A method and system for analyzing patient postoperative recovery data
By designing a data analysis system in postoperative management, monitoring and analyzing the physiological parameters and blood sample data of postoperative patients in real time, and constructing coagulation status and parasympathetic activity indicators, the problem of insufficient monitoring of coagulation status in traditional methods is solved, and the problem of improving the The accuracy and efficiency of postoperative rehabilitation management reduces the risk of complications.
Patent Information
- Application Number
- CN202411288336.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-14
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-09-14
AI Technical Summary
The lack of systematic data processing and intelligent analysis in traditional postoperative management makes it difficult to make full use of big data, especially in insufficient monitoring of coagulation status in cardiac surgery, which may lead to the possibility of missing early warning opportunities.
A patient postoperative recovery data analysis system was designed, including data monitoring module, data processing module, postoperative device introduction analysis module, patient recovery analysis module and management module. Physiological parameters and blood sample data are monitored in real time through multiple sets of medical equipment. Data preprocessing and analysis were performed using dimensionless processing and convolutional neural networks, and the coagulation state coefficient and parasympathetic activity coefficient were constructed, postoperative rehabilitation stability index was generated, and the recovery degree was evaluated in real time and corresponding interventions were implemented.
The comprehensive monitoring and intelligent analysis of postoperative patient physiological parameters and blood sample data is achieved, which improves the accuracy of coagulation management, prevents postoperative bleeding or thrombosis risks, optimizes rehabilitation management efficiency, and reduces the incidence of complications.
Smart Images

Figure CN118800474B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of medical technology, and in particular to a method and system for analyzing patient postoperative recovery data. Background Art
[0002] Data analysis plays an important role in the field of medical data analysis and patient monitoring, especially in the rehabilitation management of patients after cardiac surgery. The patient's recovery process is very complex and critical, involving real-time monitoring of multiple physiological parameters, including fluctuations in multiple key physiological parameters such as heart rate, blood pressure, blood oxygen level, and changes in blood coagulation function. Therefore, accurate monitoring and analysis of these parameters are of great significance for preventing postoperative complications, optimizing rehabilitation plans, and improving patients' rehabilitation effects.
[0003] In traditional postoperative management, although there are a variety of medical devices used to monitor patients' physiological parameters, the data are usually scattered and lack systematic processing and analysis. Existing methods often rely on doctors' experience and judgment, and it is difficult to fully utilize big data and intelligent analysis technology. In addition, in cardiac surgery, if an extracorporeal membrane oxygenation machine (ECMO) is used, special attention should be paid to the coagulation state in the extracorporeal circulation system. The extracorporeal membrane oxygenation machine draws blood from the body through a pipe, and returns it to the body after oxygenation and temperature control. This process has high requirements for coagulation function, so the coagulation state needs to be monitored in time, and the traditional manual analysis method may ignore this point, which ultimately leads to the missed opportunity for early warning. Summary of the invention
[0004] In view of the deficiencies in the prior art, the present invention provides a method and system for analyzing patient postoperative recovery data, which solves the problems in the above-mentioned background technology.
[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a patient postoperative recovery data analysis system, including a data monitoring module, a data processing module, a postoperative instrument introduction analysis module, a patient recovery analysis module and a control module;
[0006] The data monitoring module is used to monitor and obtain relevant physiological parameters and relevant blood sample data of postoperative patients through several groups of medical equipment;
[0007] The data processing module is used to pre-process the relevant physiological parameters and relevant blood sample data, and combine the dimensionless processing technology to unify the units, and finally summarize and generate a recovery state set;
[0008] The postoperative instrument introduction analysis module is used to construct the patient's coagulation state coefficient Nzxs based on the relevant blood sample data after preprocessing, and through the preset safety lower limit and safety upper limit , determine the corresponding coagulation instruction issued;
[0009] The patient recovery analysis module is used to construct the parasympathetic nerve activity coefficient Fhxs according to the relevant physiological parameters after pretreatment after receiving the coagulation instruction, and to obtain the postoperative rehabilitation stability index Skzs by fitting according to the trained recovery prediction model;
[0010] The control module is used to pre-set an evaluation threshold L, and compare and analyze the postoperative rehabilitation stability index Skzs with the evaluation threshold L to comprehensively predict the current postoperative patient's recovery degree.
[0011] Preferably, the data monitoring module includes a monitoring device unit, a first monitoring unit and a second monitoring unit;
[0012] The monitoring equipment unit is used to perform physical examination on the postoperative patient using several sets of medical equipment, wherein the several sets of medical equipment include an enzyme-linked immunosorbent assay instrument, an automatic blood analyzer, a coagulation analyzer, a respiratory sensor and an electrocardiograph;
[0013] The first monitoring unit is used to monitor and record relevant physiological parameters of the postoperative patient, wherein the relevant physiological parameters include each continuous RR interval and the respiratory rate Hp in each monitoring period;
[0014] The second monitoring unit is used to monitor and record the relevant blood sample data of the postoperative patient, wherein the relevant blood sample data includes the platelet count Xjs, the coagulation ratio Nbz, the plasmin concentration and the Fibrin degradation product concentration .
[0015] Preferably, the data processing module includes a preprocessing unit and a summarizing unit;
[0016] The preprocessing unit is used to use a convolutional neural network (CNN) and data preprocessing technology to identify and eliminate errors, abnormal values or noise data information of relevant physiological parameters and relevant blood sample data, and to extract features from the data to extract useful feature data;
[0017] The aggregation unit is used to standardize the relevant data information processed in the preprocessing unit based on the dimensionless processing technology, and use a standardization method to make it have a unified scale, wherein the standardization method includes Z-score standardization, and then aggregate the processed relevant data information into a recovery state set.
[0018] Preferably, the postoperative instrument introduction analysis module includes a blood status analysis unit and a preliminary judgment unit;
[0019] The blood state analysis unit includes a first analysis subunit and a second analysis subunit;
[0020] The first analysis subunit is used to obtain the fibrinolytic activity factor Qhyz in different monitoring periods according to the relevant blood sample data, specifically in the following manner: ; In the formula, Expressed as the concentration of fibrin degradation products, Expressed as plasmin concentration, and All are weight values;
[0021] Preferably, the second analysis subunit is used to calculate the coagulation state coefficient Nzxs of the patient in different monitoring periods based on the relevant blood sample data and in combination with the fibrinolytic activity factor Qhyz, which is specifically obtained by the following formula: ; Nbz represents the coagulation ratio, Xjs represents the platelet count, and are expressed as weight values, Expressed as the first correction constant;
[0022] Among them, the coagulation ratio Nbz is obtained by the following formula: ;in, It is expressed as the actual measured coagulation time. Indicates the normal coagulation time.
[0023] Preferably, the preliminary judgment unit is used to perform statistics on the coagulation state coefficients Nzxs of the patients in the monitoring period obtained in the second analysis subunit, and combine the statistical algorithm to obtain the average coagulation state coefficients of the patients. and standard deviation of coagulation state coefficient , and based on the patient's average coagulation state coefficient and standard deviation of coagulation state coefficient , set a lower safety limit and safety upper limit , the specific settings are as follows: ; ; In the formula, r is a constant, and the specific value is set by the user;
[0024] By comparing the patient's coagulation state coefficient Nzxs during the current monitoring period with the safety lower limit and safety upper limit Compare and determine the coagulation state of the wound of the current postoperative patient. The specific determination contents are as follows:
[0025] If the coagulation state coefficient Nzxs is less than the safety lower limit When the patient is diagnosed with a risk of thrombosis at the wound after surgery, a coagulation instruction will be issued;
[0026] If the safety limit ≤ coagulation state coefficient Nzxs<safety upper limit When the blood coagulation at the wound of the postoperative patient is judged to be in a normal state, there is no need to issue a blood coagulation instruction;
[0027] If the coagulation state coefficient Nzxs ≥ the safety upper limit When the patient's wound is judged to be at risk of bleeding after surgery, a coagulation command will be issued.
[0028] Preferably, the patient recovery analysis module includes an activity analysis unit and a comprehensive analysis unit;
[0029] The activity analysis unit is used to construct the patient's parasympathetic nerve activity coefficient Fhxs based on relevant physiological parameters, which is specifically obtained in the following manner: ; In the formula, It is represented by the total number of RR intervals; i=1, 2, 3, ..., N; M represents the monitoring period; j=1, 2, 3, ..., M-1; is the i+1th RR interval, indicating the time interval between the i+1th heartbeat and the i-th heartbeat; is the i-th RR interval, which indicates the time interval between the i-th heartbeat and the i−1-th heartbeat; is the respiratory rate in the j+1th monitoring period; It is expressed as the respiratory rate during the jth monitoring period.
[0030] Preferably, the comprehensive analysis unit is used to construct a recovery prediction model using a convolutional neural network, and input the parasympathetic nerve activity coefficient Fhxs and the coagulation state coefficient Nzxs into the recovery prediction model, and map the corresponding data values in the interval In order to construct the postoperative rehabilitation stability index Skzs, it is obtained in the following way: ; In the formula, and are weight values, Expressed as the second correction constant.
[0031] Preferably, the control module includes a comparison unit and a management unit;
[0032] The comparison unit is used to compare and analyze the postoperative rehabilitation stability index Skzs with the evaluation threshold L to comprehensively predict the current postoperative patient's recovery degree. The specific contents are as follows:
[0033] If the postoperative rehabilitation stability index Skzs exceeds the evaluation threshold L, it means that the current postoperative patient's recovery is in a normal state;
[0034] If the postoperative rehabilitation stability index Skzs does not exceed the evaluation threshold L, it means that the patient's recovery after surgery is not yet in a normal state;
[0035] The management unit is used to determine and implement corresponding medical interventions based on the analysis results of the comparison unit, and is responsible for recording all intervention measures and their effects, and feeding them back to the cloud platform to optimize the subsequent rehabilitation prediction model; the specific intervention contents are:
[0036] If the patient is in a normal state, the current rehabilitation plan and medical intervention measures will continue at this time, and no additional intervention is needed;
[0037] If it is not in a normal state, the patient's rehabilitation treatment plan will be adjusted at this time. Implantable devices or non-invasive technologies will be used to directly stimulate the vagus nerve to enhance the activity of the patient's parasympathetic nerves. At the same time, the coagulation state will be adjusted by taking anticoagulant drugs or supplementing fibrinogen.
[0038] A method for analyzing patient postoperative recovery data, comprising:
[0039] The relevant physiological parameters and blood sample data of the postoperative patients are monitored and obtained through several groups of medical equipment;
[0040] Preprocess the relevant physiological parameters and related blood sample data, and combine the dimensionless processing technology to unify the units, and finally summarize and generate a recovery status set;
[0041] Based on the pre-processed blood sample data, the patient's coagulation state coefficient Nzxs is constructed and the pre-set safety lower limit is used. and safety upper limit , determine the corresponding coagulation instruction issued;
[0042] After receiving the coagulation instruction, the parasympathetic nerve activity coefficient Fhxs is constructed based on the relevant physiological parameters after pretreatment, and the postoperative rehabilitation stability index Skzs is fitted based on the trained recovery prediction model;
[0043] An evaluation threshold L is preset, and the postoperative rehabilitation stability index Skzs is compared and analyzed with the evaluation threshold L to comprehensively predict the current postoperative patient's recovery degree.
[0044] The present invention provides a method and system for analyzing patient postoperative recovery data, which has the following beneficial effects:
[0045] By integrating multiple modules, the system further realizes the all-round monitoring and intelligent analysis of the physiological parameters and blood sample data of postoperative patients. First, the data monitoring module collects the physiological parameters and blood sample data of postoperative patients in real time with the help of multiple sets of medical equipment to ensure the multi-faceted and real-time nature of the data. The postoperative instrument introduction analysis module constructs the coagulation state coefficient Nzxs by analyzing the pre-treated blood sample data, and issues corresponding coagulation instructions based on the preset safety range. This function is particularly critical in postoperative coagulation management and can effectively prevent the risk of postoperative bleeding or thrombosis. After receiving the coagulation instruction, the patient recovery analysis module combines the pre-treated physiological parameter data to construct the parasympathetic nerve activity coefficient Fhxs, and fits the postoperative rehabilitation stability index Skzs through the trained recovery prediction model. This index can further accurately reflect the patient's postoperative recovery stability. Finally, the control module can evaluate the patient's recovery degree in real time by comparing and analyzing the postoperative rehabilitation stability index Skzs with the pre-set evaluation threshold L. In short, the system not only provides clinicians with clear indications of postoperative recovery status, but also optimizes intervention measures through intelligent analysis, further improving the efficiency and accuracy of postoperative rehabilitation management, thereby improving patients' postoperative recovery effects and reducing the incidence of postoperative complications.
[0046] The design of the postoperative instrument introduction analysis module in this system provides a more scientific basis for the rehabilitation monitoring of postoperative patients through accurate analysis of blood status. Specifically, the blood status analysis unit can obtain and analyze the key indicator of fibrinolytic activity factor Qhyz in different monitoring periods through the collaborative work of the first analysis subunit and the second analysis subunit, so as to timely identify potential risks such as abnormal coagulation or excessive fibrinolysis during the postoperative recovery process. This real-time and dynamic blood status analysis not only provides an important reference for subsequent treatment decisions, but also can make more scientific choices in the introduction or regulation of postoperative instruments, and further avoid complications caused by abnormal coagulation or fibrinolysis.
[0047] The patient recovery analysis module in the present invention provides a more accurate evaluation method for the cardiac recovery status of postoperative patients by constructing the parasympathetic nerve activity coefficient Fhxs. The activity analysis unit uses the RR interval between consecutive heartbeats and the respiratory rate in different monitoring periods to dynamically analyze the heart rate variability, which is one of the important indicators of cardiac autonomic nervous function. By calculating the time difference between adjacent RR intervals, the system can sensitively capture the irregularity of heartbeat time and provide an in-depth understanding of the patient's autonomic nervous system state.
[0048] By recording and feeding back all intervention measures and their effects to the cloud platform, the system can continuously optimize the rehabilitation prediction model, improve the accuracy of future predictions and the effectiveness of interventions. This closed-loop feedback system improves the intelligence level of rehabilitation management and helps improve the long-term prognosis of patients. Under the multi-faceted monitoring of the system, abnormal conditions in the postoperative rehabilitation process, such as insufficient parasympathetic nerve activity or abnormal coagulation, can be discovered and corrected in a timely manner, effectively reducing the risk of serious complications in patients and ensuring their safety. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] Figure 1 This is a block diagram of a patient postoperative recovery data analysis system of the present invention;
[0050] Figure 2 The present invention is a flow chart of a method for analyzing patient postoperative recovery data. DETAILED DESCRIPTION
[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.
[0052] Example 1: Please refer to Figure 1 , the present invention provides a patient postoperative recovery data analysis system, including a data monitoring module, a data processing module, a postoperative instrument introduction analysis module, a patient recovery analysis module and a control module;
[0053] The data monitoring module is used to monitor and obtain relevant physiological parameters and relevant blood sample data of postoperative patients through several groups of medical equipment;
[0054] The data processing module is used to pre-process the relevant physiological parameters and relevant blood sample data, and combine the dimensionless processing technology to unify the units, and finally summarize and generate a recovery state set;
[0055] The postoperative instrument introduction analysis module is used to construct the patient's coagulation state coefficient Nzxs based on the relevant blood sample data after preprocessing, and through the preset safety lower limit and safety upper limit , determine the corresponding coagulation instruction issued;
[0056] The patient recovery analysis module is used to construct the parasympathetic nerve activity coefficient Fhxs according to the relevant physiological parameters after pretreatment after receiving the coagulation instruction, and to obtain the postoperative rehabilitation stability index Skzs by fitting according to the trained recovery prediction model;
[0057] The control module is used to pre-set an evaluation threshold L, and compare and analyze the postoperative rehabilitation stability index Skzs with the evaluation threshold L to comprehensively predict the current postoperative patient's recovery degree.
[0058] During the operation of this system, firstly, the system integrates multiple groups of medical equipment through the data monitoring module, further realizing real-time and multi-faceted monitoring of the physiological parameters and blood sample data of postoperative patients, ensuring the timeliness and accuracy of the data. This multi-dimensional data collection method further improves the refinement of postoperative management, enabling doctors to make clinical decisions based on richer and more reliable data. Secondly, by pre-processing the physiological parameters and blood sample data through the data processing module, and unifying the units by combining the dimensionless processing technology, the system can effectively eliminate the unit differences between different data sources and further avoid analysis bias caused by inconsistent data. The system also introduces an analysis module through postoperative instruments, constructs the patient's coagulation state coefficient Nzxs based on blood sample data, and accurately judges and issues coagulation instructions through the pre-set safety lower and upper limits, thereby intervening in potential bleeding or thrombosis risks early after surgery, further improving the patient's postoperative safety. Finally, the system uses the preprocessed physiological parameters through the patient recovery analysis module to construct the parasympathetic nerve activity coefficient Fhxs, and combines it with the trained recovery prediction model to fit and generate the postoperative rehabilitation stability index Skzs. This index can objectively reflect the patient's postoperative recovery status, and is compared and analyzed with the preset evaluation threshold L through the management and control module to achieve a comprehensive prediction of the patient's recovery degree. This systematic analysis and evaluation method not only improves the efficiency of postoperative rehabilitation management, but also provides a scientific basis for the formulation of personalized treatment plans, thereby significantly improving the patient's postoperative rehabilitation stability and overall treatment effect.
[0059] It should be noted that the necessity of coagulation function testing is not only reflected in the use of extracorporeal membrane oxygenation machines in cardiac surgery, but also in some other surgeries. For example, in some open-chest surgeries, a heart-lung bypass machine (CPB) is usually used to replace the functions of the heart and lungs. The heart-lung bypass machine (CPB) also requires a high level of management of the blood pathway to prevent thrombosis or other problems.
[0060] Example 2: Please refer to Figure 1 ,Specifically, the data monitoring module includes a monitoring device unit, a first monitoring unit, and a second monitoring unit;
[0061] The monitoring equipment unit is used to perform physical examination on the postoperative patient using several sets of medical equipment, wherein the several sets of medical equipment include an enzyme-linked immunosorbent assay instrument, an automatic blood analyzer, a coagulation analyzer, a respiratory sensor and an electrocardiograph;
[0062] The first monitoring unit is used to monitor and record relevant physiological parameters of the postoperative patient, wherein the relevant physiological parameters include each continuous RR interval and the respiratory rate Hp in each monitoring period;
[0063] The second monitoring unit is used to monitor and record the relevant blood sample data of the postoperative patient, wherein the relevant blood sample data includes the platelet count Xjs, the coagulation ratio Nbz, the plasmin concentration and the Fibrin degradation product concentration .
[0064] The data processing module includes a preprocessing unit and a summarizing unit;
[0065] The preprocessing unit is used to use a convolutional neural network (CNN) and data preprocessing technology to identify and eliminate errors, abnormal values or noise data information of relevant physiological parameters and relevant blood sample data, and to extract features from the data to extract useful feature data;
[0066] The aggregation unit is used to standardize the relevant data information processed in the preprocessing unit based on the dimensionless processing technology, and use a standardization method to make it have a unified scale, wherein the standardization method includes Z-score standardization, and then aggregate the processed relevant data information into a recovery state set.
[0067] In this embodiment, the data monitoring module and data processing module in the system further realize comprehensive monitoring and accurate analysis of the postoperative patient's recovery status through multi-level and refined data collection and processing. Specifically, the data monitoring module not only uses multiple sets of medical equipment to perform physical examinations on postoperative patients through the monitoring equipment unit, but also obtains the patient's physiological parameters and blood sample data through the first monitoring unit and the second monitoring unit. The first monitoring unit focuses on recording continuous RR intervals and respiratory rate Hp, while the second monitoring unit records key blood sample data such as platelet count Xjs, coagulation ratio Nbz, plasmin concentration, and fibrin degradation product concentration in detail. This comprehensive monitoring ensures a multi-dimensional grasp of the patient's postoperative physiological state and provides rich and accurate basic information for subsequent data processing. On this basis, the data processing module uses convolutional neural networks (CNN) and advanced data preprocessing technology through the preprocessing unit to efficiently identify and eliminate errors, outliers or noise in the collected data to ensure the reliability of the data. At the same time, the preprocessing unit also extracts data features to extract key feature data with clinical significance, laying a solid foundation for accurate analysis and prediction. The summary unit further standardizes the processed data through dimensionless processing technology and Z-score standardization method, so that all types of data have a unified scale. This standardization not only eliminates the differences in data units, but also enables data from different sources to be integrated and compared on the same platform, ultimately forming a recovery state set, providing accurate and consistent data support for subsequent postoperative rehabilitation prediction and decision-making. Overall, the system's multi-level monitoring and refined data processing further improve the accuracy and reliability of postoperative recovery monitoring, can timely identify potential postoperative risks, and provide a scientific basis for personalized intervention, thereby improving patients' rehabilitation effects and clinical management levels.
[0068] Example 3: Please refer to Figure 1 ,Specifically, the postoperative instrument introduction analysis module includes a blood status analysis unit and a preliminary judgment unit;
[0069] The blood state analysis unit includes a first analysis subunit and a second analysis subunit;
[0070] The first analysis subunit is used to obtain the fibrinolytic activity factor Qhyz in different monitoring periods according to the relevant blood sample data, specifically in the following manner: ; In the formula, Expressed as the concentration of fibrin degradation products, Expressed as plasmin concentration, and are weight values; where 0 < ≤1,0< ≤1, and + =1.
[0071] The concentration of fibrin degradation products mentioned above Typically measured by blood chemistry analyzer or ELISA instrument, high levels of FDPs may indicate abnormal fibrinolysis, which may be associated with a bleeding tendency.
[0072] Plasmin concentration It is tested through blood samples using an enzyme-linked immunosorbent assay (ELISA) instrument.
[0073] In this embodiment, the postoperative instrument in the system introduces an analysis module, and through in-depth analysis of the blood status of the postoperative patient, the ability to accurately monitor and evaluate the coagulation and fibrinolysis status during the postoperative recovery process is further improved. Specifically, the first analysis subunit in the blood status analysis unit can accurately obtain the fibrinolytic activity factor Qhyz in different monitoring periods based on the relevant blood sample data. By introducing two key parameters, the concentration of fibrin degradation products and the concentration of plasmin, the accurate evaluation of the fibrinolytic activity factor is further ensured. The beneficial effect of this method is that it can more accurately reflect the fibrinolytic activity of the patient in different time periods after surgery, so as to timely identify potential thrombotic risks or abnormal fibrinolytic activity. In addition, through the set weight value, the system can be flexibly adjusted according to the specific patient's situation to ensure that the calculation results are more in line with actual clinical needs. The introduction of this module provides a more scientific and refined tool for the management of the coagulation status of postoperative patients, which can effectively prevent the occurrence of postoperative complications and promote the smooth recovery of patients.
[0074] Example 4: Please refer to Figure 1 Specifically, the second analysis subunit is used to calculate the coagulation state coefficient Nzxs of the patient in different monitoring periods based on the relevant blood sample data and in combination with the fibrinolytic activity factor Qhyz, which is specifically obtained by the following formula: ; Where Nbz represents the coagulation ratio, Xjs represents the platelet count, and are all expressed as weight values, where 0 < ≤1,0< ≤1, and + =1, Expressed as the first correction constant;
[0075] Among them, the coagulation ratio Nbz is obtained by the following formula: ;in, It is expressed as the actual measured coagulation time. Indicates the normal coagulation time.
[0076] The above-mentioned platelet count Xjs can be directly measured by an automatic hematology analyzer.
[0077] Actual measured coagulation time The test was performed by a coagulation analyzer.
[0078] Normal clotting time It is a standard value obtained through statistics of healthy people as a reference value.
[0079] The preliminary judgment unit is used to perform statistics on the coagulation state coefficients Nzxs of the patients in the monitoring period obtained in the second analysis subunit, and combine the statistical algorithm to obtain the average coagulation state coefficients of the patients respectively. and standard deviation of coagulation state coefficient , and based on the patient's average coagulation state coefficient and standard deviation of coagulation state coefficient , set a lower safety limit and safety upper limit , the specific settings are as follows: ; ; In the formula, r is a constant, usually with a value of 1-3, corresponding to different confidence levels, and the specific value is set by the user (according to the actual situation);
[0080] By comparing the patient's coagulation state coefficient Nzxs during the current monitoring period with the safety lower limit and safety upper limit Compare and determine the coagulation state of the wound of the current postoperative patient. The specific determination contents are as follows:
[0081] If the coagulation state coefficient Nzxs is less than the safety lower limit When the patient is diagnosed with a risk of thrombosis at the wound after surgery, a coagulation instruction will be issued;
[0082] If the safety limit ≤ coagulation state coefficient Nzxs<safety upper limit When the blood coagulation at the wound of the postoperative patient is judged to be in a normal state, there is no need to issue a blood coagulation instruction;
[0083] If the coagulation state coefficient Nzxs ≥ the safety upper limit When the patient's wound is judged to be at risk of bleeding after surgery, a coagulation command will be issued.
[0084] In this embodiment, the postoperative instrument introduction analysis module in the system further improves the monitoring and risk prediction capabilities of the coagulation state of postoperative patients through the design of the second analysis subunit. Specifically, the second analysis subunit combines the patient's fibrinolytic active factor Qhyz and related blood sample data, and accurately calculates the coagulation state coefficient Nzxs to quantitatively analyze the coagulation state of the patient in different monitoring periods. Using the weighted formula, the influence of the coagulation ratio Nbz and the platelet count Xjs on the coagulation state is comprehensively considered, and the stability and accuracy of the calculation are ensured by the first correction constant. In addition, the preliminary judgment unit obtains the average coagulation state coefficient and standard deviation of the patient by statistically analyzing the coagulation state coefficient Nzxs data of multiple monitoring periods, and sets the safety lower limit and upper limit based on this. This process combines the statistical algorithm to ensure the reliability of the coagulation state judgment. When the coagulation state coefficient Nzxs is compared with the preset safety range, the system can determine the coagulation state of the postoperative patient's wound in real time, quickly identify potential bleeding or thrombosis risks, and issue corresponding coagulation instructions. This beneficial effect further improves the safety of postoperative patients in practical applications. Through precise monitoring and real-time risk prediction, the system can intervene before the risk of bleeding or thrombosis occurs, effectively reducing the incidence of postoperative complications. In addition, this system can also help doctors better formulate postoperative treatment plans and provide personalized support for patients' rehabilitation, ultimately improving the effect and speed of postoperative recovery.
[0085] Example 5: Please refer to Figure 1 ,Specifically, the patient recovery analysis module includes an activity analysis unit and a comprehensive analysis unit;
[0086] The activity analysis unit is used to construct the patient's parasympathetic nerve activity coefficient Fhxs based on relevant physiological parameters, which is specifically obtained in the following manner: ; In the formula, It is represented by the total number of RR intervals; i=1, 2, 3, ..., N; M represents the monitoring period; j=1, 2, 3, ..., M-1; is the i+1th RR interval, indicating the time interval between the i+1th heartbeat and the i-th heartbeat; is the i-th RR interval, which indicates the time interval between the i-th heartbeat and the i−1-th heartbeat; is the respiratory rate during the j+1th monitoring period; It is expressed as the respiratory rate during the jth monitoring period.
[0087] The RR interval represents the time between consecutive heart beats and is the basic measure of heart rate variability.
[0088] It is the time difference between two adjacent RR intervals, indicating the change between the i-th heartbeat interval and the i+1-th heartbeat interval. This difference reflects the heart rate variability. The larger the difference, the stronger the irregularity of the heartbeat time.
[0089] The RR interval is measured by an electrocardiogram (ECG) to monitor the heart's electrical activity and to analyze the time intervals between R waves.
[0090] Respiratory rate measures the period and frequency of breathing using a respiration sensor or respiration monitoring device.
[0091] Parasympathetic nerve activity can help postoperative patients maintain a lower and more stable heart rate, thereby reducing the workload on the heart.
[0092] In this embodiment, the activity analysis unit in the system provides a means of accurately analyzing the heart rate variability and autonomic nervous system state of postoperative patients by constructing the patient's parasympathetic nerve activity coefficient Fhxs. By comprehensively considering the RR interval between consecutive heartbeats and the respiratory rate Hp during the monitoring period, the system can capture the important characteristics of the patient's heart rate variability. Specifically, by calculating the time difference between two adjacent RR intervals, the system can quantify the regularity and irregularity of the heart rate, and further improve the evaluation of parasympathetic nerve activity through correlation analysis with the respiratory rate. The uniqueness of this method is that it not only considers the change in the heartbeat interval, but also combines the dynamic changes in the respiratory rate, further forming a more comprehensive understanding of heart rate variability. Through the calculated parasympathetic nerve activity coefficient Fhxs, the system can accurately reflect the recovery of the patient's autonomic nervous system after surgery. The higher the value of the parasympathetic nerve activity coefficient Fhxs, it usually means that the patient's heart rate variability is larger and the parasympathetic nerve activity is stronger, which is usually a manifestation of good heart function and ideal postoperative recovery. Ultimately, through the analysis of this module, the medical team can better understand the patient's postoperative neurological recovery status and adjust the recovery plan in a timely manner according to the changing trend of Fhxs, thereby improving the patient's overall recovery effect. This not only improves the accuracy of control over the postoperative rehabilitation process, but also provides a scientific basis for formulating personalized postoperative rehabilitation plans.
[0093] Example 6: Please refer to Figure 1 Specifically, the comprehensive analysis unit is used to construct a recovery prediction model using a convolutional neural network, and input the parasympathetic nerve activity coefficient Fhxs and the coagulation state coefficient Nzxs into the recovery prediction model, and map the corresponding data values in the interval In order to construct the postoperative rehabilitation stability index Skzs, it is obtained in the following way: ; In the formula, and are weight values, where 0 < ≤1,0< ≤1, and + =1, Expressed as the second correction constant.
[0094] A convolutional neural network is used to build an initial model, and the initial model is trained and tested with a recovery state set. The trained initial model is used as a state recognition model, and feature information in the state recognition model is obtained. The state recognition model is trained and tested with the obtained feature information, and the trained state recognition model is used as a recovery prediction model.
[0095] The control module includes a comparison unit and a management unit;
[0096] The comparison unit is used to compare and analyze the postoperative rehabilitation stability index Skzs with the evaluation threshold L to comprehensively predict the current postoperative patient's recovery degree. The specific contents are as follows:
[0097] If the postoperative rehabilitation stability index Skzs exceeds the evaluation threshold L, it means that the current postoperative patient's recovery is in a normal state;
[0098] If the postoperative recovery stability index Skzs does not exceed the assessment threshold L, it means that the patient's recovery after surgery is not yet in a normal state, indicating that there are problems with the patient's postoperative recovery, which may involve factors such as insufficient parasympathetic nerve activity or unstable coagulation state;
[0099] The management unit is used to determine and implement corresponding medical interventions based on the analysis results of the comparison unit, and is responsible for recording all intervention measures and their effects, and feeding them back to the cloud platform to optimize the subsequent rehabilitation prediction model; the specific intervention contents are:
[0100] If the patient is in a normal state, the current rehabilitation plan and medical intervention measures will continue to be maintained, and no additional intervention is required. Although the patient is in a good state of recovery, the patient's relevant parameters still need to be monitored regularly to ensure continued stability;
[0101] If it is not in a normal state, the postoperative rehabilitation treatment plan of the patient will be adjusted at this time. Implantable devices or non-invasive technologies can be used to directly stimulate the vagus nerve, enhance the activity of the parasympathetic nerves in the patient's body after surgery, and improve heart rate variability. Alternatively, the patient can be trained to autonomously regulate heart rate, breathing, and blood pressure to enhance the activity of the parasympathetic nerves and improve heart rate variability. Alternatively, drug treatment, such as neostigmine, can be used to increase parasympathetic nerve activity, inhibit acetylcholinesterase, prolong the action time of acetylcholine in nerve synapses, and promote neurotransmission. At the same time, anticoagulant drugs or fibrinogen supplements, such as enoxaparin, can be taken to prevent thrombosis and adjust the coagulation state. Among them, fibrinogen supplementation is through intravenous infusion of fibrinogen to enhance the blood's coagulation ability and help stop bleeding.
[0102] In this embodiment, the comprehensive analysis unit and the control module in the system further realize the accurate evaluation and dynamic management of the postoperative patient's recovery status by constructing a recovery prediction model and a postoperative rehabilitation stability index Skzs. First, the comprehensive analysis unit uses a convolutional neural network model to input important physiological indicators such as the parasympathetic nerve activity coefficient Fhxs and the coagulation state coefficient Nzxs into the model. After standardization, a rehabilitation stability index Skzs that comprehensively reflects the patient's current recovery status is obtained. This index can comprehensively map different physiological parameters into a unified index range, providing an intuitive and accurate basis for rehabilitation evaluation. The control module further uses the rehabilitation stability index Skzs to dynamically evaluate the patient's recovery status by comparing it with the set evaluation threshold L. When the rehabilitation stability index Skzs exceeds the evaluation threshold L, the system determines that the patient's recovery is in a normal state, reducing unnecessary medical interventions and reducing the waste of medical resources. However, when the rehabilitation stability index Skzs does not reach the assessment threshold L, the system can promptly identify possible recovery problems, such as insufficient parasympathetic nerve activity or unstable coagulation state, and take corresponding medical intervention measures proactively. This precise assessment and dynamic management mechanism helps to detect potential risks in postoperative rehabilitation early and can adjust the rehabilitation treatment plan in a targeted manner. For example, by stimulating the vagus nerve, regulating heart rate variability, taking anticoagulants or supplementing fibrinogen, the system can effectively improve the patient's physiological state and prevent the occurrence of complications, which not only improves the effect of postoperative rehabilitation, but also further reduces the medical risks of patients during postoperative recovery, ultimately providing a strong guarantee for the patient's comprehensive rehabilitation.
[0103] Example 7: Please refer to Figure 2 Specifically, a method for analyzing patient postoperative recovery data includes the following steps:
[0104] Step 1: Monitor and obtain relevant physiological parameters and blood sample data of postoperative patients through several sets of medical equipment;
[0105] Step 2: Preprocess the relevant physiological parameters and related blood sample data, and combine the dimensionless processing technology to unify the units, and finally summarize and generate a recovery state set;
[0106] Step 3: Based on the pre-processed blood sample data, construct the patient's coagulation state coefficient Nzxs and pass the pre-set safety lower limit and safety upper limit , determine the corresponding coagulation instruction issued;
[0107] Step 4: After receiving the coagulation instruction, the parasympathetic nerve activity coefficient Fhxs is constructed based on the relevant physiological parameters after pretreatment, and the postoperative rehabilitation stability index Skzs is obtained by fitting according to the recovery prediction model after training;
[0108] Step 5: pre-set the evaluation threshold L, and compare and analyze the postoperative rehabilitation stability index Skzs with the evaluation threshold L to comprehensively predict the current postoperative patient's recovery degree.
[0109] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. A patient postoperative recovery data analysis system, characterized in that: It includes data monitoring module, data processing module, postoperative instrument introduction analysis module, patient recovery analysis module and control module; The data monitoring module is used to monitor and obtain relevant physiological parameters and relevant blood sample data of postoperative patients through several groups of medical equipment; The data monitoring module includes a monitoring device unit, a first monitoring unit and a second monitoring unit; The monitoring equipment unit is used to perform physical examination on the postoperative patient using several sets of medical equipment, wherein the several sets of medical equipment include an enzyme-linked immunosorbent assay instrument, an automatic blood analyzer, a coagulation analyzer, a respiratory sensor and an electrocardiograph; The first monitoring unit is used to monitor and record relevant physiological parameters of the postoperative patient, wherein the relevant physiological parameters include each continuous RR interval and the respiratory rate Hp in each monitoring period; The second monitoring unit is used to monitor and record the relevant blood sample data of the postoperative patient, wherein the relevant blood sample data includes the platelet count Xjs, the coagulation ratio Nbz, the plasmin concentration and the Fibrin degradation product concentration ; The data processing module is used to pre-process the relevant physiological parameters and relevant blood sample data, and combine the dimensionless processing technology to unify the units, and finally summarize and generate a recovery state set; The data processing module includes a preprocessing unit and a summarizing unit; The preprocessing unit is used to use a convolutional neural network (CNN) and data preprocessing technology to identify and eliminate errors, abnormal values or noise data information of relevant physiological parameters and relevant blood sample data, and to extract features from the data to extract useful feature data; The aggregation unit is used to standardize the relevant data information processed in the preprocessing unit according to the dimensionless processing technology, and use a standardization method to make it have a unified scale, wherein the standardization method includes Z-score standardization, and then aggregate the processed relevant data information into a recovery state set; The postoperative instrument introduction analysis module is used to construct the patient's coagulation state coefficient Nzxs based on the relevant blood sample data after preprocessing, and through the preset safety lower limit and safety upper limit , determine the corresponding coagulation instruction issued; The postoperative instrument introduction analysis module includes a blood status analysis unit and a preliminary judgment unit; The blood state analysis unit includes a first analysis subunit and a second analysis subunit; The first analysis subunit is used to obtain the fibrinolytic activity factor Qhyz in different monitoring periods according to the relevant blood sample data, specifically in the following manner: ; In the formula, Expressed as the concentration of fibrin degradation products, Expressed as plasmin concentration, and All are weight values; The second analysis subunit is used to calculate the coagulation state coefficient Nzxs of the patient in different monitoring periods according to the relevant blood sample data and in combination with the fibrinolytic activity factor Qhyz, which is specifically obtained by the following formula: ; Nbz represents the coagulation ratio, Xjs represents the platelet count, and are expressed as weight values, Expressed as the first correction constant; Among them, the coagulation ratio Nbz is obtained by the following formula: ;in, It is expressed as the actual measured coagulation time. It is expressed as the normal coagulation time; The preliminary judgment unit is used to perform statistics on the coagulation state coefficients Nzxs of the patients in the monitoring period obtained in the second analysis subunit, and combine the statistical algorithm to obtain the average coagulation state coefficients of the patients respectively. and standard deviation of coagulation state coefficient , and based on the patient's average coagulation state coefficient and standard deviation of coagulation state coefficient , set a lower safety limit and safety upper limit , the specific settings are as follows: ; ; In the formula, r is a constant, and the specific value is set by the user; By comparing the patient's coagulation state coefficient Nzxs during the current monitoring period with the safety lower limit and safety upper limit Compare and determine the coagulation state of the wound of the current postoperative patient. The specific determination contents are as follows: If the coagulation state coefficient Nzxs is less than the safety lower limit When the patient is diagnosed with a risk of thrombosis at the wound after surgery, a coagulation instruction will be issued; If the safety limit ≤ coagulation state coefficient Nzxs<safety upper limit When the blood coagulation at the wound of the postoperative patient is judged to be in a normal state, there is no need to issue a blood coagulation instruction; If the coagulation state coefficient Nzxs ≥ the safety upper limit When the patient is diagnosed with bleeding risk after surgery, a blood coagulation command will be issued. The patient recovery analysis module is used to construct the parasympathetic nerve activity coefficient Fhxs according to the relevant physiological parameters after pretreatment after receiving the coagulation instruction, and to obtain the postoperative rehabilitation stability index Skzs by fitting according to the trained recovery prediction model; The patient recovery analysis module includes an activity analysis unit and a comprehensive analysis unit; The activity analysis unit is used to construct the patient's parasympathetic nerve activity coefficient Fhxs based on relevant physiological parameters, which is specifically obtained in the following manner: ; In the formula, It is represented by the total number of RR intervals; i=1, 2, 3, ..., N; M represents the monitoring period; j=1, 2, 3, ..., M-1; is the i+1th RR interval, indicating the time interval between the i+1th heartbeat and the i-th heartbeat; is the i-th RR interval, which indicates the time interval between the i-th heartbeat and the i−1-th heartbeat; is the respiratory rate in the j+1th monitoring period; It is expressed as the respiratory rate in the jth monitoring period; The comprehensive analysis unit is used to construct a recovery prediction model using a convolutional neural network, and input the parasympathetic nerve activity coefficient Fhxs and the coagulation state coefficient Nzxs into the recovery prediction model, and map the corresponding data values in the interval In order to construct the postoperative rehabilitation stability index Skzs, it is obtained in the following way: ; In the formula, and are weight values, Expressed as the second correction constant; The control module is used to pre-set the evaluation threshold L, and compare and analyze the postoperative rehabilitation stability index Skzs with the evaluation threshold L to comprehensively predict the recovery degree of the current postoperative patient; The control module includes a comparison unit and a management unit; The comparison unit is used to compare and analyze the postoperative rehabilitation stability index Skzs with the evaluation threshold L to comprehensively predict the current postoperative patient's recovery degree. The specific contents are as follows: If the postoperative rehabilitation stability index Skzs exceeds the evaluation threshold L, it means that the current postoperative patient's recovery is in a normal state; If the postoperative rehabilitation stability index Skzs does not exceed the evaluation threshold L, it means that the patient's recovery after surgery is not yet in a normal state; The management unit is used to determine and implement corresponding medical interventions based on the analysis results of the comparison unit, and is responsible for recording all intervention measures and their effects, and feeding them back to the cloud platform to optimize the subsequent rehabilitation prediction model; the specific intervention contents are: If the patient is in a normal state, the current rehabilitation plan and medical intervention measures will continue at this time, and no additional intervention is needed; If it is not in a normal state, the patient's rehabilitation treatment plan will be adjusted at this time. Implantable devices or non-invasive technologies will be used to directly stimulate the vagus nerve to enhance the activity of the patient's parasympathetic nerves. At the same time, the coagulation state will be adjusted by taking anticoagulant drugs or supplementing fibrinogen.
2. A method for analyzing patient postoperative recovery data, used to implement the patient postoperative recovery data analysis system described in claim 1, characterized in that: include: Monitor and obtain relevant physiological parameters and blood sample data of postoperative patients through several groups of medical equipment; Preprocess the relevant physiological parameters and blood sample data, and combine the dimensionless processing technology to unify the units, and finally summarize and generate a recovery status set; Based on the pre-processed blood sample data, the patient's coagulation state coefficient Nzxs is constructed and the pre-set safety lower limit is used. and safety upper limit , determine the corresponding coagulation instruction issued; After receiving the coagulation instruction, the parasympathetic nerve activity coefficient Fhxs is constructed based on the relevant physiological parameters after pretreatment, and the postoperative rehabilitation stability index Skzs is fitted based on the trained recovery prediction model; An evaluation threshold L is preset, and the postoperative rehabilitation stability index Skzs is compared and analyzed with the evaluation threshold L to comprehensively predict the current postoperative patient's recovery degree.
Citation Information
Patent Citations
Weight loss surgical post-operative monitoring
CN117043881A
Post-thoracic monitoring and complication prediction
CN117043883A
Intelligent auxiliary system for cardiovascular and cerebrovascular rehabilitation
CN118039165A
Postoperative risk prediction method and system based on big data and artificial intelligence
CN118197615A
Coagulation and fibrinolysis assays
US20200208194A1
