AI-based long-term follow-up and prognostic assessment system for gynecological endocrine disorders

Abstract

This invention relates to the field of medical data processing technology, specifically to an artificial intelligence-based long-term follow-up and prognostic assessment system for gynecological endocrine diseases. The system includes a data acquisition module for acquiring diagnostic and physical examination data of individuals undergoing prognosis; a time period filtering module for determining periods of stable disease and periods of disease deterioration during follow-up; a diagnostic data analysis module for determining disease deterioration characteristic values ​​by combining medication use, the number of follow-up diagnoses during periods of disease deterioration, and the time intervals between these periods; a physical examination data analysis module for determining disease confidence factors based on fluctuations in physical examination data during different periods of disease deterioration; and an assessment module for adjusting the systematic assessment value of the individual's condition by combining the number of follow-up diagnoses, the disease confidence factors, and the disease deterioration characteristic values, thereby obtaining an adjusted disease assessment value and classifying the individual's risk. This invention improves the accuracy of long-term follow-up and prognostic assessment.

Description

Technical Field

[0001] This invention relates to the field of medical data processing technology, specifically to an artificial intelligence-based long-term follow-up and prognostic assessment system for gynecological endocrine diseases. Background Technology

[0002] Polycystic ovary syndrome (PCOS) is the most common endocrine and metabolic disorder among women of reproductive age, affecting approximately 10% to 15% of women. The etiology of PCOS is complex, and its main characteristics include irregular menstruation, excessive androgens, polycystic ovaries, and insulin resistance. Due to its diverse clinical manifestations and pathological mechanisms, there are significant individual differences in the diagnosis and treatment of PCOS. Therefore, long-term follow-up and effective prognostic assessment are crucial for management and prevention.

[0003] Existing follow-up systems for gynecological endocrine disorders largely rely on subjective human assessment based on the individual's current physical condition and clinical examination results, and on developing treatment plans based on symptoms. However, this method often overlooks the changes in the disease over time and the individual's disease history. This results in diagnostic results at each follow-up visit only reflecting the individual's current physical condition, leading to a somewhat one-sided judgment and failing to comprehensively consider long-term health changes. Furthermore, while the individual's condition may fluctuate between follow-up intervals, existing systems fail to effectively integrate real-time changes in vital signs for dynamic assessment of disease recovery. This deficiency may cause prognostic assessments to deviate from actual changes, resulting in inaccurate prognostic evaluations. Summary of the Invention

[0004] To address the technical problem of inaccurate prognostic assessment, the present invention aims to provide an artificial intelligence-based long-term follow-up and prognostic assessment system for gynecological endocrine diseases. The specific technical solution adopted is as follows:

[0005] In a first aspect, embodiments of the present invention provide a long-term follow-up and prognostic assessment system for gynecological endocrine diseases based on artificial intelligence, the system comprising the following modules:

[0006] The data acquisition module is used to acquire diagnostic data and vital sign data of individuals with poor prognosis.

[0007] The time period filtering module is used to determine the stable disease period during follow-up based on the similarity between diagnostic data from two adjacent follow-up diagnoses; and to determine the period of disease deterioration for prognostic individuals based on medication use during the stable disease period.

[0008] The diagnostic data analysis module is used to determine the characteristic values ​​of disease deterioration by combining the medication use of patients with poor prognosis, the number of follow-up diagnoses during the period of disease deterioration, and the time interval between follow-up diagnoses.

[0009] The vital signs data analysis module is used to determine the prognostic confidence factors of individuals based on the fluctuations in vital signs data during different periods of disease deterioration.

[0010] The assessment module is used to adjust the systematic assessment value of the prognostic personnel's condition by combining the number of follow-up diagnoses, the condition confidence factor, and the condition deterioration characteristic value, so as to obtain the adjusted condition assessment value of the prognostic personnel; based on the adjusted condition assessment value, the prognostic personnel are classified into risks.

[0011] Furthermore, determining the stable disease time series based on the similarity between diagnostic data from two adjacent follow-up diagnoses includes:

[0012] The diagnostic data includes: keywords from the diagnostic results report;

[0013] The keywords are transformed into vectors in a high-dimensional space to obtain the word vector for each keyword;

[0014] For any two adjacent follow-up diagnoses, the similarity of the word vectors corresponding to the keywords in the two diagnostic reports is calculated. The average similarity between all word vectors in the two diagnostic reports is taken as the overall similarity between the two follow-up diagnoses. The two word vectors corresponding to the similarity are from different diagnostic reports.

[0015] When the overall similarity between two follow-up diagnoses is within a preset stable range, the time period between the two follow-up diagnoses is determined as the stable time sequence of the follow-up condition; among them, the stable time sequences of the follow-up condition that are consecutive in time are merged.

[0016] Furthermore, the determination of the period of disease deterioration in prognostic individuals based on medication use during the stable period of follow-up includes:

[0017] Based on medication use during the stable period of follow-up, the characteristic values ​​of the disease during the stable period of follow-up were determined;

[0018] When the disease characteristic value is within the preset deterioration range, the follow-up period of stable disease corresponding to the disease characteristic value is determined as the period of disease deterioration.

[0019] Furthermore, the determination of disease characteristic values ​​for the stable disease period based on medication use during the follow-up period includes:

[0020] The diagnostic data includes: keywords in the diagnostic results report; the keywords include drug keywords;

[0021] The average number of drug keyword types in the diagnostic results report of all follow-up diagnoses within the stable follow-up time period is used as the total number of drugs.

[0022] The number of drug keyword types in the diagnostic results report obtained from the last follow-up diagnosis within the stable follow-up time series is used as the end drug quantity.

[0023] The number of drug keyword types in the diagnostic results report obtained from the first follow-up diagnosis within the stable follow-up time period is used as the initial drug quantity.

[0024] By negatively mapping the difference between the initial and final drug quantities, the drug maintenance coefficient is obtained.

[0025] By combining the total number of drugs and the drug maintenance coefficient, the disease characteristic values ​​of prognostic individuals during the stable period of follow-up were determined.

[0026] Furthermore, the determination of disease deterioration characteristic values ​​by combining the patient's medication history, the number of follow-up diagnoses during the period of disease progression, and the time interval between follow-up diagnoses includes:

[0027] Based on medication use during the stable period of follow-up, the characteristic values ​​of the disease during the stable period of follow-up were determined;

[0028] The degree of disease deterioration is determined by combining the number of follow-up diagnoses during the period of disease progression with the characteristic values ​​of the disease.

[0029] Based on the time interval between follow-up diagnoses and the degree of disease deterioration during the period of disease progression in prognostic individuals, disease recovery control factors for prognostic individuals were determined.

[0030] By combining the number of follow-up diagnoses and the disease recovery control factors, characteristic values ​​for disease deterioration were determined.

[0031] Furthermore, the determination of the degree of disease deterioration by combining the number of follow-up diagnoses during the period of disease progression with disease characteristic values ​​includes:

[0032] The product of the number of follow-up diagnoses during the period of disease deterioration and the corresponding disease characteristic value during the period of disease deterioration is normalized, and the normalized result is used as the degree of disease deterioration.

[0033] Furthermore, the determination of disease recovery control factors for prognostic individuals based on the time interval between follow-up diagnoses and the degree of disease deterioration during the period of disease progression includes:

[0034] Any period of disease deterioration is taken as the target period of disease deterioration; the sum of the degree of disease deterioration in the target period of disease deterioration and the previous period of disease deterioration is taken as the numerator, and the time interval between the first follow-up diagnosis in the target period of disease deterioration and the first follow-up diagnosis in the previous period of disease deterioration is taken as the denominator. The ratio of the numerator and the denominator is taken as the single-segment control factor for prognostic personnel in the target period of disease deterioration.

[0035] The sum of the individual control factors for all periods of disease deterioration in prognostic individuals is calculated as the overall control factor; the overall control factor is then subjected to negative correlation normalization mapping to obtain the disease recovery control factor for prognostic individuals.

[0036] Furthermore, the determination of disease deterioration characteristic values ​​by combining the number of follow-up diagnoses and disease recovery control factors includes:

[0037] The percentage of follow-up diagnoses during all periods of disease deterioration for prognostic individuals is calculated as the percentage of follow-up diagnoses during disease deterioration.

[0038] By performing negative correlation normalization mapping on the product of the percentage of follow-up visits for disease deterioration and the disease recovery control factor, the characteristic value of disease deterioration is obtained.

[0039] Furthermore, the determination of prognostic confidence factors based on fluctuations in vital signs data during different periods of disease progression in prognostic individuals includes:

[0040] The vital signs data include: luteinizing hormone (LH) levels, follicle-stimulating hormone (FSH) levels, androgen levels, and physical health index;

[0041] The normalized value of the ratio of luteinizing hormone (LH) to follicle-stimulating hormone (FSH) was calculated as the first sign of dysfunction in the prognostic population. The normalized value of the difference between the physical health index and a preset standard range of physical health index was calculated as the second sign of dysfunction in the prognostic population. The normalized value of the difference between the androgen level and a preset standard range of androgen levels was calculated as the third sign of dysfunction in the prognostic population. The first, second, and third sign of dysfunction values ​​were weighted and summed to obtain the total sign of dysfunction. Curve fitting was performed on the sign of dysfunction values ​​at different sampling times during the target period of disease progression to obtain the sign of dysfunction change curve. The proportion of sign of dysfunction values ​​in the decreasing phase of the sign of dysfunction change curve was obtained as the dysfunction percentage.

[0042] The difference between the average value of arrhythmias at all sampling times during the target period of disease deterioration and the value of arrhythmias at the first sampling time during the target period of disease deterioration is used as the initial confidence factor.

[0043] By combining the disordered percentage during the target period of disease deterioration with the initial confidence factor, the disease confidence factor for prognostic individuals during the target period of disease deterioration was determined.

[0044] Furthermore, the systematic assessment value of the prognostic personnel's condition is adjusted by combining the number of follow-up diagnoses, the confidence factor of the condition, and the characteristic value of the condition deterioration, resulting in the adjusted assessment value of the prognostic personnel's condition, including:

[0045] Any period of disease deterioration is taken as the target period of disease deterioration; the proportion of the number of follow-up diagnoses during the target period of disease deterioration of prognostic personnel to the total number of follow-up diagnoses during all periods of disease deterioration is calculated as a correction factor for the target period of disease deterioration.

[0046] Calculate the product of the correction factor, the confidence factor, and the characteristic value of disease deterioration for the target disease deterioration period, and use it as the single-segment disease adjustment coefficient for the target disease deterioration period; standardize the sum of the single-segment disease adjustment coefficients for all disease deterioration periods to obtain the disease adjustment coefficient for prognostic individuals.

[0047] By combining the disease adjustment coefficient, the disease system assessment value of the prognostic personnel is corrected to obtain the disease adjustment assessment value.

[0048] Secondly, an artificial intelligence-based method for long-term follow-up and prognostic assessment of gynecological endocrine diseases is provided, the method comprising the following steps:

[0049] Obtain diagnostic and vital sign data from individuals with poor prognosis;

[0050] Based on the similarity between diagnostic data from two consecutive follow-up diagnoses, the time series of stable disease during follow-up was determined; based on medication use during the stable disease period, the time series of disease deterioration for individuals with good prognosis was determined.

[0051] The characteristic values ​​of disease deterioration were determined by combining the medication use of patients with poor prognosis, the number of follow-up diagnoses during the period of disease deterioration, and the time interval between follow-up diagnoses.

[0052] Based on the fluctuations in vital signs data of prognostic individuals during different periods of disease deterioration, we determined the prognostic confidence factors for each individual's condition.

[0053] By combining the number of follow-up diagnoses, disease confidence factors, and disease deterioration characteristic values ​​of the prognostic individuals, the systematic assessment values ​​of their disease status were adjusted to obtain the adjusted disease status values. Based on these adjusted disease status values, the prognostic individuals were classified into risk groups.

[0054] Thirdly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, it implements the various possible implementations of the first aspect.

[0055] Fourthly, embodiments of the present invention provide a computer program product comprising: computer program code, which, when executed on a computer, causes the computer to perform the method described in the first aspect or any possible implementation thereof.

[0056] Fifthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the various possible implementations of the first aspect.

[0057] The embodiments of the present invention have at least the following beneficial effects:

[0058] This invention, by integrating multiple diagnostic results and real-time vital sign data of individuals undergoing prognosis, can more comprehensively and accurately grasp their health status, avoiding the errors and biases that may arise from a single diagnosis, and providing a more reliable diagnostic basis. By collecting vital sign data in real time and combining it with historical diagnostic results, the system assessment value of the condition can be corrected, dynamically reflecting the changing trend of the individual's condition, promptly detecting fluctuations in the condition, and further accurately reflecting changes in the individual's condition through corrected deterioration characteristic values, thus obtaining a more accurate prognostic assessment. Attached Figure Description

[0059] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0060] Figure 1 This is a system block diagram of an artificial intelligence-based long-term follow-up and prognostic assessment system for gynecological endocrine diseases, provided as an embodiment of the present invention.

[0061] Figure 2 This is a flowchart of a method for long-term follow-up and prognostic assessment of gynecological endocrine diseases based on artificial intelligence, provided as an embodiment of the present invention. Detailed Implementation

[0062] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of the artificial intelligence-based long-term follow-up and prognostic assessment system for gynecological endocrine diseases proposed in accordance with the present invention.

[0063] In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments may be combined in any suitable form.

[0064] In the description of the embodiments of the present invention, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of the present invention, "multiple" means two or more.

[0065] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0066] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0067] The embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art will recognize that, with technological advancements and the emergence of new scenarios, the technical solutions provided by the embodiments of the present invention are also applicable to similar technical problems.

[0068] This invention provides a specific implementation method for an artificial intelligence-based long-term follow-up and prognostic assessment system for gynecological endocrine diseases. This method is applicable to long-term follow-up and prognostic assessment scenarios for gynecological endocrine diseases. Polycystic ovary syndrome (PCOS) is the most common endocrine and metabolic disorder among women of reproductive age, affecting approximately 10% to 15% of women. The etiology of PCOS is complex, and due to its diverse clinical manifestations and pathological mechanisms, there are significant individual differences in the diagnosis and treatment of PCOS. Although PCOS is a long-term disease, the condition of individuals undergoing follow-up may fluctuate to some extent. However, existing systems fail to effectively integrate changes in real-time vital signs data to dynamically assess disease recovery. This deficiency may lead to deviations in the assessment of the individual's condition from actual changes, resulting in inaccurate prognostic assessments.

[0069] The following description, in conjunction with the accompanying drawings, details the specific scheme of the artificial intelligence-based long-term follow-up and prognostic assessment system for gynecological endocrine diseases provided by this invention.

[0070] Please see Figure 1 The diagram illustrates a system block diagram of an artificial intelligence-based long-term follow-up and prognostic assessment system for gynecological endocrine diseases according to an embodiment of the present invention. The system includes the following modules:

[0071] The data acquisition module 10 is used to acquire diagnostic data and vital sign data of individuals with poor prognosis.

[0072] The diagnostic report issued by the doctor after each follow-up visit is obtained from the hospital's internal database. In subsequent steps, the diagnostic report can also be referred to as diagnostic data. The diagnostic report includes text data, which includes diagnostic information and medication information.

[0073] The TF-IDF method was used to extract keywords from the text data of the diagnostic result reports of prognostic individuals, and the extracted keywords were then input into a trained neural network for recognition. This yielded all drug keywords and diagnostic keywords from any follow-up diagnostic report of the prognostic individuals. These drug keywords and diagnostic keywords are collectively referred to as keywords.

[0074] During the time interval between two consecutive follow-up diagnoses, individuals undergoing prognostic assessments collected luteinizing hormone (LH), follicle-stimulating hormone (FSH), and androgen levels using a portable urine testing device. Their weight and height were also recorded to obtain the corresponding Body Mass Index (BMI). The LH, FSH, and androgen levels, along with the BMI, were used as vital sign data. Sampling was conducted every two days, with data collected using the portable urine testing device each time. It should be noted that the BMI was calculated as weight / height squared, where weight is in kilograms and height is in meters. This method of calculating the BMI is existing technology and will not be elaborated upon further.

[0075] The time period filtering module 20 is used to determine the stable time period of follow-up condition based on the similarity between the diagnostic data of two adjacent follow-up diagnoses; and to determine the time period of deterioration of the prognosis of the person based on the medication used during the stable time period of follow-up condition.

[0076] The similarity between diagnostic data from follow-up diagnoses can characterize the similarity of drug types used by prognostic individuals and the stability of their condition within different time intervals of follow-up diagnoses. The higher the similarity of diagnostic data between two follow-up diagnoses, the more stable the condition is. Therefore, the follow-up time sequence of prognostic individuals can be segmented.

[0077] For any keyword in the diagnostic data from any follow-up diagnosis of a prognostic individual, the keyword is transformed into a vector in a high-dimensional space by training a word vector model (such as Word2Vec, GloVe, etc.), thus obtaining the word vector for each keyword. It should be noted that the transformation of keywords into vectors in a high-dimensional space is an existing technology and will not be elaborated upon here.

[0078] For any two consecutive follow-up diagnoses, the similarity of the word vectors corresponding to the keywords in the two diagnostic reports is calculated. The average similarity between all word vectors in the two diagnostic reports is taken as the overall similarity between the two follow-up diagnoses. Specifically, the two word vectors corresponding to the similarity score come from different diagnostic reports.

[0079] Taking any two follow-up diagnoses as an example, specifically the i-th and j-th follow-up diagnoses, for the diagnostic data from the i-th and j-th follow-up diagnoses, the keywords in the diagnostic data from the i-th and j-th follow-up diagnoses are arbitrarily paired to obtain several keyword combinations between the i-th and j-th follow-up diagnoses. Each keyword combination contains two keywords, which come from different follow-up diagnoses. The cosine similarity between the word vectors of the two keywords in each keyword combination is taken as the similarity of each keyword combination. The average similarity of all keyword combinations between the i-th and j-th follow-up diagnoses is taken as the overall similarity between the i-th and j-th follow-up diagnoses.

[0080] When the overall similarity between two follow-up diagnoses is within a preset stable range, the time period between the two follow-up diagnoses is determined as the stable follow-up period; wherein, temporally consecutive stable follow-up periods are merged. In this embodiment of the invention, the preset stable range is [0.8, 1].

[0081] In other words, in the follow-up timeline of prognostic individuals, if the overall similarity between the diagnostic data of the first and second follow-up diagnoses is greater than or equal to 0.8, the time period consisting of the first and second follow-up diagnoses is recorded as the first stable follow-up timeline for the prognostic individual. If the similarity between the diagnostic data of the second and third follow-up diagnoses is also greater than or equal to 0.8, the third follow-up is added to the first stable follow-up timeline, and so on, until the similarity between the next adjacent follow-up diagnostic results is less than 0.8, at which point the merging of the stable follow-up timelines ends, thus obtaining all stable follow-up timelines for the prognostic individual.

[0082] The number of medication types can reflect whether a person's condition is effectively controlled. For example, common PCOS treatments include oral contraceptives, insulin sensitizers, and anti-androgens. A gradual decrease in the number of these medications may indicate effective management of the condition; a large number of medications may suggest a more complex condition or that symptoms are not yet effectively controlled. Therefore, based on the medication use of individuals during each stable disease period in follow-up, disease characteristic values ​​for each stable disease period are obtained.

[0083] Based on the medication use of prognostic individuals during each stable disease period in each follow-up period, the disease characteristic values ​​of prognostic individuals during each stable disease period are obtained. Specifically: the mean number of drug keyword types in the diagnostic results reports of all follow-up diagnoses within the stable disease period is obtained as the total number of drugs; the number of drug keyword types in the diagnostic results report of the last follow-up diagnose within the stable disease period is obtained as the final drug quantity; the number of drug keyword types in the diagnostic results report of the first follow-up diagnose within the stable disease period is obtained as the initial drug quantity; a negative correlation mapping is performed on the difference between the initial drug quantity and the final drug quantity to obtain the drug maintenance coefficient; combining the total drug quantity and the drug maintenance coefficient, the disease characteristic values ​​of prognostic individuals during the stable disease period in each follow-up period are determined.

[0084] In some embodiments, taking the i-th follow-up period of stable disease as any follow-up period of stable disease as an example, the disease characteristic value of the i-th follow-up period of stable disease is... The calculation formula is: ;in, is the average number of drug keyword types in the diagnostic results reports of all follow-up diagnoses within the i-th follow-up period when the condition is stable, which is also the total number of drugs in the i-th follow-up period when the condition is stable; exp is an exponential function with the natural constant as the base. The number of drug keywords in the diagnostic results report during the first follow-up diagnosis within the i-th follow-up period when the condition is stable. The number of drug keyword types in the diagnostic report of the last follow-up diagnosis during the i-th follow-up period when the condition is stable; norm is a normalization function, preferably a maximum-minimum value normalization function.

[0085] The larger the total number of medications used during the stable disease period in the follow-up, the more complex the patient's condition and the less effectively the symptoms were controlled during the corresponding stable disease period in the follow-up, and the higher the disease characteristic value.

[0086] in, When it is a positive value, A larger value indicates that the patient's condition has stabilized during the i-th follow-up period, the condition has been effectively controlled, and the doctor has reduced medication use; the corresponding condition characteristic value is smaller. Conversely, a smaller value indicates a lower condition. Negative value The smaller the value of , the greater the corresponding disease characteristic value, indicating that the prognostic person's condition worsened during the i-th follow-up period when the condition was stable, and the doctor increased the use of medication.

[0087] When the disease characteristic value is within a preset deterioration range, the stable follow-up period corresponding to the disease characteristic value is determined to be the period of disease deterioration. In this embodiment of the invention, the preset deterioration range is [0.7, 1]. In other embodiments, the implementer may adjust this range according to the actual situation. That is, when the disease deterioration characteristic value is greater than or equal to 0.7, the corresponding stable follow-up period is determined to be the period of disease deterioration.

[0088] Preferably, two thresholds, 0.3 and 0.7, can be preset. If the disease characteristic value of the prognostic individual in the i-th follow-up period of stable condition is less than or equal to 0.3, it indicates that the prognostic individual's condition has been stably controlled and is recovering well, and the corresponding follow-up period of stable condition is taken as the recovery period. If the disease characteristic value of the prognostic individual in the i-th follow-up period of stable condition is greater than 0.3 and less than 0.7, it indicates that the prognostic individual's condition is in a stable state, neither deteriorating nor recovering well, and the corresponding follow-up period of stable condition is taken as the stable period. If the disease characteristic value of the prognostic individual in the i-th follow-up period of stable condition is greater than or equal to 0.7, it indicates that the prognostic individual's condition is deteriorating, and the corresponding follow-up period of stable condition is taken as the deterioration period.

[0089] The diagnostic data analysis module 30 is used to determine the characteristic values ​​of disease deterioration by combining the medication use of the prognostic personnel, the number of follow-up diagnoses during the period of disease deterioration, and the time interval between follow-up diagnoses.

[0090] For any period of disease deterioration in a prognostic individual, the longer the duration and the higher the disease characteristic value, the more severe the disease deterioration, leading to a worsening of the condition and more pronounced symptoms, indicating a poorer treatment outcome.

[0091] Therefore, the degree of disease deterioration can be determined by combining the number of follow-up diagnoses during the period of disease deterioration with the disease characteristic values. Specifically, the product of the number of follow-up diagnoses during the period of disease deterioration and the disease characteristic values ​​corresponding to the period of disease deterioration is normalized, and the normalized result is used as the degree of disease deterioration.

[0092] If, during follow-up, the disease deterioration occurs multiple times at short intervals, and the severity of the disease worsens with each episode, it indicates a poorer disease control effect. Therefore, the method for obtaining the disease deterioration characteristic value of prognostic individuals is as follows: Based on the time interval between follow-up diagnoses during the disease deterioration period and the severity of the disease, the disease recovery control factor is determined; combining the number of follow-up diagnoses and the disease recovery control factor, the disease deterioration characteristic value is determined, specifically:

[0093] First, calculate the percentage of follow-up diagnoses during all periods of disease deterioration for the prognostic individuals out of the total number of follow-up diagnoses, which is the percentage of follow-up diagnoses during disease deterioration. In other words, the sum of the number of follow-up diagnoses during all periods of disease deterioration for the prognostic individuals is recorded as the first sum. The ratio between the first sum and the number of all follow-up diagnoses for the prognostic individuals is used as the percentage of follow-up diagnoses during disease deterioration for the prognostic individuals.

[0094] Secondly, any period of disease deterioration is taken as the target period of disease deterioration; the sum of the degree of disease deterioration in the target period of disease deterioration and the previous period of disease deterioration is taken as the numerator, and the time interval between the first follow-up diagnosis in the target period of disease deterioration and the first follow-up diagnosis in the previous period of disease deterioration is taken as the denominator. The ratio of the numerator and denominator is taken as the single-segment control factor for the prognostic personnel in the target period of disease deterioration; the sum of the single-segment control factors for all periods of disease deterioration of the prognostic personnel is calculated as the overall control factor; the overall control factor is subjected to negative correlation normalization mapping to obtain the prognostic personnel's disease recovery control factor.

[0095] In some embodiments, taking the j-th period of disease deterioration as the target period of disease deterioration, the formula for calculating the disease recovery control factor K is as follows: ;in, The degree of disease deterioration during the target period of disease progression; The degree of disease deterioration preceding the target period of disease deterioration; The time interval between the first follow-up diagnosis during the target period of disease deterioration and the first follow-up diagnosis during the previous period of disease deterioration; J represents the single-segment control factor for the target disease exacerbation period in prognostic individuals; J represents the number of disease exacerbation periods. It should be noted that for the first disease exacerbation period in prognostic individuals, due to the large amount of data and its singularity, the disease recovery control factor is not calculated.

[0096] After obtaining the percentage of follow-up visits for disease deterioration and the disease recovery control factor, the product of the percentage of follow-up visits for disease deterioration and the disease recovery control factor is negatively correlated and normalized to obtain the disease deterioration characteristic value.

[0097] The vital signs data analysis module 40 is used to determine the confidence factor of the prognosis of individuals based on the fluctuations in vital signs data during different periods of disease deterioration.

[0098] Because each follow-up visit to the hospital may involve different doctors providing diagnoses, which may be inconsistent, and the time intervals between visits may also prevent timely detection of changes in the condition, the accuracy of the degree of disease deterioration during the worsening period may be inaccurate.

[0099] However, the vital signs data of the prognostic personnel are collected in real time, which can provide continuous information on changes in the condition and reflect the health status of the prognostic personnel in a timely manner, avoiding the information loss caused by the diagnostic gap in a single follow-up visit; therefore, it can be further combined with real-time vital signs data analysis to accurately obtain the prognostic assessment of the prognostic personnel.

[0100] The ratio of luteinizing hormone (LH) to follicle-stimulating hormone (FSH) is often used as an important indicator of the severity of polycystic ovary syndrome (PCOS). This is primarily because the ratio reflects hormonal imbalances in a woman's body, particularly an imbalance in the LH / FSH ratio. In a normal menstrual cycle, FSH and LH secretion are regular; FSH is responsible for promoting follicle maturation, while LH plays a crucial role in ovulation. Normally, the FSH / LH ratio is approximately 1:1. However, in individuals with PCOS, due to hormonal imbalances, LH secretion is typically significantly increased, while FSH secretion is lower, leading to an elevated LH / FSH ratio. Therefore, in this embodiment of the invention, the normalized value of the ratio of luteinizing hormone (LH) to follicle-stimulating hormone (FSH) is calculated as the first physical sign disorder value for the prognostic individual; the normalized value of the difference between the physical health index and the preset standard physical health index range is calculated as the second physical sign disorder value for the prognostic individual; the normalized value of the difference between the androgen level and the preset standard androgen level range is calculated as the third physical sign disorder value for the prognostic individual; the first, second, and third physical sign disorder values ​​are weighted and summed to obtain the physical sign disorder value.

[0101] The specific method for obtaining the difference between the physical health index and the preset standard physical health index range is as follows: when the physical health index is within the preset standard physical health index range, the difference between the physical health index and the preset standard physical health index range is 0; when the physical health index exceeds the preset standard physical health index range, the absolute value of the difference between the physical health index and the upper limit of the preset standard physical health index range is calculated as the difference between the physical health index and the preset standard physical health index range; when the physical health index is lower than the preset standard physical health index range, the absolute value of the difference between the physical health index and the lower limit of the preset standard physical health index range is calculated as the difference between the physical health index and the preset standard physical health index range.

[0102] Similarly, the specific method for obtaining the difference between the androgen value and the preset standard androgen value range is as follows: when the androgen value is within the preset standard androgen value range, the difference between the androgen value and the preset standard androgen value range is 0; when the androgen value exceeds the preset standard androgen value range, the absolute value of the difference between the androgen value and the upper limit of the preset standard androgen value range is calculated as the difference between the androgen value and the preset standard androgen value range; when the androgen value is lower than the preset standard androgen value range, the absolute value of the difference between the androgen value and the lower limit of the preset standard androgen value range is calculated as the difference between the androgen value and the preset standard androgen value range.

[0103] In this embodiment of the invention, when the first, second, and third abnormality values ​​are weighted and summed, each of the three data values ​​is assigned a weight of 1 / 3. In other embodiments, the implementer may assign different weight values ​​to these three data values ​​according to the actual emphasis placed on different abnormality data. In this embodiment of the invention, the preset standard healthy body range is [18.5, 24], and the preset standard androgen range is 50-60 ng / dL. The androgen referred to in this embodiment of the invention is total testosterone. In other embodiments, the implementer may set other preset standard healthy body ranges and preset standard androgen ranges according to the regulations of different hospitals. In this embodiment of the invention, the unit for androgen values ​​is nanograms per deciliter (ng / dL).

[0104] The sequence of arrhythmia values ​​of prognostic individuals at all sampling times during each period of disease deterioration is obtained and denoted as the sequence of arrhythmia values ​​of prognostic individuals during each period of disease deterioration; wherein, each sampling time has a corresponding arrhythmia value.

[0105] If the vital signs of a prognostic individual continue to rise during the period of disease deterioration, it indicates that the individual's PCOS condition has been worsening throughout this period, and the confidence level of the severity of the disease deterioration during this period is relatively high. Conversely, if the vital signs of a prognostic individual decrease or stabilize during the period of disease deterioration, it indicates that the individual's PCOS condition is recovering well during this period, but the severity of the disease deteriorates due to the influence of other complications, and therefore the confidence level of the severity of the disease deterioration during this period is relatively low.

[0106] Based on the fluctuations in vital signs data of individuals during different stages of disease progression, prognostic confidence factors for each individual were determined, specifically:

[0107] First, curve fitting is performed on the arrhythmia values ​​of the prognostic individuals at different sampling times during the target period of disease deterioration to obtain the arrhythmia change curve. More specifically, the least squares method is used to perform curve fitting on the arrhythmia values ​​of the prognostic individuals at all sampling times during the target period of disease deterioration to obtain the arrhythmia change curve of the prognostic individuals during the target period of disease deterioration.

[0108] Then, the proportion of arrhythmias in the declining phase of the arrhythmia change curve is obtained as the arrhythmia proportion. The difference between the average arrhythmia value at all sampling times during the target disease deterioration period and the arrhythmia value at the first sampling time during the target disease deterioration period is calculated as the initial confidence factor. Combining the arrhythmia proportion and the initial confidence factor during the target disease deterioration period, the prognostic confidence factor for the individual during the target disease deterioration period is determined. It should be noted that arrhythmias in the declining phase are those with a slope value less than 0.

[0109] By combining the disorder percentage during the target period of disease deterioration and the initial confidence factor, the prognostic confidence factor for individuals during the target period of disease deterioration is determined. Specifically, the normalized value of the product of the disorder percentage during the target period of disease deterioration and the initial confidence factor is used as the prognostic confidence factor for individuals during the target period of disease deterioration.

[0110] In some embodiments, taking the j-th time period of disease exacerbation as the target time period of disease exacerbation as an example, the prognostic confidence factor of the disease at the target time period of disease exacerbation is... The calculation formula is: ;in, Indicates the prognosis of the person in the first month. The number of all abnormal signs values ​​with a slope less than 0 on the curve of abnormal signs changes during a period of disease deterioration; Indicates the prognosis of the person in the first month. The number of all abnormal signs values ​​on the curve of abnormal signs during a period of disease progression; Indicates the prognosis of the person in the first month. The percentage of disorders during each period of disease progression; Indicates the prognosis of the person in the first month. The average value of signs and arrhythmias at all times during a period of disease deterioration; Indicates the prognosis of the person in the first month. The value of abnormal signs at the first sampling time during the period of disease deterioration; Indicates the prognosis of the person in the first month. Initial confidence factor for each period of disease deterioration.

[0111] Among them, the greater the proportion of dysregulation during the period of disease deterioration and the longer the period of PCOS disease deterioration in the prognostic individuals, the greater the confidence factor of the disease; the greater the initial confidence factor during the period of disease deterioration, the greater the degree of increase in the initial signs of dysregulation in the prognostic individuals, and the greater the confidence factor of the disease during the period of disease deterioration.

[0112] The assessment module 50 is used to adjust the systematic assessment value of the prognostic personnel's condition by combining the number of follow-up diagnoses, the condition confidence factor, and the condition deterioration characteristic value, so as to obtain the adjusted condition assessment value of the prognostic personnel; based on the adjusted condition assessment value, the prognostic personnel are classified into risks.

[0113] The longer the period of disease deterioration lasts, the more times the prognostic personnel follow up for diagnosis during this period, the more information is lost due to the diagnostic gap, and the greater the weight that needs to be adjusted for the degree of disease deterioration during this period. Therefore, the prognostic personnel's systematic assessment value is adjusted by combining the number of follow-up diagnoses, the disease confidence factor, and the disease deterioration characteristic value, resulting in the prognostic personnel's adjusted disease assessment value.

[0114] First, any period of disease deterioration is taken as the target period of disease deterioration. The percentage of follow-up diagnoses during the target period of disease deterioration for prognostic individuals is calculated as the proportion of follow-up diagnoses during all periods of disease deterioration, and this percentage is used as a correction factor for the target period of disease deterioration. That is, using the [missing information - likely a specific timeframe or period]... The period of disease deterioration is taken as the target period, and the first period is... The ratio of the number of diagnoses diagnosed during all follow-up visits of patients with deterioration during a specific period of disease progression to the total number of diagnoses diagnosed during all follow-up visits of patients with deterioration during all periods of disease progression is used as the basis for determining the number of diagnoses diagnosed during all follow-up visits of patients with deterioration during a specific period of disease progression. Correction factors for each period of disease progression.

[0115] Furthermore, the product of the correction factor, the confidence factor, and the characteristic value of disease deterioration during the target disease deterioration period is calculated as the single-segment disease adjustment coefficient for the target disease deterioration period. The sum of the single-segment disease adjustment coefficients for all disease deterioration periods is standardized to obtain the disease adjustment coefficient for the prognostic personnel. In this embodiment of the invention, standardization is also known as normalization, which can be achieved through the maximum-minimum normalization method.

[0116] The latest diagnostic reports of patients with prognoses are analyzed using existing clinical scoring systems commonly used within hospitals to obtain a systematic assessment value for their condition. In other embodiments, physicians may manually score the latest diagnostic reports of patients with prognoses, and the resulting scores may be used as the systematic assessment value for their condition.

[0117] Then, by combining the condition adjustment coefficient obtained by analyzing the physical signs and diagnostic data of the prognostic personnel in the embodiments of the present invention, the subjective condition system assessment value is corrected to obtain the condition adjustment assessment value.

[0118] Specifically: Calculate the product of the condition-adjusted assessment value and the condition-system assessment value as the adjustment assessment value; and normalize the sum of the adjustment assessment value and the condition-adjusted assessment value as the condition-adjusted assessment value.

[0119] In some embodiments, the prognostic adjusted assessment value for individuals is... The calculation formula is: ;in, Adjustment coefficient for the condition; This is a systematic assessment value for the prognosis of individuals.

[0120] Since the current disease-adjusted assessment value is obtained by further optimizing the doctor's diagnosis based on the real-time changes in the prognostic person's vital signs, the disease-adjusted assessment value of the prognostic person is more accurate. The higher the current disease-adjusted assessment value of the prognostic person, the greater the deterioration of the prognostic person's disease during the follow-up period, and the prognostic person needs more active treatment and close follow-up.

[0121] Finally, based on the adjusted assessment values, risk classification was performed for individuals with poor prognosis:

[0122] Two risk parameter thresholds are preset: the first risk parameter threshold T1 = 0.75 and the second risk parameter threshold T2 = 0.25. If the adjusted assessment value of the prognostic person's condition is greater than or equal to the first risk parameter threshold, the prognostic person is recorded as a high-risk prognostic person; if the current adjusted assessment value of the prognostic person's condition is less than or equal to the second risk parameter threshold, the prognostic person is recorded as a low-risk prognostic person; if the current adjusted assessment value of the prognostic person's condition is less than the first risk parameter threshold but greater than the second risk parameter threshold, the prognostic person is recorded as a medium-risk prognostic person.

[0123] In a preferred embodiment of the present invention, the follow-up time for prognostic individuals is adjusted based on their prognostic assessment:

[0124] Among all gynecological prognostic patients with PCOS in the hospital, the follow-up interval for high-risk patients was shortened, and these patients were given priority to be notified to come to the hospital for follow-up diagnosis; the follow-up interval for medium-risk patients was shortened, and they were notified to come to the hospital for follow-up diagnosis after the high-risk patients had completed their follow-up visits; and low-risk patients were managed and diagnosed through routine treatment and regular check-up visits.

[0125] For individuals with a high-risk prognostic assessment, more frequent and closer follow-up is required. This helps to detect changes in the condition or complications in a timely manner, ensuring intervention before the condition worsens, thereby improving the treatment success rate. For individuals with a low-risk prognostic assessment, the follow-up interval can be appropriately extended, reducing unnecessary frequent examinations and treatments, and allowing for a more rational allocation of resources.

[0126] Please see Figure 2 , Figure 2 A flowchart of a method for long-term follow-up and prognostic assessment of gynecological endocrine diseases based on artificial intelligence is provided for embodiments of the present invention. The method includes the following steps:

[0127] Obtain diagnostic and vital sign data from individuals with poor prognosis;

[0128] Based on the similarity between diagnostic data from two consecutive follow-up diagnoses, the time series of stable disease during follow-up was determined; based on medication use during the stable disease period, the time series of disease deterioration for individuals with good prognosis was determined.

[0129] The characteristic values ​​of disease deterioration were determined by combining the medication use of patients with poor prognosis, the number of follow-up diagnoses during the period of disease deterioration, and the time interval between follow-up diagnoses.

[0130] Based on the fluctuations in vital signs data of prognostic individuals during different periods of disease deterioration, we determined the prognostic confidence factors for each individual's condition.

[0131] By combining the number of follow-up diagnoses, disease confidence factors, and disease deterioration characteristic values ​​of the prognostic individuals, the systematic assessment values ​​of their disease status were adjusted to obtain the adjusted disease status values. Based on these adjusted disease status values, the prognostic individuals were classified into risk groups.

[0132] Alternatively, the transmission medium may be a wired link, such as, but not limited to, coaxial cable, fiber optic cable and digital subscriber line, or a wireless link, such as, but not limited to, wireless Fidelity (WIFI), Bluetooth and mobile device networks.

[0133] It should be noted that the device provided in the above embodiments is only an example of the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above.

[0134] This invention provides a computer device. Exemplarily, the computer device includes: a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the computer device can execute any of the aforementioned artificial intelligence-based long-term follow-up and prognostic assessment systems for gynecological endocrine diseases.

[0135] Furthermore, embodiments of the present invention also protect an apparatus that may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to execute the artificial intelligence-based long-term follow-up and prognostic assessment system for gynecological endocrine diseases provided in embodiments of the present invention.

[0136] In this embodiment of the invention, the device can be divided into functional modules according to the above method example. For example, each module can correspond to a separate function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and is only a logical functional division. In actual implementation, there may be other division methods.

[0137] When each module is divided according to its function, the device may also include a signal uploading module, a determination module, and an adjustment module. It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional descriptions of the corresponding functional modules, and will not be repeated here.

[0138] It should be understood that the device provided in this embodiment of the invention is used to execute the above-mentioned artificial intelligence-based long-term follow-up and prognostic assessment system for gynecological endocrine diseases, and thus can achieve the same effect as the above-mentioned implementation method.

[0139] When using integrated units, the device may include a processing module and a storage module. When applied to a device, the processing module can be used to control and manage the device's operations. The storage module can be used to support the device in executing program code, etc. The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits as described in this disclosure. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of Digital Signal Processing (DSP) and a microprocessor, etc., and the storage module may be a memory.

[0140] In addition, the device provided in the embodiments of the present invention may specifically be a chip, component or module. The chip may include a connected processor and a memory. The memory is used to store instructions. When the processor calls and executes the instructions, the chip can execute the artificial intelligence-based long-term follow-up and prognostic assessment system for gynecological endocrine diseases provided in the above embodiments.

[0141] This invention also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer, the computer executes the aforementioned method steps to implement the artificial intelligence-based long-term follow-up and prognostic assessment system for gynecological endocrine diseases provided in the above embodiments.

[0142] This invention also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned steps to realize the artificial intelligence-based long-term follow-up and prognostic assessment system for gynecological endocrine diseases provided in the above embodiments.

[0143] In this invention, the apparatus, computer-readable storage medium, computer program product, or chip provided in the embodiments are all used to execute the corresponding methods described above. Therefore, the beneficial effects they achieve can be referred to the beneficial effects in the corresponding methods described above, and will not be repeated here. Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In the embodiments provided by this invention, it should be understood that the disclosed apparatus and method can be implemented in other ways.

[0144] The device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical functional division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, 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 devices or units may be electrical, mechanical, or other forms.

[0145] It should also be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0146] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0147] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0148] The above content is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the protection scope of the present invention.

Claims

1. A long-term follow-up and prognostic assessment system for gynecological endocrine diseases based on artificial intelligence, characterized in that, The system includes the following modules: The data acquisition module is used to acquire diagnostic data and vital sign data of individuals with poor prognosis. The time period filtering module is used to determine the stable disease period during follow-up based on the similarity between diagnostic data from two adjacent follow-up diagnoses; and to determine the period of disease deterioration for prognostic individuals based on medication use during the stable disease period. The diagnostic data analysis module is used to determine the characteristic values ​​of disease deterioration by combining the medication use of patients with poor prognosis, the number of follow-up diagnoses during the period of disease deterioration, and the time interval between follow-up diagnoses. The vital signs data analysis module is used to determine the prognostic confidence factors of individuals based on the fluctuations in vital signs data during different periods of disease deterioration. The assessment module is used to adjust the systematic assessment value of the prognostic personnel's condition by combining the number of follow-up diagnoses, the condition confidence factor, and the condition deterioration characteristic value, so as to obtain the adjusted condition assessment value of the prognostic personnel; based on the adjusted condition assessment value, the prognostic personnel are classified into risks.

2. The long-term follow-up and prognostic assessment system for gynecological endocrine diseases based on artificial intelligence according to claim 1, characterized in that, The step of determining the stable disease time series based on the similarity between diagnostic data from two adjacent follow-up diagnoses includes: The diagnostic data includes: keywords from the diagnostic results report; The keywords are transformed into vectors in a high-dimensional space to obtain the word vector for each keyword; For any two adjacent follow-up diagnoses, the similarity of the word vectors corresponding to the keywords in the two diagnostic reports is calculated. The average similarity between all word vectors in the two diagnostic reports is taken as the overall similarity between the two follow-up diagnoses. The two word vectors corresponding to the similarity are from different diagnostic reports. When the overall similarity between two follow-up diagnoses is within a preset stable range, the time period between the two follow-up diagnoses is determined as the stable time sequence of the follow-up condition; among them, the stable time sequences of the follow-up condition that are consecutive in time are merged.

3. The long-term follow-up and prognostic assessment system for gynecological endocrine diseases based on artificial intelligence according to claim 1, characterized in that, The determination of periods of disease deterioration in individuals with good prognosis based on medication use during stable follow-up periods includes: Based on medication use during the stable period of follow-up, the characteristic values ​​of the disease during the stable period of follow-up were determined; When the disease characteristic value is within the preset deterioration range, the follow-up period of stable disease corresponding to the disease characteristic value is determined as the period of disease deterioration.

4. The long-term follow-up and prognostic assessment system for gynecological endocrine diseases based on artificial intelligence according to claim 3, characterized in that, The determination of disease characteristic values ​​for the stable disease period based on medication use during the follow-up period includes: The diagnostic data includes: keywords in the diagnostic results report; the keywords include drug keywords; The average number of drug keyword types in the diagnostic results report of all follow-up diagnoses within the stable follow-up time period is used as the total number of drugs. The number of drug keyword types in the diagnostic results report obtained from the last follow-up diagnosis within the stable follow-up time series is used as the end drug quantity. The number of drug keyword types in the diagnostic results report obtained from the first follow-up diagnosis within the stable follow-up time period is used as the initial drug quantity. By negatively mapping the difference between the initial and final drug quantities, the drug maintenance coefficient is obtained. By combining the total number of drugs and the drug maintenance coefficient, the disease characteristic values ​​of prognostic individuals during the stable period of follow-up were determined.

5. The long-term follow-up and prognostic assessment system for gynecological endocrine diseases based on artificial intelligence according to claim 1, characterized in that, The determination of disease deterioration characteristic values, based on the patient's medication history, the number of follow-up diagnoses during periods of disease progression, and the time intervals between follow-up diagnoses, includes: Based on medication use during the stable period of follow-up, the characteristic values ​​of the disease during the stable period of follow-up were determined; The degree of disease deterioration is determined by combining the number of follow-up diagnoses during the period of disease progression with the characteristic values ​​of the disease. Based on the time interval between follow-up diagnoses and the degree of disease deterioration during the period of disease progression in prognostic individuals, disease recovery control factors for prognostic individuals were determined. By combining the number of follow-up diagnoses and the disease recovery control factors, characteristic values ​​for disease deterioration were determined.

6. The long-term follow-up and prognostic assessment system for gynecological endocrine diseases based on artificial intelligence according to claim 5, characterized in that, The determination of the degree of disease deterioration by combining the number of follow-up diagnoses during the period of disease progression with disease characteristic values ​​includes: The product of the number of follow-up diagnoses during the period of disease deterioration and the corresponding disease characteristic value during the period of disease deterioration is normalized, and the normalized result is used as the degree of disease deterioration.

7. The long-term follow-up and prognostic assessment system for gynecological endocrine diseases based on artificial intelligence according to claim 5, characterized in that, The determination of prognostic recovery control factors based on the time intervals between follow-up diagnoses and the degree of disease deterioration during the period of disease progression includes: Any period of disease deterioration is taken as the target period of disease deterioration; the sum of the degree of disease deterioration in the target period of disease deterioration and the previous period of disease deterioration is taken as the numerator, and the time interval between the first follow-up diagnosis in the target period of disease deterioration and the first follow-up diagnosis in the previous period of disease deterioration is taken as the denominator. The ratio of the numerator and the denominator is taken as the single-segment control factor for prognostic personnel in the target period of disease deterioration. The sum of the individual control factors for all periods of disease deterioration in prognostic individuals is calculated as the overall control factor; the overall control factor is then subjected to negative correlation normalization mapping to obtain the disease recovery control factor for prognostic individuals.

8. The long-term follow-up and prognostic assessment system for gynecological endocrine diseases based on artificial intelligence according to claim 5, characterized in that, The determination of disease deterioration characteristic values ​​by combining the number of follow-up diagnoses and disease recovery control factors includes: The percentage of follow-up diagnoses during all periods of disease deterioration for prognostic individuals is calculated as the percentage of follow-up diagnoses during disease deterioration. By performing negative correlation normalization mapping on the product of the percentage of follow-up visits for disease deterioration and the disease recovery control factor, the characteristic value of disease deterioration is obtained.

9. The long-term follow-up and prognostic assessment system for gynecological endocrine diseases based on artificial intelligence according to claim 1, characterized in that, The determination of prognostic confidence factors based on fluctuations in vital signs data during different periods of disease progression in prognostic individuals includes: The vital signs data include: luteinizing hormone (LH) levels, follicle-stimulating hormone (FSH) levels, androgen levels, and physical health index; The normalized value of the ratio of luteinizing hormone (LH) to follicle-stimulating hormone (FSH) was calculated as the first sign of dysfunction in the prognostic population. The normalized value of the difference between the physical health index and a preset standard range of physical health index was calculated as the second sign of dysfunction in the prognostic population. The normalized value of the difference between the androgen level and a preset standard range of androgen levels was calculated as the third sign of dysfunction in the prognostic population. The first, second, and third sign of dysfunction values ​​were weighted and summed to obtain the total sign of dysfunction. Curve fitting was performed on the sign of dysfunction values ​​at different sampling times during the target period of disease progression to obtain the sign of dysfunction change curve. The proportion of sign of dysfunction values ​​in the decreasing phase of the sign of dysfunction change curve was obtained as the dysfunction percentage. The difference between the average value of arrhythmias at all sampling times during the target period of disease deterioration and the value of arrhythmias at the first sampling time during the target period of disease deterioration is used as the initial confidence factor. By combining the disordered percentage during the target period of disease deterioration with the initial confidence factor, the disease confidence factor for prognostic individuals during the target period of disease deterioration was determined.

10. The long-term follow-up and prognostic assessment system for gynecological endocrine diseases based on artificial intelligence according to claim 1, characterized in that, The systematic assessment value of the prognostic individuals' condition is adjusted by combining the number of follow-up diagnoses, disease confidence factors, and disease deterioration characteristic values, resulting in an adjusted assessment value for the prognostic individuals' condition, including: Any period of disease deterioration is taken as the target period of disease deterioration; the proportion of the number of follow-up diagnoses during the target period of disease deterioration of prognostic personnel to the total number of follow-up diagnoses during all periods of disease deterioration is calculated as a correction factor for the target period of disease deterioration. Calculate the product of the correction factor, the confidence factor, and the characteristic value of disease deterioration for the target disease deterioration period, and use it as the single-segment disease adjustment coefficient for the target disease deterioration period; standardize the sum of the single-segment disease adjustment coefficients for all disease deterioration periods to obtain the disease adjustment coefficient for prognostic individuals. By combining the disease adjustment coefficient, the disease system assessment value of the prognostic personnel is corrected to obtain the disease adjustment assessment value.

Images