A method and system for determining colonoscopy surgery nursing plan based on clinical data

Abstract

The present invention proposes a method and system for determining a colonoscopy surgical nursing plan based on clinical data, which relates to the technical field of colonoscopy. The method comprises: obtaining clinical data of the patient, obtaining a first eigenvector and a second eigenvector according to the clinical data, inputting the first eigenvector into an improved CNN network, outputting a first nursing plan, inputting the second eigenvector into an improved LSTM network, and outputting a second nursing plan. The present invention constructs a precise analysis vector by fusing multi-dimensional patient data to realize the scientific basis of personalized surgical nursing plans, and at the same time uses a dual model to improve the effectiveness and pertinence of the plan, optimizes the data processing process by correlation screening, and adaptively adjusts the model parameters, thereby comprehensively improving the scientific nature, efficiency, patient acceptance and medical service quality of colonoscopy surgical nursing.

Description

Technical Field

[0001] The present invention relates to the technical field of colonoscopy, and in particular to a method and system for determining a colonoscopy surgery nursing plan based on clinical data. Background Art

[0002] In current colonoscopy nursing practice, the development of nursing plans primarily relies on the personal experience and expertise of medical staff. While this approach can meet patients' basic needs to a certain extent, its subjectivity and uncertainty limit optimal nursing outcomes. In recent years, with the advancement of medical information technology, some medical institutions have begun to explore the use of mathematical models or algorithms to predict and formulate nursing plans, aiming to improve the accuracy and efficiency of care. However, existing model-based nursing plan prediction methods have significant shortcomings.

[0003] First, these methods fail to fully utilize rich clinical data resources when building models, such as patients' medical history, physiological indicators, and psychological status. These data are crucial for developing personalized care plans. Therefore, models lacking clinical data support are significantly reduced in predictive accuracy and practicality.

[0004] Second, existing models often overlook the characteristics of input and output data during their design and application. Clinical data is often complex, diverse, and nonlinear, and existing models often fail to adapt and optimize to these characteristics, resulting in poor performance when processing real-world data.

[0005] Finally, existing methods also have significant inapplicability in terms of model training parameter setting. Due to a lack of in-depth understanding of the characteristics of clinical data, the selection and adjustment of parameters during model training often rely on experience or default settings, which not only affects the training effect of the model but also limits the model's generalization ability in practical applications.

[0006] In summary, existing methods for developing colonoscopy nursing plans, whether based on experience or model prediction, have significant limitations and deficiencies. Therefore, there is an urgent need to develop a novel colonoscopy nursing plan determination method and system that fully utilizes clinical data, considers the characteristics of input and output data, and rationally sets model training parameters to improve the accuracy and personalization of nursing plans. Summary of the Invention

[0007] In view of this, the present invention provides a method and system for determining a colonoscopy surgery nursing plan based on clinical data to solve the above problems.

[0008] A method for determining a colonoscopy surgery nursing plan based on clinical data specifically comprises the following steps:

[0009] Step S1, obtaining clinical data of the patient to be tested, wherein the clinical data includes personal information, biochemical examination report and preoperative psychological monitoring index information;

[0010] Step S2, obtaining a first feature vector based on the personal information and the biochemical examination report;

[0011] Step S3: input the first feature vector into the trained first model and output a first nursing plan; the learning rate of the first model is dynamically adjusted through a formula;

[0012] Step S4, obtaining the patient's stress score based on the preoperative psychological monitoring index information;

[0013] Step S5, obtaining a second eigenvector based on the first eigenvector and the patient's stress score;

[0014] Step S6: input the second feature vector into the trained second model and output a second nursing plan; the number of stacking layers of the second model is dynamically adjusted through a formula.

[0015] Furthermore, in step S2, a first feature vector is obtained based on the personal information and the biochemical examination report, specifically:

[0016] Step S21, performing index screening on the personal information based on the correlation coefficient between the personal information and key indicators of colonoscopy surgery to obtain a personal information vector;

[0017] Step S22, screening the biochemical examination report based on the correlation coefficient between the biochemical examination report and the key indicators of colonoscopy surgery to obtain a biochemical indicator vector;

[0018] Step S23: forming a first feature vector from the personal information vector and the biochemical indicator vector.

[0019] Furthermore, in step S21, the personal information is screened based on the correlation coefficient between the personal information and the key indicators of colonoscopy surgery, specifically:

[0020] Step S211, obtaining past medical history information in the personal information;

[0021] Step S212, calculating the correlation coefficient between each indicator in the past medical history information and the key indicators of colonoscopy surgery;

[0022] Step S213: if the correlation coefficient is less than or equal to the first threshold, retain the corresponding indicator; otherwise, delete the corresponding indicator;

[0023] In step S22, the biochemical examination report is screened for indicators based on the correlation coefficient between the biochemical examination report and the key indicators of colonoscopy surgery, specifically:

[0024] Step S221, obtaining abnormal items in the biochemical examination report;

[0025] Step S222, calculating the correlation coefficient between each abnormal item and the key index of colonoscopy surgery;

[0026] Step S223: If the correlation coefficient is greater than the second threshold, the corresponding indicator is retained; otherwise, the corresponding indicator is deleted.

[0027] Furthermore, the key indicators of colonoscopy surgery include: white blood cell count, red blood cell count, platelet count, prothrombin time, calprotectin, thrombin time, fibrinogen, alanine aminotransferase, aspartate aminotransferase, total bilirubin, direct bilirubin, urea nitrogen, creatinine, sodium ions, potassium ions, chloride ions, hepatitis B surface antigen, hepatitis C antibody, AIDS antibody and blood sugar.

[0028] Furthermore, in step S4, the patient's stress score is obtained based on the preoperative psychological monitoring index information, specifically:

[0029] Step S41, obtaining the actual value, standard value, maximum normal value and minimum normal value of each psychological monitoring indicator based on the preoperative psychological monitoring indicator information;

[0030] Step S42: Calculate the patient's stress score based on the psychological monitoring index data; the specific formula is:

[0031] ;

[0032] Among them, T is the stress score, N is the number of psychological monitoring indicators, k is the impact factor, T i实际值 is the actual measured value of the i-th indicator, T i标准值 is the standard value of the i-th indicator, T i最大值 is the maximum normal value of the i-th indicator, T i最小值 is the minimum normal value of the i-th indicator.

[0033] Furthermore, the first model is a convolutional neural network, and the learning rate adjustment formula is:

[0034] ;

[0035] in,

[0036] α t is the learning rate of the tth iteration;

[0037] α0 is the initial learning rate;

[0038] ω is the attenuation factor;

[0039] t is the current iteration number;

[0040] β is the learning rate adjustment factor;

[0041] ||e t || is the norm of the output error in the current iteration step;

[0042] ||Δx t ||² is the square norm of the difference between the current input feature and the input feature of the previous iteration;

[0043] σx² is the square of the standard deviation of the input feature;

[0044] ε is a positive constant.

[0045] Furthermore, the second model is an LSTM network, and the stacking layer number adjustment formula is:

[0046] ;

[0047] in:

[0048] L t is the number of stacking layers at the tth iteration;

[0049] L base is the original number of stacking layers;

[0050] γ is the stacking layer adjustment factor;

[0051] P prev is the loss value of the previous iteration;

[0052] P target is the preset target loss value;

[0053] ||Δx|| is the change in input data x between the current iteration and the previous iteration;

[0054] σx is the standard deviation of the input data x;

[0055] θ is a positive constant.

[0056] Furthermore, the first nursing plan includes:

[0057] How to popularize knowledge about colonoscopy, recommended diet, medication method, recommended water intake, contraindications, normal reactions and adverse reactions after medication, if described 3.

[0058] Furthermore, the second nursing plan includes:

[0059] Precautions during the operation, emotional soothing methods, breathing rhythm adjustment, abdominal massage methods and types of music to be played.

[0060] A colonoscopy surgery nursing plan determination system based on clinical data, the system adopts the colonoscopy surgery nursing plan determination method based on clinical data as described above, and specifically includes the following modules:

[0061] A clinical data acquisition module is used to obtain clinical data of the patient to be tested, including personal information, biochemical test reports, and preoperative psychological monitoring index information;

[0062] a first feature vector acquisition module, connected to the clinical data acquisition module, for acquiring a first feature vector based on the personal information and the biochemical examination report;

[0063] A first model is connected to the first feature vector acquisition module and is used to output a first nursing plan based on the first feature vector; the learning rate of the first model is dynamically adjusted through a formula;

[0064] a second eigenvector acquisition module, connected to the first eigenvector acquisition module, configured to acquire a patient stress score based on the preoperative psychological monitoring index information; and acquire a second eigenvector based on the first eigenvector and the patient stress score;

[0065] The second model is connected to the second feature vector acquisition module and is used to output a second nursing plan based on the second feature vector; the number of stacking layers of the second model is dynamically adjusted through a formula.

[0066] Compared with the prior art, the present invention has the following beneficial effects:

[0067] First, by integrating the patient's personal information, biochemical test reports, and psychological monitoring data, the present invention can construct an analysis vector that accurately reflects the patient's overall condition. This vector not only encompasses the patient's physiological condition but also reflects their psychological state, thus providing a scientific basis for formulating personalized and precise preoperative care plans. Compared with traditional care plans based on the experience and subjective judgment of medical staff, this approach is more scientific and objective.

[0068] Secondly, based on the acquired feature vectors, the present invention uses two models to output nursing plans for different periods of time. This not only improves the effectiveness and pertinence of the nursing plans, but also makes it easier for patients to accept and cooperate with nursing work, thereby improving the overall quality and efficiency of colonoscopy surgery care.

[0069] Third, by screening for correlation between personal information and biochemical test reports, the present invention effectively reduces the amount of data, reducing the complexity and time cost of data processing while also improving the accuracy and reliability of analysis results. By optimizing the nursing plan determination process, the present invention can more quickly develop personalized surgical care plans for patients, thereby improving the efficiency and satisfaction of medical services.

[0070] Fourthly, the present invention adaptively adjusts and optimizes the key parameters of the model based on the complexity, diversity and nonlinearity of clinical data, which not only improves the model's ability to interpret clinical data, but also further enhances the model's practicality and reliability in the formulation of colonoscopic surgery nursing plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0072] Figure 1 To identify a methodological flow chart for a colonoscopy care plan based on clinical data;

[0073] Figure 2 The patient acceptance curve of the generated nursing plan when different influencing factors are taken;

[0074] Figure 3 This is a nursing plan interface diagram generated in one embodiment of the present application;

[0075] Figure 4 Determine the system architecture for a colonoscopy care plan based on clinical data. DETAILED DESCRIPTION

[0076] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention are described clearly and completely below. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are also within the scope of protection of the present invention.

[0077] The present invention proposes a method and system for determining a colonoscopy nursing plan based on clinical data. To address the shortcomings of the existing technology, the present application obtains patient clinical data, obtains a first eigenvector and a second eigenvector based on the clinical data, inputs the first eigenvector into an improved CNN network, outputs a first nursing plan, and inputs the second eigenvector into an improved LSTM network, outputs a second nursing plan. The present invention constructs a precise analysis vector by fusing multi-dimensional patient data to provide a scientific basis for personalized surgical nursing plans. At the same time, it uses a dual model to improve the effectiveness and pertinence of the plan, optimizes the data processing process through correlation screening, and adaptively adjusts the model parameters to comprehensively improve the scientific nature, efficiency, patient acceptance, and quality of medical services of colonoscopy nursing.

[0078] The specific embodiments of the present invention are described below with reference to the accompanying drawings (tables).

[0079] Example 1

[0080] like Figure 1 As shown, the present invention proposes a method for determining a colonoscopy nursing plan based on clinical data, which specifically includes steps S1-S6:

[0081] Step S1, obtaining clinical data of the patient to be tested, wherein the clinical data includes personal information, biochemical examination report and preoperative psychological monitoring index information;

[0082] Personal information, including age, medical history, and allergy history, influences the personalized care plan and risk assessment. Biochemical test results, such as blood sugar and electrolyte balance, directly influence specific measures in the care plan, such as medication use and dietary adjustments. Preoperative psychological monitoring indicators directly impact the patient's compliance and anxiety level, which in turn influences the smooth progress and ultimate success of the colonoscopy. Therefore, comprehensive access to this data is crucial for developing a scientific and effective surgical care plan.

[0083] Existing techniques analyze this information based on physician experience, which can lead to subjective omissions or overemphasis of certain information, resulting in low accuracy and straining medical resources. This application uses this information as basic research data, ensuring comprehensiveness while avoiding subjective assumptions.

[0084] Step S2, obtaining a first feature vector based on the personal information and the biochemical examination report; specifically:

[0085] Step S21, based on the correlation coefficient between the personal information and the key indicators of colonoscopy surgery, the personal information is screened for indicators to obtain a personal information vector; the purpose of screening the indicators based on the correlation coefficient between the personal information and the key indicators of colonoscopy surgery is to select factors that are directly related to the surgery and have an important impact on the formulation of the nursing plan from a large amount of personal information, thereby constructing a concise and effective personal information vector to provide accurate data support for the subsequent formulation of the nursing plan.

[0086] Step S22, based on the correlation coefficient between the biochemical examination report and the key indicators of colonoscopy surgery, the biochemical examination report is screened to obtain a biochemical indicator vector; by analyzing the correlation coefficient between each indicator in the biochemical examination report and the key indicators of colonoscopy surgery, the biochemical indicators that are directly related to the surgery and postoperative care and have a significant impact are screened out to form a biochemical indicator vector to ensure that the formulation of the nursing plan can be based on the most relevant and critical biochemical data, thereby improving the pertinence and effectiveness of nursing.

[0087] Step S23: forming a first feature vector from the personal information vector and the biochemical indicator vector.

[0088] In step S21, the personal information is screened based on the correlation coefficient between the personal information and the key indicators of colonoscopy surgery, specifically:

[0089] Step S211, obtaining past medical history information in the personal information;

[0090] Step S212, calculating the correlation coefficient between each indicator in the past medical history information and the key indicators of colonoscopy surgery;

[0091] Step S213: if the correlation coefficient is less than or equal to the first threshold, retain the corresponding indicator; otherwise, delete the corresponding indicator;

[0092] In steps S211 to S213, by obtaining the medical history information in the personal information and calculating the correlation coefficient between the medical history information and the key indicators of colonoscopy surgery, the medical history information with low correlation with the key indicators of surgery is screened out and retained, while the highly correlated ones are deleted. In this way, the key indicators that have changed due to the medical history can be removed, the personal information vector can be streamlined, redundant information can be removed, and the accuracy and pertinence of the nursing plan can be ensured.

[0093] In step S22, the biochemical examination report is screened for indicators based on the correlation coefficient between the biochemical examination report and the key indicators of colonoscopy surgery, specifically:

[0094] Step S221, obtaining abnormal items in the biochemical examination report;

[0095] Step S222, calculating the correlation coefficient between each abnormal item and the key index of colonoscopy surgery;

[0096] Step S223: If the correlation coefficient is greater than the second threshold, the corresponding indicator is retained; otherwise, the corresponding indicator is deleted.

[0097] In steps S221 to S223, by identifying abnormal items in the biochemical examination report and calculating the correlation coefficients between these abnormal items and the key indicators of colonoscopy surgery, abnormal biochemical indicators that are highly correlated with the key indicators of surgery are retained, while indicators with low or insignificant correlation are eliminated. The purpose is to focus on key biochemical abnormalities and provide a strong basis for formulating targeted nursing plans.

[0098] The key indicators of colonoscopy surgery include: white blood cell count, red blood cell count, platelet count, prothrombin time, calprotectin, thrombin time, fibrinogen, alanine aminotransferase, aspartate aminotransferase, total bilirubin, direct bilirubin, urea nitrogen, creatinine, sodium ions, potassium ions, chloride ions, hepatitis B surface antigen, hepatitis C antibody, HIV antibody and blood sugar.

[0099] Common indices for intestinal disease examination were obtained, and the correlation coefficients between these indicators and the risk of colonoscopy were calculated. The obtained coefficient ranking is shown in Table 1:

[0100] Table 1 Correlation coefficient ranking table

[0101]

[0102] Indicators with correlation coefficients greater than a threshold are selected as key indicators for colonoscopy. In this embodiment, the threshold is 0.85, that is, indicators with correlation coefficients greater than or equal to 0.85 are selected as key indicators, while indicators with correlation coefficients less than 0.85 are selected as general indicators.

[0103] The selection of the threshold will affect the accuracy of the model. In other embodiments, different threshold values ​​are selected, and the accuracy of the model is different. This embodiment selects a threshold of 0.85 that gives the highest model accuracy.

[0104] The screening of the above key indicators takes into account the indicators that are critical to the nursing plan, greatly reduces the scope of indicators involved, reduces the amount of data, and improves calculation efficiency. It is crucial for evaluating patients' surgical tolerance, predicting surgical risks, and formulating postoperative care plans.

[0105] Step S3, inputting the first feature vector into the trained first model and outputting a first nursing plan;

[0106] The first model primarily processes the first eigenvector, which consists of a personal information vector and a biochemical indicator vector. These eigenvectors typically contain a large amount of numerical data, such as age, gender, and biochemical indicators. CNNs excel at processing numerical data and extracting features, especially when the data exhibits local correlation and spatial structure. Furthermore, the convolutional and pooling layers of CNNs can effectively extract features, reduce data volume, and improve computational efficiency.

[0107] The first model training method is specifically as follows:

[0108] Acquiring historical data of the first feature vector, the historical data including multiple groups of sample data consisting of personal information vectors and biochemical indicator vectors and first nursing plans corresponding to the sample data;

[0109] The neural network model is trained using the historical data of the first feature vector until a training end condition is met, thereby obtaining a trained first model.

[0110] When analyzing the first model, the applicant found that the input and output data had the following characteristics:

[0111] Input data: The first eigenvector, which consists of the patient's personal information vector and biochemical indicator vector, including the patient's age, gender, medical history, key indicators in the biochemical examination report, and other information.

[0112] Output data: First nursing plan, which reflects the nursing plan for the patient determined based on the patient's physiological condition and general nursing needs.

[0113] Because the input data for the first model includes multiple types of clinical information, these data may have complex correlations and nonlinear relationships. Therefore, as the model learns these data, it needs to continuously adjust weights to adapt to the complexity of the data. Therefore, real-time adjustment of the learning rate is necessary to optimize model performance, improve training efficiency, and adapt to the complexity of the data.

[0114] An embodiment of the present invention is based on the commonly used Adam optimizer and combines the characteristics of the first model to provide a formula for adaptive adjustment of the learning rate.

[0115] ;

[0116] in,

[0117] α t is the learning rate of the tth iteration;

[0118] α0 is the initial learning rate; it can be set to 0.001;

[0119] ω is the decay factor; it is used to control the decay rate of the learning rate over time;

[0120] t is the current iteration number;

[0121] β is the learning rate adjustment factor; it is used to control the influence of output error on learning rate adjustment;

[0122] ||e t || is the norm of the output error in the current iteration step;

[0123] ||Δx t ||² is the square norm of the difference between the current input feature and the input feature of the previous iteration, reflecting the degree of change of the input feature;

[0124] σx² is the square of the standard deviation of the input feature, which is used to normalize the degree of change of the input feature;

[0125] ε is a positive constant used to prevent the denominator from being zero.

[0126] The learning rate adjustment formula dynamically adjusts the learning rate to optimize model training performance by comprehensively considering multiple factors, including the current number of iterations, the output error norm, and the change in input features. This formula can improve the model's ability to interpret clinical data, enhancing its practicality and reliability in developing colonoscopy nursing plans, thereby improving the scientific nature, efficiency, and patient acceptance of nursing plans.

[0127] The first nursing plan includes:

[0128] Popularization methods of colonoscopy surgery knowledge, recommended diet, medication methods, recommended water intake, contraindication types, normal reactions and adverse reactions after medication.

[0129] Colonoscopy knowledge dissemination methods: Explain in detail to patients the purpose, procedure, possible risks and benefits, and postoperative precautions of colonoscopy. This can be done through oral explanations, written materials, video demonstrations, and other methods to ensure patients fully understand and actively cooperate with the procedure.

[0130] Recommended Diet: Before surgery, patients need to follow specific dietary guidelines. These include abstaining from liquid, low-residue, or semi-liquid diets starting three days before surgery, taking a laxative to cleanse the bowels the night before surgery or performing a cleansing enema on the day of the procedure, and abstaining from breakfast. After surgery, patients should adhere to a light, easily digestible diet, avoiding irritating foods such as liquid or semi-liquid foods (rice porridge, noodle soup, etc.), high-protein foods (eggs, tofu, etc.), and vitamin-rich foods (cooked vegetable and fruit purees, etc.).

[0131] Medication administration: Depending on the surgical requirements and the patient's specific condition, the doctor will prescribe appropriate medications, such as bowel cleansers, anti-foaming agents, and antibiotics. Nurses should provide patients with detailed information on the medication's name, dosage, time of administration, and method of administration, and emphasize precautions during medication administration, such as avoiding certain foods or beverages.

[0132] Recommended water intake: Before surgery, patients need to drink plenty of water to cleanse their bowels. Drinking small amounts in small portions, adjusting the water temperature, and varying the taste can help alleviate hydration difficulties. Nurses should closely monitor patients' water intake to ensure they complete bowel preparation on time.

[0133] Contraindications: Colonoscopy is not suitable for all patients. Certain contraindications exist, such as severe cardiopulmonary disease, pregnancy, and suspected intestinal perforation. Before surgery, the doctor should inquire in detail about the patient's medical history and physical condition to ensure that the patient meets the surgical requirements and avoid surgical risks.

[0134] Normal and adverse reactions to medication: Patients may experience normal reactions during medication use, such as abdominal distension, abdominal pain, and increased bowel movements. Nurses should explain the causes and countermeasures of these reactions to patients to alleviate their anxiety and restlessness. Nurses should also closely monitor patients' medication use and promptly identify and address adverse reactions, such as allergic reactions and severe abdominal pain.

[0135] The First Care Plan is a comprehensive and meticulous nursing program designed to provide patients with comprehensive preoperative preparation and postoperative guidance. By providing surgical knowledge, recommending diet and medication, guiding water intake, identifying contraindications, and monitoring medication reactions, we ensure patients complete preoperative bowel cleansing safely and smoothly, fully preparing for colonoscopy and promoting postoperative recovery.

[0136] Step S4: Obtaining a patient stress score based on the preoperative psychological monitoring indicator information. During medical procedures such as colonoscopy, the patient's psychological state, particularly stress, is an important consideration. Stress not only reflects the patient's anxiety and fear of surgery but can also directly impact surgical outcomes and postoperative recovery. High stress levels can increase the patient's heart rate and blood pressure, increasing surgical risk and hindering postoperative recovery. Therefore, accurately assessing the patient's stress level and implementing appropriate nursing interventions are crucial for ensuring smooth surgery and a speedy recovery for the patient.

[0137] Specifically:

[0138] Step S41, obtaining the actual value, standard value, maximum normal value and minimum normal value of each psychological monitoring indicator based on the preoperative psychological monitoring indicator information;

[0139] Step S42: Calculate the patient's stress score based on the psychological monitoring index data; the specific formula is:

[0140] ;

[0141] Among them, T is the tension score, N is the number of psychological monitoring indicators, and k is the influence factor used to control the growth rate of the score with the degree of deviation. i实际值 is the actual measured value of the i-th indicator, T i标准值 is the standard value of the i-th indicator, T i最大值 is the maximum normal value of the i-th indicator, T i最小值 is the minimum normal value of the i-th indicator.

[0142] The psychological monitoring indicator information in this application can select indicators related to psychological state, reflecting the multi-dimensional data of the patient's preoperative psychological state, including physiological indicators and biochemical indicators.

[0143] Physiological indicators include heart rate, skin conductance level (SCL), blood pressure, respiratory rate, heart rate variability (HRV), etc.

[0144] Biochemical indicators include cortisol (saliva / serum), epinephrine / norepinephrine (plasma), serotonin (serum), C-reactive protein (CRP), blood glucose (fasting), etc.

[0145] In one embodiment, it is verified through multiple groups of clinical experiments that different values ​​of k have different effects on the stress score, thereby affecting the output results of the model.

[0146] When the k value is small, such as k=5, the score is less sensitive to indicator deviation, a small deviation from the standard value has a weaker impact on the total score, and the score distribution is flatter; the generated nursing plan is more conservative, and intervention measures are only taken for tension states with significant deviations. It is suitable for patient groups with less fluctuation in psychological state.

[0147] When the k value is large, such as k=8, the sensitivity is extremely high, and a small deviation can lead to a large jump in the score. The score of extreme values ​​saturates quickly, which may amplify the impact of noise or short-term fluctuations. The nursing plan may be too radical and needs to be verified in combination with other indicators to avoid misjudgment. It is suitable for close monitoring scenarios of high-risk patients.

[0148] In this embodiment, through multiple clinical experiments, it was verified that when k=6.7, the score can not only effectively capture the patient's anxiety characteristics, but also maintain a high degree of stability. When k=6.7, the generated nursing plan has a patient acceptance rate of 93%. The test results are as follows Figure 2 As shown in Table 2:

[0149] Table 2 Patients' acceptance of nursing plans under different influencing factor values

[0150]

[0151] From the above table and Figure 2 By combining the dynamic characteristics of clinical data with patient feedback, and using cross-validation and ROC curve analysis, we determined that k = 6.7 was the optimal solution for balancing sensitivity and stability. This value not only significantly improved the personalization of care plans but also ensured the model's robustness in complex clinical scenarios.

[0152] In this embodiment, the stress scoring formula fully considers multiple psychological monitoring indicators and is easy to obtain. It has the advantages of comprehensiveness, objectivity, sensitivity, comparability, and ease of operation. It can provide medical staff with accurate and reliable assessment results, thereby guiding them to take appropriate nursing measures for intervention.

[0153] Step S5, obtaining a second eigenvector based on the first eigenvector and the patient's stress score;

[0154] By incorporating patient stress scores, we can more accurately understand and process the meaning and usage of medical terminology within a patient's specific psychological state, thereby improving the accuracy of medical term standardization. Combining the first eigenvector with information about the patient's psychological state creates a more comprehensive dataset, providing more valuable information for subsequent data analysis and mining.

[0155] Step S6, inputting the second feature vector into the trained second model and outputting a second nursing plan;

[0156] The second model not only processes the first eigenvector but also considers the patient's stress score, involving time series data (because psychological states can change over time). LSTM performs well in processing time series data and can capture temporal and long-term dependencies in the data.

[0157] The second model training method is specifically as follows:

[0158] Acquiring historical data of the second eigenvector, the historical data including multiple groups of sample data consisting of the first eigenvector and the tension score and second nursing plans corresponding to the sample data;

[0159] The neural network model is trained using the historical data of the second eigenvector until a training end condition is met, thereby obtaining a trained second model.

[0160] When analyzing the second model, the applicant found that the input and output data had the following characteristics:

[0161] Input data characteristics: The input of the second model includes the first eigenvector (personal information and biochemical test reports) and the patient's stress score, which is a multidimensional eigenvector; and the patient's psychological state and stress will change over time, especially during preoperative preparation.

[0162] Output data characteristics: The output is a personalized care plan determined by the second eigenvector, which requires the model to accurately capture subtle differences in the input data and make corresponding output adjustments.

[0163] The number of LSTM stacking layers has the following characteristics: stacking multiple LSTM layers can increase the complexity of the model, enabling it to learn more complex feature representations and data relationships; by adjusting the number of LSTM stacking layers in real time, the complexity and generalization ability of the model can be balanced during the training process; by adjusting the number of LSTM stacking layers, computing efficiency and resource utilization can be optimized while ensuring model performance.

[0164] Therefore, combining the input and output data characteristics of the second model, calculating the number of LSTM stacking layers can improve the complexity of the model, avoid overfitting and underfitting, and optimize performance and efficiency, which helps the model to more accurately capture the features and information in the input data, thereby outputting more personalized care plans.

[0165] The second model is a stacking layer adjustment formula:

[0166] ;

[0167] in:

[0168] L t is the number of stacked layers of LSTM at the tth iteration or evaluation;

[0169] L base The number of basic layers indicates the default number of stacked layers of LSTM in the absence of performance feedback or under specific conditions;

[0170] γ is the stacking layer adjustment factor, which is used to control the speed and amplitude of the layer adjustment and can be fine-tuned according to actual needs;

[0171] P prev To represent the performance indicators of the model at the last iteration or evaluation (such as accuracy, loss value, etc.);

[0172] P target is the preset target performance indicator, which indicates the performance level that the model is expected to achieve;

[0173] ||Δx|| is the change in the input data x between the current iteration and the previous iteration, reflecting the dynamic nature of the input data.

[0174] σx is the standard deviation of the input data x or some stability measure, which is used to normalize the variation of the input data.

[0175] θ is a small positive number used to prevent the denominator from being zero and increase the stability of the formula.

[0176] The stacking layer adjustment formula dynamically adjusts the number of stacking layers of the LSTM network by combining parameters such as the loss value of the previous iteration, the preset target loss value, the input data change and the standard deviation, thereby optimizing the complexity and generalization ability of the model, effectively improving the model's adaptability to clinical data, and being able to output more personalized colonoscopy surgery care plans, thereby improving the overall quality and efficiency of care.

[0177] The second nursing plan includes intraoperative precautions, emotional comfort methods, breathing rhythm adjustment, abdominal massage methods, and music types:

[0178] Precautions during the operation: During the operation, the patient should maintain a normal body posture and avoid moving around. Emotional comfort, breathing rhythm adjustment, music playing, etc. can be used to assist the patient in successfully completing the colonoscopy operation.

[0179] Emotional comfort methods: Use gentle words and patient explanations to soothe the patient's emotions, help them relax, and reduce tension and fear; use professional psychological intervention techniques, such as deep breathing guidance and mindfulness meditation, to help patients relax and improve their tolerance for surgery;

[0180] Breathing rhythm adjustment: During the colonoscopy, patients are instructed to practice deep breathing exercises and adjust their breathing rhythm to relax their body and reduce tension. This helps lower physiological indicators such as heart rate and blood pressure, and improves the safety of the procedure.

[0181] Music Type: During a colonoscopy or postoperative recovery period, playing soft, soothing music can help reduce anxiety, increase pain thresholds, and promote relaxation. Healthcare professionals can choose music appropriate for the patient's care plan. For example, consider light music, classical music, or nature sounds, all of which are known to soothe and relax the patient.

[0182] Postoperative abdominal massage: After a colonoscopy, patients may experience abdominal distension, abdominal pain, and other discomfort. Medical staff can guide patients through appropriate abdominal massages based on the model's output to promote intestinal motility and relieve symptoms such as bloating and constipation. Patients and their families can also follow the model's output, providing appropriate techniques and strength to avoid causing additional pain or discomfort to the patient due to inappropriate massage methods.

[0183] The application of the Second Care Plan during colonoscopy surgery aims to provide patients with a comprehensive and meticulous intraoperative and postoperative care experience. By focusing on intraoperative precautions, emotional comfort, breathing regulation, abdominal massage, and music therapy, it can promote patients' physical and mental recovery and improve the safety and comfort of the surgery.

[0184] In one embodiment, the patient information is as follows:

[0185] Gender: male, age: 62 years old, elementary school graduate, patient tension score: T=0.82 (significant anxiety);

[0186] Biochemical abnormalities: high blood sugar (fasting blood sugar 8.5mmol / L), low platelet count (120×10 9 / L);

[0187] Past medical history: hypertension, diabetes.

[0188] The first and second nursing plans output according to the patient's condition are as follows:

[0189] The first nursing plan is:

[0190] 1. Popularization of surgical knowledge:

[0191] Use easy-to-understand pictures or animated videos (no text or a small amount of large text) to explain the colonoscopy process, focusing on "painless", "safe", and "doctor's presence throughout the process".

[0192] I repeatedly emphasized verbally: "The examination is like taking a nap, it's painless, the doctor will do the procedure gently, and you can go home and rest after it's done."

[0193] 2. Recommended diet:

[0194] 3 days before surgery:

[0195] Breakfast: white porridge + steamed egg (without oil or salt);

[0196] Lunch: Soft noodles (no vegetables, lightly seasoned with soy sauce);

[0197] Dinner: rice porridge (rice crushed and cooked into a paste).

[0198] Prohibited: Rice, vegetables, fruits, beans.

[0199] 1 day before surgery:

[0200] Drink only clear liquids: light salt water, filtered clear soup (without residue), and sugar-free jelly.

[0201] On the day of surgery:

[0202] Completely fast and stop drinking water 4 hours before surgery.

[0203] 3. How to take the medicine:

[0204] Intestinal cleansers:

[0205] Drink the "big bottle of medicine" in 4 times, half a cup (about 250ml) each time, with an interval of 15 minutes. You can hold a candy in your mouth after drinking to prevent nausea.

[0206] Blood sugar control:

[0207] The dose of insulin injected the night before surgery was adjusted by the physician to ensure that the fasting blood glucose was ≤7.0 mmol / L.

[0208] Figure 3 This is the generated nursing plan interface diagram.

[0209] 4. Please use popular taboo prompts, such as:

[0210] If you have low platelet count, you need to take platelet-replenishing medicine before checking to avoid bleeding.

[0211] Measure your blood pressure before the examination. If the high blood pressure is over 160, you need to take medicine to lower your blood pressure.

[0212] 5. Adverse reaction warning:

[0213] It is normal to feel bloated and have diarrhea after taking medicine. Only after you have a complete bowel movement can you get a clear diagnosis.

[0214] If you feel dizzy or have cold sweats, take a candy immediately and call a nurse.

[0215] The second nursing plan is:

[0216] 1. Precautions during surgery:

[0217] During the examination, you should lie on your left side with your knees hugging your chest. The doctor will pat your shoulders and remind you not to move.

[0218] 2. Emotional soothing methods:

[0219] Before surgery:

[0220] Arrange for family members to accompany the patient, and the nurse repeatedly comforted them in dialect: "Don't be afraid, it will be fine soon, the doctor's skills are very good."

[0221] During surgery:

[0222] The nurse held the patient's hand and said every 2 minutes: "Well done, it will be over soon!"

[0223] 3. Breathing rhythm adjustment:

[0224] Teach the patient to "breathe in slowly through the nose (count 1-2-3) and breathe out slowly through the mouth (count 1-2-3-4)" and practice following the nurse's gestures.

[0225] 4. Music type:

[0226] Choose classic songs from the 60s and 70s (such as Teresa Teng's "Sweet Honey"), light music (piano piece "Autumn Whispers"), and turn the volume to soft.

[0227] 5. Postoperative abdominal massage:

[0228] Family members are advised to "rub the area around the belly button clockwise" with movements as gentle as "touching a kitten", three times a day, each time for five minutes.

[0229] like Figure 4 As shown, an embodiment of the present invention further proposes a colonoscopy surgery nursing plan determination system based on clinical data, using the colonoscopy surgery nursing plan determination method based on clinical data as described in any of the above items, including the following modules:

[0230] A clinical data acquisition module is used to obtain clinical data of the patient to be tested, including personal information, biochemical test reports, and preoperative psychological monitoring index information;

[0231] a first feature vector acquisition module, connected to the clinical data acquisition module, for acquiring a first feature vector based on the personal information and the biochemical examination report;

[0232] A first model is connected to the first feature vector acquisition module and is used to output a first nursing plan based on the first feature vector; the learning rate of the first model is dynamically adjusted through a formula;

[0233] a second eigenvector acquisition module, connected to the first eigenvector acquisition module, configured to acquire a patient stress score based on the preoperative psychological monitoring index information; and acquire a second eigenvector based on the first eigenvector and the patient stress score;

[0234] The second model is connected to the second feature vector acquisition module and is used to output a second nursing plan based on the second feature vector; the number of stacking layers of the second model is dynamically adjusted through a formula.

[0235] An embodiment of the present invention further provides an electronic device, comprising:

[0236] processor and memory;

[0237] The processor is configured to execute the steps of the method for determining a colonoscopy surgery care plan based on clinical data as described above by calling the program or instruction stored in the memory.

[0238] An embodiment of the present invention further provides a computer-readable storage medium, which includes computer program instructions, and the computer program instructions enable a computer to execute the steps of a method for determining a colonoscopy surgery care plan based on clinical data as described in any one of the above items.

[0239] The computer-readable storage medium may be any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (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 thereof.

[0240] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A method for determining a colonoscopy nursing plan based on clinical data, characterized in that: The steps include: Step S1, obtaining clinical data of the patient to be tested, wherein the clinical data includes personal information, biochemical examination report and preoperative psychological monitoring index information; Step S2: obtaining a first feature vector based on the personal information and the biochemical examination report; the first feature vector is composed of a personal information vector and a biochemical indicator vector; the personal information vector is obtained by screening the personal information based on the correlation coefficient between the personal information and key indicators of colonoscopy surgery; the key indicators of colonoscopy surgery include: white blood cell count, red blood cell count, platelet count, prothrombin time, calprotectin, thrombin time, fibrinogen, alanine aminotransferase, aspartate aminotransferase, total bilirubin, direct bilirubin, urea nitrogen, creatinine, sodium ion, potassium ion, chloride ion, hepatitis B surface antigen, hepatitis C antibody, HIV antibody, and blood glucose; Step S3: input the first feature vector into the trained first model and output a first nursing plan; the learning rate of the first model is dynamically adjusted through a formula; Step S4, obtaining the patient's stress score based on the preoperative psychological monitoring index information; specifically: Step S41, obtaining the actual value, standard value, maximum normal value and minimum normal value of each psychological monitoring indicator based on the preoperative psychological monitoring indicator information; Step S42: Calculate the patient's stress score based on the psychological monitoring index data; the specific formula is: ； Among them, T is the stress score, N is the number of psychological monitoring indicators, k is the impact factor, T i实际值 is the actual measured value of the i-th indicator, T i标准值 is the standard value of the i-th indicator, T i最大值 is the maximum normal value of the i-th indicator, T i最小值 is the minimum normal value of the i-th indicator; the impact factor k of patients undergoing colonoscopy surgery is 6.7; Step S5, obtaining a second eigenvector based on the first eigenvector and the patient's stress score; Step S6: input the second feature vector into the trained second model and output a second nursing plan; the number of stacking layers of the second model is dynamically adjusted through a formula.

2. A method for determining a colonoscopy nursing plan based on clinical data according to claim 1, characterized in that: In step S2, a first feature vector is obtained based on the personal information and the biochemical examination report, specifically: Step S21, performing index screening on the personal information based on the correlation coefficient between the personal information and key indicators of colonoscopy surgery to obtain a personal information vector; Step S22, screening the biochemical examination report based on the correlation coefficient between the biochemical examination report and the key indicators of colonoscopy surgery to obtain a biochemical indicator vector; Step S23: forming a first feature vector from the personal information vector and the biochemical indicator vector.

3. The method for determining a colonoscopy nursing plan based on clinical data according to claim 2, characterized in that: In step S21, the personal information is screened based on the correlation coefficient between the personal information and the key indicators of colonoscopy surgery, specifically: Step S211, obtaining past medical history information in the personal information; Step S212, calculating the correlation coefficient between each indicator in the past medical history information and the key indicators of colonoscopy surgery; Step S213: if the correlation coefficient is less than or equal to the first threshold, retain the corresponding indicator; otherwise, delete the corresponding indicator; In step S22, the biochemical examination report is screened for indicators based on the correlation coefficient between the biochemical examination report and the key indicators of colonoscopy surgery, specifically: Step S221, obtaining abnormal items in the biochemical examination report; Step S222, calculating the correlation coefficient between each abnormal item and the key index of colonoscopy surgery; Step S223: If the correlation coefficient is greater than the second threshold, the corresponding indicator is retained; otherwise, the corresponding indicator is deleted.

4. The method for determining a colonoscopy nursing plan based on clinical data according to claim 1, characterized in that: The first model is a convolutional neural network, and the learning rate adjustment formula is: ； in, α t is the learning rate of the tth iteration; α0 is the initial learning rate; ω is the attenuation factor; t is the current iteration number; β is the learning rate adjustment factor; ||e t || is the norm of the output error in the current iteration step; ||Δx t ||² is the square norm of the difference between the current input feature and the input feature of the previous iteration; σx² is the square of the standard deviation of the input feature; ε is a positive constant.

5. The method for determining a colonoscopy nursing plan based on clinical data according to claim 1, characterized in that: The second model is an LSTM network, and the adjustment formula for the number of stacked layers is: ； in: L t is the number of stacking layers at the tth iteration; L base is the original number of stacking layers; γ is the stacking layer adjustment factor; P prev is the loss value of the previous iteration; P target is the preset target loss value; ||Δx|| is the change in input data x between the current iteration and the previous iteration; σx is the standard deviation of the input data x; θ is a positive constant.

6. The method for determining a colonoscopy nursing plan based on clinical data according to claim 1, characterized in that: The first nursing plan includes: Popularization methods of colonoscopy surgery knowledge, recommended diet, medication methods, recommended water intake, contraindication types, normal reactions and adverse reactions after medication.

7. The method for determining a colonoscopy nursing plan based on clinical data according to claim 1, characterized in that: The second care plan includes: Precautions during the operation, emotional soothing methods, breathing rhythm adjustment, abdominal massage methods and types of music to be played.

8. A colonoscopy surgery nursing plan determination system based on clinical data, characterized in that: The system adopts the method for determining a colonoscopy surgery nursing plan based on clinical data according to any one of claims 1 to 7, and specifically includes the following modules: A clinical data acquisition module is used to obtain clinical data of the patient to be tested, including personal information, biochemical test reports, and preoperative psychological monitoring index information; a first feature vector acquisition module, connected to the clinical data acquisition module, for acquiring a first feature vector based on the personal information and the biochemical examination report; A first model is connected to the first feature vector acquisition module and is used to output a first nursing plan based on the first feature vector; the learning rate of the first model is dynamically adjusted through a formula; a second eigenvector acquisition module, connected to the first eigenvector acquisition module, configured to acquire a patient stress score based on the preoperative psychological monitoring index information; and acquire a second eigenvector based on the first eigenvector and the patient stress score; The second model is connected to the second feature vector acquisition module and is used to output a second nursing plan based on the second feature vector; the number of stacking layers of the second model is dynamically adjusted through a formula.

Images