Decision aiding method and system for delirium nursing

Abstract

The invention relates to the technical field of clinical nursing decision making, and discloses an auxiliary decision making method and system for delirium nursing, and the method comprises the steps: obtaining delirium-related multi-dimensional data; normalizing the multi-dimensional data to obtain normalized data; performing feature mining and correlation analysis on the standardized data through a preset analysis model to obtain a feature correlation analysis result; generating a preliminary nursing decision suggestion through a feature correlation analysis result; carrying out adaptability verification on the preliminary nursing decision suggestion to obtain a verification result; and optimizing the nursing decision suggestions in combination with the verification result to obtain a final delirium nursing aid decision scheme. According to the method, a complete technical path of multi-source data standardization integration, feature association intelligent analysis, adaptability verification and closed-loop optimization is constructed, so that the core problem that an existing method is lack of multi-source data standardization integration, dynamic adaptation optimization and closed-loop mechanisms is solved; the delirium nursing decision is converted from single data support and static generation to full-dimensional data drive and dynamic adaptation.

Description

Technical Field

[0001] This invention relates to the field of clinical nursing decision-making technology, specifically to auxiliary decision-making methods and systems for delirium nursing. Background Technology

[0002] Nursing decisions for delirium require a comprehensive consideration of multiple dimensions, including the patient's clinical condition, individual differences, and the characteristics of both traditional Chinese medicine and Western medicine treatments. However, the core technical problem with existing delirium nursing decision support methods is the lack of a closed-loop mechanism for standardized integration and dynamic optimization of multi-source data. Existing methods often rely on single types of data (such as Western medical psychological indicators) and lack effective means of integrating key dimensions of data, such as TCM diagnostic information, psychological state, and treatment environment. Furthermore, there is no unified standardized processing procedure for heterogeneous data (numerical signs, textual symptoms, and image-based tongue images), leading to biased decision-making and compromised accuracy.

[0003] This core issue directly leads to a series of limitations: on the one hand, the disorder of data integration makes it difficult for decision-making recommendations to accurately match individual patient characteristics; on the other hand, the lack of a systematic adaptation verification and feedback optimization mechanism after decision generation results in insufficient adaptability of initial recommendations to the actual patient condition and nursing implementation conditions, and the inability to continuously iterate and improve through clinical practice. Ultimately, this leads to the inability of nursing decision-making accuracy and practicality to meet clinical needs, and there is an urgent need to build a complete technical path covering data integration, intelligent analysis, verification and optimization. Summary of the Invention

[0004] In view of the shortcomings of the existing technology, the present invention proposes an auxiliary decision-making method and system for delirium care to solve the above-mentioned technical problems.

[0005] Firstly, it provides auxiliary decision-making methods for delirium care, including: Obtain multi-dimensional data related to delirium; The multi-dimensional data is then normalized to obtain normalized data. Feature mining and correlation analysis are performed on the standardized data using a preset analysis model to obtain feature correlation analysis results; Preliminary nursing decision-making suggestions are generated based on the results of the feature correlation analysis. The suitability of the preliminary nursing decision recommendations was verified, and the verification results were obtained. Based on the validation results, nursing decision-making suggestions were optimized to obtain the final auxiliary decision-making scheme for delirium nursing.

[0006] Furthermore, obtain multi-dimensional data related to delirium, including: Collect patients' clinical diagnosis and treatment information, physiological signs data, and information related to traditional Chinese medicine syndrome differentiation; Collect data on the patient's psychological state, daily behavior, and the relevant data of the treatment environment; By integrating the clinical diagnosis and treatment information, physiological signs data, TCM syndrome differentiation information, psychological state performance, lifestyle behavior data, and treatment environment data, a complete multi-dimensional data set is obtained.

[0007] Furthermore, the multi-dimensional data is normalized to obtain normalized data, including: Formatting is performed on different types of data in multi-dimensional data to unify the data representation form and obtain formatted data. The normalized data is processed to remove interference information, resulting in de-interference data. Standardized data is obtained by uniformly transforming the data after removing interference using a standardization method.

[0008] Furthermore, feature mining and correlation analysis are performed on the standardized data using a preset analysis model to obtain feature correlation analysis results, including: Feature extraction algorithms were used to extract core features related to delirium care from normalized data, resulting in a core feature set. Establish association mapping rules between core features, explore the inherent associations between different types of core features, and obtain feature association relationships; Based on association mapping rules and core features, the data dimensionality is reduced and key information is enhanced through analysis models to obtain feature association analysis results.

[0009] Furthermore, preliminary nursing decision recommendations are generated based on the analysis results, including: A pre-defined delirium nursing decision-making knowledge base is invoked, which contains the correspondence between different feature combinations and nursing intervention measures; The feature association analysis results are matched with the corresponding relationships in the knowledge base to obtain a suitable initial nursing intervention combination; Based on the patient's individual basic information, the initial nursing intervention combination was adjusted to obtain preliminary nursing decision recommendations.

[0010] Furthermore, the construction of the delirium nursing decision-making knowledge base includes: Collect data on past delirium nursing cases, clinical nursing guidelines, and literature on TCM syndrome differentiation and nursing theories; Information was extracted from the case data, guidelines, and theoretical literature to analyze the correspondence between nursing interventions and patient characteristics, thus obtaining characteristic-measure correspondence information. The extracted information is categorized and stored according to data type, resulting in a nursing intervention library covering clinical nursing, traditional Chinese medicine nursing, psychological nursing, and environmental intervention, as well as a feature matching rule library that records core features and nursing intervention adaptation logic.

[0011] Furthermore, the suitability of the preliminary nursing decision recommendations was verified, and the verification results were obtained, including: Collect patient's current physiological status feedback data and nursing implementation condition data; The feedback data, implementation condition data, and the adaptation requirements of the preliminary nursing decision-making suggestions are compared to obtain the comparison results. By comparing the results, we can determine the feasibility and suitability of the initial nursing decision recommendations and obtain the verification results.

[0012] Furthermore, based on the validation results, the nursing decision-making recommendations were optimized to obtain the final delirium nursing auxiliary decision-making scheme, including: Based on the mismatch items in the validation results, the combination of intervention measures and implementation details in the initial nursing decision-making recommendations were adjusted to obtain the adjusted nursing decision-making recommendations. By analyzing the synergistic effects among different interventions based on the adjusted nursing decision-making recommendations, the results of the synergistic effect analysis were obtained. By integrating the adjusted intervention measures, synergistic effect analysis results, and validation feedback information, a final delirium nursing auxiliary decision-making scheme was obtained.

[0013] Secondly, an auxiliary decision-making system for delirium care is provided, based on any of the auxiliary decision-making methods for delirium care described above, including: The acquisition module is configured to acquire multi-dimensional data related to delirium; The processing module is configured to perform normalization processing on the multi-dimensional data to obtain normalized data; The analysis module is configured to perform feature mining and correlation analysis on the standardized data using a preset analysis model to obtain feature correlation analysis results; The generation module is configured to generate preliminary nursing decision suggestions based on the results of the feature association analysis. The verification module is configured to perform adaptability verification on the preliminary nursing decision recommendations and obtain verification results; The decision-making module is configured to optimize nursing decision-making suggestions based on the validation results, and obtain the final delirium nursing auxiliary decision-making scheme.

[0014] Thirdly, a terminal is provided, including a processor, an input device, an output device, and a memory, wherein the processor, input device, output device, and memory are interconnected, and the memory is used for... A computer program is stored, the computer program including program instructions, and the processor is configured to invoke the program instructions to execute the auxiliary decision-making method for delirium care as described in any of the preceding descriptions.

[0015] The invention employing the above technical solution has the following advantages: This invention addresses the core issues of existing methods that lack standardized integration of multi-source data, dynamic adaptation and optimization, and a closed-loop mechanism by constructing a complete technical path of multi-source data standardization integration → intelligent feature association analysis → adaptability verification → closed-loop optimization. It realizes the transformation of delirium nursing decision-making from single data support and static generation to multi-dimensional data-driven, dynamically adapted and continuously iterative, providing clinical practice with accurate, adaptable and long-term optimizable delirium nursing auxiliary decision support. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart of the auxiliary decision-making method for delirium care according to the present invention; Figure 2 This is a flowchart of the auxiliary decision-making system for delirium care according to the present invention; Figure 3 This is a schematic diagram of the terminal structure in the auxiliary decision-making method and system for delirium care of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0020] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application can be combined with other embodiments.

[0021] like Figures 1-3 As shown, the auxiliary decision-making method for delirium care of the present invention includes: Step 1: Obtain multi-dimensional data related to delirium; Step 2: Normalize the multi-dimensional data to obtain normalized data; Step 3: Perform feature mining and correlation analysis on the standardized data using a preset analysis model to obtain the feature correlation analysis results; Step 4: Generate preliminary nursing decision suggestions based on the results of feature association analysis; Step 5: Perform suitability verification on the preliminary nursing decision recommendations and obtain the verification results; Step 6: Optimize nursing decision-making suggestions based on the verification results to obtain the final delirium nursing auxiliary decision-making scheme.

[0022] Specifically, this invention addresses the core problem of existing methods lacking a standardized integration of multi-source data and a dynamic adaptation and optimization closed-loop mechanism by constructing a complete technical path of multi-source data standardization integration → intelligent feature association analysis → adaptability verification → closed-loop optimization. This achieves a transformation in delirium nursing decision-making from single-data support and static generation to multi-dimensional data-driven, dynamically adaptable, and continuously iterative approaches. The individual adaptation accuracy of decision recommendations is improved compared to existing technologies, and the average time to relief of delirium symptoms is shortened. This provides clinical practice with precise, adaptable, and long-term optimizable nursing auxiliary decision support, significantly improving nursing efficiency and quality and reducing nursing risks.

[0023] In this embodiment, multi-dimensional data related to delirium are obtained, including: Collect patients' clinical diagnosis and treatment information, physiological signs data, and information related to traditional Chinese medicine syndrome differentiation; Collect data on the patient's psychological state, daily behavior, and the relevant data of the treatment environment; By integrating clinical diagnosis and treatment information, physiological signs data, TCM syndrome differentiation information, psychological state performance, lifestyle behavior data, and data related to the diagnosis and treatment environment, a complete multi-dimensional data set is obtained.

[0024] Specifically, the data collection and integration process is as follows: Clinical diagnosis and treatment information: Extract patient basic information, surgical information, medication records, and laboratory test results through the hospital's electronic medical record system; Physiological data: collected in real time via bedside monitors, including heart rate (HR), blood pressure, blood oxygen saturation, and body temperature; Information related to TCM diagnosis: collected by attending TCM physicians, including tongue appearance (dark red tongue with yellow and greasy coating), pulse (wiry and rapid), constitution type (damp-heat constitution), and symptoms (irritability, incoherent speech, and worsening delirium at night). Psychological state manifestations: The score of the Self-Rating Anxiety Scale (SAS) was 65 (moderate anxiety). The emotional state (fear of unfamiliar environment, refusal of nursing procedures) was observed and recorded by the responsible nurse. Daily life data: Records food intake, bowel movements, and activity levels; Data related to the treatment environment: collected through ward environment monitoring equipment, including temperature 25℃, humidity 65%, light intensity, and noise intensity.

[0025] The above six types of data are linked and integrated according to the patient's unique identifier and the collection timestamp to form a structured multi-dimensional data set. Among them, numerical data is stored as floating-point numbers, text data is encoded as strings, and image-type tongue image data is stored as the path address of a 256×256 pixel RGB image.

[0026] In this embodiment, the multi-dimensional data is normalized to obtain normalized data, including: Formatting is performed on different types of data in multi-dimensional data to unify the data representation form and obtain formatted data. The normalized data is processed to remove interference information, resulting in de-interference data. Standardized data is obtained by uniformly transforming the data after removing interference using a standardization method.

[0027] Specifically, the normalization process consists of three steps: format regularization, interference removal, and standardization conversion. The specific algorithms and examples are as follows: Formatting guidelines: Numerical data (heart rate, blood pressure, SAS score, etc.): should be uniformly retained to one decimal place; Textual data (constitution type, syndrome manifestations, etc.): is converted into binary vectors using unique thermal encoding. For example, damp-heat constitution is encoded as [0,0,0,0,1,0,0,0,0] (corresponding to nine TCM constitution classifications), and syndrome keywords such as irritability and incoherent speech are encoded as two-dimensional binary vectors [1,1]. Image data (tongue image): uniformly converted into a 256×256 pixel RGB tensor matrix with dimensions of 3×256×256 (number of channels × height × width).

[0028] Removal of interference information: Outlier handling in physiological data: Median filtering is used to remove outliers caused by accidental interference. The formula is as follows: Let the acquisition sequence of a certain physiological indicator be... Select the size of the sliding window k =5 (odd number), for each data point Take the median of the sorted data within the window as the filtering result:

[0029] in, ≥3, edge data is padded with mirror image; Example: The patient's HR collection sequence is [102, 105, 160, 108, 104]. After sorting within the window, it becomes [102, 104, 105, 108, 160]. The median is 105, so the outlier 160 is replaced with 105. The filtered sequence is [102, 105, 105, 108, 104].

[0030] It should be noted that edge data is padded using mirroring. A specific example is as follows: Taking the filtered HR sequence [102, 105, 105, 108, 104] as an example, when the data index... When x = 1 (the first data point x1 = 102), the missing data in the left window (x -2 x -1 Following the principle of mirror symmetry, fill in the corresponding position on the right, i.e., x -2 =x3=105、x -1 =x2=105, after filling the window data, the value is [105, 105, 102, 105, 105], and the median value after sorting is 105; when When x = 2 (the second data point x2 = 105), the missing x -1 Fill with x1=102, the window data is [102, 102, 105, 105, 108], the median after sorting is 105; index For intermediate data of ≥3, the calculation is performed directly using a continuous window to ensure consistent filtering logic across the entire sequence.

[0031] Stop word filtering for text-based data: A stop word list based on a clinical nursing corpus (containing more than 300 meaningless words such as "of", "and", "to proceed") was used to filter out the core keywords such as "irritable and restless", "incoherent speech", and "worsened at night".

[0032] Standardization conversion: The Z-score normalization algorithm is used to eliminate the dimensional differences in numerical data and unify the dimensions. The formula is as follows:

[0033] in, The data is in the original numerical format. This represents the mean of the clinical normal range for this indicator. The standard deviation of the clinical normal range. This is the standardized data (the value range is usually [-3, 3]).

[0034] The final result is a normalized dataset containing numerical standardized data, text encoded vectors, and image tensor paths.

[0035] In this embodiment, feature mining and association analysis are performed on standardized data using a preset analysis model to obtain feature association analysis results, including: Feature extraction algorithms were used to extract core features related to delirium care from normalized data, resulting in a core feature set. Establish association mapping rules between core features, explore the inherent associations between different types of core features, and obtain feature association relationships; Based on association mapping rules and core features, the data dimensionality is reduced and key information is enhanced through analysis models to obtain feature association analysis results.

[0036] Specifically, this step is divided into three parts: core feature extraction, feature association mining, and dimensionality reduction and information enhancement. The specific algorithm is as follows: Core feature extraction: Numerical normalized data: Statistical feature extraction method is used to calculate the 24-hour mean and trend slope of each indicator; Text encoding vector: The weights of syndrome keywords are extracted using the TF-IDF algorithm, as shown in the following formula: Term Frequency (TF): in, The number of times the keywords appear in the patient's syndrome text. This represents the total number of occurrences of all keywords in text d. Inverse document frequency (IDF): Where N is the total number of texts describing the symptoms of delirium patients in the knowledge base. The number of texts containing the keyword t (1800 for "irritability and restlessness"). value: Example: The keyword "irritability" appears 3 times in the patient's text, and the total number of keyword occurrences is 5. Therefore... =3 / 5=0.6; =log(5000 / 1800)≈0.44; =0.6×0.44≈0.26, which is the core syndrome characteristic; Image-based data (tongue image): Visual features are extracted using a lightweight MobileNetV2 CNN network. Input is a 256×256 RGB tongue image. After convolution and pooling operations, a 256-dimensional tongue image feature vector is output, covering core information such as tongue color, tongue coating texture, and tongue coating color.

[0037] Integrating the above features, an initial feature set of 384 dimensions is formed (32 dimensions of numerical statistical features + 64 dimensions of text TF-IDF features + 256 dimensions of tongue image visual features + 32 dimensions of environmental features).

[0038] Feature association mining: The nonlinear correlation between different types of core features is mined using mutual information entropy, as shown in the following formula:

[0039] in, There are two types of features (such as TF-IDF features of agitation and restlessness and HR standardized data). for X = and Y= The joint probability, , They are respectively X= 、Y= The marginal probability, It was determined to be a strong association.

[0040] Dimensional Reduction and Information Enhancement: Principal Component Analysis (PCA) was used to reduce the dimensionality of the initial 384-dimensional features, retaining principal components with a cumulative variance contribution rate ≥ 90%, as shown in the following formula: Calculate the initial characteristic matrix The covariance matrix (where m is the number of samples collected):

[0041] in, It is the feature mean vector; Solving the covariance matrix With corresponding feature vectors ; The projection matrix is ​​formed by selecting the first k eigenvectors. ,satisfy ; Generate the dimensionality-reduced feature matrix: .

[0042] In this embodiment, the first 64 principal components are selected, and the final 64-dimensional core feature association analysis results are obtained.

[0043] In this embodiment, preliminary nursing decision recommendations are generated based on the analysis results, including: The system invokes a pre-defined delirium nursing decision-making knowledge base, which contains the correspondence between different feature combinations and nursing intervention measures. The results of feature association analysis are matched with the corresponding relationships in the knowledge base to obtain a suitable initial nursing intervention combination; Based on the patient's individual basic information, the initial nursing intervention combination was adjusted to obtain preliminary nursing decision-making suggestions.

[0044] In this embodiment, the construction of the delirium care decision-making knowledge base includes: Collect data on past delirium nursing cases, clinical nursing guidelines, and literature on TCM syndrome differentiation and nursing theories; Information was extracted from case data, guidelines, and theoretical literature to analyze the correspondence between nursing interventions and patient characteristics, thus obtaining information on the correspondence between characteristics and interventions. The extracted information is categorized and stored according to data type, resulting in a nursing intervention library covering clinical nursing, traditional Chinese medicine nursing, psychological nursing, and environmental intervention, as well as a feature matching rule library that records core features and nursing intervention adaptation logic.

[0045] Specifically, this step relies on a pre-built delirium care decision-making knowledge base, and generates preliminary suggestions through feature matching and individual adjustments. The specific process is as follows: Construction of a knowledge base for delirium nursing decision-making: Data sources: 5,000 past delirium nursing cases (including postoperative, critical, and elderly patients), 15 clinical guidelines such as the "Chinese Expert Consensus on Delirium Nursing (2023 Edition)" and the "Guidelines for Traditional Chinese Medicine Syndrome Differentiation and Nursing", and 40 theoretical literatures on traditional Chinese medicine syndrome differentiation and nursing. Information extraction: The BERT pre-trained model was used to extract information from cases, guidelines and literature, extract the correspondence between patient characteristics and nursing measures (e.g., damp-heat constitution and irritability → acupoint massage (Quchi, Hegu)), and sort out the implementation parameters of nursing measures (e.g., massage frequency and duration). Categorized Storage: Information is categorized and stored according to patient characteristic type and nursing intervention type, forming two main sub-databases: Nursing intervention measures library: covering four major categories: clinical nursing (analgesia, sedation adjustment), traditional Chinese medicine nursing (acupoint intervention, Chinese medicine conditioning), psychological nursing (music therapy, cognitive intervention), and environmental intervention (light adjustment, noise control), with a total of 130 specific measures and parameter ranges; Feature matching rule base: Stores the adaptation logic of 64 core features and nursing measures (e.g., HR standardized value > 2.0 + irritability syndrome TF-IDF > 0.2 → adjust analgesia pump parameters + acupoint massage).

[0046] Initial nursing decision recommendations are generated: Feature matching: The cosine similarity algorithm is used to calculate the matching degree between the 64-dimensional core features and the feature templates in the rule base. The formula is as follows:

[0047] Where A is the current patient's 64-dimensional core feature vector. For A's i Dimensional values ​​( i =1,2,...,64, where the first dimension is the standardized HR value and the second dimension is the TF-IDF value of the irritability syndrome. B is a 64-dimensional vector of a feature template in the rule base. For B's i Each dimension value (corresponding one-to-one with the dimensions of A, such as the threshold of HR standardized values ​​in the template, the threshold of TF-IDF for the irritability syndrome). Let A be the dot product of vectors A and B; Let L2 be the magnitude of vector A. Let L2 be the magnitude of vector B; Sim(A,B) represents the similarity result, with a value range of [0,1]. Sim(A,B)≥0.8 indicates a successful match, meaning that the current patient features and template features are highly compatible.

[0048] Initial nursing intervention combination: Four highly similar templates were matched, and the combination was generated by calling the intervention library: ① Adjusting the analgesia pump parameters; ② Traditional Chinese medicine acupoint massage (Quchi, Hegu, twice a day); ③ Environmental intervention (nighttime light intensity reduced to ≤40 lux, noise control ≤50 dB); ④ Psychological care; Individual adjustments: Based on the patient's basic information (history of coronary heart disease), adjust the parameters of the measures: ① Adjust the analgesic pump dosage (to avoid a sudden drop in blood pressure that may induce cardiac discomfort); ② Reduce the intensity of acupoint massage (to avoid stimulating blood vessels), and finally form preliminary nursing decision recommendations.

[0049] In this embodiment, the suitability of the preliminary nursing decision recommendations is verified, and the verification results are obtained, including: Collect patient's current physiological status feedback data and nursing implementation condition data; The feedback data, implementation condition data, and the matching requirements of the preliminary nursing decision-making recommendations are compared to obtain the comparison results. By comparing the results, we can determine the feasibility and suitability of the initial nursing decision recommendations and obtain the verification results.

[0050] Specifically, by collecting feedback data and implementation condition data, the suitability of the initial recommendations is quantitatively verified, as follows: Feedback and Conditional Data Collection: Patient's current physiological status feedback data: Physiological signs, symptom manifestations (reduced irritability, reduced refusal of care), and decreased SAS score 6 hours after the initial suggestion was generated; Nursing implementation conditions data: existing ward equipment (equipped with dimmable LED lights and noise detectors), nursing staff (one TCM specialist nurse per bed), patient tolerance (no obvious resistance to acupoint massage, and calm mood during music therapy).

[0051] Quantitative verification of adaptability: The verification results were calculated using a weighted summation fitness scoring model, as shown in the following formula:

[0052] in, Physiological fitness (the degree to which feedback data meets the expected goals of the measures); The degree of suitability for implementation (the extent to which existing resources meet the requirements of the measures); For patient tolerance; , , These are the weighting coefficients.

[0053] In this embodiment, the nursing decision-making suggestions are optimized based on the validation results to obtain the final delirium nursing auxiliary decision-making scheme, including: Based on the mismatch items in the validation results, the combination of intervention measures and implementation details in the initial nursing decision-making recommendations were adjusted to obtain the adjusted nursing decision-making recommendations. By analyzing the synergistic effects among different interventions based on the adjusted nursing decision-making recommendations, the results of the synergistic effect analysis were obtained. By integrating the adjusted intervention measures, synergistic effect analysis results, and validation feedback information, a final delirium nursing auxiliary decision-making scheme was obtained.

[0054] Specifically, based on the verification results, measures are adjusted, synergistic effects are analyzed, and a structured final solution is generated, as follows: Adjustment of intervention measures: In response to the issue of slightly low physiological compatibility, two measures in the initial recommendations have been adjusted: Clinical care: For example, adjust the analgesia pump dose from 2.6 ml / h to 2.8 ml / h (to balance analgesic effect with cardiac safety and avoid residual pain that may induce agitation). Traditional Chinese Medicine Nursing Care: Add Huanglian Jiedu Decoction for oral administration, suitable for damp-heat syndrome (dark red tongue with yellow and greasy coating, and wiry and rapid pulse).

[0055] Synergistic effect analysis: The Apriori association rule algorithm was used to analyze the synergistic relationship of the five adjusted measures. The minimum support was set to 0.7 and the minimum confidence to 0.8. Strong synergistic rules were found: Huanglian Jiedu Decoction and acupoint massage → improved relief rate of irritability symptoms. The implementation order was determined: acupoint massage was performed 1 hour after oral administration of Huanglian Jiedu Decoction.

[0056] Final solution generated: By integrating and adjusting the intervention measures, the collaborative implementation logic, and the verification feedback information, a structured final delirium nursing auxiliary decision-making plan is generated. The core content is as follows: Table 1 ; In some embodiments, the implementation effect of the final solution is fed back to the knowledge base: Feature matching rule library: Added 64 core features and coronary heart disease history → matching rules for analgesic pump 2.8ml / h and Huanglian Jiedu Decoction; Nursing intervention database: Replenishing damp-heat constitution and postoperative delirium → Strong synergistic combination of Coptis chinensis decoction and acupoint massage and implementation parameters; Fit rating model: Based on the validation results of 100 similar patients, α (physiological state fit weight) was adjusted from 0.45 to 0.48 to further enhance the influence of physiological indicators on decision optimization.

[0057] Among them, patients of the same type refer to those aged 60-80 years who have delirium after femoral neck fracture surgery, have one or more underlying cardiovascular diseases (such as coronary heart disease, hypertension), and are diagnosed with damp-heat constitution / phlegm-dampness constitution in traditional Chinese medicine. The screening criteria must be met simultaneously: ① the surgical type is closed reduction and internal fixation of femoral neck fracture; ② delirium symptoms appear within 24-72 hours after surgery; ③ the history of underlying diseases is ≥5 years; ④ no severe liver and kidney dysfunction. This ensures that the validation data is consistent with the clinical characteristics of the current patients and improves the reliability of weight adjustment.

[0058] In other embodiments, an auxiliary decision-making system for delirium care is provided, and an auxiliary decision-making method for delirium care based on any of the preceding embodiments includes: The acquisition module is configured to acquire multi-dimensional data related to delirium; The processing module is configured to perform normalization processing on multi-dimensional data to obtain normalized data; The analysis module is configured to perform feature mining and correlation analysis on standardized data using a preset analysis model to obtain feature correlation analysis results. The generation module is configured to generate preliminary nursing decision suggestions based on the results of feature association analysis. The verification module is configured to perform adaptability verification on the initial nursing decision recommendations and obtain the verification results. The decision-making module is configured to optimize nursing decision-making suggestions based on the validation results, and obtain the final delirium nursing auxiliary decision-making scheme.

[0059] In other embodiments, please refer to Figure 3 , Figure 3 A terminal is provided, including a processor, an input device, an output device, and a memory, which are interconnected. The memory is used to store a computer program, which includes program instructions. The processor is configured to invoke the program instructions, which include instructions for performing the following steps. Obtain multi-dimensional data related to delirium; Normalize multi-dimensional data to obtain normalized data; By using a pre-defined analysis model, feature mining and correlation analysis are performed on the standardized data to obtain the feature correlation analysis results; Preliminary nursing decision-making suggestions are generated based on the results of feature association analysis; The suitability of the initial nursing decision recommendations was validated, and the validation results were obtained. Based on the validation results, nursing decision-making suggestions were optimized to obtain the final auxiliary decision-making scheme for delirium nursing.

[0060] The above mainly describes the solutions of the embodiments of this application from the perspective of the method execution process. It is understood that, in order to achieve the above functions, the terminal includes the corresponding hardware structure and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments provided herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0061] This application embodiment can divide the terminal into functional units according to the above method example. For example, each function can be divided into a separate functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0062] This application also provides a computer storage medium storing a computer program for electronic data interchange that causes a computer to perform some or all of the steps of any of the delirium care auxiliary decision-making methods described in the above method embodiments.

[0063] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program that causes a computer to perform some or all of the steps of any delirium care auxiliary decision-making method as described in the above method embodiments.

[0064] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0065] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0066] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0067] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0068] Furthermore, the functional units in the various embodiments of the application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software program module.

[0069] If the integrated unit is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0070] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage device, which may include: a flash drive, a read-only memory, a random access memory, a magnetic disk, or an optical disk, etc.

[0071] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method of assisted decision making for delirium care, characterized in that, The method comprises the following steps: Obtaining delirium-related multidimensional data; Standardizing the multidimensional data to obtain standardized data; Performing feature mining and correlation analysis on the standardized data through a preset analysis model to obtain a feature correlation analysis result; Generating a preliminary nursing decision suggestion based on the feature correlation analysis result; Adaptability verification of the preliminary nursing decision suggestion to obtain a verification result; Optimizing the nursing decision suggestion in combination with the verification result to obtain a final delirium nursing auxiliary decision scheme.

2. The auxiliary decision-making method for delirium care according to claim 1, characterized in that, Obtaining delirium-related multidimensional data comprises: Collecting clinical diagnosis and treatment information, physiological sign data, and traditional Chinese medicine syndrome differentiation related information of the patient; Collecting psychological state performance, life behavior data, and diagnosis and treatment environment related data of the patient; Integrating the clinical diagnosis and treatment information, physiological sign data, traditional Chinese medicine syndrome differentiation related information, psychological state performance, life behavior data, and diagnosis and treatment environment related data to obtain a complete multidimensional data set.

3. The delirium care assisted decision method according to claim 1, characterized by, Standardizing the multidimensional data to obtain standardized data comprises: Respectively formatting different types of data in the multidimensional data to unify the data representation form to obtain formatted data; Removing interference information from the formatted data to obtain de-interference data; Converting the de-interference data to a unified dimension through a standardization method to obtain standardized data.

4. The delirium care supporting decision method according to claim 1, characterized by, Performing feature mining and correlation analysis on the standardized data through a preset analysis model to obtain a feature correlation analysis result comprises: Extracting core features related to delirium nursing from the standardized data using a feature extraction algorithm to obtain a core feature set; Establishing an association mapping rule between the core features to mine the internal association of different types of core features to obtain a feature correlation relationship; Based on the association mapping rule and the core features, performing data dimension reduction and key information strengthening through an analysis model to obtain a feature correlation analysis result.

5. The delirium care assisted decision method according to claim 1, characterized by, Generating a preliminary nursing decision suggestion based on the analysis result comprises: Calling a preset delirium nursing decision knowledge base, which contains the corresponding relationship between different feature combinations and nursing intervention measures; Matching the feature correlation analysis result with the corresponding relationship in the knowledge base to obtain an adapted initial nursing intervention combination; Adjusting the initial nursing intervention combination in combination with the individual basic information of the patient to obtain a preliminary nursing decision suggestion.

6. The method of assisted decision making for delirium care according to claim 5, characterized in that, The construction of the delirium nursing decision knowledge base comprises: Collecting previous delirium nursing case data, clinical nursing guideline files, and traditional Chinese medicine syndrome differentiation and nursing theory literature; Extracting information from the case data, guideline files, and theory literature, and sorting out the corresponding logic of nursing intervention measures and patient features to obtain feature-measure corresponding relationship information; Classifying and storing the extracted information according to data types to obtain a nursing intervention measure library covering clinical nursing, traditional Chinese medicine nursing, psychological nursing, and environmental intervention, and a feature matching rule library recording the adaptation logic of core features and nursing measures.

7. The delirium care assisted decision method according to claim 1, characterized by, Adaptability verification of the preliminary nursing decision suggestion to obtain a verification result comprises: Collecting patient current physiological state feedback data and nursing implementation condition data; Comparing the feedback data, implementation condition data, and adaptation requirements of the preliminary nursing decision suggestion to obtain a comparison result; The implementation feasibility and adaptation degree of the preliminary nursing decision suggestion are determined according to the comparison result, and a verification result is obtained.

8. The delirium care assisted decision method according to claim 1, characterized by, The nursing decision suggestion is optimized in combination with the verification result, and a final delirium nursing auxiliary decision scheme is obtained, including: According to the unadapted items in the verification result, the combination and implementation details of the intervention measures in the preliminary nursing decision suggestion are adjusted, and an adjusted nursing decision suggestion is obtained. Through the adjusted nursing decision suggestion, the synergistic effect relationship between different intervention measures is analyzed, and a synergistic effect analysis result is obtained. The final delirium nursing auxiliary decision scheme is obtained by integrating the adjusted intervention measures, the synergistic effect analysis result and the verification feedback information.

9. An assisted decision system for delirium care, characterized in that, The auxiliary decision-making method for delirium nursing according to any one of claims 1 to 8 comprises: An acquisition module configured to acquire delirium-related multidimensional data; A processing module configured to normalize the multidimensional data to obtain normalized data; An analysis module configured to perform feature mining and correlation analysis on the normalized data through a preset analysis model to obtain a feature correlation analysis result; A generation module configured to generate a preliminary nursing decision suggestion through the feature correlation analysis result; A verification module configured to verify the adaptation of the preliminary nursing decision suggestion to obtain a verification result; A decision module configured to optimize the nursing decision suggestion in combination with the verification result to obtain a final delirium nursing auxiliary decision scheme.

10. A terminal, characterized by comprising: A device comprising a processor, an input device, an output device and a memory, which are connected to each other, wherein the memory is used to store a computer program, the computer program comprising program instructions, the processor is configured to invoke the program instructions, and execute the auxiliary decision-making method for delirium nursing according to any one of claims 1 to 8.

Images