A method and system for postoperative nursing management of cardiac surgery

Abstract

The present invention is applicable to the field of medical rehabilitation, and provides a method and system for postoperative care management of cardiac surgery. The system includes: an intelligent monitoring and analysis module, a sleep posture optimization module, a secondary acquisition module, and a data storage and analysis module. The postoperative care management method of cardiac surgery comprehensively analyzes key indicators such as scar status, position offset, and shape distortion, and deeply explores the impact of sleep posture on wound healing, showing significant advantages. This method can not only monitor the patient's sleep quality and posture in real time, but also accurately evaluate the actual impact of sleep posture on scar recovery in combination with the dynamic changes of scars. Through this meticulous analysis, medical staff can gain valuable insights into the patient's recovery process, thereby formulating more accurate and personalized care strategies.

Description

Technical Field

[0001] The present invention belongs to the field of medical rehabilitation, and in particular relates to a method and system for postoperative nursing management of cardiac surgery. Background Art

[0002] Wound care after cardiac surgery is an important part of medical rehabilitation and involves keeping the wound clean, preventing infection, managing pain, monitoring the healing process, providing nutritional support, guiding appropriate activities, providing psychological support, and educating patients and their families. These comprehensive measures are designed to promote rapid and complication-free wound healing, improve the patient's quality of life, and help them smoothly return to daily activities.

[0003] Existing technologies often use universal standards to evaluate the impact of sleeping posture on wound healing, and fail to conduct personalized assessments based on individual differences such as the patient's specific scar status, positional displacement, and shape distortion. And they do not take into account the differences in sleeping postures among different patients. For example, some patients may require a specific sleeping posture to promote wound healing due to the particularity of their body structure or surgical site, and universal recommendations may not meet these special needs. This results in the nursing recommendations not being suitable for some patients, thus affecting the effectiveness of wound healing. Summary of the invention

[0004] The purpose of the present invention is to provide a method for postoperative care management of cardiac surgery, aiming to solve the technical problems existing in the prior art identified in the background technology.

[0005] The present invention is implemented as follows: a method for postoperative nursing management of cardiac surgery, the method comprising:

[0006] Monitor the patient's sleep quality, sleep cycle, sleep posture, scar recovery and physical sign data in real time, and analyze whether the patient's sleep posture has a negative impact on scar recovery;

[0007] According to the current scar status and historical scar change pictures, the scar recovery trend is judged, the scar misalignment is analyzed, and sleeping posture optimization suggestions are given based on the analysis results;

[0008] After giving suggestions for optimizing sleeping posture, the patient's scar status is collected again to determine the scar recovery and dislocation;

[0009] Store all collected data and analysis results, and generate data analysis reports.

[0010] As a further solution of the present invention, the analysis of whether the patient's sleeping posture has a negative impact on scar recovery includes:

[0011] Monitor the patient's sleep quality, sleep cycle and sleep posture in real time, analyze the patient's sleep pattern, identify the duration and proportion of deep sleep, light sleep and REM sleep, as well as body movements during sleep;

[0012] Obtain changes in scar color, shape and texture, and assess scar healing progress;

[0013] Based on the body motion data during sleep, body motion features are extracted, and scar features are extracted from scar images to analyze the correlation between sleeping posture and scar recovery.

[0014] As a further solution of the present invention, the method of judging scar recovery trend and analyzing scar dislocation at the same time, and providing sleeping posture optimization suggestions based on the analysis results, includes:

[0015] Obtain scar images at each time period, and evaluate scar recovery trends based on scar feature changes;

[0016] Identify the positional deviation and shape distortion of scars, and provide sleeping posture optimization suggestions based on the correlation results between sleeping posture and scar recovery.

[0017] As a further solution of the present invention, the second collection of the patient's scar status and determination of scar recovery and dislocation status include:

[0018] Secondary acquisition of scar images of patients and extraction of secondary scar features;

[0019] Combined with the secondary scar features, they are compared with historical scars, including scar feature comparison and scar position offset and shape distortion comparison, to determine the scar recovery progress and whether the sleeping posture optimization suggestions given have achieved positive scar recovery.

[0020] As a further solution of the present invention, the storage of all collected data and analysis results and the generation of a data analysis report include:

[0021] Based on the scar recovery progress and sleeping posture optimization data, a recovery report for the patient is generated;

[0022] Visualize the data in the recovery report and generate charts.

[0023] Another object of the present invention is to provide a cardiac surgery postoperative care management system, the system comprising:

[0024] Intelligent monitoring and analysis module, used to monitor the patient's sleep quality, sleep cycle, sleep posture, scar recovery and physical sign data in real time, and analyze whether the patient's sleep posture has a negative impact on scar recovery;

[0025] The sleeping posture optimization module is used to determine the scar recovery trend based on the current scar status and historical scar change pictures, analyze the scar misalignment, and provide sleeping posture optimization suggestions based on the analysis results;

[0026] The secondary collection module is used to collect the patient's scar status for the second time after giving the sleeping posture optimization suggestion, and to judge the scar recovery and dislocation;

[0027] The data storage and analysis module is used to store all collected data and analysis results, and generate data analysis reports.

[0028] As a further solution of the present invention, the intelligent monitoring and analysis module includes:

[0029] Sleep monitoring unit, used to monitor the patient's sleep quality, sleep cycle and sleep posture in real time, analyze the patient's sleep pattern, identify the duration and proportion of deep sleep, light sleep and REM sleep, and body movements during sleep;

[0030] Scar monitoring unit, used to obtain scar color, shape and texture changes and evaluate scar healing progress;

[0031] The scar recovery impact analysis unit is used to extract body motion features based on body motion data during sleep, extract scar features from scar images, and analyze the correlation between sleeping posture and scar recovery.

[0032] As a further solution of the present invention, the sleeping posture optimization module includes:

[0033] Scar status evaluation unit, used to obtain scar images at each time period, and evaluate scar recovery trends based on scar feature changes;

[0034] The scar recovery optimization unit is used to identify the position offset and shape distortion of the scar, and give sleeping posture optimization suggestions based on the correlation results between sleeping posture and scar recovery.

[0035] As a further solution of the present invention, the secondary acquisition module includes:

[0036] An image secondary acquisition unit, used for secondary acquisition of scar images of patients and extraction of secondary scar features;

[0037] The scar recovery evaluation unit is used to combine the secondary scar features and compare them with historical scars, including scar feature comparison and scar position offset and shape distortion comparison, to determine the scar recovery progress and whether the sleeping posture optimization suggestions given have achieved positive scar recovery.

[0038] As a further solution of the present invention, the data storage and analysis module includes:

[0039] A report generating unit, for generating a recovery report for the patient based on scar recovery progress and sleep posture optimization data;

[0040] The data visualization unit is used to visualize the data in the recovery report and generate charts.

[0041] The beneficial effects of the present invention are:

[0042] This postoperative care management method for cardiac surgery comprehensively analyzes key indicators such as scar status, position deviation, and shape distortion, and deeply explores the impact of sleeping posture on wound healing, showing significant advantages. This method can not only monitor the patient's sleep quality and posture in real time, but also accurately evaluate the actual impact of sleeping posture on scar recovery in combination with the dynamic changes of scars. Through this meticulous analysis, medical staff can gain valuable insights into the patient's recovery process, thereby formulating more accurate and personalized care strategies.

[0043] In addition, the dynamic evaluation mechanism of the method allows medical staff to adjust the sleep posture optimization suggestions in a timely manner based on the real-time data of scar recovery, ensuring that these suggestions are always consistent with the patient's recovery needs. This flexibility and adaptability greatly improves the effectiveness of nursing measures, helps accelerate the wound healing process, and reduces the risk of complications. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A flowchart of a cardiac surgery postoperative nursing management method provided by an embodiment of the present invention;

[0045] Figure 2 A flow chart for analyzing whether a patient's sleeping posture has a negative impact on scar recovery provided by an embodiment of the present invention;

[0046] Figure 3 A flowchart for determining scar recovery trends, analyzing scar dislocation, and providing sleep posture optimization suggestions based on the analysis results provided by an embodiment of the present invention;

[0047] Figure 4 A flowchart of a second collection of a patient's scar status and determination of scar recovery and dislocation provided in an embodiment of the present invention;

[0048] Figure 5 A flowchart for storing all collected data and analysis results and generating a data analysis report provided by an embodiment of the present invention;

[0049] Figure 6 A structural block diagram of a cardiac surgery postoperative care management system provided by an embodiment of the present invention;

[0050] Figure 7A structural block diagram of an intelligent monitoring and analysis module provided in an embodiment of the present invention;

[0051] Figure 8 A structural block diagram of a sleep posture optimization module provided in an embodiment of the present invention;

[0052] Fig. 9 A structural block diagram of a secondary acquisition module provided in an embodiment of the present invention;

[0053] Fig.10 A structural block diagram of a data storage and analysis module provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0055] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.

[0056] Figure 1 A flowchart of a postoperative nursing management method for cardiac surgery provided by an embodiment of the present invention is shown in FIG. Figure 1 A method for postoperative care management of cardiac surgery is shown, the method comprising:

[0057] S100 monitors the patient's sleep quality, sleep cycle, sleep posture, scar recovery and physical sign data in real time, and analyzes whether the patient's sleep posture has a negative impact on scar recovery;

[0058] In this step, by real-time monitoring of the patient's sleep quality, sleep cycle, sleep posture and scar recovery, a scientific basis is provided for subsequent nursing decisions. This step uses high-precision sleep monitoring equipment and image acquisition equipment to comprehensively record the patient's sleep status and scar changes. Through image processing and machine learning algorithms, the color, shape, texture and other characteristics of the scar are analyzed, and the body movement characteristics during sleep are extracted. In addition, this step also establishes a regression model to analyze the relationship between sleep posture characteristics and scar recovery indicators, determine the degree of influence of sleep posture characteristics on scar recovery, and provide a scientific basis for sleep posture optimization.

[0059] This step has the ability to monitor and analyze comprehensively, ensuring the integrity and accuracy of the data, and providing a solid foundation for the formulation of personalized care plans. Through scientific data analysis methods, such as regression analysis, the correlation between sleep posture and scar recovery can be accurately identified, improving the pertinence and effectiveness of care. In addition, automated and intelligent monitoring and analysis greatly improves care efficiency and reduces the workload of medical staff. At the same time, by optimizing the patient's sleep posture, it promotes scar recovery and improves the patient's quality of life.

[0060] S200, based on the current scar status and historical scar change pictures, determines the scar recovery trend and analyzes the scar misalignment, and gives sleeping posture optimization suggestions based on the analysis results;

[0061] In this step, the scar recovery trend is determined based on the current scar status and historical scar change pictures, and sleeping posture optimization suggestions are given. This step evaluates the scar recovery progress by regularly taking photos of the patient's scars using high-resolution image acquisition equipment, and using image processing and machine learning algorithms to analyze the scar's color, shape, and texture changes. At the same time, through image comparison and feature matching technology, the scar's position offset and shape distortion are identified, the cause of scar misalignment is analyzed, and combined with the regression analysis results in the previous step, the degree of influence of sleeping posture characteristics on scar recovery is determined, and specific sleeping posture optimization suggestions are given.

[0062] This step can timely detect trends and problems in scar recovery and provide real-time support for nursing decisions. By providing personalized nursing advice and based on the correlation analysis between scar characteristics and sleeping posture, targeted sleeping posture optimization suggestions can be provided to each patient to improve the pertinence and effectiveness of nursing. In addition, automated and intelligent image analysis has greatly improved nursing efficiency and reduced the workload of medical staff. At the same time, by optimizing the patient's sleeping posture, it promotes scar recovery and improves the patient's quality of life. Specific sleeping posture optimization recommendations include advising patients to adopt a side-lying position, especially the left side, use pillows to support the knees and abdomen, avoid compressing scars, change postures regularly, and reduce body movement and other measures to promote rapid recovery of patients.

[0063] S300, after giving sleeping posture optimization suggestions, collects the patient's scar status for the second time to determine the scar recovery and dislocation;

[0064] This step is responsible for collecting the patient's scar status again after implementing the sleep posture optimization suggestions to determine the scar recovery and dislocation. This step uses a high-resolution image acquisition device to take photos of the patient's scars again, and uses image processing technology to extract the color, shape, texture and other features of the secondary scars, as well as the location and shape information of the scars. Subsequently, through image comparison and feature matching technology, these secondary collected scar features are compared with historical scar features to evaluate the scar recovery progress and determine whether the sleep posture optimization suggestions given have achieved positive scar recovery.

[0065] This step can provide timely feedback on the implementation effect of the sleep posture optimization suggestions and provide real-time feedback for nursing decisions. Through comparative analysis, the effect of personalized nursing suggestions can be accurately evaluated, the pertinence and effectiveness of nursing can be improved, and it can be ensured that nursing measures can truly promote the patient's recovery. In addition, based on the results of secondary collection and comparison, the nursing plan can be further optimized and the sleep posture optimization suggestions can be adjusted to better meet the patient's recovery needs. By showing the positive progress of scar recovery, it can also enhance the patient's confidence, improve the patient's compliance, and promote the patient's active participation in the postoperative recovery process. In summary, this step dynamically evaluates the scar recovery situation, verifies and optimizes the sleep posture optimization suggestions, thereby improving the overall effect of nursing and promoting the patient's rapid recovery.

[0066] S400, storing all collected data and analysis results, and generating a data analysis report.

[0067] This step first collects and integrates all data, including the patient's sleep quality, sleep cycle, sleep posture, scar recovery, physical sign data, and the implementation effect of sleep posture optimization suggestions. Then, using advanced data analysis tools and algorithms, the data is deeply analyzed to evaluate the progress of scar recovery and the impact of sleep posture optimization suggestions on scar recovery, and a detailed recovery report is generated accordingly. The report not only covers the interim results of scar recovery and the effect evaluation of sleep posture optimization suggestions, but also provides suggestions for future care.

[0068] In addition, this step also uses data visualization tools to convert key data and analysis results in the recovery report into intuitive and easy-to-understand charts, such as a timeline chart of scar recovery progress, a trend chart of sleeping posture changes, a comparison chart of scar feature changes, etc. These charts not only help medical staff understand the patient's recovery more intuitively, but also provide patients with clear visual feedback, enhancing their sense of participation and confidence in the nursing process.

[0069] This step provides medical staff with a strong basis for decision-making by generating detailed data analysis reports and visual charts, while also improving the transparency and understandability of the nursing process. This not only helps optimize the quality and efficiency of care, but also promotes the active participation and compliance of patients, thereby comprehensively improving the overall effect of postoperative care. Through this step, medical staff can promptly identify and solve problems in the nursing process, ensure that patients receive the most appropriate care, and accelerate their recovery process.

[0070] Figure 2 A flowchart for analyzing whether a patient's sleeping posture has a negative impact on scar recovery is provided in an embodiment of the present invention, such as Figure 2 As shown, the analysis of whether the patient's sleeping posture has a negative impact on scar recovery includes:

[0071] S110 monitors the patient's sleep quality, sleep cycle and sleep posture in real time, analyzes the patient's sleep pattern, identifies the duration and proportion of deep sleep, light sleep and REM sleep, as well as body movements during sleep;

[0072] S120, obtaining changes in scar color, shape, and texture, and evaluating scar healing progress;

[0073] S130, extracting body motion features based on the body motion data during sleep, extracting scar features from the scar image, and analyzing the correlation between sleeping posture and scar recovery.

[0074] Preferably, body motion features are extracted based on body motion data during sleep, and scar features are extracted from scar images to analyze the correlation between sleeping posture and scar recovery. Specifically:

[0075] Obtain scar images and body motion data, use convolutional neural network to extract features from scar images to obtain scar features, perform sampling Fourier transform and wavelet analysis to extract features from body motion data to obtain body motion features, and fuse scar features and body motion features to obtain mixed features;

[0076] The process of extracting features from scar images using a convolutional neural network corresponds to the following relationship:

[0077] Image Features = f cnn (I);

[0078] Among them, ImageFeatures represents scar features, I represents scar image, and f cnn (·) indicates the preference for using convolutional neural networks for feature extraction;

[0079] The process of extracting features from body motion data by sampling Fourier transform and wavelet analysis corresponds to the following relationship:

[0080] Motion Features=FFT(T)∪Wavelet(T);

[0081] Among them, Motion Features represents body motion features, FFT(·) represents Fourier transform operation, Wavelet(·) represents wavelet analysis operation, and ∪ represents fusion operation;

[0082] The process of fusing scar features with body motion features corresponds to the following relationship:

[0083] X=Image Features∪ Motion Features;

[0084] Among them, X represents the fusion feature;

[0085] The first prediction model is constructed based on multivariate regression analysis, and the fusion features are input into the first prediction model to obtain the prediction results. The corresponding process has the following relationship:

[0086]

[0087] in, represents the predicted scar recovery trend under different body motion characteristics, β1 represents the regression coefficient of the first prediction model, y z represents the actual value of the zth data point, X z represents the fusion feature of the zth data point, δ represents the regularization parameter of the first prediction model, Z represents the number of data points, and ||β1||1 represents the L1 regularization term in Lasso regression;

[0088] A hybrid model is constructed based on machine learning and deep learning algorithms. The hybrid model includes several different second prediction models. The fusion features and prediction results are used as inputs and input into different second prediction models to obtain the second prediction results of different second prediction models. The second prediction results of different second prediction models are combined together in a linear weighted summation manner to obtain the prediction results of the hybrid model to realize time series data and capture the dynamic pattern of changes in sleeping posture. The corresponding process has the following relationship:

[0089]

[0090] in, It indicates the final scar recovery trend predicted under different body motion characteristics. Represents the prediction results of the random forest model. represents the prediction result of the model based on recurrent neural network, represents the prediction result of the model based on the gradient boosting tree, α2 represents the weight of the random forest model, β2 represents the weight of the recursive neural network model, and γ2 represents the weight of the gradient boosting tree model.

[0091] In the above scheme, the present invention uses multivariate regression analysis to capture the linear relationship between the input features and the target variable, and uses this as an additional feature input into the hybrid model to provide more information dimensions. The hybrid model uses machine learning and deep learning models, which are good at capturing nonlinear relationships and local features. Multivariate regression provides an information source different from the nonlinear model, enabling the model to capture more comprehensive features. Improve the accuracy of the prediction of the present invention.

[0092] A single model may overfit the training data, resulting in poor performance in testing or actual applications. The present invention adopts a hybrid model, which can effectively reduce the risk of overfitting through diversified predictions and improve the generalization ability of the model on different data sets. It can smooth the abnormal fluctuations and noise of individual models, making the final prediction results more stable and robust. Even if a model performs poorly in certain cases, the prediction results of other models can play a corrective role, thereby improving the robustness of the overall model. And combining the prediction results of multiple models can more comprehensively capture the complex relationships and patterns in the data, thereby improving the accuracy of the overall prediction.

[0093] Figure 3 A flowchart for determining scar recovery trends, analyzing scar misalignment, and providing sleep posture optimization suggestions based on the analysis results provided by an embodiment of the present invention, such as Figure 3 As shown, the scar recovery trend is judged, scar misalignment is analyzed, and sleeping posture optimization suggestions are given based on the analysis results, including:

[0094] S210, obtaining scar images in each time period, and evaluating scar recovery trends based on scar feature changes;

[0095] S220, identifying the position offset and shape distortion of the scar, and providing sleeping posture optimization suggestions based on the correlation results between the sleeping posture and the scar recovery. The corresponding process has the following relationship:

[0096]

[0097] Among them, OSP(I t , I t-1 , P t , Θ s , f hybrid ) indicates sleeping posture optimization suggestions, I t represents the scar image at the current time t, I t-1represents the scar image of the previous time period t-1, P t represents the patient's sleeping posture data at the current time t, Θ s represents the parameter set used to evaluate scar misalignment and shape distortion, ε represents the preset scar restoration effect threshold, and D pos (I t , I t-1 , Θ s ) represents the calculation of the positional offset between the current scar image and the scar image at the previous time point, D shape (I t , I t-1 , Θ s ) represents the calculation of the degree of distortion in shape between the current scar image and the scar image at the previous time point. It indicates the contribution of the current sleeping posture to scar recovery based on the prediction results of the hybrid model, λ1 indicates the weight of the position offset, λ2 indicates the weight of the shape distortion, and λ3 indicates the weight of the influence of the sleeping posture on scar recovery. Indicates the default sleeping posture. Indicates the optimal sleeping posture;

[0098] In the above scheme, the present invention finds the optimal sleeping posture by minimizing the weighted sum of the three parts of scar position deviation, scar shape distortion and the influence of sleeping posture on scar recovery. If the prediction result of the hybrid model exceeds the preset threshold, the optimized sleeping posture is adopted, otherwise, the default sleeping posture is adopted. This allows the present invention to further optimize the patient's sleeping posture on the premise of good scar recovery prediction results, so that scar recovery is more ideal. At the same time, the changes in scar position and shape are monitored through image analysis technology to ensure the accuracy and personalization of optimization suggestions. Figure 4 The flowchart of the second collection of the scar status of the patient and the determination of scar recovery and dislocation provided by the embodiment of the present invention is as follows: Figure 4 As shown, the second collection of the patient's scar status and the determination of scar recovery and dislocation include:

[0099] S310, collecting the patient's scar image for a second time and extracting secondary scar features;

[0100] S320, combining the secondary scar features, comparing them with the historical scars, including scar feature comparison and scar position offset and shape distortion comparison, to determine the scar recovery progress and whether the sleeping posture optimization suggestions given have achieved positive scar recovery, specifically:

[0101] The scar images and historical scars collected twice are preprocessed and feature extracted to obtain image features. The corresponding process has the following relationship:

[0102] EF(I,θf )={Hist c (I), GLCM(I), Edge(I), Shape(I, θ f )};

[0103] F1=EF(I′ t-1 ,θ f );

[0104] F2=EF(I′ t ,θ f );

[0105] Among them, EF(I,θ f ) represents the feature extraction operation on the input scar image, θ f Represents the feature extraction parameter set, Hist c (I) represents the color histogram feature, GLCM(I) represents the gray-level co-occurrence matrix feature, Edge(I) represents the edge feature, Shape(I, θ f ) represents the morphological characteristics, I′ t-1 represents the historical scar image, I′ t represents the secondary collection of scar images, F1 represents the image features of historical scars, and F2 represents the image features of secondary collection of scars;

[0106] Multi-scale feature analysis is performed on the scar images collected twice and the historical scars to obtain multi-scale features. The corresponding process has the following relationship:

[0107] MA(I, θ ms )={LP(I,Θ ms ), WT(I, Θ ms )};

[0108] M1=MA(I′ t-1 , Θ ms );

[0109] M2=MA(I′ t , Θ ms );

[0110] Among them, MA(I, Θ ms ) represents the multi-scale feature analysis operation on the input scar image, Θ ms represents the characteristic multi-scale analysis parameters, LP(I, Θ ms ) represents the Laplacian pyramid feature, WT(I, Θ ms ) represents the wavelet transform feature, M1 represents the multi-scale feature of the historical scar, and M2 represents the multi-scale feature of the secondary acquisition scar;

[0111] The image features and multi-scale features of the historical scars are compared with the image features and multi-scale features of the secondary collected scars to obtain the matching degree of the features. The corresponding process has the following relationship:

[0112] {Matches, Scores}=FM({F1, M1}, {F2, M2}, Θ m );

[0113] Among them, FM({F1, M1}, {F2, M2}, Θ m ) represents the feature comparison operation, Θ m Represents the parameters of feature matching, Matches represents the matched feature pairs, and Scores represents the matching scores;

[0114] The position offset is calculated based on the matched feature pairs and matching scores to obtain the offset between the historical scar and the secondary collection scar. The corresponding process has the following relationship:

[0115] Total displacement vector calculation:

[0116]

[0117] in, represents the total displacement vector, Respectively represent the position of the matching pair, i, j represent the feature points of the two matching images, Score ij Represents the score of two matching feature points

[0118] Total weight calculation:

[0119]

[0120] Among them, W total represents the total weight;

[0121] Weighted mean displacement calculation:

[0122]

[0123] in, Represents the offset between the historical scar and the secondary acquisition scar;

[0124] Hausdorff distance and Procrustes analysis are used to calculate scar morphological changes and obtain shape distortion metrics. The corresponding process has the following relationship:

[0125] D shape =SD(S1, S2, θ s )=μ1·Hausdorff(S1, S2)+μ2·Procrustesf(S1, S2);

[0126] Among them, D shape represents the shape distortion metric, SD(S1, S2, Θ s ) represents the operation of calculating scar morphological changes, Hausdorff(S1, S2) represents the farthest and closest distance between two point sets in space, Procrustesf(S1, S2) represents the shape difference between the two point sets after optimal alignment, μ1, μ2 represent the weights of Hausdorff distance and Procrustes analysis respectively;

[0127] Based on the analysis results of feature comparison, position shift and shape distortion, a comprehensive evaluation index is constructed. Using the weighted average model, each evaluation index is weighted and summed to obtain the final evaluation result. The corresponding process has the following relationship:

[0128]

[0129] Among them, R represents the final evaluation result, α3, β3, and γ3 represent the weights of the matching score, displacement vector, and shape distortion metric, respectively. represents the Euclidean norm of the displacement vector, AverageSco re represents the average matching score, and the calculation process of the average matching score has the following relationship:

[0130]

[0131] Here, |Matches| represents the number of matching pairs.

[0132] In the above scheme, in order to improve the accuracy of comparison, the present invention introduces multi-scale feature analysis technology to ensure that the subtle changes of scars are captured at different scales. And based on the analysis results of feature comparison, position shift and shape distortion, a comprehensive evaluation index is constructed to ensure the accuracy of judging the recovery progress of scars.

[0133] Figure 5 The flowchart of storing all collected data and analysis results and generating a data analysis report provided by the embodiment of the present invention is as follows: Figure 5 As shown, the storage of all collected data and analysis results and the generation of a data analysis report include:

[0134] S410, generating a recovery report for the patient based on the scar recovery progress and the sleep posture optimization data;

[0135] S420, visually display the data in the recovery report and generate a chart.

[0136] Figure 6 A structural block diagram of a postoperative care management system for cardiac surgery provided by an embodiment of the present invention, such as Figure 6As shown, a cardiac surgery postoperative care management system, the system comprising:

[0137] The intelligent monitoring and analysis module 100 is used to monitor the patient's sleep quality, sleep cycle, sleep posture, scar recovery and physical sign data in real time, and analyze whether the patient's sleep posture has a negative impact on scar recovery;

[0138] In this module, by real-time monitoring of the patient's sleep quality, sleep cycle, sleep posture and scar recovery, a scientific basis is provided for subsequent nursing decisions. This module uses high-precision sleep monitoring equipment and image acquisition equipment to comprehensively record the patient's sleep status and scar changes. Through image processing and machine learning algorithms, it analyzes the color, shape, texture and other characteristics of the scar, and extracts body movement characteristics during sleep. In addition, this module also establishes a regression model to analyze the relationship between sleep posture characteristics and scar recovery indicators, determine the degree of influence of sleep posture characteristics on scar recovery, and provide a scientific basis for sleep posture optimization.

[0139] This module has the ability to monitor and analyze comprehensively, ensuring the integrity and accuracy of the data, and providing a solid foundation for the formulation of personalized nursing plans. Through scientific data analysis methods, such as regression analysis, it can accurately identify the correlation between sleeping posture and scar recovery, and improve the pertinence and effectiveness of nursing. In addition, automated and intelligent monitoring and analysis greatly improves nursing efficiency and reduces the workload of medical staff. At the same time, by optimizing the patient's sleeping posture, it promotes scar recovery and improves the patient's quality of life.

[0140] The sleeping posture optimization module 200 is used to determine the scar recovery trend according to the current scar state and the historical scar change pictures, and analyze the scar misalignment, and give sleeping posture optimization suggestions based on the analysis results;

[0141] In this module, scar recovery trends are determined based on the current scar status and historical scar change images, and sleep posture optimization suggestions are given. This module regularly uses high-resolution image acquisition equipment to take photos of patients' scars, and uses image processing and machine learning algorithms to analyze scar color, shape, and texture changes to evaluate scar recovery progress. At the same time, through image comparison and feature matching technology, the position offset and shape distortion of scars are identified, the causes of scar dislocation are analyzed, and combined with the regression analysis results in the previous module, the degree of influence of sleep posture characteristics on scar recovery is determined, and specific sleep posture optimization suggestions are given.

[0142] This module can timely detect trends and problems in scar recovery and provide real-time support for nursing decisions. Through the provision of personalized nursing advice, based on the correlation analysis between scar characteristics and sleeping posture, it can provide each patient with targeted sleeping posture optimization suggestions to improve the pertinence and effectiveness of nursing. In addition, automated and intelligent image analysis has greatly improved nursing efficiency and reduced the workload of medical staff. At the same time, by optimizing the patient's sleeping posture, it promotes scar recovery and improves the patient's quality of life. Specific sleeping posture optimization recommendations include advising patients to adopt a side-lying position, especially the left side, use pillows to support the knees and abdomen, avoid pressure on scars, change postures regularly, and reduce body movement and other measures to promote rapid recovery of patients.

[0143] The secondary collection module 300 is used to collect the patient's scar status for the second time after giving the sleeping posture optimization suggestion, and to judge the scar recovery and dislocation;

[0144] This module is responsible for collecting the patient's scar status again after implementing the sleep posture optimization suggestions to determine the scar recovery and dislocation. This module uses high-resolution image acquisition equipment to take photos of the patient's scars again, and uses image processing technology to extract the color, shape, texture and other features of the secondary scars, as well as the location and shape information of the scars. Subsequently, through image comparison and feature matching technology, these secondary collected scar features are compared with historical scar features to evaluate the scar recovery progress and determine whether the sleep posture optimization suggestions given have achieved positive scar recovery.

[0145] This module can provide timely feedback on the implementation effect of sleep posture optimization suggestions and provide real-time feedback for nursing decisions. Through comparative analysis, the effect of personalized nursing suggestions can be accurately evaluated, the pertinence and effectiveness of nursing can be improved, and it can be ensured that nursing measures can truly promote the patient's recovery. In addition, based on the results of secondary collection and comparison, the nursing plan can be further optimized and the sleep posture optimization suggestions can be adjusted to better meet the patient's recovery needs. By showing the positive progress of scar recovery, it can also enhance the patient's confidence, improve the patient's compliance, and promote the patient's active participation in the postoperative recovery process. In summary, this module dynamically evaluates the scar recovery situation, verifies and optimizes the sleep posture optimization suggestions, thereby improving the overall effect of nursing and promoting the rapid recovery of patients.

[0146] The data storage and analysis module 400 is used to store all collected data and analysis results, and generate a data analysis report.

[0147] This module first collects and integrates all data, including the patient's sleep quality, sleep cycle, sleep posture, scar recovery, physical sign data, and the implementation effect of sleep posture optimization suggestions. Then, using advanced data analysis tools and algorithms, this data is deeply analyzed to evaluate the progress of scar recovery and the impact of sleep posture optimization suggestions on scar recovery, and a detailed recovery report is generated accordingly. The report not only covers the interim results of scar recovery and the effect evaluation of sleep posture optimization suggestions, but also provides suggestions for future care.

[0148] In addition, this module also uses data visualization tools to convert key data and analysis results in the recovery report into intuitive and easy-to-understand charts, such as a timeline chart of scar recovery progress, a trend chart of sleeping posture changes, a comparison chart of scar feature changes, etc. These charts not only help medical staff understand the patient's recovery more intuitively, but also provide patients with clear visual feedback, enhancing their sense of participation and confidence in the nursing process.

[0149] This module provides medical staff with a strong basis for decision-making by generating detailed data analysis reports and visual charts, while also improving the transparency and comprehensibility of the nursing process. This not only helps to optimize the quality and efficiency of nursing, but also promotes the active participation and compliance of patients, thereby comprehensively improving the overall effect of postoperative care. Through this module, medical staff can promptly identify and solve problems in the nursing process, ensure that patients receive the most appropriate care, and accelerate their recovery process.

[0150] Figure 7 The structure block diagram of the intelligent monitoring and analysis module provided by the embodiment of the present invention is as follows: Figure 7 As shown, the intelligent monitoring and analysis module includes:

[0151] The sleep monitoring unit 110 is used to monitor the patient's sleep quality, sleep cycle and sleep posture in real time, analyze the patient's sleep pattern, identify the duration and proportion of deep sleep, light sleep and REM sleep, and body movement during sleep;

[0152] Scar monitoring unit 120, used to obtain the color, shape and texture changes of scars and evaluate the healing progress of scars;

[0153] The scar recovery impact analysis unit 130 is used to extract body motion features based on body motion data during sleep, extract scar features from scar images, and analyze the correlation between sleeping posture and scar recovery.

[0154] Figure 8 The structural block diagram of the sleep posture optimization module provided in the embodiment of the present invention is as follows: Figure 8 As shown, the sleeping posture optimization module includes:

[0155] The scar status evaluation unit 210 is used to obtain scar images in each time period and evaluate the recovery trend of the scar in combination with the scar feature changes;

[0156] The scar recovery optimization unit 220 is used to identify the position deviation and shape distortion of the scar, and provide sleeping posture optimization suggestions based on the correlation results between the sleeping posture and the scar recovery.

[0157] Fig. 9 The structural block diagram of the secondary acquisition module provided by the embodiment of the present invention is as follows: Fig. 9 As shown, the secondary acquisition module includes:

[0158] The image secondary acquisition unit 310 is used for secondary acquisition of the patient's scar image and extraction of secondary scar features;

[0159] The scar recovery evaluation unit 320 is used to combine the secondary scar features and compare them with historical scars, including scar feature comparison and scar position offset and shape distortion comparison, to determine the recovery progress of the scar and whether the sleeping posture optimization suggestions given have achieved positive scar recovery.

[0160] Fig.10 The structural block diagram of the data storage and analysis module provided in the embodiment of the present invention is as follows: Fig.10 As shown, the data storage and analysis module includes:

[0161] A report generating unit 410, configured to generate a recovery report for the patient based on the scar recovery progress and the sleep posture optimization data;

[0162] The data visualization unit 420 is used to visualize the data in the recovery report and generate charts.

[0163] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0164] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0165] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0166] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0167] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for postoperative nursing management of cardiac surgery, characterized in that: The method comprises the following steps: Monitor the patient's sleep quality, sleep cycle, sleep posture, scar recovery and physical sign data in real time, and analyze whether the patient's sleep posture has a negative impact on scar recovery; According to the current scar status and historical scar change pictures, the scar recovery trend is judged, the scar misalignment is analyzed, and sleeping posture optimization suggestions are given based on the analysis results; After giving suggestions for optimizing sleeping posture, the patient's scar status is collected again to determine the scar recovery and dislocation; Store all collected data and analysis results, and generate data analysis reports; The step of analyzing whether the patient's sleeping posture has a negative impact on scar recovery specifically includes the following steps: Monitor the patient's sleep quality, sleep cycle and sleep posture in real time, analyze the patient's sleep pattern, identify the duration and proportion of deep sleep, light sleep and REM sleep, as well as body movements during sleep; Obtain changes in scar color, shape and texture, and assess scar healing progress; Based on the body motion data during sleep, the body motion features are extracted, and the scar features are extracted from the scar images to analyze the correlation between sleeping posture and scar recovery. The method extracts body motion features based on body motion data during sleep, extracts scar features from scar images, and analyzes the correlation between sleeping posture and scar recovery. Specifically, the method includes the following steps: Obtain scar images and body motion data, use convolutional neural network to extract features from scar images to obtain scar features, perform sampling Fourier transform and wavelet analysis to extract features from body motion data to obtain body motion features, and fuse scar features and body motion features to obtain mixed features; The process of extracting features from scar images using a convolutional neural network corresponds to the following relationship: ； in, Indicates scar characteristics, represents a scar image, Indicates the use of convolutional neural network for feature extraction; The process of extracting features from body motion data by sampling Fourier transform and wavelet analysis corresponds to the following relationship: ； in, Indicates body movement characteristics, represents the Fourier transform operation, represents the wavelet analysis operation, represents a fusion operation; The process of fusing scar features with body motion features corresponds to the following relationship: ； in, Indicates fusion features; The first prediction model is constructed based on multivariate regression analysis, and the fusion features are input into the first prediction model to obtain the prediction results. The corresponding process has the following relationship: ； in, It represents the predicted scar recovery trend under different body motion characteristics. represents the regression coefficient of the first prediction model, Indicates z The actual value of the data point, Indicates z The fusion features of data points, represents the regularization parameter of the first prediction model, represents the number of data points, Represents the L1 regularization term in Lasso regression; A hybrid model is constructed based on machine learning and deep learning algorithms. The hybrid model includes several different second prediction models. The fusion features and prediction results are used as inputs and input into different second prediction models to obtain the second prediction results of different second prediction models. The second prediction results of different second prediction models are combined together in a linear weighted summation manner to obtain the prediction results of the hybrid model to realize time series data and capture the dynamic pattern of changes in sleeping posture. The corresponding process has the following relationship: ； in, It indicates the final scar recovery trend predicted under different body motion characteristics. Represents the prediction results of the random forest model. represents the prediction result of the model based on recurrent neural network, Represents the model prediction results based on the gradient boosting tree, represents the weight of the random forest model, represents the weights of the recurrent neural network model, Represents the weights of the gradient boosted tree model.

2. The postoperative nursing management method for cardiac surgery according to claim 1, characterized in that: The method of judging the scar recovery trend and analyzing the scar dislocation, and providing sleeping posture optimization suggestions based on the analysis results, specifically includes the following steps: Obtain scar images at each time period, and evaluate scar recovery trends based on scar feature changes; Identify the positional deviation and shape distortion of scars, and provide sleeping posture optimization suggestions based on the correlation results between sleeping posture and scar recovery.

3. The postoperative nursing management method for cardiac surgery according to claim 2, characterized in that: Identify the positional offset and shape distortion of scars, and based on the correlation between sleeping posture and scar recovery, give sleeping posture optimization suggestions. The corresponding process has the following relationship: The corresponding process has the following relationship: ； in, Indicates sleeping posture optimization suggestions. Indicates the current time t Scar images, Indicates the last time period t- 1 scar image, Indicates the current time t Patient sleeping posture data, represents the parameter set used to evaluate scar misalignment and shape distortion, Indicates the preset scar recovery effect threshold. It means calculating the positional offset between the current scar image and the scar image at the previous time point. It means calculating the degree of distortion in shape between the current scar image and the scar image at the previous time point. represents the contribution of the current sleeping posture to scar recovery based on the prediction results of the hybrid model. represents the weight of the position offset, represents the weight of shape distortion, represents the weight of the effect of sleeping posture on scar recovery, Indicates the default sleeping posture. Indicates the optimal sleeping posture.

4. The postoperative nursing management method for cardiac surgery according to claim 3, characterized in that: The second collection of the patient's scar status and determination of scar recovery and dislocation include: Secondary acquisition of scar images of patients and extraction of secondary scar features; Combined with the secondary scar features, they are compared with historical scars, including scar feature comparison and scar position offset and shape distortion comparison, to determine the scar recovery progress and whether the sleeping posture optimization suggestions given have achieved positive scar recovery.

5. The postoperative nursing management method for cardiac surgery according to claim 4, characterized in that: Combine the secondary scar features and compare them with the historical scars, including scar feature comparison, scar position offset and shape distortion comparison, to determine the scar recovery progress and whether the sleeping posture optimization suggestions have achieved positive scar recovery, including: The scar images and historical scars collected twice are preprocessed and feature extracted to obtain image features. The corresponding process has the following relationship: ； ； ； in, Indicates the feature extraction operation on the input scar image. represents the feature extraction parameter set, represents the color histogram feature, represents the gray-level co-occurrence matrix feature, represents edge features, Represents morphological characteristics, Represents a historical scar image, represents the secondary collection of scar images, Image features representing historical scars, Represents the image features of the secondary acquisition scar; Multi-scale feature analysis is performed on the scar images collected twice and the historical scars to obtain multi-scale features. The corresponding process has the following relationship: ； ； ； in, Indicates the multi-scale feature analysis operation on the input scar image. represents the characteristic multi-scale analysis parameters, represents the Laplacian pyramid feature, represents the wavelet transform feature, Representing multi-scale features of historical scars, Representing the multi-scale features of secondary acquisition scars; The image features and multi-scale features of the historical scars are compared with the image features and multi-scale features of the secondary collected scars to obtain the matching degree of the features. The corresponding process has the following relationship: ； in, Represents the feature comparison operation, Indicates the parameters for feature matching, represents the matching feature pairs, represents the matching score; The position offset is calculated based on the matched feature pair and the matching score to obtain the offset between the historical scar and the secondary collection scar; Hausdorff distance and Procrustes analysis are used to calculate scar morphological changes and obtain shape distortion metrics. The corresponding process has the following relationship: ； in, represents the shape distortion metric, Indicates the operation of calculating scar morphological changes, Represents the farthest and closest distance between two point sets in space. represents the shape difference between the two point sets after optimal alignment, Represent the weights of Hausdorff distance and Procrustes analysis respectively; Based on the analysis results of feature comparison, position shift and shape distortion, a comprehensive evaluation index is constructed. The weighted average model is used to weight the sum of various evaluation indicators to obtain the final evaluation result. The corresponding process has the following relationship: ； in, Indicates the final evaluation result. Represent the weights of matching score, displacement vector and shape distortion metric respectively, represents the Euclidean norm of the displacement vector, Represents the offset between the historical scar and the secondary collection scar, Represents the average matching score.

6. The postoperative nursing management method for cardiac surgery according to claim 5, characterized in that: The position offset is calculated based on the matched feature pairs and matching scores. The process of obtaining the offset between the historical scar and the secondary collection scar has the following relationship: Total displacement vector calculation: ； in, represents the total displacement vector, Represent the positions of matching pairs, represents the feature points of two matching images, Represents the score of two matching feature points; Total weight calculation: ； in, represents the total weight; Weighted mean displacement calculation: 。 7. The method for postoperative care management of cardiac surgery according to claim 6, characterized in that: The calculation process of the average matching score has the following relationship: ； in, Indicates the number of matching pairs.

8. The method for postoperative care management of cardiac surgery according to claim 7, characterized in that: The storage of all collected data and analysis results and the generation of data analysis reports include: Based on the scar recovery progress and sleeping posture optimization data, a recovery report for the patient is generated; Visualize the data in the recovery report and generate charts.

9. A postoperative care management system for cardiac surgery, characterized in that: The postoperative care management method for cardiac surgery according to any one of claims 1 to 8 is applied, wherein the system comprises: Intelligent monitoring and analysis module, used to monitor the patient's sleep quality, sleep cycle, sleep posture, scar recovery and physical sign data in real time, and analyze whether the patient's sleep posture has a negative impact on scar recovery; The sleeping posture optimization module is used to determine the scar recovery trend based on the current scar status and historical scar change pictures, analyze the scar misalignment, and provide sleeping posture optimization suggestions based on the analysis results; The secondary collection module is used to collect the patient's scar status for the second time after giving the sleeping posture optimization suggestion, and to judge the scar recovery and dislocation; The data storage and analysis module is used to store all collected data and analysis results, and generate data analysis reports.

Images