Intelligent infusion monitoring method and system

Abstract

The invention belongs to the technical field of infusion monitoring, and provides an intelligent infusion monitoring method and system.The intelligent infusion monitoring method comprises the steps that liquid medicine information and infusion information are obtained, input liquid medicine is determined according to to-be-infused liquid medicine of a patient and in combination with an infusion sequence list, a monitoring time period is preset, and the infusion dripping speed of the input liquid medicine in the monitoring time period is subjected to stability analysis; judging whether the infusion dripping speed in the monitoring time period is stable or not; if the infusion dripping speed is stable, the infusion dripping speed is subjected to mean value calculation, and the infusion ending time is determined; the method comprises the following steps of: judging whether the infusion dripping speed is stable or not, if the infusion dripping speed is unstable, carrying out abnormal continuity analysis on the infusion dripping speed, judging whether the infusion dripping speed is continuous and abnormal or not, and if the infusion dripping speed is non-continuous and abnormal, removing abnormal infusion dripping speed data and determining the infusion ending time. The accuracy of determining the infusion ending time is ensured, and the medical staff can reasonably arrange work.

Description

Technical Field

[0001] The present invention belongs to the technical field of infusion monitoring, and in particular relates to an intelligent infusion monitoring method and system. Background Art

[0002] During the medical infusion process, accurate control and real-time monitoring of the infusion drip rate are crucial to the patient's treatment effect and safety.

[0003] The traditional infusion method mainly relies on manual observation and manual adjustment by nurses, which has many shortcomings. On the one hand, manual observation of the drip rate of infusion not only consumes a lot of manpower, but is also prone to errors and negligence. It is difficult to achieve real-time and accurate monitoring, and it is impossible to timely detect the unstable drip rate during the infusion process. The treatment effect may be affected by too fast or too slow infusion, and even cause serious harm to the patient. On the other hand, when determining the end time of infusion, there is a lack of scientific and accurate methods, and usually only relies on empirical estimates, resulting in inaccurate judgment of the end time of infusion, and it is easy to have problems such as untimely bottle replacement, which affects the normal progress of the infusion process. In addition, for the situation where multiple patients are infused at the same time, the existing technology cannot reasonably classify patients and optimize resource allocation. It is difficult for medical staff to reasonably arrange work according to the actual needs of patients and the infusion process, resulting in waste of medical resources and low work efficiency.

[0004] To this end, the present invention provides an intelligent infusion monitoring method and system. Summary of the invention

[0005] In order to make up for the deficiencies of the prior art, at least one technical problem raised in the background technology is solved.

[0006] In a first aspect, the present invention provides an intelligent infusion monitoring method, comprising the following steps: Obtaining drug solution information and infusion information, wherein the drug solution information includes the drug solution to be infused, and the infusion information includes the infusion start time and the infusion drip rate; According to the patient's infusion solution, combined with the infusion sequence table, determine the infusion solution to be infused, preset the monitoring period, and perform stability analysis on the infusion drip rate of the infusion solution in the monitoring period to determine whether the infusion drip rate in the monitoring period is stable; If the infusion drip rate is stable, the infusion drip rate is averaged to determine the end time of the infusion; if the infusion drip rate is unstable, the infusion drip rate is abnormally analyzed to determine whether the infusion drip rate is abnormally continuous. If it is abnormally discontinuous, the abnormal infusion drip rate data is eliminated to determine the effective infusion drip rate, and the average is calculated to determine the end time of the infusion; According to the end time of the infusion of the current drug solution, all patients are clustered and analyzed, and the priority treatment cluster is determined in chronological order, and the patients in the priority treatment cluster are given priority treatment.

[0007] As a further solution of the present invention: The process of performing stability analysis on the infusion drip rate of the input liquid medicine during the monitoring period is as follows: Divide the monitoring period into several monitoring time points, obtain the infusion drip rate of the currently input liquid medicine at the monitoring time points, and perform analysis and processing to obtain the standard deviation and mean value of the infusion drip rate of the currently input liquid medicine during the monitoring period. Use the coefficient of variation calculation formula to obtain the drip rate variation value; if the drip rate variation value ≥ the drip rate variation threshold, it indicates that the infusion drip rate of the currently input liquid medicine during the monitoring period is unstable; otherwise, it indicates that the infusion drip rate of the currently input liquid medicine during the monitoring period is stable.

[0008] As a further solution of the present invention: The method for obtaining the standard deviation and mean value of the infusion drip rate of the currently input liquid medicine during the monitoring period is as follows: Integrate the infusion drip rates of all monitoring time points during the monitoring period into an infusion drip rate sequence; Extract all the data in the infusion drip rate sequence and use the mean value calculation formula to obtain the mean value of the infusion drip rate of the currently input liquid medicine during the monitoring period. Extract all the data in the infusion drip rate sequence and use the standard deviation calculation formula to obtain the standard deviation of the infusion drip rate of the currently input liquid medicine during the monitoring period.

[0009] As a further solution of the present invention: The process of obtaining the infusion end time when the infusion drip rate is stable is as follows: Multiply the duration corresponding to the monitoring period by the mean value of the infusion drip rate to obtain the volume of the input liquid medicine; Divide the remaining volume of the input liquid medicine by the mean value of the infusion drip rate of the current liquid medicine to obtain the remaining infusion duration of the currently input liquid medicine. Record the end time point of the remaining infusion duration as the infusion end time of the currently input liquid medicine.

[0010] As a further solution of the present invention: When the infusion drip rate is unstable, the specific process of performing abnormal continuity analysis on the infusion drip rate is as follows: Analyze the infusion drip rate at the monitoring time points to determine the sudden change time points among the monitoring time points; Traverse all the sudden change time points on the time axis, count the number of times the sudden change time points continuously appear on the time axis, and perform a ratio process with the maximum value of the number of times the preset sudden change time points continuously appear to obtain the sudden change continuity value; if the sudden change continuity value is less than the sudden change continuity threshold, it indicates that the infusion drip rate shows non - continuous abnormality.

[0011] As a further solution of the present invention: The process of obtaining the sudden change time points among the monitoring time points is as follows: Subtract the preset infusion drip rate from the infusion drip rate at the monitoring time point, and take the absolute value of the difference to obtain the abnormal drip rate deviation value; If the abnormal drip rate deviation value is not within the preset drip rate deviation range, the corresponding monitoring time point is recorded as the sudden change time point.

[0012] As a further solution of the present invention: the process of obtaining the effective infusion drip rate is as follows: Calculate the proportion of the number of sudden change time points in the monitoring time points. If the proportion of the number of sudden change time points is less than the threshold of the proportion of the number of sudden change time points, then from the infusion drip rate sequence of the monitoring period, eliminate the abnormal drip rate corresponding to the sudden change time point, retain the infusion drip rate at the normal time point, and record the retained infusion drip rate at the normal time point as the effective drip rate.

[0013] As a further solution of the present invention: the process of obtaining the infusion end time of the infusion with unstable drip rate is as follows: Integrate the effective drip rates at all normal time points into an effective drip rate sequence, extract all the data in the effective drip rate sequence, and perform a mean calculation to obtain the mean value of the effective drip rate of the current liquid medicine. Divide the remaining input liquid medicine volume by the mean value of the effective drip rate of the current liquid medicine to obtain the remaining infusion duration of the current input liquid medicine, and record the end time of the remaining infusion duration as the infusion end time of the current input liquid medicine.

[0014] As a further solution of the present invention: the process of obtaining the priority processing cluster is as follows: Integrate the infusion end times of all patients' current input liquid medicines into an infusion end time data set, use the K-Means algorithm for clustering to determine the clustering clusters of the infusion end period; Sort all the clustering clusters of the infusion end period in chronological order to obtain a sorted table of the clustering clusters of the infusion end period, and extract the clustering cluster of the infusion end period ranked first in the sorted table of the clustering clusters of the infusion end period as the priority processing cluster.

[0015] In the second aspect, the present invention provides an intelligent infusion monitoring system, which includes: Data acquisition module: acquire liquid medicine information and infusion information, where the liquid medicine information includes the liquid medicine to be infused, and the infusion information includes the infusion start time and the infusion drip rate; Drip rate stability analysis module: determine the input liquid medicine and the preset monitoring period according to the liquid medicine to be infused by the patient and in combination with the infusion sequence table, and judge whether the infusion drip rate within the monitoring period is stable by performing stability analysis on the infusion drip rate of the input liquid medicine within the monitoring period; Abnormal continuity judgment module: if the infusion drip rate is stable, calculate the mean value of the infusion drip rate to determine the infusion end time; if the infusion drip rate is unstable, perform abnormal continuity analysis on the infusion drip rate to judge whether the infusion drip rate is abnormally continuous. If it shows non-continuous abnormality, eliminate the abnormal infusion drip rate data, determine the effective infusion drip rate, and perform a mean calculation to determine the infusion end time; Priority processing cluster generation module: According to the infusion end time of the currently input liquid medicine, cluster analysis is performed on all patients, the priority processing cluster is determined in chronological order, and the patients in the priority processing cluster are given priority treatment.

[0016] The beneficial effects of the present invention are as follows: 1. By obtaining liquid medicine information and infusion information, where the liquid medicine information includes the liquid medicine to be infused, and the infusion information includes the infusion start time and infusion drip rate. According to the liquid medicine to be infused by the patient and in combination with the infusion order list, the input liquid medicine is determined, and a preset monitoring period is set. By performing a stability analysis on the infusion drip rate of the input liquid medicine within the monitoring period, it is judged whether the infusion drip rate within the monitoring period is stable. By judging whether the infusion drip rate is stable, the present invention helps medical staff to promptly discover the situation where the drip rate is unstable during the infusion process, ensures the safety of the infusion and the treatment effect, and can effectively monitor and adjust the infusion process according to the actual situations of different patients and liquid medicines.

[0017] 2. By judging the stability of the infusion drip rate of the currently input liquid medicine within the monitoring period, the infusion end time is determined; according to the infusion end time of the currently input liquid medicine, cluster analysis is performed on all patients to determine the infusion end period clustering clusters, the priority processing cluster is determined in chronological order, and the patients in the priority processing cluster are given priority treatment. According to whether the infusion drip rate is stable, the present invention adopts different processing methods to determine the infusion end time respectively, ensuring the accuracy of the determined infusion end time, helping medical staff to reasonably arrange their work and promptly perform operations such as changing the infusion bottle. When the infusion drip rate is unstable, by judging whether the infusion drip rate is continuously abnormal or discontinuously abnormal, corresponding measures are taken for different types of abnormalities, ensuring the safety of the infusion process, and potential risks such as equipment failures or changes in the patient's condition can be promptly discovered and handled. Using the K-Means algorithm to perform cluster analysis on the infusion end times of all patients to determine the infusion end period clustering clusters and determining the priority processing cluster in chronological order enables medical staff to reasonably arrange their work according to the sequence of patients' infusion ends, give priority treatment to the patients in the priority processing cluster, improve the efficiency of medical work, realize the optimal allocation of medical resources, and avoid waste of resources and disorderliness of work. Brief Description of the Drawings

[0018] The present invention will be further described below with reference to the accompanying drawings.

[0019] Figure 1 is the step flow chart of the intelligent infusion monitoring method according to the embodiment of the present invention; Figure 2 is the system block diagram of the intelligent infusion monitoring system according to the embodiment of the present invention. Detailed Embodiments

[0020] In order to make the technical means, creative features, achieved purposes and effects of the present invention easy to understand, the present invention will be further described below in conjunction with specific embodiments.

[0021] Embodiment 1:

[0022] Please refer to Figure 1 As shown, the intelligent infusion monitoring method described in the embodiment of the present invention includes the following steps: Step 1: Obtain liquid medicine information and infusion information. Among them, the liquid medicine information includes the liquid medicine to be infused, and the infusion information includes the infusion start time and the infusion drip rate; It can be understood that both the liquid medicine information and the infusion information are determined by relevant medical staff according to the actual situation of the patient. Different liquid medicines to be infused have different suitable infusion drip rates, and different patients also have different infusion drip rates for the same liquid medicine to be infused; When the nurse prepares the infusion for the patient, a scanning device is used to scan the electronic label on the infusion bottle. The scanning device transmits the read liquid medicine information to the data processing terminal, and the data processing terminal stores this information in the database. At the same time, the nurse determines the order of the liquid medicine to be infused according to the actual situation of the patient on the data processing terminal according to the doctor's order, and the system integrates it into an infusion order list; the infusion drip rate is obtained through an intelligent infusion pump; Step 2: According to the liquid medicine to be infused by the patient, combined with the infusion order list, determine the infused liquid medicine, preset the monitoring period, and judge whether the infusion drip rate within the monitoring period is stable by analyzing the stability of the infusion drip rate of the infused liquid medicine within the monitoring period; Extract the first liquid medicine to be infused in the infusion order list and record it as the infused liquid medicine; Divide the monitoring period into several monitoring time points with equal time intervals, obtain the infusion drip rate of the current infused liquid medicine at the monitoring time points, and integrate the infusion drip rates of all monitoring time points within the monitoring period into an infusion drip rate sequence , where n represents the total number of monitoring time points; Extract all the data in the infusion drip rate sequence and use the mean calculation formula to obtain the mean value of the infusion drip rate of the current infused liquid medicine within the monitoring period. Extract all the data in the infusion drip rate sequence and use the standard deviation calculation formula to obtain the standard deviation of the infusion drip rate of the current infused liquid medicine within the monitoring period. Use the coefficient of variation calculation formula to perform a ratio process on the standard deviation of the infusion drip rate of the current infused liquid medicine within the monitoring period and the mean value of the infusion drip rate to obtain the drip rate variation value of the infusion drip rate of the current infused liquid medicine within the monitoring period; In some embodiments, the drip rate variation value is compared with the drip rate variation threshold. The specific comparison process is as follows: If the drip rate variation value is greater than or equal to the drip rate variation threshold, it means that the infusion drip rate of the current infused liquid medicine within the monitoring period is unstable; If the drip rate variation value is less than the drip rate variation threshold, it indicates that the infusion drip rate of the current input liquid medicine is stable during the monitoring period; Exemplarily, assume that the infusion drip rate sequence (unit: drops per minute) is (30, 32, 35, 28, 34, 36, 31, 29, 33, 30), Calculate the mean value: (30 + 32 + 35 + 28 + 34 + 36 + 31 + 29 + 33 + 30) / 10 = 32.8; Calculate the standard deviation: Calculate the sum of the squares of the differences between each infusion drip rate data in the infusion drip rate sequence and the mean value, that is: 7.84 + 0.64 + 5.76 + 23.04 + 1.44 + 10.24 + 3.24 + 14.44 + 0.04 + 7.84 = 74.48, then the standard deviation is: ; The drip rate variation value is: 2.729 / 32.8 * 100% = 8.30%; During the clinical infusion process, medical staff need to quickly judge the drip rate stability. Usually, the drip rate fluctuation range is controlled within 10% as stable. Set the drip rate variation threshold at 10%. The drip rate variation value 8.30% < 10%, which indicates that the infusion drip rate of the current input liquid medicine is stable during the monitoring period; The function of determining the drip rate variation value is as follows: Function 1: By judging whether the infusion drip rate of the input liquid medicine is stable during the monitoring period, it helps medical staff to timely discover possible abnormal situations during the infusion process, such as too fast or too slow drip rate, and too large drip rate fluctuations, etc., so as to take corresponding measures for adjustment to ensure the safety and effectiveness of the infusion treatment; Function 2: In medical quality management, effective monitoring and control of the infusion drip rate is an important part. Determining the drip rate variation value helps to standardize the infusion operation, improve the quality and safety of medical care. At the same time, this also provides data support for the evaluation and improvement of medical quality, helps the hospital continuously improve the infusion management process, and enhances the overall medical service level; The technical solution of this embodiment is: Obtain liquid medicine information and infusion information. Among them, the liquid medicine information includes the liquid medicine to be infused, and the infusion information includes the infusion start time and the infusion drip rate. According to the liquid medicine to be infused by the patient, combined with the infusion sequence table, determine the input liquid medicine, preset the monitoring period, and judge whether the infusion drip rate is stable by analyzing the stability of the infusion drip rate of the input liquid medicine during the monitoring period. By judging whether the infusion drip rate is stable, the present invention helps medical staff to timely discover the situation of unstable drip rate during the infusion process, ensure the infusion safety and treatment effect, and can effectively monitor and adjust the infusion process according to the actual situations of different patients and liquid medicines.

[0023] Embodiment 2:

[0024] See also Figure 2 As shown, the intelligent infusion monitoring method described in the embodiment of the present invention further includes the following steps: Step 3: If the infusion drip rate of the current infusion liquid is stable during the monitoring period, the infusion drip rate is averaged to determine the end time of the infusion; if the infusion drip rate of the current infusion liquid is unstable during the monitoring period, the infusion drip rate is abnormally analyzed to determine whether the infusion drip rate is abnormally continuous. If it is abnormally discontinuous, the abnormal infusion drip rate data is eliminated to determine the effective infusion drip rate, and the effective infusion drip rate is averaged to determine the end time of the infusion; The remaining amount of the currently input medicine liquid is collected through the weighing sensor. Based on the stability of the infusion drip rate of the currently input medicine liquid during the monitoring period, the duration corresponding to the monitoring period is multiplied by the average infusion drip rate to obtain the amount of medicine liquid that has been input; The remaining amount of the input drug solution is processed by ratio with the average drip rate of the current drug solution infusion to obtain the remaining infusion time of the current drug solution infusion, and the end time of the remaining infusion time is recorded as the end time of the infusion of the current drug solution infusion; Based on the instability of the infusion drip rate of the current infusion liquid during the monitoring period, the infusion drip rate at the monitoring time point is subtracted from the preset infusion drip rate, and the absolute value of the difference is taken to obtain the abnormal drip rate deviation value; If the abnormal drip rate deviation value is not within the preset drip rate deviation range, the corresponding monitoring time point is recorded as the sudden change time point; If the abnormal drip rate deviation value is within the preset drip rate deviation range, the corresponding monitoring time point is recorded as a normal time point; Traverse all sudden change time points on the time axis, count the number of times the sudden change time points appear continuously on the time axis, and perform ratio processing on the maximum value of the number of consecutive appearances of the preset sudden change time points to obtain the sudden change continuous value; It should be explained that if the number of times the sudden change time point appears on the time axis is greater than two, it means that the sudden change time point appears continuously on the time axis, and the maximum number of times the sudden change time point appears continuously is set by those skilled in the art based on historical experience; If the sudden change continuous value is greater than or equal to the sudden change continuous threshold, it means that the infusion drip rate is abnormal in continuity. Close the infusion clamp, suspend the infusion, and prompt the medical staff to intervene manually to check the equipment or patient's condition. If the sudden change continuous value is less than the sudden change continuous threshold, it means that the infusion drip rate is abnormally discontinuous; Based on the discontinuous abnormality of the infusion drip rate, the number of sudden change time points is counted, and the proportion of the number of sudden change time points is calculated. If the proportion of the number of sudden change time points is greater than or equal to the threshold of the proportion of the number of sudden change time points, the infusion clamp is closed, the infusion is suspended, and the medical staff is prompted to intervene manually to check the changes in the equipment or the patient's condition; If the proportion of the number of occurrences at the sudden change time point is less than the threshold of the proportion of the number of occurrences at the sudden change time point, a rejection signal is generated; Based on the rejection signal, from the infusion drip rate sequence of the monitoring period, the abnormal drip rate corresponding to the sudden change time point is rejected, and the infusion drip rate at the normal time point is retained. The infusion drip rate at the normal time point is recorded as the effective drip rate, and the effective drip rates at all normal time points are integrated into an effective drip rate sequence , where m represents the total number of normal time points; Extract all the data in the effective drip rate sequence and calculate the mean value to obtain the effective drip rate mean of the current liquid medicine. The remaining input liquid medicine volume is divided by the effective drip rate mean of the current liquid medicine to obtain the remaining infusion duration of the current input liquid medicine. The end time of the remaining infusion duration is recorded as the infusion end time of the current input liquid medicine; It can be understood that at the infusion end time, the infusion clamp is closed to remind the medical staff to change the infusion bottle; Step four: According to the infusion end time of the current input liquid medicine, perform cluster analysis on all patients to determine the cluster of the infusion end period, determine the priority cluster in chronological order, and give priority to the patients in the priority cluster; Integrate the infusion end times of all patients' current input liquid medicines into an infusion end time data set; Use the K-Means algorithm for clustering to determine the number of clusters K; Specifically, the elbow method can be used to determine the number of clusters K, and calculate the sum of squared errors SSE under different K values, where, is the jth cluster, is the Euclidean distance from the data point x to the cluster center ; Set the candidate range of K. For each K, use the K-Means clustering algorithm to cluster the data and calculate the corresponding SSE; Taking K as the abscissa and SSE as the ordinate, draw the K-SSE curve, calculate the change rate of the decrease in SSE corresponding to adjacent K values, and select the K value that becomes flat after the sudden drop in the change rate as the optimal number of clusters; Exemplarily, calculate the SSE corresponding to different Ks for the infusion end time data set, set the candidate range of K as 1, 2, 3, 4, 5, and the SEE corresponding to different Ks is 1000, 600, 300, 200, 150; after drawing the K-SSE curve, when K = 3, the decrease speed significantly slows down, and K = 3 is the elbow point and can be regarded as the optimal number of clusters; Regarding the infusion end time as a point on the time axis, calculate the time difference between the infusion end times of different patients as the distance, and randomly select the infusion end times of K patients as the initial cluster centers; For each patient, calculate the time difference between the end time of their infusion and each cluster center, and assign them to the cluster with the smallest time difference. Recalculate the average value of the infusion end times of all patients in each cluster, and use it as the new cluster center. Continuously repeat the above steps of assigning patients to clusters and updating the cluster centers until the cluster centers no longer change or reach the preset number of iterations, and determine the cluster of infusion end periods. Sort all the clusters of infusion end periods in chronological order to obtain a sorted table of clusters of infusion end periods. Extract the cluster of infusion end periods ranked first in the sorted table of clusters of infusion end periods as the priority processing cluster, and give priority to processing the patients in the priority processing cluster. Exemplarily, if the clustering result is 3 clusters, the end time of cluster 1 is 10:00 (5 people), the end time of cluster 2 is 10:15 (8 people), and the end time of cluster 3 is 10:30 (3 people). The nurse can give priority to processing cluster 1 in chronological order and prepare 5 doses of the next-stage medicine; centrally process the 8 people in cluster 2 at 10:15, and so on, to avoid frequent trips to the ward and optimize the utilization of time. In summary, this step uses the K-Means algorithm to cluster patients with the same infusion end time, determines the optimal number of clusters K through the elbow method, and optimizes the initial cluster centers using the K-Means++ algorithm. After iterative calculation until the cluster centers converge; according to the chronological order of the clusters of infusion end periods, determine the priority processing cluster, and give priority to processing the patients in the priority processing cluster. Function 1: Through cluster analysis, the hospital can understand the distribution of patient groups with infusion endings in different time periods. For the time periods when the infusion end times are relatively concentrated, it can reasonably arrange nursing staff for patrol, needle removal, etc., improve the efficiency and quality of nursing work, and avoid waste of human resources. Function 2: It can analyze the infusion characteristics of different groups of patients based on the clustering results and optimize the infusion process. Patients in different clusters may have different characteristics and needs. Patients with earlier infusion end times may have better physical conditions and recover faster, while patients with later infusion end times may have more complex conditions or weaker bodies. Medical staff can provide more targeted care for different groups of patients based on the clustering results, improving patient satisfaction and treatment effects. The technical solution of this embodiment is as follows: If the infusion drip rate of the currently input liquid medicine is stable during the monitoring period, the average value of the infusion drip rate is calculated to determine the infusion end time; if the infusion drip rate of the currently input liquid medicine is unstable during the monitoring period, an abnormal continuity analysis is performed on the infusion drip rate to determine whether the infusion drip rate is abnormally continuous. If it is discontinuously abnormal, the abnormal infusion drip rate data is excluded, the effective infusion drip rate is determined, the average value of the effective infusion drip rate is calculated to determine the infusion end time, and clustering analysis is performed on all patients according to the infusion end time of the currently input liquid medicine to determine the clustering cluster of the infusion end period. The priority processing cluster is determined in chronological order, and the patients in the priority processing cluster are given priority treatment. According to whether the infusion drip rate is stable or not, the present invention adopts different processing methods to determine the infusion end time, ensuring the accuracy of the determined infusion end time, helping medical staff to reasonably arrange work and perform operations such as changing the infusion bottle in a timely manner. When the infusion drip rate is unstable, by judging whether the infusion drip rate is continuously abnormal or discontinuously abnormal, corresponding measures are taken for different types of abnormalities, ensuring the safety of the infusion process, and potential risks such as equipment failures or patient condition changes can be detected and handled in a timely manner. Using the K-Means algorithm to perform clustering analysis on the infusion end times of all patients to determine the clustering cluster of the infusion end period and determining the priority processing cluster in chronological order can enable medical staff to reasonably arrange work according to the order of patients' infusion ends, give priority treatment to the patients in the priority processing cluster, improve the efficiency of medical work, realize the optimal allocation of medical resources, and avoid waste of resources and disorderliness of work.

[0025] Embodiment 3:

[0026] Please refer to Figure 2 as shown, the intelligent infusion monitoring system described in the embodiment of the present invention includes the following modules: Data acquisition module: Acquire liquid medicine information and infusion information. Among them, the liquid medicine information includes the liquid medicine to be infused, and the infusion information includes the infusion start time and the infusion drip rate; The nurse determines the order of the liquid medicine to be infused according to the actual situation of the patient on the data processing terminal, and the system integrates it into an infusion order list; Obtain the infusion drip rate through the intelligent infusion pump; Drip rate stability analysis module: According to the liquid medicine to be infused by the patient, combined with the infusion order list, determine the input liquid medicine, preset the monitoring period, and judge whether the infusion drip rate within the monitoring period is stable by performing stability analysis on the infusion drip rate of the input liquid medicine within the monitoring period; Extract the first liquid medicine to be infused in the infusion order list and record it as the input liquid medicine; Preset the monitoring period, divide the monitoring period into several monitoring time points with equal time intervals, obtain the infusion drip rate of the current infusion drug solution at the monitoring time point, and integrate the infusion drip rates of all monitoring time points in the monitoring period into an infusion drip rate sequence , where n represents the total number of monitoring time points; Extract all data in the infusion drip rate sequence and use the mean calculation formula to obtain the mean infusion drip rate of the current input drug solution during the monitoring period; extract all data in the infusion drip rate sequence and use the standard deviation calculation formula to obtain the standard deviation of the infusion drip rate of the current input drug solution during the monitoring period; use the coefficient of variation calculation formula to perform ratio processing on the standard deviation of the infusion drip rate of the current input drug solution during the monitoring period and the mean infusion drip rate to obtain the drip rate variation value of the infusion drip rate of the current input drug solution during the monitoring period; If the drip rate variation value is greater than or equal to the drip rate variation threshold, it means that the infusion drip rate of the current input drug solution during the monitoring period is unstable; otherwise, it means that the infusion drip rate of the current input drug solution during the monitoring period is stable; Abnormal continuity judgment module: If the infusion drip rate of the current input drug solution is stable during the monitoring period, the infusion drip rate is averaged to determine the end time of the infusion; if the infusion drip rate of the current input drug solution is unstable during the monitoring period, the infusion drip rate is abnormally analyzed to determine whether the infusion drip rate is abnormally continuous. If it is discontinuously abnormal, the abnormal infusion drip rate data is eliminated to determine the effective infusion drip rate, and the effective infusion drip rate is averaged to determine the end time of the infusion; The remaining amount of the currently input medicine liquid is collected through the weighing sensor. Based on the stability of the infusion drip rate of the currently input medicine liquid during the monitoring period, the duration corresponding to the monitoring period is multiplied by the average infusion drip rate to obtain the amount of medicine liquid that has been input; The remaining amount of the input drug solution is processed by ratio with the average drip rate of the current drug solution infusion to obtain the remaining infusion time of the current drug solution infusion, and the end time of the remaining infusion time is recorded as the end time of the infusion of the current drug solution infusion; Based on the instability of the infusion drip rate of the current infusion liquid during the monitoring period, the infusion drip rate at the monitoring time point is subtracted from the preset infusion drip rate, and the absolute value of the difference is taken to obtain the abnormal drip rate deviation value; If the abnormal drip rate deviation value is not within the preset drip rate deviation range, the corresponding monitoring time point is recorded as the sudden change time point; If the abnormal drip rate deviation value is within the preset drip rate deviation range, the corresponding monitoring time point is recorded as a normal time point; Traverse all sudden change time points on the time axis, count the number of times the sudden change time points appear continuously on the time axis, and perform ratio processing on the maximum value of the number of consecutive appearances of the preset sudden change time points to obtain the sudden change continuous value; If the sudden change continuous value is greater than or equal to the sudden change continuous threshold, it indicates that the infusion drip rate shows continuous abnormality. Close the infusion clamp, pause the infusion, and prompt the medical staff to perform manual intervention to check for equipment or patient condition changes; If the sudden change continuous value is less than the sudden change continuous threshold, it indicates that the infusion drip rate shows discontinuous abnormality; Based on the discontinuous abnormality of the infusion drip rate, count the number of occurrences of the sudden change time points, calculate the proportion of the number of occurrences of the sudden change time points. If the proportion of the number of occurrences of the sudden change time points is greater than or equal to the proportion threshold of the number of occurrences of the sudden change time points, close the infusion clamp, pause the infusion, and prompt the medical staff to perform manual intervention to check for equipment or patient condition changes; If the proportion of the number of occurrences of the sudden change time points is less than the proportion threshold of the number of occurrences of the sudden change time points, generate an exclusion signal; Based on the exclusion signal, in the infusion drip rate sequence of the monitoring period, exclude the abnormal drip rates corresponding to the sudden change time points, retain the infusion drip rates at normal time points, record the infusion drip rates at normal time points as effective drip rates, and integrate all the effective drip rates at normal time points into an effective drip rate sequence , where m represents the total number of normal time points; Extract all the data in the effective drip rate sequence and perform mean calculation to obtain the effective drip rate mean of the current liquid medicine. Perform a ratio process on the remaining input liquid medicine volume and the effective drip rate mean of the current liquid medicine to obtain the remaining infusion duration of the current input liquid medicine, and record the end time of the remaining infusion duration as the infusion end time of the current input liquid medicine; Priority processing cluster generation module: According to the infusion end time of the current input liquid medicine, perform clustering analysis on all patients to determine the clustering clusters in the infusion end period, determine the priority processing clusters in chronological order, and perform priority processing on the patients in the priority processing clusters; Integrate the infusion end times of all patients' current input liquid medicines into an infusion end time data set; Use the K-Means algorithm for clustering to determine the number of clusters K. Regarding the infusion end times as points on the time axis according to the number of clusters K, calculate the time difference between the infusion end times of different patients as the distance, and randomly select the infusion end times of K patients as the initial clustering centers; For each patient, calculate the time difference between its infusion end time and each clustering center, and assign it to the cluster with the smallest time difference; Recalculate the average value of the infusion end times of all patients in each cluster, and use it as the new clustering center; Continuously repeat the above steps of assigning patients to clusters and updating the clustering centers until the clustering centers no longer change or reach the preset number of iterations to determine the clustering clusters in the infusion end period; Sort all the infusion end time period clustering clusters in chronological order to obtain an infusion end time period clustering cluster sorting table. Extract the infusion end time period clustering cluster ranked first in the infusion end time period clustering cluster sorting table as the priority processing cluster, and give priority to the patients in the priority processing cluster.

[0027] The above has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification only illustrates the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent infusion monitoring method, characterized in that: include: Obtaining drug solution information and infusion information, wherein the drug solution information includes the drug solution to be infused, and the infusion information includes the infusion start time and the infusion drip rate; According to the patient's infusion solution, combined with the infusion sequence table, determine the infusion solution to be infused, preset the monitoring period, and perform stability analysis on the infusion drip rate of the infusion solution in the monitoring period to determine whether the infusion drip rate in the monitoring period is stable; If the infusion drip rate is stable, the infusion drip rate is averaged to determine the end time of the infusion; if the infusion drip rate is unstable, the infusion drip rate is abnormally analyzed to determine whether the infusion drip rate is abnormally continuous. If it is abnormally discontinuous, the abnormal infusion drip rate data is eliminated to determine the effective infusion drip rate, and the average is calculated to determine the end time of the infusion; According to the end time of the infusion of the current drug solution, all patients are clustered and analyzed, and the priority treatment cluster is determined in chronological order, and the patients in the priority treatment cluster are given priority treatment.

2. The intelligent infusion monitoring method according to claim 1, characterized in that: The process of performing stability analysis on the drip rate of the infusion of the drug solution during the monitoring period is as follows: The monitoring period is divided into several monitoring time points, and the infusion drip rate of the current input drug solution at the monitoring time point is obtained, and the infusion drip rate standard deviation and the infusion drip rate mean of the current input drug solution in the monitoring period are obtained, and the drip rate variation value is obtained using the coefficient of variation calculation formula; if the drip rate variation value ≥ the drip rate variation threshold, it indicates that the infusion drip rate of the current input drug solution in the monitoring period is unstable; otherwise, it indicates that the infusion drip rate of the current input drug solution in the monitoring period is stable.

3. The intelligent infusion monitoring method according to claim 2, characterized in that: The method for obtaining the standard deviation of the infusion drip rate and the mean value of the infusion drip rate of the current infusion liquid during the monitoring period is as follows: Integrate the infusion drip rates at all monitoring time points within the monitoring period into an infusion drip rate sequence; Extract all data in the infusion drip rate sequence and use the mean calculation formula to obtain the mean infusion drip rate of the current input drug solution during the monitoring period. Extract all data in the infusion drip rate sequence and use the standard deviation calculation formula to obtain the standard deviation of the infusion drip rate of the current input drug solution during the monitoring period.

4. The intelligent infusion monitoring method according to claim 3, characterized in that: The process of obtaining the end time of the infusion with a stable infusion drip rate is as follows: The duration corresponding to the monitoring period is multiplied by the average infusion drip rate to obtain the amount of liquid medicine that has been infused; The remaining amount of the input medicine liquid is ratioed to the average infusion drip rate of the current medicine liquid to obtain the remaining infusion time of the current medicine liquid, and the end time point of the remaining infusion time is recorded as the infusion end time of the current medicine liquid.

5. The intelligent infusion monitoring method according to claim 4, characterized in that: The infusion drip rate is unstable, and the specific process of abnormal continuity analysis of the infusion drip rate is as follows: Analyze the infusion drip rate at the monitoring time point to determine the sudden change time point in the monitoring time point Traverse all the sudden change time points on the time axis, count the number of consecutive appearances of the sudden change time points on the time axis, and perform ratio processing with the maximum value of the consecutive appearance of the preset sudden change time points to obtain the sudden change continuity value; if the sudden change continuity value is less than the sudden change continuity threshold, it means that the infusion drip rate shows a discontinuous abnormality.

6. The intelligent infusion monitoring method according to claim 5, characterized in that: The process of obtaining the sudden change time point in the monitoring time point is as follows: The infusion drip rate at the monitoring time point is subtracted from the preset infusion drip rate, and the absolute value of the difference is taken to obtain the abnormal drip rate deviation value; If the abnormal dripping rate deviation value is not within the preset dripping rate deviation range, the corresponding monitoring time point is recorded as the sudden change time point.

7. The intelligent infusion monitoring method according to claim 5, characterized in that: The process of obtaining the effective infusion drip rate is as follows: Calculate the proportion of sudden change time points in the monitoring time points. If the proportion of sudden change time points is less than the threshold of the proportion of sudden change time points, then remove the abnormal drip rate corresponding to the sudden change time points from the infusion drip rate sequence of the monitoring period, and retain the infusion drip rate at the normal time points. The infusion drip rate retained at the normal time points is recorded as the effective drip rate.

8. The intelligent infusion monitoring method according to claim 5, characterized in that: The process of obtaining the end time of the infusion with unstable infusion drip rate is as follows: The effective drip rates of all normal time points are integrated into an effective drip rate sequence, all data in the effective drip rate sequence are extracted, and the mean is calculated to obtain the mean effective drip rate of the current medicine solution, the remaining input medicine solution volume is processed with the mean effective drip rate of the current medicine solution to obtain the remaining infusion time of the current input medicine solution, and the end time of the remaining infusion time is recorded as the end time of the infusion of the current input medicine solution.

9. The intelligent infusion monitoring method according to claim 5, characterized in that: The acquisition process of the priority processing cluster is as follows: The end time of the infusion of all patients' current medications is integrated into the infusion end time dataset, and the K-Means algorithm is used for clustering to determine the clustering clusters of the infusion end time period; All the infusion end time period clusters are sorted in chronological order to obtain an infusion end time period cluster sorting table, and the infusion end time period cluster that is first in the infusion end time period cluster sorting table is extracted as a priority processing cluster.

10. Intelligent infusion monitoring system, characterized in that: The system is used to execute the method described in any one of claims 1 to 9, and the system comprises: Data acquisition module: acquires drug solution information and infusion information, wherein the drug solution information includes the drug solution to be infused, and the infusion information includes the infusion start time and the infusion drip rate; Drip rate stability analysis module: Determine the infusion rate according to the patient's infusion solution and the infusion sequence table, preset the monitoring period, and perform stability analysis on the drip rate of the infusion solution during the monitoring period to determine whether the drip rate is stable during the monitoring period; Abnormal continuity judgment module: If the infusion drip rate is stable, the infusion drip rate is averaged to determine the end time of the infusion; if the infusion drip rate is unstable, the infusion drip rate is abnormally analyzed to determine whether the infusion drip rate is abnormally continuous. If it is abnormally discontinuous, the abnormal infusion drip rate data is eliminated to determine the effective infusion drip rate, and the average is calculated to determine the end time of the infusion; Priority cluster generation module: Based on the end time of the current infusion of the drug solution, cluster analysis is performed on all patients, priority clusters are determined in chronological order, and patients in the priority clusters are given priority treatment.

Images