A method and system for monitoring abnormal data during the entire process of wound infection

Abstract

The present invention proposes a method and system for monitoring abnormal data of the whole process period of wound infection, which relates to the field of data monitoring technology. The method collects data of the preset whole process period of wound infection, obtains the collected data of the whole process period, calculates the node infection coefficient of each cycle time node, and establishes an infection cycle monitoring image; extracts positive infection data and negative infection data according to the infection cycle monitoring image information, calibrates the positive infection nodes and the negative infection nodes, and then obtains the node connection lines; obtains adjacent infection differences according to the node infection coefficients, compares the adjacent infection differences with the preset infection development threshold, and then obtains the development node group; judges the positive development and negative development of the development node group, and then judges whether to issue an infection warning, issues a warning according to the judgment result, obtains warning information, and realizes comprehensive monitoring and warning of the whole process period of wound infection.

Description

Technical Field

[0001] The present invention proposes a method and system for monitoring abnormal periodic data during the whole process of wound infection, which relates to the technical field of data monitoring, and specifically to the technical field of monitoring abnormal periodic data during the whole process of wound infection. Background Art

[0002] In the medical field, monitoring and early warning of wound infection are particularly important. Traditional wound infection monitoring methods mainly rely on the clinical observation and experience judgment of medical staff. This method has problems such as strong subjectivity and insufficient accuracy, and it is difficult to fully and accurately reflect the development of wound infection. Existing wound infection monitoring methods often only focus on data at a certain point in time, and lack comprehensive monitoring and analysis of the entire process cycle of wound infection. This method cannot accurately reflect the development trend of wound infection, and it is difficult to detect and deal with potential infection risks in a timely manner. Due to the diversity and complexity of wound infection data, traditional data processing methods often find it difficult to effectively extract key information, resulting in inaccurate early warning results and an inability to provide reliable decision-making support for medical staff. Summary of the invention

[0003] The present invention provides a method and system for monitoring abnormal data during the entire process of wound infection to solve the above problems:

[0004] The present invention proposes a method and system for monitoring abnormal data of the entire period of wound infection, the monitoring method comprising:

[0005] S1. Collect data of the preset whole process cycle of wound infection, obtain the whole process collection data of the cycle, calculate the node infection coefficient of each cycle time node, and establish the infection cycle monitoring image;

[0006] S2. Extract positive infection data and negative infection data according to the infection cycle monitoring image information, calibrate positive infection nodes and negative infection nodes, and then obtain node connection lines;

[0007] S3, obtaining adjacent infection differences according to the node infection coefficient, comparing the adjacent infection differences with a preset infection development threshold, and then obtaining a development node group;

[0008] S4. The development node group is judged to be positively developed or negatively developed, and then it is judged whether to issue an infection warning. An early warning is issued according to the judgment result to obtain early warning information.

[0009] Further, the S1 includes:

[0010] Obtaining a preset full-process cycle for wound surface monitoring, performing periodic data collection on the preset full-process cycle, and obtaining periodic full-process collection data;

[0011] Preprocessing the collected data during the entire cycle to obtain preprocessed collected data during the entire cycle;

[0012] Obtaining node collection data of each preset periodic time node, and calculating the node infection coefficient of the corresponding periodic time node according to the node collection data;

[0013] An infection cycle monitoring image is established with the cycle time node as the horizontal axis, the node infection coefficient as the vertical axis, the preset node infection threshold and the cycle initial node as the origin.

[0014] Further, the S2 includes:

[0015] Acquire infection cycle monitoring image information, extract data information of the first quadrant of the infection cycle monitoring image, and obtain infection positive data;

[0016] Extract the fourth quadrant of the infection cycle monitoring image to obtain negative infection data;

[0017] Obtain the node infection coefficient of each period time node in the positive infection data and mark it as a positive infection node;

[0018] Obtain the node infection coefficient of each period time node in the negatively infected data and mark it as a negatively infected node;

[0019] The positive infection nodes and the negative infection nodes are connected according to the periodic time node sequence to obtain the node connection lines.

[0020] Further, the S3 includes:

[0021] Obtain the difference in node infection coefficients between every two adjacent nodes in the node connection line to obtain the adjacent infection difference;

[0022] Compare each adjacent infection difference with a preset infection development threshold to obtain an infection development comparison result;

[0023] Obtaining adjacent nodes whose adjacent infection difference values ​​are greater than a preset infection development threshold value in the infection development comparison result, and marking them as a development node group;

[0024] The node with the smaller node infection coefficient in the development node group is marked as the first node, and the node with the larger node infection coefficient in the development node group is marked as the second node;

[0025] It is determined whether the second node in the development node group is a positive infection node, and node determination information is obtained.

[0026] Further, the S4 includes:

[0027] When the second node in the development node group is a positively infected node, the corresponding development node group is determined to be positively developed, and an infection warning is issued for the development node group;

[0028] When the second node in the development node group is a negatively infected node, the corresponding development node group is determined to be negatively developed, and no infection warning is issued for the development node group;

[0029] Infection warning is performed on the infection cycle monitoring image through infection warning of all development node groups.

[0030] Furthermore, the monitoring system comprises:

[0031] The periodic acquisition image establishment module is used to collect data of the preset full-process cycle of wound infection, obtain the full-process acquisition data of the cycle, calculate the node infection coefficient of each cycle time node, and establish the infection cycle monitoring image;

[0032] The node calibration module is used to extract positive infection data and negative infection data according to the infection cycle monitoring image information, calibrate the positive infection nodes and negative infection nodes, and then obtain the node connection lines;

[0033] A difference analysis module is used to obtain adjacent infection differences according to the node infection coefficient, compare the adjacent infection differences with a preset infection development threshold, and then obtain a development node group;

[0034] The judgment and early warning module is used to judge the positive and negative development of the development node group, and then determine whether to issue an infection warning, issue a warning based on the judgment result, and obtain warning information.

[0035] Furthermore, the periodic image acquisition establishment module includes:

[0036] A data acquisition module is used to obtain a preset full-process cycle of wound surface monitoring, perform periodic data acquisition on the preset full-process cycle, and obtain periodic full-process acquisition data;

[0037] A preprocessing module, used for preprocessing the data collected during the whole cycle to obtain the preprocessed data collected during the whole cycle;

[0038] An infection calculation module is used to obtain node collection data of each preset periodic time node, and calculate the node infection coefficient of the corresponding periodic time node according to the node collection data;

[0039] The image establishment module is used to establish an infection cycle monitoring image with the cycle time node as the horizontal coordinate, the node infection coefficient as the vertical coordinate, and the preset node infection threshold and the cycle initial node as the origin.

[0040] Furthermore, the node calibration module includes:

[0041] A data extraction module is used to obtain infection cycle monitoring image information, extract data information of the first quadrant of the infection cycle monitoring image, and obtain infection positive data;

[0042] Extract the fourth quadrant of the infection cycle monitoring image to obtain negative infection data;

[0043] The positive node calibration module is used to obtain the node infection coefficient of each period time node in the positive infection data and calibrate it as a positive infection node;

[0044] The negative node calibration module is used to obtain the node infection coefficient of each period time node in the infected negative data and calibrate it as a negative infection node;

[0045] The node connection module is used to connect the positive infection nodes and the negative infection nodes according to the periodic time node sequence to obtain the node connection line.

[0046] Furthermore, the difference analysis module includes:

[0047] A difference acquisition module is used to obtain the difference of the node infection coefficients of every two adjacent nodes in the node connection line to obtain the adjacent infection difference;

[0048] A difference comparison module is used to compare each adjacent infection difference with a preset infection development threshold to obtain an infection development comparison result;

[0049] A node development calibration module, used for obtaining adjacent nodes whose adjacent infection difference is greater than a preset infection development threshold in the infection development comparison result, and calibrating them as a development node group;

[0050] A coefficient size calibration module, used for calibrating a node with a smaller node infection coefficient in the development node group as a first node, and calibrating a node with a larger node infection coefficient in the development node group as a second node;

[0051] The node judgment module is used to judge whether the second node in the development node group is a positive infection node and obtain node judgment information.

[0052] Furthermore, the judgment and early warning module includes:

[0053] An infection warning module, used for determining that the corresponding development node group is in positive development when the second node in the development node group is a positively infected node, and performing infection warning on the development node group;

[0054] A no-warning module, used for determining that the corresponding development node group is negatively developing when the second node in the development node group is a negatively infected node, and not issuing an infection warning for the development node group;

[0055] The comprehensive early warning module is used to provide infection early warning for infection cycle monitoring images through infection early warning for all development node groups.

[0056] Beneficial effects of the present invention: through real-time monitoring and data analysis, abnormal changes can be detected in the early stage of infection, thereby triggering early warning in time. By quantitatively evaluating changes in the infection status, accurate monitoring of the infection process can be achieved. Based on the monitoring results, the direction and degree of infection development in each cycle can be known in time, and corresponding early warnings can be issued. Through early warnings, the risk of aggravated infection can be reduced. This method relies on methods such as data analysis, and can provide objective and quantifiable decision support to help doctors make more scientific judgments. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 A schematic diagram of a method for monitoring abnormal periodic data during the entire process of wound infection;

[0058] Figure 2 Monitor images for the infection cycle. DETAILED DESCRIPTION

[0059] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0060] In one embodiment of the present invention, a method and system for monitoring abnormal data of the entire period of wound infection is proposed by the present invention. The monitoring method comprises:

[0061] S1. Collect data of the preset whole process cycle of wound infection, obtain the whole process collection data of the cycle, calculate the node infection coefficient of each cycle time node, and establish the infection cycle monitoring image, such as Figure 2 As shown;

[0062] S2. Extract positive infection data and negative infection data according to the infection cycle monitoring image information, calibrate positive infection nodes and negative infection nodes, and then obtain node connection lines;

[0063] S3, obtaining adjacent infection differences according to the node infection coefficient, comparing the adjacent infection differences with a preset infection development threshold, and then obtaining a development node group;

[0064] S4. Determine the positive and negative development of the development node group, and then determine whether to issue an infection warning. Issue a warning based on the judgment result to obtain warning information, such as Figure 1 shown.

[0065] The working principle of the above technical solution is: data is collected for the entire process cycle of wound infection, covering all relevant data from the beginning to the end of the infection, which may include the size, color, temperature, nature of exudate, bacterial culture results, etc. of the wound. By calculating the node infection coefficient at each cycle time node, the comprehensive infection status at each time point can be quantitatively evaluated. These coefficients are comprehensive scores based on multiple parameters. Using the collected data and the calculated node infection coefficient, an infection cycle monitoring image can be drawn. This image shows the changing trend of the infection throughout the cycle, and the development of the infection can be intuitively understood. Positive infection data and negative infection data are extracted from the infection cycle monitoring image. Positive data indicates that the infection is aggravating or worsening, while negative data indicates that the infection is mitigating or improving. By comparing and analyzing these data, positive infection nodes and negative infection nodes can be calibrated, and the connecting lines between nodes can be determined to reflect the changing path of the infection status. The difference between adjacent infection nodes, that is, the adjacent infection difference, is calculated, and this difference reflects the rate of change of the infection status in a short period of time. These differences are compared with the preset infection progression threshold to determine which node groups represent situations where the infection status has changed significantly. These node groups are divided into progression node groups. The progression node groups are further analyzed to determine whether the nodes are progressing positively (infection is getting worse) or negatively (infection is getting less). Based on the judgment results, if it is determined that the infection is getting worse or reaches the warning conditions, the infection warning is triggered and the warning information is generated.

[0066] The technical effect of the above technical solution is: through real-time monitoring and data analysis, abnormal changes can be detected in the early stage of infection, thereby triggering early warning in time. By quantitatively evaluating changes in the infection status, accurate monitoring of the infection process can be achieved. Based on the monitoring results, the direction and degree of infection development in each cycle can be known in time, and corresponding early warnings can be issued. Early warnings can reduce the risk of worsening infection. This method relies on data analysis and other methods, and can provide objective and quantifiable decision support to help doctors make more scientific judgments.

[0067] In one embodiment of the present invention, the S1 includes:

[0068] Obtaining a preset full-process cycle for wound surface monitoring, performing periodic data collection on the preset full-process cycle, and obtaining periodic full-process collection data;

[0069] Preprocessing the collected data during the entire cycle to obtain preprocessed collected data during the entire cycle;

[0070] Obtaining node collection data of each preset periodic time node, and calculating the node infection coefficient of the corresponding periodic time node according to the node collection data;

[0071] The calculation formula of the node infection coefficient is:

[0072]

[0073] Among them, R jd is the node infection coefficient, b is the number of infection monitoring indicators, S ri is the collected data of the ith infection monitoring indicator, Y ri is the data threshold of the i-th infection monitoring indicator, Q ri is the preset weight data of the ith infection monitoring indicator, T rj is the current duration of the node in the cycle time node, T zq The total duration of the preset whole process cycle;

[0074] An infection cycle monitoring image is established with the cycle time node as the horizontal axis, the node infection coefficient as the vertical axis, the preset node infection threshold and the cycle initial node as the origin.

[0075] The working principle of the above technical solution is: based on clinical experience and the natural process of wound infection, a full process cycle of wound monitoring is preset. This cycle may include various stages from the appearance of the wound to complete healing. In this preset full process cycle, data collection is performed at predetermined time intervals (such as every day, every two days, etc.). The collected data may include the appearance characteristics of the wound (such as color, size), physiological indicators (such as temperature, humidity), etc. The collected raw data is preprocessed to eliminate noise, fill missing values, standardize data, etc., to ensure the accuracy and consistency of the data. At each preset cycle time node, the collected data of the node is obtained. These data may include multiple indicators, such as the area of ​​the wound, color change, etc. According to the collected data of these nodes, the node infection coefficient of the corresponding cycle time node is calculated. The node infection coefficient is a comprehensive indicator used to quantitatively evaluate the infection status of the time node. A two-dimensional coordinate system is established with the cycle time node as the horizontal coordinate and the node infection coefficient as the vertical coordinate. In this coordinate system, the infection cycle monitoring image is drawn with the preset node infection threshold and the cycle initial node as the origin (i.e., the zero point of the coordinate system). This image intuitively shows the changing trend of the infection status throughout the cycle.

[0076] The technical effect of the above technical solution is: by real-time monitoring of changes in the infection status of the wound surface, an early warning is triggered when the infection coefficient reaches or exceeds a preset threshold. The node infection coefficient provides an indicator for quantitatively evaluating the infection status, which can enable doctors to understand the infection status of the wound surface more accurately. The comprehensive difference between all indicator data and the threshold at the same time node can be calculated. The coefficient also takes into account the weight of the indicator, and the difference coefficient of indicators with different weights can be calculated. At the same time, the factor of the infection duration of the current node is also considered. Combining the above factors, the above formula can calculate the node infection coefficient of the comprehensive node under the influence of the actual data of the indicator, time factors and weight factors. The infection cycle monitoring image shows the changing trend of the infection status in an intuitive way, allowing doctors to more easily identify the development stage and potential risks of the infection. Based on the infection cycle monitoring image and the node infection coefficient, doctors can formulate and adjust treatment plans more scientifically to ensure the effectiveness and safety of treatment.

[0077] In one embodiment of the present invention, S2 includes:

[0078] Acquire infection cycle monitoring image information, extract data information of the first quadrant of the infection cycle monitoring image, and obtain infection positive data;

[0079] Extract the fourth quadrant of the infection cycle monitoring image to obtain negative infection data;

[0080] Get the node infection coefficient of each period time node in the positive infection data, and mark it as a positive infection node (if there is no positive infection node, no calibration will be performed);

[0081] Obtain the node infection coefficient of each period time node in the infected negative data, and mark it as a negatively infected node (if there is none, no calibration will be performed);

[0082] The positive infection nodes and the negative infection nodes are connected according to the periodic time node sequence to obtain the node connection lines.

[0083] The working principle of the above technical solution is to extract information from the established infection cycle monitoring image. This image is a two-dimensional coordinate system, with the horizontal axis representing the cycle time node and the vertical axis representing the node infection coefficient. The quadrants represent different infection states or trends. In the infection cycle monitoring image, the first quadrant usually represents the area where the infection state develops positively (i.e., the infection coefficient increases over time), while the fourth quadrant represents the area where the infection state develops negatively (i.e., the infection coefficient decreases over time).

[0084] Extract the data points in these two quadrants respectively to obtain positive infection data and negative infection data. In the positive infection data, for each cycle time node, extract the corresponding node infection coefficient, and mark these nodes as positive infection nodes. If a time node does not have a corresponding infection coefficient, it may be in another quadrant; in the negative infection data, extract the node infection coefficient of each cycle time node, and mark these nodes as negative infection nodes. Connect the marked positive infection nodes and negative infection nodes in the order of cycle time nodes. This is achieved by drawing line segments or curves to form node connection lines. The node connection lines can intuitively show the changing trend of the infection status throughout the cycle, including the positive and negative development of the infection.

[0085] The technical effect of the above technical solution is: through the node connection line, the changing trend of the infection status in the whole cycle can be intuitively seen. The node connection line can be used as an auxiliary diagnosis tool to help doctors judge the development trend and potential risks of the infection.

[0086] By real-time monitoring and visualizing infection trends, doctors can more quickly identify changes in infection status, take timely treatment measures, and improve treatment efficiency. Node connection lines can also be used to optimize patient management. Doctors can ensure the safety and comfort of patients based on changes in infection trends.

[0087] In one embodiment of the present invention, S3 includes:

[0088] Obtain the difference in node infection coefficients between every two adjacent nodes in the node connection line to obtain the adjacent infection difference;

[0089] Compare each adjacent infection difference with a preset infection development threshold to obtain an infection development comparison result;

[0090] Obtaining adjacent nodes whose adjacent infection difference values ​​are greater than a preset infection development threshold value in the infection development comparison result, and marking them as a development node group;

[0091] The node with the smaller node infection coefficient in the development node group is marked as the first node, and the node with the larger node infection coefficient in the development node group is marked as the second node;

[0092] It is determined whether the second node in the development node group is a positive infection node, and node determination information is obtained.

[0093] The working principle of the above technical solution is: extract the node infection coefficient of each two adjacent nodes from the established node connection line. Calculate the difference of the node infection coefficients of the two adjacent nodes to obtain the adjacent infection difference. This difference reflects the degree of change of the infection state in a short period of time (i.e., between two adjacent time nodes). Compare each adjacent infection difference with the preset infection development threshold. The threshold is used to determine whether the infection state has changed significantly. If the adjacent infection difference is greater than the preset infection development threshold, it is considered that the infection state has changed significantly in a short period of time and needs further attention. In the infection development comparison result, the adjacent nodes whose adjacent infection difference is greater than the preset infection development threshold are screened out, and the two nodes are marked as a development node group. This group contains node pairs with significant changes in infection status. In the development node group, according to the size of the node infection coefficient, the node with a smaller node infection coefficient is marked as the first node, and the node with a larger node infection coefficient is marked as the second node. This helps to further analyze the changing trend of the infection state. Determine whether the second node in the development node group is a positive infection node (reflecting the node infection development trend). This is usually done by comparing the infection coefficient of the second node with the preset positive infection threshold. If the infection coefficient of the second node is greater than or equal to the positive infection threshold, it is determined as a positive infection node; otherwise, it is determined as a negative infection node or in other states.

[0094] The technical effect of the above technical solution is: by calculating the difference between adjacent infections and comparing it with the preset threshold, it is possible to accurately identify significant changes in the infection status in a short period of time. Based on the information of the development node group, the doctor can more accurately judge the development trend of the infection. By real-time monitoring and rapid response to changes in the infection status, the efficiency of infection monitoring is improved and abnormal data is identified in a timely manner. The development node group and node judgment information provide doctors with objective and quantitative decision-making support. The application of this method can improve medical quality and safety and reduce medical risks and costs.

[0095] In one embodiment of the present invention, the S4 includes:

[0096] When the second node in the development node group is a positively infected node, the corresponding development node group is determined to be positively developed, and an infection warning is issued for the development node group;

[0097] When the second node in the development node group is a negatively infected node, the corresponding development node group is determined to be negatively developed, and no infection warning is issued for the development node group;

[0098] Infection warning is performed on the infection cycle monitoring image through infection warning of all development node groups.

[0099] The working principle of the above technical solution is: in the determined development node group, the infection trend of the entire development node group is judged according to the infection status of the second node (positive infection node or negative infection node). If the second node is a positive infection node, that is, its infection coefficient is greater than or equal to the preset positive infection threshold, the corresponding development node group is judged to be positive development, indicating that the infection status is gradually worsening or spreading. If the second node is a negative infection node, that is, its infection coefficient is less than the preset positive infection threshold (and may be greater than or equal to the negative infection threshold, depending on the setting of the threshold), the corresponding development node group is judged to be negative development, indicating that the infection status is gradually improving or under control. For the development node group judged to be positive development, infection warning is performed. This is achieved by issuing an alarm, displaying a warning message, or triggering a specific medical process to remind doctors or nursing staff to take timely intervention measures. For the development node group judged to be negative development, no infection warning is performed, because this means that the infection status is developing in a good direction. The above infection warning information is integrated into the infection cycle monitoring image to show in an intuitive way which time periods or areas have infection risks. This can be done by adding color coding, arrow indicators or other visual elements to the images so that doctors can quickly identify and respond to early warning signs of infection.

[0100] The technical effect of the above technical solution is: by judging the infection trend of the development node group and making targeted early warnings, the accuracy of infection early warnings can be significantly improved, and false positives and missed reports can be reduced. Infection early warnings can help medical institutions allocate medical resources more reasonably, focus limited resources on patients who need intervention the most, and improve the efficiency and quality of medical services. Timely infection early warnings and intervention measures can reduce the risk of serious complications in patients and improve patient safety and treatment effects. Infection early warnings provide doctors with objective and quantitative decision support, helping doctors make diagnostic and treatment decisions more quickly and accurately.

[0101] In one embodiment of the present invention, the monitoring system comprises:

[0102] The periodic acquisition image establishment module is used to collect data of the preset full-process cycle of wound infection, obtain the full-process acquisition data of the cycle, calculate the node infection coefficient of each cycle time node, and establish the infection cycle monitoring image;

[0103] The node calibration module is used to extract positive infection data and negative infection data according to the infection cycle monitoring image information, calibrate the positive infection nodes and negative infection nodes, and then obtain the node connection lines;

[0104] A difference analysis module is used to obtain adjacent infection differences according to the node infection coefficient, compare the adjacent infection differences with a preset infection development threshold, and then obtain a development node group;

[0105] The judgment and early warning module is used to judge the positive and negative development of the development node group, and then determine whether to issue an infection warning, issue a warning based on the judgment result, and obtain warning information.

[0106] The working principle of the above technical solution is: data is collected for the entire process cycle of wound infection, covering all relevant data from the beginning to the end of the infection, which may include the size, color, temperature, nature of exudate, bacterial culture results, etc. of the wound. By calculating the node infection coefficient at each cycle time node, the comprehensive infection status at each time point can be quantitatively evaluated. These coefficients are comprehensive scores based on multiple parameters. Using the collected data and the calculated node infection coefficient, an infection cycle monitoring image can be drawn. This image shows the changing trend of the infection throughout the cycle, and the development of the infection can be intuitively understood. Positive infection data and negative infection data are extracted from the infection cycle monitoring image. Positive data indicates that the infection is aggravating or worsening, while negative data indicates that the infection is mitigating or improving. By comparing and analyzing these data, positive infection nodes and negative infection nodes can be calibrated, and the connecting lines between nodes can be determined to reflect the changing path of the infection status. The difference between adjacent infection nodes, that is, the adjacent infection difference, is calculated, and this difference reflects the rate of change of the infection status in a short period of time. These differences are compared with the preset infection progression threshold to determine which node groups represent situations where the infection status has changed significantly. These node groups are divided into progression node groups. The progression node groups are further analyzed to determine whether the nodes are progressing positively (infection is getting worse) or negatively (infection is getting less). Based on the judgment results, if it is determined that the infection is getting worse or reaches the warning conditions, the infection warning is triggered and the warning information is generated.

[0107] The technical effect of the above technical solution is: through real-time monitoring and data analysis, abnormal changes can be detected in the early stage of infection, thereby triggering early warning in time. By quantitatively evaluating changes in the infection status, accurate monitoring of the infection process can be achieved. Based on the monitoring results, the direction and degree of infection development in each cycle can be known in time, and corresponding early warnings can be issued. Early warnings can reduce the risk of worsening infection. This method relies on data analysis and other methods, and can provide objective and quantifiable decision support to help doctors make more scientific judgments.

[0108] In one embodiment of the present invention, the periodic image acquisition establishment module includes:

[0109] A data acquisition module is used to obtain a preset full-process cycle of wound surface monitoring, perform periodic data acquisition on the preset full-process cycle, and obtain periodic full-process acquisition data;

[0110] A preprocessing module, used for preprocessing the data collected during the whole cycle to obtain the preprocessed data collected during the whole cycle;

[0111] An infection calculation module is used to obtain node collection data of each preset periodic time node, and calculate the node infection coefficient of the corresponding periodic time node according to the node collection data;

[0112] The calculation formula of the node infection coefficient is:

[0113]

[0114] Among them, R jd is the node infection coefficient, b is the number of infection monitoring indicators, S ri is the collected data of the ith infection monitoring indicator, Y ri is the data threshold of the i-th infection monitoring indicator, Q ri is the preset weight data of the ith infection monitoring indicator, T rj is the current duration of the node in the cycle time node, T zq The total duration of the preset whole process cycle;

[0115] The image establishment module is used to establish an infection cycle monitoring image with the cycle time node as the horizontal coordinate, the node infection coefficient as the vertical coordinate, and the preset node infection threshold and the cycle initial node as the origin.

[0116] The working principle of the above technical solution is: based on clinical experience and the natural process of wound infection, a full process cycle of wound monitoring is preset. This cycle may include various stages from the appearance of the wound to complete healing. In this preset full process cycle, data collection is performed at predetermined time intervals (such as every day, every two days, etc.). The collected data may include the appearance characteristics of the wound (such as color, size), physiological indicators (such as temperature, humidity), etc. The collected raw data is preprocessed to eliminate noise, fill missing values, standardize data, etc., to ensure the accuracy and consistency of the data. At each preset cycle time node, the collected data of the node is obtained. These data may include multiple indicators, such as the area of ​​the wound, color change, etc. According to the collected data of these nodes, the node infection coefficient of the corresponding cycle time node is calculated. The node infection coefficient is a comprehensive indicator used to quantitatively evaluate the infection status of the time node. A two-dimensional coordinate system is established with the cycle time node as the horizontal coordinate and the node infection coefficient as the vertical coordinate. In this coordinate system, the infection cycle monitoring image is drawn with the preset node infection threshold and the cycle initial node as the origin (i.e., the zero point of the coordinate system). This image intuitively shows the changing trend of the infection status throughout the cycle.

[0117] The technical effect of the above technical solution is: by real-time monitoring of changes in the infection status of the wound, and triggering an early warning when the infection coefficient reaches or exceeds the preset threshold. The node infection coefficient provides an indicator for quantitatively evaluating the infection status, which can enable doctors to understand the infection status of the wound more accurately. The infection cycle monitoring image shows the changing trend of the infection status in an intuitive way, allowing doctors to more easily identify the development stage and potential risks of the infection. Based on the infection cycle monitoring image and the node infection coefficient, doctors can formulate and adjust treatment plans more scientifically to ensure the effectiveness and safety of the treatment.

[0118] In one embodiment of the present invention, the node calibration module includes:

[0119] A data extraction module is used to obtain infection cycle monitoring image information, extract data information of the first quadrant of the infection cycle monitoring image, and obtain infection positive data;

[0120] Extract the fourth quadrant of the infection cycle monitoring image to obtain negative infection data;

[0121] The positive node calibration module is used to obtain the node infection coefficient of each period time node in the positive infection data and calibrate it as a positive infection node (no calibration is performed if there is none);

[0122] The negative node calibration module is used to obtain the node infection coefficient of each period time node in the infected negative data and calibrate it as a negative infection node (no calibration will be performed if there is none);

[0123] The node connection module is used to connect the positive infection nodes and the negative infection nodes according to the periodic time node sequence to obtain the node connection line.

[0124] The working principle of the above technical solution is to extract information from the established infection cycle monitoring image. This image is a two-dimensional coordinate system, with the horizontal axis representing the cycle time node and the vertical axis representing the node infection coefficient. The quadrants represent different infection states or trends. In the infection cycle monitoring image, the first quadrant usually represents the area where the infection state develops positively (i.e., the infection coefficient increases over time), while the fourth quadrant represents the area where the infection state develops negatively (i.e., the infection coefficient decreases over time).

[0125] Extract the data points in these two quadrants respectively to obtain positive infection data and negative infection data. In the positive infection data, for each cycle time node, extract the corresponding node infection coefficient, and mark these nodes as positive infection nodes. If a time node does not have a corresponding infection coefficient, it may be in another quadrant; in the negative infection data, extract the node infection coefficient of each cycle time node, and mark these nodes as negative infection nodes. Connect the marked positive infection nodes and negative infection nodes in the order of cycle time nodes. This is achieved by drawing line segments or curves to form node connection lines. The node connection lines can intuitively show the changing trend of the infection status throughout the cycle, including the positive and negative development of the infection.

[0126] The technical effect of the above technical solution is: through the node connection line, the changing trend of the infection status in the whole cycle can be intuitively seen. The node connection line can be used as an auxiliary diagnosis tool to help doctors judge the development trend and potential risks of the infection.

[0127] By real-time monitoring and visualizing infection trends, doctors can more quickly identify changes in infection status, take timely treatment measures, and improve treatment efficiency. Node connection lines can also be used to optimize patient management. Doctors can ensure the safety and comfort of patients based on changes in infection trends.

[0128] In one embodiment of the present invention, the difference analysis module includes:

[0129] A difference acquisition module is used to obtain the difference of the node infection coefficients of every two adjacent nodes in the node connection line to obtain the adjacent infection difference;

[0130] A difference comparison module is used to compare each adjacent infection difference with a preset infection development threshold to obtain an infection development comparison result;

[0131] A node development calibration module, used for obtaining adjacent nodes whose adjacent infection difference is greater than a preset infection development threshold in the infection development comparison result, and calibrating them as a development node group;

[0132] A coefficient size calibration module, used for calibrating a node with a smaller node infection coefficient in the development node group as a first node, and calibrating a node with a larger node infection coefficient in the development node group as a second node;

[0133] The node judgment module is used to judge whether the second node in the development node group is a positive infection node and obtain node judgment information.

[0134] The working principle of the above technical solution is: extract the node infection coefficient of each two adjacent nodes from the established node connection line. Calculate the difference of the node infection coefficients of the two adjacent nodes to obtain the adjacent infection difference. This difference reflects the degree of change of the infection state in a short period of time (i.e., between two adjacent time nodes). Compare each adjacent infection difference with the preset infection development threshold. The threshold is used to determine whether the infection state has changed significantly. If the adjacent infection difference is greater than the preset infection development threshold, it is considered that the infection state has changed significantly in a short period of time and needs further attention. In the infection development comparison result, the adjacent nodes whose adjacent infection difference is greater than the preset infection development threshold are screened out, and the two nodes are marked as a development node group. This group contains node pairs with significant changes in infection status. In the development node group, according to the size of the node infection coefficient, the node with a smaller node infection coefficient is marked as the first node, and the node with a larger node infection coefficient is marked as the second node. This helps to further analyze the changing trend of the infection state. Determine whether the second node in the development node group is a positive infection node (reflecting the node infection development trend). This is usually done by comparing the infection coefficient of the second node with the preset positive infection threshold. If the infection coefficient of the second node is greater than or equal to the positive infection threshold, it is determined as a positive infection node; otherwise, it is determined as a negative infection node or in other states.

[0135] The technical effect of the above technical solution is: by calculating the difference between adjacent infections and comparing it with the preset threshold, it is possible to accurately identify significant changes in the infection status in a short period of time. Based on the information of the development node group, the doctor can more accurately judge the development trend of the infection. By real-time monitoring and rapid response to changes in the infection status, the efficiency of infection monitoring is improved and abnormal data is identified in a timely manner. The development node group and node judgment information provide doctors with objective and quantitative decision-making support. The application of this method can improve medical quality and safety and reduce medical risks and costs.

[0136] In one embodiment of the present invention, the judgment and early warning module includes:

[0137] An infection warning module, used for determining that the corresponding development node group is in positive development when the second node in the development node group is a positively infected node, and performing infection warning on the development node group;

[0138] A no-warning module, used for determining that the corresponding development node group is negatively developing when the second node in the development node group is a negatively infected node, and not issuing an infection warning for the development node group;

[0139] The comprehensive early warning module is used to provide infection early warning for infection cycle monitoring images through infection early warning for all development node groups.

[0140] The working principle of the above technical solution is: in the determined development node group, the infection trend of the entire development node group is judged according to the infection status of the second node (positive infection node or negative infection node). If the second node is a positive infection node, that is, its infection coefficient is greater than or equal to the preset positive infection threshold, the corresponding development node group is judged to be positive development, indicating that the infection status is gradually worsening or spreading. If the second node is a negative infection node, that is, its infection coefficient is less than the preset positive infection threshold (and may be greater than or equal to the negative infection threshold, depending on the setting of the threshold), the corresponding development node group is judged to be negative development, indicating that the infection status is gradually improving or under control. For the development node group judged to be positive development, infection warning is performed. This is achieved by issuing an alarm, displaying a warning message, or triggering a specific medical process to remind doctors or nursing staff to take timely intervention measures. For the development node group judged to be negative development, no infection warning is performed, because this means that the infection status is developing in a good direction. The above infection warning information is integrated into the infection cycle monitoring image to show in an intuitive way which time periods or areas have infection risks. This can be done by adding color coding, arrow indicators or other visual elements to the images so that doctors can quickly identify and respond to early warning signs of infection.

[0141] The technical effect of the above technical solution is: by judging the infection trend of the development node group and making targeted early warnings, the accuracy of infection early warnings can be significantly improved, and false positives and missed reports can be reduced. Infection early warnings can help medical institutions allocate medical resources more reasonably, focus limited resources on patients who need intervention the most, and improve the efficiency and quality of medical services. Timely infection early warnings and intervention measures can reduce the risk of serious complications in patients and improve patient safety and treatment effects. Infection early warnings provide doctors with objective and quantitative decision support, helping doctors make diagnostic and treatment decisions more quickly and accurately.

[0142] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for monitoring abnormal data during the entire process of wound infection, characterized in that: The monitoring method comprises: S1. Collect data of the preset whole process cycle of wound infection, obtain the whole process collection data of the cycle, calculate the node infection coefficient of each cycle time node, and establish the infection cycle monitoring image; Wherein, the S1 includes: Obtaining a preset full-process cycle for wound surface monitoring, performing periodic data collection on the preset full-process cycle, and obtaining periodic full-process collection data; Preprocessing the collected data during the entire cycle to obtain preprocessed collected data during the entire cycle; Obtaining node collection data of each preset periodic time node, and calculating the node infection coefficient of the corresponding periodic time node according to the node collection data; The calculation formula of the node infection coefficient is: Among them, R jd is the node infection coefficient, b is the number of infection monitoring indicators, S ri is the collected data of the ith infection monitoring indicator, Y ri is the data threshold of the i-th infection monitoring indicator, Q ri is the preset weight data of the ith infection monitoring indicator, T rj is the current duration of the node in the cycle time node, T zq The total duration of the preset whole process cycle; With the cycle time node as the horizontal axis, the node infection coefficient as the vertical axis, and the preset node infection threshold and the cycle initial node as the origin, an infection cycle monitoring image is established; S2. Extract positive infection data and negative infection data according to the infection cycle monitoring image information, calibrate positive infection nodes and negative infection nodes, and then obtain node connection lines; Wherein, the S2 includes: Acquire infection cycle monitoring image information, extract data information of the first quadrant of the infection cycle monitoring image, and obtain infection positive data; Extract the fourth quadrant of the infection cycle monitoring image to obtain negative infection data; Obtain the node infection coefficient of each period time node in the positive infection data and mark it as a positive infection node; Obtain the node infection coefficient of each period time node in the negatively infected data and mark it as a negatively infected node; Connect the positive infection nodes and negative infection nodes according to the periodic time node sequence to obtain the node connection line; S3, obtaining adjacent infection differences according to the node infection coefficient, comparing the adjacent infection differences with a preset infection development threshold, and then obtaining a development node group; S4. The development node group is judged to be positively developed or negatively developed, and then it is judged whether to issue an infection warning. An early warning is issued according to the judgment result to obtain early warning information.

2. According to claim 1, a method for monitoring abnormal data during the entire process of wound infection, characterized in that: The S3 includes: Obtain the difference in node infection coefficients between every two adjacent nodes in the node connection line to obtain the adjacent infection difference; Compare each adjacent infection difference with a preset infection development threshold to obtain an infection development comparison result; Obtaining adjacent nodes whose adjacent infection difference values ​​are greater than a preset infection development threshold value in the infection development comparison result, and marking them as a development node group; The node with the smaller node infection coefficient in the development node group is marked as the first node, and the node with the larger node infection coefficient in the development node group is marked as the second node; It is determined whether the second node in the development node group is a positive infection node, and node determination information is obtained.

3. According to claim 1, a method for monitoring abnormal data during the entire process of wound infection, characterized in that: The S4 includes: When the second node in the development node group is a positively infected node, the corresponding development node group is determined to be positively developed, and an infection warning is issued for the development node group; When the second node in the development node group is a negatively infected node, the corresponding development node group is determined to be negatively developed, and no infection warning is issued for the development node group; Infection warning is performed on the infection cycle monitoring image through infection warning of all development node groups.

4. A system for monitoring abnormal data during the entire period of wound infection, characterized in that: The monitoring system comprises: The periodic acquisition image establishment module is used to collect data of the preset full-process cycle of wound infection, obtain the full-process acquisition data of the cycle, calculate the node infection coefficient of each cycle time node, and establish the infection cycle monitoring image; Wherein, the periodic image acquisition establishment module includes: A data acquisition module is used to obtain a preset full-process cycle of wound surface monitoring, perform periodic data acquisition on the preset full-process cycle, and obtain periodic full-process acquisition data; A preprocessing module, used for preprocessing the data collected during the whole cycle to obtain the preprocessed data collected during the whole cycle; An infection calculation module is used to obtain node collection data of each preset periodic time node, and calculate the node infection coefficient of the corresponding periodic time node according to the node collection data; The calculation formula of the node infection coefficient is: Among them, R jd is the node infection coefficient, b is the number of infection monitoring indicators, S ri is the collected data of the ith infection monitoring indicator, Y ri is the data threshold of the i-th infection monitoring indicator, Q ri is the preset weight data of the ith infection monitoring indicator, T rj is the current duration of the node in the cycle time node, T zq The total duration of the preset whole process cycle; An image building module is used to build an infection cycle monitoring image with the cycle time node as the horizontal coordinate, the node infection coefficient as the vertical coordinate, and the preset node infection threshold and the cycle initial node as the origin; The node calibration module is used to extract positive infection data and negative infection data according to the infection cycle monitoring image information, calibrate the positive infection nodes and negative infection nodes, and then obtain the node connection lines; Wherein, the node calibration module includes: A data extraction module is used to obtain infection cycle monitoring image information, extract data information of the first quadrant of the infection cycle monitoring image, and obtain infection positive data; Extract the fourth quadrant of the infection cycle monitoring image to obtain negative infection data; The positive node calibration module is used to obtain the node infection coefficient of each period time node in the positive infection data and calibrate it as a positive infection node; The negative node calibration module is used to obtain the node infection coefficient of each period time node in the infected negative data and calibrate it as a negative infection node; A node connection module is used to connect positive infection nodes and negative infection nodes according to the periodic time node sequence to obtain node connection lines; A difference analysis module is used to obtain adjacent infection differences according to the node infection coefficient, compare the adjacent infection differences with a preset infection development threshold, and then obtain a development node group; The judgment and early warning module is used to judge the positive and negative development of the development node group, and then determine whether to issue an infection warning, issue a warning based on the judgment result, and obtain warning information.

5. According to claim 4, a system for monitoring abnormal data during the entire period of wound infection, characterized in that: The difference analysis module includes: A difference acquisition module is used to obtain the difference of the node infection coefficients of every two adjacent nodes in the node connection line to obtain the adjacent infection difference; A difference comparison module is used to compare each adjacent infection difference with a preset infection development threshold to obtain an infection development comparison result; A node development calibration module, used for obtaining adjacent nodes whose adjacent infection difference is greater than a preset infection development threshold in the infection development comparison result, and calibrating them as a development node group; A coefficient size calibration module, used for calibrating a node with a smaller node infection coefficient in the development node group as a first node, and calibrating a node with a larger node infection coefficient in the development node group as a second node; The node judgment module is used to judge whether the second node in the development node group is a positive infection node and obtain node judgment information.

6. According to claim 4, a system for monitoring abnormal data of the whole process of wound infection, characterized in that: The judgment and early warning module comprises: An infection warning module, used for determining that the corresponding development node group is in positive development when the second node in the development node group is a positively infected node, and performing infection warning on the development node group; A no-warning module, used for determining that the corresponding development node group is negatively developing when the second node in the development node group is a negatively infected node, and not issuing an infection warning for the development node group; The comprehensive early warning module is used to provide infection early warning for infection cycle monitoring images through infection early warning for all development node groups.

Images