A headache risk assessment system and methods of use thereof

Abstract

This invention discloses a headache risk assessment system and its usage method, specifically relating to the field of medical testing technology. This invention achieves stratified, quantified, and objective assessment of headache risk, addressing the pain point of traditional assessments relying on subjective feedback. It stratifies by gender and age range, constructs a stratified reference control set based on the mean laboratory indicators of healthy controls, and generates a specific threshold control table by combining headache subject data, ensuring the assessment results align with the physiological characteristics of different populations. Simultaneously, it transforms laboratory test indicators into calculable risk coefficients, replacing traditional subjective scales. This achieves early objective screening of asymptomatic individuals, improves the relevance, accuracy, and repeatability of the assessment results, and reduces the risk of missed or misdiagnosed clinical cases.

Description

Technical Field

[0001] This invention relates to the field of medical testing technology, and more specifically, to a headache risk assessment system and its method of use. Background Technology

[0002] Headache is one of the most common clinical symptoms in neurology. Primary headaches (including migraines, tension headaches, cluster headaches, etc.) have a high global incidence and are prone to recurrence, which seriously affects patients' quality of life. At the same time, long-term recurrent headaches are also an independent risk factor for cardiovascular and cerebrovascular diseases such as stroke and cognitive impairment.

[0003] Currently, the diagnosis and risk assessment of headaches in clinical practice mainly rely on patients' subjective symptom descriptions, clinical history taking, and physical examinations. The lack of objective, quantitative, and repeatable laboratory assessment indicators leads to significant subjectivity in early risk screening and warning of headaches, resulting in a high risk of missed or misdiagnosis. Existing risk assessment tools for headaches are mostly subjective rating scales, entirely dependent on patient feedback, failing to achieve objective risk quantification and being unsuitable for early screening of asymptomatic individuals. The few headache-related assessment methods that involve laboratory indicators also suffer from the following core deficiencies:

[0004] Existing technologies do not incorporate individual characteristics such as gender and age for stratified assessment, ignoring the impact of physiological differences among different populations on headache risk. The assessment results lack specificity and accuracy, lack a standardized risk threshold determination system, and lack a unified stratified reference control standard, resulting in a lack of comparability and authority in the assessment results, making it difficult to promote and apply them in clinical practice.

[0005] Furthermore, relying solely on static test results from laboratory indicators without combining them with self-reported clinical indicators such as blood pressure, body mass index, and sleep quality, and without considering the dynamic trends of laboratory indicators, results in a single assessment dimension that fails to fully reflect the potential headache risk of the individuals being assessed.

[0006] To address this, a headache risk assessment system and its usage methods have been developed. Summary of the Invention

[0007] To overcome the above-mentioned deficiencies of the prior art, embodiments of the present invention provide a headache risk assessment system and a method for using it.

[0008] To achieve the above objectives, the present invention provides the following technical solution:

[0009] A headache risk assessment system includes the following modules:

[0010] The data import module is used to input the basic information of the person being evaluated, laboratory test data, and self-reported indicators;

[0011] The threshold quantification module is used to extract the basic information and laboratory test data of the headache subjects and the basic information and laboratory test data of the healthy controls. According to the preset gender and age grouping rules, the headache subjects are stratified. The laboratory test data of the stratified headache subjects and healthy controls are used to generate a headache risk threshold comparison table for different strata after comprehensive analysis and processing.

[0012] The risk output module is used to retrieve the laboratory test data of the person to be assessed and input it into the headache risk threshold comparison table for index comparison. Based on the comparison results, it selectively combines the symptom coefficient and trend coefficient to trigger a headache risk alarm.

[0013] Specifically, basic information includes gender and age;

[0014] Laboratory test data include blood lipid and inflammatory parameters, blood glucose parameters, and basic blood parameters;

[0015] Inflammatory parameters of blood lipids include total cholesterol, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, and high-sensitivity C-reactive protein;

[0016] Blood glucose parameters include glycated hemoglobin and fasting blood glucose;

[0017] Basic blood parameters include hemoglobin and platelet count;

[0018] Self-reported indicators include blood pressure, body mass index, and sleep quality.

[0019] Specifically, generate a comparison table of headache risk thresholds for different strata;

[0020] For each headache subject in each stratum, after extracting blood lipid and inflammatory parameters, blood glucose parameters, and basic blood parameters, they are matched with the corresponding reference control set for comparison and comprehensive processing, and the risk threshold coefficient of each headache subject in each stratum is output.

[0021] For each headache subject in each stratum, the highest and lowest coefficients are identified to construct a coefficient range, which serves as the risk threshold range.

[0022] By integrating risk threshold ranges from different strata, a comparison table of headache risk thresholds for different strata is generated.

[0023] Specifically, refer to the construction logic of the reference set;

[0024] After calculating the mean of the same laboratory test data for each healthy control in each stratum, the mean was used as the reference test data. The reference test data of each stratum were then integrated to obtain the reference control set for each headache subject in each stratum.

[0025] Specifically, the laboratory test data of the person to be evaluated are retrieved and entered into a headache risk threshold comparison table for index comparison;

[0026] Identify the basic information of the person to be evaluated, determine the stratum to which the person to be evaluated belongs, extract the reference control set of the stratum, and after normalization and comprehensive processing between the reference control set and the laboratory test data of the person to be evaluated, obtain the risk coefficient of the person to be evaluated.

[0027] Based on the stratum to which the person to be assessed belongs, the corresponding risk threshold range is located from the headache risk threshold comparison table. The calculated risk coefficient of the person to be assessed is compared with the risk threshold range. If it is at or above the risk threshold range, a headache risk alarm is triggered for the person to be assessed. If it is below the risk threshold range, a combined signaling is triggered.

[0028] Specifically, the logic for triggering a headache risk alarm based on signaling;

[0029] After triggering the binding signal, the self-reported indicators of the person to be evaluated are extracted, fused, and the self-state coefficient is obtained. The laboratory test data of the person to be evaluated before the current time point Q are extracted, and the Q groups of laboratory test data are sorted in chronological order and then fused to obtain the trend coefficient; where Q>3.

[0030] The assessed risk coefficient is multiplied by the individual's status coefficient and trend coefficient to obtain the updated assessed risk coefficient. The updated assessed risk coefficient is then compared with the risk threshold range. If the risk coefficient is at or above the risk threshold range, a headache risk alarm for the assessed person is triggered.

[0031] Specifically, the logic for obtaining the self-state coefficient;

[0032] The phenotype coefficient is obtained by comprehensively processing the blood pressure score, weight score, and sleep score of the person to be evaluated.

[0033] Set phenotypic threshold coefficients for phenotypic coefficients corresponding to different strata. If the phenotypic coefficient of the person to be evaluated is lower than the phenotypic threshold coefficient, the phenotypic coefficient is determined to be 1. Otherwise, the difference between the phenotypic coefficient and the phenotypic threshold coefficient is calculated and recorded as the phenotypic difference.

[0034] The pre-defined phenotype difference ranges are set for each group, and each group of difference ranges corresponds to a set of phenotype coefficients. After matching the phenotype difference of the person to be evaluated with the corresponding difference range, the phenotype coefficients are determined.

[0035] Specifically, the logic behind obtaining blood pressure scores, weight scores, and sleep scores;

[0036] Obtain the systolic and diastolic blood pressure of the person to be assessed; use the pre-built blood pressure level mapping rules, and combine the systolic and diastolic blood pressure of the person to be assessed to output the blood pressure level of the person to be assessed; set a blood pressure score corresponding to different blood pressure levels; convert the blood pressure level of the person to be assessed into a blood pressure score;

[0037] Based on the weight and height of the person being assessed, calculate the body mass index (BMI); and use a pre-built weight scoring mapping rule to convert the BMI into a weight score.

[0038] The study obtains the sleep intervals of the subject within a set time window prior to the headache risk assessment. For each day within the set time window, the sleep onset time and wake-up time are identified, and the average of the time differences is calculated to obtain the average sleep duration of the subject within the set time window. Normal sleep durations are defined for different strata. Based on the subject's stratum, the ratio of the subject's average sleep duration (numerator) to normal sleep duration (denominator) is calculated to obtain the sleep performance ratio. The sleep onset time of the subject within the set time window is compared with the preset normal sleep interval. If the subject's sleep onset time is later than the normal sleep interval on a certain day, it is determined as abnormal sleep. The number of abnormal sleep events within the set time window is counted, and the percentage of abnormal sleep events in the total number of days is calculated to obtain the abnormal sleep percentage.

[0039] The sleep performance ratio and abnormal sleep percentage of the subjects to be evaluated are converted into sleep scores using pre-built sleep scoring mapping rules.

[0040] Specifically, the logic for obtaining the trend coefficient;

[0041] The laboratory test data of group Q were compared with the reference control set of their respective strata to calculate the risk coefficient of the person to be evaluated for the Q tests before the current time point.

[0042] The slope of the fitted line for the risk coefficient of group Q is calculated using the least squares method. If the slope of the fitted line is less than or equal to 0, the trend coefficient is determined to be 1. Otherwise, the slope of the fitted line is converted into the trend coefficient according to the slope-trend coefficient mapping rule.

[0043] The technical effects and advantages of this invention are as follows:

[0044] (1) This invention achieves stratified, quantified and objective assessment of headache risk, solving the pain point of traditional assessment relying on subjective feedback. It is stratified by gender and age range, constructs a stratified reference control set based on the mean laboratory indicators of healthy controls, and generates a specific threshold control table by combining headache subject data, so that the assessment results are consistent with the physiological characteristics of different groups. At the same time, the laboratory test indicators are converted into calculable risk coefficients to replace traditional subjective scales, which not only realizes early objective screening of asymptomatic people, but also improves the pertinence, accuracy and repeatability of assessment results, and reduces the risk of clinical missed diagnosis and misdiagnosis.

[0045] (2) This invention adopts a multi-dimensional indicator fusion assessment logic to comprehensively and accurately reflect the headache risk status of the person being assessed. The assessment not only relies on static laboratory test data such as blood lipids, inflammation, and blood sugar, but also combines self-reported indicators such as blood pressure, weight, and sleep quality to calculate the self-status coefficient. At the same time, historical laboratory data is included, and the dynamic change trend of the indicators is considered through the trend coefficient. The basic risk coefficient is used for initial screening, and if the threshold is not reached, the self-status and trend coefficients are integrated for secondary assessment. The progressive judgment logic makes up for the shortcomings of traditional assessments that are single in dimension and ignore the dynamic changes of indicators, making the risk assessment more comprehensive and providing a scientific and reliable basis for early screening and early intervention of clinical headache risk. Attached Figure Description

[0046] Figure 1 This is a schematic diagram of a headache risk assessment system according to the present invention;

[0047] Figure 2 This is a flowchart illustrating the usage method of a headache risk assessment system according to the present invention. Detailed Implementation

[0048] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] Example 1

[0050] like Figure 1 As shown, a headache risk assessment system module is as follows:

[0051] The data import module is used to input the basic information of the person being evaluated, laboratory test data, and self-reported indicators;

[0052] Basic information includes gender and age;

[0053] Laboratory test data include blood lipid and inflammatory parameters, blood glucose parameters, and basic blood parameters;

[0054] Inflammatory parameters of blood lipids include total cholesterol, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, and high-sensitivity C-reactive protein;

[0055] Blood glucose parameters include glycated hemoglobin and fasting blood glucose;

[0056] Basic blood parameters include hemoglobin and platelet count;

[0057] Self-reported indicators include blood pressure, body mass index, and sleep quality;

[0058] It is important to note that sensitive information regarding the individuals to be evaluated and subsequent headache subjects (basic information and laboratory test data, etc.) is stored in encrypted form.

[0059] The threshold quantification module is used to extract the basic information and laboratory test data of subjects diagnosed with headaches according to the standard in the database, as well as the basic information and laboratory test data of healthy controls. According to the preset gender and age grouping rules, each headache subject is stratified. After comprehensive analysis and processing of the laboratory test data of the stratified headache subjects and healthy controls, a headache risk threshold comparison table for different strata is generated.

[0060] Additional notes: Configure preset gender and age grouping rules. The age grouping rules include at least four age ranges: 18-30 years old, 31-45 years old, 46-60 years old, and 61 years old and above, forming age groups for different genders. If the grouping is done according to the above age grouping rules, the final result will be 2 x 4 age ranges = 8 stratified groups, each of which includes headache subjects and healthy controls.

[0061] Specifically:

[0062] Data screening: Samples with headache subjects who had non-standard diagnosis or more than one missing laboratory data were excluded;

[0063] Samples from healthy controls with a history of headaches or abnormal laboratory data (beyond the normal clinical range) were excluded; ultimately, two groups of valid data were obtained: the headache group and the healthy control group.

[0064] After calculating the mean of the same laboratory test data of each healthy control in each stratum, the mean was used as the reference test data. The reference test data of each stratum were integrated to obtain the reference control set of each headache subject in each stratum.

[0065] That is, using formulas to reference test data The calculation yielded the result, where This represents the number of valid samples of healthy controls in the i-th stratum; The measured value of the k-th indicator of the n-th healthy control in the i-th stratum; Output: 8 reference test data for each stratum i, which is the reference control set for that stratum.

[0066] For each headache subject in each stratum, after extracting blood lipid and inflammatory parameters, blood glucose parameters, and basic blood parameters, they are matched with the corresponding reference control set for comparison and comprehensive processing, and the risk threshold coefficient of each headache subject in each stratum is output.

[0067] That is, using formulas After weighted calculation, the blood lipid risk coefficient is obtained. Blood sugar risk factor and blood risk factor ;

[0068] in , , as well as These represent total cholesterol, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, and high-sensitivity C-reactive protein, respectively, in the headache subjects.

[0069] , , as well as These represent the reference test data for total cholesterol, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, and high-sensitivity C-reactive protein in the reference control set within the stratum of the headache subjects. , , as well as These are preset weighting coefficients, and their sum is one;

[0070] Higher total cholesterol promotes atherosclerosis, affects the autoregulation of cerebral blood flow, and thus increases susceptibility to headaches. Lower high-density lipoprotein cholesterol means a decrease in vascular protection and a weakening of inflammation clearance. There is a certain correlation between migraines and elevated low-density lipoprotein cholesterol. During migraine attacks and remissions, migraine patients have higher levels of high-sensitivity C-reactive protein than healthy individuals.

[0071] , These represent the glycated hemoglobin and fasting blood glucose levels of the headache subjects, respectively.

[0072] , These represent the reference test data for glycated hemoglobin and fasting blood glucose in the reference control set within the stratum of headache subjects, respectively; , These are preset weighting coefficients, and their sum is one;

[0073] An elevated level of glycated hemoglobin indicates an increased risk of metabolic-related headaches.

[0074] Both elevated and decreased fasting blood sugar levels are potential triggers for headaches.

[0075] , These represent the hemoglobin and platelet counts, respectively, of the subject experiencing headaches.

[0076] , These represent the reference test data for hemoglobin and platelet counts within the reference control set of the headache subject's stratum, respectively. , These are preset weighting coefficients, and their sum is one;

[0077] Decreased hemoglobin and elevated platelet count are both potential triggers for headaches;

[0078] Risk factor for blood lipids Blood sugar risk factor and blood risk factor After normalization, the formula is used. The risk threshold coefficient is obtained by weighted calculation. ;in , as well as The weighting coefficients are set, and their sum is one.

[0079] For each headache subject in each stratum, the highest and lowest coefficients are identified to construct a coefficient range, which serves as the risk threshold range.

[0080] By integrating risk threshold ranges from different strata, a comparison table of headache risk thresholds for different strata is generated.

[0081] The risk output module is used to retrieve the laboratory test data of the person to be assessed and input it into the headache risk threshold comparison table for index comparison. Based on the comparison results, it selectively combines the symptom coefficient and trend coefficient to trigger a headache risk alarm.

[0082] Specifically:

[0083] The process involves identifying the basic information of the person to be evaluated, determining the stratum to which the person belongs, extracting the reference control set for the stratum, and then normalizing and integrating the data with the laboratory test data of the person to be evaluated to obtain the risk coefficient of the person to be evaluated.

[0084] Additional explanation: This refers to the risk factor for similar blood lipid levels. Blood sugar risk factor and blood risk factor The calculation logic involves substituting the lipid and inflammatory parameters, blood glucose parameters, and basic blood parameters of the individual to be assessed into the corresponding calculation formulas to obtain the lipid coefficient, blood glucose coefficient, and blood coefficient to be assessed. Similarly, the risk threshold coefficient is applied to the lipid coefficient, blood glucose coefficient, and blood coefficient to be assessed. The calculation logic outputs the risk coefficient to be evaluated.

[0085] Based on the stratification of the person to be assessed, the corresponding risk threshold range is located from the headache risk threshold comparison table. The calculated risk coefficient of the person to be assessed is compared with the risk threshold range. If it is at or above the risk threshold range, a headache risk alarm is triggered for the person to be assessed. If it is below the risk threshold range, a combined signaling is triggered.

[0086] After triggering the binding signal, the self-reported indicators of the person to be evaluated are extracted, fused, and the self-state coefficient is obtained. The laboratory test data of the person to be evaluated before the current time point Q are extracted, and the Q groups of laboratory test data are sorted in chronological order and then fused to obtain the trend coefficient.

[0087] Q > 3, which is specifically set based on the historical test records of the person being evaluated.

[0088] The assessed risk coefficient is multiplied by the individual status coefficient and the trend coefficient to obtain the updated assessed risk coefficient. The updated assessed risk coefficient is then compared with the risk threshold range. If it is at or above the risk threshold range, a headache risk alarm for the assessed person is triggered.

[0089] Self-reported indicators include blood pressure, body mass index, and sleep quality;

[0090] Obtain the systolic and diastolic blood pressure of the person to be evaluated;

[0091] Using a pre-built blood pressure level mapping rule, the blood pressure level of the person being assessed is output by combining the systolic and diastolic blood pressure.

[0092] The blood pressure level mapping rule includes blood pressure levels corresponding to different range sets; the blood pressure levels are divided into 1-5 levels; the range set includes systolic blood pressure range and diastolic blood pressure range. The blood pressure level is determined after the systolic and diastolic blood pressure of the person to be evaluated is successfully matched with the range set.

[0093] Different blood pressure levels are assigned a blood pressure score; the blood pressure levels of the individuals to be assessed are converted into blood pressure scores.

[0094] Based on the weight and height of the person being assessed, calculate the body mass index (BMI); and use a pre-built weight scoring mapping rule to convert the BMI into a weight score.

[0095] Body mass index = weight (kg) / height (m)².

[0096] Obesity is an independent risk factor for chronic headaches, especially chronic daily headaches.

[0097] The weight score mapping rules include weight scores corresponding to different body mass index (BMI) ranges. The higher the BMI, the higher the weight score will be. The weight score range is limited to 1-10.

[0098] Based on the forms filled out by the person to be assessed before the assessment, obtain the sleep interval of the person to be assessed within the time window set before the headache risk assessment.

[0099] The default time window is 7 consecutive days, but the specific time window should be set according to the information provided by the person being evaluated.

[0100] For the sleep intervals of the person to be evaluated on each day within the set time window, the time of falling asleep and the time of waking up are identified, and the time difference is calculated and the average value is taken to obtain the average sleep duration of the person to be evaluated within the set time window.

[0101] Normal sleep duration is set for different levels. Based on the level to which the person being evaluated belongs, the average sleep duration of the person being evaluated is used as the numerator and the normal sleep duration is used as the denominator to calculate the ratio and obtain the sleep performance ratio.

[0102] The sleep time of the person to be evaluated on each day within the set time window is compared with the preset normal sleep interval. If the sleep time of the person to be evaluated on a certain day is later than the normal sleep interval, it is judged as abnormal sleep. The number of abnormal sleep events within the set time window is counted and the percentage of abnormal sleep events in the total number of days is calculated to obtain the percentage of abnormal sleep.

[0103] For the sleep performance ratio and abnormal sleep percentage of the subject to be evaluated, a pre-built sleep scoring mapping rule is used to convert them into a sleep score.

[0104] The sleep rating mapping rules include sleep ratings corresponding to different sleep sets. The higher the sleep performance ratio and the percentage of abnormal sleep, the higher the matched sleep rating, indicating that the sleep quality of the person being evaluated is worse. The sleep rating range is limited to 1-10. The sleep set includes the range of sleep performance ratio and the range of abnormal sleep percentage. The sleep rating is determined after the sleep performance ratio and the percentage of abnormal sleep of the person being evaluated are successfully matched with the corresponding sleep set.

[0105] The phenotype coefficient is obtained by comprehensively processing the blood pressure score, weight score, and sleep score of the person to be evaluated.

[0106] After normalizing the blood pressure score, weight score, and sleep score, the data were substituted into the formula. The phenotypic coefficient is obtained by weighted calculation. ,in , as well as These represent blood pressure score, weight score, and sleep score, respectively. , as well as The weighting coefficients are set, and their sum is one.

[0107] Set phenotypic threshold coefficients for phenotypic coefficients corresponding to different strata. If the phenotypic coefficient of the person to be evaluated is lower than the phenotypic threshold coefficient, the phenotypic coefficient is determined to be 1. Otherwise, the difference between the phenotypic coefficient and the phenotypic threshold coefficient is calculated and recorded as the phenotypic difference.

[0108] The system presets the range of differences for each group of phenotype differences, and each range corresponds to a set of phenotype coefficients. The range of phenotype coefficients is limited to 1.038-1.113. The larger the phenotype difference, the worse the overall blood pressure, weight and sleep status of the person being evaluated, and the higher the probability of matching 1.113. The range of 1.038-1.113 is initially set by technicians and can be dynamically updated according to the actual situation.

[0109] After matching the phenotype difference of the individuals to be evaluated with the corresponding difference intervals, the phenotype coefficient is determined.

[0110] Extract the laboratory test data of the subject to be evaluated from the Q tests before the current time point, sort the Q sets of laboratory test data in chronological order, and calculate the risk coefficient of the subject to be evaluated by comparing the Q sets of laboratory test data with the reference control set of their respective strata, so as to obtain the risk coefficient of the subject to be evaluated for the Q tests before the current time point.

[0111] The slope of the fitted line for the risk coefficient of group Q is calculated using the least squares method. If the slope of the fitted line is less than or equal to 0, the trend coefficient is determined to be 1. Otherwise, the slope of the fitted line is converted into the trend coefficient according to the slope-trend coefficient mapping rule.

[0112] The slope-trend coefficient mapping rule includes the trend coefficient corresponding to each slope range, where the trend coefficient range is limited to 1.042-1.187; it is initially set by technical personnel and can be dynamically updated according to the actual situation; the larger the slope, the higher the probability of matching 1.187.

[0113] Example 2

[0114] Please see Figure 2As shown, based on Embodiment 1 of this application, a headache risk assessment system is provided. Embodiment 2 of this application proposes a method for using the headache risk assessment system. Embodiment 2 is merely a preferred embodiment of Embodiment 1, and the implementation of Embodiment 2 will not affect the individual implementation of Embodiment 1.

[0115] Specifically, Embodiment 2 of this application provides a method for using a headache risk assessment system, including:

[0116] Step 1: Enter the basic, laboratory, and self-reported indicator data of the person to be evaluated in the input interface of the data import module;

[0117] Step 2: Using the built-in stratified processing logic of the threshold quantization module, extract the pre-stored headache subject data, stratify it by gender and age, and then calculate the mean values ​​of the indicators of healthy controls in each stratum to build a reference control set.

[0118] Step 3: Calculate the risk threshold coefficient of headache subjects by combining laboratory indicator data, and construct a threshold comparison table;

[0119] Step 4: Match the individuals to be assessed and calculate their risk coefficients. If the risk coefficient reaches the threshold, a headache risk alarm is triggered. If the risk coefficient does not reach the threshold, a headache risk alarm is triggered by combining signaling and calculating the symptom coefficient and trend coefficient. After the risk coefficient is updated, if it reaches the threshold, a headache risk alarm is triggered.

[0120] The above formulas are all dimensionless calculations. Dimensionless calculations can be performed using various methods such as standardization, which will not be elaborated here. The formulas are derived from software simulations based on a large amount of collected data, and the preset parameters in the formulas can be set by those skilled in the art according to the actual situation.

[0121] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as 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, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, ATA hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid-state ATA hard disk.

[0122] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0123] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0124] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0125] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0126] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0127] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable ATA hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0128] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A headache risk assessment system, characterized by, Includes the following modules: The data import module is used to input the basic information of the person being evaluated, laboratory test data, and self-reported indicators; The threshold quantification module is used to extract the basic information and laboratory test data of the headache subjects and the basic information and laboratory test data of the healthy controls. According to the preset gender and age grouping rules, the headache subjects are stratified. The laboratory test data of the stratified headache subjects and healthy controls are used to generate a headache risk threshold comparison table for different strata after comprehensive analysis and processing. The risk output module is used to retrieve the laboratory test data of the person to be assessed and input it into the headache risk threshold comparison table for index comparison. Based on the comparison results, it selectively combines the symptom coefficient and trend coefficient to trigger a headache risk alarm.

2. The headache risk assessment system according to claim 1, characterized in that: Basic information includes gender and age; Laboratory test data include blood lipid and inflammatory parameters, blood glucose parameters, and basic blood parameters; Inflammatory parameters of blood lipids include total cholesterol, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, and high-sensitivity C-reactive protein; Blood glucose parameters include glycated hemoglobin and fasting blood glucose; Basic blood parameters include hemoglobin and platelet count; Self-reported indicators include blood pressure, body mass index, and sleep quality.

3. The headache risk assessment system according to claim 2, characterized in that: Generate a comparison table of headache risk thresholds for different strata; For each headache subject in each stratum, after extracting blood lipid and inflammatory parameters, blood glucose parameters, and basic blood parameters, they are matched with the corresponding reference control set for comparison and comprehensive processing, and the risk threshold coefficient of each headache subject in each stratum is output. For each headache subject in each stratum, the highest and lowest coefficients are identified to construct a coefficient range, which serves as the risk threshold range. By integrating risk threshold ranges from different strata, a comparison table of headache risk thresholds for different strata is generated.

4. A headache risk assessment system according to claim 3, characterized in that: The construction logic of the reference set; After calculating the mean of the same laboratory test data for each healthy control in each stratum, the mean was used as the reference test data. The reference test data of each stratum were then integrated to obtain the reference control set for each headache subject in each stratum.

5. A headache risk assessment system according to claim 3, characterized in that: Retrieve the laboratory test data of the person to be evaluated and input them into the headache risk threshold comparison table for index comparison; Identify the basic information of the person to be evaluated, determine the stratum to which the person to be evaluated belongs, extract the reference control set of the stratum, and after normalization and comprehensive processing between the reference control set and the laboratory test data of the person to be evaluated, obtain the risk coefficient of the person to be evaluated. Based on the stratum to which the person to be assessed belongs, the corresponding risk threshold range is located from the headache risk threshold comparison table. The calculated risk coefficient of the person to be assessed is compared with the risk threshold range. If it is at or above the risk threshold range, a headache risk alarm is triggered for the person to be assessed. If it is below the risk threshold range, a combined signaling is triggered.

6. A headache risk assessment system according to claim 5, characterized in that: Triggering the headache risk alarm judgment logic after combining signaling; After triggering the binding signal, the self-reported indicators of the person to be evaluated are extracted, fused, and the self-state coefficient is obtained. The laboratory test data of the person to be evaluated before the current time point Q are extracted, and the Q groups of laboratory test data are sorted in chronological order and then fused to obtain the trend coefficient; where Q>3. The assessed risk coefficient is multiplied by the individual's status coefficient and trend coefficient to obtain the updated assessed risk coefficient. The updated assessed risk coefficient is then compared with the risk threshold range. If the risk coefficient is at or above the risk threshold range, a headache risk alarm for the assessed person is triggered.

7. A headache risk assessment system according to claim 6, characterized in that: The logic for obtaining the self-state coefficient; The phenotype coefficient is obtained by comprehensively processing the blood pressure score, weight score, and sleep score of the person to be evaluated. Set phenotypic threshold coefficients for phenotypic coefficients corresponding to different strata. If the phenotypic coefficient of the person to be evaluated is lower than the phenotypic threshold coefficient, the phenotypic coefficient is determined to be 1. Otherwise, the difference between the phenotypic coefficient and the phenotypic threshold coefficient is calculated and recorded as the phenotypic difference. The pre-defined phenotype difference ranges are set for each group, and each group of difference ranges corresponds to a set of phenotype coefficients. After matching the phenotype difference of the person to be evaluated with the corresponding difference range, the phenotype coefficients are determined.

8. A headache risk assessment system according to claim 6, characterized in that: The logic behind obtaining blood pressure scores, weight scores, and sleep scores; Obtain the systolic and diastolic blood pressure of the person to be assessed; use the pre-built blood pressure level mapping rules, and combine the systolic and diastolic blood pressure of the person to be assessed to output the blood pressure level of the person to be assessed; set a blood pressure score corresponding to different blood pressure levels; convert the blood pressure level of the person to be assessed into a blood pressure score; Based on the weight and height of the person being assessed, calculate the body mass index (BMI); and use a pre-built weight scoring mapping rule to convert the BMI into a weight score. The study obtains the sleep intervals of the subject within a set time window prior to the headache risk assessment. For each day within the set time window, the sleep onset time and wake-up time are identified, and the average of the time differences is calculated to obtain the average sleep duration of the subject within the set time window. Normal sleep durations are defined for different strata. Based on the subject's stratum, the ratio of the subject's average sleep duration (numerator) to normal sleep duration (denominator) is calculated to obtain the sleep performance ratio. The sleep onset time of the subject within the set time window is compared with the preset normal sleep interval. If the subject's sleep onset time is later than the normal sleep interval on a certain day, it is determined as abnormal sleep. The number of abnormal sleep events within the set time window is counted, and the percentage of abnormal sleep events in the total number of days is calculated to obtain the abnormal sleep percentage. The sleep performance ratio and abnormal sleep percentage of the subjects to be evaluated are converted into sleep scores using pre-built sleep scoring mapping rules.

9. A headache risk assessment system according to claim 7, characterized in that: Logic for obtaining trend coefficients; The laboratory test data of group Q were compared with the reference control set of their respective strata to calculate the risk coefficient of the person to be evaluated for the Q tests before the current time point. The slope of the fitted line for the risk coefficient of group Q is calculated using the least squares method. If the slope of the fitted line is less than or equal to 0, the trend coefficient is determined to be 1. Otherwise, the slope of the fitted line is converted into the trend coefficient according to the slope-trend coefficient mapping rule.

10. A method of using a headache risk assessment system, applied to the headache risk assessment system according to any one of claims 1-9, characterized in that: Step 1: Enter the basic, laboratory, and self-reported indicator data of the person to be evaluated in the input interface of the data import module; Step 2: Using the built-in stratified processing logic of the threshold quantization module, extract the pre-stored headache subject data, stratify it by gender and age, and then calculate the mean values ​​of the indicators of healthy controls in each stratum to build a reference control set. Step 3: Calculate the risk threshold coefficient of headache subjects by combining laboratory indicator data, and construct a threshold comparison table; Step 4: Match the individuals to be assessed and calculate their risk coefficients. If the risk coefficient reaches the threshold, a headache risk alarm is triggered. If the risk coefficient does not reach the threshold, a headache risk alarm is triggered by combining signaling and calculating the symptom coefficient and trend coefficient. After the risk coefficient is updated, if it reaches the threshold, a headache risk alarm is triggered.

Images