Intravenous therapy information data tracking method, system and equipment
By analyzing heart rate, respiratory rate, blood pressure, and intravenous drip rate data during intravenous therapy, clustering and similarity analysis were used to address the accuracy limitations of traditional intravenous therapy data tracking methods, achieving more accurate tracking and similarity matching of intravenous therapy information.
Patent Information
- Application Number
- CN202610251536.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-03-03
- Publication Date
- 2026-04-28
AI Technical Summary
Traditional methods for tracking intravenous therapy data cannot accurately extract relevant information from patients during intravenous therapy and lack matching and comparison with big data, making it difficult to provide scientific and robust data support for intravenous therapy.
By acquiring the patient's heart rate, respiratory rate, blood pressure, and intravenous drip rate for each preset time period, feature vectors are formed, cluster analysis is performed to determine information contribution and effective factors, and combined with differences in intravenous drip rate, threshold segmentation algorithm and similarity analysis are used to track intravenous treatment data.
It improves the accuracy and reliability of intravenous treatment data, and can more accurately reflect the abnormal characteristics and information contribution effectiveness of patients during intravenous treatment, and realizes the matching of intravenous treatment similarity among patients in the same disease group.
Smart Images
Figure CN121938658A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of intravenous therapy data tracking technology, specifically to a method, system, and device for tracking intravenous therapy information data. Background Technology
[0002] With the continuous advancement of modern medicine and the widespread adoption of digital information, intravenous therapy has evolved from a simple nursing procedure into a multidisciplinary and multi-layered process involving knowledge and skills. Intravenous therapy involves the delivery of medications, blood, and blood products into the bloodstream via venous access, offering advantages such as rapid administration and fast onset of action. However, intravenous therapy also carries certain risks, such as complications and phlebitis. When patients are unable to provide subjective feedback on their condition, intravenous therapy data tracking, as an innovative technology in the field of medical data informatization, can improve the safety and efficiency of treatment through real-time monitoring and data recording of the intravenous therapy process.
[0003] Traditional methods for tracking intravenous therapy information data typically rely on simple infusion warnings and data aggregation, which fail to accurately extract relevant information from patients during intravenous therapy and lack matching and comparison with big data, making it difficult to provide scientific and robust data support for intravenous therapy. Summary of the Invention
[0004] In a first aspect, embodiments of this application provide a method for tracking intravenous therapy information data, the method comprising the following steps: The heart rate, respiratory rate, blood pressure and intravenous drip rate of each patient at each preset time period are obtained and used to form the feature vector of each patient at each time period. The feature vectors of each patient at all times within each time period are clustered to obtain multiple clusters. Based on the similarity between the feature vector at each time period and all other feature vectors in its cluster, as well as the difference between the feature vector at each time period and all feature vectors in other clusters, the information contribution of each patient at each time period is determined. Based on the differences between the information contribution of each moment within each time period and the information contribution of all other moments, as well as the degree of confusion in the information contribution of all moments, the effective information factors of each patient within each time period are determined. Based on the differences in intravenous drip rate between each time period and all times in its neighborhood, and combined with the aforementioned effective information factors, the characteristic factors of intravenous treatment for each patient at each time period are determined. A threshold segmentation algorithm is used to obtain the segmentation threshold of the intravenous treatment feature factors at all times within each time period. The times when the intravenous treatment feature factors are greater than or equal to the segmentation threshold are recorded as the data tracking times. Based on the differences between the feature vectors of each patient at any time period and the feature vectors of all other patients in the same disease group at any time period, the similarity of intravenous treatment between each patient and all other patients in the same disease group is determined, and the intravenous treatment data of the patients is tracked.
[0005] Preferably, the method for determining the information contribution of each patient at each time point within each time period is as follows: Based on the similarity between the feature vector of each patient at each time point within each time period and all other feature vectors in its cluster, the information similarity of each patient at each time point within each time period is determined. Analyze the mean difference between the feature vector of each patient at each time point within each time period and the feature vectors of all remaining clusters excluding the patient's own cluster; Based on the information similarity and the mean, the information contribution of each patient at each time point within each time period is determined.
[0006] Preferably, the information similarity of each patient at each time point within each time period is the average of the similarity between the feature vector of each patient at each time point within each time period and all other feature vectors in its cluster.
[0007] Preferably, the information contribution of each patient at each time point within each time period is further determined as the sum of the information similarity of each patient at each time point within each time period and the mean value.
[0008] Preferably, the expression for the effective information factor of each patient at each time point within each time period is: In the formula, The effective factor representing the information at time j within the i-th time period of the i-th patient; Shannon entropy represents the information contribution of the i-th patient at all times within the i-th time period; They represent the j-th and j-th time periods of the i-th patient, respectively. The information contribution at any given moment; This represents the number of all moments within the i-th time period for the i-th patient.
[0009] Preferably, the expression for the intravenous treatment characteristic factors of each patient at each time point within each time period is as follows: In the formula, This represents the characteristic factor of intravenous treatment at time j within the i-th time period for patient I. This represents the difference in intravenous drip rate between patient I at time j within the i-th time period and between patient I at time u within its neighborhood. This represents the number of intravenous drip rates at all times within the i-th time period for the i-th patient; norm() represents the normalization function.
[0010] Preferably, determining the similarity of intravenous treatment between each patient and all other patients in the same disease group, and tracking the patients' intravenous treatment data, includes: The feature vectors of all data tracking moments for each patient in each time period are used to form the intravenous treatment tracking matrix for each time period. Based on the difference between the intravenous treatment tracking matrix of each patient in all time periods and the intravenous treatment tracking matrix of other patients in the same disease group in all time periods, the similarity of intravenous treatment between each patient and other patients in the same disease group is determined. The similarity of intravenous treatment for each patient to that of all other patients in the same disease group is stored.
[0011] Preferably, the similarity of intravenous treatment between each patient and the other patients in the same disease group is the reciprocal of the mean square error of the intravenous treatment tracking matrix of each patient at all time periods and the intravenous treatment tracking matrix of the other patients in the same disease group at all time periods.
[0012] Secondly, embodiments of this application provide an intravenous therapy information data tracking system, the system comprising: The venous data acquisition module is used to acquire the heart rate, respiratory rate, blood pressure and intravenous drip rate of each patient at each preset time period, and to form the feature vector of each patient at each time period. The venous data analysis module is used to cluster the feature vectors of each patient at all times within each time period to obtain multiple clusters. Based on the similarity between the feature vector at each time period and all other feature vectors in its cluster, as well as the difference between the feature vector at each time period and all feature vectors in other clusters, the information contribution of each patient at each time period is determined. Based on the differences between the information contribution of each moment within each time period and the information contribution of all other moments, as well as the degree of confusion in the information contribution of all moments, the effective information factors of each patient within each time period are determined. Based on the differences in intravenous drip rate between each time period and all times in its neighborhood, and combined with the aforementioned effective information factors, the characteristic factors of intravenous treatment for each patient at each time period are determined. The vein data storage module is used to obtain the segmentation threshold of the vein treatment feature factors at all times within each time period using a threshold segmentation algorithm, and to record the time when the vein treatment feature factor is greater than or equal to the segmentation threshold as the data tracking time. Based on the differences between the feature vectors of each patient at any time period and the feature vectors of all other patients in the same disease group at any time period, the similarity of intravenous treatment between each patient and all other patients in the same disease group is determined, and the intravenous treatment data of the patients is tracked.
[0013] Thirdly, embodiments of this application also provide a device for tracking intravenous treatment information data, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of any of the above-described methods for tracking intravenous treatment information data.
[0014] As can be seen from the above embodiments, the intravenous therapy information data tracking method provided in this application has at least the following beneficial effects: This application determines the information contribution of each patient at each time period by analyzing the similarity between the feature vector of each patient at each time period and all other feature vectors in its cluster, as well as the difference between the feature vector at each time period and all feature vectors in other clusters. Its beneficial effect is that it comprehensively considers the abnormal characteristics and information validity of intravenous treatment-related data during the patient's intravenous treatment process. Based on the difference between the information contribution at each time period and the information contribution at all other times, as well as the degree of disorder in the information contribution at all times, it determines the information effectiveness factor at each time period for each patient. Its beneficial effect is that it more accurately reflects the effectiveness of the patient's intravenous treatment information data at each moment. By analyzing the difference between the intravenous drip rate at each time period and its neighborhood, combined with the aforementioned information effectiveness factor, it determines the intravenous treatment characteristic factor at each time period for each patient, and uses this to obtain intravenous treatment similarity, completing the matching of similar patients for each patient in the medical information database. Its beneficial effect is that, based on the effective analysis of information contribution, it further incorporates the consideration of short-term changes in intravenous drip rate, more accurately segmenting the moments when effective information for the patient occurs during intravenous treatment.
[0015] This application comprehensively analyzes relevant data during intravenous treatment, determines the similarity of intravenous treatment among patients within the same disease group, improves the accuracy of extracting effective information, and enhances the credibility of intravenous treatment-related data. Attached Figure Description
[0016] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0017] Figure 1 A flowchart illustrating the steps of a method for tracking intravenous therapy information data, provided in one embodiment of this application; Figure 2 This is a schematic diagram of the process for extracting characteristic factors of intravenous therapy according to an embodiment of this application; Figure 3 This is a block diagram of an intravenous therapy information data tracking system provided in one embodiment of this application. Detailed Implementation
[0018] To further illustrate the technical means and effects adopted by this application to achieve the intended purpose of the invention, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a method, system, and device for tracking intravenous therapy information data according to this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.
[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.
[0020] The following description, in conjunction with the accompanying drawings, details the specific scheme of the intravenous therapy information data tracking method, system, and equipment provided in this application.
[0021] Please see Figure 1 The diagram illustrates a flowchart of a method for tracking intravenous therapy information data according to an embodiment of this application. The method includes the following steps: Step S1: Obtain the heart rate, respiratory rate, blood pressure and intravenous drip rate of each patient at each preset time period.
[0022] During the patient's intravenous treatment, the heart rate, respiratory rate, blood pressure and intravenous drip rate of each patient at each time point during the intravenous treatment are acquired through the heart rate sensor, respiratory rate sensor, blood pressure sensor and intravenous infusion monitor in the data acquisition module.
[0023] The system includes a heart rate sensor, a respiratory rate sensor, a blood pressure sensor, and an intravenous drip rate sensor. The data acquisition time interval in the intravenous injection monitor is [time interval missing]. The data collection time is t, that is, the length of each time period is t.
[0024] It should be noted that the time interval The values for the data collection duration t are all manually set; in this embodiment, the time interval... The value of t is 30s, and the collection duration t is 1h. Implementers can also set it according to specific circumstances. This embodiment does not impose any special restrictions.
[0025] Missing value imputation is used to fill in missing values in the acquired sensor data, thereby unifying the data dimensions.
[0026] It should be noted that there are many commonly used methods for filling missing values. In this embodiment, the nearest neighbor method is used to fill missing data in the sensor data. Implementers may also use the mean interpolation method or other methods to fill missing values. This embodiment does not impose any special restrictions.
[0027] Among them, the nearest neighbor method is a well-known technique in the field of missing value imputation, and the specific process will not be described in detail.
[0028] Step S2: Based on the similarity between the feature vector at each time point within each time period and all other feature vectors in its cluster, as well as the difference between the feature vector at each time point and all feature vectors in other clusters, determine the information contribution of each patient at each time point within each time period.
[0029] During intravenous therapy, there is usually a correlation between a patient's heart rate, respiratory rate, blood pressure, and intravenous drip rate. The pharmacological effects of different drugs may affect a patient's heart rate, respiratory rate, and blood pressure, while the intravenous drip rate can affect the rate of drug interactions. Simultaneously, the intravenous drip rate also affects cardiac load and blood volume, thus influencing the patient's heart rate, blood pressure, and respiratory rate. When tracking patient intravenous therapy data, it is necessary to comprehensively consider any abnormal correlations among the intravenous therapy data.
[0030] To comprehensively consider the correlation between the patient's heart rate, respiratory rate, blood pressure, and intravenous drip rate at each moment, and to facilitate further precise analysis of the characteristics of the patient's intravenous treatment data at each moment during intravenous treatment, we first construct a feature vector for each moment by taking the heart rate, respiratory rate, blood pressure, and intravenous drip rate of each patient within each time period. Then, we use the feature vectors of all moments of each patient within each time period as input to a clustering algorithm, which outputs multiple clusters.
[0031] If a patient experiences abnormal conditions such as effusion, complications, allergies, or phlebitis during intravenous treatment, the intravenous treatment data will differ significantly from normal intravenous treatment data. The more significant the abnormalities in the patient's intravenous treatment data, the more valuable the information about intravenous treatment it can provide.
[0032] Therefore, based on the similarity between the feature vector at each time point within each time period and all other feature vectors in its cluster, as well as the difference between the feature vector at each time point and all feature vectors in other clusters, the information contribution of each patient at each time point within each time period is determined to identify any abnormalities in the patient's intravenous treatment data. Specifically: (1) Analyze the mean similarity between the feature vector of each patient at each time period and all other feature vectors in the cluster they belong to, and denot it as the information similarity of each patient at each time period.
[0033] It should be noted that there are many methods to measure the similarity between vectors. In this embodiment, the cosine similarity between the feature vector at each time step and other feature vectors in its cluster is calculated to measure the similarity between different feature vectors in the same cluster. In practical applications, as another implementation method, the implementer can also calculate the reciprocal of the Euclidean distance between different feature vectors in the same cluster to measure the similarity between feature vectors. This embodiment does not impose any special restrictions on the method for calculating the similarity between feature vectors.
[0034] (2) Further, analyze the mean difference between the feature vector of each patient at each time period and the feature vectors of all remaining clusters except the cluster in which the patient is located.
[0035] It should be understood that there are many methods to measure the differences between vectors. In this embodiment, the difference between feature vectors in different clusters is measured by calculating the DTW distance between the feature vector at each time step and all feature vectors in all remaining clusters except the cluster in which it is located. In practical applications, as another implementation method, the implementer can also calculate the Euclidean distance between different feature vectors in the same cluster to measure the difference between feature vectors. This embodiment does not impose any special restrictions on the method for measuring the difference between vectors.
[0036] (3) Further, based on the information similarity and the mean of the difference between the feature vector of each patient at each time period and the feature vector of all remaining clusters excluding the cluster where the patient is located, the information contribution of each patient at each time period is the sum of the information similarity of each patient at each time period and the mean.
[0037] Furthermore, based on the information contribution of each patient at each time point, it can be understood that the more valuable the intravenous treatment information provided by the patient's intravenous treatment data at a given time, the greater the information similarity at that time. That is, the closer the patient's feature vector at that time is to the cluster center of its own cluster, the more valuable the intravenous treatment data at that time. Moreover, the greater the difference between the patient's feature vector at that time and all feature vectors in all other clusters except its own, the greater the information contribution at that time, and the better it reflects the uniqueness of the patient's intravenous treatment data at that time. Conversely, if the information similarity at that time is small, and the difference between the patient's feature vector at that time and all feature vectors in all other clusters except its own, the smaller the information contribution at that time.
[0038] Step S3: Based on the differences between the information contribution of each moment within each time period and the information contribution of all other moments, as well as the degree of confusion in the information contribution of all moments, determine the effective information factors for each patient within each time period.
[0039] Because patients require intravenous therapy due to illness, and may have underlying medical conditions, data such as heart rate, respiratory rate, and blood pressure may fluctuate significantly during intravenous therapy. This results in moments when the information contribution value of intravenous therapy data is lower than at other times (the value of intravenous therapy information lies in its ability to characterize the degree of abnormality in intravenous therapy data caused by non-underlying diseases). Therefore, the effectiveness of intravenous therapy information cannot be accurately measured solely by its information contribution.
[0040] Therefore, by analyzing the differences in information contribution at each moment within each time period compared to the information contribution at all other moments, as well as the degree of confusion in information contribution across all moments, the effective information factors for each patient at each moment within each time period are determined, thereby accurately measuring the effectiveness of intravenous therapy information. The specific process is as follows: The expressions for the effective factors of information at each time point within each patient's time period are as follows: In the formula, The effective factor representing the information at time j within the i-th time period of the i-th patient; Shannon entropy represents the information contribution of the i-th patient at all times within the i-th time period; They represent the j-th and j-th time periods of the i-th patient, respectively. The information contribution at any given moment; This represents the number of all moments within the i-th time period for the i-th patient.
[0041] It should be noted that there are many methods to measure differences. In this embodiment, the difference between the intravenous drip rate at different times is measured by calculating the absolute value of the difference between the intravenous drip rate at each time and the intravenous drip rate at other times. Implementers may also use other methods to measure differences, such as ratios. This embodiment does not impose any special restrictions.
[0042] Furthermore, based on the intravenous treatment characteristic factors of each patient at each time period, it can be understood that when the intravenous treatment information at any given time can more effectively characterize the abnormal conditions that occur during the patient's intravenous treatment, the larger the information effectiveness factor, the more significant the fluctuation of the information contribution at all times within the corresponding time period, that is, the larger the Shannon entropy of the information contribution at all times within the corresponding time period, and the greater the difference between the intravenous drip rate at any given time and the information contribution at all other times within the same time period; conversely, if the information effectiveness factor is smaller, the information contribution at all times within the corresponding time period is smaller, that is, the smaller the Shannon entropy of the information contribution at all times within the corresponding time period, and the smaller the difference between the intravenous drip rate at any given time and the information contribution at all other times within the same time period.
[0043] Step S4: Based on the differences in intravenous drip rate between each time period and all times in its neighborhood, and in conjunction with the aforementioned effective information factors, determine the intravenous treatment characteristic factors for each patient at each time period.
[0044] Typically, when a patient experiences abnormal changes in heart rate, respiratory rate, blood pressure, or other data during intravenous therapy, medical staff will alleviate and treat the patient's condition by changing the intravenous medication or adjusting the intravenous drip rate. At this time, the intravenous drip rate in the patient's intravenous therapy information will change significantly in a short period of time. The intravenous therapy information data within the time period of the intravenous drip rate change can better reflect the characteristics of the patient's intravenous therapy changes.
[0045] Therefore, in order to accurately understand the patient's treatment status at a specific moment, by analyzing the differences in intravenous drip rate between each time period and all times in its neighborhood, and combining this with the aforementioned effective information factors, the characteristic factors of intravenous treatment for each patient at each time period are determined, specifically: The neighborhood W is divided with each patient at each time point within each time period as the center. The value of the neighborhood W is set manually. In this embodiment, the value of the neighborhood W is 5. The implementer can also set it according to the specific situation. This embodiment does not impose any special restrictions.
[0046] The expressions for the characteristic factors of intravenous treatment for each patient at each time point within each time period are as follows: In the formula, This represents the characteristic factor of intravenous treatment at time j within the i-th time period for patient I. This represents the difference in intravenous drip rate between patient I at time j within the i-th time period and between patient I at time u within its neighborhood. This represents the number of intravenous drip rates at all times within the i-th time period for the i-th patient; norm() represents the normalization function.
[0047] It should be noted that there are many methods to measure differences. In this embodiment, the difference in intravenous drip rate between each patient and each time in their neighborhood is measured by calculating the absolute value of the difference between the intravenous drip rate at each time and the intravenous drip rate at each time in their neighborhood. Implementers may also use methods such as ratios to measure differences. This embodiment does not impose any special restrictions.
[0048] Preferably, the schematic diagram of the intravenous therapy characteristic factor extraction process provided in this embodiment is as follows: Figure 2 As shown.
[0049] Furthermore, based on the intravenous treatment characteristic factors of each patient at each time period, it can be understood that when the intravenous treatment information at any given time effectively reflects the patient's intravenous treatment changes, the corresponding intravenous drip rate changes are more significant, and the intravenous treatment information at that time is more effective in characterizing the abnormal conditions that occur during the patient's intravenous treatment. The larger the intravenous treatment characteristic factor, that is, the greater the cumulative difference between the intravenous drip rate at the corresponding time and the intravenous drip rate at other times within the same range, the larger the effective information factor at the corresponding time. Conversely, when the change in the intravenous drip rate at any given time is smaller, the intravenous treatment information at that time is less effective in characterizing the abnormal conditions that occur during the patient's intravenous treatment. The smaller the intravenous treatment characteristic factor, that is, the smaller the cumulative difference between the intravenous drip rate at the corresponding time and the intravenous drip rate at other times within the same range, the smaller the effective information factor at the corresponding time.
[0050] Step S5: Based on the differences between the feature vectors of each patient at all data tracking moments within any time period and the feature vectors of all other patients in the same disease group at all data tracking moments within any time period, determine the similarity of intravenous treatment between each patient and the other patients in the same disease group.
[0051] Patients with similar characteristics can improve the comparability between data, and similar patient groups can reduce variation, improve the power of statistical tests, and make the conclusions drawn from the data more convincing. Therefore, when tracking patients' intravenous treatment information data, it is more important to select patients with similar intravenous treatment characteristics within the same category of patients in the database.
[0052] Step S4 obtains the intravenous treatment feature factors at each moment during the patient's intravenous treatment process. Furthermore, the intravenous treatment feature factors of each patient at all moments within each time period are used as input to the threshold segmentation algorithm to obtain the segmentation threshold.
[0053] Furthermore, the time when the intravenous treatment characteristic factor is greater than or equal to the segmentation threshold is recorded as the data tracking time.
[0054] It should be noted that there are many commonly used threshold segmentation algorithms. In this embodiment, the Otsu threshold segmentation algorithm is used to divide the time corresponding to the characteristic factors of intravenous treatment. Implementers may also use other threshold segmentation algorithms, and this embodiment does not impose any special restrictions.
[0055] Among them, the Otsu threshold segmentation algorithm is a well-known technique, and the specific segmentation process will not be described in detail.
[0056] Furthermore, the feature vectors of all data tracking moments for each patient within each time period are used to construct the intravenous treatment tracking matrix for each time period. The similarity of intravenous treatment for any patient can be determined by summing the differences between the patient and the corresponding intravenous treatment tracking matrices of all patients of the same category in the medical information database. Specifically: The similarity of intravenous treatment between each patient and the other patients in the same disease group is the reciprocal of the mean square error of the intravenous treatment tracking matrix of each patient at all time periods and the intravenous treatment tracking matrix of the other patients in the same disease group at all time periods.
[0057] Based on the similarity of intravenous treatment between each patient and other patients in the same disease group, it can be understood that the smaller the mean square error of the intravenous treatment tracking matrix of each patient compared to the intravenous treatment tracking matrix of any other patient in the same disease group, the smaller the difference between the intravenous treatment tracking matrices of different patients, and the greater the similarity of intravenous treatment. Conversely, the larger the mean square error of the intravenous treatment tracking matrix of each patient compared to the intravenous treatment tracking matrix of any other patient in the same disease group, the greater the difference between the intravenous treatment tracking matrices of different patients, and the smaller the similarity of intravenous treatment.
[0058] Step S6: Based on the similarity of each patient's intravenous treatment to that of the other patients, track the patients' intravenous treatment data.
[0059] When tracking patients’ intravenous treatment information data, patients with similar intravenous treatment characteristics within the same patient group in the database should be selected. In step S5, patients with smaller cumulative mean square errors between the intravenous treatment tracking matrices corresponding to all data tracking intervals are selected for matching. Patients with higher intravenous treatment similarity are more likely to experience abnormal conditions such as effusion, complications, allergies, and phlebitis during intravenous treatment.
[0060] The intravenous treatment similarity of each patient to all other patients in the same disease group in the medical information database is stored in descending order for subsequent queries by relevant medical staff based on intravenous treatment similarity.
[0061] Based on the same inventive concept as the above method, this application also provides an intravenous therapy information data tracking system, including: The venous data acquisition module is used to acquire the heart rate, respiratory rate, blood pressure and intravenous drip rate of each patient at each preset time period, and to form the feature vector of each patient at each time period. The venous data analysis module is used to cluster the feature vectors of each patient at all times within each time period to obtain multiple clusters. Based on the similarity between the feature vector at each time period and all other feature vectors in its cluster, as well as the difference between the feature vector at each time period and all feature vectors in other clusters, the information contribution of each patient at each time period is determined. Based on the differences between the information contribution of each moment within each time period and the information contribution of all other moments, as well as the degree of confusion in the information contribution of all moments, the effective information factors of each patient within each time period are determined. Based on the differences in intravenous drip rate between each time period and all times in its neighborhood, and combined with the aforementioned effective information factors, the characteristic factors of intravenous treatment for each patient at each time period are determined. The vein data storage module is used to obtain the segmentation threshold of the vein treatment feature factors at all times within each time period using a threshold segmentation algorithm, and to record the time when the vein treatment feature factor is greater than or equal to the segmentation threshold as the data tracking time. Based on the differences between the feature vectors of each patient at any time period and the feature vectors of all other patients in the same disease group at any time period, the similarity of intravenous treatment between each patient and all other patients in the same disease group is determined, and the intravenous treatment data of the patients is tracked.
[0062] This application provides a block diagram of an intravenous therapy information data tracking system, such as... Figure 3 As shown.
[0063] Based on the same inventive concept as the above method, this application embodiment also provides a vein treatment information data tracking device, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the vein treatment information data tracking methods described above.
[0064] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.
[0065] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.
[0066] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the protection scope of this application.
Claims
1. A method for tracking intravenous therapy information data, characterized in that, The method includes the following steps: The heart rate, respiratory rate, blood pressure and intravenous drip rate of each patient at each preset time period are obtained and used to form the feature vector of each patient at each time period. The feature vectors of each patient at all times within each time period are clustered to obtain multiple clusters. Based on the similarity between the feature vector at each time period and all other feature vectors in its cluster, as well as the difference between the feature vector at each time period and all feature vectors in other clusters, the information contribution of each patient at each time period is determined. Based on the differences between the information contribution of each moment within each time period and the information contribution of all other moments, as well as the degree of confusion in the information contribution of all moments, the effective information factors of each patient within each time period are determined. Based on the differences in intravenous drip rate between each time period and all times in its neighborhood, and combined with the aforementioned effective information factors, the characteristic factors of intravenous treatment for each patient at each time period are determined. A threshold segmentation algorithm is used to obtain the segmentation threshold of the intravenous treatment feature factors at all times within each time period. The times when the intravenous treatment feature factors are greater than or equal to the segmentation threshold are recorded as the data tracking times. Based on the differences between the feature vectors of each patient at any time period and the feature vectors of all other patients in the same disease group at any time period, the similarity of intravenous treatment between each patient and all other patients in the same disease group is determined, and the intravenous treatment data of the patients is tracked.
2. The method for tracking intravenous therapy information data as described in claim 1, characterized in that, The method for determining the information contribution of each patient at each time point within each time period is as follows: Based on the similarity between the feature vector of each patient at each time point within each time period and all other feature vectors in its cluster, the information similarity of each patient at each time point within each time period is determined. Analyze the mean difference between the feature vector of each patient at each time point within each time period and the feature vectors of all remaining clusters excluding the patient's own cluster; Based on the information similarity and the mean, the information contribution of each patient at each time point within each time period is determined.
3. The method for tracking intravenous therapy information data as described in claim 2, characterized in that, The information similarity of each patient at each time point within each time period is the average of the similarity between the feature vector of each patient at each time point and all other feature vectors in its cluster.
4. The method for tracking intravenous therapy information data as described in claim 2, characterized in that, The information contribution of each patient at each time point within each time period is further determined as the sum of the information similarity of each patient at each time point within each time period and the mean value.
5. The method for tracking intravenous therapy information data as described in claim 1, characterized in that, The expressions for the effective information factors of each patient at each time point within each time period are as follows: In the formula, The effective factor representing the information at time j within the i-th time period of the i-th patient; Shannon entropy represents the information contribution of the i-th patient at all times within the i-th time period; They represent the j-th and j-th time periods of the i-th patient, respectively. The information contribution at any given moment; This represents the number of all moments within the i-th time period for the i-th patient.
6. The method for tracking intravenous therapy information data as described in claim 5, characterized in that, The expressions for the intravenous treatment characteristic factors of each patient at each time point within each time period are as follows: In the formula, This represents the characteristic factor of intravenous treatment at time j within the i-th time period for patient I. This represents the difference in intravenous drip rate between patient I at time j within the i-th time period and between patient I at time u within its neighborhood. This represents the number of intravenous drip rates at all times within the i-th time period for the i-th patient; norm() represents the normalization function.
7. The method for tracking intravenous therapy information data as described in claim 1, characterized in that, The process of determining the similarity of intravenous treatment between each patient and all other patients in the same disease group, and tracking the patients' intravenous treatment data, includes: The feature vectors of all data tracking moments for each patient in each time period are used to form the intravenous treatment tracking matrix for each time period. Based on the difference between the intravenous treatment tracking matrix of each patient in all time periods and the intravenous treatment tracking matrix of other patients in the same disease group in all time periods, the similarity of intravenous treatment between each patient and other patients in the same disease group is determined. The similarity of intravenous treatment for each patient to that of all other patients in the same disease group is stored.
8. The method for tracking intravenous therapy information data as described in claim 7, characterized in that, The similarity of intravenous treatment between each patient and the other patients in the same disease group is the reciprocal of the mean square error of the intravenous treatment tracking matrix of each patient at all time periods and the intravenous treatment tracking matrix of the other patients in the same disease group at all time periods.
9. A system for tracking intravenous therapy information data, implementing the method for tracking intravenous therapy information data as described in claim 1, characterized in that, The system includes: The venous data acquisition module is used to acquire the heart rate, respiratory rate, blood pressure and intravenous drip rate of each patient at each preset time period, and to form the feature vector of each patient at each time period. The venous data analysis module is used to cluster the feature vectors of each patient at all times within each time period to obtain multiple clusters. Based on the similarity between the feature vector at each time period and all other feature vectors in its cluster, as well as the difference between the feature vector at each time period and all feature vectors in other clusters, the information contribution of each patient at each time period is determined. Based on the differences between the information contribution of each moment within each time period and the information contribution of all other moments, as well as the degree of confusion in the information contribution of all moments, the effective information factors of each patient within each time period are determined. Based on the differences in intravenous drip rate between each time period and all times in its neighborhood, and combined with the aforementioned effective information factors, the characteristic factors of intravenous treatment for each patient at each time period are determined. The vein data storage module is used to obtain the segmentation threshold of the vein treatment feature factors at all times within each time period using a threshold segmentation algorithm, and to record the time when the vein treatment feature factor is greater than or equal to the segmentation threshold as the data tracking time. Based on the differences between the feature vectors of each patient at any time period and the feature vectors of all other patients in the same disease group at any time period, the similarity of intravenous treatment between each patient and all other patients in the same disease group is determined, and the intravenous treatment data of the patients is tracked.
10. A device for tracking intravenous therapy information data, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the intravenous treatment information data tracking method as described in any one of claims 1-8.