Digestive tract hemorrhage risk assessment method and system based on capsule gastroscopy results

Abstract

The invention provides a digestive tract hemorrhage risk assessment method and system based on capsule gastroscopy results. The method comprises the following steps: acquiring a gastrointestinal image of a patient, processing to obtain image feature data, performing lesion quantity evaluation according to lesion feature data, obtaining a gastrointestinal tract lesion quantity index, obtaining examination process data and examination technical parameter data of capsule gastroscopy, and processing in combination with the gastrointestinal feature data to obtain a gastroscopy correction coefficient. The method comprises the following steps: acquiring and processing arteriovenous blood vessel feature data and personal data of a patient, acquiring and processing blood vessel diameter quantized value data, acquiring and processing clinical data, acquiring high-risk factors of gastrointestinal hemorrhage, and finally performing risk assessment in combination with several indexes and factors to obtain risk indexes of gastrointestinal hemorrhage; and comparing the risk value with a preset risk threshold value, and obtaining a corresponding preset treatment scheme according to a comparison result to guide treatment of the patient, so that a digestive tract hemorrhage risk assessment technology based on a capsule gastroscopy result is realized.

Description

Technical Field

[0001] The present application relates to the technical field of gastrointestinal bleeding risk assessment, and in particular, to a gastrointestinal bleeding risk assessment method and system based on capsule gastroscopy results. Background Art

[0002] Gastrointestinal bleeding is one of the common clinical complications in patients with coronary heart disease taking dual antiplatelet therapy. Early and accurate assessment of bleeding risk is crucial for the treatment and prognosis of patients.

[0003] Doctors usually rely on traditional risk factors of patients to judge the risk of gastrointestinal bleeding, such as age, previous digestive system diseases, anemia, renal insufficiency, etc. This process involves a lot of manual analysis and experience judgment, which is time-consuming and easily affected by subjective factors.

[0004] In view of the above problems, effective technical solutions are urgently needed. Summary of the invention

[0005] The purpose of the present application is to provide a method and system for assessing the risk of gastrointestinal bleeding based on the results of capsule gastroscopy. The method and system can process gastroscopic images based on capsule gastroscopy, obtain lesion characteristic data, and combine them with multiple variables such as quantified values ​​of blood vessel diameter and other risk factors for processing to achieve risk assessment. The accuracy of gastrointestinal bleeding risk prediction is improved through risk assessment, thereby realizing a technology for assessing the risk of gastrointestinal bleeding based on the results of capsule gastroscopy.

[0006] The present application also provides a method for assessing the risk of gastrointestinal bleeding based on capsule gastroscopy results, comprising the following steps:

[0007] Acquire gastrointestinal images generated by capsule gastroscopy of the patient, and process and obtain image feature data, including lesion feature data and gastrointestinal feature data;

[0008] Performing lesion quantity evaluation according to the lesion characteristic data to obtain a gastrointestinal lesion quantity index;

[0009] Acquiring the inspection process data and inspection technical parameter data of the capsule gastroscopy, and processing them in combination with the gastrointestinal characteristic data to obtain a gastroscopy correction coefficient;

[0010] Acquire the arteriovenous blood vessel characteristic data and personal information data of the patient, and obtain blood vessel diameter quantitative value data by combining the arteriovenous blood vessel characteristic data and the personal information data;

[0011] Obtaining and processing the clinical data of the patient to obtain high-risk factors for gastrointestinal bleeding;

[0012] According to the gastrointestinal tract pathology index, gastroscopy correction coefficient and blood vessel diameter quantification value data, combined with the high-risk factors for gastrointestinal bleeding, risk assessment is performed to obtain a gastrointestinal bleeding risk index;

[0013] A threshold comparison is performed between the gastrointestinal bleeding risk index and a preset risk threshold, and a corresponding preset treatment plan is obtained based on the threshold comparison result to guide treatment of the patient.

[0014] Optionally, in the method for assessing the risk of gastrointestinal bleeding based on capsule gastroscopy results described in the present application, the step of obtaining a gastrointestinal image generated by a patient based on capsule gastroscopy and processing the image feature data, including lesion feature data and gastrointestinal feature data, comprises:

[0015] Obtaining gastrointestinal images of patients based on capsule gastroscopy, and collecting image information of the gastrointestinal images, including mucosal morphology information, gastric wall condition information, fold distribution information, and secretion information;

[0016] Processing the image information through a preset gastroscopy feature recognition model to obtain image feature data of the gastroscopy;

[0017] The image feature data includes lesion feature data and gastrointestinal feature data.

[0018] Optionally, in the gastrointestinal bleeding risk assessment method based on capsule gastroscopy results described in the present application, the lesion amount assessment is performed according to the lesion characteristic data to obtain a gastrointestinal lesion amount index, including:

[0019] The lesion characteristic data include data on the maximum area of ​​erosion, data on the amount of erosion, data on the maximum thickness of white fur, data on the distribution of bleeding points, data on the amount of bleeding, and data on the maximum volume of ulcer;

[0020] The morbidity index of the gastrointestinal tract is obtained by evaluating the morbidity according to the data of the maximum erosion area, the erosion volume, the maximum thickness of the white fur, the bleeding point distribution, the bleeding volume and the maximum volume of the ulcer;

[0021] The calculation formula of the gastrointestinal morbidity index is:

[0022]

[0023] Among them, Z x is the gastrointestinal morbidity index, q a 、w s 、e d They are the maximum area of ​​erosion, the maximum thickness of white fur, and the maximum volume of ulcer, respectively. f ,t g ,y hare the erosion amount data, bleeding point distribution data, and bleeding amount data. β1, β2, β3, ζ1, ζ2, and ζ3 are the preset characteristic coefficients.

[0024] Optionally, in the gastrointestinal bleeding risk assessment method based on capsule gastroscopy results described in the present application, the obtaining of the inspection process data and the inspection technical parameter data of the capsule gastroscopy, and processing in combination with the gastrointestinal characteristic data to obtain the gastroscopy correction coefficient includes:

[0025] Acquiring the inspection process data and inspection technical parameter data of the capsule gastroscopy;

[0026] The inspection process data includes capsule running speed data and capsule passing time data;

[0027] The inspection technical parameter data includes image resolution data and field of view angle data;

[0028] The gastrointestinal characteristic data include gastric cleanliness data and gastric cavity filling data;

[0029] According to the capsule running speed data, capsule passing time data, image resolution data, field of view angle data, stomach cleanliness data and stomach cavity filling degree data, a preset gastroscopy evaluation model is used to process and obtain a gastroscopy correction coefficient;

[0030] The calculation formula of the gastroscopy correction coefficient is:

[0031]

[0032] Among them, C v is the correction factor for gastroscopy, u j 、i k They are respectively the capsule running speed data and the capsule passing time data. l 、p m They are image resolution data and field of view data, s q d w are respectively the data of gastric cleanliness and gastric cavity filling degree, ε, λ is the preset characteristic coefficient.

[0033] Optionally, in the gastrointestinal bleeding risk assessment method based on capsule gastroscopy results described in the present application, the step of obtaining the arteriovenous blood vessel characteristic data and personal information data of the patient, and obtaining blood vessel diameter quantitative value data by processing the arteriovenous blood vessel characteristic data in combination with the personal information data, includes:

[0034] Acquire the arteriovenous characteristic data and personal data of the patient through a preset medical health database;

[0035] The arteriovenous blood vessel characteristic data include blood pressure data, blood flow velocity data and blood vessel wall elasticity data;

[0036] The personal data includes age data and gender data;

[0037] By combining the arteriovenous blood vessel characteristic data with the personal information data, the quantitative value data of the blood vessel diameter is obtained;

[0038] The calculation formula of the blood vessel diameter quantification value data is:

[0039]

[0040] Among them, B n is the quantitative value data of blood vessel diameter, f e , g r 、h t They are blood pressure data, blood flow velocity data, and vascular wall elasticity data, respectively. y , k u are age data and gender data respectively, and δ1, δ2, δ3, and φ are preset characteristic coefficients.

[0041] Optionally, in the method for assessing the risk of gastrointestinal bleeding based on capsule gastroscopy results described in the present application, obtaining and processing the clinical data of the patient to obtain high-risk factors for gastrointestinal bleeding includes:

[0042] Obtain clinical data of the patient through a preset medical health database, including personal health-related data, medical history data, and related disease data;

[0043] The personal health-related data includes smoking history data and drinking history data;

[0044] The medical history data includes diabetes medical history data and hypertension medical history data;

[0045] The associated disease data include liver cirrhosis data and blood biochemical data;

[0046] Processing the clinical data to obtain high-risk factors for gastrointestinal bleeding;

[0047] The calculation formula for the high-risk factor for gastrointestinal bleeding is:

[0048]

[0049] Among them, L i It is a high risk factor for gastrointestinal bleeding. q 、n w are smoking history data and drinking history data, respectively, m e 、a rThey are diabetes medical history data and hypertension medical history data, respectively. g ,t d They are liver cirrhosis data, blood biochemical data, and y , k u are age data and gender data respectively, and ω1, ω2, and ω3 are preset characteristic coefficients.

[0050] Optionally, in the gastrointestinal bleeding risk assessment method based on capsule gastroscopy results described in the present application, the risk assessment is performed based on the gastrointestinal tract morbidity index, gastroscopy correction coefficient and blood vessel diameter quantification value data, combined with the gastrointestinal bleeding high-risk factors, to obtain the gastrointestinal bleeding risk index, including:

[0051] According to the gastrointestinal tract pathology index, gastroscopy correction coefficient and blood vessel diameter quantification value data, combined with the high-risk factors for gastrointestinal bleeding, a risk assessment process is performed through a preset gastrointestinal bleeding risk assessment model to obtain a gastrointestinal bleeding risk index;

[0052] The calculation formula of the gastrointestinal bleeding risk index is:

[0053]

[0054] Among them, F e is the gastrointestinal morbidity index, Z x , C v , B n , L i They are gastrointestinal pathology index, gastroscopy correction coefficient, blood vessel diameter quantification value data, and gastrointestinal bleeding high-risk factors. ρ1, ρ2, ρ3, and ρ4 are preset characteristic coefficients.

[0055] In a second aspect, the present application provides a gastrointestinal bleeding risk assessment system based on capsule gastroscopy results, the system comprising: a memory and a processor, the memory comprising a program of a gastrointestinal bleeding risk assessment method based on capsule gastroscopy results, the program of the gastrointestinal bleeding risk assessment method based on capsule gastroscopy results when executed by the processor implements the following steps:

[0056] Acquire gastrointestinal images generated by capsule gastroscopy of the patient, and process and obtain image feature data, including lesion feature data and gastrointestinal feature data;

[0057] Performing lesion quantity evaluation according to the lesion characteristic data to obtain a gastrointestinal lesion quantity index;

[0058] Acquiring the inspection process data and inspection technical parameter data of the capsule gastroscopy, and processing them in combination with the gastrointestinal characteristic data to obtain a gastroscopy correction coefficient;

[0059] Acquire the arteriovenous blood vessel characteristic data and personal information data of the patient, and obtain blood vessel diameter quantitative value data by combining the arteriovenous blood vessel characteristic data and the personal information data;

[0060] Obtaining and processing the clinical data of the patient to obtain high-risk factors for gastrointestinal bleeding;

[0061] According to the gastrointestinal tract pathology index, gastroscopy correction coefficient and blood vessel diameter quantification value data, combined with the high-risk factors for gastrointestinal bleeding, risk assessment is performed to obtain a gastrointestinal bleeding risk index;

[0062] A threshold comparison is performed between the gastrointestinal bleeding risk index and a preset risk threshold, and a corresponding preset treatment plan is obtained based on the threshold comparison result to guide treatment of the patient.

[0063] Optionally, in the gastrointestinal bleeding risk assessment system based on capsule gastroscopy results described in the present application, the step of obtaining a gastrointestinal image generated by a patient based on capsule gastroscopy and processing the image feature data, including lesion feature data and gastrointestinal feature data, comprises:

[0064] Obtaining gastrointestinal images of patients based on capsule gastroscopy, and collecting image information of the gastrointestinal images, including mucosal morphology information, gastric wall condition information, fold distribution information, and secretion information;

[0065] Processing the image information through a preset gastroscopy feature recognition model to obtain image feature data of the gastroscopy;

[0066] The image feature data includes lesion feature data and gastrointestinal feature data.

[0067] Optionally, in the gastrointestinal bleeding risk assessment system based on capsule gastroscopy results described in the present application, the lesion amount assessment is performed according to the lesion characteristic data to obtain a gastrointestinal lesion amount index, including:

[0068] The lesion characteristic data include data on the maximum area of ​​erosion, data on the amount of erosion, data on the maximum thickness of white fur, data on the distribution of bleeding points, data on the amount of bleeding, and data on the maximum volume of ulcer;

[0069] The morbidity index of the gastrointestinal tract is obtained by evaluating the morbidity according to the data of the maximum erosion area, the erosion volume, the maximum thickness of the white fur, the bleeding point distribution, the bleeding volume and the maximum volume of the ulcer;

[0070] The calculation formula of the gastrointestinal morbidity index is:

[0071]

[0072] Among them, Z x is the gastrointestinal morbidity index, q a 、w s 、e d They are the maximum area of ​​erosion, the maximum thickness of white fur, and the maximum volume of ulcer, respectively. f ,t g ,y h are the erosion amount data, bleeding point distribution data, and bleeding amount data. β1, β2, β3, ζ1, ζ2, and ζ3 are the preset characteristic coefficients.

[0073] As can be seen from the above, the gastrointestinal bleeding risk assessment method and system based on capsule gastroscopy results provided by the present application obtains the patient's gastrointestinal images and processes them to obtain image feature data, including lesion feature data and gastrointestinal feature data, performs lesion quantity assessment based on the lesion feature data, obtains the gastrointestinal lesion quantity index, obtains the inspection process data and inspection technical parameter data of the capsule gastroscopy, and processes them in combination with the gastrointestinal feature data to obtain the gastroscopy correction coefficient, obtains the patient's arteriovenous vascular feature data and personal data and processes them to obtain vascular diameter quantification value data, obtains the patient's clinical data and processes them to obtain high-risk factors for gastrointestinal bleeding, performs risk assessment based on the gastrointestinal lesion quantity index, the gastroscopy correction coefficient and the vascular diameter quantification value data, and combines the high-risk factors for gastrointestinal bleeding to obtain a gastrointestinal bleeding risk index; performs a threshold comparison between the gastrointestinal bleeding risk index and the preset risk threshold, obtains the corresponding preset treatment plan based on the threshold comparison result to guide the treatment of the patient, thereby realizing the technology of gastrointestinal bleeding risk assessment based on capsule gastroscopy results.

[0074] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or understood by practicing the embodiments of the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0076] Figure 1 A flowchart of a method for assessing the risk of gastrointestinal bleeding based on capsule gastroscopy results provided in an embodiment of the present application;

[0077] Figure 2A flowchart of obtaining image feature data of a method for assessing the risk of gastrointestinal bleeding based on capsule gastroscopy results provided in an embodiment of the present application;

[0078] Figure 3 A flow chart of obtaining a gastrointestinal tract pathology index in a method for assessing the risk of gastrointestinal bleeding based on capsule gastroscopy results provided in an embodiment of the present application;

[0079] Figure 4 A flow chart of obtaining a gastroscopy correction coefficient for a method for assessing the risk of gastrointestinal bleeding based on capsule gastroscopy results provided in an embodiment of the present application. DETAILED DESCRIPTION

[0080] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0081] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0082] Please refer to Figure 1 , Figure 1 The present invention is a flowchart of a method for assessing the risk of gastrointestinal bleeding based on capsule gastroscopy results in some embodiments of the present invention. The method for assessing the risk of gastrointestinal bleeding based on capsule gastroscopy results is used in a terminal device, such as a computer, a mobile phone terminal, etc. The method for assessing the risk of gastrointestinal bleeding based on capsule gastroscopy results comprises the following steps:

[0083] S11, obtaining a gastrointestinal image of the patient generated based on capsule gastroscopy, and processing to obtain image feature data, including lesion feature data and gastrointestinal feature data;

[0084] S12, evaluating the lesion amount according to the lesion characteristic data to obtain a gastrointestinal lesion amount index;

[0085] S13, obtaining the inspection process data and inspection technical parameter data of the capsule gastroscopy, and processing them in combination with the gastrointestinal characteristic data to obtain a gastroscopy correction coefficient;

[0086] S14, obtaining the arteriovenous blood vessel characteristic data and personal information data of the patient, and processing the arteriovenous blood vessel characteristic data and the personal information data to obtain blood vessel diameter quantitative value data;

[0087] S15, obtaining and processing the clinical data of the patient to obtain high-risk factors for gastrointestinal bleeding;

[0088] S16, performing risk assessment based on the gastrointestinal tract morbidity index, gastroscopy correction coefficient, and blood vessel diameter quantification value data in combination with the high-risk factors for gastrointestinal bleeding to obtain a gastrointestinal bleeding risk index;

[0089] S17. Perform a threshold comparison between the gastrointestinal bleeding risk index and a preset risk threshold, and obtain a corresponding preset treatment plan based on the threshold comparison result to guide treatment of the patient.

[0090] It should be noted that in order to realize the risk assessment of gastrointestinal bleeding based on the results of capsule gastroscopy, so as to accurately assess the risk of gastrointestinal bleeding in the early stage, and achieve accurate monitoring, early detection, and early treatment, firstly, the gastrointestinal image of the patient is obtained, and the image feature data, including lesion feature data and gastrointestinal feature data, is processed to obtain the lesion feature data, and the lesion variable is evaluated according to the lesion feature data to obtain the gastrointestinal lesion variable index, the inspection process data and the inspection technical parameter data of the capsule gastroscopy are obtained, and the gastroscopy correction coefficient is obtained in combination with the gastrointestinal feature data, and the blood vessel diameter quantification value data is obtained, the patient's clinical data is obtained and processed, and the high-risk factor of gastrointestinal bleeding is obtained. According to the gastrointestinal lesion variable index, the gastroscopy correction coefficient and the blood vessel diameter quantification value data, the high-risk factor of gastrointestinal bleeding is combined to perform risk assessment and obtain the gastrointestinal bleeding risk index; the threshold value is compared between the gastrointestinal bleeding risk index and the preset risk threshold, and the corresponding preset treatment plan is obtained according to the threshold comparison result to guide the treatment of the patient, thereby realizing the technology of gastrointestinal bleeding risk assessment based on the results of capsule gastroscopy. .

[0091] Please refer to Figure 2 , Figure 2 The present invention is a flowchart of obtaining image feature data of a method for assessing the risk of gastrointestinal bleeding based on capsule gastroscopy results in some embodiments of the present invention. According to an embodiment of the present invention, the gastrointestinal image generated by the patient based on capsule gastroscopy is obtained, and the image feature data, including lesion feature data and gastrointestinal feature data, is obtained by processing:

[0092] S21, obtaining a gastrointestinal image of the patient based on capsule gastroscopy, and collecting image information of the gastrointestinal image, including mucosal morphology information, gastric wall condition information, fold distribution information, and secretion information;

[0093] S22, processing the image information by using a preset gastroscopy feature recognition model to obtain image feature data of the gastroscopy;

[0094] S23. The image feature data includes lesion feature data and gastrointestinal feature data.

[0095] It should be noted that before conducting a risk assessment, the patient's capsule gastroscopy results need to be processed. First, image information of gastrointestinal images is collected, including mucosal morphology, gastric wall condition, fold distribution, and secretions. Mucosal morphology information includes mucosal color, gloss, flatness, presence or absence of congestion, edema, erosion, ulcers, bleeding spots, etc. Gastric wall condition information refers to information such as the thickness of the gastric wall and whether the layers are clear. Fold distribution information refers to the degree of regularity of the arrangement of folds, whether they are thickened, deformed, interrupted or disappeared. The above image information is processed by a preset gastroscopy feature recognition model to obtain image feature data of the gastroscopy, including lesion feature data and gastrointestinal feature data. The gastroscopy feature recognition model is a neural network model, which is a trained gastroscopy feature recognition model obtained by training an initialized gastroscopy feature recognition model based on a large amount of gastroscopy image information from historical gastroscopy examinations.

[0096] Please refer to Figure 3 , Figure 3 The present invention is a flowchart of obtaining a gastrointestinal tract lesion variable index in a method for assessing the risk of gastrointestinal bleeding based on capsule gastroscopy results in some embodiments of the present invention. According to an embodiment of the present invention, the lesion variable index is obtained by assessing the lesion variable according to the lesion characteristic data, including:

[0097] S31, the lesion characteristic data includes data on the maximum erosion area, data on the amount of erosion, data on the maximum thickness of white fur, data on the distribution of bleeding points, data on the amount of bleeding, and data on the maximum volume of ulcer;

[0098] S32, evaluating the morbidity according to the data of the maximum erosion area, the data of the amount of erosion, the data of the maximum thickness of the white fur, the data of the distribution of bleeding points, the data of the amount of bleeding, and the data of the maximum volume of the ulcer, to obtain a gastrointestinal morbidity index;

[0099] The calculation formula of the gastrointestinal morbidity index is:

[0100]

[0101] Among them, Z xis the gastrointestinal morbidity index, q a 、w s , ed are the maximum area of ​​erosion, the maximum thickness of white fur, and the maximum volume of ulcer, respectively. f ,t g ,y h are the erosion amount data, bleeding point distribution data, and bleeding amount data; β1, β2, β3, ζ1, ζ2, and ζ3 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset medical health database).

[0102] It should be noted that in order to obtain the patient's lesion volume, it is necessary to further refine and differentiate the obtained lesion characteristic data, including the maximum erosion area, erosion volume, maximum thickness of white tongue coating, distribution of bleeding points, bleeding volume and maximum volume of ulcer, and conduct lesion volume evaluation on the above data to obtain a gastrointestinal lesion volume index that can reflect the patient's lesion volume.

[0103] Please refer to Figure 4 , Figure 4 The present invention is a flowchart of obtaining a gastroscopy correction coefficient in a method for assessing the risk of gastrointestinal bleeding based on capsule gastroscopy results in some embodiments of the present application. According to an embodiment of the present invention, obtaining the inspection process data and inspection technical parameter data of the capsule gastroscopy, and processing them in combination with gastrointestinal characteristic data to obtain a gastroscopy correction coefficient includes:

[0104] S41, obtaining the inspection process data and inspection technical parameter data of the capsule gastroscopy;

[0105] S42, the inspection process data includes capsule running speed data and capsule passing time data;

[0106] S43, the inspection technical parameter data includes image resolution data and field of view angle data;

[0107] S44, the gastrointestinal characteristic data includes stomach cleanliness data and stomach cavity filling data;

[0108] S45, processing the capsule running speed data, capsule passing time data, image resolution data, field of view angle data, stomach cleanliness data, and stomach cavity fullness data through a preset gastroscopy evaluation model to obtain a gastroscopy correction coefficient;

[0109] The calculation formula of the gastroscopy correction coefficient is:

[0110]

[0111] Among them, C v is the correction factor for gastroscopy, u j 、i kThey are respectively the capsule running speed data and the capsule passing time data. l 、p m They are image resolution data and field of view data, s q ,d w are respectively the data of gastric cleanliness and gastric cavity filling degree, ε, λ is a preset characteristic coefficient (the characteristic coefficient is obtained by querying a preset medical health database).

[0112] It should be noted that the accuracy of capsule gastroscopy will be affected by some objective factors, such as the running speed of the capsule, the time it takes for the capsule to pass through the stomach, the resolution of the gastroscopic image, the field of view, the cleanliness of the stomach and the fullness of the stomach cavity. Among them, the field of view refers to the field of view of a single shot, and the fullness of the stomach cavity refers to the filling of gas and liquid in the stomach. Therefore, these data need to be input into the calculation formula of the preset gastroscopy evaluation model for processing to obtain the gastroscopy correction coefficient.

[0113] According to an embodiment of the present invention, the step of obtaining the arteriovenous blood vessel characteristic data and the personal information data of the patient, and processing the arteriovenous blood vessel characteristic data and the personal information data to obtain the blood vessel diameter quantitative value data includes:

[0114] Acquire the arteriovenous characteristic data and personal data of the patient through a preset medical health database;

[0115] The arteriovenous blood vessel characteristic data include blood pressure data, blood flow velocity data and blood vessel wall elasticity data;

[0116] The personal data includes age data and gender data;

[0117] By combining the arteriovenous blood vessel characteristic data with the personal information data, the quantitative value data of the blood vessel diameter is obtained;

[0118] The calculation formula of the blood vessel diameter quantification value data is:

[0119]

[0120] Among them, B n is the quantitative value data of blood vessel diameter, f e , g r 、h t They are blood pressure data, blood flow velocity data, and vascular wall elasticity data, respectively. y , k u are age data and gender data respectively, and δ1, δ2, δ3, and φ are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset medical health database).

[0121] It should be noted that since the quantified value of blood vessel diameter is one of the important reference indicators for assessing the severity of gastrointestinal bleeding and formulating treatment plans, this data needs to be taken into account when conducting risk assessment. First, the arteriovenous vascular characteristic data associated with the quantified value of blood vessel diameter is obtained, including blood pressure, blood flow velocity, and vascular wall elasticity data, and then combined with age data and gender data for processing to obtain the quantified value of blood vessel diameter data.

[0122] According to an embodiment of the present invention, obtaining and processing the clinical data of the patient to obtain high-risk factors for gastrointestinal bleeding includes:

[0123] Obtain clinical data of the patient through a preset medical health database, including personal health-related data, medical history data, and related disease data;

[0124] The personal health-related data includes smoking history data and drinking history data;

[0125] The medical history data includes diabetes medical history data and hypertension medical history data;

[0126] The associated disease data include liver cirrhosis data and blood biochemical data;

[0127] Processing the clinical data to obtain high-risk factors for gastrointestinal bleeding;

[0128] The calculation formula for the high-risk factor for gastrointestinal bleeding is:

[0129]

[0130] Among them, L i It is a high risk factor for gastrointestinal bleeding. q 、n w are smoking history data and drinking history data, respectively, m e 、a r They are diabetes medical history data and hypertension medical history data, respectively. g ,t d They are liver cirrhosis data, blood biochemical data, and y , k u are age data and gender data respectively, and ω1, ω2, and ω3 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset medical health database).

[0131] It should be noted that the patient's clinical data will also affect the results of assessing the risk of gastrointestinal bleeding, such as whether the patient has the habit of smoking and drinking, whether he has a family history of disease, whether he has cirrhosis or blood biochemistry, etc. Among them, blood biochemical data refers to a series of indicators and values ​​obtained by biochemical analysis of blood samples. Therefore, these clinical data need to be processed to obtain high-risk factors for gastrointestinal bleeding.

[0132] According to an embodiment of the present invention, the risk assessment is performed based on the gastrointestinal tract morbidity index, the gastroscopy correction coefficient and the vascular diameter quantification value data, combined with the high-risk factors for gastrointestinal bleeding, to obtain a gastrointestinal bleeding risk index, including:

[0133] According to the gastrointestinal tract pathology index, gastroscopy correction coefficient and blood vessel diameter quantification value data, combined with the high-risk factors for gastrointestinal bleeding, a risk assessment process is performed through a preset gastrointestinal bleeding risk assessment model to obtain a gastrointestinal bleeding risk index;

[0134] The calculation formula of the gastrointestinal bleeding risk index is:

[0135]

[0136] Among them, F e is the gastrointestinal morbidity index, Z x , C v , B n , L i They are respectively gastrointestinal pathology index, gastroscopy correction coefficient, blood vessel diameter quantification value data, and gastrointestinal bleeding high-risk factors. ρ1, ρ2, ρ3, and ρ4 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset medical and health database).

[0137] It should be noted that in order to accurately assess the risk of gastrointestinal bleeding in the early stage, several major influencing data, including the gastrointestinal morbidity index, gastroscopy correction coefficient, vascular diameter quantification data and gastrointestinal bleeding high-risk factors, need to be input into the calculation formula of the preset gastrointestinal bleeding risk assessment model for risk assessment processing to obtain the gastrointestinal bleeding risk index. The comparison result of the gastrointestinal bleeding risk index with the preset risk threshold can directly reflect the patient's risk level of gastrointestinal bleeding.

[0138] In a second aspect, the present invention further discloses a gastrointestinal bleeding risk assessment system based on capsule gastroscopy results, comprising a memory and a processor, wherein the memory comprises a gastrointestinal bleeding risk assessment method program based on capsule gastroscopy results, and when the gastrointestinal bleeding risk assessment method program based on capsule gastroscopy results is executed by the processor, the following steps are implemented:

[0139] Acquire gastrointestinal images generated by capsule gastroscopy of the patient, and process and obtain image feature data, including lesion feature data and gastrointestinal feature data;

[0140] Performing lesion quantity evaluation according to the lesion characteristic data to obtain a gastrointestinal lesion quantity index;

[0141] Acquiring the inspection process data and inspection technical parameter data of the capsule gastroscopy, and processing them in combination with the gastrointestinal characteristic data to obtain a gastroscopy correction coefficient;

[0142] Acquire the arteriovenous blood vessel characteristic data and personal information data of the patient, and obtain blood vessel diameter quantitative value data by combining the arteriovenous blood vessel characteristic data and the personal information data;

[0143] Obtaining and processing the clinical data of the patient to obtain high-risk factors for gastrointestinal bleeding;

[0144] According to the gastrointestinal tract pathology index, gastroscopy correction coefficient and blood vessel diameter quantification value data, combined with the high-risk factors for gastrointestinal bleeding, risk assessment is performed to obtain a gastrointestinal bleeding risk index;

[0145] A threshold comparison is performed between the gastrointestinal bleeding risk index and a preset risk threshold, and a corresponding preset treatment plan is obtained based on the threshold comparison result to guide treatment of the patient.

[0146] It should be noted that in order to realize the risk assessment of gastrointestinal bleeding based on the results of capsule gastroscopy, so as to accurately assess the risk of gastrointestinal bleeding in the early stage, and achieve accurate monitoring, early detection, and early treatment, firstly, the gastrointestinal image of the patient is obtained, and the image feature data, including lesion feature data and gastrointestinal feature data, is processed to obtain the lesion feature data, and the lesion variable is evaluated according to the lesion feature data to obtain the gastrointestinal lesion variable index, the inspection process data and the inspection technical parameter data of the capsule gastroscopy are obtained, and the gastroscopy correction coefficient is obtained in combination with the gastrointestinal feature data, and the blood vessel diameter quantification value data is obtained, the patient's clinical data is obtained and processed, and the high-risk factor of gastrointestinal bleeding is obtained. According to the gastrointestinal lesion variable index, the gastroscopy correction coefficient and the blood vessel diameter quantification value data, the high-risk factor of gastrointestinal bleeding is combined to perform risk assessment and obtain the gastrointestinal bleeding risk index; the threshold value is compared between the gastrointestinal bleeding risk index and the preset risk threshold, and the corresponding preset treatment plan is obtained according to the threshold comparison result to guide the treatment of the patient, thereby realizing the technology of gastrointestinal bleeding risk assessment based on the results of capsule gastroscopy. .

[0147] According to an embodiment of the present invention, the step of obtaining a gastrointestinal image generated by a patient based on capsule gastroscopy and processing the image feature data, including lesion feature data and gastrointestinal feature data, includes:

[0148] Obtaining gastrointestinal images of patients based on capsule gastroscopy, and collecting image information of the gastrointestinal images, including mucosal morphology information, gastric wall condition information, fold distribution information, and secretion information;

[0149] Processing the image information through a preset gastroscopy feature recognition model to obtain image feature data of the gastroscopy;

[0150] The image feature data includes lesion feature data and gastrointestinal feature data.

[0151] It should be noted that before conducting a risk assessment, the patient's capsule gastroscopy results need to be processed. First, image information of gastrointestinal images is collected, including mucosal morphology, gastric wall condition, fold distribution, and secretions. Mucosal morphology information includes mucosal color, gloss, flatness, presence or absence of congestion, edema, erosion, ulcers, bleeding spots, etc. Gastric wall condition information refers to information such as the thickness of the gastric wall and whether the layers are clear. Fold distribution information refers to the degree of regularity of the arrangement of folds, whether they are thickened, deformed, interrupted or disappeared. The above image information is processed by a preset gastroscopy feature recognition model to obtain image feature data of the gastroscopy, including lesion feature data and gastrointestinal feature data. The gastroscopy feature recognition model is a neural network model, which is a trained gastroscopy feature recognition model obtained by training an initialized gastroscopy feature recognition model based on a large amount of gastroscopy image information from historical gastroscopy examinations.

[0152] According to an embodiment of the present invention, the step of evaluating the lesion amount according to the lesion characteristic data to obtain a gastrointestinal lesion amount index includes:

[0153] The lesion characteristic data include data on the maximum area of ​​erosion, data on the amount of erosion, data on the maximum thickness of white fur, data on the distribution of bleeding points, data on the amount of bleeding, and data on the maximum volume of ulcer;

[0154] The morbidity index of the gastrointestinal tract is obtained by evaluating the morbidity according to the data of the maximum erosion area, the erosion volume, the maximum thickness of the white fur, the bleeding point distribution, the bleeding volume and the maximum volume of the ulcer;

[0155] The calculation formula of the gastrointestinal morbidity index is:

[0156]

[0157] Among them, Z x is the gastrointestinal morbidity index, qa 、w s 、e d They are the maximum area of ​​erosion, the maximum thickness of white fur, and the maximum volume of ulcer, respectively. f ,t g ,y h are the erosion amount data, bleeding point distribution data, and bleeding amount data; β1, β2, β3, ζ1, ζ2, and ζ3 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset medical health database).

[0158] It should be noted that in order to obtain the patient's lesion volume, it is necessary to further refine and differentiate the obtained lesion characteristic data, including the maximum erosion area, erosion volume, maximum thickness of white tongue coating, distribution of bleeding points, bleeding volume and maximum volume of ulcer, and conduct lesion volume evaluation on the above data to obtain a gastrointestinal lesion volume index that can reflect the patient's lesion volume.

[0159] According to an embodiment of the present invention, the obtaining of the inspection process data and the inspection technical parameter data of the capsule gastroscopy and processing them in combination with the gastrointestinal characteristic data to obtain the gastroscopy correction coefficient includes:

[0160] Acquiring the inspection process data and inspection technical parameter data of the capsule gastroscopy;

[0161] The inspection process data includes capsule running speed data and capsule passing time data;

[0162] The inspection technical parameter data includes image resolution data and field of view angle data;

[0163] The gastrointestinal characteristic data include gastric cleanliness data and gastric cavity filling data;

[0164] According to the capsule running speed data, capsule passing time data, image resolution data, field of view angle data, stomach cleanliness data and stomach cavity filling degree data, a preset gastroscopy evaluation model is used to process and obtain a gastroscopy correction coefficient;

[0165] The calculation formula of the gastroscopy correction coefficient is:

[0166]

[0167] Among them, C v is the correction factor for gastroscopy, u j 、i k They are respectively the capsule running speed data and the capsule passing time data. l 、p m They are image resolution data and field of view data, s q d ware respectively the data of gastric cleanliness and gastric cavity filling degree, ε, λ is a preset characteristic coefficient (the characteristic coefficient is obtained by querying a preset medical health database).

[0168] It should be noted that the accuracy of capsule gastroscopy will be affected by some objective factors, such as the running speed of the capsule, the time it takes for the capsule to pass through the stomach, the resolution of the gastroscopic image, the field of view, the cleanliness of the stomach and the fullness of the stomach cavity. Among them, the field of view refers to the field of view of a single shot, and the fullness of the stomach cavity refers to the filling of gas and liquid in the stomach. Therefore, these data need to be input into the calculation formula of the preset gastroscopy evaluation model for processing to obtain the gastroscopy correction coefficient.

[0169] According to an embodiment of the present invention, the step of obtaining the arteriovenous blood vessel characteristic data and the personal information data of the patient, and processing the arteriovenous blood vessel characteristic data and the personal information data to obtain the blood vessel diameter quantitative value data includes:

[0170] Acquire the arteriovenous characteristic data and personal data of the patient through a preset medical health database;

[0171] The arteriovenous blood vessel characteristic data include blood pressure data, blood flow velocity data and blood vessel wall elasticity data;

[0172] The personal data includes age data and gender data;

[0173] By combining the arteriovenous blood vessel characteristic data with the personal information data, the quantitative value data of the blood vessel diameter is obtained;

[0174] The calculation formula of the blood vessel diameter quantification value data is:

[0175]

[0176] Among them, B n is the quantitative value data of blood vessel diameter, f e , g r 、h t They are blood pressure data, blood flow velocity data, and vascular wall elasticity data, respectively. y , k u are age data and gender data respectively, and δ1, δ2, δ3, and φ are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset medical health database).

[0177] It should be noted that since the quantified value of blood vessel diameter is one of the important reference indicators for assessing the severity of gastrointestinal bleeding and formulating treatment plans, this data needs to be taken into account when conducting risk assessment. First, the arteriovenous vascular characteristic data associated with the quantified value of blood vessel diameter is obtained, including blood pressure, blood flow velocity, and vascular wall elasticity data, and then combined with age data and gender data for processing to obtain the quantified value of blood vessel diameter data.

[0178] According to an embodiment of the present invention, obtaining and processing the clinical data of the patient to obtain high-risk factors for gastrointestinal bleeding includes:

[0179] Obtain clinical data of the patient through a preset medical health database, including personal health-related data, medical history data, and related disease data;

[0180] The personal health-related data includes smoking history data and drinking history data;

[0181] The medical history data includes diabetes medical history data and hypertension medical history data;

[0182] The associated disease data include liver cirrhosis data and blood biochemical data;

[0183] Processing the clinical data to obtain high-risk factors for gastrointestinal bleeding;

[0184] The calculation formula for the high-risk factor for gastrointestinal bleeding is:

[0185]

[0186] Among them, L i It is a high risk factor for gastrointestinal bleeding. q 、n w are smoking history data and drinking history data, respectively, m e 、a r They are diabetes medical history data and hypertension medical history data, respectively. g ,t d They are liver cirrhosis data, blood biochemical data, and y , k u are age data and gender data respectively, and ω1, ω2, and ω3 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset medical health database).

[0187] It should be noted that the patient's clinical data will also affect the results of assessing the risk of gastrointestinal bleeding, such as whether the patient has the habit of smoking and drinking, whether he has a family history of disease, whether he has cirrhosis or blood biochemistry, etc. Among them, blood biochemical data refers to a series of indicators and values ​​obtained by biochemical analysis of blood samples. Therefore, these clinical data need to be processed to obtain high-risk factors for gastrointestinal bleeding.

[0188] According to an embodiment of the present invention, the risk assessment is performed based on the gastrointestinal tract morbidity index, the gastroscopy correction coefficient and the vascular diameter quantification value data, combined with the high-risk factors for gastrointestinal bleeding, to obtain a gastrointestinal bleeding risk index, including:

[0189] According to the gastrointestinal tract pathology index, gastroscopy correction coefficient and blood vessel diameter quantification value data, combined with the high-risk factors for gastrointestinal bleeding, a risk assessment process is performed through a preset gastrointestinal bleeding risk assessment model to obtain a gastrointestinal bleeding risk index;

[0190] The calculation formula of the gastrointestinal bleeding risk index is:

[0191]

[0192] Among them, F e is the gastrointestinal morbidity index, Z x , C v , B n , L i They are respectively gastrointestinal pathology index, gastroscopy correction coefficient, blood vessel diameter quantification value data, and gastrointestinal bleeding high-risk factors. ρ1, ρ2, ρ3, and ρ4 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset medical and health database).

[0193] It should be noted that in order to accurately assess the risk of gastrointestinal bleeding in the early stage, several major influencing data, including the gastrointestinal morbidity index, gastroscopy correction coefficient, vascular diameter quantification data and gastrointestinal bleeding high-risk factors, need to be input into the calculation formula of the preset gastrointestinal bleeding risk assessment model for risk assessment processing to obtain the gastrointestinal bleeding risk index. The comparison result of the gastrointestinal bleeding risk index with the preset risk threshold can directly reflect the patient's risk level of gastrointestinal bleeding.

[0194] The present invention discloses a method and system for assessing the risk of gastrointestinal bleeding based on capsule gastroscopy results. The method and system acquire gastrointestinal images of patients and process them to obtain image feature data, including lesion feature data and gastrointestinal feature data. The method and system perform lesion feature assessment based on the lesion feature data to obtain a gastrointestinal lesion feature index. The method and system acquire inspection process data and inspection technical parameter data of capsule gastroscopy and process them in combination with the gastrointestinal feature data to obtain a gastroscopy correction coefficient. The method and system acquire arteriovenous feature data and personal data of patients and process them to obtain vascular diameter quantification value data. The method and system acquire clinical data of patients and process them to obtain high-risk factors for gastrointestinal bleeding. The method and system perform risk assessment based on the gastrointestinal lesion feature index, the gastroscopy correction coefficient and the vascular diameter quantification value data in combination with the high-risk factors for gastrointestinal bleeding to obtain a gastrointestinal bleeding risk index. The method performs threshold comparison between the gastrointestinal bleeding risk index and a preset risk threshold, and obtains a corresponding preset treatment plan based on the threshold comparison result to guide treatment of the patient, thereby realizing a technology for assessing the risk of gastrointestinal bleeding based on capsule gastroscopy results.

[0195] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0196] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0197] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0198] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.

[0199] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Claims

1. A method for assessing the risk of gastrointestinal bleeding based on capsule gastroscopy results, characterized in that: The following steps are involved: Acquire gastrointestinal images generated by capsule gastroscopy of the patient, and process and obtain image feature data, including lesion feature data and gastrointestinal feature data; Performing lesion quantity evaluation according to the lesion characteristic data to obtain a gastrointestinal lesion quantity index; Acquiring the inspection process data and inspection technical parameter data of the capsule gastroscopy, and processing them in combination with the gastrointestinal characteristic data to obtain a gastroscopy correction coefficient; Acquire the arteriovenous blood vessel characteristic data and personal information data of the patient, and obtain blood vessel diameter quantitative value data by combining the arteriovenous blood vessel characteristic data and the personal information data; Obtaining and processing the clinical data of the patient to obtain high-risk factors for gastrointestinal bleeding; According to the gastrointestinal tract pathology index, gastroscopy correction coefficient and blood vessel diameter quantification value data, combined with the high-risk factors for gastrointestinal bleeding, risk assessment is performed to obtain a gastrointestinal bleeding risk index; A threshold comparison is performed between the gastrointestinal bleeding risk index and a preset risk threshold, and a corresponding preset treatment plan is obtained based on the threshold comparison result to guide treatment of the patient.

2. The method for assessing the risk of gastrointestinal bleeding based on capsule gastroscopy results according to claim 1, characterized in that: The method of obtaining a gastrointestinal image generated by a capsule gastroscopy of a patient and processing the image to obtain image feature data, including lesion feature data and gastrointestinal feature data, includes: Obtaining gastrointestinal images of patients based on capsule gastroscopy, and collecting image information of the gastrointestinal images, including mucosal morphology information, gastric wall condition information, fold distribution information, and secretion information; Processing the image information through a preset gastroscopy feature recognition model to obtain image feature data of the gastroscopy; The image feature data includes lesion feature data and gastrointestinal feature data.

3. The method for assessing the risk of gastrointestinal bleeding based on capsule gastroscopy results according to claim 2, characterized in that: The step of evaluating the lesion amount according to the lesion characteristic data to obtain a gastrointestinal lesion amount index includes: The lesion characteristic data include data on the maximum area of ​​erosion, data on the amount of erosion, data on the maximum thickness of white fur, data on the distribution of bleeding points, data on the amount of bleeding, and data on the maximum volume of ulcer; The morbidity index of the gastrointestinal tract is obtained by evaluating the morbidity according to the data of the maximum erosion area, the erosion volume, the maximum thickness of the white fur, the bleeding point distribution, the bleeding volume and the maximum volume of the ulcer; The calculation formula of the gastrointestinal morbidity index is: Among them, Z x is the gastrointestinal morbidity index, q a 、w s , ed are the maximum area of ​​erosion, the maximum thickness of white fur, and the maximum volume of ulcer, respectively. f ,t g ,y h are the erosion amount data, bleeding point distribution data, and bleeding amount data. β1, β2, β3, ζ1, ζ2, and ζ3 are the preset characteristic coefficients.

4. The method for assessing the risk of gastrointestinal bleeding based on capsule gastroscopy results according to claim 3, characterized in that: The obtaining of the inspection process data and the inspection technical parameter data of the capsule gastroscopy and processing them in combination with the gastrointestinal characteristic data to obtain the gastroscopy correction coefficient includes: Acquiring the inspection process data and inspection technical parameter data of the capsule gastroscopy; The inspection process data includes capsule running speed data and capsule passing time data; The inspection technical parameter data includes image resolution data and field of view angle data; The gastrointestinal characteristic data include gastric cleanliness data and gastric cavity filling data; According to the capsule running speed data, capsule passing time data, image resolution data, field of view angle data, stomach cleanliness data and stomach cavity filling degree data, a preset gastroscopy evaluation model is used to process and obtain a gastroscopy correction coefficient; The calculation formula of the gastroscopy correction coefficient is: Among them, C v is the correction factor for gastroscopy, u j 、i k They are respectively the capsule running speed data and the capsule passing time data. l 、p m They are image resolution data and field of view data, s q d w They are respectively the data of gastric cleanliness and gastric cavity filling degree, ε, λ is the preset characteristic coefficient.

5. The method for assessing the risk of gastrointestinal bleeding based on capsule gastroscopy results according to claim 4, characterized in that: The step of obtaining the arteriovenous blood vessel characteristic data and the personal data of the patient, and processing the arteriovenous blood vessel characteristic data and the personal data to obtain blood vessel diameter quantitative value data includes: Acquire the arteriovenous characteristic data and personal data of the patient through a preset medical health database; The arteriovenous blood vessel characteristic data include blood pressure data, blood flow velocity data and blood vessel wall elasticity data; The personal data includes age data and gender data; By combining the arteriovenous blood vessel characteristic data with the personal information data, the quantitative value data of the blood vessel diameter is obtained; The calculation formula of the blood vessel diameter quantification value data is: Among them, B n is the quantitative value data of blood vessel diameter, f e , g r 、h t They are blood pressure data, blood flow velocity data, and vascular wall elasticity data, respectively. y , k u are age data and gender data respectively, and δ1, δ2, δ3, and φ are preset characteristic coefficients.

6. The method for assessing the risk of gastrointestinal bleeding based on capsule gastroscopy results according to claim 5, characterized in that: The step of obtaining and processing the clinical data of the patient to obtain high-risk factors for gastrointestinal bleeding includes: Obtain clinical data of the patient through a preset medical health database, including personal health-related data, medical history data, and related disease data; The personal health-related data includes smoking history data and drinking history data; The medical history data includes diabetes medical history data and hypertension medical history data; The associated disease data include liver cirrhosis data and blood biochemical data; Processing the clinical data to obtain high-risk factors for gastrointestinal bleeding; The calculation formula for the high-risk factor for gastrointestinal bleeding is: Among them, L i It is a high risk factor for gastrointestinal bleeding. q 、n w are smoking history data and drinking history data, respectively, m e 、a r They are diabetes medical history data and hypertension medical history data, respectively. g ,t d They are liver cirrhosis data, blood biochemical data, and y , k u are age data and gender data respectively, and ω1, ω2, and ω3 are preset characteristic coefficients.

7. The method for assessing the risk of gastrointestinal bleeding based on capsule gastroscopy results according to claim 6, characterized in that: The risk assessment is performed based on the gastrointestinal tract morbidity index, gastroscopy correction coefficient and blood vessel diameter quantification value data, combined with the high-risk factors for gastrointestinal bleeding, to obtain a gastrointestinal bleeding risk index, including: According to the gastrointestinal tract pathology index, gastroscopy correction coefficient and blood vessel diameter quantification value data, combined with the high-risk factors for gastrointestinal bleeding, a risk assessment process is performed through a preset gastrointestinal bleeding risk assessment model to obtain a gastrointestinal bleeding risk index; The calculation formula of the gastrointestinal bleeding risk index is: Among them, F e is the gastrointestinal morbidity index, Z x , C v , B n , L i They are gastrointestinal pathology index, gastroscopy correction coefficient, blood vessel diameter quantification value data, and gastrointestinal bleeding high-risk factors. ρ1, ρ2, ρ3, and ρ4 are preset characteristic coefficients.

8. A gastrointestinal bleeding risk assessment system based on capsule gastroscopy results, characterized in that: The system includes: a memory and a processor, wherein the memory includes a program of a method for assessing the risk of gastrointestinal bleeding based on capsule gastroscopy results, and when the program of the method for assessing the risk of gastrointestinal bleeding based on capsule gastroscopy results is executed by the processor, the following steps are implemented: Acquire gastrointestinal images generated by capsule gastroscopy of the patient, and process and obtain image feature data, including lesion feature data and gastrointestinal feature data; Performing lesion quantity evaluation according to the lesion characteristic data to obtain a gastrointestinal lesion quantity index; Acquiring the inspection process data and inspection technical parameter data of the capsule gastroscopy, and processing them in combination with the gastrointestinal characteristic data to obtain a gastroscopy correction coefficient; Acquire the arteriovenous blood vessel characteristic data and personal information data of the patient, and obtain blood vessel diameter quantitative value data by combining the arteriovenous blood vessel characteristic data and the personal information data; Obtaining and processing the clinical data of the patient to obtain high-risk factors for gastrointestinal bleeding; According to the gastrointestinal tract pathology index, gastroscopy correction coefficient and blood vessel diameter quantification value data, combined with the high-risk factors for gastrointestinal bleeding, risk assessment is performed to obtain a gastrointestinal bleeding risk index; A threshold comparison is performed between the gastrointestinal bleeding risk index and a preset risk threshold, and a corresponding preset treatment plan is obtained based on the threshold comparison result to guide treatment of the patient.

9. The gastrointestinal bleeding risk assessment system based on capsule gastroscopy results according to claim 8, characterized in that: The method of obtaining a gastrointestinal image generated by a capsule gastroscopy of a patient and processing the image to obtain image feature data, including lesion feature data and gastrointestinal feature data, includes: Obtaining gastrointestinal images of patients based on capsule gastroscopy, and collecting image information of the gastrointestinal images, including mucosal morphology information, gastric wall condition information, fold distribution information, and secretion information; Processing the image information through a preset gastroscopy feature recognition model to obtain image feature data of the gastroscopy; The image feature data includes lesion feature data and gastrointestinal feature data.

10. The gastrointestinal bleeding risk assessment system based on capsule gastroscopy results according to claim 9, characterized in that: The step of evaluating the lesion amount according to the lesion characteristic data to obtain a gastrointestinal lesion amount index includes: The lesion characteristic data include data on the maximum area of ​​erosion, data on the amount of erosion, data on the maximum thickness of white fur, data on the distribution of bleeding points, data on the amount of bleeding, and data on the maximum volume of ulcer; The morbidity index of the gastrointestinal tract is obtained by evaluating the morbidity according to the data of the maximum erosion area, the erosion volume, the maximum thickness of the white fur, the bleeding point distribution, the bleeding volume and the maximum volume of the ulcer; The calculation formula of the gastrointestinal morbidity index is: Among them, Z x is the gastrointestinal morbidity index, q a 、w s 、e d They are the maximum area of ​​erosion, the maximum thickness of white fur, and the maximum volume of ulcer, respectively. f ,t g ,y h are the erosion amount data, bleeding point distribution data, and bleeding amount data. β1, β2, β3, ζ1, ζ2, and ζ3 are the preset characteristic coefficients.

Images