Nursing risk assessment management equipment based on artificial intelligence

Abstract

The invention relates to the technical field of nursing risk assessment, in particular to nursing risk assessment management equipment based on artificial intelligence, the equipment comprises a data acquisition module, a nursing risk assessment module and an early warning and resource prediction module, the data acquisition module is used for acquiring real-time nursing data, historical nursing data and nursing resource data; the nursing risk assessment module is used for calculating the similarity between the real-time nursing data and the historical nursing data of the patient, presetting a similarity threshold, screening abnormal nursing indexes of the patient, and calculating a nursing risk coefficient in a nursing period of the patient; and the early warning and resource prediction module is used for presetting a nursing risk threshold value, and predicting the nursing resource demand of the next nursing period when the nursing risk coefficient in the nursing period of the patient is smaller than the nursing risk threshold value.

Description

Technical Field

[0001] The present invention relates to the technical field of nursing risk assessment, and in particular to a nursing risk assessment management device based on artificial intelligence. Background Art

[0002] Traditional nursing management systems often rely on manual record-keeping or semi-automated data entry, which results in data collection delays. This prevents them from fully reflecting patients' real-time status and struggles to capture subtle changes during the nursing process. Existing technologies often employ fixed thresholds or simple statistical methods for nursing risk assessment, lacking in-depth analysis of the correlation between historical and real-time patient data. This can lead to inaccurate or delayed risk warnings. Traditional systems often rely on experience to allocate nursing resources, failing to leverage data-driven predictive methods. This can lead to irrational allocation of nursing resources, resulting in both wasted and insufficient resources. Summary of the Invention

[0003] In response to the shortcomings of the existing technology, the present invention proposes a nursing risk assessment and management device based on artificial intelligence. The present invention sets up a special data acquisition module to collect real-time nursing data, historical nursing data and nursing resource data respectively, to ensure the timeliness and integrity of the data, and provide a sufficient basis for subsequent analysis; a similarity calculation unit is used to compare the patient's real-time nursing data with the historical data of recovered patients, which can more accurately capture the abnormalities of the patient's nursing indicators, thereby calculating the nursing risk coefficient and realizing more intelligent risk monitoring and early warning; when the patient's nursing risk coefficient is lower than the preset risk threshold, the system predicts the resource demand of the next nursing cycle in advance through the nursing resource prediction unit, so that resource allocation is more reasonable and helps to optimize the overall nursing process; by introducing artificial intelligence algorithms and data-driven analysis methods, the dependence on manual experience is reduced, which not only improves the accuracy of nursing decisions, but also enables timely intervention measures to be taken before risks occur, thereby improving patient safety and nursing quality.

[0004] To achieve the above object, the technical solution of the present invention is as follows:

[0005] The artificial intelligence-based nursing risk assessment and management device is characterized in that the device includes a data acquisition module, a nursing risk assessment module and an early warning and resource prediction module. The data acquisition module is used to acquire real-time nursing data, historical nursing data and nursing resource data; the nursing risk assessment module is used to calculate the similarity between the patient's real-time nursing data and historical nursing data, and preset a similarity threshold to screen the patient's abnormal nursing indicators, and calculate the nursing risk coefficient within the patient's nursing cycle; the early warning and resource prediction module is used to preset a nursing risk threshold, and when the nursing risk coefficient within the patient's nursing cycle is less than the nursing risk threshold, predict the nursing resource demand for the next nursing cycle.

[0006] A further improvement of the present invention is that the data acquisition module includes a real-time nursing data acquisition unit, a historical nursing data acquisition unit and a nursing resource data acquisition unit, wherein the real-time nursing data acquisition unit is used to acquire nursing operation records within the patient nursing cycle. j and nursing indicator x ij The nursing indicators include heart rate h j , blood pressure b j , body temperature t j , dosage m j The historical nursing data acquisition unit is used to obtain the nursing indicators of recovered patients A during the historical nursing cycle. The nursing resource data acquisition unit is used to obtain the number of nurses n that can be deployed during the nursing cycle. j , available nursing equipment j and pharmaceutical stocks j , where j represents the jth nursing cycle, i represents the i-th nursing indicator, and a represents the a-th recovered patient.

[0007] A further improvement of the present invention is that the nursing risk assessment module includes a similarity calculation unit and a nursing risk coefficient calculation unit. The similarity calculation unit is used to run a similarity calculation strategy to calculate the similarity between the patient's real-time nursing data and the historical nursing data; the nursing risk coefficient calculation unit is used to run a nursing risk coefficient calculation strategy to calculate the nursing risk coefficient within the patient's nursing cycle.

[0008] A further improvement of the present invention is that the early warning and resource prediction module includes an early warning unit and a nursing resource prediction unit. The early warning unit is used to preset a nursing risk threshold and trigger an early warning to the nursing team when the nursing risk coefficient within the patient's nursing cycle is greater than or equal to the nursing risk threshold; the nursing resource prediction unit is used to run the nursing resource prediction strategy and predict the nursing resource requirements for the next nursing cycle when the nursing risk coefficient within the patient's nursing cycle is less than the nursing risk threshold.

[0009] A further improvement of the present invention is that the similarity calculation unit runs a similarity calculation strategy to calculate the similarity between the patient's real-time nursing data and the historical nursing data. The similarity calculation formula is:

[0010]

[0011] Among them, k ij It represents the similarity between the nursing indicator of patient i in the jth nursing cycle and the nursing indicator of recovered patients A in the historical nursing cycle.

[0012] A further improvement of the present invention is that the nursing risk coefficient calculation unit runs a nursing risk coefficient calculation strategy to calculate the nursing risk coefficient within the patient's nursing cycle. The calculation formula of the nursing risk coefficient is:

[0013]

[0014] Among them, H j represents the nursing risk coefficient of the patient's jth nursing cycle, c ij Indicates that the i-th nursing indicator of the patient j-th nursing cycle exceeds the range of the historical nursing cycle of A recovered patients If and only if the similarity between all nursing indicators of the patient j-th nursing cycle and the nursing indicators of A recovered patients in the historical nursing cycle is greater than the similarity threshold, H j =0.

[0015] A further improvement of the present invention is that the nursing resource prediction unit runs a nursing resource prediction strategy to predict the nursing resource demand for the next nursing cycle, and the nursing resource prediction strategy includes the following specific steps:

[0016] S11. Construct a nursing resource prediction model, combine the number of nursing cycles j and the corresponding nursing resource data into the form of a feature vector, use the set of all feature vectors as the input of the nursing resource prediction model, the nursing resource prediction model uses the nursing resource data predicted by each set of feature vectors as output, uses the actual nursing resource data corresponding to each set of feature vectors as the prediction target, and uses minimizing the sum of the prediction accuracies of all predicted nursing resource data as the training target, and stops training when the sum of the prediction accuracies reaches convergence; the nursing resource prediction model is any one of a random forest model, a support vector machine, and a neural network model;

[0017] S12. The calculation formula of the prediction accuracy is: j =(x j -X j ) 2 Where, X j is the nursing resource data predicted by the jth group of feature vectors, x j is the actual nursing resource data of the jth group of feature vectors, p j The prediction accuracy between the nursing resource data predicted by the jth group of feature vectors and the actual nursing resource data.

[0018] The technical effects of the present invention are as follows:

[0019] The present invention sets up a special data acquisition module to collect real-time nursing data, historical nursing data and nursing resource data respectively, to ensure the timeliness and integrity of the data, and provide sufficient basis for subsequent analysis; a similarity calculation unit is used to compare the patient's real-time nursing data with the historical data of recovered patients, which can more accurately capture the abnormal situation of the patient's nursing indicators, thereby calculating the nursing risk coefficient and realizing more intelligent risk monitoring and early warning; when the patient's nursing risk coefficient is lower than the preset risk threshold, the system predicts the resource demand of the next nursing cycle in advance through the nursing resource prediction unit, so that resource allocation is more reasonable and helps to optimize the overall nursing process; by introducing artificial intelligence algorithms and data-driven analysis methods, the dependence on manual experience is reduced, which not only improves the accuracy of nursing decisions, but also enables timely intervention measures to be taken before risks occur, thereby improving patient safety and nursing quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0021] Figure 1 This is a structural diagram of the artificial intelligence-based nursing risk assessment and management device of the present invention. DETAILED DESCRIPTION

[0022] Example 1

[0023] This embodiment proposes an artificial intelligence-based nursing risk assessment and management device, which sets up a special data acquisition module to collect real-time nursing data, historical nursing data and nursing resource data respectively, to ensure the timeliness and integrity of the data, and provide a sufficient basis for subsequent analysis; a similarity calculation unit is used to compare the patient's real-time nursing data with the historical data of recovered patients, which can more accurately capture abnormalities in the patient's nursing indicators, thereby calculating the nursing risk coefficient and realizing more intelligent risk monitoring and early warning; when the patient's nursing risk coefficient is lower than the preset risk threshold, the system predicts the resource demand for the next nursing cycle in advance through the nursing resource prediction unit, making resource allocation more reasonable and helping to optimize the overall nursing process; by introducing artificial intelligence algorithms and data-driven analysis methods, the dependence on manual experience is reduced, which not only improves the accuracy of nursing decisions, but also enables timely intervention measures to be taken before risks occur, thereby improving patient safety and nursing quality.

[0024] like Figure 1As shown, the artificial intelligence-based nursing risk assessment and management device is characterized in that the device includes a data acquisition module, a nursing risk assessment module and an early warning and resource prediction module, the data acquisition module is used to acquire real-time nursing data, historical nursing data and nursing resource data; the nursing risk assessment module is used to calculate the similarity between the patient's real-time nursing data and the historical nursing data, and preset the similarity threshold to screen the patient's abnormal nursing indicators, and calculate the nursing risk coefficient within the patient's nursing cycle; the early warning and resource prediction module is used to preset a nursing risk threshold, and when the nursing risk coefficient within the patient's nursing cycle is less than the nursing risk threshold, predict the nursing resource demand for the next nursing cycle.

[0025] In this embodiment, the data acquisition module includes a real-time nursing data acquisition unit, a historical nursing data acquisition unit and a nursing resource data acquisition unit. The real-time nursing data acquisition unit is used to acquire the nursing operation records within the patient nursing cycle. j and nursing indicator x ij The nursing indicators include heart rate h j , blood pressure b j , body temperature t j , dosage m j The historical nursing data acquisition unit is used to obtain the nursing indicators of recovered patients A during the historical nursing cycle. The nursing resource data acquisition unit is used to obtain the number of nurses n that can be deployed during the nursing cycle. j , available nursing equipment j and pharmaceutical stocks j , where j represents the jth nursing cycle, i represents the i-th nursing indicator, and a represents the a-th recovered patient.

[0026] In this embodiment, the nursing risk assessment module includes a similarity calculation unit and a nursing risk coefficient calculation unit. The similarity calculation unit is used to run the similarity calculation strategy to calculate the similarity between the patient's real-time nursing data and the historical nursing data; the nursing risk coefficient calculation unit is used to run the nursing risk coefficient calculation strategy to calculate the nursing risk coefficient within the patient's nursing cycle.

[0027] In this embodiment, the early warning and resource prediction module includes an early warning unit and a nursing resource prediction unit. The early warning unit is used to preset a nursing risk threshold and trigger an early warning to the nursing team when the nursing risk coefficient within the patient's nursing cycle is greater than or equal to the nursing risk threshold; the nursing resource prediction unit is used to run the nursing resource prediction strategy and predict the nursing resource requirements for the next nursing cycle when the nursing risk coefficient within the patient's nursing cycle is less than the nursing risk threshold.

[0028] In this embodiment, the similarity calculation unit runs a similarity calculation strategy to calculate the similarity between the patient's real-time nursing data and the historical nursing data. The similarity calculation formula is:

[0029]

[0030] Among them, k ij It represents the similarity between the nursing indicator of patient i in the jth nursing cycle and the nursing indicator of recovered patients A in the historical nursing cycle.

[0031] In this embodiment, the nursing risk coefficient calculation unit runs the nursing risk coefficient calculation strategy to calculate the nursing risk coefficient within the patient's nursing cycle. The calculation formula of the nursing risk coefficient is:

[0032]

[0033] Among them, h j represents the nursing risk coefficient of the patient's jth nursing cycle, c ij Indicates that the i-th nursing indicator of the patient j-th nursing cycle exceeds the range of the historical nursing cycle of A recovered patients If and only if the similarity between all nursing indicators of the patient j-th nursing cycle and the nursing indicators of A recovered patients in the historical nursing cycle is greater than the similarity threshold, H j =0.

[0034] In this embodiment, the nursing resource prediction unit runs a nursing resource prediction strategy to predict the nursing resource demand for the next nursing cycle. The nursing resource prediction strategy includes the following specific steps:

[0035] S11. Construct a nursing resource prediction model, combine the number of nursing cycles j and the corresponding nursing resource data into the form of a feature vector, use the set of all feature vectors as the input of the nursing resource prediction model, the nursing resource prediction model uses the nursing resource data predicted by each set of feature vectors as output, uses the actual nursing resource data corresponding to each set of feature vectors as the prediction target, and uses minimizing the sum of the prediction accuracies of all predicted nursing resource data as the training target, and stops training when the sum of the prediction accuracies reaches convergence; the nursing resource prediction model is any one of a random forest model, a support vector machine, and a neural network model;

[0036] S12. The calculation formula of the prediction accuracy is: j =(x j -X j ) 2 Where, X j is the nursing resource data predicted by the jth group of feature vectors, x jis the actual nursing resource data of the jth group of feature vectors, p j The prediction accuracy between the nursing resource data predicted by the jth group of feature vectors and the actual nursing resource data.

[0037] It should be noted here that by setting up a special data acquisition module, real-time nursing data, historical nursing data and nursing resource data are collected respectively to ensure the timeliness and completeness of the data, providing sufficient basis for subsequent analysis; the similarity calculation unit is used to compare the patient's real-time nursing data with the historical data of recovered patients, which can more accurately capture the abnormalities of the patient's nursing indicators, thereby calculating the nursing risk coefficient and realizing more intelligent risk monitoring and early warning; when the patient's nursing risk coefficient is lower than the preset risk threshold, the system predicts the resource demand of the next nursing cycle in advance through the nursing resource prediction unit, making resource allocation more reasonable and helping to optimize the overall nursing process; by introducing artificial intelligence algorithms and data-driven analysis methods, the dependence on manual experience is reduced, which not only improves the accuracy of nursing decisions, but also enables timely intervention measures to be taken before risks occur, thereby improving patient safety and nursing quality.

[0038] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0039] It should be understood that determining B based on A does not mean determining B only based on A. B can also be determined based on A and / or other information.

[0040] The above embodiments can be implemented in whole or in part through software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions according to the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0041] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0042] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0043] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only one type. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not performed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of the device or unit, which can be electrical, mechanical or other forms.

[0044] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0045] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0046] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0047] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to specific embodiments. Obviously, many modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. Nursing risk assessment and management equipment based on artificial intelligence, characterized by: The device includes a data acquisition module, a nursing risk assessment module, and an early warning and resource prediction module. The data acquisition module is used to acquire real-time nursing data, historical nursing data, and nursing resource data; the nursing risk assessment module is used to calculate the similarity between the patient's real-time nursing data and historical nursing data, and preset a similarity threshold to screen the patient's abnormal nursing indicators and calculate the nursing risk coefficient within the patient's nursing cycle; The early warning and resource prediction module is used to preset a nursing risk threshold, and when the nursing risk coefficient within the patient's nursing cycle is less than the nursing risk threshold, predict the nursing resource demand for the next nursing cycle.

2. The artificial intelligence-based nursing risk assessment and management device according to claim 1, characterized in that: The data acquisition module includes a real-time nursing data acquisition unit, a historical nursing data acquisition unit and a nursing resource data acquisition unit. The real-time nursing data acquisition unit is used to acquire nursing operation records within the patient's nursing cycle. j and nursing indicator x ij The nursing indicators include heart rate h j , blood pressure b j , body temperature t j , dosage m j The historical nursing data acquisition unit is used to obtain the nursing indicators of recovered patients A during the historical nursing cycle. The nursing resource data acquisition unit is used to obtain the number of nurses n that can be deployed during the nursing cycle. j , available nursing equipment j and pharmaceutical stocks j , where j represents the jth nursing cycle, i represents the i-th nursing indicator, and a represents the a-th recovered patient.

3. The artificial intelligence-based nursing risk assessment and management device according to claim 2, characterized in that: The nursing risk assessment module includes a similarity calculation unit and a nursing risk coefficient calculation unit. The similarity calculation unit is used to run a similarity calculation strategy to calculate the similarity between the patient's real-time nursing data and historical nursing data; The nursing risk coefficient calculation unit is used to run the nursing risk coefficient calculation strategy to calculate the nursing risk coefficient within the patient's nursing cycle.

4. The artificial intelligence-based nursing risk assessment and management device according to claim 3 is characterized in that: The early warning and resource prediction module includes an early warning unit and a nursing resource prediction unit. The early warning unit is used to preset a nursing risk threshold and trigger an early warning to the nursing team when the nursing risk coefficient within the patient's nursing cycle is greater than or equal to the nursing risk threshold; The nursing resource prediction unit is used to run the nursing resource prediction strategy to predict the nursing resource demand for the next nursing cycle when the nursing risk coefficient within the patient's nursing cycle is less than the nursing risk threshold.

5. The artificial intelligence-based nursing risk assessment and management device according to claim 4 is characterized in that: The similarity calculation unit runs a similarity calculation strategy to calculate the similarity between the patient's real-time nursing data and the historical nursing data. The similarity calculation formula is: Among them, k ij It represents the similarity between the nursing indicator of patient i in the jth nursing cycle and the nursing indicator of recovered patients A in the historical nursing cycle.

6. The artificial intelligence-based nursing risk assessment and management device according to claim 5 is characterized in that: The nursing risk coefficient calculation unit runs the nursing risk coefficient calculation strategy to calculate the nursing risk coefficient within the patient's nursing cycle. The calculation formula of the nursing risk coefficient is: Among them, H j represents the nursing risk coefficient of the patient's jth nursing cycle, c ij Indicates that the i-th nursing indicator of the patient j-th nursing cycle exceeds the range of the historical nursing cycle of A recovered patients If and only if the similarity between all nursing indicators of the patient j-th nursing cycle and the nursing indicators of A recovered patients in the historical nursing cycle is greater than the similarity threshold, H j =0.

7. The artificial intelligence-based nursing risk assessment and management device according to claim 6, characterized in that: The nursing resource prediction unit runs a nursing resource prediction strategy to predict the nursing resource demand for the next nursing cycle. The nursing resource prediction strategy includes the following specific steps: S11. Construct a nursing resource prediction model, combine the number of nursing cycles j and the corresponding nursing resource data into the form of a feature vector, use the set of all feature vectors as the input of the nursing resource prediction model, the nursing resource prediction model uses the nursing resource data predicted by each set of feature vectors as output, uses the actual nursing resource data corresponding to each set of feature vectors as the prediction target, and uses minimizing the sum of the prediction accuracies of all predicted nursing resource data as the training target, and stops training when the sum of the prediction accuracies reaches convergence; the nursing resource prediction model is any one of a random forest model, a support vector machine, and a neural network model; S12. The calculation formula of the prediction accuracy is: j =(x j -X j ) 2 Where, X j is the nursing resource data predicted by the jth group of feature vectors, x j is the actual nursing resource data of the jth group of feature vectors, p j The prediction accuracy between the nursing resource data predicted by the jth group of feature vectors and the actual nursing resource data.

Images