CN113140323A - Health portrait generation method, system, medium and server - Google Patents
Health portrait generation method, system, medium and server Download PDFInfo
- Publication number
- CN113140323A CN113140323A CN202011634158.6A CN202011634158A CN113140323A CN 113140323 A CN113140323 A CN 113140323A CN 202011634158 A CN202011634158 A CN 202011634158A CN 113140323 A CN113140323 A CN 113140323A
- Authority
- CN
- China
- Prior art keywords
- user
- health
- information
- acquiring
- risk
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Abstract
The invention provides a health portrait generation method, a health portrait generation system, a health portrait generation medium and a server. The health portrait generation method comprises the following steps: acquiring basic information of a user to generate a functional label of the health portrait of the user; acquiring abnormal information of a user to generate a state label of the health portrait of the user; acquiring health risk factors of a user to generate a risk label of a health portrait of the user; and generating the health portrait of the user according to the function label, the state label and the risk label of the health portrait of the user. The user can intuitively and comprehensively know the health condition of the user through the health portrait.
Description
Technical Field
The invention belongs to the field of medical care informatics, relates to a health portrait generation method, and particularly relates to a health portrait generation method, a health portrait generation system, a health portrait generation medium and a server.
Background
With the increase of health consciousness, people pay more attention to their health conditions. However, it is difficult for the general population to fully understand their health status because they often do not have enough medical knowledge. Therefore, how to show the health condition of the user to the user in an intuitive and comprehensive manner becomes one of the technical problems that the related technical personnel need to solve urgently.
Disclosure of Invention
In view of the above-mentioned shortcomings of the prior art, an object of the present invention is to provide a method, a system, a medium and a server for generating a health representation, which are used to solve the problem that it is difficult to intuitively and comprehensively show the health status of a user to the user in the prior art.
To achieve the above and other related objects, a first aspect of the present invention provides a health image generating method; the health portrait generation method comprises the following steps: acquiring basic information of a user to generate a functional label of the health portrait of the user; acquiring abnormal information of a user to generate a state label of the health portrait of the user; acquiring health risk factors of a user to generate a risk label of a health portrait of the user; and generating the health portrait of the user according to the function label, the state label and the risk label of the health portrait of the user.
In an embodiment of the first aspect, the method for acquiring the basic information, the abnormal information, and/or the health risk factors of the user includes: acquiring a health file of a user; and acquiring basic information, abnormal information and/or health risk factors of the user according to the health record of the user.
In an embodiment of the first aspect, the method for acquiring the health profile of the user includes: generating a health file template, wherein the health file template is used for prompting a user to input file information; acquiring archive information input by a user; and generating the health record of the user according to the record information input by the user.
In an embodiment of the first aspect, the health profile template includes a profile prompt tab, and the user selects the corresponding profile prompt tab to input the profile information.
In an embodiment of the first aspect, the method for acquiring the health profile of the user further includes: and carrying out standardization processing on the archive information input by the user.
In an embodiment of the first aspect, the method for generating a health representation further includes: acquiring a health risk score of the user according to the health risk factors of the user; and acquiring an attack risk value of the user within a future period of time according to the health risk score of the user.
In an embodiment of the first aspect, the health risk score of the user includes a health risk score of the user in a current state and/or a health risk score of the user in an ideal state.
In an embodiment of the first aspect, an implementation method for obtaining a health risk score of a user according to a health risk factor of the user includes: layering the health risk factors of the user to obtain layered assignments corresponding to the risk factors; and acquiring the health risk score of the user according to the hierarchical assignment and the coefficient corresponding to each risk factor.
In an embodiment of the first aspect, the health risk factors of the user include gender, age, family genetic history, abnormal health indicators and/or bad lifestyle habits.
A second aspect of the present invention provides a health representation generation system, comprising: the basic information acquisition module is used for acquiring basic information of a user to generate a functional label of the user health portrait; the abnormal information acquisition module is used for acquiring the abnormal information of the user to generate a state label of the health portrait of the user; the risk factor acquisition module is used for acquiring health risk factors of the user to generate a risk label of the health portrait of the user; and the health portrait generating module is connected with the basic information acquiring module, the abnormal information acquiring module and the risk factor acquiring module and is used for generating a health portrait of the user according to the function label, the state label and the risk label of the health portrait of the user.
A third aspect of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the health representation generation method of any of the first aspects of the present invention.
A fourth aspect of the present invention provides a server comprising: a memory storing a computer program; a processor, communicatively coupled to the memory, for executing the health representation generation method of the first aspect of the present invention when the computer program is invoked; and the display is in communication connection with the processor and the memory and is used for displaying a related GUI (graphical user interface) of the health portrait generation method.
As described above, the method, system, medium, and server for generating a health representation according to the present invention have the following advantages:
the health portrait generation method can acquire basic information of a user and generate a functional label, acquire abnormal information of the user and generate a state label, acquire health risk factors of the user and generate a risk label, and generate the health portrait of the user based on the functional label, the state label and the risk label. The user can intuitively and comprehensively know the health condition of the user through the health portrait.
Drawings
FIG. 1 is a flowchart illustrating a method for generating a health image according to an embodiment of the invention.
FIG. 2 is a flowchart illustrating key steps of a method for generating a health image according to an embodiment of the present invention.
FIG. 3A is a flowchart illustrating a step S21 of the health image generation method according to an embodiment of the present invention.
FIG. 3B is a diagram illustrating an exemplary health file template in an embodiment of the health profile generation method according to the present invention.
FIG. 4 is a flowchart illustrating a method for generating a health profile to obtain a risk value according to an embodiment of the present invention.
FIG. 5 is a flowchart illustrating a method for generating a health profile to obtain a health risk score according to an embodiment of the present invention.
FIG. 6A is a flowchart illustrating key steps of a method for generating a health representation according to an embodiment of the invention.
FIG. 6B is a flowchart illustrating a step S62 of the health image generation method according to an embodiment of the present invention.
FIG. 6C is a diagram illustrating an example of a correlation model in an embodiment of the method for generating a health representation of the present invention.
FIG. 7A is a flowchart illustrating a method for generating a health profile according to an embodiment of the invention for obtaining a disease probability.
FIG. 7B is a flowchart illustrating a method for generating a health profile according to an embodiment of the invention for obtaining a disease probability.
FIG. 7C is a flowchart illustrating the step S71 of the health image generation method according to an embodiment of the present invention.
FIG. 8 is a schematic diagram of a health image generation system according to an embodiment of the invention.
Fig. 9 is a schematic structural diagram of a server according to an embodiment of the invention.
Description of the element reference numerals
2 correlation model
8 health figure generation system
81 basic information acquisition module
82 abnormal information acquisition module
83 risk factor acquisition module
84 health portrait generation module
9 Server
91 memory
92 processor
93 display
S11-S14
S21-S22
S211 to S213 steps
S41-S42
Steps S411 to S412
S61-S62
S621-S623 steps
S71 a-S73 a
S71 b-S73 b
Steps S711 to S713
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the drawings only show the components related to the present invention rather than being drawn according to the number, shape and size of the components in actual implementation, and the type, number and proportion of the components in actual implementation may be changed arbitrarily, and the layout of the components may be more complicated. Moreover, in this document, relational terms such as "first," "second," and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.
For the general population, the general population often has insufficient medical knowledge, so that the health condition of the general population is difficult to understand. In order to solve the problem, the invention provides a health portrait generation method, which can acquire basic information of a user, generate a functional label, acquire abnormal information of the user, generate a state label, acquire health risk factors of the user, generate a risk label, and generate a health portrait of the user based on the functional label, the state label and the risk label, so that the user can intuitively and comprehensively know the health condition of the user through the health portrait.
Referring to fig. 1, in an embodiment of the invention, the method for generating a health image includes:
s11, acquiring basic information of the user to generate a function label of the user health portrait. The basic information of the user comprises the name, age, height and the like of the user, the basic information of the user is often relatively fixed in the medium and short term, and the user can hardly modify the basic information.
S12, obtaining abnormal information of the user to generate a state label of the health portrait of the user. The abnormal information of the user refers to potential risk factors which may cause harm to the health of the user, such as: the car is driven without a safety belt, a smoke alarm is not installed in a residence, smoking, alcoholism and the like. The user can reduce or even eliminate the abnormal information by adjusting the corresponding behavior pattern or living habits.
S13, the health risk factors of the user are obtained to generate the risk label of the health portrait of the user. The risk factors of the user include factors that may cause harm to the health of the user, such as: family genetic history of hypertension, obesity, hypertension, etc. Some of the health risk factors of the user are difficult to eliminate, such as family genetic history, and some risk factors can be reduced or even eliminated by means of treatment or health intervention, such as obesity and hypertension.
And S14, generating the health portrait of the user according to the function label, the state label and the risk label of the health portrait of the user. Preferably, the health portrait of the user highlights health risk factors and abnormal information of the user so as to remind the user of the abnormal information.
As can be seen from the above description, the health portrait generation method according to this embodiment can acquire basic information of a user and generate a function tag, acquire abnormal information of the user and generate a state tag, acquire a health risk factor of the user and generate a risk tag, and generate a health portrait of the user based on the function tag, the state tag, and the risk tag, so that the user can intuitively and comprehensively understand his/her health status through the health portrait.
Referring to fig. 2, in an embodiment of the present invention, an implementation method for acquiring basic information, abnormal information and/or health risk factors of a user includes:
and S21, acquiring the health file of the user. The health record is a file for systematically recording the health condition and development changes of the user, relevant factors influencing health and health-care service process, and mainly comprises the life habits, the past medical history, diagnosis and treatment conditions, family medical history, the physical examination results and other record sub-information of the user. The user's health profile may be created and updated and maintained by the user.
And S22, acquiring basic information, abnormal information and/or health risk factors of the user according to the health profile of the user. In particular, the basic information of the user may be directly obtained from the health profile of the user. The abnormal information of the user may be obtained by searching and analyzing a health profile of the user, for example, if the health profile of the user includes: the riding habit is that the safety belt is always fastened; work and rest conditions are irregular; through searching and analyzing, the abnormal information of the user, including irregular work and rest conditions, can be obtained. The health risk factors of the user can also be obtained by searching and analyzing the health record of the user, for example, if the health record of the user includes family history of heart disease, the health risk factors of the user including family history of heart disease can be obtained by searching and analyzing.
Referring to fig. 3A, in an embodiment of the present invention, an implementation method for acquiring a health file of a user includes:
s211, generating a health profile template, wherein the health profile template is used for prompting a user to input profile information. For example, the health profile template may prompt the user to enter corresponding profile information in the form of a drop-down list box, a check box, or the like.
S212, acquiring the file information input by the user. For example, the user may enter profile information by entering text, selecting a corresponding option, and the like.
S213, generating the health profile of the user according to the profile information input by the user. Specifically, step S213 may aggregate, classify, process, etc. the profile information input by the user to generate the health profile of the user.
In a specific application, if the health portrait generation method is executed through a user terminal, the user terminal directly generates the health archive template, acquires archive information input by a user, generates a health archive of the user and sends the health archive to a server. If the health portrait generation method is executed through the server, the server generates the health archive template and sends the health archive template to the user terminal, the user terminal receives archive information input by a user and sends the archive information to the server, and the server generates the health archive of the user according to the archive information input by the user.
Preferably, referring to fig. 3B, the health profile template includes a profile prompt tab, and the user can input the profile information by selecting the corresponding profile prompt tab. The file prompt tag can be a general tag or a personalized tag designed for each user. Specifically, step S211 first obtains the health information of the user, and generates the personalized tag according to the health information of the user. For example, if the health information of the user shows that the blood pressure value of the user is higher, the health profile of the user is likely to include information such as family history of hypertension, medication history of hypotensive drug, and less amount of exercise, and based on this, the health profile template generated in step S211 should include prompt tags such as family history of hypertension, medication history of hypotensive drug, and less amount of exercise, so that the user can conveniently and quickly complete the input of the profile information.
Since the profile information input by the user often contains non-standard words such as spoken language or colloquial language, this will affect the standardization of the health profile. To address this problem, in an embodiment of the present invention, the method for acquiring the health profile of the user further includes performing a standardization process on the profile information input by the user. Specifically, the profile information input by the user is matched with standard words in a medical standard word library, and the profile information input by the user is replaced by the matched standard words, so that the standardization processing can be realized. The medical standard word library is established and maintained for authoritative medical staff and comprises common file information standard words.
Referring to fig. 4, in an embodiment of the present invention, the method for generating a health image further includes:
s41, acquiring a health risk score of the user according to the health risk factors of the user; the health risk score is used to evaluate the likelihood of a user developing a health issue. Optionally, the health risk score includes a health risk score of the user in a current state, and/or a health risk score of the user in an ideal state. The health risk score of the user in the current state refers to a health risk score obtained under the condition that the abnormal information and the health risk factors of the user are kept unchanged. The health risk score of the user in an ideal state refers to the health risk score obtained after the user eliminates all possible eliminated abnormal information and health risk factors. For example, if the user has abnormal information of irregular work and rest, and has two health risk factors of hypertension genetic history and obesity, wherein the irregular work and rest and the obesity can be eliminated by adjusting living habits or adopting medical means; at this time, when calculating the health risk score of the user in the current state, the work and rest irregularity, the hypertension genetic history and the obesity need to be considered, and when calculating the health risk score of the user in the ideal state, the hypertension genetic history only needs to be considered.
And S42, acquiring an incidence risk value of the user in a future period of time according to the health risk score of the user. The future period of time is, for example, 1 year, 2 years, 4 years, etc. Specifically, a risk score-risk value comparison table can be created through means of statistics and the like; the comparison table comprises a plurality of health risk scores and disease risk values corresponding to the health risk scores in a future period of time. And obtaining the morbidity risk value of the user in a future period of time according to the health risk score of the user obtained in the step S41 and the comparison table. Table 1 shows an example of the risk score-risk value comparison table, and based on table 1, if the health risk score of the user obtained in step S42 is 65 scores, the occurrence risk values of the user in the next 1 year, 2 years and 4 years are 0.45, 0.48 and 0.56, respectively, according to the comparison table.
TABLE 1 Risk score-Risk value comparison Table
| Health risk score | Future 1 year incidence | Future | 2 years incidence risk value | Future 4 years incidence risk value |
| 50-60 | 0.42 | 0.46 | 0.53 | |
| 60-70 | 0.45 | 0.48 | 0.56 | |
| 70-80 | 0.52 | 0.58 | 0.66 |
In this embodiment, the health portrait of the user further includes a health risk score and an attack risk value of the user, and the user can obtain the attack risk value within a period of time in the future through the health portrait, so that the user can adjust the living habits in time and take corresponding preventive and/or intervention measures.
Referring to fig. 5, in an embodiment of the present invention, an implementation method for obtaining a health risk score of a user according to a health risk factor of the user includes:
s411, the health risk factors of the user are layered to obtain layered assignments corresponding to the risk factors. Specifically, each health risk factor may be divided into multiple layers according to the risk degree thereof in advance, and a hierarchical assignment may be set for each layer. Wherein the hierarchical assignment is related to the risk level of each layer and is used to reflect the risk level of the health risk factor contained in each layer. For example, for a layer with a lower degree of risk, its hierarchical assignment is smaller; and for the layer with higher risk degree, the hierarchical assignment is larger. In a specific application, for any user, step S411 sequentially divides each health risk factor of the user into corresponding layers, and obtains a hierarchical assignment of the corresponding layer as a hierarchical assignment of each health risk factor.
And S412, acquiring the health risk score of the user according to the hierarchical assignment and the coefficient corresponding to each risk factor. Specifically, the health risk score of the user is
Wherein R is the number of health risk factors of the user, betaiA coefficient of the ith risk factor for reflecting the contribution degree of the ith risk factor to the health risk score of the user, the coefficient can be preset according to an empirical value, ViAnd (4) assigning the ith risk factor to a hierarchical layer.
Referring to fig. 6A, in an embodiment of the present invention, the health image of the user further includes a prevalence probability of the user, and the method for generating the health image further includes:
and S61, acquiring the health information of the user, wherein the health information of the user comprises symptom sub-information, index sub-information and archive sub-information of the user.
The symptom sub-information includes relevant symptom signs physically or psychologically exhibited by the user, such as: fever, dry cough, hypodynamia, dyspnea and the like, and the user can determine the symptom sub-information through the physical expression of the user. When the body of the user shows a certain symptom, the health information of the user comprises corresponding symptom sub-information. For example, when a symptom sign of cough appears in the user, the health information of the user includes a symptom sub-information of cough.
The indicator sub-information includes physical indicators describing 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 index sub-information through corresponding medical equipment, and can also obtain the index sub-information through modes such as hospital physical examination and the like. Ideally, each time a user obtains a physical index, the health information of the user includes sub-information of the index corresponding to the physical index. For example, when a user measures a blood pressure value by a blood pressure meter, the health information of the user records the blood pressure value in the form of index sub-information.
The profile sub-information of the user refers to information contained in the health profile of the user, such as: sex, age, place of residence, history of disease, genetic history, history of allergy, history of medication, etc.
Some or all of the health information of the user may be obtained by a health collection device. The health capture device may be a wearable device for the user, including wrist-supported watches (including wrist watches and wrist bands), foot-supported shoes (including shoes, socks, or other leg wear products in the future), and head-supported glasses (including glasses, helmets, head bands, etc.). The health-gathering device may also be a medical measurement device of the user, such as: a thermometer, a sphygmomanometer, a body fat scale and the like. The health collection device may also be a medical examination device or a related examination device of a hospital or medical examination facility, such as: an X-ray machine, a CT machine, an electrocardiogram measuring instrument and the like.
The health information of the user may also include information obtained from a detection report and/or medical images of the user. Wherein, the detection report refers to a report sheet obtained by a user through a hospital or a physical examination institution, such as: blood test report, urine test report, etc. In a specific application, the relevant information in the detection report can be extracted and supplemented to the health information of the user through an OCR (Optical Character Recognition) technology and the like, so that the health information is more comprehensive. The medical image is, for example, a CT image, a magnetic resonance image, or the like. In specific application, the medical image can be processed by using artificial intelligence and an image recognition technology, user information in the medical image is extracted, and the user information is supplemented to health information of a user. Processing the medical image and extracting information by using artificial intelligence and image recognition technology can be realized by the prior art, and details are not repeated here.
And S62, acquiring the prevalence probability of the user according to the health information of the user, and adding the prevalence probability of the user to the health portrait of the user. Referring to fig. 6B, the implementation method for acquiring the prevalence probability of the user in the embodiment includes:
and S621, acquiring corresponding disease information according to the health information of the user. Wherein the disease information comprises symptom signs, examination indexes and/or profile-related information. The symptom sign corresponds to symptom sub-information of the user, the check index corresponds to index sub-information of the user, and the archive related information corresponds to archive sub-information of the user. For example, the symptom sub-information of the user may include fever sub-information, which corresponds to the symptom sign of fever of a disease; the index sub-information of the user comprises blood pressure high sub-information which corresponds to an abnormal index of high blood pressure of diseases; the profile sub-information of the user includes cardiac disease history information, which corresponds to the profile-related information of the cardiac disease history of the disease.
S622, relevant diseases of the user are obtained from a correlation model according to the disease information. Wherein the association model comprises a plurality of diseases and disease information; the disease information includes symptom signs, examination indices, and/or profile-related information. Wherein the profile-related information includes past history, used products, family inheritance and/or personal history, and the like. The association model takes diseases as a core and establishes association between each disease and corresponding disease information according to an association relation. Specifically, the method comprises the following steps:
when the disease information is a symptom sign, regarding any disease and any symptom sign, if the disease causes the symptom sign to appear on the user, the disease and the symptom sign are considered to have an association relationship; if the disease does not cause the symptom sign to appear in the user, the disease and the symptom sign are considered to have no association relation; therefore, in the diagnosis process, if the user has the symptom sign, the user can be considered to have the disease according to the association relationship. For example, patients commonly suffer from fever during cold, so that the cold diseases and the fever symptoms have an association relationship; in the diagnosis process, when a patient has fever, the patient may be considered to have a cold.
When the disease information is a check index, regarding any disease and any check index, if the disease causes the check index to be abnormal, the disease and the check index are considered to have a correlation, otherwise, the disease and the check index are considered to have no correlation; therefore, in the diagnosis process, if the examination index of the user is abnormal, the user can be considered to be possibly suffered from the disease according to the association relation. For example, hypertension may cause the blood pressure value of the patient to exceed the normal value range, so there is a correlation between hypertension disease and the blood pressure value index; in the diagnosis process, when the blood pressure value index of the patient is too high, the patient can be considered to have hypertension.
When the disease information is archive related information, regarding any disease and any archive related information, the archive related information may cause the user to have the disease, considering that the disease and the archive related information have an association relation, otherwise, considering that the disease and the archive related information do not have an association relation; therefore, in the diagnosis process, if the user is found to have the profile-related information, the user can be considered to have the disease according to the association relationship. For example, the genetic history of heart disease increases the probability that a patient will have heart disease, and thus it can be considered that there is a correlation between the information related to the file of the genetic history of heart disease and heart disease. In the diagnostic process, a patient is considered likely to have a heart disease when the patient has information about a file of the genetic history of the heart disease.
The incidence relation is defined and updated by authoritative medical staff in related fields or generated by artificial intelligence technology; wherein the authoritative medical personnel are, for example, academicians. As shown in fig. 6C, a representation of the association model 2 is shown, in which the association relationship between the disease and the disease information is represented by a straight line in the figure. For example: there was a correlation between disease 1 and symptom 2, and no correlation between index 4. In practical application, related diseases can be searched from the correlation model according to symptom signs, abnormal indexes and archive information of a user, and the disease probability of a certain disease is determined according to the correlation model, so that the diagnosis of the disease is completed.
Preferably, in the association model, the disease comprises at least one subtype, the symptom sign comprises at least one attribute, and the examination indicator comprises at least one classification. For example, for the symptom sign of fever, the correlation model includes attributes of low fever, high fever, and the like; for the body temperature, the correlation model comprises classifications of 36-37 ℃, 37.3-38 ℃, 38.1-40 ℃, more than 40 ℃ and the like. The subtype refers to a combination of symptom signs, examination index, familial inheritance, disease history, medication history, age and/or gender, etc., which can be used to determine the disease type, for example: fever greater than 40 ℃ plus white blood cell count greater than 1000 can be considered one subtype, fever greater than 37 ℃ plus white blood cell count greater than 500 can be considered another subtype. By subdividing the diseases, the symptom signs and the examination indexes in the association model, the embodiment can guide a user (especially a user lacking medical knowledge) to provide more detailed self-health information, and obtain an accurate health self-test result according to the more detailed self-health information.
Based on the association model, step S622 can find, from the association model, a disease associated with each piece of disease information as a related disease of the user. For example, in the association model 2, if the disease information includes symptom 2, symptom 3, symptom 5, and index 1, the related diseases of the user are disease 1 and disease 2.
And S623, acquiring the prevalence probability of each related disease. The incidence probability of the related diseases can be obtained according to the association model, or can be obtained by machine learning, which will be described in detail below.
Referring to fig. 7A, for any related disease i, the implementation method for obtaining the prevalence probability according to the association model includes:
s71a, obtaining the diagnosis standard C of the related disease ii. Wherein the diagnostic criteria CiIs defined as: and the sub information corresponding to all the disease information associated with the related disease i comprises symptom sub information, index sub information and archive sub information. The diagnosis standard of each related disease can be obtained through the correlation model, and if the health information of a certain user contains the diagnosis standard CiAll the sub-information of (a), the probability that the user has the related disease i can be considered as 100%. For example, in the correlation model 2, the diagnosis criteria for the disease 1 include symptom sub-information corresponding to the symptom 1, symptom sub-information corresponding to the symptom 2, symptom sub-information corresponding to the symptom 5, index sub-information corresponding to the index 1, index sub-information corresponding to the index 2, index sub-information corresponding to the index 3, and profile sub-information corresponding to the profile information 3.
S72a, acquiring a sub-information collection D in the health information of the user, wherein the sub-information collection D is a collection formed by all symptom sub-information, index sub-information and/or archive sub-information in the health information of the user.
S73a, obtaining the diagnosis standard CiAnd the intersection Q of the sub information collection D, and calculating the disease probability P of the related disease i according to the sub information in the intersection Qi. In particular, the amount of the solvent to be used,
representing all sub-information contained in said intersection QThe sum of the weights; wherein, WjRepresents the weight of the sub information j, and
m is a positive integer representing the diagnostic criterion CiThe number of neutron information, and j is less than or equal to M; n is a radical ofmRepresenting the number of diseases associated with the sub-information m, NjRepresenting the number of diseases associated with the sub information j.
Next, the above-mentioned prevalence probability calculation process will be described with a specific example based on the association model 2. The diagnosis criteria C of the disease 1 can be found from the correlation model 21The method comprises the following steps: symptom subinformation 1, symptom subinformation 2, and symptom subinformation 5 corresponding to symptom 1, symptom 2, and symptom 5, respectively; index sub information 1, index sub information 2, and index sub information 3 corresponding to index 1, index 2, and index 3, respectively; archive sub information 3 corresponding to the archive information 3. At this time, M is 7.
According to the correlation model 2, the number of diseases N associated with the symptom sub-information 1 (named as sub-information 1) is known1Number of diseases N associated with symptom sub-information 2 (named sub-information 2) at 32The number of diseases associated with symptom sub-information 5 (named sub-information 3) is N as 13Number of diseases N associated with index subinformation 1 (named subinformation 4) 14Number of diseases N associated with index sub-information 2 (named sub-information 5) 25Number of diseases N associated with index sub-information 3 (named sub-information 6) is 16Number of diseases N associated with archive sub-information 3 (named sub-information 7) ═ 37＝2。
If the sub-information collection D in the health information of the user comprises: symptom sub-information 1, symptom sub-information 2, symptom sub-information 6, and index sub-information 3. At this time, the diagnostic criteria CiAnd the intersection Q of the sub-information collection D comprises: symptom sub information 1 (sub information 1), symptom sub information 2 (sub information 2), and index sub information 3 (sub information 6). For Q, it contains sub information 1, sub information 2, and sub information 3, and:
the weight of the sub information 1 is:
the weight of the sub information 2 is:
the weight of the sub information 6 is:
thus, the probability P that the user has disease 11＝W1+W2+W3＝35.6％。
In addition, in this embodiment, for the health information of the same user, the disease probability of multiple diseases can be obtained in the manner described in S71 a-S73 a, and one disease with the highest disease probability is selected as the disease that the user is most likely to suffer from.
Referring to fig. 7B, an implementation method for obtaining the prevalence probability of the related disease by machine learning includes:
s71b, acquiring training data; the training data is derived from the correlation model and the diagnostic case database, namely: the training data includes two types, one from the correlation model and the other from the diagnostic case database. The diagnostic case database contains a plurality of real diagnostic cases; the real diagnosis cases include, but are not limited to, on-line inquiry cases and off-line diagnosis cases. In the step, the two types of training data are mixed according to different mixing proportions, so that theoretical data and actual data can be combined, and the accuracy and the practicability of the probability calculation neural network model are ensured.
S72b, training a neural network model by using the training data to obtain a trained probability calculation neural network model; the training of the neural network model by using the training data can be realized by using the existing training method, which is not described herein again.
And S73b, processing the user disease information by using the probability calculation neural network model to obtain the disease probability of the related diseases. Specifically, the user disease information is used as the input of the probability calculation neural network model, and the output of the probability calculation neural network model is the disease probability of the related diseases.
Optionally, in this embodiment, in step S72b, the training data may be obtained only according to disease information and diagnosis cases associated with one related disease, and at this time, the probability-calculating neural network model can obtain the prevalence probability of the one related disease.
Optionally, in this embodiment, in step S72b, the training data may be obtained according to disease information and diagnosis cases related to a plurality of related diseases, and at this time, the probability-calculating neural network model may obtain the probability of suffering from the plurality of related diseases at the same time.
As can be seen from the above description, in this embodiment, in step S71b, the training data of the diagnosis case database is selected as the first type of training data, and the second type of training data is generated according to the association model. The first type of training data is data collected in actual diagnosis, and the second type of training data is data derived theoretically. On the basis, the S71b combines the first type of training data and the second type of training data according to a mixing proportion, so that the probability calculation neural network model has higher accuracy and practicability, and further ensures that risk factors obtained according to the disease probability can be suitable for real cases.
In this embodiment, the training data derived from the correlation model in step S71b is training data generated from the correlation model. Referring to fig. 7C, for any related disease, the implementation method for generating training data according to the association model includes:
and S711, acquiring all disease information related to the related diseases according to the association model. For example, based on the association model 2, all disease information associated with disease 1 includes symptom 1, symptom 2, symptom 5, index 1, index 2, and index 3.
S712, pairThe disease information obtained in step S711 is selected in a combined manner, so that different combinations of disease information are obtained. Specifically, a plurality of disease information combinations are selected from all the disease information according to the concept of permutation and combination in mathematics, wherein the disease information contained in each disease information combination is different from one another. For example, if all the disease information acquired in step S71 includes disease information 1, disease information 2, and disease information 3, one disease information combination acquired in step S72 may be disease information 1, disease information 1 and disease information 2, disease information 2 and disease information 3, and so on. For the related disease n, the number of disease information combinations that can be acquired in step S72 is at most
Wherein M isnIs the amount of all disease information associated with the relevant disease n.
S713, calculating the disease probability corresponding to each disease information combination; the prevalence probability may be obtained through the above steps S71a to S73a, or may be implemented in other ways, which is not limited herein. And each disease information combination of the training data and the corresponding disease probability.
In one embodiment of the present invention, the health risk factors of the user include gender, age, family genetic history, abnormal health indicators and/or bad lifestyle habits.
Based on the above description of the health portrait generation method, the invention further provides a health portrait generation system. Referring to fig. 8, in an embodiment of the present invention, the health image generation system 8 can implement the health image generation method of the present invention, which specifically includes:
a basic information acquisition module 81 for acquiring basic information of the user to generate a functional label of the user health representation;
an abnormal information acquiring module 82, configured to acquire abnormal information of the user to generate a status tag of the user health representation;
a risk factor acquiring module 83, configured to acquire a health risk factor of the user to generate a risk label of the health portrait of the user;
and the health portrait generating module 84 is connected with the basic information acquiring module 81, the abnormal information acquiring module 82 and the risk factor acquiring module 83, and is used for generating a health portrait of the user according to the function tag, the state tag and the risk tag of the health portrait of the user.
Based on the above description of the health representation generation method, the present invention also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor implements the health representation generation method of the present invention.
Based on the above description of the health portrait generation method, the invention further provides a server. Referring to fig. 9, in an embodiment of the present invention, the server 9 includes: a memory 91 storing a computer program; a processor 92, communicatively connected to the memory 91, for executing the health representation generating method of the present invention when the computer program is invoked; and a display 63, communicatively coupled to the processor 92 and the memory 91, for displaying a GUI interactive interface associated with the health representation generation method.
The protection scope of the health image generation method according to the present invention is not limited to the execution sequence of the steps illustrated in the embodiment, and all the solutions of the prior art implemented by adding, subtracting, and replacing steps according to the principles of the present invention are included in the protection scope of the present invention.
The present invention also provides a health representation generation system, which can implement the health representation generation method of the present invention, but the implementation device of the health representation generation method of the present invention includes, but is not limited to, the structure of the health representation generation system as described in the present embodiment, and all structural modifications and substitutions of the prior art made according to the principles of the present invention are included in the scope of the present invention.
The health portrait generation method can acquire basic information of a user and generate a functional label, acquire abnormal information of the user and generate a state label, acquire health risk factors of the user and generate a risk label, and generate the health portrait of the user based on the functional label, the state label and the risk label. Therefore, the user can intuitively and comprehensively know the health condition of the user through the health portrait.
In conclusion, the present invention effectively overcomes various disadvantages of the prior art and has high industrial utilization value.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (12)
1. A health portrait generation method, comprising:
acquiring basic information of a user to generate a functional label of the health portrait of the user;
acquiring abnormal information of a user to generate a state label of the health portrait of the user;
acquiring health risk factors of a user to generate a risk label of a health portrait of the user;
and generating the health portrait of the user according to the function label, the state label and the risk label of the health portrait of the user.
2. The health representation generation method of claim 1, wherein the method of obtaining the basic information, abnormal information and/or health risk factors of the user comprises:
acquiring a health file of a user;
and acquiring basic information, abnormal information and/or health risk factors of the user according to the health record of the user.
3. The method of generating a health representation as claimed in claim 2, wherein the method of obtaining the health profile of the user comprises:
generating a health file template, wherein the health file template is used for prompting a user to input file information;
acquiring archive information input by a user;
and generating the health record of the user according to the record information input by the user.
4. The health representation generation method as claimed in claim 3, wherein: the health record template comprises a record prompt label, and a user selects the corresponding record prompt label to input the record information.
5. The health representation generation method of claim 3, wherein the method for obtaining the health profile of the user further comprises: and carrying out standardization processing on the archive information input by the user.
6. The health representation generation method of claim 1, further comprising:
acquiring a health risk score of the user according to the health risk factors of the user;
and acquiring an attack risk value of the user within a future period of time according to the health risk score of the user.
7. The health representation generation method as claimed in claim 6, wherein: the health risk score of the user comprises a health risk score of the user in a current state and/or a health risk score of the user in an ideal state.
8. The health representation generation method of claim 6, wherein the method of obtaining the health risk score of the user based on the health risk factors of the user comprises:
layering the health risk factors of the user to obtain layered assignments corresponding to the risk factors;
and acquiring the health risk score of the user according to the hierarchical assignment and the coefficient corresponding to each risk factor.
9. The health representation generation method as claimed in claim 1, wherein: the health risk factors of the user include gender, age, family genetic history, abnormal health indicators, and/or poor lifestyle habits.
10. A health representation generation system, comprising:
the basic information acquisition module is used for acquiring basic information of a user to generate a functional label of the user health portrait;
the abnormal information acquisition module is used for acquiring the abnormal information of the user to generate a state label of the health portrait of the user;
the risk factor acquisition module is used for acquiring health risk factors of the user to generate a risk label of the health portrait of the user;
and the health portrait generating module is connected with the basic information acquiring module, the abnormal information acquiring module and the risk factor acquiring module and is used for generating a health portrait of the user according to the function label, the state label and the risk label of the health portrait of the user.
11. A computer-readable storage medium having stored thereon a computer program, characterized in that: the computer program, when executed by a processor, implements the health representation generation method of any of claims 1-9.
12. A server, characterized in that the server comprises:
a memory storing a computer program;
a processor, communicatively coupled to the memory, that executes the health representation generation method of any of claims 1-9 when the computer program is invoked;
and the display is in communication connection with the processor and the memory and is used for displaying a related GUI (graphical user interface) of the health portrait generation method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011634158.6A CN113140323B (en) | 2020-12-31 | 2020-12-31 | Health portrait generation method, system, medium and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011634158.6A CN113140323B (en) | 2020-12-31 | 2020-12-31 | Health portrait generation method, system, medium and server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113140323A true CN113140323A (en) | 2021-07-20 |
| CN113140323B CN113140323B (en) | 2023-01-13 |
Family
ID=76809814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011634158.6A Active CN113140323B (en) | 2020-12-31 | 2020-12-31 | Health portrait generation method, system, medium and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113140323B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113643814A (en) * | 2021-08-30 | 2021-11-12 | 平安医疗健康管理股份有限公司 | Health management scheme recommendation method, device, equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107169307A (en) * | 2017-07-07 | 2017-09-15 | 中北大学 | Health risk assessment method and apparatus |
| CN107330295A (en) * | 2017-07-17 | 2017-11-07 | 深圳市前海博志信息技术有限公司 | breast health management system and method |
| CN108897734A (en) * | 2018-06-13 | 2018-11-27 | 康键信息技术（深圳）有限公司 | User's portrait generation method, device, computer equipment and storage medium |
| CN110033837A (en) * | 2019-03-05 | 2019-07-19 | 中电科软件信息服务有限公司 | The method for generating user's portrait and knowledge mapping based on electronic health record |
| CN110277152A (en) * | 2019-06-05 | 2019-09-24 | 南京邮电大学 | Medicine thing service system based on user's portrait |
| CN110442732A (en) * | 2019-07-24 | 2019-11-12 | 万达信息股份有限公司 | A kind of intelligent medical guide method, system and storage medium |
| CN110688406A (en) * | 2019-09-06 | 2020-01-14 | 平安医疗健康管理股份有限公司 | Data processing method, data processing device, computer equipment and storage medium |
| US20200185102A1 (en) * | 2018-12-11 | 2020-06-11 | K Health Inc. | System and method for providing health information |
| CN111581300A (en) * | 2020-05-09 | 2020-08-25 | 山东健康医疗大数据有限公司 | Label matrix construction and updating method based on health medical data |
-
2020
- 2020-12-31 CN CN202011634158.6A patent/CN113140323B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107169307A (en) * | 2017-07-07 | 2017-09-15 | 中北大学 | Health risk assessment method and apparatus |
| CN107330295A (en) * | 2017-07-17 | 2017-11-07 | 深圳市前海博志信息技术有限公司 | breast health management system and method |
| CN108897734A (en) * | 2018-06-13 | 2018-11-27 | 康键信息技术（深圳）有限公司 | User's portrait generation method, device, computer equipment and storage medium |
| US20200185102A1 (en) * | 2018-12-11 | 2020-06-11 | K Health Inc. | System and method for providing health information |
| CN110033837A (en) * | 2019-03-05 | 2019-07-19 | 中电科软件信息服务有限公司 | The method for generating user's portrait and knowledge mapping based on electronic health record |
| CN110277152A (en) * | 2019-06-05 | 2019-09-24 | 南京邮电大学 | Medicine thing service system based on user's portrait |
| CN110442732A (en) * | 2019-07-24 | 2019-11-12 | 万达信息股份有限公司 | A kind of intelligent medical guide method, system and storage medium |
| CN110688406A (en) * | 2019-09-06 | 2020-01-14 | 平安医疗健康管理股份有限公司 | Data processing method, data processing device, computer equipment and storage medium |
| CN111581300A (en) * | 2020-05-09 | 2020-08-25 | 山东健康医疗大数据有限公司 | Label matrix construction and updating method based on health medical data |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113643814A (en) * | 2021-08-30 | 2021-11-12 | 平安医疗健康管理股份有限公司 | Health management scheme recommendation method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113140323B (en) | 2023-01-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10340040B2 (en) | Method and system for identifying diagnostic and therapeutic options for medical conditions using electronic health records | |
| KR102558021B1 (en) | A clinical decision support ensemble system and the clinical decision support method by using the same | |
| US10943676B2 (en) | Healthcare information technology system for predicting or preventing readmissions | |
| RU2686627C1 (en) | Automatic development of a longitudinal indicator-oriented area for viewing patient's parameters | |
| JP5977898B1 (en) | BEHAVIOR PREDICTION DEVICE, BEHAVIOR PREDICTION DEVICE CONTROL METHOD, AND BEHAVIOR PREDICTION DEVICE CONTROL PROGRAM | |
| US20140095201A1 (en) | Leveraging Public Health Data for Prediction and Prevention of Adverse Events | |
| JP2019016235A (en) | Disease onset prediction device, disease onset prediction method and program | |
| JP2018503902A (en) | A medical differential diagnostic device adapted to determine the optimal sequence of diagnostic tests for identifying disease states by adopting diagnostic validity criteria | |
| Khan et al. | A Comparative Study of Machine Learning classifiers to analyze the Precision of Myocardial Infarction prediction | |
| WO2009083886A1 (en) | Presenting patient relevant studies for clinical decision making | |
| CN114121266A (en) | Intelligent auxiliary diagnosis method and system | |
| CN112908452A (en) | Event data modeling | |
| CN113140323B (en) | Health portrait generation method, system, medium and server | |
| WO2022010384A1 (en) | Clinical decision support system | |
| CN114868203A (en) | Information transmission device and information transmission method | |
| JP7315165B2 (en) | Diagnosis support system | |
| CN116543917A (en) | Information mining method for heterogeneous time sequence data | |
| WO2022141929A1 (en) | Health self-test system, server, and health testing system | |
| CN116312926A (en) | Health path recommending method and related device, electronic equipment and storage medium | |
| EP3405894A1 (en) | Method and system for identifying diagnostic and therapeutic options for medical conditions using electronic health records | |
| Tolentino et al. | CAREdio: Health screening and heart disease prediction system for rural communities in the Philippines | |
| US20220351847A1 (en) | A device and a method for determining a path of a patient in a hospital | |
| US20230047826A1 (en) | Context based performance benchmarking | |
| US20230178197A1 (en) | Techniques for predicting immunosuppression status | |
| US20220189637A1 (en) | Automatic early prediction of neurodegenerative diseases |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |