WO2022141926A1

WO2022141926A1 - Gastrointestinal perforation diagnosis and intervention device, and diagnosis and intervention system

Info

Publication number: WO2022141926A1
Application number: PCT/CN2021/086306
Authority: WO
Inventors: 樊代明; 钟南山; 姚娟娟
Original assignee: 上海明品医学数据科技有限公司
Priority date: 2020-12-31
Filing date: 2021-04-10
Publication date: 2022-07-07
Also published as: CN113160995A

Abstract

A gastrointestinal perforation diagnosis and intervention device, and diagnosis and intervention system. The gastrointestinal perforation diagnosis device comprises: a health information acquisition module (11), configured to acquire health information of a user; a disease information acquisition module (12), connected to the health information acquisition module, and configured to acquire disease information of the user according to health information of the user and acquire first disease information according to the disease information of the user and an association model; the first disease information referring to disease information associated with gastrointestinal perforation in the disease information of the user; the association model comprising various diseases and disease information associated with the diseases, and the diseases comprising gastrointestinal perforation; and a disease diagnosis module (13), connected to the disease information acquisition module, and configured to generate a diagnostic report of the user according to the first disease information. According to the diagnostic report, the user may know, in a timely fashion, whether the user suffers from gastrointestinal perforation, so as to adopt a corresponding treatment or intervention measure.

Description

A digestive tract perforation diagnostic device, intervention device and diagnostic intervention system

technical field

The invention belongs to the field of medical or health data processing, and relates to a diagnostic device, in particular to a diagnostic device for perforation of the digestive tract, an intervention device and a diagnostic intervention system.

Background technique

With the continuous acceleration of the pace of life, it is often difficult for people to maintain good eating habits and eating patterns, which leads to a high incidence of gastrointestinal perforation in the population. Digestive tract perforation refers to the perforation of the entire digestive tract from the esophagus to the colorectum. The most common are gastric perforation and duodenal perforation. The most common cause is peptic ulcer. The membrane layer eventually penetrates the stomach or duodenum wall and perforates. Gastrointestinal perforation can cause severe abdominal pain in the user and may be accompanied by symptoms such as nausea, vomiting, palpitation, drop in blood pressure, and pallor.

In real life, due to the lack of medical knowledge, people's understanding of digestive tract perforation is generally insufficient, which makes it difficult for users to obtain the information that they have digestive tract perforation in time at the early stage of the disease. Often, when the perforation of the digestive tract occurs and causes physical discomfort, the user will find out that he has a perforation of the digestive tract only after going to the hospital for examination, which will not only increase the pain of the user, but also be detrimental to the early intervention and treatment of the perforation of the digestive tract.

SUMMARY OF THE INVENTION

In view of the shortcomings of the above-mentioned prior art, the purpose of the present invention is to provide a digestive tract perforation diagnostic device, intervention device and diagnostic intervention system, which are used to solve the problem that it is difficult for users in the prior art to know in time that they suffer from digestive tract diseases in the early stage of the disease. perforation problem.

In order to achieve the above purpose and other related purposes, a first aspect of the present invention provides a digestive tract perforation diagnosis device; the digestive tract perforation diagnosis device includes: a health information acquisition module for acquiring health information of a user; a disease information acquisition module , which is connected to the health information acquisition module, used to acquire the user's disease information according to the user's health information, and obtain the first disease information according to the user's disease information and an association model; wherein, the first disease The information refers to disease information associated with gastrointestinal perforation in the user's disease information; the association model includes multiple diseases and disease information associated with each disease, and the multiple diseases include gastrointestinal perforation; disease diagnosis module , which is connected to the disease information acquisition module and used to generate a user's diagnosis report according to the first disease information.

In an embodiment of the first aspect, the health information of the user includes symptom sub-information, indicator sub-information and/or profile sub-information; the disease information includes symptoms and signs, examination indicators and/or profile-related information; The disease information obtaining module obtains the symptoms and signs according to the symptom sub-information, obtains the examination index according to the index sub-information, and/or obtains the file-related information according to the file sub-information.

In an embodiment of the first aspect, the health information acquisition module acquires the user's symptom sub-information and/or indicator sub-information according to the user's detection report and/or medical image; and/or the health information acquisition module Obtain the user's profile sub-information based on the user's health profile.

In an embodiment of the first aspect, the health information acquisition module includes: a self-test template generation unit, configured to generate a self-test template; the self-test template is used to prompt the user to input health information; health information receiving a unit, connected with the self-test template generating unit, for receiving health information input by a user; a self-test template updating unit, connected with the self-test template generating unit and the health information receiving unit, for receiving health information according to the user The self-test template is updated with the health information and the association model; the updated self-test template is used to prompt the user to continue to input the health information.

In an embodiment of the first aspect, the self-test template updating unit includes: a prompt information obtaining subunit, which is connected to the health information receiving unit and is used for obtaining pending health information according to the currently obtained health information of the user. prompt information; a priority acquisition subunit, connected with the prompt information acquisition subunit, and used for acquiring the priority of each of the information to be prompted; a template update subunit, connected with the prompt information acquisition subunit and the priority The acquisition subunit is connected to update the self-test template according to the information to be prompted and its priority.

In an embodiment of the first aspect, the self-test template prompts the user to input the information to be prompted in the form of an information prompt label.

In an embodiment of the first aspect, the health information receiving unit is further configured to standardize the health information input by the user according to a medical standard vocabulary.

In an embodiment of the first aspect, the user's diagnosis report includes the probability that the user suffers from perforation of the digestive tract; the disease diagnosis module includes: a weight value calculation unit, connected to the disease information acquisition module, using calculating the weight value of each of the first disease information according to the association model; the probability calculation unit, connected with the weight value calculation unit, is used to calculate the user suffering from digestive tract according to the weight value of each of the first disease information The probability of perforation.

In an embodiment of the first aspect, the diagnosis report of the user includes the probability that the user suffers from perforation of the digestive tract; the disease diagnosis module includes: a training data acquisition unit for acquiring training data; a neural network training unit , connected with the training data acquisition unit, and used for training a neural network model by using the training data to obtain a probability calculation neural network model; a neural network processing unit, connected with the neural network training unit and the disease The information acquisition module is connected, and is configured to process the first disease information by using the probability calculation neural network model, so as to acquire the probability that the user suffers from perforation of the digestive tract.

In an embodiment of the first aspect, the training data includes first training data and second training data; the first training data refers to training data generated according to the correlation model, and the second training data The data refers to the training data obtained from the actual detection case database.

In an embodiment of the first aspect, the device for diagnosing perforation of the digestive tract further includes an early warning module; the early warning module generates early warning information according to the probability that the user suffers from perforation of the digestive tract.

A second aspect of the present invention provides an intervention device for perforation of the digestive tract, the device for intervention for perforation of the digestive tract includes: a diagnosis report acquisition module for acquiring a user's diagnosis report; an intervention plan generation module, which is connected to the diagnosis report acquisition module , which is used to generate the user's intervention plan according to the user's diagnosis report.

In an embodiment of the second aspect, the intervention program includes a lifestyle intervention program, a medication intervention program, a medical intervention program, a knowledge intervention program, and/or a financial intervention program.

A third aspect of the present invention provides a system for diagnosing and intervening gastrointestinal perforation. The system for diagnosing and intervening gastrointestinal perforation includes: the device for diagnosing gastrointestinal perforation according to any one of the first aspects of the present invention, which is used for diagnosing and intervening according to a user's health information A user's diagnosis report is generated; the digestive tract perforation intervention device according to any one of the second aspect of the present invention is connected to the digestive tract perforation diagnosis device, and is used for generating a user's intervention plan according to the user's diagnosis report.

As described above, a technical solution of the digestive tract perforation diagnostic device, intervention device and diagnostic intervention system of the present invention has the following beneficial effects:

The digestive tract perforation diagnosis device can obtain the health information of the user, obtain first disease information according to the health information of the user, and then generate a diagnosis report of the user according to the first disease information. According to the diagnosis report, the user can timely know whether he has gastrointestinal perforation, and then take corresponding treatment or intervention measures.

Description of drawings

FIG. 1 is a schematic structural diagram of the digestive tract perforation diagnostic device according to an embodiment of the present invention.

FIG. 2A is an exemplary diagram of a correlation model of the digestive tract perforation diagnostic apparatus according to an embodiment of the present invention.

FIG. 2B is an exemplary diagram of another correlation model of the digestive tract perforation diagnostic apparatus according to an embodiment of the present invention.

FIG. 3 is a schematic structural diagram of a health information acquisition module in a specific embodiment of the digestive tract perforation diagnostic apparatus according to the present invention.

FIG. 4 shows a flow chart of obtaining the health information of a user in a specific embodiment of the apparatus for diagnosing perforation of the digestive tract according to the present invention.

FIG. 5A is a schematic structural diagram of a self-test template updating unit in a specific embodiment of the digestive tract perforation diagnostic apparatus according to the present invention.

FIG. 5B is a diagram showing the correlation of health information in a specific embodiment of the digestive tract perforation diagnostic device of the present invention.

FIG. 6 is an exemplary diagram of a self-test template in a specific embodiment of the digestive tract perforation diagnostic device of the present invention.

FIG. 7 is a schematic structural diagram of a disease diagnosis module in a specific embodiment of the digestive tract perforation diagnosis device of the present invention.

FIG. 8A shows another schematic structural diagram of a disease diagnosis module in a specific embodiment of the digestive tract perforation diagnosis device of the present invention.

FIG. 8B shows a flow chart of acquiring training data in an embodiment of the digestive tract perforation diagnostic apparatus of the present invention.

FIG. 9 is a schematic diagram of the mechanism of the digestive tract perforation intervention device in a specific embodiment of the present invention.

Component label description

1 Digestive tract perforation diagnostic device

11 Health information acquisition module

111 Self-test template generation unit

112 Health Information Receiving Unit

113 Self-test template update unit

1131 Prompt information acquisition subunit

1132 Priority get subunit

1133 Template update subunit

12 Disease information acquisition module

13 Disease diagnosis module

131 Weight calculation unit

132 Probability calculation unit

133 Training data acquisition unit

134 Neural network training unit

135 Neural Network Processing Unit

2 Association Model

6 Self-test template

61 Symptom alert label

62 Indicator prompt label

63 File Alert Tab

9 Digestive tract perforation intervention device

91 Diagnosis report acquisition module

92 Intervention program generation module

Steps S41～S47

Steps S81～S83

Detailed ways

The embodiments of the present invention are described below through specific specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments may be combined with each other under the condition of no conflict.

It should be noted that the drawings provided in the following embodiments are only to illustrate the basic concept of the present invention in a schematic way, and the drawings only show the components related to the present invention rather than the number, shape and size of the components in actual implementation. For drawing, the type, quantity and proportion of each component can be arbitrarily changed during actual implementation, and the layout of components may also be more complicated. Furthermore, herein, relational terms such as "first," "second," etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply those entities or that there is any such actual relationship or sequence between operations.

In real life, due to the lack of medical knowledge, people's understanding of digestive tract perforation is generally insufficient, which makes it difficult for users to obtain the information that they have digestive tract perforation in time at the early stage of the disease. Often, when the perforation of the digestive tract occurs and causes physical discomfort, the user will find out that he has a perforation of the digestive tract only after going to the hospital for examination, which will not only increase the pain of the user, but also be detrimental to the early intervention and treatment of the perforation of the digestive tract. In response to this problem, the present invention provides an apparatus for diagnosing perforation of the digestive tract, which can acquire the health information of the user, obtain first disease information according to the health information of the user, and then obtain the first disease information according to the first disease information. Generate diagnostic reports for users. According to the diagnosis report, the user can timely know whether he has gastrointestinal perforation, and then take corresponding treatment or intervention measures.

Referring to FIG. 1 , in an embodiment of the present invention, the digestive tract perforation diagnosis device 1 includes a health information acquisition module 11 , a disease information acquisition module 12 and a disease diagnosis module 13 .

The health information acquisition module 11 is configured to acquire the user's health information, where the user's health information refers to information related to the user's health status, such as gender, age, body temperature, blood pressure, and the like.

The disease information obtaining module 12 is connected to the health information obtaining module 11, and is used for obtaining the user's disease information according to the user's health information, and obtaining the first disease information according to the user's disease information and an association model. The first disease information refers to disease information associated with gastrointestinal perforation in the user's disease information. The association model includes a variety of diseases, including perforation of the digestive tract, and disease information associated with each disease. In a specific application, the association model may be stored in a local storage, or may be stored in a remote server. The disease information obtains disease information associated with gastrointestinal perforation according to the association model, and the intersection between the user's disease information and the disease information associated with the gastrointestinal perforation is the first disease information.

The disease diagnosis module 13 is connected to the disease information acquisition module 12, and is configured to generate a user's diagnosis report according to the first disease information. The user's diagnosis report includes information about the user related to gastrointestinal perforation, such as the probability of the user suffering from gastrointestinal perforation, symptoms, and causes of the disease.

According to the above description, the digestive tract perforation diagnosis apparatus 1 in this embodiment can obtain the user's health information, obtain the first disease information according to the user's health information, and then generate the user's diagnosis report according to the first disease information. According to the diagnosis report, the user can timely know whether he has gastrointestinal perforation, and then take corresponding treatment or intervention measures.

In an embodiment of the present invention, the association model is shown in FIG. 2A . Wherein, the association model 2 includes disease 1, disease 2 and disease 3. In addition, the correlation model 2 also includes: symptoms and signs such as symptoms 1 to 6, inspection indicators such as indicators 1 to 4, and file-related information such as file information 1 and file information 2. Moreover, the association model 2 also defines an association relationship between the disease and the disease information.

Specifically, for any disease and any symptom and sign, if the disease causes the user to have the symptom and sign, it is considered that there is a relationship between the disease and the symptom and sign, and a straight line between the disease and the symptom and sign is used in the figure. Indicates the association relationship, for example: disease 1 and symptom 2 in the association model 2; if the disease does not cause the user to have the symptom and sign, it is considered that there is no association between the disease and the symptom and sign, for example: all the symptoms and signs Disease 1 and Symptom 3 in Association Model 2 above. Therefore, during the diagnosis process, if the user has the symptoms and signs, it can be considered that the user may have the disease according to the association relationship. For example, when a user has a cold, the user generally has fever symptoms, so there is a correlation between the cold disease and the fever symptoms; during the diagnosis process, when the user has fever symptoms, it can be considered that the user may have a cold.

For any disease and any inspection index, if the disease makes the inspection index abnormal, it is considered that there is a relationship between the disease and the inspection index. In the figure, the relationship between the disease and the inspection index is represented by a straight line. For example: disease 1 and index 1 in the association model 2; otherwise, it is considered that there is no association between the disease and the inspection index, for example: disease 1 and index 4 in the association model 2. Therefore, during the diagnosis process, if there is an abnormality in the check index of the user, it can be considered that the user may have the disease according to the association relationship. For example, high blood pressure will cause the user's blood pressure value to exceed the normal range, so there is a correlation between hypertension and blood pressure value indicators; during the diagnosis process, when the user's blood pressure value indicator is too high, it can be considered that the user may suffer from have high blood pressure.

For any disease and any file-related information, if the file-related information may cause the user to have the disease, it is considered that there is a relationship between the disease and the file-related information, and the straight line between the disease and file-related information in the figure represents the disease The association relationship, for example, the disease 1 and the file information 3 in the association model 2; otherwise, it is considered that there is no association relationship between the disease and the file-related information, for example, the disease 1 and the file information 1 in the association model 2. Therefore, in the process of diagnosis, if it is found that the user has information related to the profile, it can be considered that the user may suffer from the disease according to the association relationship. For example, a genetic history of heart disease increases the probability of a user having heart disease, so it can be assumed that there is a relationship between the information about the genetic history of heart disease and heart disease. During the diagnosis process, a user may be considered to have heart disease when the user has profile-related information about the genetic history of heart disease.

The association relationship is defined and updated by authoritative persons in related fields, or generated by artificial intelligence or big data technology. Preferably, in the association model, the disease includes at least one subtype, the symptoms and signs include at least one attribute, and the inspection index includes at least one classification. For example, for the symptom and sign of fever, the correlation model includes attributes such as low fever and high fever; for the inspection index of body temperature, the correlation model includes 36-37.2 ℃, 37.3-38 ℃, 38.1-40 ℃ and greater than 40 ℃ and other classification. The subtype refers to the combination of symptoms and signs, examination indicators, family inheritance, disease history, medication history, age and/or gender, etc., which can be used to judge the type of disease, for example: fever greater than 40°C plus white blood cell count Greater than 1000 can be used as one subtype, and fever greater than 37°C plus white blood cell count greater than 500 can be used as another subtype.

In particular, for perforation of the alimentary canal, the correlation model is shown in Figure 2B. Signs and symptoms associated with gastrointestinal perforation include abdominal pain, nausea, vomiting, fever, signs of peritoneal irritation (eg, abdominal muscle tension, abdominal tenderness, positive rebound tenderness), and reduction or disappearance of liver dullness. The inspection indicators associated with gastrointestinal perforation include the presence of free gas shadows in the abdominal cavity on the upright abdominal radiograph, and the presence of contrast medium overflow at the perforation of the gastrointestinal angiography. Dossier information associated with perforation of the gastrointestinal tract includes past history of foreign bodies entering the gastrointestinal tract, overeating, gastrointestinal cysts, gastrointestinal ulcers, etc., and includes coffee, NSAIDs, strong bases, strong acids, strong tea, etc. Used product.

In an embodiment of the present invention, the health information of the user includes symptom sub-information, index sub-information and/or file sub-information; the disease information is disease-centered, including symptoms and signs, examination indicators and/or file-related information. The disease information acquisition module 12 acquires the symptoms and signs according to the symptom sub-information, acquires the inspection index according to the index sub-information, and/or acquires the profile-related information according to the profile sub-information .

Specifically, the symptom sub-information includes the relevant symptoms and signs exhibited by the user's body or psychology, such as fever, dry cough, fatigue, difficulty breathing, etc. The user can determine the symptom sub-information based on his own physical performance. When the user's body shows a certain symptom and sign a, the user's health information records the symptom and sign in the form of symptom sub-information A, and at this time, the symptom sub-information A is associated with the symptom and sign a. For example, when the user has the symptom and sign of cough, the health information of the user includes the symptom sub-information of cough. It can be seen from this that when the health information of the user acquired by the health information acquisition module 11 includes symptom sub-information A, the disease information acquisition module 12 can acquire the symptoms and signs a associated therewith according to the symptom sub-information A and Added to the user's disease information.

The indicator sub-information includes physical indicators, which describe the physical condition of the user in a quantitative manner, such as blood pressure, body temperature, white blood cell count, hemoglobin, etc.; the user can obtain the indicator sub-information through corresponding medical equipment , the indicator sub-information can also be obtained by means of a hospital physical examination or the like. For example, when a user measures a blood pressure value through a sphygmomanometer, the user's health information records the blood pressure value in the form of index sub-information. The examination index in the disease information is associated with abnormal index sub-information, for example: hypertension in the examination index is associated with abnormal index sub-information of high blood pressure, and hypotension in the examination index is associated with low blood pressure. An abnormal indicator sub-information is associated. When the disease information obtaining module 12 obtains that there is a certain abnormal index sub-information B in the user's health information, the inspection index b associated with the abnormal index sub-information B is obtained and added to the user's disease information.

The profile sub-information includes relevant information in the user's health profile, such as gender, age, place of residence, disease history, genetic history, allergy history, medication history, and the like. The profile-related information in the disease information refers to profile sub-information that may cause the user to become ill. When the disease information acquisition module 12 finds that there is some profile sub-information C that may cause the user to be sick, the profile sub-information C is added to the user's disease information as profile-related information c.

In an embodiment of the present invention, the health information acquisition module 11 acquires symptom sub-information and/or indicator sub-information of the user according to the user's detection report and/or medical image.

Wherein, the test report refers to a report obtained by a user through a hospital or a medical examination institution, such as a blood test report, a urine test report, and the like. The health information acquisition module 11 can extract the relevant information in the detection report through OCR (Optical Character Recognition, Optical Character Recognition) and other technologies, and then supplement the relevant information into the user's health information, so that the health more comprehensive information.

The medical images are, for example, CT images, nuclear magnetic resonance images, and the like. The health information acquisition module 11 can use artificial intelligence and image recognition technology to process the medical image and extract the user information therein, and then supplement the user information to the user's health information. Using artificial intelligence and image recognition technology to process the medical image and extract information can be achieved through the existing technology, which will not be repeated here.

Optionally, the health information obtaining module 11 obtains the profile sub-information of the user according to the user's health profile.

Optionally, the health information receiving module 11 is further configured to receive the user's health information acquired by the health collection device. The health collection device can be a wearable device of the user, including watches supported by the wrist (including products such as watches and wristbands), shoes supported by the feet (including shoes, socks or other future wear on legs). products), Glass classes supported by the head (including glasses, helmets, headbands, etc.). The health collection device can also be a user's medical measurement device, such as a thermometer, a sphygmomanometer, a body fat scale, and the like. The health collection equipment may also be a medical examination equipment or related inspection equipment of a hospital or a medical examination institution, such as an X-ray machine, a CT machine, an electrocardiograph, and the like.

Referring to FIG. 3 , in an embodiment of the present invention, the health information acquisition module 11 includes a self-test template generating unit 111 , a health information receiving unit 112 and a self-test template updating unit 113 .

The self-test template generating unit 111 is used to generate a self-test template; the self-test template is used to prompt the user to input health information. The self-test template generated by the self-test template generating unit 111 is an initial self-test template.

The health information receiving unit 112 is connected to the self-test template generating unit 111, and is configured to receive the health information input by the user.

The self-test template updating unit 113 is connected to the self-test template generating unit 111 and the health information receiving unit 112, and is configured to update the self-test template according to the user's health information and the association model; The updated self-test template is used to prompt the user to continue entering health information. The health information of the user includes the health information input by the user and the health information obtained by the health information acquisition module 11 from a test report, a medical image and/or a health collection device.

Specifically, referring to FIG. 4 , the workflow of the health information obtaining module 11 obtaining the user's health information includes:

S41, the self-test template generating unit 111 generates an initial self-test template, and the user inputs health information according to the initial self-test template; wherein, the health information includes symptom sub-information, index sub-information and/or profile sub-information.

S42, the health information receiving unit 112 receives the health information input by the user.

S43, the self-test template updating unit 113 obtains the health information input by the user from the health information receiving unit 112, and obtains the relevant disease information according to the association relationship between the health information and the disease information. The relevant disease information refers to all disease information associated with the health information input by the user, including symptoms and signs, examination indicators and/or file-related information. The association relationship includes: symptoms and signs are associated with symptom sub-information, inspection indicators are associated with indicator sub-information, and profile-related information is associated with profile sub-information. For example, if the health information input by the user is a body temperature of 39°C, the disease information related to the health information is fever symptoms and an inspection index of a body temperature of 39°C.

S44, the self-assessment template updating unit 113 searches for related diseases in the association model according to the related disease information. The related disease refers to a disease associated with all or part of the disease information contained in the related disease information. For example, based on association model 2, when the related disease information is symptom 1, the related diseases are disease 1, disease 2 and disease 3; when the related disease information is symptom 1 and symptom 4, the related diseases are The relevant disease information is disease 2 and disease 3.

S45, the self-test template updating unit 113 acquires all disease information of the related diseases according to the association model, and acquires health information associated therewith according to all the disease information of the related diseases.

S46, the current self-test template is updated to obtain an updated self-test template; the updated self-test template is used to prompt the user to input the health information obtained in step S45.

S47, steps S42 to S46 are repeatedly performed until the health information obtaining module 11 obtains enough health information, or the user stops inputting health information.

According to the above description, this embodiment can provide a self-test template for the user to input health information, and update the self-test template according to the health information input by the user, so as to facilitate the user to complete the input of health information quickly and accurately.

Referring to FIG. 5A , in an embodiment of the present invention, the self-test template updating unit 113 includes a prompt information acquiring subunit 1131 , a priority acquiring subunit 1132 and a template updating subunit 1133 .

The prompt information obtaining subunit 1131 is connected to the health information receiving unit 112, and is configured to obtain the information to be prompted according to the currently obtained health information of the user. The currently obtained health information of the user may include all health information received by the health information receiving unit 112, and may also include health information obtained from test reports, medical images and/or health collection devices.

Specifically, the prompt information obtaining subunit 1131 obtains the association between multiple pieces of health information, and the association can be represented by the association diagram shown in FIG. 5B . The association between the multiple pieces of health information can be obtained through statistics. For example, if the health information of 900 patients includes both health information 1 and health information 2 among 1,000 patients, it means that health information 1 and health information 2 are There is an association between health information 2. Alternatively, the association between the multiple pieces of health information may be defined according to known medical knowledge. For example, if fever is commonly accompanied by cough, it means that there is an association between fever and cough.

The prompt information obtaining subunit 1131 obtains all the health information associated with I according to the currently obtained user's health information I, and deletes the currently obtained user's health information therefrom, as the information to be prompted.

The priority obtaining subunit 1132 is connected to the prompt information obtaining subunit 1131, and is used for obtaining the priority of each of the information to be prompted. Specifically, the priority obtaining subunit 1132 separately calculates the weight value of each piece of health information in the information to be prompted, and obtains the priority of each piece of information to be prompted according to the weight value. For any health information A in the information to be prompted, the calculation method of its weight value R(A) is:

Among them, p _A represents the probability that the user will continue to input other health information after inputting the last piece of health information. This value can be obtained by counting the input of multiple users, and its value range is 0 to 1; N is the association with health information A. The number of all health information; R(B _i ) represents the weight value of the i-th health information B _i associated with health information A, and Num(B _i ) represents the number of all health information associated with health information B _i . In a specific application, the weight value of each health information in the information to be prompted can be set to 1, and the weight value of each health information can be updated in the form of one or more iterations; wherein, each iteration A value of R(A) will be obtained, and the specific number of iterations can be set according to actual needs. After the iteration is completed, the weight value R(A) of the health information A is the priority of the health information A.

Next, the above process will be described in detail through an example. If the currently obtained health information I of the user includes health information 1 and health information 2, according to the correlation diagram shown in FIG. 5B , it can be known that the information to be prompted includes health information 3, health information 4 and health information 6.

In the first iteration process, let the weight value of all health information be 1, and take p _A =0.5, then the weight value of health information 3 is

The weight of health information 4 is

The weight of health information 6 is

Based on this iteration, the updated health template can prompt the user to input health information 3, health information 4 and health information 6, and the priority of the prompt is: health information 4>health information 6>health information 3.

It should be noted that, in specific applications, the weight value of each health information can also be recalculated according to the weight value obtained after the first iteration to complete the second iteration, and the user can be determined according to the weight value obtained after the second iteration. Priority for prompting. Further, a third iteration can be performed on the basis of the second iteration, and so on. In this process, the more iterations, the more accurate the calculation of the priority, but it will increase the amount of calculation.

The template updating subunit 1133 is connected to the prompt information obtaining subunit 1131 and the priority obtaining subunit 1132, and is used for updating the self-test template according to the information to be prompted and its priority. For example, the updated self-test template prompts the user to input all the health information contained in the information to be prompted, and preferentially prompts the health information with high priority.

In an embodiment of the present invention, the self-test template prompts the user to input the information to be prompted in the form of an information prompt label. For example, if the current information to be prompted includes symptom 1-symptom 5, indicator 1-indicator 3, profile information 1 and profile information 3, the self-test template is shown in FIG. 6, wherein the self-test template 6 includes Symptom prompt label 61 , indicator prompt label 62 , and profile prompt label 63 . Preferably, the display order of the information prompt labels is determined by the priority of the information to be prompted corresponding to each prompt label.

Since the health information input by the user according to the self-assessment template often contains non-standardized words such as colloquialism and colloquialism, it is difficult for the disease information acquisition module to obtain the user's disease information according to such non-standardized words. To solve this problem, in an embodiment of the present invention, the health information receiving unit 112 is further configured to standardize the health information input by the user according to a medical standard vocabulary. Wherein, the medical standard word database is established and maintained by authoritative medical personnel, and includes commonly used symptom sub-information standard words, index sub-information standard words and file sub-information standard words. In this embodiment, when the health information input by the user does not belong to the medical standard vocabulary database, the health information receiving unit 112 uses NLP (Natural Language Processing, natural language processing) and other technologies to convert it into the medical standard vocabulary standard words in the library to improve the standardization of the user's health information.

In an embodiment of the present invention, the diagnosis report of the user includes the probability that the user suffers from perforation of the digestive tract. Referring to FIG. 7 , the disease diagnosis module 13 in this embodiment includes a weight value calculation unit 131 and a probability calculation unit 132 .

The weight value calculation unit 131 is connected to the disease information acquisition module 12, and is configured to calculate the weight value of each of the first disease information according to the association model. Specifically, for any first disease information m, its weight value W _m in digestive tract perforation disease is:

Wherein, N _m is the number of all diseases associated with the first disease information m; for example, in the association model 2, the number of all diseases associated with index 3 is 2, and all diseases associated with symptom 1 The number of diseases is 3. Ni is the number of all diseases associated with the first disease information _i ; M is the number of all disease information associated with digestive tract perforation diseases. The above parameters N _m , _Ni and M can all be obtained from the correlation model.

The disease information associated with gastrointestinal perforation is determined by the association model. According to the association model, if the user's disease information includes all disease information associated with gastrointestinal perforation, the probability that the user suffers from gastrointestinal perforation is considered is 100%.

The probability calculation unit 132 is connected to the weight value calculation unit 131, and is configured to calculate the probability of the user suffering from digestive tract perforation according to the weight value of each of the first disease information. Specifically, if the set of all the first disease information is Q, the probability P of the user suffering from perforation of the digestive tract is:

represents the sum of the weight values of all the first disease information, and W _j represents the weight value of the first disease information j in the digestive tract perforation disease.

Next, on the basis of the correlation model 2, the above calculation process of the disease probability will be introduced through a specific example. In the correlation model 2, if the disease 1 is perforation of the digestive tract, based on the correlation model 2, it can be known that the disease information associated with perforation of the digestive tract includes: symptom 1 (named disease information 1), all related Number of diseases N ₁ =3; symptom 2 (named disease information 2), number N ₂ of all diseases associated with it; symptom 5 (named disease information 3), number N of all diseases associated with it ₃ = 1; indicator 1 (named disease information 4), the number of all diseases associated with it N ₄ =2; indicator 2 (named disease information 5), the number of all diseases associated with it N ₅ =1; Index 3 (named disease information 6 ), number N ₆ =2 of all diseases associated with it; profile information 3 (named disease information 7 ), number N ₇ =2 of all diseases associated with it.

If the set Q composed of the first disease information includes: symptom 1 (disease information 1), symptom 2 (disease information 2) and index 3 (disease information 6), then:

The weight of disease information 1 is:

The weight of disease information 2 is:

The weight of disease information 6 is:

Therefore, the probability that the user suffers from perforation of the digestive tract P=W ₁ +W ₂ +W ₆ =34.5%.

In an embodiment of the present invention, the diagnosis report of the user includes the probability that the user suffers from perforation of the digestive tract. Referring to FIG. 8A , the disease diagnosis module 13 includes a training data acquisition unit 133 , a neural network training unit 134 and a neural network processing unit 135 .

The training data obtaining unit 133 is used for obtaining training data. Preferably, the training data includes first training data and second training data. The first training data refers to the training data generated according to the correlation model, and is theoretical data constructed by artificial means. The second training data refers to the training data obtained from the actual detection case database, and the diagnosis case database contains a large number of real diagnosis cases; the real diagnosis cases include but are not limited to online consultation cases and offline diagnosis cases. cases, therefore, the second training data is actual data obtained from real cases in actual diagnosis. The training data acquisition unit 133 mixes the above two types of training data according to different mixing ratios, so as to realize the combination of theoretical data and actual data, so as to ensure the accuracy and practicability of the probability calculation neural network model.

The neural network training unit 134 is connected to the training data acquisition unit 133, and is configured to use the training data to train a neural network model to obtain a probability calculation neural network model. The method for training the neural network model by using the training data can be implemented by using the existing gradient descent method, the conjugate gradient method, etc., which will not be repeated here.

The neural network processing unit 135 is connected with the neural network training unit 134 and the disease information acquisition module 12, and is used to process the first disease information by using the probability calculation neural network model to obtain information about the user suffering from the disease. Probability of gastrointestinal perforation. Specifically, the first disease information is input into the probability calculation neural network model, and the output of the probability calculation neural network model is the probability that the user suffers from digestive tract perforation.

Referring to FIG. 8B , the implementation method for obtaining the first training data in this embodiment includes:

S81. Acquire all disease information associated with digestive tract perforation according to the correlation model. For example, in the correlation model 2, if disease 1 is perforation of the digestive tract, all disease information associated with perforation of the digestive tract includes symptom 1, symptom 2, symptom 5, index 1, index 2, index 3 and profile information 3.

S82, combine the disease information obtained in step S81 to obtain different disease information combinations. Specifically, according to the concept of arrangement and combination in mathematics, multiple disease information combinations are selected from all disease information, wherein the disease information contained in each disease information combination is different. For example, if all disease information obtained in step S81 includes disease information 1, disease information 2 and disease information 3, then a combination of disease information obtained in step S82 may be disease information 1, or disease information 1 and disease information 2 , it can also be disease information 2 and disease information 3, and so on. For digestive tract perforation, the maximum number of disease information combinations that can be acquired in step S82 is 2 ^M −1; where M is the number of all disease information associated with digestive tract perforation.

S83, calculate the probability of disease corresponding to each combination of the disease information; the probability of disease may be implemented by the weight calculation unit 131 and the probability calculation unit 132, or may be implemented by other methods, which are not limited here. Each combination of the disease information and its corresponding disease probability is the first training data.

In an embodiment of the present invention, the digestive tract perforation diagnosis device further includes an early warning module; the early warning module generates early warning information according to the probability that the user suffers from digestive tract perforation. Specifically, the range between 0 and 1 can be divided into two or more intervals according to actual needs, each interval corresponds to a different risk degree, and the user is judged according to the interval in which the probability of the user suffering from digestive tract perforation is located. The risk level of the disease, and then trigger the corresponding level of early warning information. The warning information may be sent to the user and/or the user's family doctor.

The invention also provides an intervention device for perforation of the digestive tract. Referring to FIG. 9 , in an embodiment of the present invention, the digestive tract perforation intervention device 9 includes a diagnosis report acquisition module 91 and an intervention plan generation module 92 .

The diagnostic report obtaining module 91 is used to obtain a user's diagnostic report. In a specific application, the diagnosis report obtaining module 91 may obtain the user's diagnosis report from an external device or server, or may generate the user's diagnosis report by itself. Preferably, the user's diagnosis report includes the probability that the user suffers from perforation of the digestive tract.

The intervention plan generation module 92 is connected to the diagnosis report acquisition module 91, and is configured to generate a user's intervention plan according to the user's diagnosis report.

Optionally, the intervention scheme includes a lifestyle habit intervention scheme, a medication intervention scheme, a medical intervention scheme, a knowledge intervention scheme and/or a financial intervention scheme.

The living habit intervention scheme refers to an intervention scheme related to the user's living habit and associated with perforation of the digestive tract. The living habit intervention plan includes, for example: do not eat too fast, avoid eating rough, too cold, hot and irritating food, quit smoking, alcohol and the like. The lifestyle intervention scheme is applicable regardless of the probability of the user suffering from perforation of the digestive tract.

The drug intervention scheme includes medication recommendation, medication guidance, etc., and is used when the probability of the user suffering from perforation of the digestive tract is greater than the first threshold. Wherein, the first threshold is an empirical value, and its value can be set according to actual requirements.

The medical intervention plan includes recommendations of medical departments, diseases, hospitals, etc., and is used when the probability of the user suffering from perforation of the digestive tract is greater than the second threshold. The second threshold is also an empirical value, and its value can be set according to actual requirements.

The knowledge intervention scheme is used to provide users with knowledge and/or popular science information about perforation of the digestive tract. The knowledge intervention protocol applies regardless of the probability that the user suffers from a perforation of the digestive tract.

The financial intervention plan includes one or more financial intervention measures, and the financial intervention measures are used to provide the user with a financial plan related to the relevant disease or the user's health status, including but not limited to wealth management purchases, insurance purchases, etc. . The financial intervention protocol applies regardless of the probability that the user suffers from a perforation of the digestive tract.

Based on the above description of the digestive tract perforation diagnostic device and the digestive tract perforation intervention device, the present invention also provides a digestive tract perforation diagnosis and intervention system. The digestive tract perforation diagnosis and intervention system includes the digestive tract perforation diagnosis device shown in FIG. 1 and the digestive tract perforation intervention device shown in FIG. 9 . Wherein, the digestive tract perforation diagnosis device is used to generate a user's diagnosis report according to the user's health information, and the digestive tract perforation intervention device is connected to the digestive tract perforation diagnosis device by wired or wireless communication, and is used for according to the The user's diagnostic report generates the user's intervention plan.

The digestive tract perforation diagnosis and intervention system can be deployed on a user's smart terminal, or can be deployed on a remote server. The digestive tract perforation diagnostic device and the digestive tract perforation intervention device in the digestive tract perforation diagnosis and intervention system may be located in the same set of electronic equipment, or may be located in two different sets of electronic equipment respectively.

The digestive tract perforation diagnosis device of the present invention can obtain the health information of the user, obtain the first disease information according to the health information of the user, and then generate a diagnosis report of the user according to the first disease information. According to the diagnosis report, the user can timely know whether he has gastrointestinal perforation, and then take corresponding treatment or intervention measures.

To sum up, the present invention effectively overcomes various shortcomings in the prior art and has high industrial utilization value.

The above-mentioned embodiments merely illustrate the principles and effects of the present invention, but are not intended to limit the present invention. Anyone skilled in the art can make modifications or changes to the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or changes made by those with ordinary knowledge in the technical field without departing from the spirit and technical idea disclosed in the present invention should still be covered by the claims of the present invention.

Claims

A digestive tract perforation diagnostic device, characterized in that the digestive tract perforation diagnostic device comprises:

The health information acquisition module is used to obtain the user's health information;

a disease information acquisition module, connected to the health information acquisition module, for acquiring the user's disease information according to the user's health information, and acquiring the first disease information according to the user's disease information and an association model; The first disease information refers to disease information associated with gastrointestinal perforation in the user's disease information; the association model includes multiple diseases and disease information associated with each disease, and the multiple diseases include gastrointestinal perforation ;

A disease diagnosis module, connected with the disease information acquisition module, is used for generating a diagnosis report of the user according to the first disease information.
The digestive tract perforation diagnostic device according to claim 1, wherein: the health information of the user includes symptom sub-information, index sub-information and/or profile sub-information; the disease information includes symptoms and signs, examination indexes and/or or file-related information; the disease information acquisition module obtains the symptoms and signs according to the symptom sub-information, obtains the inspection index according to the index sub-information, and/or obtains the file-related information according to the file sub-information .
The digestive tract perforation diagnostic device according to claim 2, wherein:

The health information acquisition module acquires the user's symptom sub-information and/or index sub-information according to the user's detection report and/or medical image; and/or

The health information acquisition module acquires the profile sub-information of the user according to the user's health profile.
The digestive tract perforation diagnostic device according to claim 1, wherein the health information acquisition module comprises:

The self-test template generating unit is used to generate a self-test template; the self-test template is used to prompt the user to input health information;

a health information receiving unit, connected to the self-test template generating unit, for receiving health information input by a user;

The self-test template updating unit is connected to the self-test template generating unit and the health information receiving unit, and is used for updating the self-test template according to the user's health information and the association model; The test template is used to prompt the user to continue entering health information.
The digestive tract perforation diagnostic device according to claim 4, wherein the self-test template updating unit comprises:

a prompt information obtaining subunit, connected to the health information receiving unit, and configured to obtain the information to be prompted according to the currently obtained health information of the user;

a priority obtaining subunit, connected to the prompt information obtaining subunit, and used for obtaining the priority of each of the information to be prompted;

The template updating subunit is connected to the prompt information acquiring subunit and the priority acquiring subunit, and is used for updating the self-test template according to the information to be prompted and its priority.
The device for diagnosing gastrointestinal perforation according to claim 5, wherein the self-test template prompts the user to input the information to be prompted in the form of an information prompt label.
The digestive tract perforation diagnosis device according to claim 4, wherein the health information receiving unit is further configured to standardize the health information input by the user according to a medical standard vocabulary.
The device for diagnosing gastrointestinal perforation according to claim 1, wherein the user's diagnosis report includes a probability that the user suffers from gastrointestinal perforation; and the disease diagnosis module comprises:

a weight value calculation unit, connected to the disease information acquisition module, and configured to calculate the weight value of each of the first disease information according to the association model;

The probability calculation unit is connected to the weight value calculation unit, and is configured to calculate the probability of the user suffering from digestive tract perforation according to the weight value of each of the first disease information.
The device for diagnosing gastrointestinal perforation according to claim 1, wherein the user's diagnosis report includes a probability that the user suffers from gastrointestinal perforation; and the disease diagnosis module comprises:

A training data acquisition unit for acquiring training data;

a neural network training unit, connected with the training data acquisition unit, for training a neural network model by using the training data to obtain a probability calculation neural network model;

A neural network processing unit, connected with the neural network training unit and the disease information acquisition module, is used to process the first disease information by using the probability calculation neural network model to obtain the user suffering from digestive tract perforation. probability.
The digestive tract perforation diagnosis device according to claim 9, wherein: the training data comprises first training data and second training data; the first training data refers to the training data generated according to the correlation model, The second training data refers to the training data obtained from the actual detection case database.
The digestive tract perforation diagnosis device according to any one of claims 8-10, wherein the digestive tract perforation diagnosis device further comprises an early warning module; the early warning module generates early warning information according to the probability that the user suffers from digestive tract perforation .
A digestive tract perforation intervention device, characterized in that the digestive tract perforation intervention device comprises:

The diagnostic report acquisition module is used to acquire the user's diagnostic report;

An intervention plan generation module is connected to the diagnosis report acquisition module, and is used for generating a user's intervention plan according to the user's diagnosis report.
The digestive tract perforation intervention device according to claim 12, wherein the intervention program includes a lifestyle habit intervention program, a medication intervention program, a medical intervention program, a knowledge intervention program, and/or a financial intervention program.
A digestive tract perforation diagnosis and intervention system, characterized in that the digestive tract perforation diagnosis and intervention system comprises:

The digestive tract perforation diagnostic device according to any one of claims 1-11, which is used for generating a user's diagnosis report according to the user's health information;

The digestive tract perforation intervention device according to claim 12 or 13, connected to the digestive tract perforation diagnosis device, and used for generating a user's intervention plan according to the user's diagnosis report.