Method, system and medical equipment for monitoring vital signs and physiological data of patients with chronic kidney disease

Abstract

The present invention relates to the field of physiological data monitoring technology, and specifically to a method, system and medical device for monitoring the physiological data of chronic kidney disease patients. The method first screens out reference patients in a historical database based on intuitive monitoring data. In the real-time stage, the abnormal characteristics of the basic physiological data are analyzed, and the degree of continuity of the change of the patient's basic physiological data in the real-time stage can be determined by analyzing the similarity of the deviation characteristics between the initial moment and each moment, and then the initial abnormal degree can be determined by the abnormal weight, and the abnormal degree in the real-time stage can be obtained by combining the state at the initial moment and the initial abnormal degree. The physiological state of each patient in the latest stage can be characterized by the abnormal degree, and the reference patients are further screened to obtain related patients. The present invention screens out related patients with stronger reference significance for reference to the changes in the monitoring data of the target patient, and can perform effective physiological monitoring on the target patient.

Description

Technical Field

[0001] The present invention relates to the technical field of physiological data monitoring, and in particular to a method, system and medical equipment for monitoring vital signs and physiological data of patients with chronic kidney disease. Background Art

[0002] Chronic kidney disease patients have a slow onset of symptoms and will only have significant symptoms in the later stages. In order to effectively monitor the patient's condition and determine the patient's physical condition in a timely manner, it is necessary to conduct effective monitoring of the patient's condition. During the detection process, it is necessary not only to monitor the patient's basic physiological data such as blood pressure and heart rate in real time, but also to use specific testing equipment to obtain laboratory data such as urine protein and glomerular filtration rate in the laboratory or testing room. These data are all physiological data monitored by chronic kidney disease patients when performing physiological data monitoring.

[0003] However, in the actual process of physiological data monitoring, because chronic kidney disease patients have many complications in the later stage and develop quickly, timely disease warning cannot be achieved only by real-time monitoring of physiological data. The existing technology can refer to or predict the data of the target patient based on the data of historical patients who have completed the diagnosis and treatment process in the database. However, since there are many historical patients in the database and the physiological data in one stage are relatively complex, it is impossible to effectively find relevant patients with real reference significance in the database, and thus it is impossible to perform effective physiological monitoring on the target patient. Summary of the invention

[0004] In order to solve the technical problem that the prior art cannot effectively find relevant patients with real reference significance in the database, and thus cannot effectively monitor the target patients, the purpose of the present invention is to provide a method, system and medical device for monitoring the physiological data of chronic kidney disease patients. The technical solutions adopted are as follows:

[0005] The present invention proposes a method for monitoring vital signs and physiological data of patients with chronic kidney disease, the method comprising:

[0006] Obtaining multi-dimensional monitoring data of the target patient, wherein the monitoring data includes basic physiological data and laboratory test data;

[0007] In the historical database, the comprehensive similarity of the multi-dimensional monitoring data between the target patient and the historical patients is obtained, and the reference patient of the target patient is screened out according to the comprehensive similarity;

[0008] Divide the real-time stage of each patient in time series according to the detection time of the laboratory test data, and obtain the deviation characteristics of each dimension of the basic physiological data at each moment in the real-time stage relative to the standard basic physiological data; obtain the abnormal weight of each dimension at each moment according to the similarity of the deviation characteristics between each moment and the initial moment in the real-time stage; perform weighted statistics on the difference of the basic physiological data between the initial moment and each moment according to the abnormal weight, and obtain the initial abnormal degree of each dimension; obtain the abnormal degree of the real-time stage according to the deviation characteristics at the initial moment and the initial abnormal degree;

[0009] The relevance of each reference patient is obtained according to the difference in abnormality between the reference patient and the target patient and the comprehensive similarity; and the relevant patients are screened out according to the relevance for reference of the monitoring data changes of the target patient.

[0010] Furthermore, the method for obtaining the comprehensive similarity includes:

[0011] The monitoring data of each dimension forms a data sequence under the corresponding dimension. The dynamic time warping algorithm is used to obtain the initial similarity of the data sequence under each dimension between the target patient and the historical patient, and the average value of the initial similarities is used as the comprehensive similarity.

[0012] Furthermore, the method for obtaining the deviation feature includes:

[0013] The difference between the basic physiological data and the standard basic physiological data in each dimension at each moment in the real-time stage is used as the deviation feature.

[0014] Furthermore, the method for obtaining the abnormal weight includes:

[0015] If the deviation characteristic is a positive number, the mark value is set to a first mark value, and if the deviation characteristic is a negative number, the mark value is set to a second mark value;

[0016] For each moment in the real-time stage, if the deviation feature at the initial moment is the same as the label value of the deviation feature at the moment, the anomaly weight is set to 2; otherwise, it is set to 0.

[0017] Furthermore, the method for obtaining the initial abnormality degree includes:

[0018] In each dimension of the basic physiological data, the difference in basic physiological data between the initial moment and each moment in the real-time stage is obtained, and the difference in basic physiological data is weighted and averaged according to the abnormal weight at each moment to obtain the initial abnormality degree.

[0019] Furthermore, the method for obtaining the abnormality degree includes:

[0020] In each dimension of the basic physiological data, the ratio of the deviation feature to the standard change amplitude at the initial moment is used as the deviation weight at the initial moment, and the deviation weight is multiplied by the initial abnormality degree in the dimension to obtain the weighted abnormality degree in the dimension;

[0021] The average value of the weighted abnormality degree in all dimensions under the basic physiological data is normalized to obtain the abnormality degree in the real-time stage.

[0022] Furthermore, the method for obtaining the relevance includes:

[0023] The abnormality degree difference is negatively correlated and normalized, and then multiplied by the comprehensive similarity to obtain the correlation.

[0024] Furthermore, the basic physiological data in the monitoring data at least include heart rate, blood pressure and blood sugar; the laboratory test data at least include urine protein, blood creatinine and glomerular filtration rate; the collection frequency of the basic physiological data is greater than the collection frequency of the laboratory test data.

[0025] The present invention also proposes a system for monitoring vital signs and physiological data of patients with chronic kidney disease, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any one of the steps of a method for monitoring vital signs and physiological data of patients with chronic kidney disease when executing the computer program.

[0026] The present invention also proposes a medical device for monitoring vital signs and physiological data of patients with chronic kidney disease, the medical device comprising:

[0027] A patient data monitoring module is used to obtain multi-dimensional monitoring data of target patients, including basic physiological data and laboratory test data;

[0028] A historical database screening module is used to obtain the comprehensive similarity of multi-dimensional monitoring data between the target patient and historical patients in the historical database, and screen out reference patients for the target patient according to the comprehensive similarity;

[0029] The patient data analysis module is used to divide the real-time stage of the target patient in time series according to the detection time of the laboratory test data, and obtain the deviation characteristics of each dimension of the basic physiological data at each moment in the real-time stage relative to the standard basic physiological data; obtain the abnormal weight of each dimension at each moment according to the similarity of the deviation characteristics between each moment and the initial moment in the real-time stage; perform weighted statistics on the difference of the basic physiological data between the initial moment and each moment according to the abnormal weight, and obtain the initial abnormal degree of each dimension; obtain the abnormal degree of the real-time stage according to the deviation characteristics at the initial moment and the initial abnormal degree;

[0030] The monitoring data reference analysis module is used to obtain the relevance of each reference patient based on the difference in abnormality between the reference patient and the target patient and the comprehensive similarity; and to screen out relevant patients based on the relevance for reference to the monitoring data changes of the target patient.

[0031] The present invention has the following beneficial effects:

[0032] The embodiment of the present invention first selects reference patients from the historical database based on intuitive monitoring data. The detailed abnormal features reflected in the monitoring data of the target patient are further analyzed. Considering that basic physiological data can better characterize the basic physiological state of the patient than laboratory test data, and is easier to monitor and more real-time. Therefore, the real-time stage of each patient is divided in time series based on the detection time of the laboratory monitoring data, and the abnormal features of the basic physiological data are analyzed in the real-time stage. By analyzing the similarity of the deviation features between the initial moment and each moment, the degree of continuity of the change of the patient's basic physiological data in the real-time stage can be determined, and then the initial abnormal degree can be determined by the abnormal weight. The abnormal degree in the real-time stage can be obtained by combining the state at the initial moment and the initial abnormal degree. The abnormal degree can be characterized by the abnormal degree in the latest stage of each patient, and further screening of the reference patients can screen out relevant patients with stronger reference significance for reference to the changes in the monitoring data of the target patient. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0034] Figure 1 A flow chart of a method for monitoring vital signs and physiological data of chronic kidney disease patients provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0035] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of a method, system and medical device for monitoring the physiological data of chronic kidney disease patients proposed by the present invention, its specific implementation method, structure, characteristics and effects in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0036] Unless defined otherwise, 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 invention belongs.

[0037] The following is a detailed description of a method, system and medical device for monitoring vital signs and physiological data of chronic kidney disease patients provided by the present invention in conjunction with the accompanying drawings.

[0038] See also Figure 1 , which shows a flow chart of a method for monitoring vital signs and physiological data of a chronic kidney disease patient provided by an embodiment of the present invention, the method comprising:

[0039] Step S1: Obtain multi-dimensional monitoring data of the target patient, the monitoring data including basic physiological data and laboratory test data.

[0040] For the target patient, a series of monitoring data will be generated from the start of treatment to the real time, and these monitoring data will be recorded and stored. The monitoring data includes basic physiological data and laboratory test data. Generally, the monitoring frequency of basic physiological data is higher than that of laboratory test data.

[0041] In one embodiment of the present invention, the basic physiological data in the monitoring data at least include heart rate, blood pressure and blood sugar; the laboratory test data at least include urine protein, blood creatinine and glomerular filtration rate. It should be noted that because the monitoring data is data collected by real-time monitoring, the monitoring data of each dimension can form a data sequence, and because the data units between different dimensions are different, in one embodiment of the present invention, the collected data also needs to be standardized. The specific standardization method is a technical means well known to those skilled in the art, which will not be elaborated here. Specifically, methods such as range standardization and Z standardization can be selected.

[0042] Step S2: in the historical database, the comprehensive similarity of the multi-dimensional monitoring data between the target patient and the historical patients is obtained, and the reference patients of the target patient are screened out according to the comprehensive similarity.

[0043] As described in step S1, the monitoring data of each patient during the diagnosis and treatment process can be standardized and stored. Therefore, the historical database contains a large amount of monitoring data generated by different patients. The present invention aims to find out related patients who are strongly related to the target patient for reference of the target patient's condition. Therefore, firstly, based on the comprehensive similarity of multi-dimensional monitoring data, historical patients with high comprehensive similarity are found in the historical database as reference patients for the target patient.

[0044] It should be noted that, because the embodiment of the present invention is aimed at chronic kidney disease patients among chronic kidney disease patients, chronic kidney disease usually has multiple stages. When searching for reference patients, it is necessary to target historical patients who are at the same stage as the target patient, that is, to screen out reference patients from historical patients who are at the same stage as the target patient. And further considering that the historical patients in the historical database are patients who have completed the diagnosis and treatment process, there are data for multiple courses of treatment at the current stage of the disease, and the status of each course of treatment may be different. Therefore, when selecting historical patients, the embodiment of the present invention needs to intercept the data of historical patients based on the monitoring data length of the target patient and then analyze the comprehensive similarity. For example, if the target patient has gone through a time period of length L in the current stage of the disease, then for the historical patient, a time period of length L is also intercepted from the starting moment of the current stage of the disease, and the comprehensive similarity between the monitoring data is analyzed in this time period.

[0045] Preferably, in one embodiment of the present invention, the method for obtaining the comprehensive similarity includes:

[0046] The monitoring data of each dimension forms a data sequence under the corresponding dimension, and the dynamic time warping algorithm is used to obtain the initial similarity of the data sequence under each dimension between the target patient and the historical patient, and the average value of the initial similarity is used as the comprehensive similarity. It should be noted that the dynamic time warping algorithm is a technical means well known to those skilled in the art and will not be described in detail here.

[0047] In the embodiment of the present invention, after the comprehensive similarity is normalized, the similarity threshold is set to 0.9, and the historical patients whose comprehensive similarity is greater than the similarity threshold are used as reference patients.

[0048] Step S3: Divide the real-time stage of each patient in time series according to the detection time of the laboratory test data, and obtain the deviation characteristics of each dimension of the basic physiological data at each moment in the real-time stage relative to the standard basic physiological data; obtain the abnormal weight of each dimension at each moment according to the similarity of the deviation characteristics between each moment in the real-time stage and the initial moment; perform weighted statistics on the difference in basic physiological data between the initial moment and each moment according to the abnormal weight, and obtain the initial abnormal degree of each dimension; obtain the abnormal degree of the real-time stage according to the deviation characteristics at the initial moment and the initial abnormal degree.

[0049] As described in step S2 above, the data of each patient analyzed in the embodiment of the present invention has obvious time period characteristics, and for the target patient, the characteristics reflected by the monitoring data in the real-time stage are the data that need attention. Therefore, for each patient, the real-time stage of each patient can be divided in time series according to the detection time of the laboratory test data, that is, the laboratory test time point is used as the dividing point, and the time period between the real-time moment and the nearest laboratory test time point is the real-time stage.

[0050] Because the monitoring data characteristics of chronic kidney disease in the early stage of the outbreak of complications will not have obvious data anomalies, when analyzing the monitoring data of chronic kidney disease patients, more attention should be paid to the abnormal characteristics reflected by the changes in the data. The detection frequency of laboratory test data is significantly lower than the detection frequency of basic physiological data, so the embodiment of the present invention further analyzes the deviation characteristics of each dimension of the basic physiological data at each moment in the real-time stage relative to the standard basic physiological data. If the deviation characteristics have continuous changes in the entire real-time stage, it means that the more unstable the condition of the current patient is, the more likely it is to have abnormal changes. Therefore, the abnormal weight of each dimension at each moment can be obtained according to the similarity of the deviation characteristics between each moment and the initial moment in the real-time stage. If the deviation characteristics between each moment and the initial moment are similar, it means that the moment continues the change of the initial moment, and there is still a significant deviation from the standard data, which means that the current patient is more abnormal at this moment. Further, the difference in basic physiological data between the initial moment and each moment can be weighted and counted according to the abnormal weight. The greater the difference in the basic physiological data, the greater the difference in the basic physiological data, which means that the physiological characteristics of the patient have changed significantly between the time period. If the abnormal weight is larger at the same time, it means that this change is continuous, and the initial abnormal degree is more obvious. Because the initial abnormality degree is the abnormal data in each dimension of the basic physiological data, the initial abnormality degree of each dimension is further combined, and the physiological state at the initial moment is determined according to the deviation characteristics at the initial moment, and then the abnormality degree of the current patient in the real-time stage is determined.

[0051] It should be noted that the standard basic physiological data under each dimension can be set according to the patient's condition, and will not be elaborated or limited here.

[0052] Preferably, in one embodiment of the present invention, the method for obtaining the deviation feature includes:

[0053] The difference between the basic physiological data and the standard basic physiological data in each dimension at each moment in the real-time stage is taken as the deviation feature. That is, the deviation feature is a data with positive and negative signs, a positive value indicates that it is larger than the standard basic physiological data, and a negative value indicates that it is smaller than the standard basic physiological data.

[0054] Furthermore, in an embodiment of the present invention, a method for obtaining anomaly weights includes:

[0055] If the deviation feature is a positive number, the mark value is set to a first mark value, and if the deviation feature is a negative number, the mark value is set to a second mark value. In the embodiment of the present invention, the first mark value is set to 1, and the second mark value is set to -1.

[0056] For each moment in the real-time stage, if the deviation feature at the initial moment has the same tag value as the deviation feature at the moment, the anomaly weight is set to 2; otherwise, it is set to 0. That is, an anomaly weight of 2 indicates that the data change is continuous, and an anomaly weight of 0 indicates that the data change has changed at the current moment and the degree of anomaly has weakened.

[0057] Preferably, in one embodiment of the present invention, the method for obtaining the initial abnormality degree includes:

[0058] In each dimension of basic physiological data, the difference in basic physiological data between the initial moment and each moment in the real-time stage is obtained, and the difference in basic physiological data is weighted and averaged according to the abnormal weight of each moment to obtain the initial abnormality degree. That is, all data features are integrated by weighted averaging, and the abnormal weight is used as the confidence of each moment. The larger the abnormal weight, the more likely the abnormality is to occur at that moment, and the corresponding difference in basic physiological data reflects the greater the abnormality. The greater the difference in basic physiological data, the greater the fluctuation of physiological data between the current moment and the initial moment, and the greater the abnormality. The initial abnormality degree is expressed by the formula:

[0059] ;in is the initial abnormality degree of the kth dimension of the basic physiological data, is the number of moments in the real-time phase, is the abnormal weight at the tth moment in the kth dimension, is the initial moment in the kth dimension Basic physiological data, is the basic physiological data at the tth moment in the kth dimension.

[0060] Preferably, in one embodiment of the present invention, the method for obtaining the abnormality degree includes:

[0061] In each dimension of basic physiological data, the ratio of the deviation feature at the initial moment to the standard change amplitude is used as the deviation weight at the initial moment. That is, the deviation weight represents the size of the deviation feature at the initial moment relative to the amplitude of the change. The larger the deviation weight, the more abnormal the state at the initial moment. By introducing the deviation weight, the sensitivity of physiological data monitoring in the real-time stage can be enhanced.

[0062] Multiply the deviation weight by the initial abnormality degree under the dimension to obtain the weighted abnormality degree under the dimension;

[0063] The average value of the weighted abnormality degree in all dimensions under the basic physiological data is normalized to obtain the abnormality degree in the real-time stage. That is, all data are statistically combined using the weighted average method to obtain the abnormality degree of each patient in the real-time stage, which can enhance the sensitivity of physiological data fluctuations and more accurately quantify the abnormality degree of each patient in the real-time stage by emphasizing the data characteristics under the continuous abnormal process.

[0064] Step S4: Obtain the relevance of each reference patient based on the difference in abnormality degree and the comprehensive similarity between the reference patient and the target patient; and select relevant patients based on the relevance for reference of the monitoring data changes of the target patient.

[0065] After the above steps, the abnormality level of each patient in the real-time stage can be obtained, and then the relevance of each reference patient can be obtained according to the difference in abnormality level and comprehensive similarity between the reference patient and the target patient. That is, the smaller the difference in abnormality level and the greater the comprehensive similarity, the greater the relevance.

[0066] Preferably, in one embodiment of the present invention, the method for obtaining the relevance includes:

[0067] The abnormality degree difference is negatively correlated and normalized, and then multiplied by the comprehensive similarity to obtain the correlation. The negative correlation mapping and normalization method used in the embodiment of the present invention is: the abnormality degree difference is the absolute value of the difference between the two abnormality degrees, and the opposite number of the abnormality degree difference is used as the power of the exponent with the natural constant as the base to obtain the negative correlation mapping and normalization result.

[0068] In an embodiment of the present invention, after obtaining the relevance of each reference patient, the reference patients can be sorted according to the relevance, and the reference patients with higher relevance can be selected as relevant patients. For relevant patients, the key data generated during their diagnosis and treatment stages can be graphed to show the fluctuation of monitoring data, abnormality comparison, trend analysis, etc., so as to facilitate the comparison between doctors and target patients' data. It is also possible to predict the monitoring data of target patients at future times based on the diagnosis and treatment of relevant patients, so that the condition of the target patients can be evaluated and analyzed in a timely manner.

[0069] In summary, the embodiment of the present invention first selects reference patients from the historical database based on intuitive monitoring data. The detailed abnormal features reflected in the monitoring data of the target patient are further analyzed. Considering that basic physiological data can better characterize the basic physiological state of the patient than laboratory test data, and is easier to monitor and more real-time. Therefore, the real-time stage of each patient is divided in time series based on the detection time of the laboratory monitoring data, and the abnormal features of the basic physiological data are analyzed in the real-time stage. By analyzing the similarity of the deviation features between the initial moment and each moment, the degree of change of the basic physiological data of the patient in the real-time stage can be determined, and then the initial abnormal degree can be determined by the abnormal weight. The abnormal degree in the real-time stage can be obtained by combining the state at the initial moment and the initial abnormal degree. The abnormal degree can be characterized by the abnormal degree in the latest stage of each patient, and further screening of the reference patients can screen out relevant patients with stronger reference significance for reference to the changes in the monitoring data of the target patient.

[0070] Based on the same inventive concept, the present invention also proposes a system for monitoring vital signs and physiological data of patients with chronic kidney disease, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any step of a method for monitoring vital signs and physiological data of patients with chronic kidney disease.

[0071] The present invention also proposes a medical device for monitoring vital signs and physiological data of patients with chronic kidney disease, the medical device comprising:

[0072] A patient data monitoring module is used to obtain multi-dimensional monitoring data of target patients, including basic physiological data and laboratory test data;

[0073] A historical database screening module is used to obtain the comprehensive similarity of multi-dimensional monitoring data between the target patient and historical patients in the historical database, and screen out reference patients for the target patient according to the comprehensive similarity;

[0074] The patient data analysis module is used to divide the real-time stage of the target patient in time series according to the detection time of the laboratory test data, and obtain the deviation characteristics of each dimension of the basic physiological data at each moment in the real-time stage relative to the standard basic physiological data; obtain the abnormal weight of each dimension at each moment according to the similarity of the deviation characteristics between each moment and the initial moment in the real-time stage; perform weighted statistics on the difference of the basic physiological data between the initial moment and each moment according to the abnormal weight, and obtain the initial abnormal degree of each dimension; obtain the abnormal degree of the real-time stage according to the deviation characteristics at the initial moment and the initial abnormal degree;

[0075] The monitoring data reference analysis module is used to obtain the relevance of each reference patient based on the difference in abnormality between the reference patient and the target patient and the comprehensive similarity; and to screen out relevant patients based on the relevance for reference to the monitoring data changes of the target patient.

[0076] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0077] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for monitoring vital signs and physiological data of patients with chronic kidney disease, characterized in that: The method comprises: Obtaining multi-dimensional monitoring data of target patients, wherein the monitoring data includes basic physiological data and laboratory test data; In the historical database, the comprehensive similarity of the multi-dimensional monitoring data between the target patient and the historical patients is obtained, and the reference patient of the target patient is screened out according to the comprehensive similarity; Divide the real-time stage of each patient in time series according to the detection time of the laboratory test data, and obtain the deviation characteristics of each dimension of the basic physiological data at each moment in the real-time stage relative to the standard basic physiological data; obtain the abnormal weight of each dimension at each moment according to the similarity of the deviation characteristics between each moment and the initial moment in the real-time stage; perform weighted statistics on the difference in basic physiological data between the initial moment and each moment according to the abnormal weight, and obtain the initial abnormal degree of each dimension; obtain the abnormal degree of the real-time stage according to the deviation characteristics at the initial moment and the initial abnormal degree; take the laboratory test time point as the dividing point, and the time period between the real-time moment and the nearest laboratory test time point is the real-time stage; Obtaining the relevance of each reference patient according to the difference in abnormality between the reference patient and the target patient and the comprehensive similarity; screening out relevant patients according to the relevance for reference of changes in monitoring data of the target patient; The method for obtaining the comprehensive similarity includes: The monitoring data of each dimension forms a data sequence under the corresponding dimension, and the dynamic time warping algorithm is used to obtain the initial similarity of the data sequence under each dimension between the target patient and the historical patient, and the average value of the initial similarities is used as the comprehensive similarity; The method for obtaining the deviation feature includes: The difference between the basic physiological data and the standard basic physiological data in each dimension at each moment in the real-time stage is used as the deviation feature; The method for obtaining the abnormal weight includes: If the deviation characteristic is a positive number, the mark value is set to a first mark value, and if the deviation characteristic is a negative number, the mark value is set to a second mark value; For each moment in the real-time stage, if the deviation feature at the initial moment has the same tag value as the deviation feature at the moment, the anomaly weight is set to 2; otherwise, it is set to 0; The method for obtaining the abnormality degree includes: In each dimension of the basic physiological data, the ratio of the deviation feature to the standard change amplitude at the initial moment is used as the deviation weight at the initial moment, and the deviation weight is multiplied by the initial abnormality degree in the dimension to obtain the weighted abnormality degree in the dimension; The average value of the weighted abnormality degree in all dimensions under the basic physiological data is normalized to obtain the abnormality degree in the real-time stage.

2. A method for monitoring vital signs and physiological data of patients with chronic kidney disease according to claim 1, characterized in that: The method for obtaining the initial abnormality degree includes: In each dimension of the basic physiological data, the difference in basic physiological data between the initial moment and each moment in the real-time stage is obtained, and the difference in basic physiological data is weighted and averaged according to the abnormal weight at each moment to obtain the initial abnormality degree.

3. A method for monitoring vital signs and physiological data of patients with chronic kidney disease according to claim 1, characterized in that: The method for obtaining the relevance includes: The abnormality degree difference is negatively correlated and normalized, and then multiplied by the comprehensive similarity to obtain the correlation.

4. A method for monitoring vital signs and physiological data of patients with chronic kidney disease according to claim 1, characterized in that: The basic physiological data in the monitoring data at least include heart rate, blood pressure and blood sugar; the laboratory test data at least include urine protein, blood creatinine and glomerular filtration rate; the collection frequency of the basic physiological data is greater than the collection frequency of the laboratory test data.

5. A system for monitoring vital signs and physiological data of patients with chronic kidney disease, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of a method for monitoring vital signs and physiological data of a chronic kidney disease patient as described in any one of claims 1 to 4 are implemented.

6. A medical device for monitoring vital signs and physiological data of patients with chronic kidney disease, characterized in that: The medical equipment includes: A patient data monitoring module is used to obtain multi-dimensional monitoring data of target patients, including basic physiological data and laboratory test data; A historical database screening module is used to obtain the comprehensive similarity of multi-dimensional monitoring data between the target patient and historical patients in the historical database, and screen out reference patients for the target patient according to the comprehensive similarity; The patient data analysis module is used to divide the real-time stage of the target patient in time series according to the detection time of the laboratory test data, and obtain the deviation characteristics of each dimension of the basic physiological data at each moment in the real-time stage relative to the standard basic physiological data; obtain the abnormal weight of each dimension at each moment according to the similarity of the deviation characteristics between each moment and the initial moment in the real-time stage; perform weighted statistics on the difference in basic physiological data between the initial moment and each moment according to the abnormal weight, and obtain the initial abnormal degree of each dimension; obtain the abnormal degree of the real-time stage according to the deviation characteristics at the initial moment and the initial abnormal degree; take the laboratory test time point as the segmentation point, and the time period between the real-time moment and the nearest laboratory test time point is the real-time stage; A monitoring data reference analysis module is used to obtain the relevance of each reference patient based on the difference in abnormality between the reference patient and the target patient and the comprehensive similarity; and to screen out relevant patients based on the relevance for reference to the monitoring data changes of the target patient; The method for obtaining the comprehensive similarity includes: The monitoring data of each dimension forms a data sequence under the corresponding dimension, and the dynamic time warping algorithm is used to obtain the initial similarity of the data sequence under each dimension between the target patient and the historical patient, and the average value of the initial similarities is used as the comprehensive similarity; The method for obtaining the deviation feature includes: The difference between the basic physiological data and the standard basic physiological data in each dimension at each moment in the real-time stage is used as the deviation feature; The method for obtaining the abnormal weight includes: If the deviation characteristic is a positive number, the mark value is set to a first mark value, and if the deviation characteristic is a negative number, the mark value is set to a second mark value; For each moment in the real-time stage, if the deviation feature at the initial moment has the same tag value as the deviation feature at the moment, the anomaly weight is set to 2; otherwise, it is set to 0; The method for obtaining the abnormality degree includes: In each dimension of the basic physiological data, the ratio of the deviation feature to the standard change amplitude at the initial moment is used as the deviation weight at the initial moment, and the deviation weight is multiplied by the initial abnormality degree in the dimension to obtain the weighted abnormality degree in the dimension; The average value of the weighted abnormality degree in all dimensions under the basic physiological data is normalized to obtain the abnormality degree in the real-time stage.

Images