Ear-nose-throat patient postoperative rehabilitation nursing strategy optimization method based on big data

Abstract

The invention discloses an ear-nose-throat patient postoperative rehabilitation nursing strategy optimization method based on big data, and relates to the technical field of data analysis, and the method comprises the following steps: collecting various original data of an ear-nose-throat operation patient, including preoperative, intraoperative and postoperative whole-process data, integrating the collected data, and forming a rehabilitation nursing data set; and traversing data of the rehabilitation nursing data set, and performing feature extraction. According to the big-data-based postoperative rehabilitation nursing strategy optimization method for the ear-nose-throat patient, personalized requirements of postoperative rehabilitation of the ear-nose-throat patient are accurately matched through big data analysis, a rehabilitation nursing plan is customized for the patient by utilizing a rehabilitation nursing risk assessment result and combining physiological function scores, wound healing states and physiological state change data of the patient, and the patient can be effectively protected. The rehabilitation training device can provide targeted rehabilitation training according to specific conditions of a patient, can more effectively promote rehabilitation of the patient, reduces complications, and improves rehabilitation efficiency and quality.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a method for optimizing postoperative rehabilitation nursing strategies for ENT patients based on big data. Background Art

[0002] With the rapid development of information technology, big data technology has been widely used in many fields such as medical care, finance, and education. In the medical field, big data technology provides strong support for the prevention, diagnosis, and treatment of diseases. By collecting, analyzing, and utilizing a large amount of medical data, medical staff can more accurately judge the patient's condition and develop personalized treatment plans and care plans. Patients after ENT surgery require more meticulous and professional rehabilitation care due to the particularity of the surgical site. Traditional rehabilitation care methods often rely on the experience and intuition of medical staff and lack scientificity and accuracy.

[0003] In the existing technology, the healing state of the wound after ENT surgery will affect the patient's rehabilitation trajectory, and the changes in the physiological state during the rehabilitation process will also affect the patient's rehabilitation progress to a certain extent. Therefore, how to comprehensively evaluate the patient's rehabilitation nursing risks and dynamically adjust the patient's postoperative rehabilitation nursing strategy during the rehabilitation process is the problem we need to solve. To this end, a method for optimizing the postoperative rehabilitation nursing strategy for ENT patients based on big data is proposed. Summary of the invention

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for optimizing postoperative rehabilitation nursing strategies for ENT patients based on big data, comprising the following steps:

[0005] Step 1: Collect various original data of patients undergoing ENT surgery, including preoperative, intraoperative and postoperative data, and integrate the collected data to form a rehabilitation nursing data set;

[0006] Step 2: traverse the data of the rehabilitation nursing data set, perform feature extraction, obtain the relevant features of the patient's wound healing status assessment and physiological status analysis, and obtain a comprehensive feature set;

[0007] Step 3: Based on the data of the comprehensive feature set, a healing sign evaluation model is established to evaluate the wound healing status of the patient after surgery, and the physiological state data is extracted from the comprehensive feature set, compared with the patient's normal physiological state baseline value, and the change trend of the patient's physiological state is analyzed;

[0008] Step 4: Score the patient's physiological function, and comprehensively consider the patient's wound healing status and physiological status changes to construct a rehabilitation nursing risk prediction model, evaluate the patient's rehabilitation nursing risk, and analyze the risk level of the patient's rehabilitation process;

[0009] Step 5. Develop personalized rehabilitation care strategies based on the results of rehabilitation care risk assessment, and dynamically adjust the patient's postoperative rehabilitation care strategies.

[0010] Preferably, in step 1, the process of forming the rehabilitation nursing data set includes:

[0011] Collect the original data of the entire process of ENT surgery patients before, during and after the operation. Preoperative data include the patient's basic information, past medical history, allergy history, family medical history, preoperative diagnosis, and surgical indications. Intraoperative data include the type of surgery, operation time, surgical team, special circumstances during the operation, and medical devices and materials used. Postoperative data include postoperative recovery, wound healing examination data, physiological status data, drug treatment, physical therapy, and physiological function scores.

[0012] Preprocess the collected raw data. The preprocessing operation includes data cleaning and data standardization steps. Data cleaning checks the integrity of the data, removes or fills in missing values, identifies and processes outliers or erroneous data, and data formatting converts the collected data into a unified format to facilitate subsequent processing and analysis. The preprocessed data are then integrated into a data set to form a rehabilitation nursing data set.

[0013] Indexes are created for various types of data in the rehabilitation nursing dataset, including patient ID, surgery time, and surgery type, to facilitate retrieval and analysis, and the relevant data of the rehabilitation nursing dataset is stored in the data warehouse.

[0014] Preferably, in step 2, the process of obtaining the comprehensive feature set includes:

[0015] Load the rehabilitation nursing data set from the data warehouse, traverse the entire rehabilitation nursing data set, extract features from the perspectives of wound healing status and physiological status, and set corresponding scoring criteria for each feature;

[0016] Obtain wound healing examination data based on the rehabilitation nursing dataset, and extract wound healing status assessment features from it, including wound size, wound color, wound edge, and exudate, and record the date of each wound examination;

[0017] Acquire physiological state data based on the rehabilitation nursing data set, and extract physiological state analysis features from it, including heart rate, blood pressure, respiratory rate, body temperature, blood oxygen saturation, white blood cell count, and hemoglobin, and mark the acquisition time of each physiological state feature data;

[0018] The wound healing status assessment features and physiological status analysis features are integrated, and the feature data are normalized to obtain a comprehensive feature set containing features related to wound healing status assessment and physiological status analysis.

[0019] Preferably, in step 3, the process of evaluating the patient's postoperative wound healing status and analyzing the trend of changes in the patient's physiological status includes:

[0020] The wound healing status evaluation feature data of the comprehensive feature set is used, and the data set is divided into a training set and a test set. A healing sign evaluation model is constructed in combination with a linear regression model. The healing sign evaluation model is trained using the training set data, and the trained healing sign evaluation model is verified using the test set data. The healing sign evaluation model is used to evaluate the patient's wound healing status.

[0021] Based on the evaluation results of the trained healing sign evaluation model and the collected wound healing status evaluation feature data, the healing status evaluation index is calculated to analyze the changing trend of the patient's wound healing status over time;

[0022] Extracting the associated data of physiological status analysis features from the comprehensive feature set, building a physiological sign evaluation model using a neural network model, and using the trained physiological sign evaluation model to analyze the patient's physiological status;

[0023] The patient's actual physiological state data is compared with the normal physiological state baseline value, and combined with the analysis results of the physiological sign assessment model to obtain the physiological state assessment index, calculate the deviation, analyze the changing trend of the patient's physiological state, and determine whether it is developing in a direction that is conducive to wound healing.

[0024] Preferably, the expression of the healing status assessment index is:

[0025] ;

[0026] in, is the healing status assessment index, is the number of evaluation cycles, It is The wound size score of the second assessment, It is Wound color score of the first assessment, It is The wound edge score of the second assessment, It is The exudate score of the second assessment, is the tuning parameter used to adjust the sensitivity of the index;

[0027] The expression of the physiological state assessment index is:

[0028] ;

[0029] ;

[0030] in, It is an index of physiological status assessment. is the number of evaluation cycles, is the minimum physiological state scoring function, is the adjustment factor used to balance the effect of blood pressure score on the overall index. express score, correspond The benchmark values ​​of It is Heart rate score for each assessment, It is The blood pressure score of the second assessment, It is The respiratory rate score of the second assessment, It is The temperature score of the second assessment, It is The blood oxygen saturation score of the second assessment, It is The white blood cell count score of the second assessment, It is The hemoglobin score of the second assessment, and Corresponding to the baseline values ​​of heart rate score and blood pressure score, The value range is , The closer the value is to 0, the more the physiological state deviates from the normal baseline value.

[0031] Preferably, in step 4, the patient rehabilitation nursing risk assessment process includes:

[0032] The patient's physiological function is scored, including the dysphagia degree score, language ability score and hearing test result score. The physiological function evaluation index is calculated comprehensively to evaluate the patient's physiological function status and recovery trend. The dysphagia degree score is evaluated using the dysphagia grading scale, which includes multiple evaluation items, such as the patient's swallowing movements, food residue, and whether assisted swallowing is needed. According to the patient's specific performance, the medical staff will give a corresponding score. The higher the score, the more severe the dysphagia. The language ability score uses the language ability test scale to evaluate the patient's language expression, comprehension, reading, writing and other aspects of the ability. According to the patient's performance, a corresponding score is given. The higher the score, the stronger the language ability. The hearing test result score is tested using an audiometric test instrument. According to the patient's hearing threshold and speech recognition rate, a corresponding score is given. The higher the score, the smaller the hearing loss.

[0033] Based on the relevant data of the patient's physiological function score results, wound healing status assessment results, and physiological status change assessment results, the rehabilitation nursing characteristics are extracted, and a rehabilitation nursing risk prediction model is constructed in combination with the decision tree model. The trained rehabilitation nursing risk prediction model is used to evaluate the patient's rehabilitation nursing risk.

[0034] Combined with the evaluation results of the rehabilitation nursing risk prediction model, the healing status evaluation index, physiological status evaluation index and physiological function evaluation index are comprehensively calculated to obtain the rehabilitation risk evaluation coefficient, and the trend of patient rehabilitation nursing risk is quantitatively analyzed;

[0035] According to the analysis results of the rehabilitation risk evaluation coefficient and the patient's rehabilitation nursing risk trend, the patient's rehabilitation nursing risk is divided into different risk levels, namely low risk level, medium risk level and high risk level, and the corresponding evaluation threshold is matched for each risk level.

[0036] Preferably, the expression of the physiological function evaluation index is:

[0037] ;

[0038] in, It is an index of physiological function assessment. is the number of evaluation cycles, It is The dysphagia score of the second assessment was It is Language proficiency score for the assessment, It is The listening test results of the assessment were scored. , , The corresponding normal physiological function benchmark values, is the adjustment factor used to balance the impact of language proficiency scores on the overall index. The value range is , The closer the value is to 0, the more the physiological function deviates from the normal baseline value.

[0039] Preferably, the expression of the rehabilitation risk assessment coefficient is:

[0040] ;

[0041] in, is the rehabilitation risk assessment coefficient, is the healing status assessment index, It is an index of physiological status assessment. It is an index of physiological function assessment. , , Corresponding to , and The weight coefficient of , , They are , and Maximum value, The value of is between 0 and 1. The closer the value is to 0, the lower the risk of recovery. The closer the value is to 1, the higher the risk of recovery.

[0042] Preferably, the plurality of risk levels correspond to a plurality of evaluation thresholds, wherein the evaluation thresholds include an upper threshold and a lower threshold;

[0043] The multiple risk levels and the multiple evaluation thresholds satisfy the following relationship:

[0044] Low risk level ; It indicates that the patient's rehabilitation care risk is low and no additional intervention is required, but the patient's rehabilitation progress needs to be monitored regularly;

[0045] Medium risk level ; Indicates that the patient's rehabilitation care risk is moderate and requires further evaluation and intervention, such as adjusting the rehabilitation plan or increasing the frequency of monitoring;

[0046] High risk level ; Indicates that the patient's rehabilitation care risk is high and requires urgent intervention and close monitoring, adjustment of treatment plans or more active rehabilitation measures;

[0047] in, is the rehabilitation risk assessment coefficient, is the lower threshold corresponding to the medium risk level and the upper threshold corresponding to the low risk level, is the lower threshold corresponding to the high risk level and the upper threshold corresponding to the medium risk level, , .

[0048] Preferably, in step 5, the process of dynamically adjusting the patient's postoperative rehabilitation nursing strategy includes:

[0049] According to the results of rehabilitation nursing risk assessment, determine the patient's risk level, and conduct in-depth analysis of the main factors that lead to the patient's current risk level, such as the degree of physiological function limitation, wound healing speed, psychological state, etc.;

[0050] Based on the evaluation results, combined with the patient's specific situation and rehabilitation goals, short-term and long-term rehabilitation goals are set for the patient, and a nursing plan is formulated. For physiological function recovery, targeted rehabilitation training plans are designed according to the patient's limited swallowing, language, hearing and other physiological functions, such as swallowing training, speech therapy, hearing rehabilitation, etc. For wound care, wound cleaning, dressing changes, moisturizing and other nursing measures are formulated according to the wound healing status;

[0051] Regularly monitor the patient's rehabilitation progress and changes in risk factors, dynamically adjust the frequency and intensity of care according to the patient's risk level and rehabilitation goals, ensure that nursing resources are reasonably allocated, and promptly adjust rehabilitation care strategies, such as increasing or decreasing the intensity of rehabilitation training, changing wound care methods, adjusting diet plans, etc.

[0052] The present invention provides a method for optimizing postoperative rehabilitation nursing strategies for ENT patients based on big data. It has the following beneficial effects:

[0053] 1. This big data-based optimization method for postoperative rehabilitation nursing strategies for ENT patients can accurately match the personalized needs of ENT patients for postoperative rehabilitation through big data analysis. It uses the results of rehabilitation nursing risk assessment and combines the patient's physiological function score, wound healing status, and physiological state change data to customize rehabilitation nursing plans for patients. It can provide targeted rehabilitation training based on the patient's specific situation, which can more effectively promote patient rehabilitation, reduce the occurrence of complications, and improve rehabilitation efficiency and quality.

[0054] 2. This big data-based optimization method for postoperative rehabilitation nursing strategies for ENT patients can monitor and analyze the patient's postoperative physiological state, wound healing and physiological function in real time. Medical staff can promptly identify potential risk factors and predict the patient's recovery trend, which helps medical staff intervene in advance, reduce the occurrence of serious complications and improve the patient's recovery quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 This is a method flow chart of a method for optimizing postoperative rehabilitation nursing strategies for ENT patients based on big data according to the present invention;

[0056] Figure 2 This is a flow chart for evaluating the postoperative wound healing status of patients and analyzing the trend of changes in the physiological status of patients according to the present invention;

[0057] Figure 3 The present invention is a flowchart for assessing the risk of patient rehabilitation care. DETAILED DESCRIPTION

[0058] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments of the present invention are provided for the purpose of illustration and description, and are not intended to be exhaustive or to limit the present invention to the disclosed forms. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present invention, and to enable those of ordinary skill in the art to understand the present invention and thereby design various embodiments with various modifications suitable for specific uses.

[0059] The first embodiment, as Figure 1 , Figure 2 As shown, the present invention provides a technical solution: a method for optimizing postoperative rehabilitation nursing strategies for ENT patients based on big data, comprising the following steps:

[0060] Step 1: Collect all kinds of original data of ENT surgery patients, including preoperative, intraoperative and postoperative full-process data, integrate the collected data to form a rehabilitation nursing data set, collect the full-process original data of ENT surgery patients before, during and after the operation, among which the preoperative data include the patient's basic information, past medical history, allergy history, family medical history, preoperative diagnosis, and surgical indications. The intraoperative data include the type of surgery, operation time, surgical team, special circumstances during the operation, and the medical equipment and materials used. The postoperative data include postoperative recovery, wound healing examination data, physiological status data, drug treatment, physical therapy, and physiological function score. Preprocess the collected original data. The preprocessing operation includes data cleaning and data standardization steps. Data cleaning checks the integrity of the data, removes or fills in missing values, identifies and processes outliers or erroneous data, and data formatting converts the collected data into a unified format for subsequent processing and analysis. The preprocessed data are integrated into a data set to form a rehabilitation nursing data set. Indexes are established for various types of data in the rehabilitation nursing data set, including patient ID, operation time, and operation type, to facilitate retrieval and analysis, and the relevant data of the rehabilitation nursing data set is stored in the data warehouse;

[0061] Step 2: Traverse the data of the rehabilitation nursing data set, perform feature extraction, obtain the associated features of the patient's wound healing status evaluation and physiological status analysis, obtain a comprehensive feature set, load the rehabilitation nursing data set from the data warehouse, traverse the entire rehabilitation nursing data set, extract features from the perspective of wound healing status and physiological status, and set corresponding scoring standards for each feature. Based on the rehabilitation nursing data set, obtain wound healing examination data and extract wound healing status evaluation features from it, including wound size, wound color, wound edge and exudate, record the date of each wound inspection, wound size: 0-10 points, 0 points means no wound, 10 points means a very large wound, wound color: 0-3 points, 0 points means normal, 3 points means abnormal color, wound edge: 0-3 points, 0 points means neat edges, 3 points means irregular edges, exudate: 0-3 points, 0 points means no exudate, 3 points means a lot of exudate, wound size records the size of the wound, wound color records the color of the wound, wound edge records the state of the wound edge, exudate records whether the wound has exudate and its nature, physiological state data is obtained based on the rehabilitation nursing data set, and physiological state analysis features are extracted from it, including heart rate, blood pressure, respiratory rate, body temperature, blood oxygen saturation, white blood cell count and hemoglobin, marking the acquisition time of each physiological state feature data, integrating wound healing state assessment features and physiological state analysis features, and normalizing each feature data to obtain a comprehensive feature set containing features related to wound healing state assessment and physiological state analysis;

[0062] Step 3. Based on the data of the comprehensive feature set, a healing sign evaluation model is established to evaluate the postoperative wound healing status of the patient. The physiological state data is extracted from the comprehensive feature set, compared with the patient's normal physiological state baseline value, and the changing trend of the patient's physiological state is analyzed. The wound healing state evaluation feature data of the comprehensive feature set is used, and the data set is divided into a training set and a test set. The healing sign evaluation model is constructed in combination with the linear regression model. The training set data is used to train the healing sign evaluation model, and the test set data is used to verify the trained healing sign evaluation model. The healing sign evaluation model is evaluated using the healing sign evaluation model. Based on the trained The evaluation results of the healing sign evaluation model and the collected wound healing status evaluation feature data are used to calculate the healing status evaluation index, analyze the changing trend of the patient's wound healing status over time, extract the associated data of the physiological status analysis feature from the comprehensive feature set, use the neural network model to build a physiological sign evaluation model, use the trained physiological sign evaluation model to analyze the patient's physiological state, compare the patient's actual physiological state data with the normal physiological state baseline value, combine the analysis results of the physiological sign evaluation model to obtain the physiological state evaluation index, calculate the deviation, analyze the changing trend of the patient's physiological state, and determine whether it is developing in a direction that is conducive to wound healing;

[0063] Furthermore, the expression of the healing status evaluation index is:

[0064] ;

[0065] in, is the healing status assessment index, is the number of evaluation cycles, It is The wound size score of the second assessment, It is Wound color score of the first assessment, It is The wound edge score of the second assessment, It is The exudate score of the second assessment, is an adjustment parameter used to adjust the sensitivity of the index. Increase, or wound color score Increase, The value increases, indicating that the healing state is deteriorating. Decreased and / or exudate scores reduce, Decreased, indicating improved healing, The square root of the weighted sum of wound size and color scores in all evaluation cycles was calculated, and a logarithmic function was used to reduce the influence of extreme values ​​and make the scores smoother. Considering the relative improvement or deterioration of wound margins and exudate, if the wound margins improve and exudate decreases, the value of this component will be close to 1 (or greater), making the overall The value increases, indicating a good healing state. On the contrary, if the wound edge deteriorates and the exudate increases, the value of this part will be less than 1, decreasing Value, indicating poor healing status;

[0066] The expression of physiological status assessment index is:

[0067] ;

[0068] ;

[0069] in, It is an index of physiological status assessment. is the number of evaluation cycles, is the minimum physiological state scoring function, is the adjustment factor used to balance the effect of blood pressure score on the overall index. express score, correspond The benchmark values ​​of It is Heart rate score for each assessment, It is The blood pressure score of the second assessment, It is The respiratory rate score of the second assessment, It is The temperature score of the second assessment, It is The blood oxygen saturation score of the second assessment, It is The white blood cell count score of the second assessment, It is The hemoglobin score of the second assessment, and Corresponding to the baseline values ​​of heart rate score and blood pressure score, The value range is , The closer the value is to 0, the more the physiological state deviates from the normal baseline value. The larger the value, the closer the physiological state is to or better than the normal baseline value. If the patient's physiological state data gradually approaches or exceeds the normal physiological state baseline value, The value of will increase, indicating that the physiological state has improved. If the patient's physiological state data gradually deviates from the normal physiological state baseline value, The value of will decrease, indicating a deterioration in physiological status;

[0070] Step 4: Score the patient's physiological function, and comprehensively consider the patient's wound healing status and physiological status changes to construct a rehabilitation nursing risk prediction model, evaluate the patient's rehabilitation nursing risk, and analyze the risk level of the patient's rehabilitation process;

[0071] Step 5. Develop personalized rehabilitation care strategies based on the results of rehabilitation care risk assessment, and dynamically adjust the patient's postoperative rehabilitation care strategies.

[0072] The second embodiment is based on the first embodiment. Figure 3 As shown in step 4, the assessment process of patient rehabilitation care risks includes:

[0073] The patient's physiological function is scored, including the dysphagia degree score, language ability score and hearing test result score. The physiological function evaluation index is calculated comprehensively to evaluate the patient's physiological function status and recovery trend. The dysphagia degree score is evaluated using the dysphagia grading scale, which includes multiple evaluation items, such as the patient's swallowing movements, food residue, and whether assisted swallowing is needed. According to the patient's specific performance, the medical staff will give a corresponding score. The higher the score, the more severe the dysphagia. The language ability score uses the language ability test scale to evaluate the patient's language expression, comprehension, reading, writing and other aspects of the ability. According to the patient's performance, a corresponding score is given. The higher the score, the stronger the language ability. The hearing test result score is tested using an audiometric test instrument. According to the patient's hearing threshold and speech recognition rate, a corresponding score is given. The higher the score, the smaller the hearing loss. Based on the relevant data of the patient's physiological function score results, wound healing status assessment results, and physiological status change assessment results, the rehabilitation nursing characteristics are extracted, and a rehabilitation nursing risk prediction model is constructed in combination with the decision tree model. The trained rehabilitation nursing risk prediction model is used to evaluate the patient's rehabilitation nursing risk. Combined with the assessment results of the rehabilitation nursing risk prediction model, the healing status assessment index, the physiological status assessment index, and the physiological function assessment index are comprehensively calculated to obtain the rehabilitation risk evaluation coefficient, and the trend of the patient's rehabilitation nursing risk is quantitatively analyzed. According to the analysis results of the rehabilitation risk evaluation coefficient and the patient's rehabilitation nursing risk trend, the patient's rehabilitation nursing risk is divided into different risk levels, namely low risk level, medium risk level, and high risk level, and the corresponding evaluation threshold is matched for each risk level;

[0074] Furthermore, the expression of the physiological function evaluation index is:

[0075] ;

[0076] in, It is an index of physiological function assessment. is the number of evaluation cycles, It is The dysphagia score of the second assessment was It is Language proficiency score for the assessment, It is The listening test results of the assessment were scored. , , The corresponding normal physiological function benchmark values, is the adjustment factor used to balance the impact of language proficiency scores on the overall index. The value range is , The closer the value is to 0, the more the physiological function deviates from the normal baseline value. The larger the value, the closer the physiological function is to or better than the normal baseline value. If the patient's physiological function data gradually approaches or exceeds the normal physiological function baseline value, The value will increase, indicating that the physiological function has improved. If the patient's physiological function data gradually deviates from the normal physiological function baseline value, The value will decrease, indicating that physiological function deteriorates. The inverse of the square root of the deviation between the dysphagia score and the baseline value was calculated to reflect the stability of the dysphagia score. The deviation between the language proficiency score and the benchmark value is taken into account. The exponential function is used to amplify or reduce the impact of the deviation. The product part The minimum value of the ratio of the audiometric test result score to the baseline value was calculated to ensure that all physiological function scores were taken into account;

[0077] Furthermore, the expression of the rehabilitation risk assessment coefficient is:

[0078] ;

[0079] in, is the rehabilitation risk assessment coefficient, is the healing status assessment index, It is an index of physiological status assessment. It is an index of physiological function assessment. , , Corresponding to , and The weight coefficient of , , They are , and Maximum value, The value of is between 0 and 1. The closer the value is to 0, the lower the risk of recovery. The closer the value is to 1, the higher the risk of recovery. , or Any one or more of the increases, The value will increase, indicating an increased risk of recovery. , and All reduced, The values ​​will decrease, indicating a reduced risk of recovery;

[0080] Furthermore, the multiple risk levels correspond to multiple evaluation thresholds, wherein the evaluation thresholds include an upper threshold and a lower threshold;

[0081] Multiple risk levels and multiple evaluation thresholds satisfy the following relationship:

[0082] Low risk level ; It indicates that the patient's rehabilitation care risk is low and no additional intervention is required, but the patient's rehabilitation progress needs to be monitored regularly;

[0083] Medium risk level ; Indicates that the patient's rehabilitation care risk is moderate and requires further evaluation and intervention, such as adjusting the rehabilitation plan or increasing the frequency of monitoring;

[0084] High risk level ; Indicates that the patient's rehabilitation care risk is high and requires urgent intervention and close monitoring, adjustment of treatment plans or more active rehabilitation measures;

[0085] in, is the rehabilitation risk assessment coefficient, is the lower threshold corresponding to the medium risk level and the upper threshold corresponding to the low risk level, is the lower threshold corresponding to the high risk level and the upper threshold corresponding to the medium risk level, , ;

[0086] In step five, the process of dynamically adjusting the patient's postoperative rehabilitation nursing strategy includes:

[0087] According to the results of rehabilitation nursing risk assessment, the patient's risk level is determined, and the main factors that lead to the patient's current risk level are analyzed in depth, such as the degree of limitation of physiological function, wound healing speed, psychological state, etc. Based on the assessment results, combined with the patient's specific situation and rehabilitation goals, short-term and long-term rehabilitation goals are set for the patient, and a nursing plan is formulated. For physiological function recovery, targeted rehabilitation training plans are designed for the patient's swallowing, language, hearing and other physiological function limitations, such as swallowing training, speech therapy, hearing rehabilitation, etc. For wound care, wound cleaning, dressing changes, moisturizing and other nursing measures are formulated according to the wound healing status. The patient's rehabilitation progress and changes in risk factors are regularly monitored. According to the patient's risk level and rehabilitation goals, the frequency and intensity of nursing are dynamically adjusted to ensure that nursing resources are reasonably allocated, and rehabilitation nursing strategies are adjusted in a timely manner, such as increasing or decreasing the intensity of rehabilitation training, changing the method of wound care, adjusting the diet plan, etc.

[0088] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field and related fields without creative work should fall within the scope of protection of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention are implemented according to the conventional means in the field unless otherwise specified and limited.

Claims

1. A method for optimizing postoperative rehabilitation nursing strategies for ENT patients based on big data, characterized in that: The following steps are involved: Step 1: Collect various original data of patients undergoing ENT surgery, including preoperative, intraoperative and postoperative data, and integrate the collected data to form a rehabilitation nursing data set; Step 2: traverse the data of the rehabilitation nursing data set, perform feature extraction, obtain the relevant features of the patient's wound healing status assessment and physiological status analysis, and obtain a comprehensive feature set; Step 3: Based on the data of the comprehensive feature set, a healing sign evaluation model is established to evaluate the wound healing status of the patient after surgery, and the physiological state data is extracted from the comprehensive feature set, compared with the patient's normal physiological state baseline value, and the change trend of the patient's physiological state is analyzed; Step 4: Score the patient's physiological function, and comprehensively consider the patient's wound healing status and physiological status changes to construct a rehabilitation nursing risk prediction model, evaluate the patient's rehabilitation nursing risk, and analyze the risk level of the patient's rehabilitation process; Step 5. Develop personalized rehabilitation care strategies based on the results of rehabilitation care risk assessment, and dynamically adjust the patient's postoperative rehabilitation care strategies.

2. According to the big data-based optimization method for postoperative rehabilitation nursing strategies for ENT patients according to claim 1, it is characterized by: In the step 1, the process of forming the rehabilitation nursing data set includes: Collect the original data of the entire process of ENT surgery patients before, during and after the operation. Preoperative data include the patient's basic information, past medical history, allergy history, family medical history, preoperative diagnosis, and surgical indications. Intraoperative data include the type of surgery, operation time, surgical team, special circumstances during the operation, and medical devices and materials used. Postoperative data include postoperative recovery, wound healing examination data, physiological status data, drug treatment, physical therapy, and physiological function scores. Preprocess the collected raw data, including data cleaning and data standardization steps, and integrate the preprocessed data into a data set to form a rehabilitation nursing data set; Create indexes for various types of data in the rehabilitation nursing dataset, including patient ID, surgery time, and surgery type, and store relevant data of the rehabilitation nursing dataset in the data warehouse.

3. According to claim 2, a method for optimizing postoperative rehabilitation nursing strategies for ENT patients based on big data, characterized in that: In the step 2, the process of obtaining the comprehensive feature set includes: Load the rehabilitation nursing data set from the data warehouse, traverse the entire rehabilitation nursing data set, extract features from the perspectives of wound healing status and physiological status, and set corresponding scoring criteria for each feature; Obtain wound healing examination data based on the rehabilitation nursing dataset, and extract wound healing status assessment features from it, including wound size, wound color, wound edge, and exudate, and record the date of each wound examination; Acquire physiological state data based on the rehabilitation nursing data set, and extract physiological state analysis features from it, including heart rate, blood pressure, respiratory rate, body temperature, blood oxygen saturation, white blood cell count, and hemoglobin, and mark the acquisition time of each physiological state feature data; The wound healing status assessment features and physiological status analysis features are integrated, and the feature data are normalized to obtain a comprehensive feature set containing features related to wound healing status assessment and physiological status analysis.

4. According to claim 3, a method for optimizing postoperative rehabilitation nursing strategies for ENT patients based on big data is characterized in that: In step 3, the evaluation of the patient's postoperative wound healing status and the analysis of the patient's physiological status change trend include: The wound healing status evaluation feature data of the comprehensive feature set is used, and the data set is divided into a training set and a test set. A healing sign evaluation model is constructed in combination with a linear regression model. The healing sign evaluation model is trained using the training set data, and the trained healing sign evaluation model is verified using the test set data. The healing sign evaluation model is used to evaluate the patient's wound healing status. Based on the evaluation results of the trained healing sign evaluation model and the collected wound healing status evaluation feature data, the healing status evaluation index is calculated to analyze the changing trend of the patient's wound healing status over time; Extracting the associated data of physiological status analysis features from the comprehensive feature set, building a physiological sign evaluation model using a neural network model, and using the trained physiological sign evaluation model to analyze the patient's physiological status; The patient's actual physiological state data is compared with the normal physiological state baseline value, and combined with the analysis results of the physiological sign assessment model to obtain the physiological state assessment index, calculate the deviation, and analyze the changing trend of the patient's physiological state.

5. According to claim 4, a method for optimizing postoperative rehabilitation nursing strategies for ENT patients based on big data is characterized in that: The expression of the healing status evaluation index is: ； in, is the healing status assessment index, is the number of evaluation cycles, It is The wound size score of the second assessment, It is Wound color score of the first assessment, It is The wound edge score of the second assessment, It is The exudate score of the second assessment, is the tuning parameter used to adjust the sensitivity of the index; The expression of the physiological state assessment index is: ； ； in, It is an index of physiological status assessment. is the number of evaluation cycles, is the minimum physiological state scoring function, is the adjustment factor used to balance the effect of blood pressure score on the overall index. express score, correspond The benchmark values ​​of It is Heart rate score for each assessment, It is The blood pressure score of the second assessment, It is The respiratory rate score of the second assessment, It is The temperature score of the second assessment, It is The blood oxygen saturation score of the second assessment, It is The white blood cell count score of the second assessment, It is The hemoglobin score of the second assessment, and Corresponding to the baseline values ​​of heart rate score and blood pressure score, The value range is , The closer the value of is to 0, the more the physiological state deviates from the normal baseline value.

6. The method for optimizing postoperative rehabilitation nursing strategies for ENT patients based on big data according to claim 5 is characterized by: In step 4, the assessment process of patient rehabilitation nursing risk includes: The patient's physiological function is scored, including the dysphagia score, language ability score and hearing test result score, and the physiological function evaluation index is calculated comprehensively to evaluate the patient's physiological function status and recovery trend; Based on the relevant data of the patient's physiological function score results, wound healing status assessment results, and physiological status change assessment results, the rehabilitation nursing characteristics are extracted, and a rehabilitation nursing risk prediction model is constructed in combination with the decision tree model. The trained rehabilitation nursing risk prediction model is used to evaluate the patient's rehabilitation nursing risk. Combined with the evaluation results of the rehabilitation nursing risk prediction model, the healing status evaluation index, physiological status evaluation index and physiological function evaluation index are comprehensively calculated to obtain the rehabilitation risk evaluation coefficient, and the trend of patient rehabilitation nursing risk is quantitatively analyzed; According to the analysis results of the rehabilitation risk evaluation coefficient and the patient's rehabilitation nursing risk trend, the patient's rehabilitation nursing risk is divided into different risk levels, namely low risk level, medium risk level and high risk level, and the corresponding evaluation threshold is matched for each risk level.

7. The method for optimizing postoperative rehabilitation nursing strategies for ENT patients based on big data according to claim 6 is characterized by: The expression of the physiological function evaluation index is: ； in, It is an index of physiological function assessment. is the number of evaluation cycles, It is The dysphagia score of the second assessment was It is Language proficiency score for the assessment, It is The listening test results of the assessment were scored. , , The corresponding normal physiological function baseline values, is the adjustment factor used to balance the impact of language proficiency scores on the overall index. The value range is , The closer the value is to 0, the more the physiological function deviates from the normal baseline value.

8. The method for optimizing postoperative rehabilitation nursing strategies for ENT patients based on big data according to claim 7 is characterized in that: The expression of the rehabilitation risk assessment coefficient is: ； in, is the rehabilitation risk assessment coefficient, is the healing status assessment index, It is an index of physiological status assessment. It is an index of physiological function assessment. , , Corresponding to , and The weight coefficient of , , They are , and Maximum value, The value of is between 0 and 1. The closer the value of is to 0, the lower the risk of recovery. The closer the value is to 1, the higher the risk of recovery.

9. The method for optimizing postoperative rehabilitation nursing strategies for ENT patients based on big data according to claim 8, characterized in that: A plurality of the risk levels correspond to a plurality of the evaluation thresholds, wherein the evaluation thresholds include an upper threshold and a lower threshold; The multiple risk levels and the multiple evaluation thresholds satisfy the following relationship: Low risk level ; Medium risk level ; High risk level ; in, is the rehabilitation risk assessment coefficient, is the lower threshold corresponding to the medium risk level and the upper threshold corresponding to the low risk level, is the lower threshold corresponding to the high risk level and the upper threshold corresponding to the medium risk level, , .

10. The method for optimizing postoperative rehabilitation nursing strategies for ENT patients based on big data according to claim 9, characterized in that: In step 5, the process of dynamically adjusting the patient's postoperative rehabilitation nursing strategy includes: Determine the patient's risk level based on the results of rehabilitation nursing risk assessment, and conduct in-depth analysis of the main factors that lead to the patient's current risk level; Based on the assessment results, combined with the patient's specific situation and rehabilitation goals, set short-term and long-term rehabilitation goals for the patient and develop a care plan; Regularly monitor the patient's rehabilitation progress and changes in risk factors, dynamically adjust the frequency and intensity of care according to the patient's risk level and rehabilitation goals, and promptly adjust the rehabilitation care strategy.

Images