Hemodynamic data processing method, device and equipment, readable storage medium and program product

Abstract

The invention relates to a hemodynamic data processing method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring synchronous measurement data of various hemodynamic parameters of a target object; performing data anomaly detection on each piece of synchronous measurement data in each pulse period to obtain an anomaly detection result corresponding to each pulse period; if the abnormal data volume of at least one piece of synchronous measurement data in the pulse period does not meet the data recovery condition, data corresponding to the pulse period in the synchronous measurement data is abandoned, and if the abnormal data volume of the synchronous measurement data in the pulse period meets the data recovery condition, data recovery processing is conducted on the abnormal data in the pulse period; and obtaining a synchronous measurement result of the hemodynamic parameters of the target object according to the updated synchronous measurement data. By adopting the method, a high-quality data basis can be provided for evaluation of the automatic cerebral blood flow regulation function.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical data processing, and in particular, to a hemodynamic data processing method and device, computer equipment, computer readable storage medium and computer program product. BACKGROUND

[0002] In the occurrence and development process of cerebrovascular diseases, the hemodynamic characteristics of cerebral blood vessels usually change. Among them, cerebral autoregulation (CA) is an important physiological mechanism for the body to maintain the relative stability of cerebral blood flow. Its functional state can reflect the ability of cerebral blood vessels to maintain relatively constant cerebral blood flow under blood pressure fluctuations, so that by evaluating the function of cerebral autoregulation, it can provide auxiliary information with reference significance for the evaluation and monitoring of cerebrovascular diseases. In related technologies, when evaluating the function of cerebral autoregulation, hemodynamic parameters such as cerebral blood flow and blood pressure are usually measured synchronously. However, the actual data measurement process is easily affected by various factors, resulting in poor quality of collected data, affecting the accuracy and reliability of the evaluation results of cerebral autoregulation. SUMMARY

[0003] Therefore, it is necessary to provide a hemodynamic data processing method, device, computer equipment, computer readable storage medium and computer program product to solve the above technical problems.

[0004] In a first aspect, the present application provides a hemodynamic data processing method, comprising:

[0005] obtaining synchronous measurement data of multiple hemodynamic parameters of a target object; the synchronous measurement data includes synchronously measured cerebral blood flow data and arterial blood pressure data, and the synchronous measurement data covers multiple pulse cycles of the target object;

[0006] performing data anomaly detection on each of the synchronous measurement data in each of the pulse cycles to obtain an anomaly detection result corresponding to each of the pulse cycles;

[0007] if the anomaly detection result indicates that the amount of abnormal data of at least one of the synchronous measurement data in the pulse cycle does not meet the data repair condition, discarding the data corresponding to the pulse cycle in each of the synchronous measurement data to obtain updated synchronous measurement data;

[0008] if the anomaly detection result indicates that the amount of abnormal data of each of the synchronous measurement data in the pulse cycle meets the data repair condition, performing data repair processing on the abnormal data in the pulse cycle to obtain updated synchronous measurement data;

[0009] According to the updated synchronization measurement data, a synchronization measurement result of the hemodynamic parameter of the target object is obtained.

[0010] In one of the embodiments, the data anomaly detection on the synchronization measurement data in each pulse cycle to obtain the anomaly detection result corresponding to the pulse cycle comprises: performing missing value detection on the synchronization measurement data in the pulse cycle to obtain a missing detection result corresponding to the pulse cycle; when the missing detection result indicates that the number of sampling points with missing data in at least one of the synchronization measurement data in the pulse cycle is greater than a first threshold, an anomaly detection result indicating that the amount of abnormal data of the synchronization measurement data does not meet the data repair condition is obtained; when the missing detection result indicates that the number of sampling points with missing data in each of the synchronization measurement data in the pulse cycle is not greater than the first threshold, performing outlier detection on the synchronization measurement data in the pulse cycle to obtain an outlier detection result corresponding to the pulse cycle; when the outlier detection result indicates that the number of sampling points with abnormal data values in at least one of the synchronization measurement data in the pulse cycle is greater than a second threshold, an anomaly detection result indicating that the amount of abnormal data of the synchronization measurement data does not meet the data repair condition is obtained; when the outlier detection result indicates that the number of sampling points with abnormal data values in each of the synchronization measurement data in the pulse cycle is not greater than the second threshold, an anomaly detection result indicating that the amount of abnormal data of each of the synchronization measurement data in the pulse cycle meets the data repair condition is obtained.

[0011] In one of the embodiments, the data repair processing on the abnormal data in the pulse cycle comprises: in the case that there are abnormal sampling points with missing data or abnormal data values in the synchronization measurement data in the pulse cycle, obtaining data estimation values corresponding to each of the abnormal sampling points according to the measurement values of normal sampling points of the synchronization measurement data in the pulse cycle; performing data repair processing on the abnormal sampling points according to the data estimation values to obtain updated synchronization measurement data.

[0012] In one of the embodiments, the obtaining of the synchronization measurement result of the hemodynamic parameter of the target object according to the updated synchronization measurement data comprises: performing filtering and noise reduction processing on the updated synchronization measurement data to obtain processed synchronization measurement data; and obtaining the synchronization measurement result of the hemodynamic parameter of the target object according to the processed synchronization measurement data.

[0013] In one of the embodiments, the cerebral blood flow data comprises left cerebral blood flow velocity data and right cerebral blood flow velocity data, and the arterial blood pressure data comprises left brachial artery blood pressure data and right brachial artery blood pressure data.

[0014] In one of the embodiments, the obtaining the synchronization measurement result of the hemodynamic parameter of the target object according to the updated synchronization measurement data comprises: calculating the cerebral blood flow statistical data and the arterial blood pressure statistical data of the target object in each of the pulse cycles according to the updated synchronization measurement data; and obtaining the synchronization measurement result of the hemodynamic parameter of the target object according to the synchronization measurement data of the target object and the cerebral blood flow statistical data and the arterial blood pressure statistical data in each of the pulse cycles; and the method further comprises: displaying the synchronization measurement result of the target object.

[0015] In a second aspect, the present application further provides a hemodynamic data processing device, comprising:

[0016] a data acquisition module configured to acquire synchronization measurement data of multiple hemodynamic parameters of a target object; the synchronization measurement data comprises synchronization measurement cerebral blood flow data and arterial blood pressure data, and the synchronization measurement data covers multiple pulse cycles of the target object;

[0017] an anomaly detection module configured to perform data anomaly detection on each of the synchronization measurement data in each of the pulse cycles to obtain an anomaly detection result corresponding to each of the pulse cycles;

[0018] a first updating module configured to, if the anomaly detection result indicates that an abnormal data amount of at least one of the synchronization measurement data in the pulse cycle does not meet a data repair condition, discard the data corresponding to the pulse cycle in each of the synchronization measurement data to obtain updated synchronization measurement data;

[0019] a second updating module configured to, if the anomaly detection result indicates that the abnormal data amount of each of the synchronization measurement data in the pulse cycle meets the data repair condition, perform data repair processing on the abnormal data in the pulse cycle to obtain updated synchronization measurement data;

[0020] a result acquisition module configured to obtain a synchronization measurement result of a hemodynamic parameter of the target object according to the updated synchronization measurement data.

[0021] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0022] acquiring synchronization measurement data of multiple hemodynamic parameters of a target object; the synchronization measurement data comprises synchronization measurement cerebral blood flow data and arterial blood pressure data, and the synchronization measurement data covers multiple pulse cycles of the target object;

[0023] perform data anomaly detection on each of the synchronous measurement data in each of the pulse cycles to obtain an anomaly detection result corresponding to each of the pulse cycles;

[0024] If the anomaly detection result indicates that the abnormal data amount of at least one of the synchronous measurement data in the pulse cycle does not meet the data repair condition, discard the data corresponding to the pulse cycle in each of the synchronous measurement data to obtain updated synchronous measurement data;

[0025] If the anomaly detection result indicates that the abnormal data amount of each of the synchronous measurement data in the pulse cycle meets the data repair condition, perform data repair processing on the abnormal data in the pulse cycle to obtain updated synchronous measurement data;

[0026] According to the updated synchronous measurement data, obtain a synchronous measurement result of a hemodynamic parameter of the target object.

[0027] In a fourth aspect, the present application also provides a computer readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the following steps:

[0028] Obtain synchronous measurement data of multiple hemodynamic parameters of a target object; the synchronous measurement data includes synchronously measured cerebral blood flow data and arterial blood pressure data, and the synchronous measurement data covers multiple pulse cycles of the target object;

[0029] Perform data anomaly detection on each of the synchronous measurement data in each of the pulse cycles to obtain an anomaly detection result corresponding to each of the pulse cycles;

[0030] If the anomaly detection result indicates that the abnormal data amount of at least one of the synchronous measurement data in the pulse cycle does not meet the data repair condition, discard the data corresponding to the pulse cycle in each of the synchronous measurement data to obtain updated synchronous measurement data;

[0031] If the anomaly detection result indicates that the abnormal data amount of each of the synchronous measurement data in the pulse cycle meets the data repair condition, perform data repair processing on the abnormal data in the pulse cycle to obtain updated synchronous measurement data;

[0032] According to the updated synchronous measurement data, obtain a synchronous measurement result of a hemodynamic parameter of the target object.

[0033] In a fifth aspect, the present application also provides a computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the following steps:

[0034] synchronous measurement data of a plurality of hemodynamic parameters of a target object; the synchronous measurement data comprises synchronously measured cerebral blood flow data and arterial blood pressure data, and the synchronous measurement data covers a plurality of pulse cycles of the target object;

[0035] performing data anomaly detection on each of the synchronous measurement data in each of the pulse cycles to obtain an anomaly detection result corresponding to each of the pulse cycles;

[0036] if the anomaly detection result indicates that the amount of abnormal data of at least one of the synchronous measurement data in the pulse cycle does not meet the data repair condition, discarding the data corresponding to the pulse cycle in each of the synchronous measurement data to obtain updated synchronous measurement data;

[0037] if the anomaly detection result indicates that the amount of abnormal data of each of the synchronous measurement data in the pulse cycle meets the data repair condition, performing data repair processing on the abnormal data in the pulse cycle to obtain updated synchronous measurement data;

[0038] obtaining synchronous measurement results of the hemodynamic parameters of the target object according to the updated synchronous measurement data.

[0039] The method, device, computer device, computer readable storage medium and computer program product for processing hemodynamic data described above obtain synchronous measurement data of multiple hemodynamic parameters of a target object, the synchronous measurement data comprising synchronous measurement brain blood flow data and arterial blood pressure data and covering multiple pulse cycles of the target object, then perform data anomaly detection on each synchronous measurement data in each pulse cycle to obtain an anomaly detection result corresponding to each pulse cycle, wherein if the anomaly detection result indicates that the amount of abnormal data of at least one synchronous measurement data in the pulse cycle does not meet the data repair condition, the data corresponding to the pulse cycle in each synchronous measurement data is discarded to obtain updated synchronous measurement data, if the anomaly detection result indicates that the amount of abnormal data of each synchronous measurement data in the pulse cycle meets the data repair condition, data repair processing is performed on the abnormal data in the pulse cycle to obtain updated synchronous measurement data, and then a synchronous measurement result of the hemodynamic parameters of the target object is obtained according to the updated synchronous measurement data. In this scheme, after obtaining the synchronous measurement data of multiple hemodynamic parameters, the anomaly of each synchronous measurement data in each pulse cycle is detected by taking the pulse cycle as the processing unit, and whether to retain the synchronous measurement data corresponding to the pulse cycle is determined according to the size of the amount of abnormal data, so that data with too many abnormal values can be discarded and data with fewer abnormal values can be repaired, which can improve the utilization efficiency of data on the basis of improving the quality of synchronous measurement data. Therefore, the synchronous measurement result obtained according to the updated synchronous measurement data can provide a high-quality data basis for subsequent evaluation of the cerebral blood flow autoregulation function, which is beneficial to improving the accuracy of the evaluation result of the cerebral blood flow autoregulation function. BRIEF DESCRIPTION OF DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the description of the embodiments of the present application or the related art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other related drawings can also be obtained without creative labor.

[0041] Figure 1 A flowchart of a method for processing hemodynamic data in an embodiment;

[0042] Figure 2 A flowchart of obtaining an anomaly detection result in an embodiment;

[0043] Figure 3 A structural diagram of a hemodynamic data processing system in an embodiment;

[0044] Figure 4 A structural block diagram of a hemodynamic data processing device in an embodiment;

[0045] Figure 5 Fig. 1 is a schematic diagram of an internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0046] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely intended to explain the present application and not to limit the present application.

[0047] It should be noted that the terms "first", "second", etc. used in the present application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "include" and "have" and any variations thereof used in the present application are intended to cover non-exclusive inclusion. The term "multiple" used in the present application refers to two or more. The term "and / or" used in the present application refers to one of the options or any combination of multiple options.

[0048] In one embodiment, as shown in Figure 1 A method for processing hemodynamic data is provided, and the present embodiment takes the method applied to a terminal as an example. It should be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and can be realized through the interaction of the terminal and the server. In the present embodiment, the method includes the following steps:

[0049] In step S101, the synchronous measurement data of multiple hemodynamic parameters of a target object is obtained. The synchronous measurement data includes brain blood flow data and arterial blood pressure data measured synchronously, and the synchronous measurement data covers multiple pulse cycles of the target object.

[0050] Specifically, the target object can be an object that needs to be measured for hemodynamic parameters. In this step, the synchronous measurement data corresponding to multiple hemodynamic parameters of the target object can be obtained under the authorization of the target object. Exemplarily, the synchronous measurement data can include brain blood flow data measured by transcranial Doppler (TCD) and arterial blood pressure data measured synchronously by continuous wave blood pressure monitoring method. The time span of the synchronous measurement data can cover multiple continuous pulse cycles of the target object.

[0051] In one exemplary embodiment, the brain blood flow data can include left brain blood flow velocity data and right brain blood flow velocity data, and the arterial blood pressure data includes left brachial artery blood pressure data and right brachial artery blood pressure data. Exemplarily, the data recording time label (i.e. sampling point) can be recorded as the left brain blood flow velocity data is recorded as Let the right brain blood flow velocity data be denoted as Let the left brachial artery blood pressure data be denoted as Let the right brachial artery blood pressure data be denoted as .

[0052] In step S102, data anomaly detection is performed on each of the synchronous measurement data in each pulse cycle to obtain an anomaly detection result corresponding to each pulse cycle.

[0053] In this way, for each pulse cycle, a plurality of segments of synchronous measurement data corresponding to the pulse cycle can be obtained.

[0054] For example, the pulse cycle can be determined by analyzing the periodic waveform in the blood flow or blood pressure signal, such as identifying adjacent systolic peaks and taking the time interval between adjacent systolic peaks as the pulse cycle (e.g., T sampling points). In this way, one of the synchronous measurement data can be taken as a reference, and the various synchronous measurement data can be associated according to the signal transmission characteristics between the various synchronous measurement data. For example, in the same pulse cycle (e.g., the kth pulse cycle), the time position of the pulse component in the left brain blood flow signal caused by the heartbeat precedes the corresponding pulse component in the left brachial artery blood pressure signal, so the sampling point corresponding to the peak value of the left brain blood flow velocity data in the kth pulse cycle can be taken as the first feature point of the pulse cycle, and the sampling point corresponding to the first peak value in the left brachial artery blood pressure data that is delayed in time from the first feature point can be taken as the second feature point, so that the feature points of each synchronous measurement data corresponding to the kth pulse cycle can be determined. In this way, the feature points of each synchronous measurement data can be taken as the center, and N1 sampling points in front and N2 sampling points behind in time (where N1+N2+1=T) can be taken to obtain the data segment of each synchronous measurement data corresponding to the kth pulse cycle.

[0055] In this way, for each pulse cycle, data anomaly detection can be performed on each of the synchronous measurement data corresponding to the pulse cycle to obtain an anomaly detection result corresponding to each pulse cycle. For example, data anomaly detection can include one or more of missing value detection, outlier detection, etc. In this way, missing value detection can be used to detect whether each sampling point of each segment of synchronous measurement data corresponding to a pulse cycle has a data missing condition, and outlier detection can be used to detect whether each sampling point of each segment of synchronous measurement data corresponding to a pulse cycle has a data value anomaly condition. In this way, the anomaly detection result corresponding to a pulse cycle can include the sampling points in each synchronous measurement data corresponding to the cycle that have a data anomaly condition, and the total number of sampling points that have a data anomaly condition, etc.

[0056] Specifically, based on the anomaly detection results corresponding to each pulse cycle, it can be determined whether the amount of abnormal data in each segment of synchronous measurement data corresponding to that pulse cycle meets the data repair conditions. If at least one segment of synchronous measurement data corresponding to the same pulse cycle has an abnormal data amount that does not meet the data repair conditions, the process proceeds to step S103; otherwise, it proceeds to step S104. For example, the abnormal data amount can be the total number of sampling points with data anomalies in a segment of synchronous measurement data corresponding to the pulse cycle, and the data repair condition can be that the abnormal data amount is not greater than a preset quantity threshold or proportion threshold.

[0057] Step S103: If the abnormal detection result indicates that the abnormal data amount of at least one synchronous measurement data within the pulse cycle does not meet the data repair conditions, then discard the data corresponding to the pulse cycle in each synchronous measurement data to obtain the updated synchronous measurement data.

[0058] In cases where at least one segment of synchronous measurement data within the same pulse cycle exhibits abnormal data that does not meet the data repair criteria, all synchronous measurement data corresponding to that pulse cycle can be discarded. This involves deleting the data segment corresponding to that pulse cycle from each type of synchronous measurement data, thereby obtaining updated synchronous measurement data. This prevents low-quality synchronous measurement data from being used in subsequent assessments of cerebral blood flow autoregulation, which could affect the accuracy and reliability of the assessment results.

[0059] Step S104: If the abnormal detection result indicates that the amount of abnormal data in each synchronous measurement data within the pulse cycle meets the data repair conditions, then the abnormal data within the pulse cycle is processed for data repair to obtain updated synchronous measurement data.

[0060] If the amount of abnormal data in each segment of synchronous measurement data corresponding to the same pulse cycle meets the data repair conditions, the synchronous measurement data corresponding to that pulse cycle can be retained, and the abnormal data can be repaired. For example, the data repair process for abnormal data may include filling in missing values ​​and modifying outliers. After repairing the abnormal data, updated synchronous measurement data that does not contain abnormal data can be obtained.

[0061] Step S105: Based on the updated synchronous measurement data, obtain the synchronous measurement results of the hemodynamic parameters of the target object.

[0062] Based on the updated synchronous measurement data, the synchronous measurement results of the hemodynamic parameters of the target object can be obtained. For example, the synchronous measurement results may include a graph constructed based on the updated synchronous measurement data of the target object, or information such as cerebral blood flow statistics and arterial blood pressure statistics obtained statistically from the updated synchronous measurement data within each pulse cycle.

[0063] In the aforementioned hemodynamic data processing method, after obtaining synchronous measurement data of multiple hemodynamic parameters, anomalies in each synchronous measurement data within each pulse cycle are detected using the pulse cycle as the processing unit. The retention of synchronous measurement data corresponding to a given pulse cycle is determined based on the magnitude of the abnormal data. This allows for the removal of data with excessive outliers and the repair of data with fewer outliers, improving the quality of synchronous measurement data while ensuring data utilization efficiency. Consequently, the synchronous measurement results obtained from the updated synchronous measurement data provide a high-quality data foundation for subsequent assessments of cerebral blood flow autoregulation function, thus improving the accuracy of the assessment results.

[0064] In one exemplary embodiment, such as Figure 2 As shown, anomaly detection is performed on the synchronous measurement data within each pulse cycle, and the anomaly detection results for each pulse cycle are obtained, including:

[0065] Step S201: Perform missing value detection on each synchronous measurement data within the pulse cycle to obtain the missing value detection result corresponding to the pulse cycle.

[0066] Specifically, for each segment of synchronous measurement data corresponding to each pulse cycle, missing value detection can be performed, and the corresponding missing value detection results can be obtained. For example, when the measurement value corresponding to a certain sampling point in the synchronous measurement data is null, it can be determined that there is a data missing situation at that sampling point. The missing value detection results corresponding to the pulse cycle can be used to indicate the sampling points with missing data in each segment of synchronous measurement data corresponding to that pulse cycle, as well as the number of sampling points with missing data.

[0067] Step S202: When the number of missing sampling points in at least one synchronous measurement data within the pulse cycle indicated by the missing detection result is greater than the first threshold, an abnormal detection result indicating that the abnormal data volume of the synchronous measurement data does not meet the data repair conditions is obtained.

[0068] Each type of synchronous measurement data can have a first threshold set for the number of missing sampling points. For example, this first threshold can be determined based on a preset data missing ratio, such as the proportion of the number of missing sampling points to the total number of sampling points in the pulse cycle not exceeding 5%.

[0069] Specifically, when the number of sampling points with missing data for at least one type of synchronous measurement data in each segment of the pulse cycle exceeds a first threshold corresponding to that type of synchronous measurement data, an anomaly detection result indicating that the amount of abnormal data in the synchronous measurement data does not meet the data repair conditions can be obtained. For example, taking synchronous measurement data including left cerebral blood flow velocity data and left brachial artery blood pressure data as an example, the first threshold corresponding to the left cerebral blood flow velocity data can be denoted as... The first threshold corresponding to the left brachial artery blood pressure data can be denoted as: When the number of missing sampling points in the left brain blood flow velocity data within a pulse cycle is greater than Or, the number of missing sampling points in the left brachial artery blood pressure data is greater than At that time, an anomaly detection result can be obtained indicating that the amount of abnormal data in the synchronous measurement data within the pulse cycle does not meet the data repair conditions.

[0070] Step S203: When the number of missing sampling points in each synchronous measurement data within the pulse cycle is not greater than the first threshold, outlier detection is performed on each synchronous measurement data within the pulse cycle to obtain the outlier detection result corresponding to the pulse cycle.

[0071] Specifically, when the number of missing sampling points in all synchronous measurement data corresponding to each segment of the pulse cycle is no greater than the first threshold corresponding to that type of synchronous measurement data, outlier detection can be further performed on each synchronous measurement data within the pulse cycle to obtain the outlier detection result corresponding to the pulse cycle.

[0072] For example, still taking the synchronous measurement data including left cerebral blood flow velocity data and left brachial artery blood pressure data as an example, when the number of missing sampling points in the left cerebral blood flow velocity data within a pulse cycle is no greater than Furthermore, the number of missing sampling points in the left brachial artery blood pressure data is no greater than [number missing]. At this time, abnormal value detection can be performed on the left brain blood flow velocity data and left brachial artery blood pressure data within the pulse cycle.

[0073] Outlier detection in the synchronous measurement data can involve checking whether the measured value at each sampling point in the synchronous measurement data exceeds a corresponding threshold range. For example, taking the synchronous measurement data as including left cerebral blood flow velocity data and left brachial artery blood pressure data, the left cerebral blood flow velocity data is typically... and Fluctuations within the range, left brachial artery blood pressure data are usually in and The range fluctuates within this range. When the measured value at a certain sampling point in the left brain blood flow velocity data is lower than... or more If so, then the sampling point can be determined as a sampling point with an abnormal data value. Similarly, when the measured value of a sampling point in the left brachial artery blood pressure data is lower than... or more If so, the sampling point can be determined as a sampling point with an abnormal data value. The abnormal value detection result corresponding to the pulse cycle can be used to indicate the sampling points with abnormal data values ​​in each segment of synchronous measurement data corresponding to that pulse cycle, as well as the number of sampling points with abnormal data values.

[0074] Step S204: When the number of sampling points with abnormal data values ​​in at least one synchronous measurement data within the pulse cycle indicated by the abnormal value detection result is greater than the second threshold, an abnormal detection result indicating that the amount of abnormal data in the synchronous measurement data does not meet the data repair conditions is obtained.

[0075] Each type of synchronous measurement data can have a second threshold set for the number of sampling points with abnormal data values. For example, this second threshold can be determined based on a preset data missing ratio, such as the proportion of the number of sampling points with abnormal data values ​​to the total number of sampling points in the pulse cycle not exceeding 5%.

[0076] Specifically, when the number of sampling points with abnormal data values ​​in at least one of the synchronous measurement data segments corresponding to the pulse cycle is greater than the second threshold corresponding to that synchronous measurement data, an abnormal detection result indicating that the amount of abnormal data in the synchronous measurement data does not meet the data repair conditions can be obtained.

[0077] For example, taking the synchronous measurement data including left cerebral blood flow velocity data and left brachial artery blood pressure data as an example, the second threshold corresponding to the left cerebral blood flow velocity data can be denoted as: The second threshold corresponding to the left brachial artery blood pressure data can be denoted as: When the number of sampling points with abnormal data values ​​in the left brain blood flow velocity data within a pulse cycle is greater than Or, the number of sampling points with abnormal data values ​​in the left brachial artery blood pressure data is greater than [a certain number]. At that time, an anomaly detection result can be obtained indicating that the amount of abnormal data in the synchronous measurement data within the pulse cycle does not meet the data repair conditions.

[0078] Step S205: When the number of sampling points with abnormal data values ​​in each synchronous measurement data within the pulse cycle indicated by the abnormal value detection result is not greater than the second threshold, an abnormal detection result is obtained in which the abnormal data volume of each synchronous measurement data within the pulse cycle meets the data repair conditions.

[0079] Specifically, when the number of sampling points with abnormal data values ​​in all synchronous measurement data corresponding to each segment of the pulse cycle is not greater than the second threshold corresponding to that type of synchronous measurement data, an abnormal detection result indicating that the amount of abnormal data in each synchronous measurement data within that pulse cycle meets the data repair conditions can be obtained.

[0080] In this embodiment, by first detecting missing values ​​in the synchronous measurement data and then detecting outliers after the detection passes, synchronous measurement data with a large amount of missing data can be excluded in advance, which helps to improve the efficiency of data anomaly detection.

[0081] In an exemplary embodiment, data repair processing for abnormal data within the pulse cycle includes: when there are abnormal sampling points with missing data or abnormal data values ​​in the synchronous measurement data within the pulse cycle, obtaining the data estimate value corresponding to each abnormal sampling point based on the measurement value of the normal sampling point in the synchronous measurement data within the pulse cycle; and performing data repair processing on the abnormal sampling points based on the data estimate value to obtain updated synchronous measurement data.

[0082] Specifically, if the amount of abnormal data in each synchronous measurement data within the pulse cycle meets the data repair conditions, the abnormal data in the pulse cycle can be repaired.

[0083] First, based on the anomaly detection results corresponding to the pulse cycle, identify the abnormal sampling points with missing data and abnormal data values ​​in each segment of synchronous measurement data corresponding to the pulse cycle, as well as the normal sampling points without data anomalies. Then, for each segment of synchronous measurement data with abnormal sampling points in the pulse cycle, estimate the measurement values ​​of each abnormal sampling point using the measurement values ​​of the normal sampling points in that segment of synchronous measurement data to obtain the estimated data value corresponding to each abnormal sampling point. Finally, perform data repair processing on the abnormal sampling points. For example, methods for estimating the measurement values ​​of each abnormal sampling point may include, but are not limited to, mean imputation, hot-calorie imputation, nearest neighbor imputation, and model prediction imputation.

[0084] For example, for outlier sampling points with missing data, data restoration processing can be used as the estimated value of the data corresponding to that sampling point as the measured value of that sampling point. For example, for outlier sampling points with abnormal data values, data restoration processing can be used to replace the original measured value (i.e., the measured value with abnormal data value) corresponding to that sampling point with the estimated value of that sampling point.

[0085] After completing the data repair process for all abnormal sampling points, updated synchronous measurement data can be obtained.

[0086] In this embodiment, by estimating the estimated values ​​of abnormal sampling points based on the measured values ​​of normal sampling points in the synchronous measurement data, the abnormal data can be repaired by combining the real data patterns of the synchronous measurement data, which is beneficial to obtaining more accurate and meaningful synchronous measurement data.

[0087] In an exemplary embodiment, obtaining the synchronous measurement results of the hemodynamic parameters of the target object based on the updated synchronous measurement data includes: performing filtering and noise reduction processing on the updated synchronous measurement data to obtain processed synchronous measurement data; and obtaining the synchronous measurement results of the hemodynamic parameters of the target object based on the processed synchronous measurement data.

[0088] Since synchronous measurements of hemodynamic data are prone to random noise and high-frequency noise, this embodiment can first perform filtering and noise reduction processing on the updated synchronous measurement data to remove noise from the data. Then, based on the processed synchronous measurement data, the synchronous measurement results of the hemodynamic parameters of the target object can be obtained. For example, the filtering and noise reduction processing on the updated synchronous measurement data can include smoothing filtering and low-pass filtering. Smoothing filtering can be performed using methods such as mean filtering, median filtering, weighted moving average, and exponentially weighted moving average, while low-pass filtering can be performed using filters such as Butterworth filters and Chebyshev filters.

[0089] In this embodiment, by filtering and denoising the synchronous measurement data, noise in the synchronous measurement data can be removed, resulting in more accurate synchronous measurement data.

[0090] In an exemplary embodiment, obtaining the synchronous measurement results of the hemodynamic parameters of the target object based on the updated synchronous measurement data may include: calculating the cerebral blood flow statistics and arterial blood pressure statistics of the target object in each pulse cycle based on the updated synchronous measurement data; obtaining the synchronous measurement results of the hemodynamic parameters of the target object based on the synchronous measurement data of the target object and the cerebral blood flow statistics and arterial blood pressure statistics in each pulse cycle; the method may further include: displaying the synchronous measurement results of the target object.

[0091] After obtaining the updated synchronous measurement data, the system can calculate the cerebral blood flow statistics and arterial blood pressure statistics of the target object within each pulse cycle, based on the synchronous measurement data corresponding to each pulse cycle. For example, the cerebral blood flow statistics may include the maximum, minimum, and average values ​​of cerebral blood flow, and the arterial blood pressure statistics may include the maximum, minimum, and average values ​​of arterial blood pressure. Subsequently, a synchronous measurement result containing the synchronous measurement data and the cerebral blood flow statistics and arterial blood pressure statistics within each pulse cycle can be obtained.

[0092] Once the synchronous measurement results of the hemodynamic parameters of the target object are obtained, they can be visualized. For example, the updated curves corresponding to each synchronous measurement data of the target object, as well as various cerebral blood flow statistics and arterial blood pressure statistics in each pulse cycle can be displayed.

[0093] In one exemplary embodiment, a method for processing hemodynamic data is provided.

[0094] Specifically, the hemodynamic data processing method in this embodiment can be achieved through, for example... Figure 3 The hemodynamic data processing system shown includes a data import module, a data reading module, a period interpretation module, a data missing detection module, a data exceeding threshold detection module, a data deletion module, a data imputation module, a filtering module, a data alignment module, and a result generation module.

[0095] The system can import synchronously measured data of various hemodynamic parameters of the target object using a data import module. This data can include synchronously measured left cerebral blood flow velocity, right cerebral blood flow velocity, left brachial artery blood pressure, and right brachial artery blood pressure. Cerebral blood flow velocity data can be measured using transcranial Doppler (TCD), and arterial blood pressure data can be measured using continuous wave-by-wave blood pressure monitoring. Subsequently, the synchronously measured data can be read using a data reading module. The data recording time stamp (i.e., sampling point) can be recorded as... The blood flow velocity data of the left brain is recorded as The blood flow velocity data of the right brain is recorded as Record the left brachial artery blood pressure data as Record the right brachial artery blood pressure data as .

[0096] The system utilizes a cycle interpretation module to mark data segments corresponding to different pulse cycles based on synchronous measurements of cerebral blood flow and brachial artery blood pressure, and associates each segment of synchronous measurement data according to its corresponding pulse cycle. For example, the cycle interpretation module can determine the pulse cycle through human-computer interaction. For instance, it can display multiple consecutive cycles of cerebral blood flow data as curves, allowing users to zoom in, zoom out, and observe specific areas of the cerebral blood flow data to determine the pulse cycle, with T data measurement points constituting one pulse cycle.

[0097] The system can process the synchronous measurement data corresponding to each pulse cycle in sequence.

[0098] For example, taking the synchronous measurement data corresponding to the k-th pulse cycle as an example, the system can use the data missing detection module to perform missing value detection on each synchronous measurement data within the k-th pulse cycle, and obtain the missing detection result corresponding to the k-th pulse cycle. When the missing detection result indicates that the number of missing sampling points in at least one synchronous measurement data within the k-th pulse cycle is greater than a first threshold, an anomaly detection result indicating that the abnormal data volume of the synchronous measurement data does not meet the data repair conditions can be obtained. Wherein, when the missing detection result indicates that the number of missing sampling points in each synchronous measurement data within the k-th pulse cycle is not greater than the first threshold, the data exceeding the threshold detection module can be further used to perform anomaly detection on the synchronous measurement data corresponding to the k-th pulse cycle. Specifically, when the outlier detection result indicates that the number of sampling points with abnormal data values ​​in at least one synchronous measurement data within the k-th pulse cycle is greater than the second threshold, an outlier detection result indicating that the amount of abnormal data in the synchronous measurement data does not meet the data repair conditions can be obtained. Conversely, when the outlier detection result indicates that the number of sampling points with abnormal data values ​​in each synchronous measurement data within the k-th pulse cycle is not greater than the second threshold, an outlier detection result indicating that the amount of abnormal data in each synchronous measurement data within the k-th pulse cycle meets the data repair conditions can be obtained.

[0099] Specifically, when the data missing detection module or the data exceeding the threshold detection module outputs an abnormal detection result indicating that the amount of abnormal data in the synchronous measurement data does not meet the data repair conditions, the data deletion module can be used to delete the synchronous measurement data segments corresponding to the k-th pulse cycle. After this part is executed, k = k + 1, and the data processing process for the next pulse cycle (k + 1) can begin.

[0100] Specifically, when the data over-threshold detection module outputs an anomaly detection result indicating that the amount of abnormal data in each synchronous measurement data within the k-th pulse cycle meets the data repair conditions, the data filling module can be used to repair the abnormal data within the k-th pulse cycle, obtaining updated synchronous measurement data. Subsequently, the filtering module can be used to filter and reduce noise in each updated synchronous measurement data, obtaining processed synchronous measurement data. Then, the data alignment module can be used to shift the left brachial artery blood pressure data within the k-th pulse cycle to the left, using the maximum left cerebral blood flow value as a reference, so that the maximum left cerebral blood flow value and the maximum left brachial artery blood pressure value are aligned within this pulse cycle. Then, N1 data points are taken to the left and N2 data points to the right, respectively, centered on the maximum left cerebral blood flow value and the maximum left brachial artery blood pressure value, thus forming a cerebral blood flow measurement cycle and an arterial blood pressure measurement cycle consisting of N1+N2+1 points.

[0101] The data processing module, including the missing data detection module, the data over-threshold detection module, the data filling module, and the data alignment module, can complete the processing of the synchronous measurement data of each segment corresponding to the kth pulse cycle and then proceed to the data processing process of the next pulse cycle (k+1).

[0102] After processing data for all pulse cycles, the results generation module can calculate the maximum, minimum, and average cerebral blood flow values ​​for the target object in each pulse cycle, as well as the maximum, minimum, and average arterial blood pressure values, based on the processed synchronous measurement data. Subsequently, the synchronous measurement data of the target object can be displayed in the form of cerebral blood flow curves and brachial artery blood pressure curves, along with statistical data on cerebral blood flow and arterial blood pressure for each pulse cycle. Simultaneously, data reports can be generated and stored according to a specific format based on this information.

[0103] In this embodiment, to address the operational issues such as large measurement errors often encountered when simultaneously measuring cerebral blood flow and brachial artery blood pressure, the implementation steps of data import, data reading, anomaly detection, data deletion and filling, data alignment, and data reporting are adopted to achieve simultaneous measurement of cerebral blood flow and brachial artery blood pressure and automatic preprocessing of batch data. This enables the establishment of intuitive and accurate cerebral blood flow and brachial artery blood pressure curves, providing good data conditions for further diagnosis and treatment of cerebrovascular diseases.

[0104] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0105] Based on the same inventive concept, this application also provides a hemodynamic data processing apparatus for implementing the hemodynamic data processing method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more embodiments of the hemodynamic data processing apparatus provided below can be found in the limitations of the hemodynamic data processing method described above, and will not be repeated here.

[0106] In one exemplary embodiment, such as Figure 4 As shown, a hemodynamic data processing device is provided, comprising:

[0107] The data acquisition module 401 is used to acquire synchronous measurement data of multiple hemodynamic parameters of the target object; the synchronous measurement data includes synchronously measured cerebral blood flow data and arterial blood pressure data, and the synchronous measurement data covers multiple pulse cycles of the target object;

[0108] Anomaly detection module 402 is used to perform data anomaly detection on the synchronous measurement data within each pulse cycle and obtain anomaly detection results corresponding to each pulse cycle.

[0109] The first update module 403 is used to discard the data corresponding to the pulse cycle in each of the synchronous measurement data if the abnormal detection result indicates that the abnormal data amount of at least one of the synchronous measurement data within the pulse cycle does not meet the data repair conditions, and obtain the updated synchronous measurement data.

[0110] The second update module 404 is used to perform data repair processing on the abnormal data in the pulse cycle if the abnormal detection result indicates that the abnormal data amount of each of the synchronous measurement data in the pulse cycle meets the data repair conditions, so as to obtain updated synchronous measurement data.

[0111] The result acquisition module 405 is used to obtain the synchronous measurement results of the hemodynamic parameters of the target object based on the updated synchronous measurement data.

[0112] In an exemplary embodiment, the anomaly detection module 402 is configured to: perform missing value detection on each of the synchronous measurement data within the pulse cycle to obtain a missing value detection result corresponding to the pulse cycle; when the missing value detection result indicates that the number of missing sampling points in at least one of the synchronous measurement data within the pulse cycle is greater than a first threshold, obtain an anomaly detection result indicating that the abnormal data volume of the synchronous measurement data does not meet the data repair conditions; when the missing value detection result indicates that the number of missing sampling points in each of the synchronous measurement data within the pulse cycle is not greater than the first threshold, perform anomaly detection on each of the synchronous measurement data within the pulse cycle to obtain an anomaly detection result corresponding to the pulse cycle; when the anomaly detection result indicates that the number of sampling points with abnormal data values ​​in at least one of the synchronous measurement data within the pulse cycle is greater than a second threshold, obtain an anomaly detection result indicating that the abnormal data volume of the synchronous measurement data does not meet the data repair conditions; and when the anomaly detection result indicates that the number of sampling points with abnormal data values ​​in each of the synchronous measurement data within the pulse cycle is not greater than the second threshold, obtain an anomaly detection result indicating that the abnormal data volume of each of the synchronous measurement data within the pulse cycle meets the data repair conditions.

[0113] In an exemplary embodiment, the second update module 404 is configured to: in the case that there are abnormal sampling points with missing data or abnormal data values ​​in the synchronous measurement data within the pulse cycle, obtain the data estimate value corresponding to each abnormal sampling point based on the measurement value of the normal sampling point in the pulse cycle of the synchronous measurement data; and perform data repair processing on the abnormal sampling points based on the data estimate value to obtain updated synchronous measurement data.

[0114] In an exemplary embodiment, the result acquisition module 405 is configured to: perform filtering and noise reduction processing on the updated synchronous measurement data to obtain processed synchronous measurement data; and obtain the synchronous measurement results of the hemodynamic parameters of the target object based on the processed synchronous measurement data.

[0115] In one exemplary embodiment, the cerebral blood flow data includes left brain blood flow velocity data and right brain blood flow velocity data, and the arterial blood pressure data includes left brachial artery blood pressure data and right brachial artery blood pressure data.

[0116] In an exemplary embodiment, the result acquisition module 405 is configured to: calculate cerebral blood flow statistics and arterial blood pressure statistics of the target object in each pulse cycle based on the updated synchronous measurement data; obtain synchronous measurement results of hemodynamic parameters of the target object based on the synchronous measurement data of the target object and the cerebral blood flow statistics and arterial blood pressure statistics in each pulse cycle; the device further includes: a result display module, configured to display the synchronous measurement results of the target object.

[0117] Each module in the aforementioned hemodynamic data processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0118] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When executed by the processor, the computer program implements a method for processing hemodynamic data. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0119] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0120] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0121] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0122] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0123] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0124] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0125] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0126] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for processing hemodynamic data, characterized in that, The method includes: Acquire synchronous measurement data of multiple hemodynamic parameters of the target object; the synchronous measurement data includes synchronously measured cerebral blood flow data and arterial blood pressure data, and the synchronous measurement data covers multiple pulse cycles of the target object; Data anomaly detection is performed on the synchronous measurement data within each pulse cycle to obtain the anomaly detection result corresponding to each pulse cycle; If the anomaly detection result indicates that the amount of abnormal data in at least one of the synchronous measurement data within the pulse cycle does not meet the data repair conditions, then the data corresponding to the pulse cycle in each of the synchronous measurement data is discarded to obtain updated synchronous measurement data. If the anomaly detection result indicates that the amount of abnormal data in each of the synchronous measurement data within the pulse cycle meets the data repair conditions, then the abnormal data within the pulse cycle is subjected to data repair processing to obtain updated synchronous measurement data. Based on the updated synchronous measurement data, the synchronous measurement results of the hemodynamic parameters of the target object are obtained.

2. The method according to claim 1, characterized in that, The step of performing data anomaly detection on the synchronous measurement data within each pulse cycle to obtain anomaly detection results corresponding to each pulse cycle includes: Missing values ​​are detected for each of the synchronous measurement data within the pulse cycle to obtain the missing detection result corresponding to the pulse cycle; When the missing detection result indicates that the number of sampling points with missing data in at least one of the synchronous measurement data within the pulse cycle is greater than a first threshold, an abnormal detection result is obtained indicating that the amount of abnormal data in the synchronous measurement data does not meet the data repair conditions. When the missing data detection result indicates that the number of missing sampling points in each of the synchronous measurement data within the pulse cycle is not greater than the first threshold, outlier detection is performed on each of the synchronous measurement data within the pulse cycle to obtain the outlier detection result corresponding to the pulse cycle. When the number of sampling points in the synchronous measurement data within the pulse cycle that indicate abnormal data values ​​in the abnormal value detection result is greater than the second threshold, an abnormal detection result indicating that the amount of abnormal data in the synchronous measurement data does not meet the data repair conditions is obtained. When the outlier detection result indicates that the number of sampling points with abnormal data values ​​in each of the synchronous measurement data within the pulse cycle is not greater than the second threshold, an outlier detection result is obtained indicating that the amount of abnormal data in each of the synchronous measurement data within the pulse cycle meets the data repair conditions.

3. The method according to claim 2, characterized in that, The data repair process for abnormal data within the pulse cycle includes: In the event that there are abnormal sampling points with missing data or abnormal data values ​​in the synchronous measurement data within the pulse cycle, the estimated data value corresponding to each abnormal sampling point is obtained based on the measurement value of the normal sampling point within the pulse cycle of the synchronous measurement data. Based on the estimated data, the abnormal sampling points are repaired to obtain updated synchronous measurement data.

4. The method according to claim 1, characterized in that, The process of obtaining the synchronous measurement results of the hemodynamic parameters of the target object based on the updated synchronous measurement data includes: The updated synchronous measurement data are filtered and denoised to obtain the processed synchronous measurement data. Based on the processed synchronous measurement data, the synchronous measurement results of the hemodynamic parameters of the target object are obtained.

5. The method according to claim 1, characterized in that, The cerebral blood flow data includes left brain blood flow velocity data and right brain blood flow velocity data, and the arterial blood pressure data includes left brachial artery blood pressure data and right brachial artery blood pressure data.

6. The method according to any one of claims 1 to 5, characterized in that, The process of obtaining the synchronous measurement results of the hemodynamic parameters of the target object based on the updated synchronous measurement data includes: Based on the updated synchronous measurement data, calculate the cerebral blood flow statistics and arterial blood pressure statistics of the target object during each pulse cycle; Based on the synchronous measurement data of the target object and the cerebral blood flow statistics and arterial blood pressure statistics in each pulse cycle, the synchronous measurement results of the hemodynamic parameters of the target object are obtained; The method further includes: The synchronous measurement results of the target object are displayed.

7. A hemodynamic data processing device, characterized in that, The device includes: The data acquisition module is used to acquire synchronous measurement data of multiple hemodynamic parameters of the target object; the synchronous measurement data includes synchronously measured cerebral blood flow data and arterial blood pressure data, and the synchronous measurement data covers multiple pulse cycles of the target object; An anomaly detection module is used to perform data anomaly detection on the synchronous measurement data within each pulse cycle, and obtain the anomaly detection result corresponding to each pulse cycle. The first update module is used to discard the data corresponding to the pulse cycle in each of the synchronous measurement data if the abnormal detection result indicates that the abnormal data amount of at least one of the synchronous measurement data within the pulse cycle does not meet the data repair conditions, and obtain the updated synchronous measurement data. The second update module is used to perform data repair processing on the abnormal data in the pulse cycle if the abnormal detection result indicates that the abnormal data amount of each of the synchronous measurement data in the pulse cycle meets the data repair conditions, so as to obtain updated synchronous measurement data. The result acquisition module is used to obtain the synchronous measurement results of the hemodynamic parameters of the target object based on the updated synchronous measurement data.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images