Gynecological endocrine disease long-term follow-up visit and prognosis evaluation system based on artificial intelligence

Abstract

The invention relates to the technical field of medical data processing, in particular to a gynecological endocrine disease long-term follow-up visit and prognosis evaluation system based on artificial intelligence. The system comprises a data acquisition module used for acquiring diagnosis data and sign data of a prognostic person; the time period screening module is used for determining a follow-up visit illness state stability time sequence period and an illness state worsening time period; the diagnosis data analysis module is used for determining a condition deterioration characteristic value by combining the medication condition of the prognostic personnel, the number of times of back-diagnosis in the condition deterioration period and the time interval; the physical sign data analysis module is used for determining a disease condition confidence factor according to the fluctuation of the physical sign data of the prognostic personnel in different disease worsening periods; and the evaluation module is used for adjusting an illness state system evaluation value of the prognostic personnel in combination with the return visit diagnosis times, the illness state confidence factor and the illness state deterioration characteristic value to obtain an illness state adjustment evaluation value, and carrying out risk division on the prognostic personnel. The accuracy of long-term follow-up visit and prognosis evaluation is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical data processing, in particular to a gynecological endocrine disease long-term follow-up and prognosis evaluation system based on artificial intelligence. BACKGROUND

[0002] Polycystic ovary syndrome (PCOS) is the most common endocrine metabolic disease in women of childbearing age, affecting about 10% to 15% of women. The etiology of PCOS is complex, and its main features include irregular menstruation, excessive male hormones, polycystic ovaries, and insulin resistance. Due to its diverse clinical manifestations and pathological mechanisms, there is a large individual difference in the diagnosis and treatment of PCOS. Therefore, long-term follow-up and effective prognosis evaluation of the prognosis personnel are crucial for management and prevention.

[0003] The existing gynecological endocrine disease follow-up system mostly relies on subjective judgment based on the current physical condition of the prognosis personnel and the results of clinical examination, and develops a treatment plan according to the symptoms. However, this method usually ignores the changes of the disease over time and the historical course of the prognosis personnel, resulting in a diagnosis that only reflects the physical condition of the prognosis personnel at the time of each follow-up, which may be a one-sided judgment without considering the long-term health changes of the prognosis personnel. The condition of the prognosis personnel may fluctuate during the follow-up interval, but the existing system fails to effectively combine the changes in the real-time physical data of the prognosis personnel to dynamically evaluate the recovery of the disease, which may cause the prognosis evaluation to deviate from the actual changes, resulting in inaccurate prognosis evaluation. SUMMARY

[0004] In order to solve the technical problem of inaccurate prognosis evaluation, the purpose of the present application is to provide a gynecological endocrine disease long-term follow-up and prognosis evaluation system based on artificial intelligence, and the technical solution adopted is as follows: In a first aspect, the present application provides a gynecological endocrine disease long-term follow-up and prognosis evaluation system based on artificial intelligence, which comprises the following modules: A data acquisition module for acquiring diagnosis data and physical data of the prognosis personnel; A time period screening module for determining a stable follow-up condition time period according to the similarity between the diagnosis data at the time of adjacent two return diagnoses, and determining a condition deterioration period of the prognosis personnel according to the medication during the stable follow-up condition time period; A diagnosis data analysis module for determining a condition deterioration characteristic value in combination with the medication of the prognosis personnel, the number of return diagnoses in the condition deterioration period, and the time interval of the return diagnoses; A physical data analysis module for determining a condition confidence factor of the prognosis personnel according to the fluctuation of the physical data of the prognosis personnel in different condition deterioration periods; The evaluation module is configured to adjust a disease system evaluation value of the prognosis person based on a number of times of follow-up diagnosis, a disease confidence factor, and a disease deterioration characteristic value of the prognosis person, and obtain a disease adjustment evaluation value of the prognosis person; and divide the prognosis person into a risk category based on the disease adjustment evaluation value.

[0005] Further, the follow-up disease stable time period is determined according to similarity between diagnosis data of two adjacent follow-up diagnoses. The diagnosis data includes keywords in a diagnosis result report. The keywords are converted into vectors in a high-dimensional space to obtain a keyword vector of each keyword. For any two adjacent follow-up diagnoses, similarity is calculated for keyword vectors corresponding to keywords in diagnosis result reports of the two diagnoses, and an average value of similarity between all keyword vectors in the diagnosis result reports of the two diagnoses is taken as overall similarity of the two follow-up diagnoses; wherein the two keyword vectors corresponding to the similarity are from different diagnosis result reports. When the overall similarity of the two follow-up diagnoses is within a preset stable range, a time period between the two follow-up diagnoses is determined as a follow-up disease stable time period; wherein follow-up disease stable time periods that are continuous in time are combined.

[0006] Further, the disease deterioration period of the prognosis person is determined according to medication during the follow-up disease stable time period. A disease characteristic value of the follow-up disease stable time period is determined according to medication during the follow-up disease stable time period. When the disease characteristic value is within a preset deterioration range, the follow-up disease stable time period corresponding to the disease characteristic value is determined as a disease deterioration period.

[0007] Further, the disease characteristic value of the follow-up disease stable time period is determined according to medication during the follow-up disease stable time period. The diagnosis data includes keywords in a diagnosis result report; and the keywords include drug keywords. An average value of a type number of the drug keywords in the diagnosis result report of the diagnosis data of all follow-up diagnoses during the follow-up stable time period is taken as a total number of drugs. A type number of the drug keywords in the diagnosis result report of the diagnosis data at the last follow-up diagnosis during the follow-up stable time period is taken as an end drug number. A type number of the drug keywords in the diagnosis result report of the diagnosis data at the first follow-up diagnosis during the follow-up stable time period is taken as an initial drug number. A difference value between the initial drug number and the end drug number is negatively correlated to obtain a drug maintenance coefficient. Determine the illness characteristic value of the prognosis personnel in the follow-up illness stable time period, in combination with the total number of drugs and the drug maintenance coefficient.

[0008] Further, determine the illness deterioration characteristic value in combination with the medication of the prognosis personnel, the number of return diagnosis in the illness deterioration period, and the time interval of return diagnosis. Determine the illness characteristic value of the follow-up illness stable time period according to the medication in the follow-up illness stable time period; Determine the illness deterioration degree in combination with the number of return diagnosis in the illness deterioration period and the illness characteristic value. Determine the illness recovery control factor of the prognosis personnel based on the time interval of return diagnosis in the illness deterioration period and the illness deterioration degree. Determine the illness deterioration characteristic value in combination with the number of return diagnosis and the illness recovery control factor.

[0009] Further, determine the illness deterioration degree in combination with the number of return diagnosis in the illness deterioration period and the illness characteristic value, comprising: Carry out normalization on the product value of the number of return diagnosis in the illness deterioration period and the illness characteristic value corresponding to the illness deterioration period, and take the normalized result value as the illness deterioration degree.

[0010] Further, determine the illness recovery control factor of the prognosis personnel based on the time interval of return diagnosis in the illness deterioration period and the illness deterioration degree, comprising: Take any illness deterioration period as a target illness deterioration period; take the sum value of the illness deterioration degree of the target illness deterioration period and the previous illness deterioration period as the numerator, take the time interval between the first return diagnosis in the target illness deterioration period and the first return diagnosis in the previous illness deterioration period as the denominator, and take the ratio composed of the numerator and the denominator as the single-period control factor of the prognosis personnel in the target illness deterioration period. Calculate the sum value of the single-period control factors of all illness deterioration periods of the prognosis personnel as the overall control factor; carry out negative correlation normalization mapping on the overall control factor to obtain the illness recovery control factor of the prognosis personnel.

[0011] Further, determine the illness deterioration characteristic value in combination with the number of return diagnosis and the illness recovery control factor, comprising: Calculate the proportion of the number of return diagnosis in all illness deterioration periods of the prognosis personnel in the total number of return diagnosis as the illness deterioration return proportion. Carry out negative correlation normalization mapping on the product value of the illness deterioration return proportion and the illness recovery control factor to obtain the illness deterioration characteristic value.

[0012] Further, the method further comprises the following steps: The sign data comprises the value of luteinizing hormone, the value of follicle-stimulating hormone, the value of androgen, and the body health index; The method further comprises the following steps: The method further comprises the following steps: The method further comprises the following steps:

[0013] Further, the method further comprises the following steps: The method further comprises the following steps: The method further comprises the following steps: The method further comprises the following steps:

[0014] In a second aspect, a method for long-term follow-up and prognosis evaluation of gynecological endocrine diseases based on artificial intelligence is provided, and the method comprises the following steps: Obtaining the diagnosis data and the sign data of the prognosis personnel; determine a follow-up illness stable time period according to similarity between diagnosis data at two adjacent follow-up diagnosis times; determine an illness deterioration period of the prognosis personnel according to medication in the follow-up illness stable time period; determine an illness deterioration characteristic value according to medication of the prognosis personnel, number of times of follow-up diagnosis in the illness deterioration period and time interval of the follow-up diagnosis; determine an illness confidence factor of the prognosis personnel according to fluctuation of the sign data of the prognosis personnel in different illness deterioration periods; adjust an illness system evaluation value of the prognosis personnel by combining the number of times of follow-up diagnosis of the prognosis personnel, the illness confidence factor and the illness deterioration characteristic value, and obtain an illness adjusted evaluation value of the prognosis personnel; and divide the prognosis personnel into different risk levels based on the illness adjusted evaluation value.

[0015] In a third aspect, an electronic device is provided, including a memory and a processor, the memory stores executable code, and the processor executes the executable code to implement the embodiments of each possible implementation of the first aspect.

[0016] In a fourth aspect, a computer program product is provided, which includes computer program code, when the computer program code runs on a computer, the computer executes the method in the first aspect or any one of the possible implementation manners of the first aspect.

[0017] In a fifth aspect, a computer readable storage medium is provided, which stores a computer program, when the computer program is executed in a computer, the computer executes the embodiments of each possible implementation of the first aspect.

[0018] The embodiments of the present application have at least the following beneficial effects: The present application can more comprehensively and accurately grasp the health condition of the prognosis personnel by comprehensively considering the multiple diagnosis results and real-time sign data of the prognosis personnel, avoid errors and one-sidedness caused by single diagnosis, and provide more reliable diagnosis basis; real-time acquisition of the sign data and combination with the historical diagnosis results can correct the illness system evaluation value, dynamically reflect the change trend of the illness of the prognosis personnel, timely find the illness fluctuation, and more accurately reflect the illness change of the prognosis personnel through the corrected illness deterioration characteristic value, and obtain more accurate prognosis evaluation. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, and the advantages thereof, a brief introduction will be given to the drawings that need to be used in the embodiments or prior art description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0020] Figure 1 The system block diagram of the gynecological endocrine disease long-term follow-up and prognosis evaluation system based on artificial intelligence provided by an embodiment of the present application; Figure 2 The method flowchart of the gynecological endocrine disease long-term follow-up and prognosis evaluation method based on artificial intelligence provided by an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined purpose, the specific embodiments, structure, features and effects of the gynecological endocrine disease long-term follow-up and prognosis evaluation system based on artificial intelligence according to the present application are described in detail as follows in combination with the drawings and preferred embodiments.

[0022] In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0023] In the description of the embodiments of the present application, unless otherwise specified, " / " represents the meaning of or, for example, A / B can represent A or B: "and / or" in the text only describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent: A exists alone, A and B exist together, and B exists alone, in addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0024] Hereinafter, the terms "first", "second" are only used for description purposes, and cannot be understood as implying or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more features.

[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as understood by those skilled in the art to which the present application belongs.

[0026] The embodiments of the present application are described below with reference to the accompanying drawings. Those skilled in the art can know that, with the development of technology and the emergence of new scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0027] The embodiment of the present application provides a specific implementation method of a gynecological endocrine disease long-term follow-up and prognosis evaluation system based on artificial intelligence. The method is suitable for the scene of gynecological endocrine disease long-term follow-up and prognosis evaluation. Polycystic ovary syndrome (PCOS) is the most common endocrine metabolic disease in women of childbearing age, affecting about 10% to 15% of women. The etiology of PCOS is complex, and due to its diversified clinical manifestations and pathological mechanisms, there is a large individual difference in the diagnosis and treatment of PCOS: although PCOS is a long-term disease, the condition of the prognosis personnel will fluctuate to a certain extent during the follow-up process, but the existing system fails to effectively combine the change of the real-time physical sign data of the prognosis personnel to dynamically evaluate the recovery of the disease, and this deficiency may lead to the evaluation of the condition of the prognosis personnel deviating from the actual change, so that the prognosis evaluation is inaccurate.

[0028] The specific scheme of the gynecological endocrine disease long-term follow-up and prognosis evaluation system based on artificial intelligence provided by the present application is described below in detail with reference to the accompanying drawings.

[0029] Please refer to Figure 1 which shows the system block diagram of the gynecological endocrine disease long-term follow-up and prognosis evaluation system based on artificial intelligence provided by an embodiment of the present application. The system includes the following modules: The data acquisition module 10 is used to acquire the diagnosis data and physical sign data of the prognosis personnel.

[0030] The diagnosis result report of the prognosis personnel after each return visit is obtained through the hospital database, and the diagnosis result report can also be referred to as diagnosis data in the subsequent steps; the diagnosis result report includes text data, which includes diagnosis information and drug information.

[0031] The text data of the diagnosis result report of the prognosis personnel is extracted by using the TF-IDF method, and is input into the trained neural network for recognition to obtain all drug keywords and diagnosis keywords in the diagnosis result report of the diagnosis of any return visit of the prognosis personnel. The drug keywords and diagnosis keywords are collectively referred to as keywords.

[0032] In the time interval between two adjacent return diagnoses, the prognostic personnel collects luteinizing hormone (LH), follicle-stimulating hormone (FSH), and androgen by wearing a portable urine reagent detection device, and records the body weight and height of the prognostic personnel to obtain the corresponding body mass index (BMI), and takes the values of luteinizing hormone (LH), follicle-stimulating hormone (FSH), androgen, and body mass index (BMI) as the physical sign data. Every 2 days is a sampling time, and the physical sign data of the prognostic personnel is collected by the portable urine reagent detection device each time. It should be noted that the method for obtaining the body mass index is: weight / height squared, wherein the unit of weight is kilogram and the unit of height is meter. The method for obtaining the body mass index is prior art and will not be described here.

[0033] The period screening module 20 is configured to determine a follow-up stable condition time period according to the similarity between the diagnosis data at two adjacent return diagnoses, and determine a prognosis personnel's condition deterioration period according to the medication in the follow-up stable condition time period.

[0034] The similarity between the diagnosis data of the return diagnoses can represent the similarity of the types of drugs used by the prognostic personnel in the time interval between different return diagnoses and the condition stability, and the higher the similarity between the diagnosis data of the two return diagnoses, the more stable the condition is. Therefore, the follow-up time sequence of the prognostic personnel can be segmented.

[0035] For any keyword in the diagnosis data of any return diagnosis of the prognostic personnel, the keyword is converted into a vector in a high-dimensional space by training a word vector model (such as Word2Vec, GloVe, etc.) to obtain a word vector of each keyword. It should be noted that converting the keyword into a vector in a high-dimensional space is prior art and will not be described here.

[0036] For any two adjacent return diagnoses, the similarity between the word vectors corresponding to the keywords in the two diagnosis result reports is calculated, and the average of the similarities between all word vectors in the two diagnosis result reports is taken as the overall similarity between the two return diagnoses. The two word vectors corresponding to the similarity are from different diagnosis result reports, and more specifically: Taking any two return diagnoses as an example, taking the ith return diagnosis and the jth return diagnosis as an example, for the diagnosis data of the ith return diagnosis and the jth return diagnosis, the keywords in the diagnosis data of the ith return diagnosis and the jth return diagnosis are combined in any two, to obtain a plurality of keyword combinations between the diagnosis data of the ith return diagnosis and the jth return diagnosis, wherein each keyword combination contains two keywords, and the two keywords come from the diagnosis data of different return 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 of the similarities of all keyword combinations between the diagnosis data of the ith return diagnosis and the jth return diagnosis is taken as the overall similarity between the diagnosis data of the ith return diagnosis and the jth return diagnosis.

[0037] When the overall similarity corresponding to the two return diagnoses is in the preset stable range, it is determined that the time period between the two return diagnoses is a follow-up stable time period; wherein the follow-up stable time periods that are continuous in time are combined. In the embodiment of the present application, the preset stable range is [0.8, 1].

[0038] That is, during the follow-up of the prognosis personnel, if the overall similarity between the diagnosis data of the first return diagnosis and the second return diagnosis is greater than or equal to 0.8, the time period formed by the first return diagnosis and the second return diagnosis is recorded as the first follow-up stable time period of the prognosis personnel; if the similarity between the diagnosis data of the second return diagnosis and the third return diagnosis is also greater than or equal to 0.8, the third return diagnosis is added to the first follow-up stable time period, and so on, until the similarity between the next adjacent return diagnosis result reports is less than 0.8, the combination of the follow-up stable time period is ended, and then all the follow-up stable time periods of the prognosis personnel are obtained.

[0039] The number of drug types can reflect whether the condition of the prognosis personnel is effectively controlled. For example, common PCOS treatment drugs include oral contraceptives, insulin sensitizers, anti-androgen drugs, etc.; if the types of these drugs are gradually reduced, it may indicate that the condition is effectively managed; if the drug types are many, it may mean that the condition is more complex or the symptoms have not been effectively controlled. Therefore, according to the medication of the prognosis personnel in each follow-up stable time period, the condition characteristic value of each follow-up stable time period is obtained.

[0040] According to the medication of the prognostic person in each follow-up stable disease time period, the disease characteristic value of the prognostic person in each follow-up stable disease time period is obtained, specifically: the mean value of the type quantity of the drug keywords in the diagnosis result report of the diagnosis data of all return diagnosis in the follow-up stable time period is obtained as the total quantity of drugs; the type quantity of the drug keywords in the diagnosis result report of the diagnosis data at the last return diagnosis in the follow-up stable time period is obtained as the terminal drug quantity; the type quantity of the drug keywords in the diagnosis result report of the diagnosis data at the first return diagnosis in the follow-up stable time period is obtained as the initial drug quantity; the difference value of the initial drug quantity and the terminal drug quantity is negatively correlated to obtain a drug maintenance coefficient; and the disease characteristic value of the prognostic person in the follow-up stable disease time period is determined in combination with the total quantity of drugs and the drug maintenance coefficient.

[0041] In some embodiments, taking the i th follow-up stable disease time period as an example, the disease characteristic value of the i th follow-up stable disease time period is calculated according to the following formula: ; wherein, is the mean value of the type quantity of the drug keywords in the diagnosis result report of the diagnosis data of all return diagnosis in the i th follow-up stable disease time period, that is, the total quantity of drugs in the i th follow-up stable disease time period; exp is an exponential function with a natural constant as the base; is the type quantity of the drug keywords in the diagnosis result report of the diagnosis data at the first return diagnosis in the i th follow-up stable disease time period; is the type quantity of the drug keywords in the diagnosis result report of the diagnosis data at the last return diagnosis in the i th follow-up stable disease time period; and norm is a normalization function, preferably, the normalization function can be a maximum and minimum value normalization function.

[0042] Wherein, the greater the total quantity of drugs in the follow-up stable disease time period, the more complex the disease of the prognostic person in the corresponding follow-up stable disease time period, and the disease symptoms have not been effectively controlled, and the disease characteristic value is greater.

[0043] Wherein, When the value of is positive, the greater the value, the more the disease of the prognostic person in the i th follow-up stable disease time period is stable, the disease is effectively controlled, and the doctor reduces the use of drugs, and the corresponding disease characteristic value is smaller; on the contrary, is negative, the smaller the value, the more the disease of the prognostic person in the i th follow-up stable disease time period is deteriorated, and the doctor increases the use of drugs, and the corresponding disease characteristic value is greater.

[0044] ​When the illness characteristic value is in a preset deterioration range, it is determined that the follow-up illness stable time period corresponding to the illness characteristic value is an illness deterioration period. In the embodiment of the present application, the preset deterioration range is [0.7, 1], and in other embodiments, the range can be adjusted by the implementer according to the actual situation. That is, when the illness deterioration characteristic value is greater than or equal to 0.7, it is determined that the corresponding follow-up illness stable time period is an illness deterioration period.

[0045] Preferably, two threshold values 0.3 and 0.7 can be preset. If the illness characteristic value of the prognosis personnel in the i th follow-up illness stable time period is less than or equal to 0.3, it indicates that the illness of the prognosis personnel is under stable control and is recovering well, and the corresponding follow-up illness stable time period is taken as an illness recovery period. If the illness characteristic value of the prognosis personnel in the i th follow-up illness stable time period is greater than 0.3 and less than 0.7, it indicates that the illness of the prognosis personnel is in a stable state and neither deteriorates nor recovers well, and the corresponding follow-up illness stable time period is taken as an illness stable period. If the illness characteristic value of the prognosis personnel in the i th follow-up illness stable time period is greater than or equal to 0.7, it indicates that the illness of the prognosis personnel is in a deterioration state, and the corresponding follow-up illness stable time period is taken as an illness deterioration period.

[0046] The diagnosis data analysis module 30 is used to determine the illness deterioration characteristic value in combination with the medication of the prognosis personnel, the number of times of return diagnosis in the illness deterioration period and the time interval of return diagnosis.

[0047] For any illness deterioration period of the prognosis personnel, the longer the time duration and the greater the illness characteristic value, the more serious the illness deterioration degree of the prognosis personnel, which will lead to the aggravation of the illness and more obvious symptoms, indicating that the treatment effect is poor.

[0048] Therefore, the illness deterioration degree can be determined in combination with the number of times of return diagnosis in the illness deterioration period and the illness characteristic value corresponding to the illness deterioration period. Specifically, the product value of the number of times of return diagnosis in the illness deterioration period and the illness characteristic value corresponding to the illness deterioration period is normalized, and the normalized result value is taken as the illness deterioration degree.

[0049] If the illness deterioration period appears in multiple short time intervals on the follow-up time sequence, and the illness deterioration degree is greater each time the illness deterioration period appears, it indicates that the illness recovery control effect is poorer. Therefore, the method for obtaining the illness deterioration characteristic value of the prognosis personnel is as follows: based on the time interval of return diagnosis and the illness deterioration degree in the illness deterioration period, the illness recovery control factor of the prognosis personnel is determined; in combination with the number of times of return diagnosis and the illness recovery control factor, the illness deterioration characteristic value is determined, specifically: Firstly, the proportion of the number of return visit diagnoses in all disease deterioration periods in the total number of return visit diagnoses of the prognosis personnel is calculated as the disease deterioration return visit proportion; that is, the cumulative sum of the number of all return visit diagnoses in all disease deterioration periods of the prognosis personnel is denoted as a first sum value; and the ratio between the first sum value and the number of all return visit diagnoses of the prognosis personnel is taken as the disease deterioration return visit proportion of the prognosis personnel.

[0050] Secondly, an arbitrary disease deterioration period is taken as a target disease deterioration period; the sum value of the disease deterioration degree of the target disease deterioration period and the previous disease deterioration period is taken as the numerator, and the time interval between the first return visit diagnosis in the target disease deterioration period and the first return visit diagnosis in the previous disease deterioration period is taken as the denominator, and the ratio composed of the numerator and the denominator is taken as the single-period control factor of the prognosis personnel in the target disease deterioration period; the sum value of the single-period control factors of all disease deterioration periods of the prognosis personnel is taken as the overall control factor; and the overall control factor is subjected to negative correlation normalization mapping to obtain the disease recovery control factor of the prognosis personnel.

[0051] In some embodiments, taking the jth disease deterioration period as the target disease deterioration period, the calculation formula of the disease recovery control factor K is: ; wherein, is the disease deterioration degree of the target disease deterioration period; is the disease deterioration degree of the previous disease deterioration period of the target disease deterioration period; is the time interval between the first return visit diagnosis in the target disease deterioration period and the first return visit diagnosis in the previous disease deterioration period; is the single-period control factor of the prognosis personnel in the target disease deterioration period; and J is the number of disease deterioration periods. It should be noted that for the first disease deterioration period of the prognosis personnel, the disease recovery control factor is no longer calculated due to too much single data.

[0052] After obtaining the disease deterioration return visit proportion and the disease recovery control factor, the product value of the disease deterioration return visit proportion and the disease recovery control factor is subjected to negative correlation normalization mapping to obtain the disease deterioration characteristic value.

[0053] The physical sign data analysis module 40 is configured to determine the disease confidence factor of the prognosis personnel according to the fluctuation of the physical sign data of the prognosis personnel in different disease deterioration periods.

[0054] Since the prognosis personnel may face different doctors for diagnosis each time they go to the hospital for return visit, there may be inconsistency, and the time interval between return visits may also make the change of the disease unable to be captured in time, resulting in that the disease deterioration degree of the prognosis personnel in the disease deterioration period is not accurate.

[0055] But the sign data of the prognosis personnel is collected in real time, it can provide continuous disease change information, timely reflect the health status of the prognosis personnel, avoid the information loss caused by the diagnosis gap in single return visit; therefore can further combine the real-time sign data analysis, accurately get the prognosis evaluation of the prognosis personnel.

[0056] The ratio of the value of luteinizing hormone (LH) and the value of follicle-stimulating hormone (FSH) is commonly used as an important indicator of the degree of polycystic ovary syndrome (PCOS), the main reason is that the ratio reflects the imbalance of hormones in the female body, especially the imbalance of luteinizing hormone (LH) and follicle-stimulating hormone (FSH); in a normal menstrual cycle, the secretion of FSH and LH is regular; FSH is responsible for promoting the maturation of follicles, while LH plays a decisive role in the ovulation process. Under normal circumstances, the ratio of FSH and LH is about 1:1; however, in the prognosis personnel of PCOS, due to the imbalance of hormones in the body, the secretion of LH is usually significantly increased, while the secretion of FSH is lower, resulting in the increase of the ratio of LH / FSH. Therefore, in the embodiment of the present application, the normalized value of the ratio of the value of luteinizing hormone and the value of follicle-stimulating hormone is calculated as the first sign imbalance value of the prognosis personnel; the normalized value of the difference value of the body health index and the preset standard body health index range is calculated as the second sign imbalance value of the prognosis personnel; the normalized value of the difference value of the value of androgen and the preset standard androgen value range is calculated as the third sign imbalance value of the prognosis personnel; the first sign imbalance value, the second sign imbalance value and the third sign imbalance value are weighted and summed to obtain the sign imbalance value.

[0057] The specific method for obtaining the difference value of the body health index and the preset standard body health index range is as follows: when the body health index is in the preset standard body health index range, the difference value of the body health index and the preset standard body health index range is 0; when the body health index exceeds the preset standard body health index range, the absolute value of the difference value between the body health index and the upper limit of the preset standard body health index range is calculated as the difference value of the body health index and the preset standard body health index range; when the body health index is lower than the preset standard body health index range, the absolute value of the difference value between the body health index and the lower limit of the preset standard body health index range is calculated as the difference value of the body health index and the preset standard body health index range.

[0058] Similarly, the specific method for obtaining the difference value of the androgen value and the preset standard androgen value range is as follows: when the androgen value is in the preset standard androgen value range, the difference value of 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 value of 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 value of the androgen value and the preset standard androgen value range.

[0059] In the embodiment of the present application, the weight values respectively given to the three data values are 1 / 3 when the first, second and third sign imbalance values are weighted and summed, and in other embodiments, the implementer can give different weight values to the three data values according to the actual emphasis on different sign data. In the embodiment of the present application, the preset standard body health range is [18.5, 24], the preset standard androgen range is 50-60 ng / dL, and in the embodiment of the present application, the androgen referred to is total testosterone, and in other embodiments, the implementer can set other preset standard body health ranges and preset standard androgen ranges according to the regulations of different hospitals. In the embodiment of the present application, the unit of the androgen value is nanogram per deciliter (ng / dL).

[0060] A sequence of sign imbalance values of the prognosis person at all sampling time points in each disease exacerbation period is obtained, denoted as the sign imbalance value sequence of the prognosis person in each disease exacerbation period; wherein each sampling time point has a corresponding sign imbalance value.

[0061] If the sign data of the prognosis person continuously increases in the disease exacerbation period, it indicates that the PCOS condition of the prognosis person has been in a state of exacerbation in the disease exacerbation period, and thus the confidence of the disease exacerbation degree of the disease exacerbation period is larger; and if the sign data of the prognosis person appears to decrease or stabilize in the disease exacerbation period, it indicates that the PCOS condition of the prognosis person is in a good recovery state in the disease exacerbation period, but due to the influence of other complications, the disease exacerbation degree is increased, and thus the confidence of the disease exacerbation degree of the disease exacerbation period is lower.

[0062] According to the fluctuation of the sign data of the prognosis person in different disease exacerbation periods, the disease confidence factor of the prognosis person is determined, specifically: Firstly, the values of the sign of illness at different sampling time points in the target illness deterioration period are fitted to obtain a sign of illness change curve, more specifically: the values of the sign of illness of the prognosis personnel at all sampling time points in the target illness deterioration period are fitted by using the least square method to obtain the sign of illness change curve of the prognosis personnel in the target illness deterioration period.

[0063] Then, the proportion of the sign of illness values in the falling stage in the sign of illness change curve is obtained as the disorder proportion; the difference between the average value of the sign of illness values at all sampling time points in the target illness deterioration period and the sign of illness value at the first sampling time point in the target illness deterioration period is calculated as the initial confidence factor; the illness confidence factor of the prognosis personnel in the target illness deterioration period is determined in combination with the disorder proportion of the target illness deterioration period and the initial confidence factor. It should be noted that the sign of illness values in the falling stage are the sign of illness values corresponding to the slope values less than 0.

[0064] In combination with the disorder proportion of the target illness deterioration period and the initial confidence factor, the illness confidence factor of the prognosis personnel in the target illness deterioration period is determined, specifically: the normalized value of the product value of the disorder proportion of the target illness deterioration period and the initial confidence factor is taken as the illness confidence factor of the prognosis personnel in the target illness deterioration period.

[0065] In some embodiments, taking the jth illness deterioration period as the target illness deterioration period as an example, the calculation formula of the illness confidence factor of the prognosis personnel in the target illness deterioration period is: ; wherein represents the number of sign of illness values with a slope less than 0 on the sign of illness change curve of the prognosis personnel in the jth illness deterioration period; represents the number of all sign of illness values on the sign of illness change curve of the prognosis personnel in the jth illness deterioration period; represents the disorder proportion of the prognosis personnel in the jth illness deterioration period; represents the average value of the sign of illness values at all time points of the prognosis personnel in the jth illness deterioration period; represents the sign of illness value of the prognosis personnel at the first sampling time point in the jth illness deterioration period; represents the initial confidence factor of the prognosis personnel in the jth illness deterioration period.

[0066] ​​​​​​​Among them, the greater the proportion of imbalance during the period of disease exacerbation, the longer the PCOS disease exacerbation time of the prognostic person, and the greater the disease confidence factor; the greater the initial confidence factor during the period of disease exacerbation, the greater the degree of increase in the initial physical sign imbalance value of the prognostic person, and the greater the disease confidence factor during the period of disease exacerbation.

[0067] The evaluation module 50 is used to adjust the system evaluation value of the prognostic person's condition based on the number of follow-up diagnoses, the condition confidence factor and the characteristic value of the condition deterioration of the prognostic person to obtain the condition-adjusted evaluation value of the prognostic person; based on the condition-adjusted evaluation value, the prognostic person is risk-classified.

[0068] If the duration of the period of worsening condition is longer, and the number of times the prognostic personnel return for diagnosis during this period of worsening condition is more, then the more information is missing due to the diagnostic gap, and the greater the weight that needs to be corrected for the degree of worsening condition during this period of worsening condition; therefore, combined with the number of follow-up diagnoses of the prognostic personnel, the condition confidence factor and the characteristic value of the condition worsening, the system evaluation value of the prognostic personnel's condition is adjusted to obtain the adjusted evaluation value of the prognostic personnel's condition.

[0069] First, take any period of disease exacerbation as the target period of disease exacerbation; calculate the ratio of the number of follow-up diagnoses during the target period of disease exacerbation to the total number of follow-up diagnoses during all periods of disease exacerbation as the correction factor for the target period of disease exacerbation. The period of worsening of the disease is taken as the target period, and the The ratio between the number of all follow-up diagnoses of prognostic personnel in the first period of disease exacerbation and the total number of all follow-up diagnoses of prognostic personnel in all periods of disease exacerbation is taken as the first Correction factor for each exacerbation period.

[0070] Furthermore, the product of the correction factor, the disease confidence factor, and the disease exacerbation characteristic value for the target disease exacerbation period is calculated as the single-segment disease adjustment coefficient for the target disease exacerbation period. The sum of the single-segment disease adjustment coefficients for all disease exacerbation periods is normalized to obtain the disease adjustment coefficient for the prognostic person. In this embodiment of the present invention, normalization is also referred to as normalization, which can be achieved using the maximum and minimum value normalization method.

[0071] The latest diagnosis report of the prognostic person in the hospital is analyzed using an existing clinical scoring system commonly used in the hospital to obtain a system evaluation value of the prognostic person's condition. In other embodiments, the latest diagnosis report of the prognostic person can also be manually scored by a doctor, and the resulting score is used as the system evaluation value of the condition.

[0072] Then, the subjective disease condition system evaluation value is corrected by combining the disease condition adjustment coefficient obtained by analyzing the sign data and the diagnosis data of the prognosis personnel in the embodiment of the application, to obtain a disease condition adjustment evaluation value.

[0073] Specifically, a product value of the disease condition adjustment evaluation value and the disease condition system evaluation value is calculated as an adjustment evaluation value; and a normalized value of a sum value of the adjustment evaluation value and the disease condition adjustment evaluation value is taken as the disease condition adjustment evaluation value.

[0074] In some embodiments, the disease condition adjustment evaluation value of the prognosis personnel is calculated by the following formula: ; wherein, is a disease condition adjustment coefficient; is the disease condition system evaluation value of the prognosis personnel.

[0075] Since the current disease condition adjustment evaluation value is further optimized by the diagnosis result of the doctor through the change of the real-time sign data of the prognosis personnel, the disease condition adjustment evaluation value of the prognosis personnel is more accurate; the greater the current disease condition adjustment evaluation value of the prognosis personnel, the more serious the deterioration of the prognosis personnel during the disease follow-up period, and the prognosis personnel needs more active treatment and close follow-up.

[0076] Finally, the prognosis personnel is classified into different risks based on the disease condition adjustment evaluation value. Two risk parameter thresholds are respectively preset, the first risk parameter threshold T1 is 0.75, and the second risk parameter threshold T2 is 0.25; if the disease condition adjustment evaluation value of the prognosis personnel is greater than or equal to the first risk parameter threshold, the prognosis personnel is recorded as a high-risk prognosis personnel; if the current disease condition adjustment evaluation value of the prognosis personnel is less than or equal to the second risk parameter threshold, the prognosis personnel is recorded as a low-risk prognosis personnel; if the current disease condition adjustment evaluation value of the prognosis personnel is less than the first risk parameter threshold and greater than the second risk parameter threshold, the prognosis personnel is recorded as a medium-risk prognosis personnel.

[0077] As a preferred embodiment of the application, the follow-up time of the prognosis personnel is adjusted based on the prognosis evaluation of the prognosis personnel. Among all the gynecological prognosis personnel with PCOS in the hospital, the follow-up time interval of the high-risk prognosis personnel is shortened, and these prognosis personnel are preferentially notified to go to the hospital for return visit diagnosis; the follow-up time interval of the medium-risk prognosis personnel is shortened, and these prognosis personnel are notified to go to the hospital for return visit diagnosis after the high-risk prognosis personnel have returned; the low-risk prognosis personnel are managed and diagnosed through regular treatment and regular check return visit.

[0078] For the prognosis of the evaluation results show high risk of prognosis personnel, need more frequent and closer follow-up. This helps to find changes in the disease or complications in time, ensures that intervention measures are taken before the disease worsens, thereby improving the success rate of treatment; for the prognosis of the evaluation results show low risk of prognosis personnel, the follow-up interval can be appropriately extended, unnecessary frequent examination and treatment can be reduced, and resources can be more reasonably allocated.

[0079] Please refer to Figure 2 , Figure 2 A method flowchart for providing a gynecological endocrine disease long-term follow-up and prognosis evaluation method based on artificial intelligence is provided for the embodiments of the application, and the method comprises the following steps: Obtain the diagnosis data and the physical data of the prognosis personnel; According to the similarity between the diagnosis data at the time of diagnosis of adjacent two return visits, the follow-up stable disease time period is determined; according to the medication in the follow-up stable disease time period, the disease deterioration period of the prognosis personnel is determined; In combination with the medication of the prognosis personnel, the number of return diagnosis in the disease deterioration period and the time interval of return diagnosis, the disease deterioration characteristic value is determined; According to the fluctuation of the physical data of the prognosis personnel in different disease deterioration periods, the disease confidence factor of the prognosis personnel is determined; In combination with the number of return diagnosis of the prognosis personnel, the disease confidence factor and the disease deterioration characteristic value, the disease system evaluation value of the prognosis personnel is adjusted to obtain the disease adjusted evaluation value of the prognosis personnel; based on the disease adjusted evaluation value, the risk of the prognosis personnel is divided.

[0080] Optionally, the transmission medium can be a wired link, such as but not limited to a coaxial cable, an optical fiber, and a digital subscriber line, or a wireless link, such as but not limited to Wireless Fidelity (WIFI), Bluetooth, and a mobile device network.

[0081] It should be noted that: the device provided by the above embodiments is only exemplified by the division of the above functional modules, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above.

[0082] The computer device provided by the embodiments of the application. Illustratively, the computer device comprises 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 above-mentioned artificial intelligence-based gynecological endocrine disease long-term follow-up and prognosis evaluation systems.

[0083] In addition, the embodiment of the present application also protects a device, which can include a memory and a processor, wherein the memory stores executable program code, and the processor is configured to invoke and execute the executable program code to execute the long-term follow-up and prognosis evaluation system for gynecological endocrine diseases based on artificial intelligence provided by the embodiment of the present application.

[0084] The embodiment of the present application can divide the device into functional modules according to the above-mentioned method examples, for example, each functional module can be corresponding, or two or more functions can be integrated in one processing module, and the integrated module can be realized in the form of hardware. It should be noted that the division of modules in the present embodiment is illustrative, and is only a logical functional division. In actual implementation, another division mode can be used.

[0085] In the case of dividing each module corresponding to each function, the device can also include a signal uploading module, a determination module, and an adjustment module, etc. It should be noted that all related contents of each step involved in the above-mentioned method embodiment can be cited to the function description of the corresponding functional module, which will not be repeated here.

[0086] It should be understood that the device provided by the embodiment of the present application is used to execute the above-mentioned long-term follow-up and prognosis evaluation system for gynecological endocrine diseases based on artificial intelligence, and thus the same effect as the above-mentioned implementation method can be achieved.

[0087] In the case of using integrated units, the device can include a processing module and a storage module. When the device is applied to a device, the processing module can be used to control and manage the actions of the device. The storage module can be used to support the device to execute mutual program codes, etc. The processing module can be a processor or a controller, which can realize or execute various exemplary logical blocks, modules and circuits described in combination with the disclosure of the present application. The processor can also be a combination of computing functions, such as one or more microprocessor combinations, combinations of digital signal processing (Digital Signal Processing, DSP) and microprocessors, etc. The storage module can be a memory.

[0088] In addition, the device provided by the embodiment of the present application can be a chip, an assembly or a module, the chip can include a connected processor and a memory; wherein the memory is used to store instructions, when the processor invokes and executes the instructions, the chip can execute the long-term follow-up and prognosis evaluation system for gynecological endocrine diseases based on artificial intelligence provided by the above-mentioned embodiment.

[0089] The embodiment of the present application also provides a computer readable storage medium, which stores computer program codes, and when the computer program codes are run on a computer, the computer is caused to execute the related method steps to realize the gynecological endocrine disease long-term follow-up and prognosis evaluation system based on artificial intelligence provided by the above embodiment.

[0090] The embodiment of the present application also provides a computer program product, which, when run on a computer, causes the computer to execute the related steps to realize the gynecological endocrine disease long-term follow-up and prognosis evaluation system based on artificial intelligence provided by the above embodiment.

[0091] Among them, the device, computer readable storage medium, computer program product or chip provided by the embodiment of the present application are used to execute the corresponding method provided above, so the beneficial effects that can be achieved are referred to the beneficial effects in the corresponding method provided above, which will not be repeated here. Through the description of the above implementation mode, those skilled in the art can understand that, for the convenience and brevity of description, only the above division of functional modules is taken as an example, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In the embodiments provided by the present application, it should be understood that the disclosed device and method can be implemented in other ways.

[0092] The device embodiment described above is only schematic, for example, the division of modules or units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed each other can be indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other form.

[0093] It should also be noted that in this document, the terms "comprising", "including", or any other variant thereof are intended to cover non-exclusive inclusion, so that processes, methods, articles or terminal devices including a series of elements not only include those elements, but also include other elements not explicitly listed, or further include elements inherent to such processes, methods, articles or terminal devices. Without more limitations, the element defined by the statement "including a" does not exclude the presence of additional identical elements in the process, method, article or terminal device including the element.

[0094] It is to be noted that the above-mentioned order of the embodiments of the present application is merely intended for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the figures do not necessarily require the particular order or sequential order shown or to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0095] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each of the embodiments focuses on the difference from other embodiments.

[0096] The above is merely a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application.

Claims

1. An artificial intelligence-based long-term follow-up and prognosis assessment system for gynecological endocrine diseases, characterized by: The system includes the following modules: A data acquisition module is used to obtain diagnostic data and vital sign data of the prognostic personnel; The time period screening module is used to determine the stable time period of the follow-up condition based on the similarity between the diagnostic data of two adjacent follow-up diagnoses; and to determine the worsening time period of the prognosis person based on the medication situation within the stable time period of the follow-up condition; The diagnostic data analysis module is used to determine the characteristic value of the disease worsening by combining the medication status of the prognostic personnel, the number of return diagnosis visits during the period of disease worsening, and the time interval between return diagnosis visits; The vital sign data analysis module is used to determine the confidence factor of the prognostic person's condition based on the fluctuation of the vital sign data of the prognostic person during different periods of condition deterioration; The evaluation module is used to adjust the system evaluation value of the prognostic person's condition based on the number of follow-up diagnoses, the condition confidence factor and the characteristic value of the condition deterioration, so as to obtain the condition-adjusted evaluation value of the prognostic person; based on the condition-adjusted evaluation value, the prognostic person is risk-classified.

2. The artificial intelligence-based long-term follow-up and prognosis evaluation system for gynecological endocrine diseases according to claim 1 is characterized in that: Determining the stable follow-up time period based on the similarity between the diagnostic data of two adjacent follow-up diagnoses includes: The diagnostic data includes: keywords in the diagnostic result report; Convert keywords into vectors in high-dimensional space to obtain word vectors for each keyword; For any two consecutive follow-up diagnoses, the similarity between the word vectors corresponding to the keywords in the two diagnosis result reports is calculated. The average of the similarities between all word vectors in the two diagnosis result reports is used as the overall similarity between the two follow-up diagnoses. The two word vectors corresponding to the similarity come from different diagnosis result reports. When the overall similarity corresponding to the two follow-up diagnoses is within a preset stable range, the period between the two follow-up diagnoses is determined to be a stable follow-up disease state time series segment; wherein, the temporally continuous stable follow-up disease state time series segments are merged.

3. The artificial intelligence-based long-term follow-up and prognosis evaluation system for gynecological endocrine diseases according to claim 1 is characterized in that: The determination of the period of worsening of the condition of the prognostic person based on the medication status during the stable period of follow-up includes: According to the medication situation during the stable follow-up period, the characteristic value of the disease condition during the stable follow-up period is determined; When the disease condition characteristic value is within the preset deterioration range, the follow-up disease condition stable time segment corresponding to the disease condition characteristic value is determined to be the disease condition deterioration period.

4. The artificial intelligence-based long-term follow-up and prognosis evaluation system for gynecological endocrine diseases according to claim 3 is characterized in that: Determining the disease condition characteristic value of the stable disease condition time sequence period according to the medication situation during the stable disease condition time sequence period includes: The diagnostic data includes: keywords in the diagnostic result report; the keywords include drug keywords; Obtain the average number of drug keyword types in the diagnostic result reports of all follow-up diagnostic data within the stable follow-up time series as the total number of drugs; Obtain the number of drug keyword types in the diagnostic result report of the last follow-up diagnosis data within the stable follow-up time period as the terminal drug number; Obtain the number of drug keyword types in the diagnostic result report of the first follow-up diagnosis data within the stable follow-up time period as the initial drug quantity; The difference between the initial drug quantity and the final drug quantity is negatively correlated to obtain the drug maintenance coefficient; Combined with the total number of drugs and the drug maintenance coefficient, the characteristic value of the condition of the prognostic personnel during the stable condition time period of follow-up is determined.

5. The artificial intelligence-based long-term follow-up and prognosis evaluation system for gynecological endocrine diseases according to claim 1 is characterized in that: The determination of the characteristic value of the disease worsening by combining the medication status of the prognostic person, the number of return diagnosis during the period of disease worsening, and the time interval between the return diagnosis, includes: According to the medication situation during the stable follow-up period, the characteristic value of the disease condition during the stable follow-up period is determined; The degree of disease worsening is determined by combining the number of return diagnoses during the period of disease worsening and the disease characteristic value; Determine the recovery control factor of the prognostic person based on the time interval between follow-up diagnoses and the degree of disease deterioration during the period of disease deterioration; The characteristic value of disease worsening is determined by combining the number of return diagnosis and the disease recovery control factor.

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

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

8. The artificial intelligence-based long-term follow-up and prognosis evaluation system for gynecological endocrine diseases according to claim 5, characterized in that: The method of determining the characteristic value of the disease worsening by combining the number of return diagnosis and the disease recovery control factor includes: Calculate the proportion of follow-up diagnoses during all periods of worsening condition of the prognostic personnel to the total number of follow-up diagnoses, and use this as the proportion of follow-up diagnoses during worsening condition. The product of the proportion of return visits due to worsening of the condition and the control factor for condition recovery was subjected to negative correlation normalization mapping to obtain the characteristic value of condition worsening.

9. The artificial intelligence-based long-term follow-up and prognosis evaluation system for gynecological endocrine diseases according to claim 1, characterized in that: The determination of the condition confidence factor of the prognostic person according to the fluctuation of the vital sign data of the prognostic person during different periods of worsening of the condition includes: The physical sign data include: the value of luteinizing hormone, the value of follicle-stimulating hormone, the value of androgen and the physical health index; Calculate the normalized value of the ratio of the values ​​of luteinizing hormone to follicle-stimulating hormone as the first physical sign imbalance value of the prognostic person; calculate the normalized value of the difference between the physical health index and the preset standard physical health index range as the second physical sign imbalance value of the prognostic person; calculate the normalized value of the difference between the androgen value and the preset standard androgen value range as the third physical sign imbalance value of the prognostic person; perform weighted summation of the first physical sign imbalance value, the second physical sign imbalance value, and the third physical sign imbalance value to obtain the physical sign imbalance value; perform curve fitting on the physical sign imbalance values ​​at different sampling times within the target disease exacerbation period to obtain a physical sign imbalance change curve; obtain the proportion of physical sign imbalance values ​​in the declining stage of the physical sign imbalance change curve as the imbalance proportion; Calculate the difference between the average of the physical sign disorder values ​​at all sampling moments in the target disease exacerbation period and the physical sign disorder value at the first sampling moment in the target disease exacerbation period as the initial confidence factor; The disorder ratio and initial confidence factor of the target disease worsening period are combined to determine the disease confidence factor of the prognostic personnel in the target disease worsening period.

10. The artificial intelligence-based long-term follow-up and prognosis evaluation system for gynecological endocrine diseases according to claim 1, characterized in that: The system assessment value of the condition of the prognostic person is adjusted based on the number of return diagnosis, the condition confidence factor, and the condition deterioration characteristic value of the prognostic person to obtain the condition adjustment assessment value of the prognostic person, including: Any period of disease exacerbation is taken as the target period of disease exacerbation; the proportion of the number of follow-up diagnoses during the target period of disease exacerbation of the prognostic personnel to the total number of follow-up diagnoses during all periods of disease exacerbation is calculated as the correction factor for the target period of disease exacerbation; Calculate the product of the correction factor, the disease confidence factor, and the disease exacerbation characteristic value of the target disease exacerbation period as the single-segment disease adjustment coefficient of the target disease exacerbation period; standardize the sum of the single-segment disease adjustment coefficients of all disease exacerbation periods to obtain the disease adjustment coefficient of the prognostic person; Combined with the disease adjustment coefficient, the disease system assessment value of the prognostic personnel is corrected to obtain the disease adjustment assessment value.

Images