Dynamic hemodynamic parameter management method and device, equipment and medium

Abstract

The invention relates to a dynamic hemodynamic parameter management method and device, equipment and a medium. The method comprises the steps that hemodynamic parameters are monitored; wherein the hemodynamic parameters at least comprise the age of a patient, the maximum value of the chest fluid level, a heart index, the maximum increase rate of the heart index and the maximum increase rate of myocardial contractility; inputting the hemodynamic parameters into a preset decision tree to output mechanical ventilation time; wherein the decision tree is used for representing a decision relation between each hemodynamic parameter and the mechanical ventilation time; the hemodynamic parameters and the mechanical ventilation time are sent to a terminal to be displayed. The clinical decision-making efficiency can be remarkably improved.

Description

Technical Field

[0001] The present disclosure relates to the field of data management technology, and in particular to a method, device, equipment and medium for dynamic hemodynamic parameter management. Background Art

[0002] Traditional monitoring technologies for congenital heart disease have their own shortcomings. For example, invasive monitoring is difficult to use routinely due to its invasiveness and high risk. Echocardiography assesses cardiac function only through static indicators (such as left ventricular ejection fraction and ventricular size), making continuous monitoring impossible. Biomarkers such as N-terminal pro-B-type natriuretic peptide have a detection lag, making it difficult to provide real-time guidance for clinical decision-making.

[0003] In terms of empirical assessment, scoring systems such as the Ross cardiac function classification are highly subjective and lack quantitative standards. Related technologies such as the ICON (Index of Contractility) non-invasive cardiac output monitor, although capable of monitoring hemodynamic parameters, are limited to the data acquisition level. They neither establish a predictive model nor provide intelligent decision-making support, limiting their clinical application value.

[0004] Therefore, the main defects of relevant technologies are reflected in four aspects: first, the intermittent nature of monitoring methods makes it impossible to capture the dynamic changes in cardiac function, which may delay the optimal treatment time; second, traditional prediction models rely on subjective judgment and do not integrate dynamic parameters, so the prediction accuracy is low; third, the raw data output by existing ICON devices lacks automated analysis functions and quantitative decision thresholds, making it difficult to directly guide clinical practice; finally, the monitoring, evaluation and intervention links are separated from each other, failing to form a closed-loop management system, which increases the complexity of clinical operations. Summary of the Invention

[0005] In order to solve the above technical problems, the present disclosure provides a dynamic hemodynamic parameter management method, device, equipment and medium.

[0006] According to one aspect of the present disclosure, a method for dynamic hemodynamic parameter management is provided, the method comprising: Monitoring hemodynamic parameters; wherein the hemodynamic parameters include at least: patient age, maximum pleural fluid level, cardiac index, maximum rate of increase of cardiac index, and maximum rate of increase of myocardial contractility; Inputting the hemodynamic parameters into a preset decision tree to output the mechanical ventilation time; wherein the decision tree is used to represent the decision relationship between each of the hemodynamic parameters and the mechanical ventilation time; The hemodynamic parameters and the mechanical ventilation time are sent to a terminal for display.

[0007] According to another aspect of the present disclosure, a dynamic hemodynamic parameter management device is provided, comprising: A monitoring module for monitoring hemodynamic parameters; wherein the hemodynamic parameters include at least: patient age, maximum pleural fluid level, cardiac index, maximum rate of increase of cardiac index, and maximum rate of increase of myocardial contractility; A decision module, configured to input the hemodynamic parameters into a preset decision tree to output a mechanical ventilation time; wherein the decision tree is configured to represent a decision relationship between each of the hemodynamic parameters and the mechanical ventilation time; The display module is used to send the hemodynamic parameters and the mechanical ventilation time to the terminal for display.

[0008] According to another aspect of the present disclosure, an electronic device is provided, comprising: processor; a memory for storing instructions executable by the processor; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the above-mentioned dynamic hemodynamic parameter management method.

[0009] According to another aspect of the present disclosure, a computer-readable storage medium is provided, wherein the storage medium stores a computer program for executing the above-mentioned dynamic hemodynamic parameter management method.

[0010] The technical solution provided by the embodiments of the present disclosure has the following advantages over the prior art: The technical solution provided by the embodiments of the present disclosure includes: monitoring hemodynamic parameters; wherein the hemodynamic parameters include at least: patient age, maximum pleural fluid level, cardiac index, maximum rate of increase of cardiac index, and maximum rate of increase of myocardial contractility; inputting the hemodynamic parameters into a preset decision tree to output the mechanical ventilation time; wherein the decision tree is used to represent the decision relationship between each hemodynamic parameter and the mechanical ventilation time; and sending the hemodynamic parameters and the mechanical ventilation time to a terminal for display.

[0011] This technical solution builds a full-process automated system that monitors hemodynamic parameters, predicts mechanical ventilation time based on a decision tree, and displays various data, which can significantly improve clinical decision-making efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0013] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0014] Figure 1 This is a flow chart of the dynamic hemodynamic parameter management method according to an embodiment of the present disclosure; Figure 2 This is a schematic diagram of the system architecture described in an embodiment of the present disclosure; Figure 3 A schematic diagram of a decision tree according to an embodiment of the present disclosure; Figure 4 This is a schematic diagram of the structure of the dynamic hemodynamic parameter management device according to an embodiment of the present disclosure; Figure 5 This is a schematic diagram of the structure of the electronic device described in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0015] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features therein can be combined with each other in the absence of conflict.

[0016] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0017] Currently, the main deficiencies in the technologies related to perioperative management of congenital heart disease in infants and young children are reflected in four aspects: First, the intermittent nature of monitoring methods makes it impossible to capture the dynamic changes in cardiac function, which may delay the optimal treatment opportunity; second, traditional prediction models have low prediction accuracy because they rely on subjective judgment and do not integrate dynamic parameters such as the ICON rate (ICONR), cardiac index rate (CIR), and maximum thoracic fluid content (TFCmax); third, the raw data output by existing ICON devices lacks automated analysis functions and quantitative decision thresholds, making it difficult to directly guide clinical practice; finally, the monitoring, evaluation, and intervention links are separated from each other, failing to form a closed-loop management system, which increases the complexity of clinical operations.

[0018] In order to improve at least one of the above-mentioned systemic defects, the present disclosure provides a dynamic hemodynamic parameter management method, device, equipment and medium.

[0019] The present disclosure can be applied to the perioperative management of infants and young children with congenital heart disease, for example, to provide an intelligent and dynamic decision support system. Specifically, the present disclosure aims to solve the following key technical problems: 1) Breaking through the limitations of traditional intermittent monitoring, by continuously and dynamically collecting hemodynamic parameters such as ICONR, CIR, and TFCmax, to track the trend of changes in cardiac function in real time; 2) Compensating for the subjectivity and one-sidedness of existing evaluation methods, building a decision tree, and significantly improving the accuracy of predicting mechanical ventilation time and complication risk; 3) Eliminating clinical decision support faults, and developing an automated decision module with clear quantitative thresholds (such as ICONR ≥ 25%); 4) Integrating existing discrete monitoring-assessment-intervention links to form a closed-loop management system driven by real-time data.

[0020] Figure 1 This is a flow chart of a dynamic hemodynamic parameter management method provided by an embodiment of the present disclosure. This method can be executed by a dynamic hemodynamic parameter management device, which can be implemented using software and / or hardware. Figure 1 As shown, the dynamic hemodynamic parameter management method may include the following steps: S102, monitoring hemodynamic parameters; wherein the hemodynamic parameters include at least: patient age, TFCmax, CI, CIR, and ICONR; S104, inputting the hemodynamic parameters into a preset decision tree to output a duration of mechanical ventilation (DMV); wherein the decision tree is used to represent the influence relationship between each hemodynamic parameter and the duration of mechanical ventilation DMV; S106: Send the hemodynamic parameters and mechanical ventilation time to the terminal for display.

[0021] To better understand the solution, each of the above steps will be described below.

[0022] Regarding step S102 , this embodiment provides a method for monitoring hemodynamic parameters, including the following contents.

[0023] The step of monitoring basic parameters includes: collecting basic parameters of the patient in multiple time windows through a preset monitoring device; wherein the basic parameters include but are not limited to: the basic value, final value and maximum value of the cardiac index CI, the basic value, final value and maximum value of the myocardial contractility ICON, the thoracic fluid level (TFC, thoracic fluid content), and the systolic time ratio (STR, systolic time ratio).

[0024] Specifically, refer to Figure 2 The system architecture shown includes: monitoring device layer, data transmission layer, server layer and terminal layer.

[0025] At the monitoring equipment level, there are monitoring devices such as non-invasive cardiac function monitors and electrocardiogram monitors, which collect basic patient parameters in multiple time windows.

[0026] The time window can be divided into multiple time periods based on the initial period of a patient's hospitalization, such as a baseline period, an adjustment period, and a terminal period. For example, the first day of hospitalization can be used as the baseline period, the second day of hospitalization to the day before surgery can be used as the adjustment period, and the day before surgery can be used as the terminal period.

[0027] During the baseline period, the monitoring device monitors the baseline values ​​of the cardiac index (CI) and the myocardial contractility (ICON), denoted as Baseline CI and Baseline ICON, respectively. It will be appreciated that during the baseline period, the monitoring device can continuously collect a large number of cardiac index values. To mitigate data fluctuations, this embodiment utilizes median filtering to select the median as the baseline value of the cardiac index, thereby improving data accuracy. Similarly, the median of the myocardial contractility (ICON) is selected as the baseline value.

[0028] During the adjustment period, the monitoring device continuously collects real-time values ​​of the cardiac index (CI), myocardial contractility (ICON), and pleural fluid level (TFC). Taking the cardiac index (CI) as an example, a large number of real-time CI values ​​are collected throughout the adjustment period, from which the maximum value needs to be determined. To mitigate transient interference, this embodiment employs a sliding window peak detection algorithm to select the peak value from all real-time CI values ​​during the adjustment period, thereby obtaining the maximum value of the cardiac index (denoted as CImax). Similarly, the maximum value of myocardial contractility (denoted as ICONmax) and the maximum value of pleural fluid level (denoted as TFCmax) can be determined.

[0029] During the terminal period, the monitoring device collects the final value of the cardiac index (CI) (denoted as Final CI), the final value of the myocardial contractility (ICON) (denoted as Final ICON), the final value of the pleural fluid level (TFC) (denoted as Final TFC), and the contraction time ratio (STR). Similar to the baseline period, in this embodiment, to mitigate data fluctuations during the terminal period, the median values ​​of the cardiac index (CI), the median values ​​of the myocardial contractility (ICON), the median values ​​of the pleural fluid level (TFC), and the median values ​​of the contraction time ratio (STR) are selected as the final values ​​of the cardiac index, myocardial contractility (ICON), the final values ​​of the pleural fluid level (TFC), and the final values ​​of the contraction time ratio (STR), thereby improving data accuracy.

[0030] In the above embodiments, the use of median filtering can effectively reduce the impact of motion artifacts and equipment noise, and enhance anti-interference characteristics; the use of a sliding window peak monitoring algorithm can eliminate subjective judgment bias, improve the objectivity of various hemodynamic parameters, and establish an objective quantitative evaluation system based on this.

[0031] After the monitoring device layer collects these basic parameters, it can send them to the server via the data transmission layer. Specifically, the monitoring device layer can output basic parameters such as the baseline, final, and maximum values ​​of the cardiac index (CI), the baseline, final, and maximum values ​​of the myocardial contractility (ICON), the pleural effusion level (TFC), and the contraction time ratio (STR) to the data transmission layer in real time at a preset transmission frequency (e.g., 0.5 Hz).

[0032] The data transmission layer can include a medical-grade gateway that supports both Wi-Fi and Bluetooth dual-mode transmission. The data transmission layer converts the received basic parameters into HL7 FHIR format, encrypts them using a pre-defined encryption protocol (e.g., AES-256+HTTPS), and then uploads the encrypted parameters to the server layer via HTTPS.

[0033] The server layer may include at least one edge computing node, which is used to perform the following steps of calculating dynamic parameters; the edge computing node can also be used to cache various data within a preset time period (such as the last 24 hours) and store historical cases, etc.

[0034] At the server layer, the steps of calculating dynamic parameters include: determining the maximum increase rate CIR of the cardiac index CI based on the maximum value and the baseline value of the cardiac index CI; determining the maximum increase rate ICONR of the myocardial contractility ICON based on the maximum value and the baseline value of the myocardial contractility ICON. Specifically, the maximum increase rate of cardiac index (CIR) and the maximum increase rate of myocardial contractility (ICONR) can represent the degree of improvement in cardiac function after preoperative adjustment. The calculation method is: The maximum increase rate (CIR) of the cardiac index CI is determined by the difference between the maximum value and the baseline value of the cardiac index CI and the percentage of the baseline value of the cardiac index CI according to the following formula (1): CIR =(CImax- Baseline CI) / Baseline CI * 100% (1) According to the following formula (2), the maximum increase rate ICONR of myocardial contractility ICON is determined based on the difference between the maximum value and the basic value of myocardial contractility ICON and the percentage of the basic value of myocardial contractility ICON: ICONR =(ICONmax-Baseline ICON) / Baselinex100% (2) On the server side, Python can be used to calculate dynamic parameters such as the maximum rate of increase of cardiac index (CIR) and the maximum rate of increase of myocardial contractility (ICONR). During the calculation process, a denominator protection mechanism is added to prevent division by zero errors.

[0035] For monitoring hemodynamic parameters, this embodiment further includes the step of collecting auxiliary parameters, namely, collecting auxiliary parameters of the patient; wherein the auxiliary parameters include: patient age, N-terminal pro-Brain Natriuretic Peptide (NT-proBNP) and vital signs displayed by the electrocardiogram monitor.

[0036] In the above embodiment of monitoring hemodynamic parameters, the monitoring equipment can continuously and uninterruptedly collect multiple hemodynamic parameters such as cardiac index CI, myocardial contractility ICON, pleural fluid level TFC, contraction time ratio STR, maximum increase rate of cardiac index CIR, maximum increase rate of myocardial contractility ICONR and maximum value of pleural fluid level TFCmax, which significantly improves the dynamic tracking ability of parameters, breaks through the limitations of existing single parameter monitoring, and realizes real-time tracking of changes in cardiac function.

[0037] In step S104, the hemodynamic parameters are input into a preset decision tree to output the mechanical ventilation time. The decision tree is pre-built and can be directly applied here. The method for constructing the decision tree will be described in subsequent embodiments.

[0038] In this embodiment, the implementation process of step S104 is first described, referring to Figure 3 , which can include the following.

[0039] (1) Input hemodynamic parameters into the preset decision tree.

[0040] (2) Determine whether the patient's age is younger than a preset first age through a decision tree; the first age may be, for example, 6 months in an infant scenario, or more specifically, 6.115 months obtained through accurate calculation.

[0041] (3) If the patient's age is not less than the first age, the predicted mechanical ventilation time is not greater than the first time.

[0042] In practical applications, the mechanical ventilation time DMV is generally divided into 12 hours. Within 12 hours is the DMV normal group, and the mechanical ventilation time exceeds 12 hours is the DMV delayed group. Therefore, in this embodiment, the first time is set to 12 hours.

[0043] Among the reference factors for clinical decision-making, age is the most important predictive factor; children over 6 months old have normal DMV after surgery; children under 3 months old have prolonged DMV; for patients aged 3 to 6 months, the mechanical ventilation time is predicted by combining parameters such as the maximum increase rate of myocardial contractility ICONR, the maximum pleural fluid level TFCmax and the cardiac index CI.

[0044] In this embodiment, when it is determined that the patient's age is not less than the first age (ie, the patient's age is ≥6.115), the mechanical ventilation time is predicted to be no more than the first time (DMV≤12h).

[0045] (4) If the patient's age is younger than the first age and it is determined that the patient's age is younger than a preset second age, the predicted mechanical ventilation time is greater than the first time. The second age is, for example, 3 months in an infant scenario, or more specifically, 3.185 months obtained through accurate calculation.

[0046] In this embodiment, when it is determined that the patient's age is less than the second age (ie, the patient's age is less than 3.185), the mechanical ventilation time is predicted to be greater than the first time (DMV>12h).

[0047] (5) When the patient's age is not less than the second age and less than the first age (i.e., between 3 and 6 months old), determine whether the maximum value of the pleural fluid level TFCmax is less than a preset first threshold (e.g., 43).

[0048] (6) When the maximum value of the pleural fluid level TFCmax is not less than a preset first threshold value (ie, TFCmax ≥ 43), determine whether the maximum increase rate of the cardiac index CIR is less than a preset second threshold value (eg, 0.399).

[0049] (7) If it is less than (i.e., CIR < 0.399), the predicted mechanical ventilation time is greater than the first time (DMV > 12 h).

[0050] (8) If it is not less than (i.e., CIR ≥ 0.399), the predicted mechanical ventilation time is no more than the first time (DMV ≤ 12 h).

[0051] (9) When the maximum value of the pleural fluid level TFCmax is less than the preset first threshold value (i.e., TFCmax < 43), determine whether the maximum increase rate of myocardial contractility ICONR is less than the preset third threshold value (e.g., 25%).

[0052] Specifically, actual research has found that the maximum rate of increase in myocardial contractility (ICONR) has the strongest correlation with cardiac function classification and the highest diagnostic value for assessing the severity of cardiac function impairment. Multivariate analysis has also determined that whether the maximum rate of increase in myocardial contractility (ICONR) reaches 25% is an independent factor affecting cardiac function assessment. Possible reasons include: On the one hand, ICON reflects myocardial contractility and is less susceptible to other factors such as heart rate, volume load, and personal physical signs such as body surface area compared to hemodynamic parameters such as CI; on the other hand, as the effects of cardiotonic, sedative, diuretic, and vasodilation treatments become apparent, the child's heart rate slows, pulmonary blood volume decreases, pulmonary interstitial edema is reduced, and the cardiothoracic ratio decreases. The excessive volume load caused by excessive circulating blood volume is improved, so cardiac output decreases slightly, but myocardial compliance and contractility further improve.

[0053] Based on this, this embodiment uses the maximum increase rate of myocardial contractility ICONR as a judgment condition in the decision tree to determine whether ICONR≥25%.

[0054] (10) If the maximum increase rate of myocardial contractility ICONR is not less than the third threshold (i.e., ICONR ≥ 25%), the predicted mechanical ventilation time is no longer than the first time (DMV ≤ 12 h).

[0055] (11) If the maximum increase rate of myocardial contractility ICONR is less than the third threshold (i.e., ICONR < 25%), it is determined whether the cardiac index CI is less than the preset fourth threshold (e.g., 4.1 L / min / m2).

[0056] (12) If the cardiac index CI is less than the fourth threshold (i.e., CI < 4.1), the predicted mechanical ventilation time is greater than the first time (DMV > 12 h); (13) If the CI is not less than the fourth threshold (i.e., CI ≥ 4.1), the predicted mechanical ventilation time is no longer than the first time (DMV ≤ 12 h).

[0057] According to the embodiment of predicting mechanical ventilation time through a decision tree described in the above steps, patient age is the most important predictive factor. Patients above the first age (6 months) have normal postoperative mechanical ventilation time (DMV≤12h), and patients below the first age (3 months) have normal prolonged postoperative mechanical ventilation time (DMV>12h).

[0058] For patients aged 3 to 6 months: (a) when TFCmax < 43, ICONR ≥ 25% or CI ≥ 4.1 L / min / m2, the patient's postoperative mechanical ventilation duration was normal (DMV ≤ 12 hours); otherwise, the patient's postoperative mechanical ventilation duration was prolonged (DMV > 12 hours). (b) when TFCmax ≥ 43, CIR ≥ 0.399, the patient's postoperative mechanical ventilation duration was normal (DMV ≤ 12 hours); CIR < 0.399, the patient's postoperative mechanical ventilation duration was prolonged (DMV > 12 hours).

[0059] This embodiment is based on multiple important hemodynamic parameters that affect the postoperative mechanical ventilation time, such as patient age, maximum cavity fluid level TFCmax, maximum increase rate of cardiac index CIR, maximum increase rate of myocardial contractility ICONR, and cardiac index CI. The mechanical ventilation time is determined by a decision tree composite decision, which can improve the comprehensiveness and accuracy of the prediction.

[0060] Regarding step S106, in one embodiment, the hemodynamic parameters and mechanical ventilation time are sent to the terminal for display, as shown below.

[0061] Determine whether the mechanical ventilation time is greater than a preset first time; if not, send the hemodynamic parameters and mechanical ventilation time to the terminal for display; If it is greater, it is determined that there is a risk of complications and an alarm message is generated; the hemodynamic parameters, mechanical ventilation time and alarm information are sent to the terminal for display.

[0062] Among them, the application of mechanical ventilation after heart surgery is extremely important, especially for infants and young children. Extubation too early directly affects respiratory function, increases the probability of reintubation, and even causes respiratory and circulatory failure and death; extubation too late increases the incidence of pulmonary complications and prolongs hospitalization, both of which have an adverse effect on surgical prognosis. Early identification of the incidence rate of high-risk patients with prolonged mechanical ventilation time can improve the results. Based on this, this embodiment can determine that there is a risk of complications and generate an alarm message when it is judged that the mechanical ventilation time is greater than the preset first time.

[0063] In this embodiment, the above-mentioned hemodynamic parameters, mechanical ventilation time and alarm information can be displayed at the terminal layer. The terminal layer can include a clinical terminal layer and a mobile terminal layer.

[0064] The clinical terminal layer includes a physician workstation terminal that can display hemodynamic parameters, mechanical ventilation duration, and alarm information. It can also display dynamic trend charts, such as a time-varying trend chart of a specific hemodynamic parameter (e.g., cardiac index (CI)). The terminal also supports multi-parameter overlay comparison, for example, overlaying and comparing monitoring results for the same hemodynamic parameter across different time windows.

[0065] The mobile terminal layer can include mobile workstations, such as mobile phones and computers. These terminals are highly portable, allowing medical staff to access data anytime, anywhere. Similar to the clinical terminal layer, these terminals can display a variety of data, including hemodynamic parameters, mechanical ventilation duration, and alarm information.

[0066] In the above embodiment from steps S102 to S106, a full-process automated system for monitoring, decision-making and display is constructed. During this process, an alarm process is also added, which can significantly improve clinical decision-making efficiency.

[0067] based on Figure 2 The system architecture shown includes a monitoring device layer, a data transmission layer, a server layer, and a terminal layer. The system is based on a modular architecture and standardized data interface, supports rapid docking with multiple types of medical information systems, and can improve the system's scalability.

[0068] Regarding the decision tree in the above embodiment, a decision tree construction process is provided. This embodiment includes: First, multiple hemodynamic indices related to cardiac function were obtained.

[0069] Specifically, based on the electrical cardiometry (EC) hemodynamic indicators that are highly correlated with cardiac function, this embodiment can use multiple hemodynamic indicators such as the patient's age, weight, height, cardiac function grade, NT-proBNp, CI and ICON's respective baseline values ​​and maximum increase rates, TFC maximum value, etc. as principal components for the subsequent principal component analysis.

[0070] Secondly, the correlation between each hemodynamic indicator and mechanical ventilation time was determined through principal component analysis. Then, the principal component indicators were determined from the hemodynamic indicators based on the correlation. Among them, the principal component indicators included: patient age, maximum pleural fluid level TFCmax, cardiac index CI and its maximum increase rate CIR, and maximum increase rate ICONR of myocardial contractility ICON.

[0071] Specifically, in the principal component analysis algorithm, mechanical ventilation duration is the primary clinical factor affecting postoperative recovery, so mechanical ventilation duration was included as an analysis item. Principal component analysis combines hemodynamic indices (principal components) with mechanical ventilation duration (analysis item) to determine the load coefficient between the principal component and the analysis item. The load coefficient indicates the degree of relationship between the principal component and the analysis item. A larger absolute value of the load coefficient indicates a stronger correlation between the hemodynamic indices and mechanical ventilation duration. This effectively extracts principal component indices, including patient age, maximum pleural fluid level (TFCmax), cardiac index (CI) and its maximum increase rate (CIR), and maximum increase rate (ICONR) of myocardial contractility (ICON).

[0072] Finally, a decision path between the principal component index and the mechanical ventilation time is constructed to generate a decision tree. This embodiment can construct a decision path between the principal component index and the mechanical ventilation time based on the influence of the principal component index on the mechanical ventilation time in a large amount of real historical data to generate a decision tree.

[0073] The decision tree constructed through the above embodiment comprehensively considers multiple hemodynamic indicators and effectively extracts the principal component indicator with the greatest correlation, i.e., the one with the greatest impact on mechanical ventilation duration, thereby improving the objectivity, rationality, and accuracy of the decision tree. This principal component indicator is also the hemodynamic parameter input during the actual application of the decision tree.

[0074] In summary, the dynamic hemodynamic parameter management method provided by the embodiment of the present disclosure includes: monitoring hemodynamic parameters; wherein the hemodynamic parameters include at least: patient age, maximum pleural fluid level, cardiac index, maximum rate of increase of cardiac index, maximum rate of increase of myocardial contractility; inputting the hemodynamic parameters into a preset decision tree to output the mechanical ventilation time; wherein the decision tree is used to represent the decision relationship between each of the hemodynamic parameters and the mechanical ventilation time; sending the hemodynamic parameters and the mechanical ventilation time to the terminal for display.

[0075] This technical solution establishes a fully automated system for monitoring hemodynamic parameters, predicting mechanical ventilation duration based on a decision tree, and displaying various data. This system significantly improves clinical decision-making efficiency, achieving a transition from empirical medical care to data-driven decision-making. It provides a safer, more accurate, and more efficient solution for the perioperative management of congenital heart disease in patients, particularly infants and young children.

[0076] In some application scenarios, this technical solution can also be expanded as follows: in terms of application, the evaluation dimension can be enhanced through the integration of ultrasound and biochemical indicators through multimodal data fusion, mobile monitoring terminals can be developed to achieve home monitoring, or intelligent perfusion control can be achieved through linkage with surgical robots.

[0077] Figure 4 This is a schematic diagram of the structure of a dynamic hemodynamic parameter management device provided by an embodiment of the present disclosure, which can be used to implement a dynamic hemodynamic parameter management method. Figure 4 As shown, the dynamic hemodynamic parameter management device may include the following modules: Monitoring module 210, for monitoring hemodynamic parameters; wherein the hemodynamic parameters include at least: patient age, maximum pleural fluid level, cardiac index, maximum rate of increase of cardiac index, and maximum rate of increase of myocardial contractility; A decision module 220 is configured to input the hemodynamic parameters into a preset decision tree to output a mechanical ventilation time; wherein the decision tree is configured to represent a decision relationship between each of the hemodynamic parameters and the mechanical ventilation time; The display module 230 is used to send the hemodynamic parameters and the mechanical ventilation time to a terminal for display.

[0078] In one embodiment, the monitoring module 210 is further configured to: Using pre-set monitoring equipment, basic parameters of the patient are collected in multiple time windows; wherein the basic parameters include: basic value, final value and maximum value of cardiac index, basic value, final value and maximum value of myocardial contractility, pleural fluid level, and contraction time ratio; determining a maximum increase rate of the cardiac index according to the maximum value and the baseline value of the cardiac index; determining a maximum rate of increase of myocardial contractility according to the maximum value and the basal value of the myocardial contractility; Auxiliary parameters of the patient are collected; wherein the auxiliary parameters include: patient age, NT-proBNP and vital signs displayed by an electrocardiogram monitor.

[0079] In one embodiment, the decision module 220 is further configured to: inputting the hemodynamic parameters into a preset decision tree; Determining whether the patient's age is less than a preset first age through the decision tree; If the patient's age is not less than the first age, predicting the mechanical ventilation time to be no longer than the first time; If the patient's age is younger than the first age, and it is determined that the patient's age is younger than a preset second age, the mechanical ventilation time is predicted to be longer than the first time.

[0080] In one embodiment, the decision module 220 is further configured to: If the patient's age is not less than the second age and less than the first age, determining whether the maximum pleural fluid level is less than a preset first threshold; When the maximum value of the pleural fluid level is not less than a preset first threshold, determining whether the maximum rate of increase of the cardiac index is less than a preset second threshold; If it is less than, the mechanical ventilation time is predicted to be greater than the first time; If it is not less than, the mechanical ventilation time is predicted to be no more than the first time.

[0081] In one embodiment, the decision module 220 is further configured to: If the patient's age is not less than the second age and less than the first age, determining whether the maximum pleural fluid level is less than a preset first threshold; When the maximum value of the pleural fluid level is less than a preset first threshold, determining whether the maximum rate of increase of the myocardial contractility is less than a preset third threshold; If it is not less than the third threshold, the mechanical ventilation time is predicted to be no longer than the first time; If it is less than the third threshold, determining whether the cardiac index is less than a preset fourth threshold; If the cardiac index is less than the fourth threshold, predicting the mechanical ventilation time to be greater than the first time; If the cardiac index is not less than the fourth threshold, the mechanical ventilation time is predicted to be no more than the first time.

[0082] In one embodiment, the display module 230 is further configured to: Determining whether the mechanical ventilation time is greater than a preset first time; If not, sending the hemodynamic parameters and the mechanical ventilation time to the terminal for display; If it is greater, it is determined that there is a risk of complications and an alarm message is generated; The hemodynamic parameters, the mechanical ventilation time and the alarm information are sent to a terminal for display.

[0083] In one embodiment, the dynamic hemodynamic parameter management device further includes a decision tree construction module, which is used to: Obtain multiple hemodynamic indicators related to cardiac function; Determining the correlation between each of the hemodynamic indicators and the mechanical ventilation time by principal component analysis; Determining a principal component index from the hemodynamic index based on the correlation; wherein the principal component index includes: the patient's age, the maximum pleural fluid level, the cardiac index and its maximum increase rate, and the maximum increase rate of myocardial contractility; A decision path between the principal component index and the mechanical ventilation time is constructed to generate the decision tree.

[0084] The device provided in this embodiment has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0085] Figure 5 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. Figure 5 As shown, the electronic device 300 includes one or more processors 301 and a memory 302 .

[0086] The processor 301 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 300 to perform desired functions.

[0087] The memory 302 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), a hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 301 may execute the program instructions to implement the dynamic hemodynamic parameter management method of the embodiment of the present disclosure described above and / or other desired functions. Various contents such as input signals, signal components, noise components, etc. may also be stored in the computer-readable storage medium.

[0088] In one example, the electronic device 300 may further include an input device 303 and an output device 304 , and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0089] In addition, the input device 303 may also include, for example, a keyboard, a mouse, and the like.

[0090] The output device 304 can output various information to the outside, including determined distance information, direction information, etc. The output device 304 can include, for example, a display, a speaker, a printer, a communication network and its connected remote output device, etc.

[0091] Of course, to simplify, Figure 5 Only some of the components related to the present disclosure in the electronic device 300 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, the electronic device 300 may further include any other appropriate components according to specific application scenarios.

[0092] Furthermore, this embodiment also provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute the above-mentioned dynamic hemodynamic parameter management method.

[0093] The embodiments of the present disclosure provide a computer program product of a dynamic hemodynamic parameter management method, device, electronic device, and medium, including a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the previous method embodiments. For specific implementation, please refer to the method embodiments and will not be repeated here.

[0094] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0095] The foregoing description is intended only to provide specific embodiments of the present disclosure, intended to enable those skilled in the art to understand and implement the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the embodiments described herein, but rather to be construed in the broadest manner consistent with the principles and novel features disclosed herein.

Claims

1. A method for dynamic hemodynamic parameter management, characterized in that: The method comprises: Monitoring hemodynamic parameters; wherein the hemodynamic parameters include at least: patient age, maximum pleural fluid level, cardiac index, maximum rate of increase of cardiac index, and maximum rate of increase of myocardial contractility; Inputting the hemodynamic parameters into a preset decision tree to output the mechanical ventilation time; wherein the decision tree is used to represent the decision relationship between each of the hemodynamic parameters and the mechanical ventilation time; The hemodynamic parameters and the mechanical ventilation time are sent to a terminal for display.

2. The method according to claim 1, characterized in that The monitoring of hemodynamic parameters includes: Using pre-set monitoring equipment, basic parameters of the patient are collected in multiple time windows; wherein the basic parameters include: basic value, final value and maximum value of cardiac index, basic value, final value and maximum value of myocardial contractility, pleural fluid level, and contraction time ratio; determining a maximum increase rate of the cardiac index according to the maximum value and the baseline value of the cardiac index; determining a maximum rate of increase of myocardial contractility according to the maximum value and the basal value of the myocardial contractility; Auxiliary parameters of the patient are collected; wherein the auxiliary parameters include: patient age, NT-proBNP and vital signs displayed by an electrocardiogram monitor.

3. The method according to claim 1, characterized in that Inputting the hemodynamic parameters into a preset decision tree to output the mechanical ventilation time includes: inputting the hemodynamic parameters into a preset decision tree; Determining whether the patient's age is less than a preset first age through the decision tree; If the patient's age is not less than the first age, predicting the mechanical ventilation time to be no longer than the first time; If the patient's age is younger than the first age, and it is determined that the patient's age is younger than a preset second age, the mechanical ventilation time is predicted to be longer than the first time.

4. The method according to claim 3, characterized in that Inputting the hemodynamic parameters into a preset decision tree to output the mechanical ventilation time includes: If the patient's age is not less than the second age and less than the first age, determining whether the maximum pleural fluid level is less than a preset first threshold; When the maximum value of the pleural fluid level is not less than a preset first threshold, determining whether the maximum rate of increase of the cardiac index is less than a preset second threshold; If it is less than, the mechanical ventilation time is predicted to be greater than the first time; If it is not less than, the mechanical ventilation time is predicted to be no more than the first time.

5. The method according to claim 3, characterized in that Inputting the hemodynamic parameters into a preset decision tree to output the mechanical ventilation time includes: If the patient's age is not less than the second age and less than the first age, determining whether the maximum pleural fluid level is less than a preset first threshold; When the maximum value of the pleural fluid level is less than a preset first threshold, determining whether the maximum rate of increase of the myocardial contractility is less than a preset third threshold; If it is not less than the third threshold, the mechanical ventilation time is predicted to be no longer than the first time; If it is less than the third threshold, determining whether the cardiac index is less than a preset fourth threshold; If the cardiac index is less than the fourth threshold, predicting the mechanical ventilation time to be greater than the first time; If the cardiac index is not less than the fourth threshold, the mechanical ventilation time is predicted to be no more than the first time.

6. The method according to claim 1, characterized in that The sending of the hemodynamic parameters and the mechanical ventilation time to a terminal for display includes: Determining whether the mechanical ventilation time is greater than a preset first time; If not, sending the hemodynamic parameters and the mechanical ventilation time to the terminal for display; If it is greater, it is determined that there is a risk of complications and an alarm message is generated; The hemodynamic parameters, the mechanical ventilation time and the alarm information are sent to a terminal for display.

7. The method according to claim 1, characterized in that The decision tree construction process includes: Obtain multiple hemodynamic indicators related to cardiac function; Determining the correlation between each of the hemodynamic indicators and the mechanical ventilation time by principal component analysis; Determining a principal component index from the hemodynamic index based on the correlation; wherein the principal component index includes: the patient's age, the maximum pleural fluid level, the cardiac index and its maximum increase rate, and the maximum increase rate of myocardial contractility; A decision path between the principal component index and the mechanical ventilation time is constructed to generate the decision tree.

8. A dynamic hemodynamic parameter management device, characterized in that: The device comprises: A monitoring module for monitoring hemodynamic parameters; wherein the hemodynamic parameters include at least: patient age, maximum pleural fluid level, cardiac index, maximum rate of increase of cardiac index, and maximum rate of increase of myocardial contractility; A decision module, configured to input the hemodynamic parameters into a preset decision tree to output a mechanical ventilation time; wherein the decision tree is configured to represent a decision relationship between each of the hemodynamic parameters and the mechanical ventilation time; The display module is used to send the hemodynamic parameters and the mechanical ventilation time to the terminal for display.

9. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed on a terminal device, the terminal device implements the method according to any one of claims 1 to 7.

Images