A clinical nursing data analysis system based on big data

Abstract

The present invention discloses a clinical nursing data analysis system based on big data, which specifically relates to the technical field of clinical nursing data, including a data acquisition module and a data alignment module. The data acquisition module comprehensively collects the clinical nursing data of patients, thereby ensuring the comprehensiveness and real-time nature of the data; the data alignment module aligns the real-time monitoring data and the fixed-time point detection data and divides them into time periods, thereby effectively solving the problem of inconsistent data time and providing a clear and orderly data basis for subsequent data analysis; the first nursing data abnormality index Ta, the second nursing data abnormality index Tb and the laboratory test index abnormality index Ts are jointly analyzed to obtain the health status estimation index P of each patient J ; Adjust the distribution of monitoring resources based on the patient's health status prediction index; solve the problem that the clinical care management system in the existing technology is not objective and effective enough.

Description

Technical Field

[0001] The present invention relates to the technical field of clinical nursing data, and more specifically, to a clinical nursing data analysis system based on big data. Background Art

[0002] Clinical nursing data analysis can reveal problems and deficiencies in nursing work by collecting, organizing and analyzing various data of patients during the nursing process, and provide nursing staff with a scientific basis for decision-making. For example, by analyzing the patient's physiological indicators, complication rates and other data, potential nursing risks can be discovered in a timely manner, so that targeted intervention measures can be taken to avoid adverse events and improve the quality of nursing.

[0003] In the invention patent application document with application number CN202410034648.4 and titled "A method and system for monitoring and managing ICU ward data", the field of ward data management technology is involved. The system includes a data unification module, a data detection module, an abnormal marking module and an evaluation guidance module; its technical points are: according to the duration of the abnormal values ​​of physiological data under each type, not only can the patient's physiological data be clearly and specifically warned, but also the frequency of the marked abnormal values ​​can be comprehensively used to predict the patient's physical state estimation index. According to the physical state estimation index, the corresponding patient's examination frequency prediction evaluation value can be accurately and efficiently obtained. Medical staff or doctors can refer to the examination frequency prediction evaluation value and conduct examinations on patients within a specified period to further ensure the patient's safety, while also saving manpower to a certain extent.

[0004] However, there are still some problems. For example, in the process of obtaining the patient's physical state prediction index, the patient's physical state prediction index is obtained only based on the mean of each abnormal difference and the mean of each marking frequency, which is not objective enough and does not take into account the impact of the patient's physiological data type on the physical state prediction index; for example, the mean of the abnormal difference of blood pressure, blood sugar, blood oxygen, and body temperature will definitely have different impacts on the physical state prediction index; therefore, the clinical nursing management system in the prior art is not objective and effective enough. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides a clinical nursing data analysis system based on big data to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: a clinical nursing data analysis system based on big data, comprising:

[0007] The data collection module is used to collect the patient's clinical care data, which includes real-time continuous monitoring data, fixed-time point detection data and laboratory detection data; the clinical care data is aggregated and transmitted to the data alignment module;

[0008] The data alignment module is used to align the real-time monitoring data and the fixed time point detection data, and divide them into several time periods. Suppose there are n time periods, and i represents the sequential number of the time period;

[0009] A data analysis module is used to obtain the patient's first nursing data abnormality index Ta, second nursing data abnormality index Tb and laboratory test index abnormality index Ts; the first nursing data abnormality index Ta is obtained by analyzing the real-time continuous monitoring data, the second nursing data abnormality index Tb is obtained by analyzing the fixed time point detection data; and the laboratory test index abnormality index Ts is obtained by analyzing the laboratory test data;

[0010] The patient health status assessment module is used to obtain the estimated health status index of each patient; jointly analyze the first nursing data abnormality index Ta, the second nursing data abnormality index Tb and the laboratory test index abnormality index Ts to obtain the estimated health status index P of each patient J ;

[0011] The monitoring resource allocation module adjusts the distribution of monitoring resources based on the patient's health status estimated index.

[0012] Preferably, in the data acquisition module, the real-time continuous monitoring data refers to the continuous nursing data obtained by real-time monitoring of instruments and equipment; the fixed-time point detection data refers to the nursing data obtained by fixed-time point detection; the laboratory detection data refers to the nursing data obtained by laboratory detection; suppose that the nursing data includes m types of monitoring indicators, and j represents the type number of the monitoring indicator; for the monitoring indicator matching weight coefficient, the weight coefficient of the jth monitoring indicator is recorded as qy j .

[0013] Preferably, in the data alignment module, the real-time continuous monitoring data is aggregated into a time period corresponding to a fixed time point, and the fixed time point detection data and laboratory detection data are aligned with the records closest to the real-time monitoring data time period based on the timestamp; if the time interval between the fixed time point detection data is large, an interpolation method is used to generate intermediate data points, or data is extrapolated based on historical data to better align with the real-time monitoring data; the nursing data is divided into multiple intervals according to the patient identity and time period order, and each interval contains all the nursing data of the patient in that time period.

[0014] Preferably, the first nursing data abnormality index Ta is obtained in the following manner:

[0015] Filter out the existing monitoring indicators from the real-time continuous monitoring data, record them as set A; obtain the real-time continuous monitoring data in the i-th time period, and record the average value, abnormal difference mean and fluctuation coefficient of the j-th monitoring indicator as avg ij ,med ij , cv ij ; Use xa j Indicates the upper limit of the monitoring indicator, using xb j Indicates the lower limit of the monitoring indicator;

[0016] By formula The first nursing data abnormality index Ta is calculated.

[0017] Preferably, the abnormal difference mean refers to the average value of the difference between all observations exceeding the normal range or expected value and the corresponding benchmark value (such as median, mean, etc.) of the monitoring indicator in the i-th time period;

[0018] The coefficient of fluctuation is the ratio of the standard deviation to the mean value, which is used to measure the relative fluctuation degree of the data. The mean value of the jth monitoring indicator in the ith time period is calculated, the standard deviation of the monitoring indicator in the corresponding time period is calculated, and the coefficient of fluctuation is obtained by dividing the standard deviation by the mean value.

[0019] Preferably, the second nursing data abnormality index Tb is obtained in the following manner:

[0020] Filter out the existing monitoring indicators from the detection data at a fixed time point, and record them as set B;

[0021] Get the fixed time point detection data in the i-th time period, and record the detection value of the j-th monitoring indicator as x ij ;

[0022] By formula The second nursing data abnormality index Tb is calculated.

[0023] Preferably, the method for obtaining the abnormal index Ts of the laboratory test index is:

[0024] Filter out the existing monitoring indicators from the laboratory test data and record them as set C; obtain the closest laboratory test data in the i-th time period, record the laboratory test time, and use the formula The abnormal index Ts of laboratory test indicators is calculated, where Ta represents the laboratory test time, Tb represents the center point time of the i-th time period, and Tc represents the attenuation constant, which represents the influence of the time interval on the health status prediction index.

[0025] Preferably, the health status prediction index P J The way to obtain is:

[0026] By formula Calculate the patient's health status estimated index P J , f 1. f 2. f 3 represent the influence coefficients of each item, which are set based on the actual situation; suppose there are P patients, and q represents the patient's identity sequence number; the health status assessment index of the qth patient is recorded as ; Match monitoring resources for each patient based on the health status estimation index, and record the monitoring resources of the qth patient as JT_q; In further design, based on the formula The monitoring resources are calculated, where Xc represents the monitoring resource correction coefficient and δ represents the monitoring resource correction constant.

[0027] Preferably, a nursing data quality assessment module is also included before the data analysis module, including:

[0028] Obtain the consistency of nursing data: verify the accuracy of nursing indicators, record the accuracy of the jth monitoring indicator as JHj, set the preset accuracy of the jth monitoring indicator as yzj, and use the formula Calculate the accuracy of nursing data sz;

[0029] Missing proportion of nursing data: Get the theoretical size LC and actual size sc of nursing data through the formula The missing proportion of nursing data sq was calculated;

[0030] Get the data collection time difference, take the average to get the data collection time difference average value ΔsT, calculate the ratio of the actual data collection frequency to the preset collection frequency, and get the data update frequency ratio Fr. Calculate and obtain the data timeliness description parameter sx of the nursing data;

[0031] Taking into account the deviation parameters, missing ratio and data timeliness descriptive parameters, the nursing data quality evaluation index was obtained; in the further design, the comprehensive evaluation result was obtained by weighted summation, and the formula The nursing data quality assessment index QI is calculated, where β1, β2, and β3 are the weight coefficients of each item, which are used to adjust the impact of each part on the overall quality assessment;

[0032] Measures are taken based on the nursing data quality assessment index. If the nursing data quality assessment index is lower than the threshold, an early warning is issued, indicating that the nursing data is abnormal and the data collection module needs to be maintained; otherwise, no measures are taken and the data analysis module is entered.

[0033] Preferably, the clinical nursing data analysis system further includes a nursing risk management module, which is used to obtain a nursing risk coefficient and take measures based on the nursing risk coefficient; including:

[0034] The maximum monitoring resource at time t is recorded as ZJ_max, and the monitoring resource of the qth patient at time t is recorded as JT_q. The nursing resource shortage index ZQ is calculated. When the nursing resource shortage index exceeds the threshold, an early warning message is sent out to indicate that there is a shortage of staff.

[0035] By formula The nursing resource shortage index and the nursing data quality assessment index HF were jointly analyzed to obtain the nursing risk coefficient, where α represents the weight of the nursing resource shortage index, and Form (·) is used to convert the content in brackets into a range from 0 to 1;

[0036] If the nursing risk factor exceeds the threshold, a warning signal will be issued to prompt managers and nursing staff to pay attention and take corresponding risk management measures.

[0037] Technical effects and advantages of the present invention:

[0038] The clinical nursing data analysis system provided by the present invention obtains the first nursing data abnormality index Ta, the second nursing data abnormality index Tb and the laboratory test index abnormality index Ts by analyzing the clinical nursing data, and jointly analyzes the first nursing data abnormality index Ta, the second nursing data abnormality index Tb and the laboratory test index abnormality index Ts to obtain the health status estimation index P of each patient. J ; Adjust the distribution of monitoring resources based on the patient's health status prediction index; comprehensively collect the patient's clinical care data through the data acquisition module, including real-time continuous monitoring data, fixed-time point detection data and laboratory test data, to ensure the comprehensiveness and real-time nature of the data. The comprehensive data collection method enables doctors or caregivers to have a more comprehensive understanding of the patient's health status and to capture possible health changes in a timely manner; the data alignment module aligns the real-time monitoring data and fixed-time point detection data and divides them into time periods. This step effectively solves the problem of inconsistent data time and provides a clear and orderly data basis for subsequent data analysis. At the same time, the division of time periods also facilitates trend analysis and comparison, improves the accuracy and efficiency of data analysis, and solves the problem that the clinical care management system in the existing technology is not objective and effective enough.

[0039] The nursing risk management module in the clinical nursing data analysis system provided by the present invention can timely discover and solve problems in the nursing process, such as insufficient resources and low data quality, thereby improving nursing quality and patient satisfaction; the early warning information based on data analysis helps hospital managers to allocate nursing resources more scientifically, ensuring that there are sufficient resources to deal with emergencies at critical moments, enabling nursing staff to pay more attention to details and standardized operations in their daily work, and reducing the occurrence of nursing errors and adverse events. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a structural block diagram of the clinical nursing data analysis system of the present invention.

[0041] Figure 2 This is a structural block diagram of the nursing data quality assessment module of the present invention. DETAILED DESCRIPTION

[0042] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0043] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0044] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present application, its application, or uses.

[0045] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification. Example 1

[0046] See also Figure 1 The clinical nursing data analysis system structure diagram of the present invention provides the following Figure 1 A clinical nursing data analysis system based on big data is shown, comprising:

[0047] The data collection module is used to collect the patient's clinical care data, which includes real-time continuous monitoring data, fixed-time point detection data and laboratory detection data; the clinical care data is aggregated and transmitted to the data alignment module;

[0048] The data alignment module is used to align the real-time monitoring data and the fixed time point detection data, and divide them into several time periods. Suppose there are n time periods, and i represents the sequential number of the time period;

[0049] A data analysis module is used to obtain the patient's first nursing data abnormality index Ta, second nursing data abnormality index Tb and laboratory test index abnormality index Ts; the first nursing data abnormality index Ta is obtained by analyzing the real-time continuous monitoring data, the second nursing data abnormality index Tb is obtained by analyzing the fixed time point detection data; and the laboratory test index abnormality index Ts is obtained by analyzing the laboratory test data;

[0050] The patient health status assessment module is used to obtain the estimated health status index of each patient; jointly analyze the first nursing data abnormality index Ta, the second nursing data abnormality index Tb and the laboratory test index abnormality index Ts to obtain the estimated health status index P of each patient J ;

[0051] The monitoring resource allocation module adjusts the distribution of monitoring resources based on the patient's health status estimated index.

[0052] It needs to be further explained in the embodiment of the present invention that, in the data acquisition module, the real-time continuous monitoring data refers to the continuous nursing data obtained by real-time monitoring of instruments and equipment; the fixed time point detection data refers to the nursing data obtained by fixed time point detection; the laboratory detection data refers to the nursing data obtained by laboratory detection; suppose that the nursing data includes m types of monitoring indicators, and j represents the type number of the monitoring indicator; is the monitoring indicator matching weight coefficient, and the weight coefficient of the jth monitoring indicator is recorded as qy j .

[0053] What needs to be further explained in the embodiments of the present invention is that in the data alignment module, the real-time continuous monitoring data is aggregated into a time period corresponding to a fixed time point, and the fixed time point detection data and laboratory detection data are aligned with the records closest to the real-time monitoring data time period based on the timestamp; if the time interval between the fixed time point detection data is large, an interpolation method is used to generate intermediate data points, or data is extrapolated based on historical data to better align with the real-time monitoring data; the nursing data is divided into multiple intervals according to the patient identity and the order of the time period, and each interval contains all the nursing data of the patient in that time period.

[0054] It needs to be further explained in the embodiment of the present invention that the first nursing data abnormality index Ta is obtained in the following manner:

[0055] Filter out the existing monitoring indicators from the real-time continuous monitoring data, record them as set A; obtain the real-time continuous monitoring data in the i-th time period, and record the average value, abnormal difference mean and fluctuation coefficient of the j-th monitoring indicator as avg ij ,med ij , cv ij ; Use xa j Indicates the upper limit of the monitoring indicator, using xb j Indicates the lower limit of the monitoring indicator;

[0056] By formula The first nursing data abnormality index Ta is calculated.

[0057] What needs to be further explained in the embodiments of the present invention is that the abnormal difference mean refers to the average value of the difference between all observations that exceed the normal range or expected value and the corresponding benchmark value (such as median, mean, etc.) of the monitoring indicator in the i-th time period; the fluctuation coefficient is the ratio of the standard deviation to the mean value, which is used to measure the relative fluctuation degree of the data, calculate the mean value of the j-th monitoring indicator in the i-th time period, calculate the standard deviation of the monitoring indicator in the corresponding time period, and divide the standard deviation by the mean value to obtain the fluctuation coefficient.

[0058] It needs to be further explained in the embodiment of the present invention that the second nursing data abnormality index Tb is obtained in the following manner:

[0059] Filter out the existing monitoring indicators from the detection data at a fixed time point, and record them as set B;

[0060] Get the fixed time point detection data in the i-th time period, and record the detection value of the j-th monitoring indicator as x ij ;

[0061] By formula The second nursing data abnormality index Tb is calculated.

[0062] It needs to be further explained in the embodiment of the present invention that the method for obtaining the abnormal index Ts of the laboratory test index is:

[0063] Filter out the existing monitoring indicators from the laboratory test data and record them as set C; obtain the closest laboratory test data in the i-th time period, record the laboratory test time, and use the formula The abnormal index Ts of laboratory test indicators is calculated, where Ta represents the laboratory test time, Tb represents the center point time of the i-th time period, and Tc represents the attenuation constant, which represents the influence of the time interval on the health status prediction index.

[0064] In the embodiment of the present invention, it is necessary to further explain that the health status prediction index P J The way to obtain is:

[0065] By formula Calculate the patient's health status estimated index P J , f 1. f 2. f 3 represent the influence coefficients of each item, which are set based on the actual situation; suppose there are P patients, and q represents the patient's identity sequence number; the health status assessment index of the qth patient is recorded as ; Match monitoring resources for each patient based on the health status estimation index, and record the monitoring resources of the qth patient as JT_q; In further design, based on the formula The monitoring resources are calculated, where Xc represents the monitoring resource correction coefficient and δ represents the monitoring resource correction constant.

[0066] Example 2, see Figure 2 The structural block diagram of the nursing data quality assessment module of the embodiment of the present invention is different from the embodiment 1 in that the embodiment of the present invention further includes a nursing data quality assessment module before the data analysis module, and the nursing data quality assessment module includes a nursing data consistency analysis unit, a nursing data missing analysis unit, a collection timeliness analysis unit and a nursing data quality assessment unit;

[0067] The nursing data consistency analysis unit is used to obtain the consistency of nursing data and verify the accuracy of nursing indicators. The accuracy of the jth monitoring indicator is recorded as JHj, and the preset accuracy of the jth monitoring indicator is yzj. Calculate the accuracy of nursing data sz;

[0068] The nursing data missing analysis unit is used to obtain the missing proportion of nursing data, the theoretical size LC and the actual size sc of nursing data, and the formula The missing proportion of nursing data sq was calculated;

[0069] Get the data collection time difference, take the average to get the data collection time difference average value ΔsT, calculate the ratio of the actual data collection frequency to the preset collection frequency, and get the data update frequency ratio Fr. Calculate and obtain the data timeliness description parameter sx of the nursing data;

[0070] In the further design, the comprehensive evaluation result is obtained by weighted summation, and the formula The nursing data quality assessment index QI is calculated, where β1, β2, and β3 are the weight coefficients of each item, which are used to adjust the impact of each part on the overall quality assessment;

[0071] Measures are taken based on the nursing data quality assessment index. If the nursing data quality assessment index is lower than the threshold, an early warning is issued, indicating that the nursing data is abnormal and the data collection module needs to be maintained; otherwise, no measures are taken and the data analysis module is entered.

[0072] Embodiment 3, the difference between the embodiment of the present invention and embodiments 1 and 2 is that the clinical nursing data analysis system further includes a nursing risk management module, which is used to obtain a nursing risk coefficient and take measures based on the nursing risk coefficient, including:

[0073] The maximum monitoring resource at time t is recorded as ZJ_max, and the monitoring resource of the qth patient at time t is recorded as JT_q. The nursing resource shortage index ZQ is calculated. When the nursing resource shortage index exceeds the threshold, an early warning message is sent out to indicate that there is a shortage of staff.

[0074] By formula The nursing resource shortage index and the nursing data quality assessment index HF were jointly analyzed to obtain the nursing risk coefficient, where α represents the weight of the nursing resource shortage index, and Form (·) is used to convert the content in brackets into a range from 0 to 1;

[0075] If the nursing risk factor exceeds the threshold, a warning signal will be issued to prompt managers and nursing staff to pay attention and take corresponding risk management measures.

[0076] Finally: 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 spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A clinical nursing data analysis system based on big data, characterized in that: include: Data collection module, used to collect clinical care data of patients, including real-time continuous monitoring data, fixed time point detection data and laboratory detection data; Aggregate clinical care data and transfer them to the data alignment module; The data alignment module is used to align the real-time monitoring data and the fixed time point detection data, and divide them into several time periods. Suppose there are n time periods, and i represents the sequential number of the time period; The data analysis module obtains the first nursing data abnormality index Ta by analyzing the real-time continuous monitoring data, obtains the second nursing data abnormality index Tb by analyzing the fixed time point detection data; and obtains the laboratory detection index abnormality index Ts by analyzing the laboratory detection data; Among them, the existing monitoring indicators are screened out from the real-time continuous monitoring data, which are recorded as set A; the real-time continuous monitoring data in the i-th time period is obtained, and the average value, abnormal difference mean and fluctuation coefficient of the j-th monitoring indicator are recorded as avgij, medij, and cvij respectively; xaj is used to represent the upper limit of the monitoring indicator, and xbj is used to represent the lower limit of the monitoring indicator; through the formula The first nursing data abnormality index Ta is calculated; Filter out the existing monitoring indicators from the fixed time point detection data, and record them as set B; obtain the fixed time point detection data in the i-th time period, and record the detection value of the j-th monitoring indicator as xij; By formula The second nursing data abnormality index Tb is calculated; Filter out the existing monitoring indicators from the laboratory test data and record them as set C; obtain the closest laboratory test data in the i-th time period, record the laboratory test time, and use the formula The abnormal index Ts of laboratory test indicators is calculated; where T1 represents the laboratory test time, T2 represents the center point time of the i-th time period, and Tc represents the attenuation constant, which represents the influence of the time interval on the health status prediction index; The patient health status assessment module is used to obtain the estimated health status index of each patient; jointly analyze the first nursing data abnormality index Ta, the second nursing data abnormality index Tb and the laboratory test index abnormality index Ts to obtain the estimated health status index PJ of each patient; through the formula The patient's health status estimated index PJ is calculated, where f1, f2, and f3 represent the influence coefficients of each item respectively; suppose there are P patients, and q represents the patient's identity sequence number; the health status evaluation index of the qth patient is recorded as; based on the health status estimated index, monitoring resources are matched for each patient, and the monitoring resources of the qth patient are recorded as JT_q; The monitoring resource allocation module adjusts the distribution of monitoring resources based on the patient's health status estimation index; Based on the formula The monitoring resources are calculated, where Xc represents the monitoring resource correction coefficient and δ represents the monitoring resource correction constant.

2. The clinical nursing data analysis system based on big data according to claim 1, characterized in that: In the data acquisition module, the real-time continuous monitoring data refers to the continuous nursing data obtained through real-time monitoring by instruments and equipment; the fixed-time point detection data refers to the nursing data obtained through fixed-time point detection; the laboratory detection data refers to the nursing data obtained through laboratory detection; assuming that the nursing data includes m types of monitoring indicators, j is used to represent the type number of the monitoring indicator; the weight coefficient for monitoring indicator matching is denoted as qyj.

3. The clinical nursing data analysis system based on big data according to claim 1, characterized in that: In the data alignment module, the real-time continuous monitoring data is aggregated into a time period corresponding to a fixed time point, and the fixed time point test data and laboratory test data are aligned based on the timestamp with the records closest to the time period of the real-time monitoring data; If the time interval between the detection data at fixed time points is large, the interpolation method is used to generate intermediate data points.

4. A clinical nursing data analysis system based on big data according to claim 1, characterized in that: The data analysis module is preceded by a nursing data quality assessment module, which includes: Obtain the consistency of nursing data: verify the accuracy of nursing indicators, record the accuracy of the jth monitoring indicator as JHj, set the preset accuracy of the jth monitoring indicator as yzj, and use the formula Calculate the accuracy of nursing data sz; Missing proportion of nursing data: Get the theoretical size LC and actual size sc of nursing data through the formula The missing proportion of nursing data sq was calculated; Get the data collection time difference, take the average to get the data collection time difference average value ΔsT, calculate the ratio of the actual data collection frequency to the preset collection frequency, and get the data update frequency ratio Fr. Calculate and obtain the data timeliness description parameter sx of the nursing data; Taking into account the deviation parameters, missing ratio and data timeliness descriptive parameters, the nursing data quality evaluation index is obtained; the comprehensive evaluation result is obtained by weighted summation, and the formula The nursing data quality assessment index QI is calculated, where β1, β2, and β3 are the weight coefficients of each item, which are used to adjust the impact of each part on the overall quality assessment; Measures are taken based on the nursing data quality assessment index. If the nursing data quality assessment index is lower than the threshold, an early warning is issued, indicating that the nursing data is abnormal and the data collection module needs to be maintained; otherwise, no measures are taken and the data analysis module is entered.

5. The clinical nursing data analysis system based on big data according to claim 4 is characterized in that: The clinical nursing data analysis system further includes a nursing risk management module, which is used to obtain a nursing risk coefficient and take measures based on the nursing risk coefficient; including: The maximum monitoring resource at time t is recorded as ZJ_max, and the monitoring resource of the qth patient at time t is recorded as JT_q. The nursing resource shortage index ZQ was calculated; By formula The nursing resource shortage index and the nursing data quality assessment index HF were jointly analyzed to obtain the nursing risk coefficient, where α represents the weight of the nursing resource shortage index, and Form (·) is used to convert the content in brackets into a range from 0 to 1; If the nursing risk factor exceeds the threshold, a warning signal will be issued to prompt managers and nursing staff to pay attention and take corresponding risk management measures.

Images