Medical care data processing method and system and electronic equipment

Abstract

The invention relates to the technical field of medical data processing, and provides a medical care data processing method and system and electronic equipment, and the method comprises the steps: obtaining the medical care data of a plurality of patients; performing clustering analysis on the physiological data of the same dimension in the medical care data of different patients to obtain the physiological deviation degree of each physiological data of each patient in each dimension; deviation values of all the physiological data of the same dimension of the same patient are obtained, and the physiological difference degree of each physiological data of each dimension of each patient is obtained; acquiring a plurality of abnormal physiological data of each dimension of each patient; obtaining the priority nursing degree of each dimension of each patient; the processing priority of each patient is obtained; and processing the medical care data of the patient. The invention aims to solve the problem that physical quality and disease difference of a patient are neglected in the process of performing rehabilitation effect analysis on the patient through medical care data.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and in particular to a medical nursing data processing method, system and electronic equipment. Background Art

[0002] Medical nursing data include relevant information such as patients' medical records, treatment records and living habits. Patients' diagnosis and treatment information corresponds to medical data, and living habits during treatment correspond to nursing data. By processing medical nursing data, data collection and integration, data analysis and mining, and data visualization are carried out under medical nursing big data, which can more accurately assess disease risks and formulate personalized nursing plans, thereby improving treatment outcomes.

[0003] In the process of processing the medical nursing data of a large number of patients, the processing of medical nursing data is usually used to analyze the patient's nursing status, that is, to evaluate the patient's rehabilitation effect through the patient's nursing status; usually, the medical nursing data of a large number of patients are analyzed, and then the deviation of the medical nursing data of a single patient is processed. However, due to the differences in symptoms among patients and the differences in the degree of rehabilitation after nursing, it is impossible to accurately evaluate the rehabilitation effect. That is, in the process of quantifying the rehabilitation effect by analyzing the deviation of the medical nursing data of a large number of patients, the differences in symptoms and the physical fitness of the patients themselves will be ignored; it is necessary to analyze the recovery process of the patient's own medical nursing data. Summary of the invention

[0004] The present invention provides a medical nursing data processing method, system and electronic device to solve the problem of ignoring the differences in patients' physical fitness and symptoms during the existing analysis of rehabilitation effects of patients through medical nursing data. The technical solutions adopted are as follows: The present invention proposes a medical nursing data processing method, which comprises the following steps: Acquire medical nursing data of a number of patients, wherein the medical nursing data includes multi-dimensional physiological data; Perform cluster analysis on physiological data of the same dimension in medical nursing data of different patients to obtain several clusters in the clustering results; obtain the physiological deviation degree of each physiological data of each dimension of each patient according to the cluster in which the physiological data is located and the clustering results; obtain the deviation amount of all physiological data of the same dimension of the same patient, analyze the difference of adjacent data in time series of the deviation amount, correct the physiological deviation degree, and obtain the physiological difference degree of each physiological data of each dimension of each patient; Determine the degree of physiological difference to obtain a number of abnormal physiological data of each dimension of each patient; obtain the priority nursing degree of each dimension of each patient based on the distribution of abnormal physiological data of the same dimension of the same patient and the degree of physiological difference of all physiological data; obtain the treatment priority of each patient by combining the degree of physiological difference of physiological data of each dimension of the same patient at the current moment; The medical care data of each patient is processed according to the treatment priority of each patient.

[0005] Optionally, the cluster analysis is performed on physiological data of the same dimension in the medical nursing data of different patients to obtain several clusters in the clustering results, including the following specific methods: Any patient is taken as the target patient, and the physiological data of the target patient's blood oxygen dimension is the target patient's blood oxygen data; DBSCAN clustering is performed on all the target patient's blood oxygen data and all the blood oxygen data of a large number of patients obtained, and the distance measurement uses the absolute value of the difference between the blood oxygen data to obtain the clustering results and several clusters therein.

[0006] Optionally, the physiological deviation degree of each physiological data of each dimension of each patient is specifically obtained by: Obtain the number of blood oxygen data in each cluster of the blood oxygen dimension; take the cluster with the largest number of blood oxygen data in all clusters of the blood oxygen dimension as the reference cluster of the blood oxygen dimension; the overall deviation factor of any cluster in the blood oxygen dimension The calculation method is: in, Indicates the number of blood oxygen data in this cluster, Indicates the number of blood oxygen data in the reference cluster of the blood oxygen dimension, Represents the mean of all blood oxygen data in this cluster, Represents the mean of all blood oxygen data in the reference cluster of the blood oxygen dimension, Indicates the maximum absolute value of the difference between the blood oxygen data in the blood oxygen dimension; For any blood oxygen data of the target patient, obtain the absolute value of the difference between the blood oxygen data and the blood oxygen data corresponding to the center point of the cluster where it is located, and obtain the absolute value of the difference and The ratio of the blood oxygen data to the target patient is obtained by multiplying the ratio by the overall deviation factor of the cluster to which the blood oxygen data belongs, and the product of the ratio and the overall deviation factor of the cluster to which the blood oxygen data belongs is taken as the physiological deviation degree of the blood oxygen data of the target patient.

[0007] Optionally, the method of obtaining the deviation amount for all physiological data of the same dimension of the same patient, analyzing the difference of adjacent time series data of the deviation amount, correcting the physiological deviation degree, and obtaining the physiological difference degree of each physiological data of each dimension of each patient includes the following specific methods: The mean of all blood oxygen data in the reference cluster of the blood oxygen dimension is used as the standard blood oxygen data of the blood oxygen dimension; the difference between any blood oxygen data of the target patient and the standard blood oxygen data is obtained as the blood oxygen offset of the blood oxygen data of the target patient; the overall deviation consistency of the blood oxygen dimension of the target patient is calculated. The calculation method is: in, Represents the variance of the blood oxygen offset of all blood oxygen data of the target patient, Indicates the number of blood oxygen data of the target patient, The target patient The blood oxygen offset of each blood oxygen data, Represents the mean of all blood oxygen offsets of all blood oxygen data of the target patient, represents the standard deviation of all blood oxygen offsets of all blood oxygen data of the target patient; represents the absolute value function, represents an exponential function with a natural constant as base; According to the distribution range of the blood oxygen offset of the target patient's blood oxygen data and the difference in the blood oxygen offset of adjacent blood oxygen data, a local deviation factor of each blood oxygen data of the target patient is obtained; Target patients Physiological differences in blood oxygen data The calculation method is: in, The target patient The local deviation factor of blood oxygen data, The target patient The physiological deviation degree of blood oxygen data, Represents the overall deviation consistency of the target patient's blood oxygen dimension.

[0008] Optionally, the method of obtaining the local deviation factor of each blood oxygen data of the target patient according to the distribution range of the blood oxygen offset of the blood oxygen data of the target patient and the difference in the blood oxygen offset of adjacent blood oxygen data includes the following specific methods: For any blood oxygen data of the target patient, the blood oxygen offset of the blood oxygen data is removed, and the variance of the blood oxygen offset of other blood oxygen data of the target patient is recalculated and used as the denoted offset variance of the blood oxygen data; The difference between the variance of the blood oxygen offset of all the blood oxygen data of the target patient and the declinable offset variance of the blood oxygen data is used as the variance deviation factor of the blood oxygen data; the variance deviation factor of all the blood oxygen data of the target patient is linearly normalized, and the result is used as the variance deviation of each blood oxygen data of the target patient; Construct target patient The neighborhood range of blood oxygen data of the target patient Local deviation factor of blood oxygen data The calculation method is: in, The target patient The variance deviation of blood oxygen data, The target patient The number of blood oxygen data in the neighborhood of blood oxygen data, The target patient The blood oxygen offset of each blood oxygen data, The target patient The blood oxygen data is within the neighborhood of The blood oxygen offset of each blood oxygen data, Indicates the maximum value of the blood oxygen offset of all blood oxygen data of the target patient.

[0009] Optionally, the method of obtaining the priority nursing degree of each dimension of each patient based on the distribution of abnormal physiological data of the same dimension of the same patient and the physiological difference degree of all physiological data includes the following specific methods: The blood oxygen data of the target patient other than the abnormal blood oxygen data is recorded as the non-abnormal blood oxygen data; the non-abnormal blood oxygen data of the target patient that are continuous in time series is regarded as a blood oxygen rehabilitation segment of the target patient; The number of non-abnormal blood oxygen data in adjacent blood oxygen rehabilitation segments is compared, and the physiological recovery degree of each blood oxygen rehabilitation segment of the target patient is obtained by combining the abnormal blood oxygen data between adjacent blood oxygen rehabilitation segments and the physiological difference degree of non-abnormal blood oxygen data in the blood oxygen rehabilitation segments; The number of non-abnormal blood oxygen data in all blood oxygen rehabilitation segments of the target patient is weighted and normalized, and the result is used as the rehabilitation weight of each blood oxygen rehabilitation segment of the target patient; the priority care degree of the target patient's blood oxygen dimension The calculation method is: in, It represents the mean value of the physiological difference of all non-abnormal blood oxygen data in the last blood oxygen rehabilitation segment of the target patient. Indicates the number of non-abnormal blood oxygen data in the last blood oxygen rehabilitation segment of the target patient. Indicates the number of blood oxygen recovery segments of the target patient, The target patient The recovery weight of each blood oxygen recovery segment, The target patient Physiological recovery level of each blood oxygen recovery stage; Represents an exponential function with a natural constant as its base.

[0010] Optionally, the comparison of the number of non-abnormal blood oxygen data in adjacent blood oxygen rehabilitation segments, combining the abnormal blood oxygen data between adjacent blood oxygen rehabilitation segments and the physiological difference degree of the non-abnormal blood oxygen data in the blood oxygen rehabilitation segments, to obtain the physiological rehabilitation degree of each blood oxygen rehabilitation segment of the target patient includes the following specific methods: in, The target patient The number of non-abnormal blood oxygen data in the blood oxygen rehabilitation segment, The target patient The number of non-abnormal blood oxygen data in the blood oxygen rehabilitation segment, The target patient The blood oxygen recovery stage and the The number of consecutive abnormal blood oxygen data between blood oxygen recovery segments, The target patient The mean of the physiological difference levels of all non-abnormal blood oxygen data in the blood oxygen recovery segment.

[0011] Optionally, the obtaining of the treatment priority of each patient includes the following specific methods: The physiological difference degree of each dimension of the physiological data of the target patient at the current moment is used as the weight of the priority treatment degree of each dimension of the target patient. The priority treatment degrees of all dimensions of the target patient are weighted and averaged, and the result is used as the treatment priority of the target patient.

[0012] The present invention also proposes a medical nursing data processing system, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of the above method when executing the computer program.

[0013] The present invention also proposes a medical nursing data processing electronic device, the device comprising: A medical nursing data acquisition module is used to acquire medical nursing data of several patients; The medical nursing data analysis module is used to perform cluster analysis on physiological data of the same dimension in the medical nursing data of different patients, and obtain a number of clusters in the clustering results; obtain the physiological deviation degree of each physiological data of each dimension of each patient according to the cluster in which the physiological data is located and the clustering results; obtain the deviation amount of all physiological data of the same dimension of the same patient, and analyze the difference of adjacent data in time series of the deviation amount, correct the physiological deviation degree, and obtain the physiological difference degree of each physiological data of each dimension of each patient; Determine the degree of physiological difference to obtain a number of abnormal physiological data of each dimension of each patient; obtain the priority nursing degree of each dimension of each patient based on the distribution of abnormal physiological data of the same dimension of the same patient and the degree of physiological difference of all physiological data; obtain the treatment priority of each patient by combining the degree of physiological difference of physiological data of each dimension of the same patient at the current moment; The medical nursing data processing module is used to process the medical nursing data of the patients according to the processing priority of each patient.

[0014] The beneficial effects of the present invention are as follows: the present invention performs cluster analysis on the physiological data of each dimension of a large number of patients, quantifies the degree of physiological deviation through the distribution of physiological data in the clustering results, further analyzes the changes in the physiological data of the same dimension of the same patient, corrects the degree of physiological difference, and quantifies the rehabilitation effect of the patient in each dimension based on the degree of physiological difference; wherein, by performing cluster analysis on the physiological data of the same dimension of different patients based on the fact that they contain a large amount of normal physiological data, the deviation of the cluster and the deviation of the physiological data in the cluster are quantified respectively, and the possibility of abnormal physiological data is preliminarily quantified; and then, the overall deviation analysis is performed on the physiological data of the same dimension of the same patient to avoid the physiological data deviation caused by the difference in the physical fitness of the patients affecting the abnormality of the physiological data. Frequent analysis is performed, while considering the possibility of real abnormalities in the patient's physiological data within a local time, so as to correct the degree of physiological differences in each physiological data; and based on the degree of physiological differences, abnormal physiological data are judged, and the rehabilitation effect of the patient's corresponding dimension is quantified through the distribution of abnormal physiological data in the same dimension of the patient and the change in the degree of physiological differences of other non-abnormal physiological data, so as to reflect whether the patient's symptoms relapse and the severity of the relapse in the corresponding dimension, and obtain the priority care of the patient in each dimension; further overall analysis of the priority care of each dimension is performed, and the patient's treatment priority is comprehensively quantified; finally, priority processing of medical nursing data and corresponding care for patients with poor rehabilitation effects are achieved, so as to improve the efficiency of medical nursing data processing and the applicability of use in hospital databases. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be 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 labor.

[0016] Figure 1 A flowchart of a medical nursing data processing method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] See also Figure 1 , which shows a flow chart of a medical nursing data processing method provided by an embodiment of the present invention, the method comprising the following steps: Step S001: Obtain medical nursing data of several patients.

[0019] The purpose of this embodiment is to analyze the changes in the multi-dimensional physiological data of patients and consider the differences in physical fitness between patients in the process of medical nursing data processing to improve the accuracy of the evaluation of the patient's rehabilitation effect. Therefore, it is necessary to collect the patient's medical nursing data, that is, the patient's multi-dimensional physiological data.

[0020] Specifically, for all patients currently in the hospital, physiological data of multiple physiological indicators of the patients are collected through smart bracelets or monitoring devices when they are admitted to the hospital. The multiple physiological indicators include but are not limited to electrocardiogram data, blood pressure, blood oxygen and body temperature. This embodiment does not limit the specific physiological indicators; each physiological indicator is used as a dimension to obtain multi-dimensional physiological data of each patient, wherein the physiological data of each physiological indicator is continuously monitored; the physiological data of multiple physiological indicators recorded by a large number of patients during the hospitalization process are obtained in the hospital database to obtain multi-dimensional physiological data of the corresponding patients; the multi-dimensional physiological data of each patient are respectively constituted into the medical nursing data of each patient.

[0021] Step S002: cluster analysis is performed on physiological data of the same dimension in medical nursing data of different patients to obtain several clusters in the clustering results; the physiological deviation degree of each physiological data of each dimension of each patient is obtained according to the cluster in which the physiological data is located and the clustering results; the deviation amount is obtained for all physiological data of the same dimension of the same patient, and the difference between adjacent data in time series of the deviation amount is analyzed, the physiological deviation degree is corrected, and the physiological difference degree of each physiological data of each dimension of each patient is obtained.

[0022] It should be noted that, since a large number of patients have been undergoing treatment in the hospital for a long time, and the physiological data of each dimension only show abnormalities, that is, large deviations, in the corresponding symptoms, the physiological data of the same dimension of a large number of patients have a certain reference value, that is, they contain a large amount of normal physiological data and a small amount of abnormal physiological data; and for the physiological data of the target patients to be analyzed, cluster analysis is performed on them with a large amount of physiological data of the same dimension, and then deviation analysis is performed on the single-dimensional data based on the clustering results; since the number of abnormal physiological data is much smaller than the normal number, and there will be large deviations in the values, the degree of physiological deviation is analyzed and quantified on this basis.

[0023] Preferably, in one embodiment of the present invention, cluster analysis is performed on physiological data of the same dimension in medical nursing data of different patients to obtain several clusters in the clustering results, including the specific method of: Take any patient as the target patient, and take the blood oxygen dimension of the target patient as an example for analysis, that is, the blood oxygen saturation of the target patient. The physiological data of the blood oxygen dimension of the target patient is the blood oxygen data of the target patient; DBSCAN clustering is performed on all the blood oxygen data of the target patient and all the blood oxygen data of a large number of patients obtained, and the distance measurement uses the absolute value of the difference between the blood oxygen data to obtain the clustering results and several clusters therein.

[0024] Preferably, in one embodiment of the present invention, the physiological deviation degree of each physiological data of each dimension of each patient is obtained according to the cluster in which the physiological data is located and the clustering result, and the specific method includes: Obtain the number of blood oxygen data in each cluster of the blood oxygen dimension; take the cluster with the largest number of blood oxygen data among all clusters of the blood oxygen dimension as the reference cluster of the blood oxygen dimension; then the overall deviation factor of any cluster in the blood oxygen dimension The calculation method is: in, Indicates the number of blood oxygen data in this cluster, Indicates the number of blood oxygen data in the reference cluster of the blood oxygen dimension, Represents the mean of all blood oxygen data in this cluster, Represents the mean of all blood oxygen data in the reference cluster of the blood oxygen dimension, It represents the maximum absolute value of the difference between the blood oxygen data in the blood oxygen dimension, that is, the absolute value of the difference between any two blood oxygen data in the blood oxygen dimension is obtained, and the maximum value is obtained among all the absolute values ​​of the difference.

[0025] It should be noted that in the cluster analysis of blood oxygen data in the blood oxygen dimension, the reference cluster contains the most blood oxygen data and is more likely to be a cluster containing a large amount of normal blood oxygen data. The greater the difference in the number of blood oxygen data between other clusters and the reference cluster, and the greater the difference between the mean values ​​of blood oxygen data, the more likely it is that the cluster contains some abnormal blood oxygen data, and the larger the overall deviation factor of the corresponding cluster is, which is used to reflect the possibility that the cluster is a cluster of abnormal blood oxygen data.

[0026] Furthermore, for any blood oxygen data of the target patient, the absolute value of the difference between the blood oxygen data and the blood oxygen data corresponding to the center point of the cluster in which it is located is obtained, and the absolute value of the difference is obtained. The ratio of the blood oxygen data to the target patient is obtained, and the product of the ratio and the overall deviation factor of the cluster to which the blood oxygen data belongs is used as the physiological deviation degree of the blood oxygen data of the target patient; the physiological deviation degree of each blood oxygen data of each patient's blood oxygen dimension is obtained according to the above method; similarly, the physiological deviation degree of each physiological data of each dimension of each patient is obtained.

[0027] Preferably, in one embodiment of the present invention, the deviation amount is obtained for all physiological data of the same dimension of the same patient, and the difference of the time-series adjacent data of the deviation amount is analyzed, and the physiological deviation degree is corrected to obtain the physiological difference degree of each physiological data of each dimension of each patient, including the specific method of: It should be noted that due to the differences in physical fitness between different patients, there are large differences between the physiological data corresponding to the same physiological indicators in different patients, even if they are all normal. Therefore, it is necessary to perform analysis based on the physiological data of the corresponding dimension, and the reference clusters of each dimension can reflect a large amount of normal physiological data of the corresponding dimension; for the target patient to be analyzed, if the distribution range of the deviation between the target patient's physiological data of this dimension and the physiological data of the reference cluster is smaller, and the distribution is more concentrated, it indicates that the deviation of the target patient's overall physiological data tends to be consistent, which may not be due to abnormalities in the target patient's physiological data, but deviations caused by the physical fitness itself.

[0028] Specifically, taking the blood oxygen dimension as an example, the mean of all blood oxygen data in the reference cluster of the blood oxygen dimension is used as the standard blood oxygen data of the blood oxygen dimension; the difference between any blood oxygen data of the target patient and the standard blood oxygen data is obtained as the blood oxygen offset of the blood oxygen data of the target patient, and the blood oxygen offset of each blood oxygen data of the target patient is obtained; then the overall deviation consistency of the blood oxygen dimension of the target patient is obtained. The calculation method is: in, Represents the variance of the blood oxygen offset of all blood oxygen data of the target patient, Indicates the number of blood oxygen data of the target patient, The target patient The blood oxygen offset of each blood oxygen data, Represents the mean of all blood oxygen offsets of all blood oxygen data of the target patient, represents the standard deviation of all blood oxygen offsets of all blood oxygen data of the target patient; represents the absolute value function, represents an exponential function with a natural constant as the base. In this embodiment, Model to present inverse proportional relationship and normalization processing, As the input of the model, the implementer can set the inverse proportional function and normalization function according to the actual situation.

[0029] It should be noted that the variance of the blood oxygen offset reflects the overall distribution range of the deviation of the target patient's blood oxygen data compared with the standard blood oxygen data. The smaller the variance, the smaller the distribution range, and the more consistent the overall deviation. At the same time, the kurtosis of the blood oxygen offset is calculated. The larger the kurtosis, the more concentrated the blood oxygen offset, which further indicates that the overall deviation tends to be consistent, and the greater the consistency of the overall deviation of the blood oxygen dimension.

[0030] It should be further explained that, in terms of overall deviation consistency, it is necessary to analyze a single blood oxygen data set. The greater its impact on the variance, that is, the greater the difference in the variance of the blood oxygen offset before and after removing the blood oxygen data, the less consistent the blood oxygen data is with the overall consistent deviation, and it is more likely to be a larger deviation caused by local abnormalities. By analyzing the changing trend of the blood oxygen offset with adjacent blood oxygen data, it is further quantified as a deviation caused by a real local abnormality, rather than a single deviation occurring during the data acquisition process, that is, abnormal physiological data will last for a period of time, and will not suddenly change at a single moment and then immediately return to normal.

[0031] Specifically, for any blood oxygen data of the target patient, the blood oxygen offset of the blood oxygen data is removed, and the variance of the blood oxygen offsets of other blood oxygen data of the target patient is recalculated and used as the decimated offset variance of the blood oxygen data; the difference between the variance of the blood oxygen offset of all blood oxygen data of the target patient and the decimated offset variance of the blood oxygen data is used as the variance deviation factor of the blood oxygen data; the variance deviation factors of all blood oxygen data of the target patient are linearly normalized, and the result is used as the variance deviation of each blood oxygen data of the target patient.

[0032] Further, a neighborhood range is constructed. In this embodiment, the neighborhood range is described using 3. The left and right sides of the blood oxygen data are 3 blood oxygen data, as the target patient In particular, if there are less than 3 blood oxygen data on the left or right side of the blood oxygen data, which is insufficient to form a neighborhood range, the neighborhood range is constructed based on the actual blood oxygen data. Local deviation factor of blood oxygen data The calculation method is: in, The target patient The variance deviation of blood oxygen data, The target patient The number of blood oxygen data in the neighborhood of blood oxygen data, The target patient The blood oxygen offset of each blood oxygen data, The target patient The blood oxygen data is within the neighborhood of The blood oxygen offset of each blood oxygen data, Indicates the maximum value of the blood oxygen offset of all blood oxygen data of the target patient.

[0033] It should be noted that the greater the variance deviation of blood oxygen data, the more consistent it is with the patient's overall consistent deviation, and the more likely it is that a larger deviation will occur locally or single compared to standard blood oxygen data; and by performing difference analysis on the blood oxygen offset of adjacent blood oxygen data, the smaller the difference, the greater the possibility of a large deviation occurring locally during that period, rather than a single deviation caused by the data acquisition process.

[0034] Furthermore, the target patient Physiological differences in blood oxygen data The calculation method is: in, The target patient The physiological difference of blood oxygen data The target patient The local deviation factor of blood oxygen data, The target patient The physiological deviation degree of blood oxygen data, Indicates the overall deviation consistency of the target patient's blood oxygen dimension; obtains the degree of physiological difference of each dimension of the physiological data of each patient according to the above method.

[0035] At this point, by performing cluster analysis on the physiological data of the same dimension of different patients based on the fact that they contain a large amount of normal physiological data, the deviation of the clusters and the deviation of the physiological data within the clusters are quantified respectively, and the possibility of abnormal physiological data is preliminarily quantified; then, an overall deviation analysis is performed on the physiological data of the same dimension of the same patient to avoid the physiological data deviation caused by the difference in the physical fitness of the patients affecting the abnormal analysis of the physiological data, and at the same time, the possibility of real abnormalities in the physiological data of the patients within a local time is considered, so as to correct the degree of physiological differences in obtaining each physiological data.

[0036] Step S003, determine the degree of physiological difference to obtain several abnormal physiological data of each dimension of each patient; based on the distribution of abnormal physiological data of the same dimension of the same patient and the degree of physiological difference of all physiological data, obtain the priority care of each dimension of each patient; combine the degree of physiological difference of physiological data of each dimension of the same patient at the current moment to obtain the treatment priority of each patient.

[0037] Preferably, in one embodiment of the present invention, the degree of physiological difference is determined to obtain a number of abnormal physiological data of each patient in each dimension, including the specific method of: Taking the blood oxygen dimension as an example, an abnormal threshold is preset, and the abnormal threshold in this embodiment is described as 0.6; for any blood oxygen data of the target patient, if the physiological difference degree of the blood oxygen data is greater than or equal to the abnormal threshold, the blood oxygen data is recorded as the abnormal blood oxygen data of the target patient; obtain a number of abnormal blood oxygen data of the target patient; obtain a number of abnormal physiological data of each dimension of each patient according to the above method.

[0038] Preferably, in one embodiment of the present invention, based on the distribution of abnormal physiological data of the same dimension of the same patient and the physiological difference degree of all physiological data, the priority care degree of each patient in each dimension is obtained, including the specific method of: It should be noted that after obtaining the abnormal physiological data, the physiological data of the corresponding dimension of the same patient are segmented according to the abnormal physiological data, and the change in the time length of the segment can reflect the rehabilitation effect of the corresponding dimension. The gradual lengthening of the segment indicates that the possibility of recurrence of abnormal physiological data in the corresponding dimension is smaller and the rehabilitation effect is better. At the same time, the physiological difference degree of the physiological data within the segment is analyzed. The smaller the overall physiological difference degree, the better the recovery of the physiological data of the corresponding dimension within the segment; and the physiological difference degree of the physiological data of the most recent segment is used to further quantify the rehabilitation effect of the corresponding dimension.

[0039] Specifically, taking the blood oxygen dimension of the target patient as an example, after obtaining a number of abnormal blood oxygen data of the target patient, the blood oxygen data of the target patient other than the abnormal blood oxygen data is recorded as non-abnormal blood oxygen data; the non-abnormal blood oxygen data of the target patient that is continuous in time series is regarded as a blood oxygen recovery segment of the target patient. It should be noted that a discontinuous single non-abnormal blood oxygen data is also regarded as a blood oxygen recovery segment; and a number of blood oxygen recovery segments of the target patient are obtained.

[0040] Furthermore, for the target patient Blood oxygen recovery stage, its physiological recovery degree The calculation method is: in, The target patient The number of non-abnormal blood oxygen data in the blood oxygen rehabilitation segment, The target patient The number of non-abnormal blood oxygen data in the blood oxygen rehabilitation segment, The target patient The blood oxygen recovery stage and the The number of consecutive abnormal blood oxygen data between blood oxygen recovery segments, The target patient The average of the physiological difference levels of all non-abnormal blood oxygen data in the first blood oxygen rehabilitation segment; in particular, the physiological recovery level of the target patient in the first blood oxygen rehabilitation segment is The results are expressed as follows, where Represents the mean of the physiological difference degree of all non-abnormal blood oxygen data in the first blood oxygen rehabilitation segment of the target patient.

[0041] It should be noted that the more non-abnormal blood oxygen data added compared to the previous blood oxygen rehabilitation segment, the longer the recurrence hiding time of the corresponding blood oxygen rehabilitation segment. At the same time, the fewer the number of abnormal blood oxygen data between the two blood oxygen rehabilitation segments, the less severe the abnormal recurrence in the blood oxygen dimension, and the better the rehabilitation effect. The smaller the physiological difference of non-abnormal blood oxygen data within the blood oxygen rehabilitation segment, the better the local rehabilitation effect.

[0042] Furthermore, the number of non-abnormal blood oxygen data in all blood oxygen rehabilitation segments of the target patient is weighted and normalized, and the result is used as the rehabilitation weight of each blood oxygen rehabilitation segment of the target patient; then the priority care degree of the target patient's blood oxygen dimension is The calculation method is: in, It represents the mean value of the physiological difference of all non-abnormal blood oxygen data in the last blood oxygen rehabilitation segment of the target patient. Indicates the number of non-abnormal blood oxygen data in the last blood oxygen rehabilitation segment of the target patient. Indicates the number of blood oxygen recovery segments of the target patient, The target patient The recovery weight of each blood oxygen recovery segment, The target patient Physiological recovery level of each blood oxygen recovery stage; represents an exponential function with a natural constant as the base. In this embodiment, Model to present inverse proportional relationship and normalization processing, As the input of the model, the implementer can set the inverse proportional function and normalization function according to the actual situation.

[0043] It should be noted that the greater the mean value of the physiological difference in the most recent blood oxygen rehabilitation segment and the smaller the number of non-abnormal blood oxygen data, the more serious the recent recurrence of the disease in the blood oxygen dimension and the worse the rehabilitation effect, and priority should be given to care. At the same time, the number of non-abnormal blood oxygen data in each blood oxygen rehabilitation segment, that is, the length of time without recurrence, is used as a weight to quantify the physiological rehabilitation degree of the blood oxygen rehabilitation segment as a whole. The greater the physiological rehabilitation degree and the longer the length of time without recurrence, the greater the proportion of the blood oxygen rehabilitation segment in the quantification process, that is, the more it can reflect the rehabilitation effect. The smaller the overall quantification result, the greater the rehabilitation effect, the more priority care is needed, and the greater the priority care degree of the corresponding dimension.

[0044] Preferably, in one embodiment of the present invention, the treatment priority of each patient is obtained by combining the physiological difference degree of each dimension of the physiological data of the same patient at the current moment, and the specific method includes: It should be noted that the nursing priority of a single dimension of a patient reflects the rehabilitation effect of the physiological indicators of the corresponding dimension, while the overall treatment priority of the patient requires an overall analysis of the rehabilitation effects of all physiological indicators. On this basis, it is necessary to combine the physiological differences of the physiological data of each dimension of the patient at the current moment. The greater the physiological difference of the physiological data of the corresponding dimension at the current moment, the more likely the corresponding dimension is to be abnormal at the current moment, requiring timely nursing adjustment; and the more physiological indicators that require timely nursing adjustment, the higher the treatment priority the patient should have.

[0045] Specifically, the degree of physiological difference of the physiological data of each dimension of the target patient at the current moment is used as the weight of the priority treatment of each dimension of the target patient, and the priority treatment of all dimensions of the target patient is weighted and averaged, and the result is used as the treatment priority of the target patient; the treatment priority of each patient is obtained according to the above method.

[0046] At this point, abnormal physiological data are judged based on the degree of physiological differences, and the rehabilitation effect of the patient's corresponding dimension is quantified through the distribution of abnormal physiological data in the same dimension of the patient and the change in the degree of physiological differences of other non-abnormal physiological data. This reflects whether the patient's symptoms relapse and the severity of the relapse in the corresponding dimension, and obtains the priority care of the patient in each dimension; further analyze the priority care of each dimension as a whole, and comprehensively quantify the patient's treatment priority.

[0047] Step S004: Process the medical care data of the patients according to the processing priority of each patient.

[0048] Specifically, after obtaining the processing priorities of all patients based on their medical nursing data since admission, all patients currently being treated in the hospital are arranged in descending order of processing priority from large to small to obtain a patient priority processing sequence; the medical nursing data of the patients are processed and analyzed in the order of the patient priority processing sequence, and after processing and analysis, the corresponding patients are cared for, thereby completing the processing of the medical nursing data of the patients being treated in the hospital.

[0049] So far, cluster analysis is performed on the physiological data of each dimension of a large number of patients, the degree of physiological deviation is quantified by the distribution of physiological data in the clustering results, and the changes in physiological data of the same dimension of the same patient are further analyzed to correct the degree of physiological difference. The rehabilitation effect of each dimension of the patient is quantified based on the degree of physiological difference, and finally the medical nursing data of patients with poor rehabilitation effects are given priority processing and corresponding care, so as to improve the efficiency of medical nursing data processing and the applicability of use in hospital databases.

[0050] Another embodiment of the present invention provides a medical nursing data processing system, which includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the above-mentioned method steps S001 to S004 are implemented.

[0051] Another embodiment of the present invention provides a medical nursing data processing electronic device, the device comprising: Medical nursing data acquisition module: obtain medical nursing data of several patients; Medical nursing data analysis module: cluster analysis is performed on physiological data of the same dimension in medical nursing data of different patients to obtain several clusters in the clustering results; the physiological deviation degree of each physiological data of each dimension of each patient is obtained according to the cluster in which the physiological data is located and the clustering results; the deviation amount is obtained for all physiological data of the same dimension of the same patient, and the difference between the time-series adjacent data of the deviation amount is analyzed, the physiological deviation degree is corrected, and the physiological difference degree of each physiological data of each dimension of each patient is obtained; Determine the degree of physiological difference to obtain several abnormal physiological data of each dimension of each patient; obtain the priority nursing degree of each dimension of each patient based on the distribution of abnormal physiological data of the same dimension of the same patient and the degree of physiological difference of all physiological data; obtain the treatment priority of each patient by combining the degree of physiological deviation of physiological data of each dimension of the same patient at the current moment; Medical nursing data processing module: processes the patient's medical nursing data according to the treatment priority of each patient.

[0052] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A medical nursing data processing method, characterized in that: The method comprises the following steps: Acquire medical nursing data of a number of patients, wherein the medical nursing data includes multi-dimensional physiological data; Perform cluster analysis on physiological data of the same dimension in medical nursing data of different patients to obtain several clusters in the clustering results; obtain the physiological deviation degree of each physiological data of each dimension of each patient according to the cluster in which the physiological data is located and the clustering results; obtain the deviation amount of all physiological data of the same dimension of the same patient, analyze the difference of adjacent data in time series of the deviation amount, correct the physiological deviation degree, and obtain the physiological difference degree of each physiological data of each dimension of each patient; Determine the degree of physiological difference to obtain a number of abnormal physiological data of each dimension of each patient; obtain the priority nursing degree of each dimension of each patient based on the distribution of abnormal physiological data of the same dimension of the same patient and the degree of physiological difference of all physiological data; obtain the treatment priority of each patient by combining the degree of physiological difference of physiological data of each dimension of the same patient at the current moment; The medical care data of each patient is processed according to the treatment priority of each patient.

2. A medical nursing data processing method according to claim 1, characterized in that: The cluster analysis is performed on the physiological data of the same dimension in the medical nursing data of different patients to obtain several clusters in the clustering results, including the specific method of: Any patient is taken as the target patient, and the physiological data of the target patient's blood oxygen dimension is the target patient's blood oxygen data; DBSCAN clustering is performed on all the target patient's blood oxygen data and all the blood oxygen data of a large number of patients obtained, and the distance measurement uses the absolute value of the difference between the blood oxygen data to obtain the clustering results and several clusters therein.

3. A medical nursing data processing method according to claim 2, characterized in that: The specific method for obtaining the physiological deviation degree of each physiological data of each dimension of each patient is as follows: Obtain the number of blood oxygen data in each cluster of the blood oxygen dimension; take the cluster with the largest number of blood oxygen data in all clusters of the blood oxygen dimension as the reference cluster of the blood oxygen dimension; the overall deviation factor of any cluster in the blood oxygen dimension The calculation method is: in, Indicates the number of blood oxygen data in this cluster, Indicates the number of blood oxygen data in the reference cluster of the blood oxygen dimension, Represents the mean of all blood oxygen data in this cluster, Represents the mean of all blood oxygen data in the reference cluster of the blood oxygen dimension, Indicates the maximum absolute value of the difference between the blood oxygen data in the blood oxygen dimension; For any blood oxygen data of the target patient, obtain the absolute value of the difference between the blood oxygen data and the blood oxygen data corresponding to the center point of the cluster where it is located, and obtain the absolute value of the difference and The ratio of the blood oxygen data to the target patient is obtained by multiplying the ratio by the overall deviation factor of the cluster to which the blood oxygen data belongs, and the product of the ratio and the overall deviation factor of the cluster to which the blood oxygen data belongs is taken as the physiological deviation degree of the blood oxygen data of the target patient.

4. A medical nursing data processing method according to claim 3, characterized in that: The specific method of obtaining the deviation amount for all physiological data of the same dimension of the same patient, analyzing the difference of adjacent time series data of the deviation amount, correcting the physiological deviation degree, and obtaining the physiological difference degree of each physiological data of each dimension of each patient includes: The mean of all blood oxygen data in the reference cluster of the blood oxygen dimension is used as the standard blood oxygen data of the blood oxygen dimension; the difference between any blood oxygen data of the target patient and the standard blood oxygen data is obtained as the blood oxygen offset of the blood oxygen data of the target patient; the overall deviation consistency of the blood oxygen dimension of the target patient is calculated. The calculation method is: in, Represents the variance of the blood oxygen offset of all blood oxygen data of the target patient, Indicates the number of blood oxygen data of the target patient, The target patient The blood oxygen offset of each blood oxygen data, Represents the mean of all blood oxygen offsets of all blood oxygen data of the target patient, represents the standard deviation of all blood oxygen offsets of all blood oxygen data of the target patient; represents the absolute value function, represents an exponential function with a natural constant as base; According to the distribution range of the blood oxygen offset of the target patient's blood oxygen data and the difference in the blood oxygen offset of adjacent blood oxygen data, a local deviation factor of each blood oxygen data of the target patient is obtained; Target patients Physiological differences in blood oxygen data The calculation method is: in, The target patient The local deviation factor of blood oxygen data, The target patient The physiological deviation degree of blood oxygen data, Represents the overall deviation consistency of the target patient's blood oxygen dimension.

5. A medical nursing data processing method according to claim 4, characterized in that: The specific method of obtaining the local deviation factor of each blood oxygen data of the target patient according to the distribution range of the blood oxygen offset of the target patient's blood oxygen data and the difference in the blood oxygen offset of adjacent blood oxygen data includes: For any blood oxygen data of the target patient, the blood oxygen offset of the blood oxygen data is removed, and the variance of the blood oxygen offset of other blood oxygen data of the target patient is recalculated and used as the denoted offset variance of the blood oxygen data; The difference between the variance of the blood oxygen offset of all the blood oxygen data of the target patient and the declinable offset variance of the blood oxygen data is used as the variance deviation factor of the blood oxygen data; The variance deviation factor of all the blood oxygen data of the target patient is linearly normalized, and the obtained result is used as the variance deviation of each blood oxygen data of the target patient; Construct target patient The neighborhood range of blood oxygen data of the target patient Local deviation factor of blood oxygen data The calculation method is: in, The target patient The variance deviation of blood oxygen data, The target patient The number of blood oxygen data in the neighborhood of blood oxygen data, The target patient The blood oxygen offset of each blood oxygen data, The target patient The blood oxygen data is within the neighborhood of The blood oxygen offset of each blood oxygen data, Indicates the maximum value of the blood oxygen offset of all blood oxygen data of the target patient.

6. A medical nursing data processing method according to claim 2, characterized in that: The method of obtaining the priority nursing degree of each dimension of each patient based on the distribution of abnormal physiological data of the same dimension of the same patient and the physiological difference degree of all physiological data includes: The blood oxygen data of the target patient other than the abnormal blood oxygen data is recorded as the non-abnormal blood oxygen data; the non-abnormal blood oxygen data of the target patient that are continuous in time series is regarded as a blood oxygen rehabilitation segment of the target patient; The number of non-abnormal blood oxygen data in adjacent blood oxygen rehabilitation segments is compared, and the physiological recovery degree of each blood oxygen rehabilitation segment of the target patient is obtained by combining the abnormal blood oxygen data between adjacent blood oxygen rehabilitation segments and the physiological difference degree of non-abnormal blood oxygen data in the blood oxygen rehabilitation segments; The number of non-abnormal blood oxygen data in all blood oxygen rehabilitation segments of the target patient is weighted and normalized, and the result is used as the rehabilitation weight of each blood oxygen rehabilitation segment of the target patient; the priority care degree of the target patient's blood oxygen dimension The calculation method is: in, It represents the mean value of the physiological difference of all non-abnormal blood oxygen data in the last blood oxygen rehabilitation segment of the target patient. Indicates the number of non-abnormal blood oxygen data in the last blood oxygen rehabilitation segment of the target patient. Indicates the number of blood oxygen recovery segments of the target patient, The target patient The recovery weight of each blood oxygen recovery segment, The target patient Physiological recovery level of each blood oxygen recovery stage; Represents an exponential function with a natural constant as its base.

7. A medical nursing data processing method according to claim 6, characterized in that: The method of comparing the number of non-abnormal blood oxygen data in adjacent blood oxygen rehabilitation segments, combining the abnormal blood oxygen data between adjacent blood oxygen rehabilitation segments, and the physiological difference degree of non-abnormal blood oxygen data in the blood oxygen rehabilitation segments, and obtaining the physiological rehabilitation degree of each blood oxygen rehabilitation segment of the target patient includes the following specific methods: in, The target patient The number of non-abnormal blood oxygen data in the blood oxygen rehabilitation segment, The target patient The number of non-abnormal blood oxygen data in the blood oxygen rehabilitation segment, The target patient The blood oxygen recovery stage and the The number of consecutive abnormal blood oxygen data between blood oxygen recovery segments, The target patient The mean of the physiological difference levels of all non-abnormal blood oxygen data in the blood oxygen recovery segment.

8. A medical nursing data processing method according to claim 2, characterized in that: The specific method of obtaining the treatment priority of each patient includes: The physiological difference degree of each dimension of the physiological data of the target patient at the current moment is used as the weight of the priority treatment degree of each dimension of the target patient. The priority treatment degrees of all dimensions of the target patient are weighted and averaged, and the result is used as the treatment priority of the target patient.

9. A medical nursing data processing system, 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, the steps of the medical nursing data processing method as described in any one of claims 1-8 are implemented.

10. An electronic device for processing medical nursing data, the device comprising: A medical nursing data acquisition module is used to acquire medical nursing data of several patients; The medical nursing data analysis module is used to perform cluster analysis on physiological data of the same dimension in the medical nursing data of different patients to obtain several clusters in the clustering results; obtain the physiological deviation degree of each physiological data of each dimension of each patient according to the cluster in which the physiological data is located and the clustering results; obtain the deviation amount of all physiological data of the same dimension of the same patient, and analyze the difference of adjacent data in time series of the deviation amount, correct the physiological deviation degree, and obtain the physiological difference degree of each physiological data of each dimension of each patient; Determine the degree of the physiological difference and obtain a number of abnormal physiological data of each patient in each dimension; Based on the distribution of abnormal physiological data of the same dimension of the same patient and the physiological difference degree of all physiological data, the priority of nursing care in each dimension of each patient is obtained; combined with the physiological difference degree of physiological data of each dimension of the same patient at the current moment, the priority of treatment of each patient is obtained; The medical nursing data processing module is used to process the medical nursing data of the patients according to the processing priority of each patient.

Images