An otolaryngology patient management follow-up system and method

Abstract

The present invention discloses an otolaryngology patient management follow-up system and method, which relates to the technical field of medical follow-up systems, and specifically includes the following steps: obtaining the patient's basic information, medical records, allergic symptom descriptions, diagnostic results and treatment plans, establishing the patient's personal files, and entering their symptom data and allergy history into the system; during the peak pollen season, obtaining the symptom record information of all patients and the environmental pollen concentration information, and analyzing them after obtaining, evaluating the risk level of each patient's allergic symptoms aggravated by changes in pollen concentration, and classifying each patient according to the evaluation results; according to the classification results of all patients, respectively formulate and implement personalized follow-up plans for low risk, medium risk and high risk. The present invention can accurately evaluate and optimize the follow-up plan through real-time data monitoring and dynamic adjustment mechanism, ensuring that patients can receive follow-up guidance and treatment adjustment in time when the pollen concentration changes suddenly.

Description

Technical Field

[0001] The present invention relates to the technical field of medical follow-up systems, and particularly to an otolaryngology patient management and follow-up system and method. Background Art

[0002] The management and follow-up of otolaryngology patients refers to the process of long-term monitoring and management of their conditions in a systematic manner after patients receive otolaryngology treatment. The purpose of follow-up management is to ensure that patients receive continuous medical guidance and support during the rehabilitation process after treatment, to prevent the recurrence or deterioration of diseases, and to promptly detect and handle new health problems. This management method can help medical staff comprehensively understand the rehabilitation situation of patients, adjust treatment plans, and improve treatment effects. At the same time, follow-up management can also enhance patients' compliance, prompt them to visit the doctor on time and follow medical advice, and effectively reduce health risks caused by improper self-management. Through this systematic follow-up management, not only can the quality of life of patients be improved, but also the burden on medical resources can be reduced, and the long-term benefits of medical services can be achieved.

[0003] Existing otolaryngology patient management and follow-up technologies comprehensively manage and follow up patients through an integrated information platform. When patients first visit the doctor, the system will record in detail the patients' basic information, medical records, symptom descriptions, diagnosis results, and treatment plans. According to the patients' conditions and treatment needs, the system will automatically generate personalized follow-up plans, arranging specific follow-up dates and contents. When the follow-up date is approaching, the system will send reminder notifications via text messages, emails, or mobile applications to ensure that patients attend the follow-up on time. During the follow-up process, medical staff will record in real time the patients' latest conditions, treatment effects, and further diagnosis and treatment suggestions, and these information will be immediately updated to the system. The system also has a powerful data analysis function, which can comprehensively analyze the follow-up data of patients, generate detailed reports, and help doctors evaluate treatment effects and adjust treatment plans in a timely manner. The entire management process ensures patients' privacy and data security through user permission management and data encryption technologies, greatly improving the work efficiency of medical staff, reducing the tediousness of manual records and reminders, and at the same time helping doctors monitor and evaluate the rehabilitation progress of patients in real time, providing more accurate and personalized medical services for patients.

[0004] The existing technologies have the following deficiencies:

[0005] During the pollen peak period, due to the rapid change of pollen concentration in the environment, the allergic symptoms of patients fluctuate frequently, which may cause the actual condition of patients to not conform to the established follow-up plan. The existing technology fails to respond to these changes in pollen concentration in a timely manner, unable to monitor and analyze pollen concentration data in real time, and thus unable to generate personalized follow-up plans. Therefore, patients fail to receive timely follow-up guidance and treatment adjustment when the pollen concentration suddenly changes, which may lead to the aggravation of symptoms, affect the control of the condition and the overall treatment effect. This deficiency of the existing technology not only increases the pain and medical burden of patients during the peak period, but also may lead to the deterioration of the condition, delay the best treatment opportunity, and ultimately reduce the quality of life of patients and the effectiveness of medical services. At the same time, this lagging follow-up management increases the workload of medical staff, fails to effectively utilize medical resources, and affects the management efficiency of hospitals and the satisfaction of patients.

[0006] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure. Therefore, it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0007] The object of the present invention is to provide an ENT patient management and follow-up system and method to solve the problems in the above background art.

[0008] To achieve the above object, the present invention provides the following technical solution: An ENT patient management and follow-up method, specifically including the following steps:

[0009] Obtain the basic information, medical records, description of allergic symptoms, diagnosis results and treatment plans of patients, establish personal files of patients, and input their symptom data and allergy history into the system;

[0010] During the pollen peak period, obtain the symptom record information and environmental pollen concentration information of all patients, and analyze them after obtaining. Evaluate the risk level of the aggravation of the allergic symptoms of each patient due to the change of pollen concentration, and classify each patient according to the evaluation results;

[0011] According to the classification results of all patients, formulate and implement personalized follow-up plans for low-risk, medium-risk and high-risk patients respectively;

[0012] Obtain the dynamic information during the implementation of the follow-up plan, and analyze it after obtaining. Evaluate the implementation situation of the follow-up plan, and dynamically adjust the follow-up plan according to the evaluation results;

[0013] Regularly generate follow-up reports, send the generated follow-up reports to doctors and patients, and at the same time provide long-term health management suggestions to patients.

[0014] Preferably, during the pollen peak period, obtain the symptom record information of all patients and the environmental pollen concentration information, and analyze them after obtaining, evaluate the risk level of the allergic symptoms of each patient being aggravated due to the change in pollen concentration, and classify each patient according to the evaluation result. The specific steps are as follows:

[0015] During the pollen peak period, obtain the symptom record information of all patients and the environmental pollen concentration information;

[0016] Preprocess the symptom record information of all patients and the environmental pollen concentration information;

[0017] Extract the immune response data in the symptom record information of each preprocessed patient and the pollen concentration data in the environmental pollen concentration information, and analyze them after extraction to generate the immune response fluctuation index and pollen concentration change coefficient of each patient respectively;

[0018] Construct an aggravation risk assessment model with the generated immune response fluctuation index and pollen concentration change coefficient of each patient, generate the aggravation risk coefficient of each patient, and compare the generated aggravation risk coefficient of each patient with the pre-set aggravation risk coefficient threshold interval to evaluate the risk level of the allergic symptoms of each patient being aggravated due to the change in pollen concentration, and classify each patient according to the evaluation result.

[0019] Preferably, the acquisition logic of the immune response fluctuation index and pollen concentration change coefficient of each patient is as follows:

[0020] Extract the immune response data in the symptom record information of each preprocessed patient, including the immunoglobulin level values and corresponding time points of each patient at different times within a period of time, and use the function MYQDB i (T) to represent it, where T is the time point, and MYQDB i (T) represents the immunoglobulin level value of the i-th patient at the T-th moment within a period of time, i = 1, 2, 3,..., k, k is a positive integer, and the defined time period is [T 1 , T 2 ;

[0021] Perform Fourier transform on the immunoglobulin level value of the i-th patient at the T-th moment within a period of time, according to the formula:

[0022]

[0023] In the formula, F(MYQDB i (T)) is the immunoglobulin level value MYQDB i at the T-th moment within a period of time in the immune response data of the i-th symptom aggravated patient.(T) frequency component, where T is the time variable, f is the frequency variable, and z is the imaginary unit;

[0024] Take the amplitude of the result after Fourier transform of the immunoglobulin level value at time T of the i-th patient within a period of time, that is, the absolute value |F(MYQDB i (T))|, which represents the amplitude of the immunoglobulin level value of the i-th patient at time T within a period of time at different frequencies;

[0025] Calculate the immune response fluctuation index of each patient. The specific calculation formula is as follows:

[0026]

[0027] In the formula, IRFI i is the immune response fluctuation index of the i-th patient;

[0028] Extract the pollen concentration data from the preprocessed environmental pollen concentration information, including the average pollen concentration at different times within a period of time in the activity areas of each patient, and calibrate the average pollen concentration at different times within a period of time in the activity areas of each patient as representing the average pollen concentration at time m within a period of time in the activity area of the i-th patient, where m = 1, 2, 3,..., g, and g is a positive integer;

[0029] Calculate the average value and standard deviation of the average pollen concentration in the activity areas of each patient within a period of time according to the formula:

[0030]

[0031] In the formula, HFSN i - is the average value of the average pollen concentration in the activity area of the i-th patient within a period of time, is the standard deviation of the average pollen concentration in the activity area of the i-th patient within a period of time;

[0032] Calculate the pollen concentration change coefficient of each patient. The specific calculation formula is as follows:

[0033]

[0034] In the formula, PCVC i is the pollen concentration change coefficient of the i-th patient.

[0035] Preferably, construct a risk of exacerbation assessment model for the generated immune response fluctuation index IRFI i and pollen concentration change coefficient PCVC i of each patient, and generate the risk of exacerbation coefficient ERC of each patient through weighted summation iand the exacerbation risk coefficient ERC of each generated patient i is compared with the pre-set exacerbation risk coefficient threshold [ERC 1 , ERC 2 , and the risk level of the allergic symptoms of each patient being exacerbated due to changes in pollen concentration is evaluated, and each patient is classified according to the evaluation results. The specific analysis is as follows:

[0036] If ERC i < ERC 1 , the risk level of the allergic symptoms of this patient being exacerbated due to changes in pollen concentration is low risk, and this patient is classified as a low-risk patient;

[0037] If ERC 1 ≤ ERC i ≤ ERC 2 , the risk level of the allergic symptoms of this patient being exacerbated due to changes in pollen concentration is medium risk, and this patient is classified as a medium-risk patient;

[0038] If ERC i > ERC 2 , the risk level of the allergic symptoms of this patient being exacerbated due to changes in pollen concentration is high risk, and this patient is classified as a high-risk patient.

[0039] Preferably, according to the classification results of all patients, personalized follow-up plans for low risk, medium risk and high risk are formulated and implemented respectively, as follows:

[0040] For low-risk patients, a low-intensity follow-up plan is formulated and implemented, and basic health guidance is provided;

[0041] For medium-risk patients, a medium-intensity follow-up plan is formulated and implemented, and targeted health guidance is provided;

[0042] For high-risk patients, a high-intensity follow-up plan is formulated and implemented, an emergency treatment plan is formulated, and comprehensive health guidance and preventive measures are provided.

[0043] Preferably, dynamic information during the implementation of the follow-up plan is obtained, analyzed after acquisition, the implementation of the follow-up plan is evaluated, and the follow-up plan is dynamically adjusted according to the evaluation results. The specific steps include:

[0044] Obtain dynamic information during the implementation of the follow-up plan, including the physiological parameter record information and treatment compliance information of all patients;

[0045] Preprocess the physiological parameter record information and treatment compliance information of all patients;

[0046] Extract the key physiological data from the preprocessed physiological parameter record information of each patient and the medication record data in the treatment compliance information, and perform analysis after extraction to generate the physiological parameter fluctuation index and treatment compliance coefficient for each patient respectively;

[0047] Construct an execution evaluation model with the generated physiological parameter fluctuation index and treatment compliance coefficient of each patient to generate the execution evaluation coefficient of each patient, and compare the generated execution evaluation coefficient of each patient with the pre-set execution evaluation coefficient threshold interval to evaluate the execution situation of the follow-up plan for each patient, and dynamically adjust the follow-up plan according to the evaluation results.

[0048] Preferably, the acquisition logic of the physiological parameter fluctuation index and treatment compliance coefficient of each patient is as follows:

[0049] Extract the key physiological data from the preprocessed physiological parameter record information of each patient, including the blood oxygen saturation and corresponding time points of each patient at different moments within a period of time during the implementation of the follow-up plan, and use the function SPO i (t) to represent it, where t is the time point, and SPO i (t) represents the blood oxygen saturation of the i-th patient at the time point t within a period of time during the implementation of the follow-up plan. Define the time period as [t 1 , t 2 ;

[0050] Perform Fourier transform on the blood oxygen saturation of the i-th patient at the time point t within a period of time, according to the formula:

[0051]

[0052] In the formula, F(SPO i (t)) is the frequency component of the blood oxygen saturation SPO i (t) of the i-th patient at the time point t within a period of time, t is the time variable, j is the frequency variable, and d is the imaginary unit;

[0053] Take the amplitude of the result after Fourier transform of the blood oxygen saturation of the i-th patient at the time point t within a period of time, that is, the absolute value |F(SPO i (t))|, which represents the amplitude of the blood oxygen saturation of the i-th patient at the time point t within a period of time at different frequencies;

[0054] Calculate the physiological parameter fluctuation index of each patient. The specific calculation formula is as follows:

[0055]

[0056] In the formula, PPFI iis the physiological parameter fluctuation index of the i-th patient;

[0057] Extract the medication record data in the treatment compliance information of each preprocessed patient, including the total actual number of medication doses taken by each patient at different times within a period during the implementation of the follow-up plan, and calibrate the total actual number of medication doses taken by each patient within a period during the implementation of the follow-up plan as NA i , NA i represents the total actual number of medication doses taken by the i-th patient within a period during the implementation of the follow-up plan;

[0058] Obtain the total required number of medication doses for each patient within this period during the implementation of the follow-up plan, and calibrate the total required number of medication doses for each patient within this period during the implementation of the follow-up plan as NT i , NT i represents the total required number of medication doses for the i-th patient within a period during the implementation of the follow-up plan;

[0059] Calculate the treatment compliance coefficient for each patient. The specific calculation formula is as follows:

[0060]

[0061] In the formula, TAC i is the treatment compliance coefficient of the i-th patient.

[0062] Preferably, construct an execution evaluation model with the generated physiological parameter fluctuation index PPFI i and treatment compliance coefficient TAC i of each patient, and generate the execution evaluation coefficient EEC for each patient through weighted summation i , and compare the generated execution evaluation coefficient EEC i of each patient with the pre-set execution evaluation coefficient threshold interval EEC 1 , EEC 2 to evaluate the implementation of the follow-up plan for each patient, and dynamically adjust the follow-up plan according to the evaluation results. The specific analysis is as follows:

[0063] If EEC i < EEC 1 , the implementation of the follow-up plan for this patient is poor, and it is necessary to significantly increase the follow-up frequency of the follow-up plan, strengthen the monitoring measures, and adjust the treatment plan;

[0064] If EEC 1 ≤ EEC i ≤ EEC 2 , the implementation of the follow-up plan for this patient is average, and it is necessary to slightly increase the follow-up frequency of the follow-up plan and strengthen the monitoring measures, and adjust the treatment plan as needed;

[0065] If the EEC i > EEC 2 , the implementation of the follow-up plan for this patient is good. Maintain the follow-up frequency of the current follow-up plan without adjusting the follow-up plan.

[0066] Preferably, an otolaryngology patient management follow-up system includes a patient file management module, a peak period risk assessment module, a personalized follow-up plan module, a dynamic follow-up assessment module, and an intelligent follow-up report module;

[0067] The patient file management module obtains the patient's basic information, medical records, allergy symptom descriptions, diagnosis results, and treatment plans, establishes the patient's personal file, and enters the patient's symptom data and allergy history into the system;

[0068] The peak period risk assessment module obtains the symptom record information of all patients and the environmental pollen concentration information during the pollen peak period, analyzes the information after obtaining it, evaluates the risk level of each patient's allergy symptoms being aggravated due to the change in pollen concentration, and classifies each patient according to the evaluation results;

[0069] The personalized follow-up plan module formulates and implements personalized follow-up plans for low risk, medium risk, and high risk respectively according to the classification results of all patients;

[0070] The dynamic follow-up assessment module obtains the dynamic information during the implementation of the follow-up plan, analyzes the information after obtaining it, evaluates the implementation of the follow-up plan, and dynamically adjusts the follow-up plan according to the evaluation results;

[0071] The intelligent follow-up report module regularly generates follow-up reports, sends the generated follow-up reports to doctors and patients, and provides long-term health management suggestions to patients at the same time.

[0072] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0073] 1. By obtaining the patient's physiological parameter record information and treatment compliance information in real time, and using advanced algorithms such as Fourier transform and weighted summation, the present invention dynamically generates and adjusts the follow-up plan to ensure that the follow-up plan can respond to the change in pollen concentration in a timely manner. During the pollen peak period, due to the rapid change in the pollen concentration in the environment and the frequent fluctuation of the patient's allergy symptoms, the present invention can accurately evaluate and optimize the follow-up plan through real-time data monitoring and dynamic adjustment mechanism, ensuring that patients can receive timely follow-up guidance and treatment adjustment when the pollen concentration suddenly changes, effectively reducing the fluctuation and aggravation of allergy symptoms, and guaranteeing the disease control and overall treatment effect.

[0074] 2. The present invention formulates and implements personalized follow-up plans with low risk, medium risk, and high risk based on the classification results of patients, enabling each patient to receive follow-up management that is most suitable for their health condition. During the pollen peak period, since the actual condition of the patient does not conform to the established follow-up plan, the prior art fails to respond promptly to the change in pollen concentration. The present invention evaluates the risk level of each patient's allergic symptoms being aggravated due to the change in pollen concentration, provides targeted follow-up frequencies and health guidance, avoids excessive or insufficient medical interventions, ensures that high-, medium-, and low-risk patients receive corresponding medical support and preventive measures, and effectively improves the treatment compliance and satisfaction of patients.

[0075] 3. The present invention obtains and analyzes the symptom record information and environmental pollen concentration information of patients, evaluates the risk level of each patient's allergic symptoms being aggravated due to the change in pollen concentration, and classifies them accordingly, enabling the early identification of high-risk patients and the timely adoption of preventive measures. The prior art cannot monitor and analyze pollen concentration data in real time and cannot generate personalized follow-up plans, resulting in patients not receiving timely follow-up guidance and treatment adjustment when the pollen concentration changes suddenly. The present invention constructs an aggravation risk assessment model using the immune response fluctuation index and the pollen concentration change coefficient, realizes a rapid response to sudden changes in pollen concentration, significantly reduces the pain and medical burden of patients during the peak period, avoids the deterioration of the condition and the delay of the treatment opportunity, and improves the effectiveness and management efficiency of medical services. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings.

[0077] Figure 1 It is a schematic flowchart of a follow-up system and method for the management of otolaryngology patients according to the present invention.

[0078] Figure 2 It is a schematic diagram of the modules of a follow-up system and method for the management of otolaryngology patients according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0079] Now, the exemplary embodiments will be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these exemplary embodiments are provided so that the present disclosure will be more complete and comprehensive, and the concept of the exemplary embodiments will be fully conveyed to those skilled in the art.

[0080] The present invention provides as Figure 1An otolaryngology patient management and follow-up method is shown as follows, which specifically includes the following steps:

[0081] Obtain the patient's basic information, medical records, allergy symptom descriptions, diagnosis results, and treatment plans, establish a personal file for the patient, and enter their symptom data and allergy history into the system;

[0082] The patient's basic information and relevant medical data can be obtained through various methods. First, when the patient visits the doctor for the first time, they can fill out an electronic form or enter their basic information (such as name, gender, date of birth, contact information, etc.) and medical records on a tablet device in the consulting room. During the diagnosis and treatment process, the doctor can use the Electronic Health Record (EHR) system to record the patient's allergy symptom descriptions, diagnosis results, and treatment plans in real time. The patient's historical medical record data can be imported from the hospital's database through an interface with the Hospital Information System (HIS). In addition, by docking with the patient's mobile health application, information on symptoms and allergic reactions recorded by the patient in daily life can be obtained. These data are transmitted through a secure network transmission protocol to ensure privacy and data security.

[0083] After obtaining the patient's basic information and relevant medical data, the system will automatically generate a personal file for each patient. Through the software system, the patient's basic information, medical records, allergy symptom descriptions, diagnosis results, and treatment plans are integrated into an electronic file. The process of establishing the file includes data standardization and format conversion to ensure that all data is stored in a unified format. The system will generate a unique patient ID to ensure accurate data matching and subsequent management. The patient file can be viewed and edited through the system's user interface, and doctors and authorized medical staff can add or update the file content as needed. In addition, the system can set access permissions to ensure that only authorized personnel can view and edit sensitive information, thereby protecting the patient's privacy.

[0084] After establishing the patient's personal file, it is necessary to enter their symptom data and allergy history in detail into the system. The doctor can use a portable device (such as a tablet computer or laptop) to record the patient's symptoms and allergy history in real time during the diagnosis and treatment process, or after the diagnosis and treatment, convert the paper records into electronic data through the software system for entry. The patient can also record their daily symptoms and allergic reactions through a mobile application and synchronize this data to the system. The system will use Natural Language Processing (NLP) technology to automatically parse and structure the input data to ensure the accuracy and integrity of the symptom descriptions and allergy history. The entered data will be stored in the patient's personal file and associated with other medical data for the doctor to conduct comprehensive analysis and evaluation during subsequent follow-up. The data verification and error detection functions during the entry process can help reduce manual entry errors and improve data quality and reliability.

[0085] During the pollen peak period, obtain the symptom record information of all patients and the environmental pollen concentration information, and perform analysis after obtaining them, evaluate the risk level of the allergic symptoms of each patient being aggravated due to the change in pollen concentration, and classify each patient according to the evaluation result;

[0086] In this embodiment, during the pollen peak period, obtain the symptom record information of all patients and the environmental pollen concentration information, and perform analysis after obtaining them, evaluate the risk level of the allergic symptoms of each patient being aggravated due to the change in pollen concentration, and classify each patient according to the evaluation result, which specifically includes the following steps:

[0087] During the pollen peak period, obtain the symptom record information of all patients and the environmental pollen concentration information;

[0088] The pollen peak period can be determined by various methods. First, the pollen monitoring data provided by meteorological agencies can be used. These data usually include daily pollen concentration levels and historical pollen concentration trends. The software system can be docked with the database of the meteorological agency to obtain pollen concentration data in real time and identify the pollen peak period by analyzing historical data. Specifically, the system can set a pollen concentration threshold. When the pollen concentration levels exceed this threshold for consecutive days, the system will automatically determine that the pollen peak period has entered. In addition, the system can also analyze pollen data over the years through machine learning algorithms to predict future pollen peak periods. Through these methods, the system can accurately identify and mark the pollen peak period to ensure that specific follow-up management processes are initiated during this period.

[0089] Preprocess the symptom record information of all patients and the environmental pollen concentration information;

[0090] Obtaining the symptom record information of all patients and the environmental pollen concentration information can be achieved in various ways. For the symptom record information of patients, the software system can collect it through the patient's mobile application. These applications allow patients to record their symptoms daily, such as nasal congestion, sneezing, runny nose, etc. The system can set daily reminders to prompt patients to record symptoms on time and automatically synchronize this data to the central database. For the environmental pollen concentration information, the system can be docked with the API interfaces of meteorological monitoring stations or third-party pollen monitoring services to obtain pollen concentration data in real time. These data include daily or even hourly pollen concentration levels and can be segmented according to geographical location to obtain the specific pollen concentration situation in the patient's area. All the obtained data will be transmitted encrypted to ensure patient privacy and data security, and then stored on a secure server for subsequent analysis and processing by the system. Through these methods, the system can continuously and accurately collect and integrate patient symptom records and environmental pollen concentration data, providing the necessary basic information for follow-up management.

[0091] Extract the immune response data from the pre - processed symptom record information of each patient and the pollen concentration data from the environmental pollen concentration information, and perform analysis after extraction to generate the immune response fluctuation index and pollen concentration change coefficient for each patient respectively;

[0092] Construct a risk assessment model for exacerbation using the generated immune response fluctuation index and pollen concentration change coefficient of each patient, generate the exacerbation risk coefficient for each patient, compare the generated exacerbation risk coefficient for each patient with the pre - set exacerbation risk coefficient threshold interval, evaluate the risk level of each patient's allergic symptoms being exacerbated due to pollen concentration changes, and classify each patient according to the evaluation results.

[0093] The pre - set exacerbation risk coefficient threshold interval can be determined in various ways. First, historical patient data and clinical research results can be used to determine these thresholds through data analysis and machine learning modeling by a software system. Specifically, the system can collect a large amount of historical data, including patient symptom records, pollen concentration data, immune response fluctuation index, and actual allergic exacerbation events. Through statistical analysis, the system can identify characteristic parameters of different risk levels, such as the distribution range of the immune response fluctuation index and pollen concentration change coefficient of patients with symptom exacerbation during the pollen peak period. Then, the system can use clustering analysis or classification algorithms (such as K - means clustering, logistic regression, support vector machines, etc.) to train these data, establish a risk assessment model, and determine the corresponding risk coefficient threshold interval. To improve the accuracy and reliability of the model, the system can also perform cross - validation and parameter tuning optimization. Finally, the system will set the threshold intervals for high, medium, and low risk levels according to the output results of the model, ensuring that these intervals can accurately reflect the risk levels of different patients being exacerbated due to pollen concentration changes. This process is completed through automated data analysis and machine learning algorithms, and can dynamically adjust and optimize the threshold interval to adapt to different patient groups and changing environmental conditions.

[0094] In this embodiment, the acquisition logic of the immune response fluctuation index and pollen concentration change coefficient of each patient is as follows:

[0095] Extract the immune response data from the pre - processed symptom record information of each patient, including the immunoglobulin level values and corresponding time points of each patient at different moments within a period of time, and represent them with the function MYQDB i (T), where T is the time point, and MYQDB i (T) represents the immunoglobulin level value of the i - th patient at the time point T within a period of time, i = 1, 2, 3, …, k, k is a positive integer, and the defined time period is [T 1 , T 2;

[0096] Immune response data can be extracted from the patient's electronic health record (EHR) and symptom logs in the mobile application through a software system. Specifically, first, the software system will interface with the hospital information system (HIS) or other health management platforms to obtain the patient's immunoglobulin test results, which usually record the immunoglobulin level values of the patient at specific time points. Second, the software system can collect the symptom logs daily input by patients through the health applications they use. These logs can include manually entered immunoglobulin level data or data automatically uploaded by home testing devices (such as portable immunoassays). The system will automatically perform data preprocessing, match the immunoglobulin level values at different times with the corresponding time points, and standardize them into a unified format to ensure data consistency and accuracy. All the extracted data will be centrally stored in the cloud database for subsequent analysis. The software system will also perform data verification to eliminate outliers and noise to ensure data reliability. This process is achieved through automated data collection and preprocessing functions to ensure efficient and accurate extraction of the required immune response data.

[0097] Perform a Fourier transform on the immunoglobulin level value of the i-th patient at time T within a period of time, according to the formula:

[0098]

[0099] In the formula, F(MYQDB i (T)) is the frequency component of the immunoglobulin level value MYQDB i (T) at time T within a period of time in the immune response data of the i-th patient with symptom exacerbation, T is the time variable, f is the frequency variable, and z is the imaginary unit;

[0100] Fourier transform is a mathematical tool used to convert time domain signals into frequency domain signals. It can decompose the components of different frequencies in the signal and the corresponding amplitudes. The purpose of Fourier transforming the immunoglobulin level values ​​of the i-th patient at time T over a period of time is to analyze the frequency characteristics of the patient's immune response. The data of immunoglobulin levels changing over time may contain periodic changes and noise. The frequency components of these changes can be extracted through Fourier transform, so as to better understand and quantify the fluctuations of the patient's immune response. The frequency variable f represents the frequency of different frequency components in the signal, reflecting the speed of signal changes; the imaginary unit z is used to represent the phase information in the complex domain, which helps to describe the amplitude and phase relationship of the signal. The advantage of Fourier transform is that it can decompose complex time series data into simple sine waves and cosine waves, which is convenient for spectrum analysis, thereby identifying the main frequency components of changes in immunoglobulin levels. This is very useful for detecting periodic changes, identifying abnormal fluctuations and noise filtering. The software system can realize automated Fourier transform calculation, quickly analyze a large number of patient data, generate frequency component maps, help doctors understand the dynamic characteristics of patients' immune responses, and more accurately assess the risk level of allergic symptoms aggravated by changes in pollen concentration.

[0101] Take the immunoglobulin level of the i-th patient at time T within a period of time and perform Fourier transformation on the amplitude of the result, that is, the absolute value |F(MYQDB i (T))], represents the amplitude of the immunoglobulin level of the ith patient at time T in a period of time at different frequencies;

[0102] After performing a Fourier transform on the immunoglobulin level values of the \(i\)th patient at time \(T\) over a period of time, the result is a series of complex numbers. These complex numbers represent the amplitude and phase of the signal at different frequencies. The magnitude of the Fourier transform, i.e., the absolute value, represents the amplitude of these signals at different frequencies. Specifically, the magnitude is the modulus of the complex number, reflecting the energy intensity of the signal at that frequency component. By calculating the magnitude of the immunoglobulin level values of the \(i\)th patient over a specific period of time, the fluctuation amplitude of their immune response at different frequencies can be quantified. This magnitude information is of great significance for understanding the dynamic changes of the patient's immune system because high-frequency components may indicate rapid fluctuations in the immune response, while low-frequency components may reflect long-term trends and chronic changes. Through the software system, the magnitude information after the Fourier transform can be automatically extracted to generate spectrograms, which show the amplitude distribution of immunoglobulin levels at different frequencies. Doctors can identify the main frequency components in the immune response through these spectrograms, understand the immune fluctuation characteristics of the patient, and thus more accurately assess the risk of their allergic symptoms being exacerbated due to changes in pollen concentration. The automated processing and visualization functions of the software system make this complex mathematical analysis process intuitive and easy to understand, providing strong data support for clinical decision-making.

[0103] Calculate the immune response fluctuation index for each patient. The specific calculation formula is as follows:

[0104]

[0105] In the formula, IRFI i is the immune response fluctuation index of the \(i\)th patient;

[0106] The immune response fluctuation index of the \(i\)th patient is an indicator that measures the fluctuation intensity of their immunoglobulin level over a specific period of time. By performing a Fourier transform on the immunoglobulin level values, extracting the amplitudes at different frequencies, and then integrating these amplitudes over the entire period, it is calculated. The magnitude of IRFI i reflects the sensitivity of the patient's immune system to environmental changes. A higher IRFI i index indicates that the patient's immunoglobulin level fluctuates frequently and significantly during the period, indicating that their immune system is more sensitive and responsive to allergens such as pollen. Therefore, the risk of this patient's allergic symptoms being exacerbated due to changes in pollen concentration is higher. On the contrary, a lower IRFI i index indicates that the immunoglobulin level is relatively stable with less fluctuation, indicating that the patient's response to allergens is relatively weak, and the risk of allergic symptoms being exacerbated due to changes in pollen concentration is lower. By using IRFI iCombined with the pollen concentration variation coefficient, it is possible to more accurately evaluate the risk level of allergic symptom exacerbation for each patient during the pollen peak period, and based on this, conduct high, medium, and low risk classifications, thereby providing a scientific basis for personalized follow-up plans and treatment regimens.

[0107] Extract the pollen concentration data from the preprocessed environmental pollen concentration information, including the average pollen concentration at different times within a period of time in the activity areas of each patient, and calibrate the average pollen concentration at different times within a period of time in the activity areas of each patient as representing the average pollen concentration at the m-th moment within a period of time in the activity area of the i-th patient, where m = 1, 2, 3, …, g, and g is a positive integer;

[0108] The pollen concentration data can be obtained from environmental monitoring agencies, weather stations, or third-party pollen monitoring services through a software system. These data usually include pollen concentration levels at different times. First, the software system can interface with the API of these data sources to obtain the pollen concentration information in the activity areas of each patient in real-time or at regular intervals. The specific method is that the system extracts the pollen concentration data in the corresponding area according to the geographical location data of the patient and records the average pollen concentration values at different times within a specific time period. The system will preprocess the original data, including removing outliers and filling in missing data, to ensure the accuracy and consistency of the data. The preprocessed data will be stored in the database of the system, and the system will calculate the average pollen concentration at different times in the activity areas of each patient according to the set time interval (such as every hour or daily). Through these methods, the software system can efficiently and accurately extract and process environmental pollen concentration information, providing a reliable data basis for subsequent analysis and evaluation.

[0109] Calculate the average value and standard deviation of the average pollen concentration in the activity areas of each patient within a period of time, according to the formula:

[0110]

[0111] In the formula, is the average value of the average pollen concentration in the activity area of the i-th patient within a period of time, is the standard deviation of the average pollen concentration in the activity area of the i-th patient within a period of time;

[0112] Calculate the pollen concentration variation coefficient for each patient. The specific calculation formula is as follows:

[0113]

[0114] In the formula, PCVC i is the pollen concentration variation coefficient of the i-th patient.

[0115] Pollen Concentration Variation Coefficient (PCVC) of the i-th patient i is an indicator that measures the fluctuation intensity of pollen concentration in the area where the patient is active within a specific time period. PCVC i is obtained by calculating the ratio of the standard deviation to the average value of the average pollen concentration at different times in the patient's active area during this time period, reflecting the volatility of pollen concentration. A higher PCVC i index indicates that the pollen concentration in the patient's active area changes significantly within the time period, indicating that the patient is exposed to significantly different pollen concentration levels at different times, thus increasing the risk of exacerbation of their allergic symptoms due to changes in pollen concentration. On the contrary, a lower PCVC i index indicates that the pollen concentration is relatively stable with less fluctuation, indicating that the patient's allergic symptoms are less affected by changes in pollen concentration, and thus the risk of exacerbation of allergic symptoms is lower. By evaluating the PCVC i of each patient, it is possible to more accurately judge the likelihood of exacerbation of their allergic symptoms during the pollen peak period, thereby providing a scientific basis for classifying high, medium, and low risk levels, and formulating more personalized follow-up plans and treatment strategies based on the classification results to improve the treatment effect and quality of life of the patients.

[0116] In this embodiment, the generated Immune Response Fluctuation Index (IRFI) i and the Pollen Concentration Variation Coefficient (PCVC) i are used to construct an exacerbation risk assessment model, and the exacerbation risk coefficient (ERC) i of each patient is generated by weighted summation. Then, the generated exacerbation risk coefficient (ERC) i of each patient is compared with the pre-set exacerbation risk coefficient threshold range [[ERC 1 , ERC 2 to evaluate the risk level of exacerbation of each patient's allergic symptoms due to changes in pollen concentration, and each patient is classified according to the evaluation results. The specific analysis is as follows:

[0117] If ERC i < ERC 1, the risk level of the patient's allergic symptoms worsening due to changes in pollen concentration is low risk, and the patient is classified as a low-risk patient. This means that the combined result of the immune response fluctuation index and the pollen concentration change coefficient of the patient is low, indicating that the patient's immune system has a low sensitivity to changes in pollen concentration, and the risk of their allergic symptoms worsening due to changes in pollen concentration during the pollen peak period is small. Specifically, the immune response of low-risk patients is relatively stable, and the change range of pollen concentration in their environment is not large. Such patients usually do not experience a serious exacerbation of allergic symptoms due to fluctuations in pollen concentration. Therefore, relatively routine measures can be adopted in follow-up management and treatment plans, without the need for special intervention. This not only reduces the use of medical resources but also alleviates the patient's psychological burden, ensuring that they can maintain a normal life and work state during the pollen peak period;

[0118] If ERC 1 ≤ERC i ≤ERC 2 , the risk level of the patient's allergic symptoms worsening due to changes in pollen concentration is medium risk, and the patient is classified as a medium-risk patient. This indicates that the immune response fluctuation index and the pollen concentration change coefficient of the patient are at a medium level, meaning that the patient's immune system has a certain sensitivity to changes in pollen concentration, and the risk of their allergic symptoms worsening due to changes in pollen concentration during the pollen peak period is high. For medium-risk patients, although the risk of their allergic symptoms worsening is not as significant as that of high-risk patients, appropriate monitoring and management are still required. The follow-up plan should include regular examinations and timely symptom records. At the same time, the medication regimen may need to be adjusted to cope with symptom fluctuations. Such moderate intervention measures can help patients effectively control allergic symptoms during the pollen peak period and avoid symptom deterioration, thereby improving the patient's quality of life and treatment effect;

[0119] If ERC i >ERC 2 , the risk level of the patient's allergic symptoms worsening due to changes in pollen concentration is high risk, and the patient is classified as a high-risk patient. This means that the combined result of the immune response fluctuation index and the pollen concentration change coefficient of the patient is high, indicating that the patient's immune system is very sensitive to changes in pollen concentration, and the risk of their allergic symptoms worsening due to changes in pollen concentration during the pollen peak period is extremely high. High-risk patients require special attention and management. The follow-up plan should include frequent symptom monitoring, detailed records of allergen exposure, and personalized treatment adjustment plans. It may be necessary to strengthen medication, and even take preventive measures such as reducing outdoor activities or using air purification equipment when necessary. Such proactive management measures can significantly reduce the health risks caused by the exacerbation of the patient's allergic symptoms, prevent the occurrence of acute allergic reactions, improve the safety and comfort of the patient during the pollen peak period, and at the same time provide sufficient data support for doctors to optimize the treatment plan.

[0120] To construct a weighted risk assessment model and generate the exacerbation risk coefficient for each patient through weighted summation, it is first necessary to collect and process the immune response fluctuation index and pollen concentration change coefficient of each patient. Next, through the method of weighted summation, the immune response fluctuation index IRFI i and the pollen concentration change coefficient PCVC i of each patient are combined to generate the exacerbation risk coefficient ERC i . Specifically, the software system will use the predetermined weight coefficients α and β, which are set based on clinical data and expert experience to reflect the relative importance of immune response fluctuations and pollen concentration changes to the risk of exacerbation of allergic symptoms. Through the weighted summation formula ERC i = α * IRFI i + β * PCVC i , the system automatically calculates the exacerbation risk coefficient ERC i for each patient. The weight coefficients α and β can be adjusted according to the specific characteristics of the patient population to improve the accuracy and applicability of the model. The generated ERC i reflects the comprehensive risk of exacerbation of a patient's allergic symptoms due to changes in pollen concentration. Through this automated calculation process, the software system can efficiently and accurately generate the exacerbation risk coefficient for each patient, providing a scientific basis for further risk level assessment and personalized follow-up management.

[0121] According to the classification results of all patients, personalized follow-up plans for low risk, medium risk, and high risk are formulated and implemented respectively;

[0122] In this embodiment, according to the classification results of all patients, personalized follow-up plans for low risk, medium risk, and high risk are formulated and implemented respectively, as follows:

[0123] For low-risk patients, a low-intensity follow-up plan is formulated and implemented to regularly monitor the patient's symptom changes and health status and provide basic health guidance;

[0124] The exacerbation risk coefficient of low-risk patients is lower than the preset low-risk threshold, indicating that their immune systems are less sensitive to changes in pollen concentration, and the risk of allergic symptoms worsening due to changes in pollen concentration during the pollen peak season is relatively small. For such patients, the software system will automatically generate a low-intensity follow-up plan, including monthly symptom records and brief follow-up phone calls or online consultations. For example, the system will send an online questionnaire to patients every month, asking about changes in their allergic symptoms, and arrange a monthly phone follow-up. Doctors or nurses will learn about the patients' health status through the phone and provide general health guidance, such as how to reduce pollen exposure and keep the indoor environment clean. This follow-up method helps patients effectively manage their symptoms during the pollen peak season through regular monitoring and guidance, avoiding excessive medical intervention while ensuring that patients receive basic health support.

[0125] For medium-risk patients, a medium-intensity follow-up plan is developed and implemented to more frequently monitor changes in patients' symptoms and health status, adjust treatment plans if necessary, and provide targeted health guidance.

[0126] The exacerbation risk coefficient of medium-risk patients is within the preset medium-risk threshold range, meaning that their immune systems have medium sensitivity to changes in pollen concentration, and the risk of allergic symptoms worsening due to changes in pollen concentration during the pollen peak season is relatively high. For such patients, the software system will generate a medium-intensity follow-up plan, including detailed symptom records every two weeks and regular in-person doctor consultations or remote consultations. For example, the system will remind patients to fill out a detailed symptom log every two weeks, recording daily symptom changes, and arrange a remote video consultation every two weeks. Doctors will learn about changes in patients' symptoms through the video, adjust treatment plans if necessary, such as changing or increasing anti-allergy medications, and provide personalized health guidance, such as using an air purifier and avoiding going out during peak outdoor activity hours. Through more frequent monitoring and intervention, it is ensured that medium-risk patients receive timely and effective management during the pollen peak season.

[0127] For high-risk patients, a high-intensity follow-up plan is developed and implemented to frequently monitor changes in patients' symptoms and health status, quickly respond to symptom exacerbations, develop emergency treatment plans, and provide comprehensive health guidance and preventive measures.

[0128] The exacerbation risk coefficient of high-risk patients is higher than the preset high-risk threshold, indicating that their immune systems are very sensitive to changes in pollen concentration, and the risk of allergic symptoms worsening due to changes in pollen concentration during the pollen peak period is extremely high. For such patients, the software system will generate a high-intensity follow-up plan, including symptom records once a week or more frequently and frequent in-person doctor consultations or remote video consultations. For example, the system will remind patients to fill out a symptom log every week and arrange an in-person consultation or remote video consultation once a week. Based on the latest symptom changes of the patients, doctors can quickly adjust the treatment plan and formulate an emergency treatment plan if necessary, such as equipping emergency medications and equipment, recommending reducing outdoor activities, using high-efficiency air filtration devices, etc. Through frequent monitoring and timely medical intervention, it is ensured that high-risk patients can quickly respond to symptom exacerbation during the pollen peak period, reducing health risks and improving the quality of life.

[0129] Obtain the dynamic information during the implementation of the follow-up plan, analyze it after obtaining, evaluate the implementation of the follow-up plan, and dynamically adjust the follow-up plan according to the evaluation results;

[0130] In this embodiment, obtaining the dynamic information during the implementation of the follow-up plan, analyzing it after obtaining, evaluating the implementation of the follow-up plan, and dynamically adjusting the follow-up plan according to the evaluation results specifically include the following steps:

[0131] Obtain the dynamic information during the implementation of the follow-up plan, including the physiological parameter record information and treatment compliance information of all patients;

[0132] Obtaining the dynamic information during the implementation of the follow-up plan, including the physiological parameter record information and treatment compliance information of all patients, can be achieved through multiple software platforms and devices. First, patients can use portable physiological monitoring devices (such as smart bracelets, smart watches, or portable physiological parameter monitors) to record their physiological parameter data in real time. These devices are connected via Bluetooth or Wi-Fi and automatically synchronize the data to the patient's smartphone application. The data collected by the smartphone application includes key physiological indicators such as heart rate, respiratory rate, and blood oxygen saturation. At the same time, the software system can also interface with the hospital information system (HIS) or electronic health record system (EHR) to obtain the patient treatment compliance data recorded by doctors, such as the usage of prescription medications and the patient's medication records. Patients can also manually enter their medication times and dosages through the mobile application, and the system will automatically record this information. All data is transmitted through a secure network transmission protocol to ensure privacy and data security and is centrally stored in the cloud database. The software system will integrate and preprocess the collected physiological parameter record information and treatment compliance information for subsequent analysis and evaluation. This process realizes efficient and accurate data collection and management through automated data collection and synchronization functions, providing reliable basic information for the dynamic adjustment of the follow-up plan.

[0133] Preprocess the physiological parameter record information and treatment compliance information of all patients;

[0134] Preprocessing the physiological parameter record information and treatment compliance information of all patients is to ensure the accuracy, consistency, and availability of the data, thereby improving the reliability of subsequent analysis and evaluation. The preprocessing process includes multiple steps. First is data cleaning, where the software system automatically detects and removes outliers, duplicate records, and noisy data to ensure data accuracy. For example, for heart rate data, if the recorded value at a certain time point is significantly abnormal (such as outside the reasonable range), the system will mark and eliminate this data. Second is data imputation. For missing data points, the system can use interpolation methods or prediction algorithms based on historical data to reasonably fill in the data to ensure data integrity. Then is data standardization. To ensure the comparability of data from different devices and sources, the system standardizes the physiological parameter data, converting data with different units and ranges into a unified standard format. Finally is data synchronization and integration. The system integrates data from different times and sources into a unified database and performs time alignment on the data to ensure that the timestamps of physiological parameter records and treatment compliance information are consistent. Through the above preprocessing steps, the software system can provide high-quality data, providing a reliable basis for the dynamic adjustment and precise evaluation of the follow-up plan.

[0135] Extract the key physiological data from the physiological parameter record information of each preprocessed patient and the medication record data from the treatment compliance information, and perform analysis after extraction to generate the physiological parameter fluctuation index and treatment compliance coefficient for each patient respectively;

[0136] Construct an execution evaluation model using the physiological parameter fluctuation index and treatment compliance coefficient generated for each patient to generate the execution evaluation coefficient for each patient, and compare the generated execution evaluation coefficient for each patient with the pre-set execution evaluation coefficient threshold range to evaluate the execution of the follow-up plan for each patient, and dynamically adjust the follow-up plan according to the evaluation results.

[0137] The pre-set threshold range of the execution evaluation coefficient can be determined by analyzing a large amount of historical patient data and clinical research results. First, the software system collects and processes data on the physiological parameter fluctuation index and treatment compliance coefficient of a large number of patients, including patients with different health conditions and treatment compliance levels. Through data mining and statistical analysis, the system can identify the distribution of these parameters under different follow-up effects. Specific methods include using machine learning algorithms (such as cluster analysis, logistic regression, and decision trees, etc.) to classify and perform regression analysis on the data to determine which parameter combinations are associated with good, medium, or poor follow-up execution. The system models this historical data to generate a distribution map of the execution evaluation coefficient. Based on these analysis results, the system can set reasonable threshold ranges. For example, an execution evaluation coefficient higher than a certain threshold indicates that the follow-up plan is well executed, being in the middle range indicates that the follow-up plan is executed generally, and being lower than a certain threshold indicates that the follow-up plan is poorly executed. These threshold ranges are verified and optimized repeatedly to ensure their scientific nature and accuracy. Finally, the system incorporates these pre-set threshold ranges of the execution evaluation coefficient into the evaluation model to achieve automated evaluation and dynamic adjustment of the follow-up plan execution, so as to ensure the effectiveness and precision of follow-up management.

[0138] In this embodiment, the acquisition logic of the physiological parameter fluctuation index and treatment compliance coefficient of each patient is as follows:

[0139] Extract the key physiological data from the pre-processed physiological parameter record information of each patient, including the blood oxygen saturation of each patient at different moments within a period of time during the implementation of the follow-up plan and the corresponding time points, and represent them in a time series using the function SPO i (t), where t is the time point, and SPO i (t) represents the blood oxygen saturation of the i-th patient at time t within a period of time during the implementation of the follow-up plan. Define the time period as [t 1 , t 2 ;

[0140] The blood oxygen saturation and corresponding time points of each patient at different moments within a certain period during the implementation of the follow-up plan can be extracted in various ways. First, the patient can wear intelligent health monitoring devices, such as smart watches, smart bracelets, or portable pulse oximeters. These devices can continuously monitor and record the patient's blood oxygen saturation and transmit the data to the patient's smartphone application in real time via Bluetooth or Wi-Fi. The smartphone application uploads this data to the cloud database to ensure the real-time and security of the data. At the same time, the software system will be integrated with the electronic health record system of the medical institution to obtain the blood oxygen saturation data recorded by the doctor during the follow-up. After all this data is uploaded to the cloud, the software system will preprocess it, including timestamp alignment, outlier detection and processing, missing data filling, etc. Through these steps, the system can extract the blood oxygen saturation data of each patient at each time point within the specified period and standardize it into a unified format to ensure the consistency and accuracy of the data. This process realizes efficient and accurate data extraction through automated data collection, synchronization, and preprocessing functions, providing a reliable basis for subsequent analysis and evaluation.

[0141] Perform a Fourier transform on the blood oxygen saturation of the i-th patient at time t within a certain period, according to the formula:

[0142]

[0143] In the formula, F(SPO i (t)) is the frequency component of the blood oxygen saturation SPO i (t) of the i-th patient at time t within a certain period, t is the time variable, j is the frequency variable, and d is the imaginary unit;

[0144] The purpose of performing Fourier transform on the blood oxygen saturation of a patient at each moment over a period of time is to convert the time-domain signal into a frequency-domain signal, thereby revealing the frequency components in the change of blood oxygen saturation. Fourier transform can help us identify and analyze the periodic changes and fluctuation patterns in blood oxygen saturation data, which is very important for understanding the patient's physiological state and detecting abnormal conditions. The frequency variable j represents the frequencies of different frequency components in the signal, reflecting the speed of change of blood oxygen saturation over time. High-frequency components usually correspond to rapid, short-term fluctuations, such as acute physiological changes or noise, while low-frequency components correspond to slow, long-term trends, such as changes in chronic health conditions. The imaginary unit d is used to represent the phase information in the complex number domain, which helps describe the amplitude and phase relationship of the signal. In Fourier transform, the complex form enables us to handle both the amplitude and phase of the signal simultaneously, which is crucial for accurately describing the nature of the change in blood oxygen saturation. Through the software system, Fourier transform can be automated to perform frequency analysis on the blood oxygen saturation data of each patient, thereby generating a spectrogram showing the amplitudes at different frequencies. This process helps doctors and the medical team better understand the patient's physiological changes and formulate more effective follow-up plans and treatment regimens.

[0145] Take the amplitude of the result after performing Fourier transform on the blood oxygen saturation of the i-th patient at time t over a period of time, that is, the absolute value |F(SPO i (t))|, which represents the amplitude of the blood oxygen saturation of the i-th patient at time t over a period of time at different frequencies;

[0146] After performing Fourier transform on the blood oxygen saturation of the i-th patient at each moment over a period of time, the result is a series of complex numbers, and these complex numbers represent the amplitudes and phases of the signal at different frequencies. The amplitude of the result after Fourier transform, that is, the absolute value, reflects the energy intensity of these signals at each frequency component. Specifically, the amplitude is the modulus of the complex number, and the calculation formula is |F(SPO i (t))|, which represents the intensity of the blood oxygen saturation fluctuation at each frequency j. By calculating these amplitudes, we can quantify the fluctuation of the patient's blood oxygen saturation. A high amplitude indicates a significant fluctuation in blood oxygen saturation at a certain frequency, which may be related to specific physiological or pathological events. For example, higher-frequency components may reflect the patient's rapid breathing or instantaneous changes in blood oxygen saturation, while lower-frequency components may correspond to long-term chronic changes or the basal state. Combining the amplitude of the Fourier transform with the amplitude within the time period can comprehensively analyze the fluctuation of the patient's blood oxygen saturation at different frequencies. By automatically extracting and analyzing these amplitude data through the software system, doctors can identify abnormal fluctuation patterns, further diagnose the patient's health status, and formulate personalized treatment and follow-up plans based on these analysis results, thereby improving the accuracy and effectiveness of medical services.

[0147] Calculate the physiological parameter fluctuation index for each patient. The specific calculation formula is as follows:

[0148]

[0149] In the formula, PPFI i is the physiological parameter fluctuation index of the i-th patient;

[0150] The physiological parameter fluctuation index PPFI of the i-th patient i is the amplitude integral value of blood oxygen saturation at different frequencies calculated by Fourier transform. This index reflects the fluctuation intensity of the physiological parameters of the patient within a specific time period. A higher PPFI i indicates that the blood oxygen saturation of the patient has significant fluctuations during the follow-up period, which may imply that the patient's health condition is unstable or the follow-up plan is not well implemented. For example, frequent changes in blood oxygen saturation may indicate that the patient has not strictly followed the doctor's advice, has not taken medications on time or taken other preventive measures; it may also reflect that the treatment plan has failed to effectively control the condition. On the contrary, a lower PPFI i indicates that the blood oxygen saturation of the patient is relatively stable, indicating that the follow-up plan is well implemented, the patient's health condition is relatively stable, and the treatment plan is effective. By analyzing PPFI i , doctors can evaluate the implementation effect of the follow-up plan, adjust the treatment plan and follow-up measures in a timely manner to ensure that patients receive the best care and support. The software system can automatically calculate and monitor PPFI i , helping the medical team quickly identify poorly implemented follow-up plans, take corresponding improvement measures, and optimize the patient management process.

[0151] Extract the medication record data in the treatment compliance information of each preprocessed patient, including the total actual number of medications taken by each patient at different times within a period during the implementation of the follow-up plan. Calibrate the total actual number of medications taken by each patient within a period during the implementation of the follow-up plan as NA i , NA i represents the total actual number of medications taken by the i-th patient within a period during the implementation of the follow-up plan;

[0152] The actual total number of medication doses taken by each patient at different times during a period of time in the implementation of the follow-up plan can be extracted in various ways. First, patients can use smart medicine boxes or electronic medicine bottles, which are equipped with sensors and counters that can record the time of each opening of the medicine box to take medicine and transmit the data to the patient's smartphone application in real time via Bluetooth or Wi-Fi. The smartphone application will aggregate this data and upload it to the cloud database to ensure the timeliness and integrity of the data. Second, patients can also manually record their medication times and dosages through a mobile health management application, and the system will automatically save these records. In addition, the software system can be integrated with the hospital information system (HIS) or the electronic health record system (EHR) to obtain the patient medication information recorded by the doctor. After the data is uploaded to the cloud, the software system will perform data preprocessing, including removing duplicate records, detecting and processing outliers, timestamp alignment, etc. Through these steps, the system can extract the total number of actual medication doses taken by each patient during the specified period and standardize it into a unified format to ensure the consistency and accuracy of the data. In this way, doctors and the medical team can automatically obtain and analyze the patient's medication compliance data through the software system, providing reliable basic information for evaluating the implementation of the follow-up plan and adjusting the treatment plan.

[0153] Obtain the total number of medication doses required for each patient during this period in the implementation of the follow-up plan, and calibrate the total number of medication doses required for each patient during this period in the implementation of the follow-up plan as NT i , NT i represents the total number of medication doses required for the i-th patient during a period of time in the implementation of the follow-up plan;

[0154] The total number of medications that should be taken by each patient during a certain period in the implementation of the follow-up plan can be extracted in various ways. First, the software system can obtain this information from the electronic prescriptions and treatment plans issued by doctors, which usually record the types, dosages, and frequencies of medications that patients need to take within the specified time period. The electronic prescription system (e-Prescription) and the hospital information system (HIS) usually record the treatment plans of patients in detail and store this data in the electronic health record system (EHR). By integrating with these systems, the software can automatically extract the data on the medications that patients should take. In addition, the mobile health management application of patients can also synchronize this prescription information and generate medication reminders according to the doctor's treatment plan. The system will automatically calculate the total number of medications that should be taken by patients within a specific time period according to the time intervals and dosage requirements in the treatment plan. For example, if the treatment plan requires the patient to take medications three times a day and the follow-up period is 30 days, the system will automatically calculate that the total number of medications that should be taken is 90 times. All this data is transmitted through a secure network transmission protocol to ensure privacy and data security and is centrally stored in the cloud database. The software system will preprocess the collected data, including time alignment and format standardization, to ensure the consistency and accuracy of the data. This process realizes efficient and accurate extraction of the data on the medications that should be taken through automated data collection and processing functions, providing a solid foundation for evaluating the treatment compliance of patients and the implementation of the follow-up plan.

[0155] Calculate the treatment compliance coefficient for each patient. The specific calculation formula is as follows:

[0156]

[0157] In the formula, TAC i is the treatment compliance coefficient of the i-th patient.

[0158] The treatment compliance coefficient TAC of the i-th patient iIt reflects the ratio of the actual number of times a patient takes medicine during the follow-up period to the total number of times medicine should be taken as needed. A higher treatment compliance coefficient indicates that the patient has taken the medicine prescribed by the doctor on time and in the correct dosage, showing that the follow-up plan has been implemented well. Such patients usually show better treatment effects and stable physiological parameters, which means they are more likely to be managed according to the doctor's advice, thus effectively controlling the condition. On the contrary, a lower treatment compliance coefficient indicates that the patient has not strictly adhered to the treatment plan, and the actual number of times of taking medicine is much lower than the number of times medicine should be taken as needed, showing that the follow-up plan has been implemented poorly. Such patients may have unsatisfactory treatment effects due to taking medicine late or missing doses, and may even experience a deterioration of the condition. By evaluating the treatment compliance coefficient, doctors and the medical team can identify those patients who need more attention and intervention, adjust the follow-up plan and treatment plan in a timely manner, and provide more personalized and intensive follow-up management to improve the treatment compliance and overall health of the patients. The software system automatically calculates and monitors the treatment compliance coefficient to help the medical team quickly identify poorly implemented follow-up plans, take corresponding improvement measures, and optimize the patient management process.

[0159] In this embodiment, the physiological parameter fluctuation index PPFI of each generated patient i and the treatment compliance coefficient TAC i are used to construct an execution evaluation model, and the execution evaluation coefficient EEC of each patient is generated by weighted summation i , and the generated execution evaluation coefficient EEC of each patient i is compared with the pre-set execution evaluation coefficient threshold interval [EEC 1 , EEC 2 to evaluate the implementation of the follow-up plan for each patient, and the follow-up plan is dynamically adjusted according to the evaluation results. The specific analysis is as follows:

[0160] If EEC i < EEC 1, the implementation of the follow-up plan for this patient is poor. The patient's symptoms have not been effectively controlled or the treatment compliance is low. It is necessary to significantly increase the follow-up frequency of the follow-up plan, strengthen the monitoring measures, and adjust the treatment plan. This means that the physiological parameter fluctuation index of this patient is relatively high, and the treatment compliance coefficient is relatively low, indicating that the patient's physiological state fluctuates greatly and the patient fails to take medicine on time and in the correct dosage, resulting in an unsatisfactory implementation effect of the follow-up plan. Specifically, the patient's health condition may deteriorate or fail to improve significantly during the follow-up period, and the treatment effect is poor. Such a situation poses potential risks to the patient's health, which may lead to the aggravation of the disease or the occurrence of complications. Therefore, it is necessary to increase the follow-up frequency, such as once a week or more frequently, and strengthen the monitoring measures, such as real-time monitoring of physiological parameters and medication conditions. At the same time, the doctor needs to adjust the treatment plan according to the latest physiological and compliance data to more effectively control the disease and improve the patient's health condition. This can timely detect and address health problems, prevent the further deterioration of the disease, and ensure the health and safety of the patient;

[0161] If EEC 1 ≤EEC i ≤EEC 2 , the implementation of the follow-up plan for this patient is average. The improvement of symptoms and treatment compliance need to be enhanced. It is necessary to slightly increase the follow-up frequency of the follow-up plan and strengthen the monitoring measures, and adjust the treatment plan as needed. This means that both the physiological parameter fluctuation index and the treatment compliance coefficient of this patient are at a medium level, indicating that the patient's physiological state and medication compliance are relatively stable, but there is still room for improvement. The patient may have partial improvement of symptoms during the follow-up period, but the overall health condition still does not reach the best state. Such a situation has a certain impact on the patient's health, which may lead to the recurrence of the disease or slow improvement. Therefore, it is necessary to moderately increase the follow-up frequency, such as once every two weeks, and strengthen the monitoring measures, such as checking physiological parameters and medication records more frequently. The doctor should adjust the treatment plan in a timely manner according to the latest data of the patient to further improve the treatment effect and the patient's compliance. Through such adjustments, the changes in the patient's condition can be better tracked, medical intervention can be carried out in a timely manner, and the patient's recovery and health improvement can be promoted;

[0162] If EEC i >EEC 2, The follow-up plan for this patient has been carried out well. The patient's symptoms have improved significantly and the treatment compliance is high. Keep the follow-up frequency of the current follow-up plan without adjusting it. This means that the physiological parameter fluctuation index of this patient is low and the treatment compliance coefficient is high, indicating that the patient's physiological state is stable and strictly follows the doctor's medication instructions. The implementation effect of the follow-up plan is good, and the patient's symptoms have improved significantly during the follow-up, and the health condition has improved significantly. Such a situation has a positive impact on the patient's health, helps to continuously control the condition and prevent recurrence. Therefore, the current follow-up plan frequency, such as once a month, can be maintained, and the patient's physiological parameters and medication conditions can be continuously monitored. The doctor only needs to regularly check the data to ensure that the patient continues to receive treatment according to the established plan without major adjustments. This method can effectively consolidate the treatment effect, help the patient maintain a good health state, reduce excessive medical intervention, and improve the patient's quality of life and satisfaction.

[0163] Regularly generate follow-up reports and send the generated follow-up reports to doctors and patients, and at the same time provide long-term health management advice to patients.

[0164] In order to regularly generate follow-up reports and send them to doctors and patients, the software system will first regularly summarize and analyze all the collected patient physiological parameter record information and treatment compliance information. These data include key physiological indicators such as the patient's blood oxygen saturation, heart rate, respiratory rate, as well as the actual number of medication times and the total number of medications required. Through automated data processing and analysis algorithms, the system will generate a detailed follow-up report, and the report content includes the patient's physiological parameter fluctuation index, treatment compliance coefficient, physiological parameter trend chart, medication compliance chart, and health status assessment during the follow-up. After generating the report, the system will send the report to doctors and patients through secure encrypted emails or an integrated patient management platform. Doctors can view the detailed report through the platform, conduct a condition assessment and record feedback. At the same time, the system will also generate personalized long-term health management advice for patients based on the analysis results, including aspects such as diet, exercise, medication management, and daily care. Patients can access these suggestions through a mobile application or an online platform, receive health reminders and guidance from the system, so as to achieve full-process health management. This process ensures the efficiency, accuracy, and security of report generation and sending, provides reliable decision-making support for doctors, and helps patients continuously improve their health status.

[0165] As Figure 2 shown, an otolaryngology patient management follow-up system includes a patient file management module, a peak period risk assessment module, a personalized follow-up plan module, a dynamic follow-up assessment module, and an intelligent follow-up report module;

[0166] The patient file management module obtains the patient's basic information, medical records, allergy symptom descriptions, diagnosis results, and treatment plans, creates a personal file for the patient, and enters their symptom data and allergy history into the system;

[0167] The peak period risk assessment module obtains the symptom record information of all patients and the environmental pollen concentration information during the pollen peak period, analyzes them after acquisition, evaluates the risk level of each patient's allergy symptoms worsening due to pollen concentration changes, and classifies each patient according to the evaluation results;

[0168] The personalized follow-up plan module formulates and implements personalized follow-up plans for low-risk, medium-risk, and high-risk patients respectively according to the classification results of all patients;

[0169] The dynamic follow-up evaluation module obtains the dynamic information during the implementation of the follow-up plan, analyzes it after acquisition, evaluates the implementation of the follow-up plan, and dynamically adjusts the follow-up plan according to the evaluation results;

[0170] The intelligent follow-up report module regularly generates follow-up reports, sends the generated follow-up reports to doctors and patients, and provides long-term health management suggestions to patients.

[0171] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0172] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that contains one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0173] It should be understood that in various embodiments of the present application, the magnitudes of the serial numbers of the above processes do not imply the order of execution, and the order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0174] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0175] In several embodiments provided by the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the above-described embodiments are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces, and the indirect coupling or communication connection of devices or units can be in an electrical, mechanical or other form.

[0176] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0177] In addition, the functional units in various embodiments of the present application can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0178] 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 by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for follow-up management of otolaryngology patients, characterized in that: The specific steps include: Obtain the patient's basic information, medical records, allergy symptom descriptions, diagnosis results and treatment plans, establish the patient's personal file, and enter their symptom data and allergy history into the system; During the peak pollen season, we obtain symptom records of all patients and information on environmental pollen concentrations, analyze the information, assess the risk level of each patient's allergic symptoms being aggravated by changes in pollen concentration, and classify each patient based on the assessment results; During the peak pollen season, the symptom records of all patients and the environmental pollen concentration information are obtained and analyzed to assess the risk level of each patient's allergic symptoms being aggravated by changes in pollen concentration. The patients are then classified according to the assessment results, which specifically includes the following steps: During the peak pollen season, all patients were provided with symptom records and information on ambient pollen concentrations; Preprocessing of all patients’ symptom records and environmental pollen concentration information; Extracting the immune response data from the pre-processed symptom record information of each patient and the pollen concentration data from the environmental pollen concentration information, and analyzing them after extraction to generate the immune response fluctuation index and pollen concentration variation coefficient of each patient respectively; The logic for obtaining the immune response fluctuation index and pollen concentration variation coefficient of each patient is as follows: Extract the immune response data from the pre-processed symptom record information of each patient, including the immunoglobulin level values ​​and corresponding time points of each patient at different times over a period of time, and use the function MYQDB according to the time series i (T) represents the time point, MYQDB i (T) represents the immunoglobulin level of the i-th patient at time T in a period of time, i = 1, 2, 3, ..., k, k is a positive integer, and the time period is defined as [T1, T2]; Perform Fourier transform on the immunoglobulin level of the i-th patient at time T within a period of time, according to the formula: In the formula, F(MYQDB i (T)) is the immunoglobulin level value MYQDB at time T in the immune response data of the i-th patient with worsening symptoms i (T) frequency component, T is the time variable, f is the frequency variable, and z is the imaginary unit; The amplitude of the Fourier transform result after taking the immunoglobulin level value of the i-th patient at time T within a period of time, that is, the absolute value |F(MYQDB i (T))|, represents the amplitude of the immunoglobulin level of the i-th patient at time T in a period of time at different frequencies; Calculate the immune response fluctuation index of each patient. The specific calculation formula is as follows: Where IRFI i is the immune response fluctuation index of the i-th patient; Extract pollen concentration data from the preprocessed environmental pollen concentration information, including the average pollen concentration of each patient's activity area at different times within a period of time, and calibrate the average pollen concentration of each patient's activity area at different times within a period of time as represents the average pollen concentration of the activity area of ​​the ith patient at time m within a period of time, m = 1, 2, 3, ..., g, where g is a positive integer; Calculate the mean and standard deviation of the average pollen concentration in the activity area of ​​each patient over a period of time according to the formula: In the formula, is the average pollen concentration of the i-th patient’s activity area over a period of time, is the standard deviation of the average pollen concentration in the activity area of ​​the ith patient over a period of time; Calculate the coefficient of variation of pollen concentration for each patient. The specific calculation formula is as follows: Where, PCVC i is the coefficient of variation of pollen concentration of the ith patient; The generated immune response fluctuation index and pollen concentration variation coefficient of each patient are used to construct an aggravation risk assessment model, and the aggravation risk coefficient of each patient is generated. The generated aggravation risk coefficient of each patient is compared with a pre-set aggravation risk coefficient threshold interval to assess the risk level of aggravation of the allergic symptoms of each patient due to changes in pollen concentration, and each patient is classified according to the assessment results; The immune response fluctuation index IRFI generated for each patient i and pollen concentration variation coefficient PCVC i Construct an exacerbation risk assessment model and generate the exacerbation risk coefficient ERC for each patient by weighted summation i , and the generated risk coefficient ERC for each patient i Compared with the pre-set aggravation risk factor threshold [ERC 1 , ERC 2 ] intervals to assess the risk level of each patient's allergic symptoms being aggravated by changes in pollen concentration, and to classify each patient based on the assessment results. The specific analysis is as follows: If ERC i <ERC 1 , the patient's risk level of aggravation of allergic symptoms due to changes in pollen concentration is low risk, and the patient is classified as a low-risk patient; If ERC 1 ≤ERC i ≤ERC 2 , the patient's risk level of aggravation of allergic symptoms due to changes in pollen concentration is medium risk, and the patient is classified as a medium-risk patient; If ERC i >ERC 2 , the patient's risk level of aggravation of allergic symptoms due to changes in pollen concentration is high, and the patient is classified as a high-risk patient; According to the classification results of all patients, develop and implement personalized follow-up plans for low risk, medium risk and high risk respectively; Obtain dynamic information during the implementation of the follow-up plan, analyze it after acquisition, evaluate the implementation of the follow-up plan, and dynamically adjust the follow-up plan based on the evaluation results; Generate follow-up reports regularly and send them to doctors and patients, while providing patients with long-term health management advice.

2. The method for follow-up management of otolaryngology patients according to claim 1, characterized in that: According to the classification results of all patients, personalized follow-up plans for low risk, medium risk and high risk are formulated and implemented respectively, as follows: For low-risk patients, develop and implement a low-intensity follow-up plan and provide basic health guidance; For patients at medium risk, develop and implement a moderate intensity follow-up plan and provide targeted health guidance; For high-risk patients, develop and implement intensive follow-up plans, formulate emergency treatment plans, and provide comprehensive health guidance and preventive measures.

3. The method for follow-up management of otolaryngology patients according to claim 2, characterized in that: Obtain dynamic information during the implementation of the follow-up plan, analyze it after obtaining it, evaluate the implementation of the follow-up plan, and dynamically adjust the follow-up plan based on the evaluation results, which specifically includes the following steps: Obtain dynamic information during the implementation of the follow-up plan, including physiological parameter records and treatment compliance information of all patients; Pre-process the physiological parameter records and treatment compliance information of all patients; Extracting key physiological data from the preprocessed physiological parameter record information of each patient and medication record data from the treatment compliance information, and analyzing them after extraction to generate a physiological parameter fluctuation index and a treatment compliance coefficient for each patient respectively; The generated physiological parameter fluctuation index and treatment compliance coefficient of each patient are used to construct an execution evaluation model, and the execution evaluation coefficient of each patient is generated. The generated execution evaluation coefficient of each patient is compared with the pre-set execution evaluation coefficient threshold range to evaluate the implementation of the follow-up plan of each patient, and dynamically adjust the follow-up plan according to the evaluation results.

4. The method for follow-up management of otolaryngology patients according to claim 3, characterized in that: The logic for obtaining the physiological parameter fluctuation index and treatment compliance coefficient of each patient is as follows: Extract key physiological data from the pre-processed physiological parameter record information of each patient, including the blood oxygen saturation and corresponding time points of each patient at different times during the implementation of the follow-up plan, and use the function SPO according to the time series i (t) represents the time point, SPO i (t) represents the blood oxygen saturation of the ith patient at time t during the implementation of the follow-up plan, and the time period is defined as [t1, t2]; Perform Fourier transform on the blood oxygen saturation of the i-th patient at time t within a period of time, according to the formula: In the formula, F(SPO i (t)) is the blood oxygen saturation SPO of the i-th patient at time t within a period of time i (t) is the frequency component, where t is the time variable, j is the frequency variable, and d is the imaginary unit; Take the amplitude of the Fourier transform result of the blood oxygen saturation of the ith patient at time t within a period of time, that is, the absolute value |F(SPO i (t))|, represents the amplitude of the blood oxygen saturation of the i-th patient at time t within a period of time at different frequencies; Calculate the physiological parameter fluctuation index of each patient. The specific calculation formula is as follows: Where, PPFI i is the physiological parameter fluctuation index of the i-th patient; Extract the medication record data from the pre-processed treatment compliance information of each patient, including the total number of times each patient actually took medication at different times during a period of time during the implementation of the follow-up plan, and mark the total number of times each patient actually took medication during a period of time during the implementation of the follow-up plan as NA i , NA i It represents the total number of times the ith patient actually took medication during a period of time during the implementation of the follow-up plan; Obtain the total number of medications that each patient needs during the implementation of the follow-up plan, and mark the total number of medications that each patient needs during the implementation of the follow-up plan as NT i , NT i It represents the total number of medications that the i-th patient needs to take during a period of time during the implementation of the follow-up plan; Calculate the treatment compliance coefficient of each patient. The specific calculation formula is as follows: Where, TAC i is the treatment compliance coefficient of the ith patient.

5. The method for follow-up management of otolaryngology patients according to claim 4, characterized in that: The physiological parameter fluctuation index PPFI generated for each patient i and treatment adherence coefficient TAC i Construct an execution evaluation model and generate the execution evaluation coefficient EEC of each patient through weighted summation i , and the execution evaluation coefficient EEC of each patient generated i and the pre-set execution evaluation coefficient threshold interval [EEC 1 , EEC 2 ] to compare and evaluate the implementation of the follow-up plan for each patient, and dynamically adjust the follow-up plan based on the evaluation results. The specific analysis is as follows: If EEC i <EEC 1 , the patient's follow-up plan implementation is poor, and it is necessary to significantly increase the follow-up frequency of the follow-up plan, strengthen monitoring measures, and adjust the treatment plan; If EEC 1 ≤EEC i ≤EEC 2 The follow-up plan for this patient is generally implemented, and it is necessary to slightly increase the frequency of follow-up and strengthen monitoring measures, and adjust the treatment plan as needed; If EEC i >EEC 2 The follow-up plan for this patient is being implemented well. The follow-up frequency of the current follow-up plan will be maintained and no adjustments will be made to the follow-up plan.

6. An otolaryngology patient management and follow-up system, used to implement an otolaryngology patient management and follow-up method as described in any one of claims 1 to 5, characterized in that: It includes patient file management module, peak risk assessment module, personalized follow-up plan module, dynamic follow-up assessment module and intelligent follow-up report module; Patient file management module, which obtains the patient's basic information, medical records, allergy symptom descriptions, diagnosis results and treatment plans, establishes the patient's personal file, and enters his symptom data and allergy history into the system; Peak risk assessment module, during the peak pollen season, obtains and analyzes the symptom records of all patients and the environmental pollen concentration information, assesses the risk level of each patient's allergic symptoms being aggravated by changes in pollen concentration, and classifies each patient according to the assessment results; The personalized follow-up plan module develops and implements personalized follow-up plans for low-risk, medium-risk, and high-risk patients based on the classification results of all patients; Dynamic follow-up evaluation module, which obtains dynamic information of the follow-up plan during its implementation, analyzes it after acquisition, evaluates the implementation of the follow-up plan, and dynamically adjusts the follow-up plan based on the evaluation results; The intelligent follow-up report module generates follow-up reports regularly and sends them to doctors and patients, while providing patients with long-term health management advice.

Images