Hypertension collaborative management method based on individual case management and narrative nursing fusion

Abstract

The invention relates to the technical field of management, and particularly discloses a hypertension collaborative management method based on individual case management and narrative nursing fusion, which is used for solving the problem that the rehabilitation effect of a patient is further influenced due to the fact that the patient always lacks emotional support in the process of seeing a doctor, medical behaviors pay more attention to physiological indexes and neglect psychological needs. The blood pressure of the patient is monitored regularly through the intelligent blood pressure detection equipment, the blood pressure fluctuation of the patient is specially recognized through an anomaly detection recognition algorithm, a targeted blood pressure fluctuation record is generated, the historical medical record of the patient and the language sample of the patient in each time of seeing a doctor are collected, and the language emotion of the patient is analyzed based on the language sample. The rehabilitation effect of the patient is comprehensively evaluated on the basis of the blood pressure fluctuation record and the personalized nursing record, neglect on emotion and psychological needs of the patient in traditional hypertension management is made up, and the medical experience and rehabilitation effect of the patient can be remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of management technology. More specifically, the present invention relates to a collaborative management method for hypertension based on the integration of case management and narrative nursing. Background Art

[0002] Secondary hypertension is a type of hypertension caused by clear pathological reasons. Its causes are complex, including various factors such as kidney diseases, endocrine disorders, cardiovascular abnormalities, and drug effects. Compared with primary hypertension, secondary hypertension has a higher disability rate and fatality rate. If not intervened in a timely and accurate manner, it may lead to serious target organ damage, such as heart disease, stroke, and kidney failure. Therefore, the comprehensive management of secondary hypertension has become an important topic in the field of medical health. The traditional hypertension management model mainly focuses on drug treatment in a single department or single discipline, lacking comprehensive assessment and systematic management of patients in multiple aspects. As a result, the condition control effect of some patients is not good due to imperfect treatment plans and insufficient personalization. In addition, patients often lack emotional support during the medical treatment process, and medical behaviors pay more attention to physiological indicators while ignoring psychological needs, further affecting the rehabilitation effect of patients.

[0003] As nursing methods emerging in recent years, case management and narrative nursing emphasize patient-centered and conduct full-life-cycle management of patients through the way of multidisciplinary cooperation. The existing literature (Jia Xiaojuan. Practical Research on Case Management of Rural Elderly Chronic Disease Patients [D]. Northwest Normal University, 2024. DOI: 10.27410 / d.cnki.gxbfu.2024.001774.) formulates practical plans with the client under the background of the case management model by sorting out the client's problems and analyzing the needs, and explores the role that social workers can play in the elderly chronic disease group by using the case management model. The case management method not only pays attention to the monitoring and intervention of the patient's condition, but also focuses on the patient's mental state, lifestyle, and social support system, so as to improve the overall health level of the patient. Narrative nursing, on the other hand, plays an important psychological support role in the nursing process by establishing a humanistic emotional bond with the patient and deeply understanding the patient's emotional needs and disease experience, further enhancing the patient's trust and cooperation in treatment. Under this background, the "KY3H" traditional Chinese medicine characteristic health security service model is introduced. Through the combination of traditional Chinese and Western medicine, it emphasizes syndrome differentiation and treatment and overall conditioning, enabling patients to enjoy personalized traditional Chinese medicine rehabilitation services while receiving modern medical treatment. By organically integrating case management, narrative nursing, and the "KY3H" service model to form a multidisciplinary collaborative management model for secondary hypertension, it is expected to provide more comprehensive, accurate, and humanistic medical security for patients. To solve the above problems, a technical solution is provided now. Summary of the Invention

[0004] To overcome the above-mentioned defects of the prior art, the present invention provides a collaborative hypertension management method based on the integration of case management and narrative nursing, which is used to solve the problem that existing patients often lack emotional support during the medical treatment process, medical behaviors pay more attention to physiological indicators and ignore psychological needs, further affecting the rehabilitation effect of patients, making up for the neglect of patients' emotional and psychological needs in traditional hypertension management, and being able to significantly improve the patients' medical experience and rehabilitation effect to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A collaborative hypertension management method based on the integration of case management and narrative nursing, comprising the following steps:

[0007] Step 1, regularly monitor the patient's blood pressure through an intelligent blood pressure detection device, and use an anomaly detection and recognition algorithm to specially identify the patient's blood pressure fluctuations, generating targeted blood pressure fluctuation records;

[0008] Step 2, collect the patient's historical medical records and language samples during each medical visit, analyze the patient's language emotions based on the language samples, and form personalized nursing records;

[0009] Step 3, comprehensively evaluate the patient's rehabilitation effectiveness based on the blood pressure fluctuation records and personalized nursing records. The construction steps of the rehabilitation effectiveness evaluation model are as follows: for each stage from the first medical visit to the (T - 1)-th medical visit, calculate the influence value of emotional tendency on rehabilitation. For the blood pressure fluctuations within this stage, by taking the blood pressure abnormal fluctuation value at a certain time point and normalizing it with the range of the blood pressure fluctuation interval within this stage, obtain the relative level of the fluctuation at this time point in the overall interval. Multiply the emotional influence value of each stage by the normalized blood pressure fluctuation value, and sum for all stages to obtain the comprehensive rehabilitation effectiveness value;

[0010] The formula of the rehabilitation effectiveness evaluation model is:

[0011]

[0012] In the formula: K cx is the patient's rehabilitation effectiveness value, S emo t is the emotional tendency evaluation coefficient at the t-th medical visit, is the blood pressure abnormal fluctuation value at the f-th time point between the t-th medical visit and the (t + 1)-th medical visit, is the maximum blood pressure abnormal fluctuation value between the t-th medical visit and the (t + 1)-th medical visit, is the minimum blood pressure abnormal fluctuation value between the t-th medical visit and the (t + 1)-th medical visit, and T is the number of medical visits.

[0013] As a further solution of the present invention, in step 1, the blood pressure data of the patient is monitored regularly by an intelligent blood pressure detection device, and the abnormal detection and recognition algorithm is used to specifically identify the blood pressure fluctuations of the patient, generating a targeted blood pressure fluctuation record. The specific steps are as follows:

[0014] Step 11, regularly monitor the first blood pressure data set X = {x1, x2,..., x i ,..., x n} of the patient by an intelligent blood pressure detection device, where x1 is the first blood pressure data at the first time point, x2 is the first blood pressure data at the second time point, x i is the first blood pressure data at the i-th time point, x n is the first blood pressure data at the n-th time point, x i = (SBP i , DBP i , MB i ), SBP i is the i-th first systolic blood pressure, DBP i is the i-th first diastolic blood pressure, MB i is the i-th first pulse beating frequency; take the first blood pressure data values at each time point of the patient for one consecutive month as the observed blood pressure data;

[0015] Step 12, extract the observed blood pressure data and import it into the blood pressure reference coefficient calculation formula to calculate the blood pressure parameter coefficient. For each observed time point j, extract the first systolic blood pressure the first diastolic blood pressure and the first pulse beating frequency from the blood pressure data. Determine the maximum values of these three items respectively in all the data, which are and For each time point j, calculate the ratio of to , the ratio of to , and the ratio of to respectively. After adding these three ratios and taking the absolute value, sum up the calculation results for all m time points and divide by m to obtain the blood pressure reference coefficient;

[0016] The blood pressure reference coefficient calculation formula is:

[0017]

[0018] In the formula: X hy is the blood pressure reference coefficient, is the first systolic blood pressure in the observed blood pressure data at the j-th time point, is the maximum value of the first systolic blood pressure in the observed blood pressure data, is the first diastolic blood pressure in the observed blood pressure data at the j-th time point, is the maximum value of the first diastolic blood pressure in the observed blood pressure data, is the first pulse rate in the observed blood pressure data at the j-th time point, is the maximum value of the first pulse rate in the observed blood pressure data, and m is the number of acquisitions of the observed blood pressure data;

[0019] Step 13: Construct a blood pressure fluctuation abnormality analysis model based on the first blood pressure dataset and the blood pressure reference coefficient to analyze whether there is abnormal fluctuation in the patient's blood pressure. For each time point i, first obtain the blood pressure data at that moment, then multiply it by the blood pressure reference coefficient, perform normalization processing by subtracting the value of the exponential function from 1, and accumulate the processed results at each time point to obtain the abnormal blood pressure fluctuation;

[0020] Among them, the formula of the blood pressure abnormality analysis model is:

[0021]

[0022] In the formula: X b is the blood pressure abnormal fluctuation value, X hy is the blood pressure reference coefficient, n is the number of acquisitions of the first blood pressure data, x i is the first blood pressure data at the i-th time point, and x b is the mean value of the first blood pressure data;

[0023] Step 14: Obtain the blood pressure abnormal fluctuation value, and compare the blood pressure abnormal fluctuation value with a preset blood pressure abnormal fluctuation threshold. If the blood pressure abnormal fluctuation value is greater than or equal to the preset blood pressure abnormal fluctuation threshold, there is abnormal fluctuation in the patient's blood pressure; if the blood pressure abnormal fluctuation value is less than the preset blood pressure abnormal fluctuation threshold, there is no abnormal fluctuation in the patient's blood pressure;

[0024] Step 15: Generate a targeted blood pressure fluctuation record based on the blood pressure abnormal fluctuation value and whether there is abnormal fluctuation in the patient's blood pressure.

[0025] As a further solution of the present invention, in Step 2, collect the patient's historical medical records and language samples during each medical visit, analyze the patient's language emotions based on the language samples, and form a personalized nursing record. The specific steps are as follows:

[0026] Step 21: Collect the patient's historical medical records and language samples during each medical visit; the historical medical records include the patient's blood pressure data; the language samples are obtained by the doctor asking the patient about the home situation, and the home situation includes the health status, emotional status, sleep status, and appetite status;

[0027] Step 22: Convert the language sample into text format through automatic language recognition technology to obtain the medical treatment text. Use a Chinese word segmentation tool to segment the medical treatment text, obtaining a sequence of medical treatment vocabulary. Perform part-of-speech tagging on the sequence of medical treatment vocabulary.

[0028] Step 23: Construct a medical treatment preset sentiment dictionary, divide the medical treatment preset sentiment vocabulary into positive effect words, neutral effect words, and negative effect words. Traverse the sequence of medical treatment vocabulary, match the medical treatment vocabulary with the medical treatment preset sentiment dictionary, and extract the successfully matched medical treatment preset emotion vocabulary and classify it.

[0029] Step 24: Evaluate the emotional tendency of the language sample based on the classification results. Obtain the number of positive effect words, the number of neutral effect words, and the number of negative effect words through the classification results. Import the number of positive effect words, the number of neutral effect words, and the number of negative effect words into the calculation formula of the emotional tendency evaluation coefficient to calculate the emotional tendency evaluation coefficient. The calculation formula of the emotional tendency evaluation coefficient is:

[0030]

[0031] In the formula: S emo is the emotional tendency evaluation coefficient, P is the number of positive effect words, Z is the number of neutral effect words, and N is the number of negative effect words;

[0032] Step 25: Divide the emotional category conveyed by the language sample into three categories according to the emotional tendency evaluation coefficient: When the value of the emotional tendency evaluation coefficient is greater than zero, the emotion conveyed by the language sample is positive, and the patient's emotional state is positive and optimistic at this time; when the value of the emotional tendency evaluation coefficient is equal to zero, the emotion conveyed by the language sample is neutral, and the patient's emotional state is stable at this time; when the value of the emotional tendency evaluation coefficient is less than zero, the emotion conveyed by the language sample is negative, and the patient's emotional state is negatively anxious at this time.

[0033] Step 26: Form a personalized nursing record based on the emotional tendency evaluation coefficient and the patient's emotional state.

[0034] As a further solution of the present invention, in step 3, comprehensively evaluate the patient's rehabilitation effect based on the blood pressure fluctuation record and the personalized nursing record. The specific steps are:

[0035] Step 31: Extract the patient's targeted blood pressure fluctuation record and personalized nursing record respectively. Generate a first coefficient set based on the targeted blood pressure fluctuation record to obtain the blood pressure abnormal fluctuation value at each time point within two adjacent medical treatments, and generate a second coefficient set based on the personalized nursing record to obtain the patient's emotional tendency evaluation coefficient at each medical treatment.

[0036] Step 32: Construct a rehabilitation effectiveness evaluation model based on the first coefficient set and the second coefficient set to evaluate the patient's rehabilitation effectiveness;

[0037] Step 33: Extract the patient's rehabilitation effectiveness value, and compare the patient's rehabilitation effectiveness value with the preset rehabilitation effectiveness threshold of the patient. If the patient's rehabilitation effectiveness value is greater than or equal to the preset rehabilitation effectiveness threshold of the patient, the patient's rehabilitation effectiveness meets the standard; if the patient's rehabilitation effectiveness value is less than the preset rehabilitation effectiveness threshold of the patient, the patient's rehabilitation effectiveness does not meet the standard.

[0038] The technical effects and advantages of a hypertension collaborative management method based on the integration of case management and narrative nursing in the present invention: The present invention uses an intelligent blood pressure detection device to regularly monitor the patient's blood pressure, and uses an anomaly detection and recognition algorithm to specifically identify the patient's blood pressure fluctuations and generate targeted blood pressure fluctuation records, which can intervene at the initial stage of the patient's blood pressure fluctuations and avoid the aggravation of the condition or the occurrence of complications caused by delayed treatment; collect the patient's historical medical records and language samples during each medical visit, analyze the patient's language emotions based on the language samples to form personalized nursing records, and by analyzing the patient's language samples, pay attention to the patient's psychological needs and emotional state to achieve comprehensive health management of the patient; comprehensively evaluate the patient's rehabilitation effectiveness based on the blood pressure fluctuation records and personalized nursing records, making up for the neglect of the patient's emotional and psychological needs in traditional hypertension management, and can significantly improve the patient's medical experience and rehabilitation effect. Description of the Drawings

[0039] Figure 1 This is the user blood pressure detection management interface shown on the doctor side provided by the present invention;

[0040] Figure 2 This is a schematic flowchart of a hypertension collaborative management method based on the integration of case management and narrative nursing provided by the present invention;

[0041] Figure 3 This is a schematic flowchart of Step 1 in a hypertension collaborative management method based on the integration of case management and narrative nursing provided by the present invention;

[0042] Figure 4 This is a schematic flowchart of Step 2 in a hypertension collaborative management method based on the integration of case management and narrative nursing provided by the present invention;

[0043] Figure 5 This is a schematic flowchart of Step 3 in a hypertension collaborative management method based on the integration of case management and narrative nursing provided by the present invention. Detailed Embodiments

[0044] Next, the technical solutions of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the present invention. Obviously, the described technical solutions are only a part of the present invention, rather than all of it. Based on the technical solutions in the present invention, all other technical solutions obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0045] Figure 2 It is a schematic flowchart of a collaborative management method for hypertension based on the integration of case management and narrative nursing provided by the present invention. As Figure 2 shown, a collaborative management method for hypertension based on the integration of case management and narrative nursing includes the following steps:

[0046] Step 1: Regularly monitor the patient's blood pressure through an intelligent blood pressure detection device, and use an anomaly detection and recognition algorithm to specifically identify the patient's blood pressure fluctuations, generating targeted blood pressure fluctuation records;

[0047] Step 2: Collect the patient's historical medical records and language samples during each medical visit, analyze the patient's language emotions based on the language samples, and form personalized nursing records;

[0048] Step 3: Comprehensively evaluate the patient's rehabilitation effect based on the blood pressure fluctuation records and personalized nursing records.

[0049] As Figure 1 shown in the user blood pressure detection management interface displayed on the doctor's side, Doctor Zhang opens the blood pressure detection management interface of a 65-year-old patient, showing the patient's current blood pressure values, including a systolic blood pressure of 135, a diastolic blood pressure of 85, and a pulse of 75. This month, the patient's blood pressure has abnormal fluctuations 3 times, and the compliance rate is 92%. According to the analysis of the data updated most recently, the emotional tendency evaluation coefficient of the patient at this time is 0.85, and the emotional state is positive. A line chart of the patient's blood pressure trend analysis and a line chart of the emotional trend analysis are also shown. From the line chart of the patient's blood pressure trend analysis, the changes in the patient's systolic blood pressure, diastolic blood pressure, and pulse can be seen every day. The line chart of the emotional trend analysis reflects the changes in the patient's daily emotional coefficient (i.e., the emotional tendency evaluation coefficient).

[0050] Figure 3 It is a schematic flowchart of Step 1 in a collaborative management method for hypertension based on the integration of case management and narrative nursing of the present invention; specifically, in Step 1, the blood pressure data of the patient is regularly monitored through an intelligent blood pressure detection device, and an anomaly detection and recognition algorithm is used to specifically identify the patient's blood pressure fluctuations, generating targeted blood pressure fluctuation records. The specific steps are as follows:

[0051] Step 11: Regularly monitor the patient's first blood pressure data set X = {x1, x2, …, x i , …, xn}, where x1 is the first blood pressure data at the first time point, x2 is the first blood pressure data at the second time point, x i is the first blood pressure data at the i-th time point, x n is the first blood pressure data at the n-th time point, x i =(SBP i , DBP i , MB i ), SBP i is the i-th first systolic blood pressure, DBP i is the i-th first diastolic blood pressure, MB i is the i-th first pulse beating frequency; The first blood pressure data values of the patient at each time point for a consecutive month are taken as the observed blood pressure data;

[0052] Step 12, Extract the observed blood pressure data and import it into the blood pressure reference coefficient calculation formula to calculate the blood pressure parameter coefficient. The blood pressure reference coefficient calculation formula is:

[0053]

[0054] In the formula: X hy is the blood pressure reference coefficient, is the first systolic blood pressure in the observed blood pressure data at the j-th time point, is the maximum value of the first systolic blood pressure in the observed blood pressure data, is the first diastolic blood pressure in the observed blood pressure data at the j-th time point, is the maximum value of the first diastolic blood pressure in the observed blood pressure data, is the first pulse beating frequency in the observed blood pressure data at the j-th time point, is the maximum value of the first pulse beating frequency in the observed blood pressure data, m is the number of acquisitions of the observed blood pressure data;

[0055] Step 13, Construct a blood pressure fluctuation abnormality analysis model based on the first blood pressure dataset and the blood pressure reference coefficient, and analyze whether there is abnormal fluctuation in the patient's blood pressure. Among them, the formula of the blood pressure abnormality analysis model is:

[0056]

[0057] In the formula: X b is the blood pressure abnormal fluctuation value, X hy is the blood pressure reference coefficient, n is the number of acquisitions of the first blood pressure data, x i is the first blood pressure data at the i-th time point, x b is the mean value of the first blood pressure data;

[0058] Step 14: Obtain the abnormal blood pressure fluctuation value, and compare it with the preset abnormal blood pressure fluctuation threshold. If the abnormal blood pressure fluctuation value is greater than or equal to the preset abnormal blood pressure fluctuation threshold, then the patient's blood pressure has abnormal fluctuations; if the abnormal blood pressure fluctuation value is less than the preset abnormal blood pressure fluctuation threshold, then the patient's blood pressure does not have abnormal fluctuations.

[0059] Step 15: Generate a targeted blood pressure fluctuation record based on the abnormal blood pressure fluctuation value and whether the patient's blood pressure has abnormal fluctuations.

[0060] Through the timing monitoring mechanism, the device can continuously collect the blood pressure data set of the patient for one month, covering different time periods throughout the day, ensuring comprehensive data and avoiding misjudgment caused by occasional measurement errors. The observed data includes systolic blood pressure (SBP), diastolic blood pressure (DBP), and pulse frequency (MB). The multi-dimensional comprehensive evaluation of the patient's blood pressure status improves the accuracy of abnormal detection and reduces the risk of missed diagnosis or misdiagnosis; by calculating the blood pressure reference coefficient, the blood pressure data at different time points are standardized and normalized, so that the blood pressure fluctuation is quantified into a specific mathematical expression, avoiding subjective judgment, accurately reflecting the degree of the patient's blood pressure fluctuation, constructing an abnormal fluctuation analysis model, dynamically fitting the patient's blood pressure, sensitively capturing small fluctuations, and early warning potential risks; when the blood pressure fluctuation value exceeds the preset threshold, the system immediately generates an abnormal fluctuation record, and the doctor can quickly intervene according to the record to prevent the patient from entering a high-risk state or having an acute hypertension event. By analyzing the trend of blood pressure data through algorithms, a targeted blood pressure fluctuation record is automatically generated, reducing manual intervention, improving management efficiency and accuracy, and ensuring that the patient's blood pressure is always within a controllable range; the abnormal blood pressure fluctuation threshold can be dynamically adjusted according to the patient's age, past medical history, and physiological differences, avoiding a "one-size-fits-all" standard and providing a management plan that better meets the individual needs of the patient. According to the blood pressure fluctuation record, the doctor can formulate a personalized nursing and treatment plan for the patient's blood pressure fluctuation characteristics, optimize the drug dosage or lifestyle intervention measures, and improve the treatment effect; through the long-term accumulation of blood pressure data, the system can analyze the long-term blood pressure fluctuation trend of the patient, provide a periodic health assessment report for the doctor, contribute to the prevention and control of hypertension and chronic diseases, and reduce the risk of cardiovascular and cerebrovascular complications. Being able to receive abnormal fluctuation records regularly helps to improve the awareness of self-health management, adjust lifestyle in time, and reduce the negative impact of external risk factors on blood pressure; through the integration of intelligent blood pressure detection equipment and abnormal detection algorithms, the refined dynamic monitoring of hypertensive patients is realized, greatly improving the accuracy of identifying abnormal blood pressure fluctuations, helping doctors to detect potential risks in time, promoting the long-term stable control of the patient's blood pressure, thereby reducing the incidence of acute events and the medical burden, and having significant clinical and social value.

[0061] Figure 4This is the process schematic diagram of step 2 in a hypertension collaborative management method based on the integration of case management and narrative nursing in the present invention; specifically, in step 2, the historical medical records of the patient and the language samples during each medical visit are collected, and the language emotions of the patient are analyzed based on the language samples to form a personalized nursing record. The specific steps are as follows:

[0062] Step 21, collect the historical medical records of the patient and the language samples during each medical visit; the historical medical records include the patient's blood pressure data; the language samples are obtained by the doctor asking the patient about the home situation, and the home situation includes the health status, emotional status, sleep status, and appetite status;

[0063] Step 22, convert the language samples into text format through automatic language recognition technology to obtain medical visit texts, use a Chinese word segmentation tool to segment the medical visit texts, obtain a medical visit vocabulary sequence after segmentation, and perform part-of-speech tagging on the medical visit vocabulary sequence;

[0064] Step 23, construct a medical visit preset emotion dictionary, divide the medical visit preset emotion words into positive effect words, neutral effect words, and negative effect words, traverse the medical visit vocabulary sequence, match the medical visit vocabulary with the medical visit preset emotion dictionary, extract the successfully matched medical visit preset emotion words and classify them;

[0065] Step 24, evaluate the emotional tendency of the language samples according to the classification results, obtain the number of positive effect words, the number of neutral effect words, and the number of negative effect words through the classification results, and import them into the emotional tendency evaluation coefficient calculation formula to calculate the emotional tendency evaluation coefficient. The emotional tendency evaluation coefficient calculation formula is:

[0066]

[0067] In the formula: S emo is the emotional tendency evaluation coefficient, P is the number of positive effect words, Z is the number of neutral effect words, and Z is the number of negative effect words;

[0068] Step 25, divide the emotional categories conveyed by the language samples into three categories according to the emotional tendency evaluation coefficient: when the value of the emotional tendency evaluation coefficient is greater than zero, the emotion conveyed by the language sample is positive, and the patient's emotional state is positive and optimistic at this time; when the value of the emotional tendency evaluation coefficient is equal to zero, the emotion conveyed by the language sample is neutral, and the patient's emotional state is stable at this time; when the value of the emotional tendency evaluation coefficient is less than zero, the emotion conveyed by the language sample is negative, and the patient's emotional state is negatively anxious at this time;

[0069] Step 26, form a personalized nursing record based on the emotional tendency evaluation coefficient and the patient's emotional state.

[0070] Through the emotional tendency evaluation coefficient formula, the emotional components (positive, neutral, negative) in the patient's language sample are quantitatively and structurally analyzed to eliminate the uncertainty of subjective judgment, improve the evaluation accuracy, distinguish the patient's emotional state as positive and optimistic, neutral and stable, or negative and anxious, facilitate doctors to timely identify the patient's mental health problems, such as anxiety or depression, and conduct targeted psychological interventions; the blood pressure data is recorded in the historical medical record, and at the same time, combined with the emotional analysis of the language sample, a psychological dimension is introduced in the blood pressure fluctuation evaluation to comprehensively analyze the impact of mental state on blood pressure fluctuation, avoid one-sided focus on physiological indicators and ignore psychological factors, for patients in the negative and anxious state, reduce psychological stress through language support and emotional counseling, thereby indirectly stabilizing blood pressure and improving the overall rehabilitation effect; based on the emotional state and evaluation coefficient, the generated nursing record is specific to the patient's psychological characteristics and emotional change trend, avoiding the "one-size-fits-all" nursing plan, improving the patient's sense of participation and compliance, for patients with a negative and anxious emotional tendency evaluation result, it is recommended to provide psychological counseling, stress management or relaxation training; for patients with stable emotions, emphasize maintaining a good state; for patients with positive and optimistic emotions, encourage maintaining positive emotions; the emotional tendency evaluation results of each medical record, combined with the blood pressure fluctuation data, form a dynamic trend analysis to observe the long-term impact of mental state on blood pressure fluctuation and provide data support for subsequent interventions, by correlating the emotional tendency evaluation coefficient with the abnormal blood pressure fluctuation value, establishing an analysis model of the psychological and physiological linkage to achieve more refined management; through emotional tendency analysis and personalized nursing record generation, it makes up for the neglect of patients' psychological needs in traditional hypertension management, and has significant advantages in improving the patient's rehabilitation effect, optimizing doctor-patient interaction, supporting case management and group analysis, etc., and is applicable to various scenarios such as clinical and community health management.

[0071] Among them, the doctor constructs the language sample by asking the patient about the home situation, and the home situation includes health status, emotional status, sleep status, and appetite status. The medical visit preset emotional dictionary is constructed based on the four home situations of health status, emotional status, sleep status, and appetite status, and the medical visit preset emotional words are divided into positive effect words, neutral effect words, and negative effect words. Among them, the summary table of the medical visit preset emotional words related to the health status in the medical visit preset emotional dictionary is shown in Table 1:

[0072]

[0073]

[0074] Table 1 Summary table of the medical visit preset emotional words related to the health status in the medical visit preset emotional dictionary

[0075] The summary table of the medical visit preset emotional words related to the emotional status in the medical visit preset emotional dictionary is shown in Table 2:

[0076]

[0077] Table 2 Summary Table of Medical Treatment Preset Emotional Vocabulary Related to Emotional Status in the Medical Treatment Preset Emotional Lexicon

[0078] The summary table of the medical treatment preset emotional vocabulary related to sleep status in the medical treatment preset emotional lexicon is shown in Table 3 as follows:

[0079]

[0080]

[0081] Table 3 Summary Table of Medical Treatment Preset Emotional Vocabulary Related to Sleep Status in the Medical Treatment Preset Emotional Lexicon

[0082] The summary table of the medical treatment preset emotional vocabulary related to appetite status in the medical treatment preset emotional lexicon is shown in Table 4 as follows:

[0083]

[0084] Table 4 Summary Table of Medical Treatment Preset Emotional Vocabulary Related to Appetite Status in the Medical Treatment Preset Emotional Lexicon

[0085] Figure 5 It is the flow diagram of step 3 in a hypertension collaborative management method based on the integration of case management and narrative nursing of the present invention; specifically, in step 3, based on the blood pressure fluctuation record and personalized nursing record, the rehabilitation effect of the patient is comprehensively evaluated, and the specific steps are as follows:

[0086] Step 31, extract the targeted blood pressure fluctuation record and personalized nursing record of the patient respectively. Based on the targeted blood pressure fluctuation record, obtain the blood pressure abnormal fluctuation value at each time point within two adjacent medical treatments to generate the first coefficient set, and based on the personalized nursing record, obtain the patient's emotional tendency evaluation coefficient at each medical treatment to generate the second coefficient set;

[0087] Step 32, construct a rehabilitation effect evaluation model according to the first coefficient set and the second coefficient set to evaluate the rehabilitation effect of the patient. The formula of the rehabilitation effect evaluation model is:

[0088]

[0089] In the formula: K cx is the rehabilitation effect value of the patient, S emo t is the emotional tendency evaluation coefficient at the t-th medical treatment, is the blood pressure abnormal fluctuation value at the f-th time point between the t-th medical treatment and the (t + 1)-th medical treatment, is the maximum blood pressure abnormal fluctuation value between the t-th medical treatment and the (t + 1)-th medical treatment, is the minimum abnormal blood pressure fluctuation value between the t-th medical visit and the (t + 1)-th medical visit, and T is the number of medical visits.

[0090] Step 33: Extract the patient's rehabilitation effectiveness value, and compare the patient's rehabilitation effectiveness value with the preset rehabilitation effectiveness threshold of the patient. If the patient's rehabilitation effectiveness value is greater than or equal to the preset rehabilitation effectiveness threshold of the patient, the patient's rehabilitation effectiveness meets the standard; if the patient's rehabilitation effectiveness value is less than the preset rehabilitation effectiveness threshold of the patient, the patient's rehabilitation effectiveness does not meet the standard.

[0091] Embodiment 2

[0092] A hypertensive patient used a smart sphygmomanometer to continuously monitor for 30 days (3 times a day, morning, noon, and evening), and a total of 90 sets of blood pressure monitoring data were collected. Table 1 below shows some of the smart blood pressure monitoring data.

[0093]

[0094]

[0095] Obtained based on 90 sets of blood pressure data The total relative difference of 90 sets of blood pressure is 24.3, the blood pressure reference coefficient is 0.27, the mean systolic blood pressure is obtained as 138 mmHg, the mean diastolic blood pressure is 86 mmHg, and the mean pulse is 77 bpm. Based on the above data, the abnormal blood pressure fluctuation value is calculated as 4.6.

[0096] Construct a rehabilitation effectiveness evaluation model through dual data of abnormal blood pressure fluctuations (reflecting physiological fluctuations) and emotional tendency evaluation coefficients (reflecting psychological states), comprehensively reflecting the linkage between psychology and physiology during the patient's rehabilitation process, overcoming the limitations of traditional methods that only focus on blood pressure or pathological indicators. Introduce an emotional tendency coefficient in the evaluation process, considering the impact of emotional fluctuations on abnormal blood pressure, making the evaluation closer to the actual recovery of the patient, and avoiding the neglect or misjudgment of hypertension fluctuations; through continuous blood pressure and emotion records, the system automatically extracts blood pressure fluctuation values and emotion evaluation results between two adjacent medical consultations, dynamically tracking the rehabilitation process, and promptly capturing abnormal conditions during the patient's rehabilitation. When the rehabilitation effectiveness value is lower than the threshold, the system automatically alerts the doctor, indicating that the patient's rehabilitation process is blocked or there is a risk of hypertension fluctuations. The doctor can adjust the drug regimen or increase psychological intervention accordingly to avoid the deterioration of the condition; dynamically evaluate the rehabilitation effect according to individual differences, which helps doctors customize personalized rehabilitation plans for patients, ensuring that nursing measures match the actual needs of patients. Automatically generate nursing records and rehabilitation reports based on the rehabilitation effectiveness, reducing the workload of doctors' manual records and analysis, and improving management efficiency; monitor the hypertension fluctuation trend through abnormal blood pressure fluctuation values, promptly identify patients with unstable blood pressure, reduce the risk of hypertension recurrence caused by neglect or emotional fluctuations in the later stage of rehabilitation. The evaluation model covers the entire treatment cycle, continuously monitoring the fluctuations of patients' blood pressure and emotions, ensuring that even in the later stage of rehabilitation, patients can maintain a relatively stable blood pressure state and reduce the occurrence of cardiovascular and cerebrovascular complications; screen out patients with substandard rehabilitation through the rehabilitation effectiveness evaluation value, prioritize further intervention, reduce unnecessary reexaminations and resource waste, concentrate medical resources on patients who truly need continuous management, and for patients with good rehabilitation progress, reduce unnecessary medical visits and avoid repeated examinations, improving the follow-up efficiency, enabling doctors to focus on managing patients with complex or fluctuating conditions.

[0097] In the embodiment of the present invention, the intelligent blood pressure detection device regularly monitors the blood pressure of the patient, and uses an anomaly detection and recognition algorithm to specifically recognize the blood pressure fluctuations of the patient, generating targeted blood pressure fluctuation records, which can intervene at the initial stage of the patient's blood pressure fluctuations, avoiding the aggravation of the condition or the occurrence of complications due to delayed treatment; collect the patient's historical medical records and language samples during each medical consultation, analyze the patient's language emotions based on the language samples, form personalized nursing records, and by analyzing the patient's language samples, pay attention to the patient's psychological needs and emotional states, realizing the comprehensive health management of the patient; comprehensively evaluate the patient's rehabilitation effectiveness based on the blood pressure fluctuation records and personalized nursing records, making up for the neglect of the patient's emotional and psychological needs in traditional hypertension management, and significantly improving the patient's medical experience and rehabilitation effect.

[0098] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims described above.

[0099] Finally: The above description is only the preferred solution of the present invention and is not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A collaborative management method for hypertension based on the integration of case management and narrative nursing, characterized in that, It includes the following steps: Step 1: Regularly monitor the patient's blood pressure through an intelligent blood pressure detection device, and use an anomaly detection and recognition algorithm to specifically identify the patient's blood pressure fluctuations, generating targeted blood pressure fluctuation records; Step 2: Collect the patient's historical medical records and language samples during each medical visit, analyze the patient's language emotions based on the language samples, and form personalized nursing records; Step 3: Comprehensively evaluate the patient's rehabilitation effect based on the targeted blood pressure fluctuation records and personalized nursing records. The construction steps of the rehabilitation effect evaluation model are as follows: For each stage from the first medical visit to the (T - 1)-th medical visit, calculate the influence value of emotional tendency on rehabilitation. For the blood pressure fluctuations within this stage, normalize by taking the blood pressure anomaly fluctuation value at a certain time point and the range of the blood pressure fluctuation interval within this stage to obtain the relative level of the fluctuation at this time point in the overall interval. Multiply the emotional influence value of each stage by the normalized blood pressure fluctuation value and sum over all stages to obtain the comprehensive rehabilitation effect value.

2. The collaborative hypertension management method based on the integration of case management and narrative nursing according to claim 1, characterized in that, In Step 1, regularly monitor the patient's blood pressure data through an intelligent blood pressure detection device, and use an anomaly detection and recognition algorithm to specifically identify the patient's blood pressure fluctuations, generating targeted blood pressure fluctuation records. The specific steps are as follows: Step 11, regularly monitor the patient's first blood pressure dataset X = {x1, x2, …, x i , …, x n}, where x1 is the first blood pressure data at the first time point, x2 is the first blood pressure data at the second time point, x i is the first blood pressure data at the i-th time point, x n is the first blood pressure data at the n-th time point, x i = (SBP i , DBP i , MB i ), SBP i is the i-th first systolic blood pressure, DBP i is the i-th first diastolic blood pressure, MB i is the i-th first pulse rate; take the first blood pressure data values at each time point of the patient for a consecutive month as the observed blood pressure data; Step 12: Extract the observed blood pressure data and import it into the blood pressure reference coefficient calculation formula to calculate the blood pressure parameter coefficients; Step 13: Construct a blood pressure fluctuation anomaly analysis model based on the first blood pressure dataset and the blood pressure reference coefficient to analyze whether there are abnormal fluctuations in the patient's blood pressure. For each time point i, first take the blood pressure data at this moment, then multiply it by the blood pressure reference coefficient, and perform normalization by subtracting the value of the exponential function from 1. Accumulate the processed results of each time point to obtain the blood pressure anomaly fluctuation; Step 14: Obtain the blood pressure anomaly fluctuation value, and compare the blood pressure anomaly fluctuation value with a preset blood pressure anomaly fluctuation threshold. If the blood pressure anomaly fluctuation value is greater than or equal to the preset blood pressure anomaly fluctuation threshold, then there are abnormal fluctuations in the patient's blood pressure; if the blood pressure anomaly fluctuation value is less than the preset blood pressure anomaly fluctuation threshold, then there are no abnormal fluctuations in the patient's blood pressure; Step 15: Generate targeted blood pressure fluctuation records based on the blood pressure anomaly fluctuation value and whether there are abnormal fluctuations in the patient's blood pressure; 3. The collaborative management method for hypertension based on the integration of case management and narrative nursing according to claim 2, characterized in that, In step 12, the observed blood pressure data is extracted and imported into the blood pressure reference coefficient calculation formula to calculate the blood pressure parameter coefficients. For each observation time point j, the first systolic blood pressure is extracted from the blood pressure data The first diastolic blood pressure and the first pulse beating frequency The maximum values of these three items are determined respectively among all the data, which are For each time point j, calculate respectively The ratio of and The ratio of and, and The ratio of The absolute value is taken after adding these three ratios, and the calculation results of all m time points are summed and divided by m to obtain the blood pressure reference coefficient.

4. The hypertension collaborative management method based on the integration of case management and narrative nursing according to claim 1, wherein In Step 2, collect the patient's historical medical records and language samples during each medical visit, analyze the patient's language emotions based on the language samples, and form personalized nursing records. The specific steps are as follows: Step 21: Collect the patient's historical medical records and language samples during each medical visit; the historical medical records include the patient's blood pressure data; the language samples are obtained by the doctor asking the patient about their home situation, which includes health status, emotional status, sleep status, and appetite status; Step 22: Convert the language samples into text format through automatic speech recognition technology to obtain medical visit texts, use a Chinese word segmentation tool to segment the medical visit texts, obtain the medical visit vocabulary sequence, and perform part-of-speech tagging on the medical visit vocabulary sequence; Step 23: Construct a preset emotion dictionary for medical treatment. Classify the preset emotion words for medical treatment into positive effect words, neutral effect words, and negative effect words. Traverse the medical vocabulary sequence, match the medical vocabulary with the preset emotion dictionary for medical treatment, and extract and classify the successfully matched preset emotion words for medical treatment. Step 24: Evaluate the emotional tendency of the language sample based on the classification results. Obtain the number of positive effect words, neutral effect words, and negative effect words from the classification results, and import them into the emotional tendency evaluation coefficient calculation formula to calculate the emotional tendency evaluation coefficient. Step 25: Divide the emotional categories conveyed by the language sample into three categories according to the emotional tendency evaluation coefficient: When the value of the emotional tendency evaluation coefficient is greater than zero, the emotion conveyed by the language sample is positive, and the patient's emotional state is positive and optimistic at this time; when the value of the emotional tendency evaluation coefficient is equal to zero, the emotion conveyed by the language sample is neutral, and the patient's emotional state is stable at this time; when the value of the emotional tendency evaluation coefficient is less than zero, the emotion conveyed by the language sample is negative, and the patient's emotional state is negatively anxious at this time. Step 26: Form a personalized nursing record based on the emotional tendency evaluation coefficient and the patient's emotional state.

5. The collaborative hypertension management method based on the integration of case management and narrative nursing according to claim 1, characterized in that, In Step 3, comprehensively evaluate the patient's rehabilitation effect based on the blood pressure fluctuation record and the personalized nursing record. The specific steps are as follows: Step 31: Extract the targeted blood pressure fluctuation record and the personalized nursing record of the patient respectively. Generate a first coefficient set of blood pressure abnormal fluctuation values at each time point within two adjacent medical treatments based on the targeted blood pressure fluctuation record, and generate a second coefficient set of the patient's emotional tendency evaluation coefficients at each medical treatment based on the personalized nursing record. Step 32: Construct a rehabilitation effect evaluation model according to the first coefficient set and the second coefficient set to evaluate the patient's rehabilitation effect. Step 33: Extract the patient's rehabilitation effect value, and compare the patient's rehabilitation effect value with the preset rehabilitation effect threshold of the patient. If the patient's rehabilitation effect value is greater than or equal to the preset rehabilitation effect threshold of the patient, the patient's rehabilitation effect meets the standard; if the patient's rehabilitation effect value is less than the preset rehabilitation effect threshold of the patient, the patient's rehabilitation effect does not meet the standard.

Images