vital sign collection module, a cloud processing module, a preliminary dehydration analysis module, a deep dehydration and edema analysis module and a comprehensive evaluation push module;

[0134] The postoperative vital signs collection module equips all urological surgery patients with a sensor group to collect all patients' postoperative vital signs data in real time, and builds a cloud data processing platform to transmit the collected postoperative vital signs data to the cloud data processing platform through the Internet of Things;

[0135] The cloud processing module pre-processes the postoperative vital sign data in the cloud data processing platform to obtain the standard vital sign data of each patient, and labels and numbers the standard vital sign data of each patient. At the same time, a cloud database is set up to store the standard vital sign data in the cloud database and sort them in the order of numbers;

[0136] The preliminary dehydration analysis module builds a preliminary dehydration risk algorithm model on the cloud data processing platform, extracts each patient's standard physical sign data and inputs them into the preliminary dehydration risk algorithm model. The module then calculates and outputs a preliminary dehydration risk index DS for each patient. Based on the output of the preliminary dehydration risk index DS, a preliminary comparative assessment is conducted to screen patients at risk of dehydration.

[0137] The deep dehydration and edema analysis module screens out patients at risk of dehydration through preliminary assessment and performs deep dehydration and edema analysis. The deep dehydration and edema analysis extracts standard physical sign data and calculates and outputs the deep dehydration risk index DA and the edema risk index EA. The deep dehydration risk index DA and the edema risk index EA are then comprehensively calculated to output the comprehensive risk index R.

[0138] The comprehensive assessment push module performs a secondary comparative assessment based on the output results of the comprehensive risk index R, analyzes the current patient's dehydration and edema risks, generates early warning information, and sends it to the client to push early warning notifications.

[0139] While the embodiments of the present invention have been shown and described, it will be apparent to those skilled in the art that various changes, modifications, substitutions, and alterations can be made to the embodiments without departing from the principles and spirit of the invention.

Claims

1. A method for processing post-urological vital sign monitoring data, characterized by: The following steps are involved: S1. Equip all patients after urological surgery with a sensor set to collect postoperative vital sign data of all patients in real time, build a cloud data processing platform, and transmit the collected postoperative vital sign data to the cloud data processing platform via the Internet of Things; S2. Preprocessing the postoperative vital sign data in a cloud data processing platform to obtain standard vital sign data for each patient, labeling and numbering the standard vital sign data for each patient, and setting up a cloud database to store the standard vital sign data in the cloud database and sorting them in order of numbering; S3. Constructing a preliminary dehydration risk algorithm model on the cloud data processing platform, extracting standard vital sign data for each patient and inputting them into the preliminary dehydration risk algorithm model, calculating and outputting a preliminary dehydration risk index DS for each patient, and performing preliminary comparative evaluation based on the output of the preliminary dehydration risk index DS to screen patients at risk of dehydration; The preliminary dehydration risk indicator DS is calculated and output by the following preliminary dehydration risk algorithm model; Where, DS i represents the initial dehydration risk index of the i-th patient, ln represents the natural logarithm, UOsm i represents the urine osmotic pressure of the i-th patient, Pdi i represents the urination rate of the i-th patient, TBW i represents the total body water content of the i-th patient, HRV i Represents the heart rate variability index of the i-th patient, RHR i represents the heart rate response coefficient of the i-th patient, EL i represents the limb swelling degree of the i-th patient; S4. For patients identified as at risk of dehydration through preliminary assessment, perform a deep dehydration and edema analysis. The deep dehydration and edema analysis extracts standard physical sign data and calculates and outputs a deep dehydration risk index DA and an edema risk index EA. The deep dehydration risk index DA and the edema risk index EA are then combined to output a comprehensive risk index R. The deep dehydration risk index DA is calculated and output by the following algorithm formula: In the formula, DA i represents the deep dehydration risk index of the i-th patient, exp represents the exponential function, and HRcrit represents the critical heart rate; The edema risk index EA is calculated and output by the following algorithm formula; Where Pfl represents fluid intake, EA i represents the edema risk index EA of the i-th patient, WCR represents the water clearance rate, and T represents the unit time window; S5. Perform a secondary comparative evaluation based on the output results of the comprehensive risk index R, analyze the current patient's dehydration and edema risks, generate warning information, and send it to the client to push warning notifications.

2. The method for processing post-urological vital sign monitoring data according to claim 1, characterized in that: Said S1 includes S11 and S12; S11, equipping all patients after urological surgery with a sensor group, and setting the sensor group's acquisition frame rate to once per minute, to collect postoperative vital sign data of all patients after urological surgery in real time; The sensor group includes a urine analyzer, a smart weight scale, a blood oxygen saturation detector, an electrocardiogram device, a limb dimension measuring instrument and a bioelectrical impedance analyzer; The postoperative physical sign data include urination rate Pdi, urine osmotic pressure UOsm, heart rate variability index HRV, heart rate response coefficient RHR, total body water content TBW and limb swelling EL; S12. Through the communication module in the sensor group, use the MQTT protocol of the Internet of Things to encapsulate the postoperative vital sign data, obtain the vital sign data packet, and generate a unique identifier for each vital sign data packet. Then, transmit the vital sign data packet to the cloud data processing platform through the wireless communication network.

3. The method for processing post-urological vital sign monitoring data according to claim 2, characterized in that: Said S2 includes S21 and S22; S21. Receive vital sign data packets in real time on the cloud data processing platform, unpack the data packets, extract postoperative vital sign data, and set up an API to integrate the cloud data processing platform with the medical record system. Match the unique identifier with the patient medical record information in the medical record database to extract the patient's initials and the last four digits of their ID card. After matching the patient case information, preprocess the postoperative vital sign data of all patients, including abnormal data removal and data standardization, obtain standard vital sign data, and mark the standard vital sign data of each patient with a number; The number is composed in the following format: initials of name / last four digits of ID card / year, month, day / last two digits of unique identifier; The abnormal data elimination is carried out by using the data anomaly detection algorithm z-score on the postoperative vital sign data to eliminate sensor failure and data deviation; The data standardization is performed by denoising, filling missing values ​​and normalizing the postoperative vital sign data; S22. At the same time, a cloud database is set up, and an API application program interface is set up to integrate the cloud data processing platform with the cloud database, store the standard vital signs data in the cloud database, and sort them in order of number.

4. The method for processing post-urological vital sign monitoring data according to claim 3, characterized in that: Said S3 includes S31 and S32; S31. Based on the machine learning algorithm, a preliminary dehydration risk algorithm model is constructed in the cloud data processing platform. The standard vital signs data of each patient in the cloud database is extracted through the API application program interface, and input into the preliminary dehydration risk algorithm model to calculate and output the preliminary dehydration risk index DS for each patient, and comprehensively quantify the dehydration index of each patient.

5. The method for processing post-urological vital sign monitoring data according to claim 4, characterized in that: S32. Calculate a preliminary dehydration risk index DS for each patient and perform a preliminary assessment based on the output of the preliminary dehydration risk index DS to screen patients at risk of dehydration. The specific assessment content is as follows; When the initial dehydration risk indicator DS of the i-th patient i When the value is ≥0.05, it indicates that the patient is at risk of dehydration, and deep dehydration and edema analysis is performed at this time; When the initial dehydration risk indicator DS of the i-th patient i When the value is <0.05, it indicates that the patient is normal and needs to be monitored continuously.

6. The method for processing post-urological vital sign monitoring data according to claim 1, characterized in that: Said S4 includes S41, S42 and S43; S41. After preliminary screening of patients at risk of dehydration, further performing a deep dehydration and edema analysis, the deep dehydration and edema analysis including a deep dehydration analysis and a deep edema analysis; The deep dehydration analysis uses a nonlinear power function and an exponential function, combined with urine osmotic pressure UOsm, total body water content TBW, urination rate Pdi, heart rate variability index HRV and limb swelling EL, to calculate and output the deep dehydration risk index DA for each screened patient.

7. The method for processing post-urological vital sign monitoring data according to claim 6, characterized in that: S42. The depth edema analysis is performed by combining a nonlinear power relationship, an exponential function and standard physical sign data to calculate and output an edema risk index EA to analyze the edema risk.

8. The method for processing post-urological vital sign monitoring data according to claim 6, characterized in that: S43. Based on the obtained deep dehydration risk index DA and edema risk index EA, a comprehensive calculation is performed to obtain a comprehensive analysis index R, and the postoperative risk of the patient is analyzed; The comprehensive analysis index R is calculated and output by the following algorithm formula: Where α and β represent the deep dehydration risk index DA of the i-th patient, respectively. i and the edema risk indicator EA for the i-th patient i The weight value is set by the user, and α+β=1.

9. The method for processing post-urological vital sign monitoring data according to claim 8, characterized in that: Said S5 includes S51 and S52; S51. Based on the output of the comprehensive analysis index R, conduct a secondary comparative evaluation to analyze the dehydration and edema status of the current postoperative urology patients, and generate intervention recommendations based on the secondary comparative evaluation results. The specific evaluation contents are as follows; When the comprehensive analysis index R>1, it means that the current patient is at risk of dehydration, and the first intervention recommendation is generated; When the comprehensive analysis index R=1, it means that the patient's current dehydration risk and edema risk are normal, and there is no need for intervention and continuous monitoring; When the comprehensive analysis index R<1, it means that the current patient is at risk of edema, and the second intervention recommendation is generated; S52: Based on the obtained intervention suggestions, generate warning information and push it to the client through the cloud data processing platform to prompt medical staff to intervene in the patient after urological surgery. The client includes a mobile terminal and a nursing terminal; The specific warning information is as follows: When the first intervention recommendation is generated, the first warning message is pushed to the medical staff, reminding them that the patient is at risk of dehydration. In this case, the patient should increase fluid intake by 30%, adjust the drug dosage, and switch to intravenous fluid replacement. When the second intervention suggestion is generated, a second warning message is pushed to remind medical staff that the patient is at risk of edema. At this time, the medication use should be adjusted and the patient is advised to exercise.

10. A system for processing data of post-urological vital signs monitoring, applied to the method for processing data of post-urological vital signs monitoring according to any one of claims 1 to 9, characterized in that: It includes postoperative vital signs collection module, cloud processing module, preliminary dehydration analysis module, deep dehydration and edema analysis module and comprehensive assessment push module; The postoperative vital signs collection module equips all patients after urological surgery with a sensor group to collect the postoperative vital signs data of all patients in real time, and builds a cloud data processing platform to transmit the collected postoperative vital signs data to the cloud data processing platform through the Internet of Things; The cloud processing module pre-processes the postoperative vital sign data in a cloud data processing platform to obtain standard vital sign data of each patient, labels and numbers the standard vital sign data of each patient, and sets up a cloud database to store the standard vital sign data in the cloud database and sort them in order of numbers; The preliminary dehydration analysis module constructs a preliminary dehydration risk algorithm model in the cloud data processing platform, extracts the standard physical sign data of each patient and inputs them into the preliminary dehydration risk algorithm model, calculates and outputs a preliminary dehydration risk index DS for each patient, and performs preliminary comparative evaluation based on the output results of the preliminary dehydration risk index DS to screen patients at risk of dehydration; The deep dehydration and edema analysis module screens out patients at risk of dehydration through preliminary assessment and performs deep dehydration and edema analysis. The deep dehydration and edema analysis extracts standard physical sign data and calculates and outputs a deep dehydration risk index DA and an edema risk index EA. The deep dehydration risk index DA and the edema risk index EA are then comprehensively calculated to output a comprehensive risk index R. The comprehensive assessment push module performs a secondary comparative assessment based on the output results of the comprehensive risk index R, analyzes the current patient's dehydration and edema risks, generates warning information, and sends it to the client to push warning notifications.

Images