Nursing scheme auxiliary generation method for chronic obstructive pulmonary disease patient

Abstract

The invention relates to the technical field of medical data mining and recommendation, in particular to a nursing scheme auxiliary generation method for a patient with chronic obstructive pulmonary disease. The method comprises the following steps: acquiring an FEV1 / FVC ratio of a patient as a respiratory health index; clustering is carried out according to the difference characteristics of the respiratory health indexes of different patients at the current moment, and other patients in the cluster where the current patient is located serve as target patients in sequence; further obtaining a symptom slowing coefficient according to the decline feature and the overall decline feature of the respiratory health index in each acute exacerbation period of the illness state; further obtaining a reference coefficient according to the continuity characteristic of the illness state stability maintenance improvement period of the target patient; according to the difference characteristic of the symptom slowing coefficient of the current patient and the symptom slowing coefficient of the target patient, in combination with the reference coefficient, the patient which is most similar to the current illness state of the current patient, most similar to illness state change and high in reference value is finally screened out, and a reliable auxiliary basis is provided for a nursing scheme of the chronic obstructive pulmonary disease patient.

Description

Technical Field

[0001] The present invention relates to the field of medical data mining and recommendation technology, and in particular to a method for assisting in generating a nursing plan for patients with chronic obstructive pulmonary disease. Background Art

[0002] In the process of generating nursing plans for patients with chronic obstructive pulmonary disease (COPD), by referring to the nursing plans of historical patients with similar conditions to the current patient, we can find out which treatment measures are more effective for the current patient, so as to develop a more personalized treatment plan for the current patient. By analyzing the nursing plans and treatment outcomes of historical patients, we can identify deficiencies in nursing practice, thereby promoting continuous improvement in nursing quality.

[0003] Existing patient classification methods often only consider the patient's lung function at the current moment. However, COPD is a dynamic disease. Existing patient classification methods may not be able to reflect changes in the disease in a timely manner, which may lead to inaccurate patient classification and inaccurate screening of historical patients with similar conditions, resulting in unreliable reference nursing plans and poor results in the generation of auxiliary nursing plans. Summary of the invention

[0004] In order to solve the technical problem that the existing screening and classification of similar patients with COPD is inaccurate, which affects the reference effect of the nursing plan and leads to unsatisfactory effect of auxiliary nursing plan generation, the purpose of the present invention is to provide a method for auxiliary generation of nursing plans for COPD patients. The technical scheme adopted is as follows: The FEV1 / FVC ratio of the patient is obtained as a respiratory health index; clustering is performed according to the difference characteristics of the respiratory health index between different patients at the current moment, and each other patient in the cluster where the current patient is located is taken as a target patient in turn; According to the change characteristics of the respiratory health index of the target patient, the acute exacerbation period and the stable improvement period of the condition of the target patient are obtained; according to the decline characteristics of the respiratory health index of the target patient in each period of acute exacerbation of the condition, combined with the overall decline characteristics of the respiratory health index, the symptom relief coefficient of the target patient is obtained; According to the continuity characteristics of the target patient's condition stabilization and improvement period, the reference coefficient of the target patient is obtained; according to the difference characteristics of the symptom relief coefficients between the current patient and the target patient, combined with the corresponding reference coefficients, the reference patient of the current patient is screened out.

[0005] Furthermore, the method for obtaining the acute exacerbation period and the stable improvement period of the condition includes: For the target patient, the degree of lung function decline at each moment is obtained according to the difference between the respiratory health index at each moment and the respiratory health index at the next moment adjacent in time sequence; The moment when the degree of lung function decline is greater than a first preset threshold is marked as an acute exacerbation moment; the moment when the degree of lung function decline is less than a second preset threshold is marked as a stabilization improvement moment; The time period formed by the adjacent acute exacerbation moments is taken as the acute exacerbation period; the time period formed by the adjacent stabilization and improvement moments is taken as the stabilization and improvement period.

[0006] Furthermore, the method for obtaining the symptom relief coefficient includes: The decreasing rates of the respiratory health index of the target patient at the first and last moments in the time domain are negatively correlated and normalized to serve as the overall stability coefficient of the lung function of the target patient; For the target patient, in each period of acute exacerbation, the decreasing rates of the respiratory health index at the first and last moments are normalized and used as the degree of aggravation of the condition in each period of acute exacerbation; the local decline coefficient of lung function of the target patient is obtained according to the time intervals of all the acute exacerbation periods adjacent in time sequence and the degree of aggravation; the time intervals of the acute exacerbation periods adjacent in time sequence are negatively correlated with the local decline coefficient of lung function; the degree of aggravation of the acute exacerbation periods adjacent in time sequence is positively correlated with the local decline coefficient of lung function; According to the overall stability coefficient of lung function and the local decline coefficient of lung function of the target patient, the symptom relief coefficient of the target patient is obtained; the symptom relief coefficient is positively correlated with the overall stability coefficient of lung function; the symptom relief coefficient is negatively correlated with the local decline coefficient of lung function.

[0007] Furthermore, the method for obtaining the reference coefficient includes: For the target patient, the time domain proportion of all the periods of stable and improved condition during the treatment process is used as the first reference value coefficient of the target patient; The ratio of the longest duration of the disease condition stabilization and improvement period to the average of the time intervals of all adjacent disease condition stabilization and improvement periods is used as the second reference value coefficient; The first reference value coefficient and the second reference value coefficient of the target patient are integrated to obtain the reference coefficient of the target patient; the first reference value coefficient and the second reference value coefficient are both positively correlated with the reference coefficient.

[0008] Furthermore, the method for obtaining the reference patient includes: According to the absolute value of the difference between the symptom relief coefficient of the current patient and each of the target patients, combined with the reference coefficient of the target patient, the reference strength of each of the target patients for the current patient is obtained; the absolute value of the difference between the symptom relief coefficient of the current patient and each of the target patients is negatively correlated with the reference strength; the reference coefficient is positively correlated with the reference strength; Reference patients are screened according to the referenceable strengths.

[0009] Furthermore, the method for screening reference patients according to the referenceable strength includes: The target patient whose referenceable strength is greater than a preset screening threshold is marked as a reference patient.

[0010] Furthermore, the method of clustering according to the difference characteristics of the respiratory health index between different patients at the current moment includes: The absolute value of the difference between the respiratory health index of any two patients at the current moment is used as the cluster distance between the corresponding two patients, and hierarchical clustering is performed on all patients to obtain multiple clusters.

[0011] Furthermore, the target patient is a patient who already has an existing care plan and is still receiving treatment.

[0012] Furthermore, the symptom relief coefficient of the current patient and the symptom relief coefficient of the target patient are obtained in the same manner.

[0013] Furthermore, the FEV1 / FVC ratio of each patient is collected once a day.

[0014] The present invention has the following beneficial effects: The present invention first obtains the FEV1 / FVC ratio of the patient as a respiratory health index, and indicates the respiratory health state of the patient by the respiratory obstruction; further clusters the difference characteristics of the respiratory health index between different patients at the current moment, determines the target patient with a similar respiratory airflow obstruction as the current patient at the current moment, and preliminarily screens the patient; further obtains the acute exacerbation period and the stable improvement period of the condition of the target patient, and finely divides the different change periods of the respiratory health index of the target patient, so as to facilitate the subsequent more detailed analysis of the respiratory obstruction changes of the target patient; further analyzes the enhanced degree of respiratory obstruction during the treatment process from the overall perspective and the local perspective, obtains the symptom relief coefficient of the target patient, characterizes the condition control of the target patient during the nursing treatment process, and provides a basis for further screening of the target patient; further obtains the reference coefficient of the target patient according to the continuity characteristics of the stable improvement period of the condition of the target patient, reflects the respiratory effect of the nursing plan on the target patient, thereby reflecting the reference value of the nursing plan, and provides more basis for subsequent screening of the target patient; finally, according to the difference characteristics of the symptom relief coefficient between the current patient and the target patient, combined with the corresponding reference coefficient, the reference patient of the current patient is screened out. The present invention screens target patients through respiratory health index clustering, analyzes the time period of their condition changes, evaluates the symptom relief coefficient and reference coefficient, and ultimately screens out patients whose conditions are most similar to the current patient, whose changes are most consistent, and whose nursing plan reference value is high, providing a reliable auxiliary basis for the nursing plan for patients with COPD. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A flowchart of a method for assisting in generating a nursing plan for patients with chronic obstructive pulmonary disease provided by one embodiment of the present invention; Figure 2 A flowchart of a method for obtaining a symptom relief coefficient provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, characteristics and effects of a nursing plan auxiliary generation method for COPD patients proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0019] The following is a detailed description of a method for assisting in generating a nursing plan for COPD patients provided by the present invention in conjunction with the accompanying drawings.

[0020] See also Figure 1 , which shows a flow chart of a method for assisting in generating a nursing plan for COPD patients provided by an embodiment of the present invention, specifically comprising: Step S1: Obtain the patient's FEV1 / FVC ratio as a respiratory health index; cluster the patients according to the difference characteristics of the respiratory health indexes at the current moment, and take each other patient in the cluster where the current patient is located as a target patient in turn.

[0021] Forced Vital Capacity (FVC) is the maximum amount of air that a patient can exhale as quickly as possible after taking a deep breath. It is an important indicator for measuring lung capacity and function. Forced Expiratory Volume in 1 second (FEV1) is the amount of air that a patient can exhale in the first second after taking a deep breath. An FEV1 / FVC ratio lower than 0.70 is the main diagnostic criterion for COPD, indicating persistent airflow limitation. The smaller the FEV1 / FVC ratio, the more severe the airflow obstruction. Therefore, the patient's FEV1 / FVC ratio is obtained as a respiratory health index to represent the patient's respiratory health status.

[0022] In one embodiment of the present invention, starting from the time a patient is diagnosed with chronic obstructive pulmonary disease, the patient's FEV1 / FVC ratio is collected once a day using a pulmonary function tester. Each patient has a corresponding time series of FEV1 / FVC ratios, which are stored in the hospital database for easy retrieval.

[0023] Considering that the difference in respiratory health index between different patients reflects the difference in respiratory airflow obstruction, we first cluster them according to the difference characteristics of the respiratory health index between different patients at the current moment, and take each other patient in the cluster where the current patient is located as the target patient in turn, determine the target patient with similar respiratory airflow obstruction as the current patient at the current moment, and conduct preliminary screening of the patients.

[0024] It should be noted that since the purpose is to screen similar patients to learn from their care plans and assist in generating care plans for current patients, the target patients need to have existing care plans, while ensuring the timeliness of the treatment plans and avoiding outdated treatment plans. The target patients are also patients who are still receiving treatment.

[0025] Preferably, in one embodiment of the present invention, considering that the greater the absolute value of the difference in the respiratory health index of two patients at the current moment, the more obvious the difference characteristics of the respiratory health index, the greater the difference in the respiratory obstruction of the patients, and the more they cannot be classified into one category, the absolute value of the difference in the respiratory health index of any two patients at the current moment is used as the clustering distance between the corresponding two patients to express the difference characteristics of the respiratory health index, and all patients are hierarchically clustered to obtain multiple clusters.

[0026] As an example, agglomerative hierarchical clustering is used, the number of clusters is not preset, the cluster distance threshold is set to 0.1, and the link criterion uses the Ward method to obtain cluster clusters.

[0027] It should be noted that the hierarchical clustering algorithm is already an existing technology, and implementers can set other parameters of hierarchical clustering according to the implementation scenario, which will not be described in detail.

[0028] Step S2: According to the changing characteristics of the respiratory health index of the target patient, the acute exacerbation period and the stable improvement period of the target patient's condition are obtained; according to the decreasing characteristics of the respiratory health index of the target patient in each period of acute exacerbation of the condition, combined with the overall decreasing characteristics of the respiratory health index, the symptom relief coefficient of the target patient is obtained.

[0029] Due to the pathophysiological characteristics of COPD, the patient's lung function may gradually deteriorate over time. The goal of nursing for COPD patients is to slow down the rate of disease progression as much as possible. Therefore, according to the changing characteristics of the target patient's respiratory health index, the changes in the target patient's respiratory obstruction over time are analyzed, and the target patient's acute exacerbation period and the period of stable improvement of the condition are obtained. The different change periods of the target patient's respiratory health index are carefully divided to facilitate the subsequent more detailed analysis of the changes in the target patient's respiratory obstruction.

[0030] Preferably, in one embodiment of the present invention, considering that when the respiratory health index decreases, it can reflect a certain decrease in lung function from the perspective of respiratory obstruction, so for the target patient, the difference between the respiratory health index at each moment and the respiratory health index at the next moment adjacent in time sequence is used to represent the change characteristics of the respiratory health index, and the degree of lung function decline at each moment is obtained; Considering that the greater the decline in the respiratory health index, the more acute the increase in respiratory obstruction and the difficulty in breathing, reflecting the acute aggravation of the patient's condition, the moment when the decline in lung function is greater than the first preset threshold is marked as the acute aggravation moment; the moment when the decline in lung function is less than the second preset threshold is marked as the stabilization and improvement moment; The time period formed by adjacent acute exacerbation moments is regarded as the acute exacerbation period; the time period formed by adjacent stabilization and improvement moments is regarded as the stabilization and improvement period.

[0031] As an example, after linearly normalizing the difference between the respiratory health index at each moment and the respiratory health index at the next adjacent moment in time series, the difference between the respiratory health index at two moments is used as the minuend; the first preset threshold is 0.7, and the second preset threshold is 0.3, marking the moments of stable improvement and acute exacerbation. In addition, the moments when the degree of lung function decline is greater than or equal to 0.3 and less than or equal to 0.7 are marked as slowly aggravating moments, and the time period composed of adjacent slowly aggravating moments is the period of slowly aggravating disease.

[0032] Among them, the period of slow worsening of the condition is the normal process of the patient's condition change. The period of acute worsening of the condition is when the patient's condition rapidly deteriorates due to continued smoking or exposure to harmful environmental factors. The period of stable improvement of the condition is when the patient follows the doctor's advice for treatment and maintains lung function. Even after pulmonary rehabilitation training and the use of bronchodilators, there may be a slight increase in the FEV1 / FVC ratio.

[0033] It should be noted that the degree of lung function decline is not directly used as an indicator of lung function, but is only a basis for marking and determining the target patient at each moment; In another embodiment of the present invention, the implementer may also express the changing characteristics of the respiratory health index in the form of a ratio, such as linearly normalizing the ratio of the respiratory health index at each moment to the respiratory health index at the next adjacent moment in time series, and using the ratio as the degree of lung function decline at each moment. When the respiratory health indexes at two moments are divided by a quotient, the respiratory health index with the smallest time series is used as the dividend.

[0034] The overall decline in the target patient's respiratory health index reflects the increased degree of respiratory obstruction during the long-term treatment process from an overall perspective, and indirectly reflects the relief of the target patient's condition by nursing treatment; at the same time, the decline in the respiratory health index during each period of acute exacerbation reflects the increased degree of respiratory obstruction in a short period of time from a local perspective. Therefore, according to the decline in the target patient's respiratory health index during each period of acute exacerbation, combined with the overall decline in the respiratory health index, the symptom relief coefficient of the target patient is obtained. The symptom relief coefficient represents the target patient's condition control during the nursing treatment process, provides a basis for further screening of target patients, and improves the reference value of the final selected patients.

[0035] In a preferred embodiment of the present invention, the method for obtaining the symptom relief coefficient includes: Figure 2 , which shows a flow chart of a method for obtaining a symptom relief coefficient provided by an embodiment of the present invention, specifically comprising: Step S201: negatively correlate and normalize the decreasing rates of the respiratory health index of the target patient at the first and last moments in the time domain to obtain the overall stability coefficient of the lung function of the target patient.

[0036] Considering that the greater the decline in the respiratory health index of the target patient at the beginning and end of the time domain, and the shorter the time interval, it means that the respiratory health index of the target patient has dropped significantly in a shorter period of time. At this time, the greater the decline rate, the worse the effect of alleviating lung function decline, and the smaller the overall stability coefficient of lung function. Therefore, the decline rate of the respiratory health index of the target patient at the beginning and end of the time domain is negatively correlated and normalized as the overall stability coefficient of lung function of the target patient.

[0037] As an example, the calculation formula for the overall stability coefficient of lung function includes: ; Among them, i represents the serial number of the target patient; represents the overall stability coefficient of lung function of the i-th target patient; represents the linear normalization function; represents the respiratory health index of the i-th target patient at the first moment; represents the respiratory health index of the i-th target patient at the end moment; Indicates the time interval between the first and last moments; Represents the decreasing rate of the respiratory health index of the i-th target patient at the first and last moments.

[0038] In the calculation formula of the overall stability coefficient of lung function, the decline rate of the respiratory health index of the target patient at the first and last moments in the time domain is negatively mapped and normalized by first normalizing the decline rate and then performing negative correlation mapping, which shows the overall decline characteristics of the respiratory health index. From a holistic perspective, it measures the relief and stability of the lung function of the target patient after nursing treatment, and provides a basis for obtaining the symptom relief coefficient.

[0039] As another example, implementers may also As an independent variable, through a negative correlation mapping function such as an exponential function with the natural constant e as the base Negative correlation mapping is performed, and the mapping result is used as the overall stability coefficient of lung function. Represents the independent variable.

[0040] In another embodiment of the present invention, the implementer may also obtain the average value of the descent rate between two adjacent moments, instead of , indicating the overall downward trend of the respiratory health index, and obtaining the overall stability coefficient of lung function.

[0041] Step S202: For the target patient, in each acute exacerbation period, the decreasing rate of the respiratory health index at the first and last moments is normalized as the severity of each acute exacerbation period. According to the time intervals and severity of all adjacent acute exacerbation periods, the local decline coefficient of lung function of the target patient is obtained.

[0042] Similarly, during the period of acute exacerbation, the greater the rate of decrease of the respiratory health index at the first and last moments, the greater the severity of the condition during the period of acute exacerbation. Therefore, in each period of acute exacerbation, the rate of decrease of the respiratory health index at the first and last moments is normalized and used as the severity of the condition in each period of acute exacerbation.

[0043] Taking into account that the shorter the time interval between adjacent acute exacerbations, the greater the severity of the disease, which means that the target patient has multiple exacerbations in a short period of time, and the greater the severity of the disease, the worse the disease control, which indicates that the degree of lung function declines from a local perspective. Therefore, the time interval between adjacent acute exacerbations is negatively correlated with the local decline coefficient of lung function; the severity of acute exacerbations between adjacent acute exacerbations is positively correlated with the local decline coefficient of lung function.

[0044] As an example, the calculation formula for the local decline coefficient of lung function includes: ; in, represents the local decline coefficient of lung function of the i-th target patient; represents the number of acute exacerbation periods of the i-th target patient, represents the number of combinations of acute exacerbation periods that are adjacent in time sequence; x represents the sequence number of the acute exacerbation period; represents the rate of decline of the respiratory health index of the i-th target patient during the x-th acute exacerbation period, , It represents the respiratory health index at the first moment of the x-th acute exacerbation period of the i-th target patient. Represents the respiratory health index at the end of the xth acute exacerbation period of the i-th target patient, Represents the time interval between the first and last moments of the xth acute exacerbation period of the i-th target patient; represents the rate of decrease of the respiratory health index of the i-th target patient during the x+1-th acute exacerbation period; It represents the time interval between the xth acute exacerbation period of the ith target patient and the x+1th acute exacerbation period of the ith target patient.

[0045] In the calculation formula of the local decline coefficient of lung function, the number of acute exacerbation periods of all adjacent target patients is calculated by summing them up. , showing the poor control of the target patient's condition with multiple exacerbations in a short period of time, and indicating the decline of the target patient's respiratory health index during each period of acute exacerbation.

[0046] In another embodiment of the present invention, it is also considered that the more acute exacerbation periods of the target patient's condition, the longer the time ratio compared to the total treatment and nursing time, which means that the patient's respiratory obstruction is more frequent and the time ratio is longer, which is difficult to control in time, and the acute exacerbation of the condition is more serious. Therefore, the number of acute exacerbation periods and the time domain ratio can be combined to show the decline of the respiratory health index in each acute exacerbation period from the perspective of time domain and quantity. To supplement, ; Represents the duration of the time series of all respiratory health indexes of the i-th target patient; Represents the duration of all acute exacerbations of the condition of the i-th target patient.

[0047] Step S203: Obtain the symptom relief coefficient of the target patient according to the overall stability coefficient of the lung function and the local decline coefficient of the lung function of the target patient.

[0048] Taking into account that the larger the overall stability coefficient of lung function, the smaller the overall decline in the respiratory health index is from an overall perspective, indicating that the patient's respiratory obstruction is under control, the better the symptom relief, and the larger the symptom relief coefficient, so the symptom relief coefficient is positively correlated with the overall stability coefficient of lung function; considering that the larger the local decline coefficient of lung function, the more the target patient's respiratory health index declines during the period of acute exacerbation of the disease, reflecting that the control of the patient's respiratory obstruction is worse and the relief effect is worse, so the symptom relief coefficient is negatively correlated with the local decline coefficient of lung function.

[0049] As an example, the calculation formula for the symptom reduction factor includes: ; in, represents the overall stability coefficient of lung function of the i-th target patient; represents the symptom relief coefficient of the i-th target patient; Represents the local decline coefficient of lung function of the i-th target patient.

[0050] In the calculation formula of the symptom relief coefficient, The local decline coefficient of lung function is negatively mapped in a negative correlation manner. After adjusting the logical relationship, it is multiplied and integrated with the overall stability coefficient of lung function to obtain the symptom relief coefficient. From the perspective of disease change, it reflects the symptom relief of the target patient during the nursing treatment process.

[0051] In other embodiments of the present invention, a negative correlation mapping function such as an exponential function with the natural constant e as the base may also be used. Perform negative correlation mapping and adjust ; The symptom relief coefficient can also be obtained by weighted summation, such as .

[0052] It should be noted that the overall stability coefficient of lung function and the local decline coefficient of lung function only analyze the changes in the patient's respiratory obstruction from the perspective of changes in the FEV1 / FVC ratio, and only reflect the changes in lung function from the perspective of changes in the respiratory health index. They are used to analyze the patient's symptom relief and are not directly used as lung function indicators.

[0053] Step S3: According to the continuity characteristics of the target patient's condition stabilization and improvement period, obtain the reference coefficient of the target patient; according to the difference characteristics of the symptom relief coefficients between the current patient and the target patient, combined with the corresponding reference coefficients, screen out the reference patient for the current patient.

[0054] Taking into account the continuity characteristics of the target patient's condition stabilization and improvement period, it reflects the effect of the nursing plan on the target patient's breathing, thereby reflecting the reference value of the nursing plan. Therefore, according to the continuity characteristics of the target patient's condition stabilization and improvement period, the reference coefficient of the target patient is obtained to characterize the reference value of the nursing plan for the target patient, providing more basis for subsequent screening of target patients.

[0055] Preferably, in one embodiment of the present invention, considering that the greater the time domain proportion of the period of stable and improved condition in the treatment process, the stronger the continuity of the period of stable and improved condition, the more obvious the continuity feature, indicating that the time of the period of stable and improved condition in the treatment process is relatively longer, the greater the reference value of the nursing plan for the target patient, and the stronger the reference value, so the time domain proportion of all the periods of stable and improved condition in the treatment process is used as the first reference value coefficient of the target patient; Considering that the shorter the time interval between adjacent disease state stabilization and improvement periods, and the longer the longest disease state stabilization and improvement period, the stronger the continuity of the disease state stabilization and improvement period, and the more obvious the continuity characteristics, the ratio of the longest disease state stabilization and improvement period to the mean time interval of all adjacent disease state stabilization and improvement periods is taken as the second reference value coefficient; The first reference value coefficient and the second reference value coefficient of the target patient are integrated to obtain a reference coefficient of the target patient; As an example, the calculation formula of the reference coefficient includes: ; in, represents the reference coefficient of the i-th target patient; Represents the total duration of all periods of stable and improved condition of the i-th target patient; Represents the duration of the time series of all respiratory health indexes of the i-th target patient; represents the first reference value coefficient of the i-th target patient; Indicates the longest duration of the i-th target patient's stable and improved condition; represents the mean of the time intervals of all adjacent periods of stable and improved condition of the i-th target patient; Represents the second reference value coefficient of the i-th target patient.

[0056] In the calculation formula of the reference coefficient, the first reference value coefficient and the second reference value coefficient of the target patient are integrated by multiplication to comprehensively express the continuity characteristics of the period of stable improvement of the disease condition.

[0057] Through clustering, target patients with similar current conditions are screened out. The difference characteristics of symptom relief coefficients between patients are taken into consideration, which reflects the difference in changes in respiratory obstruction. At the same time, the reference coefficient of the target patient represents its reference value. Therefore, based on the difference characteristics of the symptom relief coefficients between the current patient and the target patient, combined with the corresponding reference coefficients, reference patients for the current patient are screened out. Finally, patients with the most similar current condition, the most similar condition changes and the highest reference value are screened out, providing a reliable auxiliary basis for the nursing plan for COPD patients.

[0058] Preferably, in one embodiment of the present invention, considering that the smaller the absolute value of the difference in symptom relief coefficients between patients is, the smaller the difference characteristics of the symptom relief coefficients between the current patient and the target patient are, the reference strength of each target patient for the current patient is obtained according to the absolute value of the difference in symptom relief coefficients between the current patient and each target patient, combined with the reference coefficient of the target patient; the absolute value of the difference in symptom relief coefficients between the current patient and each target patient is negatively correlated with the reference strength; the reference coefficient is positively correlated with the reference strength; Reference patients are screened according to the referenceable strength. Specifically, target patients whose referenceable strength is greater than a preset screening threshold are marked as reference patients.

[0059] As an example, the preset screening threshold is 0.8, and the calculation formulas for the strength that can be used include: ; in, represents the reference strength of the i-th target patient; Indicates the symptom relief coefficient of the current patient; Indicates taking the absolute value; C0 indicates the preset positive parameter of division by zero. In this example, C0=0.01.

[0060] The calculation formula of intensity can be used as a reference. By taking the inverse, the absolute value of the difference between the symptom relief coefficient of the current patient and each target patient is negatively correlated, and a positive parameter of zero division is added to the denominator to prevent the denominator from being zero. The fusion is achieved by multiplication. and The smaller the absolute value of the difference between the symptom relief coefficients of the current patient and the target patient, the smaller the difference characteristics of the symptom relief coefficients, and the more similar the changes in the condition. At the same time, the larger the reference coefficient, the better the nursing effect, the greater the reference value, and the greater the reference intensity.

[0061] It should be noted that the current patient refers to the patient for whom a nursing plan currently needs to be generated; implementers can also set other preset screening thresholds.

[0062] After screening and obtaining reference patients, we refer to the nursing plans of these reference patients and combine them with the basic information of the current patients to assist doctors in designing nursing plans for the current patients. Since nursing plan design is not the focus of this plan, it is only briefly described here: The patient's basic information may include: age, gender, weight, height, smoking history, past medical history, family medical history, allergy history, symptom description, physical examination results, lung function test data (such as FEV1 / FVC ratio), blood oxygen saturation, eating habits, exercise frequency, work environment, living conditions, anxiety, depression and other emotional assessments, etc.

[0063] Doctors can develop personalized care plans based on this basic information and referenced care plans.

[0064] The nursing plan includes: Drug treatment: According to the patient's condition and drug tolerance, recommend appropriate bronchodilators, inhaled corticosteroids and other drugs, and guide the correct medication method.

[0065] Non-drug interventions: smoking cessation counseling (providing smoking cessation counseling and support for patients with a history of smoking), respiratory rehabilitation training (including respiratory muscle training, aerobic exercise, etc. to enhance respiratory function and physical strength), nutritional guidance (developing a reasonable diet plan based on the patient's physical condition and nutritional needs), self-management education (teaching patients how to monitor their own symptoms, identify early signs of acute exacerbation and when to seek medical help), psychological support (providing psychological counseling or support groups to help patients cope with the emotional stress caused by the disease), etc.

[0066] In summary, the present invention aims at the technical problem that the existing screening and classification of similar patients with COPD is inaccurate, which affects the reference effect of the nursing plan and leads to unsatisfactory effect of the generation of auxiliary nursing plans, and proposes a method for auxiliary generation of nursing plans for patients with COPD. The present invention obtains the FEV1 / FVC ratio of the patient as the respiratory health index; clusters according to the difference characteristics of the respiratory health index between different patients at the current moment, and takes each other patient in the cluster where the current patient is located as the target patient in turn; further, according to the decline characteristics of the respiratory health index of the target patient in each period of acute exacerbation of the condition, combined with the overall decline characteristics of the respiratory health index, the symptom relief coefficient of the target patient is obtained; further, according to the continuity characteristics of the target patient's condition stabilization and improvement period, the reference coefficient of the target patient is obtained; according to the difference characteristics of the symptom relief coefficient between the current patient and the target patient, combined with the corresponding reference coefficient, finally screen out the patients who are most similar to the current patient in the current condition, the most similar condition change and the highest reference value, and provide a reliable auxiliary basis for the nursing plan of COPD patients.

[0067] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0068] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for assisting in generating a nursing plan for patients with chronic obstructive pulmonary disease, characterized in that: The method comprises: The FEV1 / FVC ratio of the patient is obtained as a respiratory health index; clustering is performed according to the difference characteristics of the respiratory health index between different patients at the current moment, and each other patient in the cluster where the current patient is located is taken as a target patient in turn; According to the change characteristics of the respiratory health index of the target patient, the acute exacerbation period and the stable improvement period of the condition of the target patient are obtained; according to the decline characteristics of the respiratory health index of the target patient in each period of acute exacerbation of the condition, combined with the overall decline characteristics of the respiratory health index, the symptom relief coefficient of the target patient is obtained; According to the continuity characteristics of the target patient's condition stabilization and improvement period, the reference coefficient of the target patient is obtained; according to the difference characteristics of the symptom relief coefficients between the current patient and the target patient, combined with the corresponding reference coefficients, the reference patient of the current patient is screened out.

2. A method for assisting in generating a nursing plan for COPD patients according to claim 1, characterized in that: The method for obtaining the acute exacerbation period and the stable improvement period of the condition includes: For the target patient, the degree of lung function decline at each moment is obtained according to the difference between the respiratory health index at each moment and the respiratory health index at the next moment adjacent in time sequence; The moment when the degree of lung function decline is greater than a first preset threshold is marked as an acute exacerbation moment; the moment when the degree of lung function decline is less than a second preset threshold is marked as a stabilization improvement moment; The time period formed by the adjacent acute exacerbation moments is regarded as the acute exacerbation period; the time period formed by the adjacent stabilization and improvement moments is regarded as the stabilization and improvement period.

3. The method for assisting in generating a nursing plan for COPD patients according to claim 1, characterized in that: The method for obtaining the symptom relief coefficient includes: The decreasing rates of the respiratory health index of the target patient at the first and last moments in the time domain are negatively correlated and normalized to serve as the overall stability coefficient of the lung function of the target patient; For the target patient, in each period of acute exacerbation, the decreasing rates of the respiratory health index at the first and last moments are normalized and used as the degree of aggravation of the condition in each period of acute exacerbation; the local decline coefficient of lung function of the target patient is obtained according to the time intervals of all the acute exacerbation periods adjacent in time sequence and the degree of aggravation; the time intervals of the acute exacerbation periods adjacent in time sequence are negatively correlated with the local decline coefficient of lung function; the degree of aggravation of the acute exacerbation periods adjacent in time sequence is positively correlated with the local decline coefficient of lung function; According to the overall stability coefficient of lung function and the local decline coefficient of lung function of the target patient, the symptom relief coefficient of the target patient is obtained; the symptom relief coefficient is positively correlated with the overall stability coefficient of lung function; the symptom relief coefficient is negatively correlated with the local decline coefficient of lung function.

4. The method for assisting in generating a nursing plan for COPD patients according to claim 1, characterized in that: The method for obtaining the reference coefficient includes: For the target patient, the time domain proportion of all the periods of stable and improved condition during the treatment process is used as the first reference value coefficient of the target patient; The ratio of the longest duration of the disease condition stabilization and improvement period to the average of the time intervals of all adjacent disease condition stabilization and improvement periods is used as the second reference value coefficient; The first reference value coefficient and the second reference value coefficient of the target patient are integrated to obtain the reference coefficient of the target patient; the first reference value coefficient and the second reference value coefficient are both positively correlated with the reference coefficient.

5. The method for assisting in generating a nursing plan for COPD patients according to claim 1, characterized in that: The method for obtaining the reference patient comprises: According to the absolute value of the difference between the symptom relief coefficient of the current patient and each of the target patients, combined with the reference coefficient of the target patient, the reference strength of each of the target patients for the current patient is obtained; the absolute value of the difference between the symptom relief coefficient of the current patient and each of the target patients is negatively correlated with the reference strength; the reference coefficient is positively correlated with the reference strength; Reference patients are screened according to the referenceable strengths.

6. A method for assisting in generating a nursing plan for COPD patients according to claim 5, characterized in that: The method for screening reference patients according to the referenceable strength comprises: The target patient whose referenceable strength is greater than a preset screening threshold is marked as a reference patient.

7. The method for assisting in generating a nursing plan for COPD patients according to claim 1, characterized in that: The method for clustering according to the difference characteristics of the respiratory health index between different patients at the current moment includes: The absolute value of the difference between the respiratory health index of any two patients at the current moment is used as the cluster distance between the corresponding two patients, and hierarchical clustering is performed on all patients to obtain multiple clusters.

8. The method for assisting in generating a nursing plan for COPD patients according to claim 1, characterized in that: The target patients are those for whom a care regimen already exists and who are still receiving treatment.

9. The method for assisting in generating a nursing plan for COPD patients according to claim 1, characterized in that: The symptom relief coefficient of the current patient is obtained in the same manner as the symptom relief coefficient of the target patient.

10. The method for assisting in generating a nursing plan for COPD patients according to claim 1, characterized in that: The FEV1 / FVC ratio of each patient was collected once a day.

Images