Nursing safety risk assessment planning method and device, and storage medium

Abstract

The invention provides a nursing safety risk assessment planning method and device, and a storage medium. According to the method, a risk assessment item matrix corresponding to each nursing safety risk assessment item is obtained based on mapping of a patient state characteristic value, and then a planning result is obtained based on calculation of the risk assessment item matrix and a corresponding judgment matrix; wherein parameters in the judgment matrix are obtained through training of a machine learning model. According to the nursing safety risk assessment planning method, planning of nursing safety risk assessment items of all time nodes is completed adaptively based on standardized analysis of all state data of a patient, so that nursing personnel are reminded of nursing safety risk assessment needing to be completed in all stages in time, and accidents of wrong assessment and missed assessment are avoided.

Description

Technical Field

[0001] The present invention belongs to the field of medical information technology, and specifically relates to a nursing safety risk assessment planning method, device, and storage medium. Background Art

[0002] In the medical and nursing industry, promoting the construction of nursing informatization with the help of information technology will help promote innovation in nursing service models, improve nursing service efficiency, and ensure patient safety. Through effective nursing risk assessment, the nursing risks that patients may have during their stay in the hospital can be screened out in a timely manner, so that targeted nursing measures can be taken. The corresponding clinical decision support system (CDSS) is an information system based on computer and informatics technology to assist nurses in making nursing decisions; it has been widely used in domestic clinical practice.

[0003] CDSS needs to use the input nursing safety risk assessment data as the basis for decision-making. However, the general CDSS contains a wide variety of nursing safety risk assessment tools, and their respective assessment timing, activation conditions, and frequency are all different. In addition, the operating procedures of the system assessment module itself will also take up a long period of nurses' working time, increasing the workload of nurses. This makes it easy for wrong assessments and missed assessments to occur, indirectly affecting the effectiveness of decision-making.

[0004] Although some existing CDSSs already have the function of reminding patients of pending assessments as a single risk assessment tool, the actual physical examination data of patients during hospitalization changes, and the corresponding nursing risk levels also change. Therefore, how to accurately select the nursing safety risk assessment items that meet the relevant industry standards according to the actual situation of the patients at each time point; in actual operation, especially for young nurses who lack experience, it is still a difficult task. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a nursing safety risk assessment planning method, device, and storage medium to solve the problem of intelligent planning reminders for nursing safety risk assessment projects.

[0006] The present invention achieves the above technical objectives through the following technical means.

[0007] A nursing safety risk assessment planning method comprises the following steps:

[0008] S1, maps the patient status characteristic values ​​to the risk assessment item matrix:

[0009] EW=EV·λ

[0010] Among them, λ is the mapping relationship matrix; EV=[ev1 … evl … ev L ] is the patient status feature matrix, ev l represents the patient's l-th state feature value, l∈[1,L]; EW=[ew1 … ew n …ew N ] is the risk assessment project matrix, ew n Corresponding to the nth nursing safety risk assessment item, n∈[1,N];

[0011] S2, calculate the results of the nursing safety risk assessment project planning:

[0012] EW·X=EF

[0013] Among them, X T =[x1 … x n … x N ] is the judgment matrix; EF is the planning result, which represents the judgment result of whether each nursing safety risk assessment project needs to be implemented.

[0014] Furthermore, the patient status characteristic value ev l , obtained by converting the patient’s actual medical care status data according to the established coding rules.

[0015] Furthermore, the patient status characteristic values ​​include: diagnosis characteristic value ev1, whether general anesthesia surgery characteristic value ev2, pain change characteristic value ev3, body position change characteristic value ev4, diet change characteristic value ev5, fall characteristic value ev6, ​​blood transfusion characteristic value ev7, new catheter insertion characteristic value ev8, new deep cervical vein tube insertion characteristic value ev9, pipeline slipping characteristic value ev1, and so on. 10 , Critical / serious illness notification feature value ev 11 , delirium eigenvalue ev 12 , past medical history characteristic value ev 13 、Allergy history characteristic value ev 14 .

[0016] Furthermore, the mapping relationship matrix λ is artificially formulated to make the mapped element ew n It is possible to characterize all the required patient conditions for the corresponding risk assessment item n.

[0017] Furthermore, ew n In matrix form, after being mapped by the mapping relationship matrix λ, we have:

[0018] ew n =[ew n,1 …ew n,l …ew n,L ]

[0019] in:

[0020]

[0021] Furthermore, the parameter x in the judgment matrix X n Obtained through machine learning.

[0022] Furthermore, the data set used for the machine learning is divided into samples by patient, and each sample contains the state feature values ​​of each time node during the patient's hospitalization and the corresponding medical safety risk assessment execution status; the judgment matrix X is trained as follows:

[0023]

[0024] The subscript m represents the corresponding time node, m∈[1,M].

[0025] A nursing safety risk assessment and planning device, comprising a memory and a processor;

[0026] The memory is used to store computer programs;

[0027] The processor is used to execute the computer program and implement the above-mentioned nursing safety risk assessment planning method when executing the computer program.

[0028] Furthermore, the nursing safety risk assessment device is connected to the nursing document system, hospital information system, inspection information system, surgical anesthesia information management system, and nursing management system via LAN; wherein:

[0029] The nursing safety risk assessment device obtains patient vital sign data through the nursing document system, including data collected by a thermometer, a blood pressure monitor, and a monitor;

[0030] The nursing safety risk assessment device obtains basic data of patients admitted to hospital through the hospital information system, including: patient name, gender, diagnosis, medical history, and allergy history;

[0031] The nursing safety risk assessment device obtains patient test data through a test information system;

[0032] The nursing safety risk assessment device obtains surgical handover data, surgical scheduling data, and anesthesia records through a surgical anesthesia information management system;

[0033] In the nursing safety risk assessment device, the mapping relationship is managed, set or adjusted by the nursing management system.

[0034] A nursing safety risk assessment planning storage medium stores a computer program, which, when executed by a processor, enables the processor to execute the above-mentioned nursing safety risk assessment planning method.

[0035] The beneficial effects of the present invention are:

[0036] (1) The present invention provides a nursing safety risk assessment planning method, device, and storage medium. Based on the standardized analysis of various patient status data, the method can adaptively complete the planning of nursing safety risk assessment projects at each time node, thereby timely reminding nursing staff of the nursing safety risk assessments that need to be completed at each stage, and avoiding the occurrence of misassessment and missed assessment accidents. The present invention can efficiently and accurately grasp the timing of risk assessment according to the actual situation of the patient, realize the full-process dynamic intelligent judgment of high-risk groups, and promote the continuous improvement of nursing quality.

[0037] (2) The present invention uses machine learning technology of the fusion model to provide reliable adaptive risk assessment and early warning nursing auxiliary decision-making, effectively improving the accuracy and efficiency of risk assessment judgment in clinical nursing.

[0038] (3) The nursing safety risk assessment planning device of the present invention can be connected to the hospital's existing information system, so as to automatically obtain data in the hospital's information system, automatically form characteristic values ​​of various parameters, dynamically generate early warning risk assessment scale reminders in real time, actively monitor and push patient adaptive risk assessment lists, integrate prior knowledge of the clinical knowledge base, quickly form clinical nursing records and provide preventive nursing measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is an architecture diagram of the nursing safety risk assessment planning device and existing information systems in the embodiment of the present application. DETAILED DESCRIPTION

[0040] Embodiments of the present invention are described in detail below. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, but should not be construed as limiting the present invention.

[0041] 1. Nursing safety risk assessment planning method

[0042] 1. Summarize patient status information

[0043] Summarize patient medical care status data related to nursing safety risk assessment and convert them into characteristic value form (i.e., patient status characteristic value) based on pre-established coding rules.

[0044] Exemplarily, the patient status characteristic values ​​include (but are not limited to): diagnosis characteristic value ev1, general anesthesia surgery characteristic value ev2, pain change characteristic value ev3, posture change characteristic value ev4, diet change characteristic value ev5, fall characteristic value ev6, ​​blood transfusion characteristic value ev7, new catheter insertion characteristic value ev8, new deep cervical vein tube insertion characteristic value ev9, pipeline slipping characteristic value ev10, 10 , Critical / serious illness notification feature value ev 11 , delirium eigenvalue ev 12 , past medical history characteristic value ev 13 、Allergy history characteristic value ev 14 .

[0045] Exemplarily, the encoding rule of the feature value may be:

[0046]

[0047] The characteristic values ​​of each state of the above patients are summarized into a matrix form: EV = [ev1 … ev l … ev L ], where ev l Represents the l-th state eigenvalue, l∈[1,L].

[0048] 2. Mapping the patient state feature matrix

[0049] (1) According to the nursing safety risk assessment project (risk assessment table, risk assessment tool), a corresponding risk assessment project matrix EW = [ew1 … ew n …ew N ], where ew n Corresponding to the nth nursing safety risk assessment project, n∈[1,N], N is the total number of all nursing safety risk assessment projects to be done.

[0050] Exemplarily, the nursing safety risk assessment items include (but are not limited to): pain assessment form (corresponding to ew1), Braden assessment form (corresponding to ew2), Caprini thrombosis risk factor assessment form (corresponding to ew3), Barthel index rating scale (corresponding to ew4), aspiration / suffocation risk factor assessment form (corresponding to ew5), fall risk factor assessment form (ew6), fall from bed risk factor assessment form (ew7), catheter risk assessment form (corresponding to ew8), GAD-7 generalized anxiety screening scale (corresponding to ew9).

[0051] (2) Map the initially obtained patient status feature matrix EV to the risk assessment item matrix EW:

[0052] EV·λ=EW

[0053] [ev1 …ev l … ev L ]·λ=[ew1 … ew n …ew N ]

[0054] Where λ is the mapping relationship matrix, and its value can be specified manually.

[0055] Exemplary:

[0056] Assume there are 4 status characteristic values ​​and 3 risk assessment items:

[0057] EV=[ev1 ev2 ev3 ev4]

[0058] EW=[ew1 ew2 ew3]

[0059] Considering that the start conditions of the risk assessment project are related to some state characteristic values; therefore, in this example, ew n It is also set in matrix form, with the same number of rows and columns as the patient state feature matrix EV, to reflect all state feature values ​​required for the nth risk assessment item, that is:

[0060] ew n =[ew n,1 …ew n,l …ew n,L ]

[0061]

[0062] For example, when ev1, ev2, and ev4 meet a certain condition, risk assessment project 1 needs to be executed; therefore, ew1 = [ev1ev2 0 ev4]. Based on this, the mapping relationship matrix λ can be set as:

[0063]

[0064] So the mapping result between EV and EW is:

[0065]

[0066] Where ew1=[ev1 ev2 0 ev4],ew2=[ev1 ev2 ev3 0],ew3=[0 0 ev3 ev4]

[0067] Through the above method, the initially entered patient status feature matrix EV is mapped to the risk assessment item matrix EW corresponding to the risk assessment item; thereby achieving preliminary screening of the patient status information required for each risk assessment item.

[0068] In addition to the above exemplary mapping methods, other equivalent mapping methods can also be used to achieve the new element ew after mapping n It is sufficient to characterize all the required patient conditions for the corresponding risk assessment item n.

[0069] 3. Nursing safety risk assessment project planning

[0070] (1) Based on the risk assessment project matrix EW, the nursing safety risk assessment project planning results are calculated according to the following formula:

[0071] EW·X=EF

[0072] Where X is the judgment matrix, X T =[x1 … x n … x N ], EF is the planning result, which is used to characterize the judgment result of whether each nursing safety risk assessment project needs to be implemented.

[0073] (2) Parameter x in the judgment matrix X n It is obtained by machine learning model training. During training, a data set is created according to the medical and nursing status characteristic values ​​of the entire process of hospitalization of patients in the past and the corresponding medical and nursing safety risk assessment execution status; then the data set is brought into the following formula, and the relevant machine learning algorithm is used to optimize the best judgment matrix X:

[0074]

[0075] Among them EW m ew m,n EF m The subscript m in represents the corresponding time node, m∈[1,M]; during the entire hospitalization period of the patient, there are multiple time nodes where the corresponding medical safety risk assessment needs to be completed, including: admission, transfer, return to the operating room, 6 hours after surgery, the fourth day after surgery, position change, diet change, discharge, etc.; for example, EW1 is the medical status feature mapping matrix of the patient at the time of admission, and EF1 is the risk assessment project to be performed at the time of admission.

[0076] (3) After the training is completed, in actual application, based on the input patient actual medical status data EW, the formula EW·X=EF is used to calculate the medical safety risk assessment items that need to be executed at each node of the patient. This can timely remind relevant nursing staff to avoid wrong assessment or missed assessment.

[0077] 2. Nursing safety risk assessment planning device and storage medium

[0078] 1. Based on the same inventive concept as the above-mentioned nursing safety risk assessment planning method, the present application also provides an electronic device, which includes a processor and a memory, in which a computer-readable code is stored, wherein when the computer-readable code is executed by the processor, the nursing safety risk assessment planning method of the present invention is implemented.

[0079] The memory includes a non-volatile storage medium and an internal memory; the non-volatile storage medium can store an operating system and a computer-readable code. The computer-readable code includes program instructions, which, when executed, can enable the processor to execute any linear impedance stabilization network calibration method. The processor is used to provide computing and control capabilities to support the operation of the entire electronic device. The memory provides an environment for the operation of the computer-readable code in the non-volatile storage medium, and when the computer-readable code is executed by the processor, the processor can execute any linear impedance stabilization network calibration method.

[0080] It should be understood that the processor may be a central processing unit, other general-purpose processors, digital signal processors, application-specific integrated circuits, field programmable gate arrays or other programmable logic devices, transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or any conventional processor.

[0081] For example, Figure 1 As shown, the nursing safety risk assessment device is connected to the hospital's existing systems such as ① nursing document system, ② hospital information system, ③ inspection information system, ④ surgical anesthesia information management system, and ⑤ nursing management system through the hospital LAN. Among them:

[0082] The nursing document system records the patient's vital signs data collected by thermometers, blood pressure monitors, monitors and other equipment;

[0083] The hospital information system records basic data such as the patient’s name, gender, diagnosis, medical history, and allergy history upon admission;

[0084] The patient's test data is recorded in the test information system;

[0085] The surgical anesthesia information management system records data such as surgical handover, surgical scheduling, and anesthesia records.

[0086] Nursing staff manages, sets or adjusts the mapping relationship through the nursing management system in accordance with the nursing-related policy document standards of the National Health Commission; then the nursing safety risk assessment device obtains relevant patient medical and nursing status data from the above-mentioned systems through LAN, and then plans the nursing safety risk assessment items that need to be completed by the patient at each time node based on the nursing safety risk assessment planning method of the present invention.

[0087] 2. The present application also provides a readable storage medium, which may be an internal storage unit of the electronic device described in the aforementioned embodiment, such as a hard disk or memory of the computer device. The readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, smart memory card, secure digital card, etc. equipped on the electronic device.

[0088] The present invention is not limited to the above-mentioned embodiments. Any obvious improvement, substitution or deformation that can be made by those skilled in the art without departing from the essential content of the present invention belongs to the protection scope of the present invention.

Claims

1. A nursing safety risk assessment planning method, characterized by: The following steps are involved: S1, maps the patient status characteristic values ​​to the risk assessment item matrix: EW=EV·λ Among them, λ is the mapping relationship matrix; EV=[ev1…ev l …ev L ] is the patient status feature matrix, ev l represents the patient's l-th state feature value, l∈[1,L]; EW=[ew1…ew n …ew N ] is the risk assessment project matrix, ew n Corresponding to the nth nursing safety risk assessment item, n∈[1,N]; S2, calculate the results of the nursing safety risk assessment project planning: EW·X=EF Among them, X T =[x1…x n …x N ] is the judgment matrix; EF is the planning result, which represents the judgment result of whether each nursing safety risk assessment project needs to be implemented.

2. The nursing safety risk assessment planning method according to claim 1 is characterized in that: The patient state characteristic value ev l , obtained by converting the patient’s actual medical care status data according to the established coding rules.

3. The nursing safety risk assessment planning method according to claim 2 is characterized in that: The patient status feature values ​​include: diagnosis feature value ev1, whether general anesthesia surgery feature value ev2, pain change feature value ev3, body position change feature value ev4, diet change feature value ev5, fall feature value ev6, ​​blood transfusion feature value ev7, new catheter placement feature value ev8, new deep cervical vein placement feature value ev9, pipeline slippage feature value ev10, 10 , Critical / serious illness notification characteristic value ev 11 , delirium eigenvalue ev 12 , past medical history characteristic value ev 13 、Allergy history characteristic value ev 14 .

4. The nursing safety risk assessment planning method according to claim 1 is characterized in that: The mapping relationship matrix λ is artificially formulated to make the mapped element ew n It is possible to characterize all the required patient conditions for the corresponding risk assessment item n.

5. The nursing safety risk assessment planning method according to claim 4 is characterized in that: ew n In matrix form, after being mapped by the mapping relationship matrix λ, we have: that one n =[he n,1 …that one n,l …that one n,L ] in:

6. The nursing safety risk assessment planning method according to claim 1 is characterized in that: The parameter x in the judgment matrix X n Obtained through machine learning.

7. The nursing safety risk assessment planning method according to claim 6 is characterized in that: The data set used for the machine learning is divided into samples by patient, and each sample contains the state feature values ​​of each time node during the patient's hospitalization and the corresponding medical safety risk assessment execution status; the judgment matrix X is trained as follows: The subscript m represents the corresponding time node, m∈[1,M].

8. A nursing safety risk assessment and planning device, characterized in that: including memory and processor; The memory is used to store computer programs; The processor is used to execute the computer program and implement the nursing safety risk assessment planning method as described in any one of claims 1 to 7 when executing the computer program.

9. The nursing safety risk assessment planning device according to claim 8, characterized in that: The nursing safety risk assessment device is connected to the nursing document system, hospital information system, inspection information system, surgical anesthesia information management system, and nursing management system via LAN; wherein: The nursing safety risk assessment device obtains patient vital sign data through the nursing document system, including data collected by a thermometer, a blood pressure monitor, and a monitor; The nursing safety risk assessment device obtains basic data of patients admitted to hospital through the hospital information system, including: patient name, gender, diagnosis, medical history, and allergy history; The nursing safety risk assessment device obtains patient test data through a test information system; The nursing safety risk assessment device obtains surgical handover data, surgical scheduling data, and anesthesia records through a surgical anesthesia information management system; In the nursing safety risk assessment device, the mapping relationship is managed, set or adjusted by the nursing management system.

10. A nursing safety risk assessment planning storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a processor, the processor executes the nursing safety risk assessment planning method according to any one of claims 1 to 7.

Images