An Adaptive Data Acquisition and Integration Method for Capturing Critical Core Monitoring Clusters

Abstract

The present invention discloses a data acquisition and integration method for adaptively capturing a core monitoring cluster in critical care, which relates to the technical field of medical monitoring. The method includes: Step 1, evaluating the change index and change correlation index of the core monitoring data, and dynamically adjusting the acquisition frequency of the core monitoring data according to the change index and change correlation index; Step 2, acquiring the core monitoring data according to the adjusted acquisition frequency, considering the network situation, and packaging the acquired core monitoring data in combination with the adjusted acquisition frequency to obtain a core monitoring data packet; Step 3, sending the core monitoring data packet to a monitoring terminal. The present invention proposes a data acquisition and integration method for adaptively capturing a core monitoring cluster in critical care, which can dynamically adjust the data acquisition frequency and packaging strategy according to the change situation of the monitoring data and the network condition, and ensure the efficient and accurate transmission of the core monitoring data.

Description

Technical Field

[0001] The present invention relates to the technical field of medical monitoring, and particularly to a data acquisition and integration method for adaptively capturing a core monitoring cluster in critical care. Background Art

[0002] Traditional data acquisition methods in intensive care often use fixed sampling rates and packet sizes. Although this method is simple and easy to implement, it has many limitations. First, the fixed sampling rate cannot be dynamically adjusted according to the actual physiological state of the patient, resulting in a large amount of redundant data when the patient's condition is stable, and may miss key information when the condition suddenly changes. Second, the fixed packet size may cause data loss or transmission delay in case of poor network conditions, affecting the timely judgment of the patient's condition. Summary of the Invention

[0003] In view of the deficiencies in the prior art, the present invention proposes a data acquisition and integration method for adaptively capturing a core monitoring cluster in critical care, which can dynamically adjust the data acquisition frequency and packaging strategy according to the changes in monitoring data and network conditions to ensure the efficient and accurate transmission of core monitoring data.

[0004] The technical solution of the present invention: A data acquisition and integration method for adaptively capturing a core monitoring cluster in critical care, comprising:

[0005] Step 1, evaluating the change index and change correlation index of the core monitoring data, and dynamically adjusting the acquisition frequency of the core monitoring data according to the change index and change correlation index;

[0006] Step 2, acquiring the core monitoring data according to the adjusted acquisition frequency, considering the network situation, and packaging the acquired core monitoring data in combination with the adjusted acquisition frequency to obtain core monitoring data packets;

[0007] Step 3, sending the core monitoring data packets to the monitoring terminal.

[0008] Preferably, before step 1, it includes:

[0009] Step 001, setting an acquisition threshold for each type of monitoring data, and the acquisition threshold is used to trigger the acquisition of core monitoring data;

[0010] Step 002, acquiring the historical monitoring data of each type of monitoring data, making a prediction according to the historical monitoring data to obtain a monitoring prediction value, calculating the difference between the monitoring prediction value and the monitoring actual value, and dynamically adjusting the acquisition threshold according to the difference;

[0011] Step 003, when the monitoring data is not within the adjusted acquisition threshold, determining the monitoring data as core monitoring data and triggering the acquisition of core monitoring data.

[0012] Preferably, in step 1, the evaluation method of the change index includes:

[0013] Step 01: Determine the length of a sliding window, which is used to calculate the time correlation of the core monitoring data at each time point;

[0014] Step 02: For each time point in the historical core monitoring data, calculate the mean and standard deviation of the data within the sliding window;

[0015] Step 03: Within the sliding window, for each core monitoring data, calculate the product of its standard deviation difference from the current core monitoring data and sum them to obtain the time correlation index. Calculate the ratio of the second derivative to the first derivative of the data to determine the data change rate. Determine the change index based on the data change rate and the time correlation coefficient.

[0016] Preferably, in step 1, the method for evaluating the change correlation index includes:

[0017] Step 04: Sort the change indexes of various types of core monitoring data in descending order and perform normalization to obtain a change index sequence;

[0018] Step 05: Calculate the correlation coefficient between two change indexes in the change index sequence;

[0019] Step 06: Based on the change index and the correlation coefficient, construct an association graph. The association graph uses the core monitoring data as points and determines the edges based on the difference between the correlation coefficient and a preset coefficient threshold. When the difference is greater than zero, there is an edge. Modify the correlation coefficient according to the association graph to obtain the change correlation index.

[0020] Preferably, the formula for modifying the correlation coefficient according to the association graph to obtain the change correlation index is:

[0021]

[0022] In the formula, represents the change correlation index, represents the correlation coefficient of the th type of core monitoring data, represents the total number of core monitoring data, represents the th type of core monitoring data with an edge connection to the th type of core monitoring data, represents the total number of the th type of core monitoring data with an edge connection to the th type of core monitoring data.

[0023] Preferably, the sampling parameter includes the sampling frequency. The formula for dynamically adjusting the sampling parameter of the core monitoring data according to the change index and the change correlation index is as follows:

[0024]

[0025] In the formula, represents the sampling frequency of the th type of core monitoring data at the current time t, represents the sampling frequency of the th type of core monitoring data at the previous time, represents the change index of the th type of core monitoring data, represents the importance weight of the th type of core monitoring data, is a constant coefficient.

[0026] Preferably, in step 2, considering the network situation and combining the adjusted sampling frequency, the core monitoring data collected is packaged, including:

[0027] Step 021: Dynamically adjust the coding packet size according to the current network bandwidth, average network bandwidth, adjusted sampling frequency, and maximum sampling frequency;

[0028] Step 022: Determine the compression parameter according to the adjusted sampling frequency and coding packet size, compress the core monitoring data according to the compression parameter, and perform random linear coding on the compressed data to obtain the core monitoring data packet.

[0029] Preferably, in step 021, the formula for dynamically adjusting the coding packet size according to the current network bandwidth, average network bandwidth, adjusted sampling frequency, and maximum sampling frequency is as follows:

[0030]

[0031] In the formula, represents the coding packet size of the th type of core monitoring data packet at the current time t, represents the coding packet size of the th type of core monitoring data at the previous time, represents the sampling frequency of the th type of core monitoring data at the current time t, that is, the adjusted sampling frequency, represents the preset maximum sampling frequency of the th type of core monitoring data, represents the current network bandwidth, represents the average network bandwidth,

[0032] The data acquisition and integration method for adaptively capturing the critical care core monitoring cluster proposed by the present invention demonstrates significant superiority and practicality compared with traditional technologies, which is specifically reflected in the following aspects:

[0033] 1) Efficient data acquisition: By dynamically evaluating the change index and change correlation index of the core monitoring data, the present invention can accurately adjust the data acquisition frequency according to the actual core monitoring data of the patient. This means that when the monitoring data is stable, the data acquisition can be automatically reduced, thus effectively avoiding data redundancy; while when the core monitoring data of the patient fluctuates or there are sudden situations, the sampling rate can be quickly increased to ensure that key information is captured in a timely manner, providing strong support for the accurate diagnosis of doctors.

[0034] 2) Intelligent data packaging: The present invention fully considers the impact of network conditions on data transmission and realizes intelligent data packaging by dynamically adjusting the coding packet size and compression parameters. This method not only improves the efficiency of data transmission, but also significantly reduces data loss and transmission delay caused by network congestion or bandwidth limitation, ensuring the integrity and real-time nature of the core monitoring data.

[0035] 3) Maximize resource utilization: Through precise data acquisition and intelligent data packaging, the present invention effectively reduces unnecessary data processing and transmission, thereby reducing the computational overhead and network resource occupation. This enables medical monitoring to operate more efficiently and provide high-quality monitoring services for more critically ill patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the specific implementation manners of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific implementation manners or the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0037] Figure 1 It is a flowchart of a data acquisition and integration method for adaptively capturing the critical care core monitoring cluster provided in Embodiment 1 of the present invention;

[0038] Figure 2 It is a flowchart of the method before Step 1 provided in Embodiment 1 of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0039] The following will describe in detail the embodiments of the technical solutions of the present invention with reference to the drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention, so they are only examples and cannot be used to limit the protection scope of the present invention.

[0040] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application shall have the ordinary meanings understood by those skilled in the art to which the present invention pertains.

[0041] Embodiment 1

[0042] As Figure 1 shown, the present invention provides an adaptive capture data acquisition and integration method for a critical care core monitoring cluster, including:

[0043] Step 1, evaluate the change index and change correlation index of the core monitoring data, and dynamically adjust the acquisition frequency of the core monitoring data according to the change index and change correlation index.

[0044] Specifically, various medical devices in the intensive care unit (such as electrocardiographs, blood pressure monitors, blood oxygen saturation monitors, etc.) are used to collect the core monitoring data of critically ill patients in real time, and the collected data is preprocessed, including data cleaning (such as removing outliers, missing value processing, etc.), data formatting (such as unifying the timestamp format, data unit, etc.), etc., to ensure the availability of the data and the accuracy of subsequent analysis.

[0045] After the above processing, change analysis is performed on the core monitoring data. Among them, the change analysis includes change index and change correlation index analysis. The change index analysis mainly focuses on the data change trend in the time dimension.

[0046] Specifically, in the above-mentioned Step 1, the evaluation method of the change index includes: Step 01, determine the length of a sliding window, and the sliding window is used to calculate the time correlation of the core monitoring data at each time point; Step 02, for each time point in the historical core monitoring data, calculate the mean and standard deviation of the data within the sliding window; Step 03, within the sliding window, for each core monitoring data, calculate the product of its standard difference from the current core monitoring data and sum them to obtain the time correlation index, calculate the ratio of the second derivative to the first derivative of the data, determine the data change rate, and determine the change index according to the data change rate and the time correlation coefficient.

[0047] The sliding window is the basis for calculating the time correlation of the core monitoring data at each time point. By setting an appropriate sliding window length, the short-term change trend of the data can be captured, while avoiding the computational complexity and memory consumption caused by too long a window. The length of the sliding window can be set according to actual needs, usually determined based on the analysis of historical data and experience. For example, for heart rate data, a few minutes may be selected as a window length to be able to capture the short-term changes in heart rate.

[0048] For the time-related coefficient, the time correlation index reflects the correlation of data over time, that is, the degree of association between the current data point and other data points within the sliding window. Within the sliding window, for each core monitoring data, calculate the product of its standard deviation from the current core monitoring data. Sum these products to obtain the time correlation index. The larger this index, the higher the degree of association between the current data point and other data points within the sliding window.

[0049] For the data change rate, the data change rate reflects the speed and direction of data change, that is, whether the data is changing at an accelerating rate, a decelerating rate, or remaining stable. Calculate the ratio of the second derivative of the data (i.e., the rate of change of the data change rate) to the first derivative (i.e., the data change rate). This ratio can reflect the speed and trend of data change. For example, when the ratio is large, it indicates that the data is changing rapidly; when the ratio is small, it indicates that the data is changing relatively smoothly.

[0050] The change index is a composite indicator that combines the time correlation index and the data change rate, used to quantify the degree of data change. Based on the time correlation index and the data change rate, set a calculation formula or rule to determine the change index. For example, the time correlation index and the data change rate can be weighted and summed to obtain the change index.

[0051] Through the above steps, the change index of the core monitoring data at each time point can be evaluated. This index not only considers the correlation of data over time but also the speed and direction of data change, so it can more comprehensively reflect the change of data.

[0052] Furthermore, in step 1, the method for evaluating the change association index includes: step 04, sorting the change indexes of various core monitoring data in descending order and performing normalization processing to obtain a change index sequence; step 05, calculating the correlation coefficient between two change indexes in the change index sequence; step 06, constructing an association graph based on the change index and the correlation coefficient. The association graph uses the core monitoring data as points and determines the edges based on the difference between the correlation coefficient and a preset coefficient threshold. When the difference is greater than zero, there is an edge. According to the association graph, the correlation coefficient is corrected to obtain the change association index.

[0053] To more clearly compare the degrees of change of different core monitoring data and eliminate the dimensional differences, it is necessary to sort and normalize the change indices of various core monitoring data. Specifically, first, sort the change indices of all core monitoring data in descending order. This allows for an intuitive view of which data has the most significant changes. Then, normalize the sorted change indices. Normalization is the process of scaling data to a specific range (usually 0 to 1), which can eliminate the dimensional differences between different data and enable them to be compared on the same scale. Normalization can be performed using methods such as linear functions and logarithmic functions.

[0054] Calculate the correlation coefficient between two change indices in the change index sequence to quantify the degree of linear correlation between them. Specifically, an appropriate type of correlation coefficient can be selected, such as the Pearson correlation coefficient, Spearman rank correlation coefficient, etc. Using the selected correlation coefficient formula, calculate the correlation coefficient between each pair of change indices in the change index sequence. The correlation coefficient value ranges from -1 to 1. The closer the value is to 1, the stronger the positive correlation between the two variables; the closer the value is to -1, the stronger the negative correlation; and a value close to 0 indicates that there is almost no linear correlation between the two variables.

[0055] There may be non-linear relationships and interactions between core monitoring data, and these complex relationships are often overlooked when directly calculating the correlation coefficient. Therefore, it is also necessary to correct the correlation coefficient to make it more specific. Specifically, each core monitoring data is regarded as a point in the association graph. Determine the edges based on the difference between the correlation coefficient and the preset coefficient threshold. If the difference between the correlation coefficient of two change indices and the preset coefficient threshold is greater than zero, draw an edge between them. In this way, the association graph shows which core monitoring data have significant association relationships. Then, perform the following formula for correcting the association relationship.

[0056] Specifically, correct the correlation coefficient according to the association graph, and the formula for obtaining the change association index is:

[0057]

[0058] In the formula, represents the change association index, represents the th correlation coefficient of the category of core monitoring data, represents the total number of core monitoring data, represents the th correlation coefficient of the category of core monitoring data that has an edge connection with the th category of core monitoring data, The total number of core monitoring data of the class.

[0059] It should be noted that the above correction only considers the influence of the correlation coefficients of other core monitoring data that have edge connections with the core monitoring data of the corrected correlation coefficient. In the actual application process, the correlation coefficients of the core monitoring data that have edge connections with other core monitoring data will also affect the correction of the correlation coefficient of the corrected core monitoring data. At the same time, considering the calculation cost, the embodiments of the present invention can consider up to two orders, that is, all other core monitoring data that have two-hop connections with the core monitoring data of the corrected correlation coefficient have edge connection relationships.

[0060] It should also be noted that in some embodiments, the operation can be performed on all correlation coefficients with edge connection relationships according to the above formula. In other embodiments, the correlation coefficients with direct edge connection relationships can be corrected using the correlation coefficients with indirect edge connection relationships according to the idea of the above formula, and then the corrected correlation coefficient can be corrected using the corrected correlation coefficients with direct edge connections according to the idea of the above formula.

[0061] Through correction, the complex relationships between data can be considered more comprehensively, improving the accuracy and reliability of the analysis results.

[0062] In the embodiments of the present invention, the sampling parameters include the acquisition frequency. The formula for dynamically adjusting the sampling parameters of the core monitoring data according to the change index and the change correlation index is:

[0063]

[0064] In the formula, represents the acquisition frequency of the th type of core monitoring data at the current time t, represents the acquisition frequency of the th type of core monitoring data at the previous time, represents the change index of the th type of core monitoring data, represents the importance weight of the th type of core monitoring data, is a constant coefficient.

[0065] Step 2: Collect the core monitoring data according to the adjusted acquisition frequency, consider the network situation, and package the collected core monitoring data in combination with the adjusted acquisition frequency to obtain a core monitoring data packet.

[0066] In an embodiment of the present invention, in step 2, considering the network condition and combining with the adjusted acquisition frequency, the collected core monitoring data is packaged, including: step 021, dynamically adjusting the size of the coding packet according to the current network bandwidth, average network bandwidth, adjusted acquisition frequency and maximum acquisition frequency; step 022, determining the compression parameter according to the adjusted acquisition frequency and the size of the coding packet, compressing the core monitoring data according to the compression parameter, and performing random linear coding on the compressed data to obtain the core monitoring data packet.

[0067] Specifically, first, it is necessary to obtain the current network bandwidth and average network bandwidth information. This can be achieved through network monitoring tools or APIs. It is also necessary to consider the adjusted acquisition frequency and the maximum acquisition frequency. The acquisition frequency determines the data generation speed, while the maximum acquisition frequency is a limiting value used to ensure that data is not sent at a speed exceeding the network processing capacity. Based on the above information, the size of each coding packet is dynamically adjusted. When the network bandwidth is large and the acquisition frequency is low, the size of the coding packet can be increased to reduce the number of transmissions; on the contrary, when the network bandwidth is limited or the acquisition frequency is high, the size of the coding packet should be reduced to avoid network congestion.

[0068] After determining the size of the coding packet, it is then necessary to determine the data compression parameter according to this size and the adjusted acquisition frequency, and compress and perform random linear coding on the core monitoring data to generate the core monitoring data packet. Specifically, each coding packet size is correspondingly set with matching compression parameters. These compression parameters can include compression ratio, compression algorithm, etc., aiming to ensure that the data can still maintain sufficient accuracy and readability after compression, while reducing the data size to adapt to the size limit of the coding packet. The core monitoring data is compressed using the determined compression parameter. Compression can significantly reduce the data size, thereby reducing the transmission cost and time. Random linear coding is performed on the compressed data. This is a data coding technology that can increase the redundancy and robustness of the data, so that even if part of the data is lost or damaged during transmission, the original data or content close to the original data can be restored through the decoding algorithm. Finally, the data that has been compressed and randomly linearly coded is packaged into the core monitoring data packet for transmission.

[0069] In an embodiment of the present invention, in step 021, the formula for dynamically adjusting the size of the coding packet according to the current network bandwidth, average network bandwidth, adjusted acquisition frequency and maximum acquisition frequency is:

[0070]

[0071] In the formula, represents the size of the coding packet of the i-th type of core monitoring data packet at the current time t, The encoding packet size representation of the i-th type of core monitoring data at the previous time represents the collection frequency of the i-th type of core monitoring data at the current time t, that is, the adjusted collection frequency, represents the preset maximum sampling frequency of the i-th type of core monitoring data, represents the current network bandwidth, represents the average network bandwidth, 、 、 are all constant coefficients.

[0072] Step 3, send the core monitoring data packet to the monitoring terminal.

[0073] Based on the above-mentioned Invention Embodiment 1, before Step 1, it includes:

[0074] Step 001, set a collection threshold for each type of monitoring data, and the collection threshold is used to trigger the collection of core monitoring data; Step 002, obtain the historical monitoring data of each type of monitoring data, make a prediction according to the historical monitoring data to obtain a monitoring prediction value, calculate the difference between the monitoring prediction value and the monitoring actual value, and dynamically adjust the collection threshold according to the difference; Step 003, when the monitoring data is not within the adjusted collection threshold, determine the monitoring data as core monitoring data and trigger the collection of core monitoring data.

[0075] The embodiment of the present invention triggers the collection of core monitoring data only when there is an abnormality in the data, avoids recording unnecessary data, and reduces the calculation overhead.

[0076] In summary, through the above specific embodiments, an adaptive capture data acquisition and integration method for a critical care core monitoring cluster of the present invention is elaborated in detail. This method can dynamically adjust the data acquisition and transmission strategies according to the changes in monitoring data and network conditions, ensure the efficient and accurate transmission of core monitoring data, and provide strong support for the monitoring and treatment of critical patients.

[0077] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered by the scope of the claims and the description of the present invention.

Claims

1. A data collection and integration method for adaptively capturing a critical core monitoring cluster, characterized in that: include: Step 1, evaluating the change index and change correlation index of the core monitoring data, and dynamically adjusting the collection frequency of the core monitoring data according to the change index and change correlation index; Step 2: collecting core monitoring data according to the adjusted collection frequency, taking into account the network conditions, and packaging the collected core monitoring data in combination with the adjusted collection frequency to obtain a core monitoring data packet; Step 3, sending the core monitoring data packet to the monitoring terminal; In step 2, the collected core monitoring data is packaged considering the network conditions and the adjusted collection frequency, including: Step 021, dynamically adjusting the size of the encoding packet according to the current network bandwidth, the average network bandwidth, the adjusted acquisition frequency and the maximum acquisition frequency; Step 022, determining compression parameters according to the adjusted acquisition frequency and encoding packet size, compressing the core monitoring data according to the compression parameters, and performing random linear encoding on the compressed data to obtain a core monitoring data packet; Step 021, according to the current network bandwidth, the average network bandwidth, the adjusted acquisition frequency and the maximum acquisition frequency, the formula for dynamically adjusting the encoding packet size is: In the formula, represents the coded packet size of the i-th type of core monitoring data packet at the current time t, Indicates the size of the encoding packet of the i-th type of core monitoring data at the previous time. represents the current time t The collection frequency of the core monitoring data, that is, the adjusted collection frequency, Indicates the preset maximum sampling frequency of the i-th type of core monitoring data, Indicates the current network bandwidth. represents the average network bandwidth, , , are all constant coefficients.

2. According to claim 1, a data collection and integration method for adaptively capturing a critical care core monitoring cluster is characterized in that: Before step 1 also include: Step 001, setting a collection threshold for each type of monitoring data, wherein the collection threshold is used to trigger the collection of core monitoring data; Step 002, obtaining historical monitoring data of various monitoring data, making predictions based on the historical monitoring data to obtain monitoring prediction values, calculating the difference between the monitoring prediction values ​​and the monitoring actual values, and dynamically adjusting the collection threshold according to the difference; Step 003: When the monitoring data is not within the adjusted collection threshold, the monitoring data is determined as core monitoring data and the collection of core monitoring data is triggered.

3. According to claim 1, a data collection and integration method for adaptively capturing a critical care core monitoring cluster is characterized in that: In step 1, the evaluation method of the change index includes: Step 01, determining the length of a sliding window, wherein the sliding window is used to calculate the time correlation of the core monitoring data at each time point; Step 02, for each time point in the historical core monitoring data, calculate the mean and standard deviation of the data in the sliding window; Step 03, within the sliding window, for each core monitoring data, calculate the product of the standard deviation value of the core monitoring data with the current core monitoring data, and sum them up to obtain the time correlation index, calculate the ratio of the second-order derivative of the data to the first-order derivative, determine the data change rate, and determine the change index based on the data change rate and the time correlation coefficient.

4. According to claim 3, a data collection and integration method for adaptively capturing a critical care core monitoring cluster is characterized in that: In step 1, the methods for evaluating the change association index include: Step 04, sorting the change indexes of various core monitoring data in descending order and normalizing them to obtain a change index sequence; Step 05, calculating the correlation coefficient between two change indexes in the change index sequence; Step 06, constructing an association graph based on the change index and the correlation coefficient. The association graph takes the core monitoring data as points and determines the edge by the difference between the correlation coefficient and the preset coefficient threshold. When the difference is greater than zero, there is an edge. The correlation coefficient is corrected according to the association graph to obtain the change correlation index.

5. According to claim 4, a data collection and integration method for adaptively capturing a critical core monitoring cluster is characterized in that: The correlation coefficient is corrected according to the correlation diagram to obtain the formula of the change correlation index: In the formula, represents the change correlation index, Indicates The correlation coefficient of the core monitoring data, Indicates the total number of core monitoring data. Indicates The core monitoring data of this class has edge connections The correlation coefficient of the core monitoring data, Indicates The core monitoring data of this class has edge connections The total number of core monitoring data of the class.

6. According to the data collection and integration method of adaptively capturing a critical core monitoring cluster according to claim 5, it is characterized in that: The formula for dynamically adjusting the sampling frequency of core monitoring data according to the change index and the change correlation index is: In the formula, represents the current time t The frequency of collecting core monitoring data, Indicates the previous time The frequency of collecting core monitoring data, Indicates The change index of the core monitoring data of the class, Indicates Importance weight of core monitoring data, is a constant coefficient.

Images