PESRDGI model-based nursing data processing method, storage medium and electronic equipment

Abstract

The invention provides a PESRDGI model-based nursing data processing method, a storage medium and electronic equipment. The PESRDGI model-based nursing data processing method comprises the following steps of: obtaining clinical evaluation data of a plurality of types of patients; on the basis of the clinical assessment data of the multiple categories of patients, matching corresponding various categories of clinical assessment data from a preset nursing evidence-based knowledge base; obtaining guide causes, symptom features and weight coefficients of related factors corresponding to nursing diagnosis in the clinical evaluation data under each category; generating nursing diagnosis based on a PESRDGI model in the nursing evidence-based knowledge base; generating existing nursing diagnosis in response to the condition that the sum of weight coefficients of symptom features corresponding to the nursing diagnosis in the clinical evaluation data under each category is greater than 1 and the guide causes exist; and generating a risk nursing diagnosis in response to the condition that the sum of the weight coefficients of the related factors corresponding to the nursing diagnosis in the clinical evaluation data under each category is greater than 1. The efficiency and accuracy of nursing evaluation and diagnosis can be effectively improved.

Description

Technical Field

[0001] The present application belongs to the field of medical management technology, and in particular to the field of medical care data processing technology. Background Art

[0002] In the modern healthcare environment, nursing assessment and nursing diagnosis are two crucial links in the nursing process, which are essential for developing effective nursing plans, improving nursing quality and patient safety. However, clinical nurses face multiple challenges and obstacles when performing these tasks.

[0003] Challenges of nursing assessment include: 1) Diversity of assessment content: Nursing assessment needs to cover the patient's physical, psychological, social and spiritual health. This diversity requires nurses to have extensive knowledge and keen insight to fully understand the patient's health status. Each patient's situation is unique, including cultural background, personal preferences and lifestyle, which need to be fully considered in nursing assessment. 2) Timeliness of assessment information: The patient's condition may change rapidly, and nurses need to be able to update their assessment in real time to reflect these changes. Therefore, all information generated in the clinical process, such as test reports, medical prescriptions, and various types of vital sign monitoring data, must be fed back to the nurse's assessment content in the shortest time. 3) Completeness of nursing assessment: A complete nursing assessment should include all necessary health information to avoid missing key data. The lack of information may lead to inaccurate diagnosis and affect the treatment effect. In particular, nurses often face challenges such as time pressure and heavy workload, as well as obstacles such as the diversity of clinical information, resulting in insufficient integrity of patient assessment and affecting the correctness of patient nursing diagnosis and comprehensive understanding of patients.

[0004] The challenges of nursing diagnosis include: 1) Interference and overlap of assessment content with diagnosis: When making nursing diagnoses, multiple problems of patients may interfere with each other. For example, the assessment of psychological state may affect the manifestation of physiological symptoms, and vice versa. In addition, some symptoms may belong to multiple different nursing diagnoses. This overlap brings additional complexity to accurate diagnosis. 2) Complexity of assessment conditions: Determining which symptoms are associated with specific nursing diagnoses requires a high degree of expertise and experience. Nurses need to assess the relevance and importance of patient symptoms, and this process is often affected by subjective judgment. The accuracy of nursing diagnosis directly affects the effectiveness of the care plan. Inaccurate diagnosis is more likely to lead to inappropriate nursing plan measures and affect the overall medical treatment and care outcomes.

[0005] It can be seen that in the existing technology, most of the obstacles for nurses in nursing assessment content are the dynamics of patient information and the diversity of sources, which leads to incomplete and untimely acquisition of assessment content. Moreover, when conducting nursing diagnosis clinically, the assessment items between various nursing diagnoses are interfering and overlapping. Summary of the invention

[0006] The present application provides a nursing data processing method, storage medium and electronic device based on the PESRDGI model, which are used to improve the efficiency and accuracy of nursing assessment and diagnosis.

[0007] In a first aspect, an embodiment of the present application provides a nursing data processing method based on the PESRDGI model, comprising: obtaining clinical assessment data of patients in multiple categories; matching corresponding clinical assessment data of each category from a preset nursing evidence-based knowledge base based on the clinical assessment data of the patients in multiple categories; obtaining the causes, symptom characteristics and weight coefficients of related factors corresponding to the nursing diagnosis in the clinical assessment data under each category; generating a nursing diagnosis based on the PESRDGI model in the nursing evidence-based knowledge base: in response to the fact that the sum of the weight coefficients of the symptom characteristics corresponding to the nursing diagnosis in the clinical assessment data under each category is greater than 1 and the cause exists, generating an existing nursing diagnosis; in response to the fact that the sum of the weight coefficients of the related factors corresponding to the nursing diagnosis in the clinical assessment data under each category is greater than 1, generating a risk nursing diagnosis.

[0008] In an implementation of the first aspect, it also includes: constructing the nursing evidence-based knowledge base: collecting patient medical data from multiple data sources, and obtaining patient clinical assessment data based on the patient medical data and the CCC classification standard code corresponding to the patient medical data; storing the patient clinical assessment data based on the data association and mutually exclusive logical attributes between each of the patient clinical assessment data to form a nursing evidence-based knowledge base; adjusting each of the weight coefficients based on nursing evidence-based feedback data and / or the Delphi method to update the nursing evidence-based knowledge base.

[0009] In an implementation of the first aspect, it also includes: establishing a PESRDGI model for each nursing diagnosis based on the nursing evidence-based knowledge base, the nursing diagnosis includes an existing nursing diagnosis and a risk nursing diagnosis, and the establishment of the PESRDGI model includes: classifying the clinical assessment data based on the assessment content, dividing the clinical assessment data under each category into causes, symptom characteristics and related factors of the nursing diagnosis, and configuring weight coefficients and numbers for the causes, the symptom characteristics and the related factors respectively; establishing a processing logic relationship between each of the nursing diagnoses and the weight coefficients of the causes, the symptom characteristics and the related factors to form the PESRDGI model.

[0010] In an implementation of the first aspect, the processing logic relationship between the nursing diagnosis and the causes, the symptom characteristics and the weight coefficients of the related factors includes: the initial sum of the weight coefficients of the causes, the symptom characteristics and the related factors of each nursing diagnosis is 1, and each weight coefficient is adjusted and updated according to nursing evidence-based feedback data and / or the Delphi method.

[0011] In an implementation of the first aspect, the processing logic relationship between the nursing diagnosis and the weight coefficients of the causes, the symptom characteristics and the related factors also includes: when the sum of the weight coefficients of the symptom characteristics of the nursing diagnosis is greater than 1 and the causes exist, an existing nursing diagnosis is generated; when the sum of the weight coefficients of the related factors of the nursing diagnosis is greater than 1, a risk nursing diagnosis is generated; when the nursing diagnosis contains a sub-diagnosis and satisfies the diagnosis generation condition at the same time, a nursing diagnosis of the sub-diagnosis is generated; when the existing nursing diagnosis and the risk nursing diagnosis satisfy the diagnosis generation condition at the same time, the existing nursing diagnosis is generated; when a diagnosis restriction condition is received, the generated nursing diagnosis is filtered based on the diagnosis restriction condition.

[0012] In an implementation of the first aspect, it also includes: obtaining the evaluation results of each of the nursing diagnoses; calculating the sensitivity and specificity of the nursing diagnosis based on the evaluation results; and adjusting the causes of the nursing diagnosis, the symptom characteristics, and the weight coefficients of the related factors based on the sensitivity and specificity of the nursing diagnosis.

[0013] In an implementation of the first aspect, it also includes: in response to receiving a nursing plan request, generating a nursing plan including bundled nursing measures based on the logical mapping relationship between the nursing diagnosis, the cause, the symptom characteristics, the related factors and the nursing plan in the PESRDGI model; wherein a logical mapping relationship between each of the nursing diagnosis, the cause, the symptom characteristics, the related factors and at least one nursing plan is established in advance, and the PESRDGI model is updated based on the logical mapping relationship.

[0014] In an implementation of the first aspect, it also includes: in response to receiving a nursing execution request, based on the logical mapping relationship between the nursing diagnosis, the cause, the symptom characteristics, the related factors and the nursing execution in the PESRDGI model, a nursing execution interface containing bundled nursing measures is generated, and based on the corresponding mapping relationship between the monitoring data or execution abnormality data and the nursing measures, corresponding nursing measures are generated; wherein, the logical mapping relationship between each of the nursing diagnosis, the cause, the symptom characteristics, the related factors and the nursing measures and the logical mapping relationship between the monitoring data or execution abnormality data and the nursing measures are established in advance, and the PESRDGI model is updated based on the logical mapping relationship.

[0015] In a second aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the nursing data processing method based on the PESRDGI model as described in any one of the first aspects of the present application.

[0016] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a memory storing a computer program; a processor communicatively connected to the memory, and executing the nursing data processing method based on the PESRDGI model described in any one of the first aspect of the present application when calling the computer program.

[0017] The nursing data processing method, storage medium and electronic device based on the PESRDGI model provided in the embodiments of the present application have the following beneficial effects:

[0018] This application can ensure that during the clinical care process, the patient's latest comprehensive, complete, and effective overall clinical assessment data content is effectively obtained, and the weight of each nursing diagnosis is independently calculated to accurately diagnose nursing problems. Therefore, this application can effectively improve the efficiency and accuracy of nursing assessment and diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 Shown is a flowchart of a nursing data processing method based on the PESRDGI model according to an embodiment of the present application.

[0020] Figure 2 Shown is a flowchart of constructing a nursing evidence-based knowledge base in a nursing data processing method based on the PESRDGI model in one embodiment of the present application.

[0021] Figure 3 Shown is a principle architecture diagram of constructing a nursing evidence-based knowledge base in a nursing data processing method based on the PESRDGI model in an embodiment of the present application.

[0022] Figure 4Shown is a flowchart of constructing a PESRDGI model in a nursing data processing method based on the PESRDGI model according to an embodiment of the present application.

[0023] Figure 5 Shown is an implementation diagram of establishing PESRDGI in a nursing data processing method based on the PESRDGI model in one embodiment of the present application.

[0024] Figure 6 Shown is an example diagram of an existing nursing diagnosis model in a nursing data processing method based on the PESRDGI model according to an embodiment of the present application.

[0025] Figure 7 Shown is an example diagram of a risk nursing diagnosis model in a nursing data processing method based on the PESRDGI model according to an embodiment of the present application.

[0026] Figure 8 Shown is a flowchart of a method for adjusting weight coefficients in a nursing data processing method based on the PESRDGI model according to an embodiment of the present application.

[0027] Fig. 9 Shown is a schematic diagram of the implementation principle of a nursing data processing method based on the PESRDGI model according to an embodiment of the present application.

[0028] Fig.10 Shown is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0029] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0030] From assessment to diagnosis, nurses must synthesize and analyze all relevant information to form an accurate nursing diagnosis. This requires: Clinical judgment ability: Accurate nursing diagnosis depends on the nurse's clinical judgment, which is a comprehensive reflection of experience, knowledge and practice. Information integration ability: The amount of information obtained from the assessment may be very large. Nurses need to effectively integrate this information and extract data that is critical to nursing diagnosis. In the application of clinical nursing diagnosis, the existing PES theory cannot be directly used as an application of nursing diagnosis informationization.

[0031] The embodiments of the present application provide a nursing data processing method, storage medium and electronic device based on the PESRDGI model, which are used to improve the efficiency and accuracy of nursing assessment and diagnosis.

[0032] The following will be combined with the attached examples of the present application Figure 1 To Attachment Fig.10 , the technical scheme in the embodiment of the present application is described in detail, so that those skilled in the art can understand and implement the nursing data processing method, storage medium and electronic device based on the PESRDGI model of the present embodiment without creative labor.

[0033] Figure 1 The flowchart of the nursing data processing method based on the PESRDGI model in the embodiment of the present application is shown. Figure 1 As shown, the nursing data processing method based on the PESRDGI model provided in the embodiment of the present application includes the following steps S110 to S140.

[0034] Step S110, obtaining clinical assessment data of multiple categories of patients;

[0035] Step S120, matching corresponding clinical assessment data of each category from a preset nursing evidence-based knowledge base based on the clinical assessment data of the patient in multiple categories;

[0036] Step S130, obtaining the causes, symptom characteristics and weight coefficients of related factors corresponding to the nursing diagnosis in the clinical assessment data under each category;

[0037] Step S140, generating nursing diagnosis based on the PESRDGI model in the nursing evidence-based knowledge base:

[0038] Step S141, in response to the sum of weight coefficients of the symptom characteristics corresponding to the nursing diagnosis in the clinical assessment data under each category being greater than 1 and the cause existing, generating an existing nursing diagnosis;

[0039] Step S142: in response to the sum of the weight coefficients of the relevant factors corresponding to the nursing diagnosis in the clinical assessment data under each category being greater than 1, generating a risk nursing diagnosis.

[0040] The above steps S110 to S140 of the nursing data processing method based on the PESRDGI model in this embodiment are described in detail below.

[0041] Step S110, obtaining clinical assessment data of multiple categories of patients.

[0042] Patient clinical assessment data include test report evaluation data generated by evaluating test report data, physician order execution and medication evaluation data generated by evaluating physician order execution and medication data, physical examination and sign evaluation data generated by evaluating physical examination and sign data, bedside instrument monitoring evaluation data generated by evaluating bedside instrument monitoring data, and nursing assessment data generated by evaluating nurses' clinical nursing work system data.

[0043] Step S120, matching corresponding clinical assessment data of each category from a preset nursing evidence-based knowledge base based on the patient clinical assessment data of multiple categories.

[0044] In one implementation of this embodiment, it also includes: constructing the nursing evidence-based knowledge base, Figure 2 The flowchart of constructing a nursing evidence-based knowledge base in a nursing data processing method based on the PESRDGI model according to an embodiment of the present application is shown as follows: Figure 2 As shown, constructing the nursing evidence-based knowledge base includes the following steps S201 to S203.

[0045] Step S201 : collecting patient medical data from multiple data sources, and acquiring patient clinical assessment data based on the patient medical data and the CCC classification standard code corresponding to the patient medical data.

[0046] In the existing technology, most of the nursing assessment content is hindered by the dynamics of patient information and the diversity of sources, resulting in incomplete and untimely acquisition of assessment content.

[0047] In this embodiment, patient medical data is dynamically collected from multiple data sources, including but not limited to hospital test report systems, doctor's order and medication execution systems, nurses' physical examination and evaluation operating systems for patients, bedside monitoring instruments and equipment, clinical nursing work systems, etc., to dynamically, timely and comprehensively collect patient clinical information. Specifically, in this embodiment, the patient medical data includes: test report data, doctor's order and medication execution data, physical examination and physical sign assessment data, bedside instrument monitoring data, and nurse clinical nursing work system data. The specific process of obtaining patient clinical assessment data based on patient medical data and the CCC classification standard code corresponding to the patient medical data is as follows:

[0048] a) Test report data: After collecting the patient's test report data, import the CCC classification standard code, obtain the normal value range of the standard code data, identify whether the test report result is positive, and if positive, assign the CCC classification standard code positive evaluation item to generate the test report evaluation data.

[0049] b) Doctor’s order execution and medication data: Collect the data collected by nurses by scanning the code with PDA or mobile device to obtain the patient’s recent medication data. Import the CCC classification standard code to obtain the CCC classification standard code of drug categories, such as antihypertensive drugs, analgesics, sleep aids, anticoagulants, etc., and generate doctor’s order execution and medication evaluation data.

[0050] c) Physical examination and sign data: Use the clinical care assessment template and CCC classification as a specialist assessment template, such as life history, past medical history, cardiovascular system, respiratory system, nervous system, genitourinary system, blood system, psychology, etc. After the assessment, the CCC classification standard coding positive assessment items are directly generated to generate physical examination and sign assessment data.

[0051] d) Bedside instrument monitoring data: After collecting the patient's bedside instrument monitoring data, import the CCC classification standard code, obtain the normal value range of the standard code data, and identify whether the clinical instrument monitoring data is positive. If positive, assign the CCC classification standard code positive evaluation item to generate bedside instrument monitoring evaluation data.

[0052] e) Nurses' clinical nursing work system data: During clinical nursing, nurses obtain relevant information data such as the patient's latest external equipment during nursing operations such as catheter placement and removal, oxygen therapy, etc., import CCC classification standard codes, obtain catheter types or oxygen therapy methods, and detailed CCC classification standard codes for ventilators, and assign CCC classification standard coded equipment use codes to generate nursing assessment data.

[0053] Step S202: storing the patient clinical assessment data based on the data association and mutually exclusive logical attributes between the patient clinical assessment data to form a nursing evidence-based knowledge base.

[0054] The clinical evaluation data of each patient formed by different data sources are correlated with each other. These evaluation details are interdependent with clinical positive signs, such as cataracts associated with visual impairment, hearing loss associated with hearing impairment, etc. This embodiment can ensure that the positive signs of the patient can be more completely understood during the evaluation process through the data correlation between the clinical evaluation data of each patient.

[0055] On the contrary, some newly added assessment items in the patient's clinical assessment data have mutually exclusive associations with the original assessments, such as catheter removal, which is mutually exclusive with the assessment item of the original catheter placement mark. If the clinical nursing operation removes the catheter, this embodiment automatically removes the catheter placement mark on the patient through the mutually exclusive association logic of each patient's clinical assessment data.

[0056] Figure 3 The schematic diagram of the principle structure of constructing a nursing evidence-based knowledge base in the nursing data processing method based on the PESRDGI model in one embodiment of the present application is shown. Figure 3 As shown, this embodiment establishes a patient evaluation summary database (CDR) based on the evaluation data obtained from multiple data sources to maintain the latest clinical information data of the patient. The CCC classification standard coding content automatically generated through dynamic data collection is continuously updated to update the patient's clinical information data and ensure that the content has mutual logical consistency. In addition, the data content of the clinical information data that has exceeded the validity period is automatically cleared. For example, clinical vital signs data such as body temperature, pulse rate, and respiratory rate are only retained for 24 hours, and expired data will be automatically cleared to ensure that the patient's clinical data information database contains valid information content.

[0057] This embodiment can ensure that nurses obtain the latest comprehensive, complete, and effective overall clinical assessment data content of patients during the clinical care process, so as to use the clinical assessment data to make subsequent nursing diagnoses for patients.

[0058] Step S203, adjusting each of the weight coefficients based on nursing evidence-based feedback data and / or the Delphi method to update the nursing evidence-based knowledge base.

[0059] This embodiment uses the constructed nursing evidence-based knowledge base to complete the active guidance of the full intelligent process of the nursing procedure. This embodiment is based on the 176 nursing diagnoses of the CCC clinical care classification system to establish the PESRDGI model. That is, starting with P as the core, collect, integrate and update the latest medical and nursing research results, clinical trial results and scientific evidence in the field of health care. These evidences include diagnostic methods, treatment methods, preventive measures and nursing methods for diseases. These data sources may include medical journals, research databases, clinical trial results, guidelines and recommendations of professional organizations. E (cause), S (defining characteristics), R (risk factor), I (intervention measures), etc. are evidence-based and sorted one by one to form the nursing evidence-based knowledge base.

[0060] Step S130, obtaining the causes, symptom characteristics and weight coefficients of related factors corresponding to the nursing diagnosis in the clinical assessment data under each category.

[0061] In one implementation of this embodiment, it also includes: establishing a PESRDGI model for each nursing diagnosis based on the nursing evidence-based knowledge base, Figure 4 The flowchart of constructing the PESRDGI model in the nursing data processing method based on the PESRDGI model according to one embodiment of the present application is shown as follows: Figure 4 As shown, the establishment of the PESRDGI model includes the following steps S204 to S205.

[0062] Step S204, classifying the clinical assessment data based on the assessment content, dividing the clinical assessment data under each category into causes, symptom characteristics and related factors of nursing diagnosis, and configuring weight coefficients and numbers for the causes, symptom characteristics and related factors respectively.

[0063] In clinical practice, various signs of patients will be obtained through assessment. The assessment content will be classified first, and the assessment will be coded according to the assessment system (life history, past medical history, cardiovascular system, respiratory system, digestive system, nervous system, genitourinary system and psychological system, etc.). The above assessment results, combined with the results of nursing evidence, will be divided into 'E-cause', 'S-defining characteristics' and 'R-related factors', and specifically numbered.

[0064] When calculating the logic of each nursing diagnosis content, there must be a weight relationship for the impact of each definitional characteristic and causal or related factor content. For example, through clinical experts and evidence-based results, each definitional characteristic and causal or related factor corresponding to each nursing diagnosis is assigned a weight value of 0.1-0.9, which can then be followed by three rounds of dialectics using the Delphi method.

[0065] In current nursing diagnosis, the evaluation result content cannot be directly used as a diagnosis source for the information system. In this embodiment, weight coefficients are respectively configured for the cause, the symptom characteristics, and the related factors, and a processing logic relationship is established between each nursing diagnosis and each weight coefficient of the cause, the symptom characteristics, and the related factors.

[0066] Step S205, establishing a processing logic relationship between each nursing diagnosis and each weight coefficient of the cause, the symptom characteristics and the related factors to form the PESRDGI model.

[0067] Figure 5 Shown is an implementation diagram of establishing PESRDGI in a nursing data processing method based on the PESRDGI model in one embodiment of the present application. When converting assessment data into nursing diagnoses, nurses need to identify the main issues affecting the patient's health status based on the collected information. This process faces the following obstacles: The correlation between defining characteristics (S) and causes (E): Nursing diagnoses usually require nurses to accurately understand and apply defining characteristics (symptoms) and causes (causes). For example, a patient's insomnia (S) may be related to anxiety (E), but the nurse needs to determine whether this association is conclusive and whether there are other potential factors. Integration of positive signs and past medical history: Nurses need to consider the patient's positive signs in combination with past medical history, which requires nurses to have not only clinical knowledge, but also the ability to perform clinical reasoning. In this embodiment, in order to solve this problem, such as Figure 5As shown in the figure, based on the 176 nursing diagnoses of the CCC clinical nursing care classification system (CCCs) as the basis of nursing problems (P), the PESRDGI nursing diagnosis model was established with P as the core, and the clinical information of patients collected during nursing assessment and clinical care as the content of the cause (E), defining characteristics (S) and related factors (R). Then, the PESR model of each nursing problem was improved through the nursing evidence-based method and used as a nursing diagnosis.

[0068] Among them, the nursing diagnosis includes existing nursing diagnosis and risk nursing diagnosis. In the existing clinical medical diagnosis theory PES, the defining characteristics and causes of clinical medical diagnosis are mainly used as the basis for medical diagnosis to clarify the substantial impact of these clinical signs and causes on these diagnoses and the observed content. However, in the nursing clinical care process, in the nursing problems based on nursing diagnosis, it is necessary to care for all the health problems of the patient's body, mind and spirit, and this embodiment includes the diagnosis of existing nursing problems (already occurred) and risk nursing problems (not occurred) in the nursing diagnosis. Figure 6 The example diagram of the existing nursing diagnosis model in the nursing data processing method based on the PESRDGI model according to one embodiment of the present application is shown, specifically, the F62.0 electrolyte imbalance existing nursing diagnosis model, Figure 7 Shown is an example diagram of a risk nursing diagnosis model in a nursing data processing method based on the PESRDGI model according to an embodiment of the present application, specifically, an existing nursing diagnosis model for fall risk of N33.6.

[0069] Among them, in one implementation of this embodiment, the processing logical relationship between the nursing diagnosis and the causes, the symptom characteristics and the weight coefficients of the related factors includes: the initial sum of the weight coefficients of the causes, the symptom characteristics and the related factors of each nursing diagnosis is 1, and each weight coefficient is adjusted and updated according to the nursing evidence-based feedback data and / or the Delphi method.

[0070] When calculating the logic of each nursing diagnosis content, each definitional feature and cause or related factor content has its own weight relationship of influence. When calculating each initial weight value, the average basic score is taken when the sum of E, S, and R is 1. Then, the nursing evidence-based feedback data formed by clinical experts and evidence-based results are used to adjust the score of each definitional feature and cause or related factor corresponding to each nursing diagnosis for the degree of relevance to the nursing problem. If the relevance is an absolute factor, the weight value is directly 1. In addition, the weight coefficients mentioned above can also be adjusted and updated through the Delphi method.

[0071] In an implementation of this embodiment, the processing logic relationship between the nursing diagnosis and the cause, the symptom characteristics and the weight coefficients of the related factors also includes:

[0072] 1) The sum of the weight coefficients of the symptom characteristics of the nursing diagnosis is greater than 1 and the cause exists, generating an existing nursing diagnosis. The presence of an existing nursing diagnosis = the sum of the evaluation items of the defining characteristics (S) is greater than or equal to 1 + the evaluation items with scores for the relevant factors (E), which means the necessity of the cause in the nursing diagnosis theory. Therefore, when calculating the values ​​of the cause and the relevant factors, it will be calculated separately whether it meets the push recommendation diagnosis criteria.

[0073] 2) The sum of the weight coefficients of the relevant factors of the nursing diagnosis is greater than 1, and a risk nursing diagnosis is generated. The emergence of risk nursing diagnosis: When the sum of the weight scores of each evaluation item is greater than 1, diagnosis D is recommended.

[0074] 3) When the nursing diagnosis contains a sub-diagnosis and meets the diagnosis generation conditions at the same time, a nursing diagnosis of the sub-diagnosis is generated. In the CCC diagnostic classification, there is an architectural hierarchy relationship between the main diagnosis classification and the sub-diagnosis (detailed diagnosis) classification. The main diagnosis will include the relevant main causes, defining characteristics and risk factors of each sub-diagnosis. In this embodiment, when the main diagnosis and sub-diagnosis appear at the same time, only the more accurate sub-diagnosis is generated. For example, when the push diagnosis conditions meet N33.0 injury risk and N33.6 fall risk at the same time, the diagnosis is pushed with the detail N33.6 fall risk.

[0075] 4) When the existing nursing diagnosis and the risk nursing diagnosis meet the diagnosis generation conditions at the same time, the existing nursing diagnosis is generated. In terms of the priority of solving nursing problems, urgent and life-threatening problems must be solved first. Therefore, in this embodiment, when existing nursing diagnoses and potential risk nursing diagnoses appear at the same time, only the existing nursing diagnosis is generated. For example, when the two nursing diagnoses F15.1 fluid deficiency and F15.2 fluid deficiency risk appear at the same time, F15.1 fluid deficiency is pushed as the nursing diagnosis, and F15.2 fluid deficiency risk nursing diagnosis is no longer pushed separately, so as to reduce the generation of false positive nursing diagnosis push caused by unnecessary diagnosis.

[0076] 5) When receiving the diagnosis restriction condition, the generated nursing diagnosis is filtered based on the diagnosis restriction condition. When there are restriction conditions such as gender and age, only the nursing diagnosis within the restriction range is generated.

[0077] Figure 8 The flowchart of a method for adjusting the weight coefficient in the nursing data processing method based on the PESRDGI model according to an embodiment of the present application is shown. Figure 8As shown, in one implementation of this embodiment, it also includes:

[0078] Step S151, obtaining the evaluation results of each nursing diagnosis;

[0079] Step S152, calculating the sensitivity and specificity of the nursing diagnosis based on the evaluation results;

[0080] Step S153, adjusting the weight coefficients of the cause, the symptom characteristics and the related factors of the nursing diagnosis based on the sensitivity and specificity of the nursing diagnosis.

[0081] In this embodiment, the evaluation results of each nursing diagnosis are generated based on the feedback determined by the nursing expert combining the original evaluation content with the actual clinical nursing diagnosis, and the evaluation results include:

[0082] 1) True positive: The generated nursing diagnosis is consistent with the expert diagnosis

[0083] 2) True negative: No nursing diagnosis was generated and the expert also believed it was not a diagnosis

[0084] 3) False positive: A nursing diagnosis is generated but the expert also considers it to be non-diagnosis

[0085] 4) False negative: No nursing diagnosis was generated but the expert believes it should be listed as a diagnosis

[0086] Sensitivity refers to the ability to correctly identify a positive diagnosis, that is, the proportion of all diagnoses actually evaluated that the system can correctly diagnose as positive. The calculation formula for sensitivity is as follows:

[0087] Sensitivity = True Positive / (True Positive + False Negative)

[0088] In multiple assessments, if a feature or cause is frequently identified as being associated with a certain diagnosis (the correlation reaches the association threshold), then its sensitivity is relatively high, and therefore it is used as the basis for adjusting the weight coefficient. The higher the sensitivity, the correspondingly increased weight coefficient. Therefore, the sensitivity of the assessment content can be determined by statistically analyzing the correct recognition rate of different assessment tools or standards, and accordingly adjusting the weight coefficient of the content in the diagnosis to enhance the sensitivity of the diagnosis.

[0089] Specificity is the ability to correctly identify true negative cases, that is, the proportion of cases that the system can correctly diagnose as negative in all cases that do not actually require a nursing diagnosis. The specificity calculation formula is as follows:

[0090] Specificity = True Negative / (True Negative + False Positive)

[0091] By analyzing the inappropriateness and low relevance of the evaluation content to the diagnosis by experts, the specificity of the evaluation content can be reduced, thereby improving the accuracy of the diagnosis, and adjusting the weight coefficient to ensure that the evaluation content with high specificity can be improved in the diagnosis. The higher the specificity, the smaller the weight coefficient.

[0092] When adjusting the weight coefficient by combining sensitivity and specificity, if the sensitivity of a certain evaluation feature is high and the specificity is moderate, its weight coefficient can be appropriately increased to increase the influence of the feature in the final diagnosis. For features with low specificity, their weight coefficient can be reduced to avoid affecting the diagnosis results under irrelevant circumstances. Through multiple evaluation and diagnosis operations and feedback from experts, the weight coefficients of each evaluation in the definitional features and related factors are continuously adjusted to gradually optimize the sensitivity and specificity of the diagnosis.

[0093] The clinical nursing experts evaluate the correctness of the diagnosis and calculate the sensitivity and specificity based on the actual clinical situation. After adjusting the weight relationship of each defining feature and the content of the cause or related factors, the sensitivity and specificity are adjusted to the threshold, for example, the sensitivity and specificity are adjusted to more than 98%.

[0094] Step S140, generating nursing diagnosis based on the PESRDGI model in the nursing evidence-based knowledge base.

[0095] Specifically, generating nursing diagnosis based on the PESRDGI model in the nursing evidence-based knowledge base includes step S141 and step S142.

[0096] Step S141, in response to the sum of weight coefficients of the symptom characteristics corresponding to the nursing diagnosis in the clinical assessment data under each category being greater than 1 and the cause existing, generating an existing nursing diagnosis;

[0097] Step S142: in response to the sum of the weight coefficients of the relevant factors corresponding to the nursing diagnosis in the clinical assessment data under each category being greater than 1, generating a risk nursing diagnosis.

[0098] For example, the sum of weight coefficients of the symptom features of an existing nursing diagnosis (such as F62.0 Electrolyte Imbalance) is calculated as follows:

[0099]

[0100] The sum of weight coefficients of the relevant factors of risk nursing diagnosis (such as N33.6 Fall risk):

[0101]

[0102] In one implementation of this embodiment, it also includes: in response to receiving a nursing plan request, generating a nursing plan including bundled nursing measures based on the logical mapping relationship between the nursing diagnosis, the cause, the symptom characteristics, the related factors and the nursing plan in the PESRDGI model; wherein a logical mapping relationship between each of the nursing diagnosis, the cause, the symptom characteristics, the related factors and at least one nursing plan is established in advance, and the PESRDGI model is updated based on the logical mapping relationship.

[0103] Fig. 9 The diagram shows the implementation principle of the nursing data processing method based on the PESRDGI model according to one embodiment of the present application. Currently, most nursing plans are based on nursing problems and list the relevant measures to be implemented, which does not meet the individualized care needs of patients (E-derived I / R-derived I).

[0104] In this embodiment, for each risky nursing problem, risk prevention measures for each relevant risk factor are screened and an association is established so that when the nurse implements the nursing plan, the nurse can push out appropriate preventive measures based on the relevant positive signs and medical history or life history and other risk factors collected during the assessment.

[0105] In this embodiment, for each existing nursing problem, the relevant causal treatment measures that lead to the problem are screened and an association is established, so that when the nurse implements the nursing plan, he or she can push out appropriate intervention instructions based on the relevant positive signs and medical history or life history collected during the assessment.

[0106] In one implementation of this embodiment, it also includes: in response to receiving a nursing execution request, based on the logical mapping relationship between the nursing diagnosis, the cause, the symptom characteristics, the related factors and the nursing execution in the PESRDGI model, a nursing execution interface containing bundled nursing measures is generated, and based on the corresponding mapping relationship between the monitoring data or execution abnormality data and the nursing measures, corresponding nursing measures are generated; wherein, the logical mapping relationship between each of the nursing diagnosis, the cause, the symptom characteristics, the related factors and the nursing measures and the logical mapping relationship between the monitoring data or execution abnormality data and the nursing measures are established in advance, and the PESRDGI model is updated based on the logical mapping relationship.

[0107] This embodiment establishes a nursing evidence-based knowledge base (NEBM) and a PESRDGI model, and performs nursing diagnosis, nursing planning, and nursing execution based on the nursing evidence-based knowledge base and the PESRDGI model, and automatically guides the process of nursing diagnosis and nursing execution.

[0108] This embodiment uses the constructed nursing evidence-based knowledge base and PESRDGI model to complete the active guidance of the full intelligent process of the nursing procedure. This embodiment is based on the 176 nursing diagnoses of the CCC clinical care classification system to establish the PESRDGI model. That is, starting with P as the core, collect, integrate and update the latest medical and nursing research results, clinical trial results and scientific evidence in the field of health care. These evidences include diagnostic methods, treatment methods, preventive measures and nursing methods for diseases. These data sources may include medical journals, research databases, clinical trial results, guidelines and recommendations of professional organizations. One by one, E (cause), S (defining characteristics), R (risk factor), I (intervention measures), etc. are evidence-based and sorted out.

[0109] 1) For nursing diagnosis

[0110] Systematic Review and Synthesis: NEBM systematically reviews and synthesizes the collected evidence. Professional nursing experts and medical researchers can rigorously review, analyze, and summarize the evidence to determine which practices are most effective, safest, and best for different patient groups.

[0111] 2) For nursing care plan

[0112] Supporting nursing decisions and planning: Nurses can access NEBM to obtain the latest evidence and guidelines for specific patient situations. This supports nurses in making clinically appropriate or evidence-based decisions when developing care plans, developing nursing interventions, implementing physician orders, and conducting patient monitoring. NEBM provides nurses with a trusted source of information to help them provide high-quality care.

[0113] 3) For nursing implementation

[0114] Developing Best Practice Guidelines: Based on its evaluation of the evidence, NEBM develops best practice guidelines. These guidelines are recommendations for nursing practice based on scientific evidence, and they provide direction for nursing decisions. These guidelines can cover a variety of areas of care, from disease management to end-of-life care, as well as individual specialty details.

[0115] When nurses provide nursing care to patients, the NEBM content automatically forms a clinical operation template, which includes monitoring content, detailed patient assessment content, observation content, nursing operation precautions, education and guidance content, etc. It can also automatically provide various required scoring scales or various special nursing content based on NEBM.

[0116] Clinical data repository (CDR) is a key information technology tool that aims to integrate and manage clinical data from different sources with a patient-centered approach to provide nurses with more comprehensive patient information.

[0117] Standardized data formats: CDR technology usually uses standardized data formats and encodings to ensure data interoperability between different systems. This means that no matter where the data comes from, they can be presented and analyzed in a consistent way in the same system.

[0118] Comprehensive patient view: CDR technology provides a comprehensive patient view, allowing nurses to access a variety of patient data from a single interface. This helps nurses better understand the patient's condition, history, and needs, allowing them to better provide personalized care.

[0119] Decision support: CDR technology can also integrate decision support tools that provide real-time advice and guidance based on patient data. Nurses can use these tools to assess the patient's condition, develop a care plan, execute orders, and make decisions based on the latest evidence.

[0120] The following is a more detailed description of the clinical data integration tool (CDR) used in the technology of this embodiment:

[0121] 1) For nursing diagnosis

[0122] Integration of multi-source data: One of the core functions of CDR technology is the ability to integrate multi-source clinical data, which may come from hospital information systems (HIS), laboratory information systems (LIS), imaging systems (PACS), electronic medical records (EMR), and various sensors and monitoring equipment. These data can include basic patient information, medical records, laboratory results, medical images, medication information, etc. When making nursing diagnoses, all of the above clinical information is directly used as E (cause), S (defining characteristics), and R (risk factors).

[0123] 2) For nursing care plan

[0124] When formulating nursing plans, the patient's clinical data integrated by CDR serves as the basis for the patient's causes (E) and risk factors (R), and can more accurately push measures that are in line with the patient's plan.

[0125] 3) For nursing implementation

[0126] Real-time data update: CDR technology supports real-time data update, allowing nurses to conduct patient assessments at any time or access the latest patient data through various sensors and monitoring devices, whether at the bedside, nurse station or remote workstation. This helps nurses obtain timely patient information and support decision-making and care.

[0127] In one implementation, a nursing diagnosis is automatically generated based on the patient's assessment information and medical record data; based on the best clinical evidence-based results and in conjunction with objective factors such as changes in the patient's condition, reassessment and nursing diagnosis are proactively prompted; automatic process guidance is provided for the nursing execution, including: if the monitoring data or assessment content is abnormal, subsequent related measures are automatically arranged based on evidence, and real-time operational guidance is provided; for the nursing plan: personalized nursing questions and nursing plans are automatically provided based on the content of the nursing diagnosis.

[0128] 1. For nursing diagnosis

[0129] Based on the best clinical evidence-based results and the objective factors of the patient's condition change, combined with information from other hospital information systems, it can proactively prompt re-evaluation and nursing diagnosis when the patient is admitted to the hospital, before and after surgery, transferred to other departments, or when the patient's condition changes.

[0130] 2. Regarding nursing execution

[0131] A) Using the principle of work scheduling, the patient's clinical instructions and nursing plan content are arranged according to the hourly work tasks of the primary patient, and the patient's hourly tasks are presented according to the care classification of the CCC clinical care classification system.

[0132] B) When performing tasks in the patient care process, if the monitoring data or assessment content is abnormal, the system can automatically arrange relevant measures based on evidence. For example, if the high body temperature is automatically prompted to take cooling measures, the subsequent temperature re-measurement will be automatically arranged in the work list; if the pain assessment reaches the point of pain, after the analgesic is used, the subsequent analgesic intervention effect evaluation will be automatically arranged in the work list according to the route of administration of the analgesic.

[0133] In one implementation of this embodiment, it also includes: automatically generating the content of nursing documents based on the nursing evidence-based knowledge base.

[0134] This embodiment can automatically generate nursing diagnoses based on the patient's assessment information and medical record data, reducing the burden on nurses and improving the accuracy of diagnosis. According to the content of the nursing diagnosis, personalized nursing questions and nursing plans can be provided to help nurses better formulate and implement nursing measures. In nursing operations, real-time operation guidance can be provided to ensure the accuracy and safety of nursing operations, and the content of nursing documents can be automatically generated to reduce the paperwork burden of nurses and improve the accuracy and standardization of records.

[0135] This embodiment has the following beneficial effects:

[0136] Integrated patient information management: Through a system that integrates patient clinical data, it is possible to integrate patient information from different sources and provide nurses with the complete patient view they need to better understand the patient's condition.

[0137] Standardized nursing process: Standardized nursing process ensures that nurses follow consistent best practices when performing nursing tasks, thus improving the quality of nursing care.

[0138] Intelligent decision support: Helps nurses make the best nursing decisions, including doctor's order execution, medication management, etc.

[0139] Workflow optimization: optimize nurses' workflow, reduce tedious manual operations, improve work efficiency and reduce work pressure.

[0140] Real-time monitoring and alerts: Provides the ability to monitor patient conditions in real time and issue alerts so nurses can respond to potential issues promptly.

[0141] Training and support: The system can automatically present clinical evidence-based nursing content and provide clinical nurses with training and support resources at any time to help nurses better use the system and keep their professional knowledge updated.

[0142] Standardized data format: CDR technology usually uses standardized data formats and codes to ensure data interoperability between different systems. The system currently integrates the CCC International Clinical Care Classification Code, which can store clinical care content with a unique code, and can provide complete data content presentation and analysis for subsequent national electronic medical record interconnection and clinical research.

[0143] Comprehensive patient view: CDR technology provides a comprehensive patient care view, and nurses can access various patient data from a single interface. This helps nurses better understand the patient's condition, history and needs, integrates them into the entire care process of the nursing program, and can better provide personalized care.

[0144] Decision support: Patient clinical data can also be integrated with decision support tools through CDR technology. These tools provide clinical nurses with real-time advice and guidance from assessment to diagnosis, nursing plan formulation, and nursing execution based on patient data. Therefore, nurses can use these tools to assess the patient's condition, formulate nursing plans, execute medical orders and nursing tasks, and make decisions based on the latest evidence.

[0145] Nursing evidence-based knowledge base plays an important role in artificial intelligence. It provides the infrastructure for storing, organizing and utilizing knowledge to support the intelligent behavior and decision-making of artificial intelligence.

[0146] The nursing evidence-based knowledge base is a system for storing and organizing clinical knowledge. In artificial intelligence, the nursing evidence-based knowledge base is used to support reasoning, decision-making, and problem solving. Artificial intelligence can acquire and utilize knowledge from the knowledge base to enhance its intelligent capabilities. The nursing evidence-based knowledge base can be used to build expert systems, recommendation systems, and natural language processing systems. It plays an important role in artificial intelligence. It provides an infrastructure for storing, organizing, and utilizing knowledge to support the intelligent behavior and decision-making of artificial intelligence.

[0147] The nursing data processing method of this embodiment provides a nursing data processing method, which automatically generates nursing diagnosis based on the patient's assessment information and medical record data, reduces the burden of nurses and improves the accuracy of diagnosis. According to the content of the nursing diagnosis, the nursing data processing method can provide personalized nursing questions and nursing plans to help nurses better formulate and implement nursing measures. In nursing operations, the nursing data processing method can provide real-time operation guidance to ensure the accuracy and safety of nursing operations. The nursing data processing method can automatically generate the content of nursing documents, reduce the paperwork burden of nurses, and improve the accuracy and standardization of records.

[0148] The nursing data processing method of this embodiment automatically generates nursing forms, and automatically generates nursing diagnoses using the nursing evidence-based knowledge base and the PESRDGI model; personalized nursing questions and nursing plans can be provided based on the content of the nursing diagnosis; nurses can perform special nursing according to the generated nursing plans; after evaluating the special nursing, nursing records and SBAR handover records are automatically generated; the intelligent information system will once again perform clinical closed-loop management of the patient's nursing content.

[0149] In one implementation of this embodiment, the process from assessment to diagnosis is: primary assessment - possible diagnosis - in-depth assessment - nursing diagnosis. The cyclic relationship is: assessment - diagnosis - planning - execution - evaluation - assessment.

[0150] In one implementation of this embodiment, the primary assessment is data collection and organization; the possible diagnosis is the judgment and listing of patient assessment information, the list includes a risk assessment table and a possible diagnosis table, all risk tables are automatically filled in and scored, and high-risk content is automatically screened out; the in-depth assessment is the judgment and list of possible diagnoses, re-analysis and exclusion; the nursing diagnosis is the final confirmation of the nursing diagnosis in order.

[0151] In one implementation of this embodiment, the nursing diagnosis first displays all problems and sorts the problems, and then displays all factors related to the corresponding problems to determine the defining characteristics; the nursing plan includes nursing problems and expected nursing goals; the nursing execution includes nurse measure execution and nursing intervention; the nursing evaluation includes automatically generating a nursing plan after nursing execution, and the plan includes multiple combinations of the following: evaluation time, problems, defining characteristics, related factors, nursing measures, executors, effect evaluation, evaluation time, and evaluators.

[0152] Specifically, the patient is assessed holistically, and the nursing assessment of the patient includes: life history, medical history, cardiovascular system, respiratory system, digestive system, nervous system, urinary system, blood system, sensory organs, psychology, etc.

[0153] For example, if you select the digestive system, the assessment content includes the oropharynx, digestive tract, abdomen, defecation and flatulence, stool characteristics and local conditions around the anus. The nurse can select the corresponding symptoms according to the patient's condition. Figure 3 The patient had no abnormalities in the oropharynx, gastrointestinal nausea and vomiting, abdominal chest pain and tenderness, constipation and flatulence during defecation, and no abnormalities in the nature of the stool or prolapsed material in the perianal area.

[0154] On the basis of overall assessment, PESRDGI is used to conduct scientific and systematic nursing diagnosis for patients. The process from assessment to diagnosis is: primary assessment - possible diagnosis - in-depth assessment - nursing diagnosis. Primary assessment is the collection and organization of information, possible diagnosis is the judgment and list of patient assessment information (the list includes risk assessment table and possible diagnosis table), in-depth assessment is the judgment and list of possible diagnosis, re-analysis and exclusion, and finally confirming the order of nursing diagnosis.

[0155] This embodiment will automatically generate various risk assessment scales based on the overall assessment content, automatically fill in and calculate the scores of each risk table, and automatically screen out high-risk content.

[0156] Nursing diagnosis theory PES reanalyzes and eliminates the patient's information and can be divided into three modules: problem (P), related factors (E), and defining characteristics (S). The problem (P) part first displays all the problems and sorts them, and then the system displays all the factors related to the corresponding problem to determine the defining characteristics.

[0157] This embodiment displays all problems related to the patient's condition (P), such as nausea, constipation, vomiting, aspiration risk, malnutrition risk, and blood pressure changes. The diagnostic order is aspiration risk 1, vomiting 2. Clicking on the vomiting problem will automatically generate factors related to nausea, vomiting, and hypertension. After exclusion, the definition features are finally determined.

[0158] In this embodiment, the nursing plan is divided into two modules: nursing problems-expected nursing goals, and measures and suggestions provided by the nursing evidence-based knowledge base and the PESRDGI model. It should be noted that this embodiment will automatically import the content of the bundled nursing measures according to the patient's condition.

[0159] The implementation plan (nursing execution) includes nurse measure execution and nursing intervention, which is divided into 5 parts: who, what, when, why, where, and how.

[0160] Effectiveness evaluation: After the nursing is executed, the system will automatically generate a nursing plan (electronic medical record requirement), which includes the evaluation time, questions, defining characteristics, relevant factors, nursing measures, executors, effectiveness evaluation, evaluation time, and evaluators.

[0161] This embodiment records life history, medical history, cardiovascular system, respiratory system and other aspects through process forms, and then uses the nursing evidence-based knowledge base and PESRDGI model to intelligently analyze the above information, automatically generate a nursing plan, and provide scientific and efficient nursing measures, so that clinical nurses can intuitively and clearly understand the various conditions of patients and improve the quality of care for patients.

[0162] In this embodiment, various data in the nursing process can be collected and analyzed to provide a basis for the evaluation and improvement of nursing quality. For example, by counting and analyzing the workload of nurses, the shifts can be optimized and work efficiency can be improved; by analyzing the patient satisfaction data, nursing services can be improved and the patient experience can be enhanced. This embodiment can provide medical staff with a comprehensive analysis of the patient's health status based on the patient's specific situation and nursing needs, helping them make more accurate diagnosis and treatment decisions, and providing a basis for the evaluation and improvement of nursing quality.

[0163] The protection scope of the nursing data processing method based on the PESRDGI model described in the embodiment of the present application is not limited to the execution order of the steps listed in this embodiment. All solutions implemented by adding, reducing or replacing steps in the prior art based on the principles of the present application are included in the protection scope of the present application.

[0164] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the nursing data processing method based on the PESRDGI model provided in any embodiment of the present application is implemented.

[0165] In the embodiment of the present application, any combination of one or more storage media can be used. The storage medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, - but not limited to - an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a RAM, a ROM, an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, a device or a device or used in combination with it.

[0166] An embodiment of the present application also provides an electronic device. Fig.10 Shown is a schematic diagram of the structure of the electronic device 100 provided in the embodiment of the present application. In some embodiments, the electronic device can be a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA) and other terminal devices. In addition, the nursing data processing method based on the PESRDGI model provided in the present application can also be applied to databases, servers, and service response systems based on terminal artificial intelligence. The embodiment of the present application does not impose any restrictions on the specific application scenarios of the nursing data processing method based on the PESRDGI model.

[0167] like Fig.10 As shown, the electronic device 100 provided in the embodiment of the present application includes a memory 101 and a processor 102 .

[0168] The memory 101 is used to store computer programs; preferably, the memory 101 includes: ROM, RAM, disk, USB flash drive, memory card or CD-ROM and other media that can store program codes.

[0169] Specifically, the memory 101 may include a computer system readable medium in the form of a volatile memory, such as a random access memory (RAM) and / or a cache memory. The electronic device 100 may further include other removable / non-removable, volatile / non-volatile computer system storage media. The memory 101 may include at least one program product having a set (e.g., at least one) of program modules, which are configured to perform the functions of the various embodiments of the present application.

[0170] The processor 102 is connected to the memory 101 and is used to execute the computer program stored in the memory 101 so that the electronic device 100 executes the nursing data processing method based on the PESRDGI model provided in any embodiment of the present application.

[0171] Optionally, the processor 102 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0172] Optionally, the electronic device 100 in this embodiment may further include a display 103. The display 103 is communicatively connected with the memory 101 and the processor 102, and is used to display a GUI interaction interface related to the nursing data processing method based on the PESRDGI model.

[0173] In summary, this application can ensure that in the clinical care process, the latest comprehensive, complete, and effective overall clinical assessment data of the patient is effectively obtained, and the weight of each nursing diagnosis is independently calculated to accurately diagnose nursing problems, so this application can effectively improve the efficiency and accuracy of nursing assessment and diagnosis. Therefore, this application effectively overcomes the various shortcomings of the prior art and has a high industrial utilization value.

[0174] The above embodiments are merely illustrative of the principles and effects of the present application and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. A nursing data processing method based on the PESRDGI model, characterized in that: include: Obtain clinical assessment data for multiple categories of patients; Matching the corresponding clinical assessment data of each category from a preset nursing evidence-based knowledge base based on the clinical assessment data of the patient in multiple categories; Obtaining the causes, symptom characteristics and weight coefficients of related factors corresponding to the nursing diagnosis in the clinical assessment data under each category; Generate nursing diagnosis based on the PESRDGI model in the nursing evidence-based knowledge base: in response to the fact that the sum of the weight coefficients of the symptom characteristics corresponding to the nursing diagnosis in the clinical assessment data under each category is greater than 1 and the cause exists, generate an existing nursing diagnosis; in response to the fact that the sum of the weight coefficients of the relevant factors corresponding to the nursing diagnosis in the clinical assessment data under each category is greater than 1, generate a risk nursing diagnosis.

2. The nursing data processing method based on the PESRDGI model according to claim 1 is characterized in that: Also includes: Constructing the nursing evidence-based knowledge base: Collecting patient medical data from multiple data sources, and obtaining patient clinical assessment data based on the patient medical data and a CCC classification standard code corresponding to the patient medical data; Based on the data association and mutually exclusive logical attributes between the clinical assessment data of each patient, the clinical assessment data of the patient are stored to form a nursing evidence-based knowledge base; Each of the weight coefficients is adjusted based on nursing evidence-based feedback data and / or the Delphi method to update the nursing evidence-based knowledge base.

3. The nursing data processing method based on the PESRDGI model according to claim 2 is characterized in that: Also includes: A PESRDGI model is established for each nursing diagnosis based on the nursing evidence-based knowledge base, wherein the nursing diagnosis includes an existing nursing diagnosis and a risk nursing diagnosis, and the establishment of the PESRDGI model includes: Classifying the clinical assessment data based on the assessment content, dividing the clinical assessment data under each category into causes, symptom characteristics and related factors of nursing diagnosis, and configuring weight coefficients and numbers for the causes, symptom characteristics and related factors respectively; A processing logic relationship is established between each nursing diagnosis and the causes, the symptom characteristics and the weight coefficients of the related factors to form the PESRDGI model.

4. The nursing data processing method based on the PESRDGI model according to claim 3 is characterized in that: The processing logic relationship between the nursing diagnosis and the causes, the symptom characteristics and the weight coefficients of the related factors includes: the initial sum of the weight coefficients of the causes, the symptom characteristics and the related factors of each nursing diagnosis is 1, and each weight coefficient is adjusted and updated according to nursing evidence-based feedback data and / or the Delphi method.

5. The nursing data processing method based on the PESRDGI model according to claim 3 or 4, characterized in that: The processing logic relationship between the nursing diagnosis and the cause, the symptom characteristics and the weight coefficients of the related factors also includes: If the sum of the weight coefficients of the symptom characteristics of the nursing diagnosis is greater than 1 and the cause exists, an existing nursing diagnosis is generated; if the sum of the weight coefficients of the related factors of the nursing diagnosis is greater than 1, a risk nursing diagnosis is generated; When the nursing diagnosis includes a sub-diagnosis and the diagnosis generation condition is met at the same time, a nursing diagnosis of the sub-diagnosis is generated; When the existing nursing diagnosis and the risk nursing diagnosis both meet the diagnosis generation conditions, generating the existing nursing diagnosis; Upon receiving the diagnosis constraints, the generated nursing diagnoses are filtered based on the diagnosis constraints.

6. The nursing data processing method based on the PESRDGI model according to claim 1 is characterized in that: Also includes: Obtaining evaluation results of each of the nursing diagnoses; Calculating the sensitivity and specificity of the nursing diagnosis based on the evaluation results; The weight coefficients of the causes, symptom characteristics, and related factors of the nursing diagnosis are adjusted based on the sensitivity and specificity of the nursing diagnosis.

7. The nursing data processing method based on the PESRDGI model according to claim 1 is characterized in that: Also includes: In response to receiving a nursing plan request, generating a nursing plan including bundled nursing measures based on a logical mapping relationship between the nursing diagnosis, the cause, the symptom characteristics, the related factors and the nursing plan in the PESRDGI model; Wherein, a logical mapping relationship between each of the nursing diagnoses, the causes, the symptom characteristics, the related factors and at least one nursing plan is pre-established, and the PESRDGI model is updated based on the logical mapping relationship.

8. The nursing data processing method based on the PESRDGI model according to claim 1 is characterized in that: Also includes: In response to receiving a nursing execution request, a nursing execution interface including bundled nursing measures is generated based on the logical mapping relationship between the nursing diagnosis, the cause, the symptom characteristics, the related factors and nursing execution in the PESRDGI model, and corresponding nursing measures are generated based on the corresponding mapping relationship between the monitoring data or execution abnormality data and the nursing measures; Among them, the logical mapping relationship between each nursing diagnosis, the cause, the symptom characteristics, the related factors and the nursing measures, as well as the logical mapping relationship between the monitoring data or execution abnormal data and the nursing measures are established in advance, and the PESRDGI model is updated based on the logical mapping relationship.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the nursing data processing method based on the PESRDGI model described in any one of claims 1 to 8 is implemented.

10. An electronic device, characterized in that: The electronic device comprises: A memory storing a computer program; A processor is communicatively connected to the memory, and executes the nursing data processing method based on the PESRDGI model described in any one of claims 1 to 8 when calling the computer program.

Images