CN110570945B - AI chronic disease management method, computer storage medium and electronic device - Google Patents
AI chronic disease management method, computer storage medium and electronic device Download PDFInfo
- Publication number
- CN110570945B CN110570945B CN201911073552.4A CN201911073552A CN110570945B CN 110570945 B CN110570945 B CN 110570945B CN 201911073552 A CN201911073552 A CN 201911073552A CN 110570945 B CN110570945 B CN 110570945B
- Authority
- CN
- China
- Prior art keywords
- information
- priority
- chronic disease
- patient module
- data set
- 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.)
- Active
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
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses an AI chronic disease management method, a computer storage medium and an electronic device, wherein the AI chronic disease management method comprises the following steps: s1, acquiring a chronic disease data set, and processing to obtain a data network set; s2, dividing the data into a common level classification data set and a priority level classification data set; s3, classifying the common-level classification data set and the priority-level classification data set to obtain a plurality of fine classification data sets; s4, respectively training to obtain training models; s5, acquiring identity information, geographic information and chronic disease information of the user, and inputting the identity information, the geographic information and the chronic disease information into a training model; and S6, associating the training model with a third party in a preset range, and determining whether the third party needs to be contacted according to the feedback information of the training model. According to the AI chronic disease management method provided by the embodiment of the invention, model training is performed by combining the chronic disease data set, and the obtained training model can be widely applied to various chronic diseases of patients, so that intervention treatment can be conveniently performed on the patients.
Description
Technical Field
The invention belongs to the technical fields of software engineering, big data, distributed storage and calculation and the like, and particularly relates to an AI chronic disease management method, a computer storage medium and electronic equipment.
Background
With the improvement of living conditions, the more and more the urban population suffers from the three highs, the more and more the disease becomes a chronic disease seriously harming human health. People usually go to a hospital to see a doctor when feeling untimely and can directly transmit the information of the disease to a doctor when seeing the doctor. In daily life, patients usually cannot transmit disease information without going to a hospital for a doctor, and a plurality of channels for knowing the disease information in real time are not available.
Disclosure of Invention
In view of this, the present invention provides an AI chronic disease management method, a computer storage medium and a device, which enable a patient to transmit disease information to a doctor and other personnel in time and to understand the disease information more deeply.
In order to solve the above technical problem, in one aspect, the present invention provides an AI chronic disease management method, including the following steps: s1, acquiring a chronic disease data set, and processing the data set to obtain a data network set; s2, obtaining the correlation degree between the user identification of each vertex in the data network set and different illness states in different chronic disease information, and dividing the data network set into a common-level classification data set and a priority-level classification data set according to the correlation degree; s3, classifying the common-grade classified data sets and the priority-grade classified data sets according to different genders, different age groups, different regions and different disease times respectively to obtain a plurality of fine classification data sets; s4, placing the common-level classification data sets and the fine classification data sets of the priority-level classification data sets in a network for training respectively to obtain training models; s5, acquiring identity information, geographic information and chronic disease information of the user, and inputting the identity information, the geographic information and the chronic disease information into a training model; and S6, the training model associates a third party in a preset range according to the identity information, the geographic information and the chronic disease information of the user, and determines whether the third party needs to be contacted according to the feedback information of the training model.
According to the AI chronic disease management method provided by the embodiment of the invention, a large number of chronic disease data sets are collected in advance, model training is carried out by combining the data sets, and the obtained training model can be widely applied to various chronic diseases of patients, so that the patients can conveniently manage the information of the chronic diseases and can conveniently carry out interventional therapy on the patients.
According to one embodiment of the present invention, step S2 includes: s21, acquiring user identifications of all vertexes in the data network set; s22, acquiring symptoms corresponding to common-level illness states and priority illness states in different chronic disease information and judging the numerical range of the illness states; s23, comparing the user identification with symptoms and numerical value ranges corresponding to different illness states, if the user identification is located in the symptoms and numerical value ranges corresponding to the ordinary illness states, dividing the user identification into an ordinary classified data set, and if the user identification is located in the symptoms and numerical value ranges corresponding to the priority illness states, dividing the user identification into a priority classified data set.
According to an embodiment of the invention, the step of training the generic class dataset in the network comprises: s41, setting a hypothetical patient module, wherein the hypothetical patient module is internally provided with common reply information aiming at common inquiry information, random identity information, geographic information and chronic disease information, and can receive and send out interactive information; s42, acquiring identity information, geographic information and chronic disease information of the hypothetical patient module, and matching the hypothetical patient module with the fine classification dataset of the common-grade classification dataset according to the acquired information; s43, sending corresponding common inquiry information to the hypothetical patient module according to the matched fine classification data set; s44, the hypothetical patient module randomly replies the ordinary reply message or does not reply message according to the ordinary inquiry message; s45, when the hypothetical patient module replies the ordinary reply information, feeding back a corresponding reply according to the ordinary reply information, and repeating the step S44; and when the hypothetical patient module does not reply within the first preset time, ending the training to obtain the training model.
According to an embodiment of the present invention, the general query information includes: diet information, exercise information and medication, and the first preset time is 15s-30 s.
According to one embodiment of the invention, the step of training the priority classification dataset in the network comprises: s41', setting a hypothetical patient module, wherein the hypothetical patient module is internally provided with priority reply information aiming at the priority inquiry information and random identity information, geographic information and chronic disease information, and can receive and send out interactive information; s42', acquiring identity information, geographic information and chronic disease information of the hypothetical patient module, and matching the hypothetical patient module with the fine classification dataset of the priority classification dataset according to the acquired information; s43', sending corresponding priority query information to the hypothetical patient module according to the matched fine classification dataset; s44', the hypothetical patient module randomly replying to the priority reply message or not replying to the priority reply message according to the priority query message; s45 ', when the hypothetical patient module replies the priority reply message, feeding back a corresponding reply according to the priority reply message, and repeating the step S44'; and when the hypothetical patient module does not reply within a second preset time, automatically contacting a third party to obtain the training model.
According to an embodiment of the present invention, in step S44', when the hypothetical patient module replies to the priority reply message, it is determined whether there is trigger information that needs to contact a third party in the priority reply message, if so, it is determined whether the third party needs to be contacted to the hypothetical patient module, and if so, it is determined that the third party needs to be contacted to the hypothetical patient module, then the third party is contacted.
According to an embodiment of the present invention, the priority query information includes: the second preset time is 30-60 s, and the third party is a family member of the patient, a family doctor, a hospital or a pharmacy within a preset range.
According to an embodiment of the invention, the method further comprises: and S7, judging whether the identity information of the user exists in the training model, if so, performing data management through the training model, and if not, performing the steps S1-S4, and adding the identity information into the training model for training.
In a second aspect, embodiments of the present invention provide a computer storage medium comprising one or more computer instructions that, when executed, implement any of the methods described above.
In a third aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor, where the memory is configured to store one or more computer instructions, and the processor is configured to call and execute the one or more computer instructions, so as to implement the method described in any one of the above.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a schematic flow chart of an AI chronic management method according to an embodiment of the invention;
FIG. 2 is a schematic diagram of an electronic device according to an embodiment of the invention.
Reference numerals:
AI chronic disease management method 100;
an electronic device 300;
a memory 310; an operating system 311; an application 312;
a processor 320; a network interface 330; an input device 340; a hard disk 350; a display device 360.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, it is to be understood that the terms "central," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," "circumferential," and the like are used in the orientations and positional relationships indicated in the drawings for convenience in describing the invention and to simplify the description, and are not intended to indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and are therefore not to be considered limiting of the invention. Furthermore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless otherwise specified.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
The AI chronic disease management method 100 according to an embodiment of the present invention will be described in detail below with reference to the drawings.
As shown in fig. 1, an AI chronic disease management method 100 according to an embodiment of the present invention includes the steps of:
and S1, acquiring a chronic disease data set, and processing the data set to obtain a data network set.
S2, obtaining the correlation degree between the user identification of each vertex in the data network set and different illness states in different chronic disease information, and dividing the data network set into a common-level classification data set and a priority-level classification data set according to the correlation degree.
S3, classifying the common-grade classified data sets and the priority-grade classified data sets according to different genders, different age groups, different regions and different disease times respectively to obtain a plurality of fine classified data sets.
S4, placing the common-level classification data set and the fine classification data sets of the priority-level classification data sets in a network for training respectively to obtain a training model.
And S5, acquiring the identity information, the geographic information and the chronic disease information of the user and inputting the identity information, the geographic information and the chronic disease information into the training model.
And S6, the training model associates a third party in a preset range according to the identity information, the geographic information and the chronic disease information of the user, and determines whether the third party needs to be contacted according to the feedback information of the training model.
In other words, according to the AI chronic disease management method 100 of the embodiment of the present invention, a chronic disease data set can be obtained, and a server can process the obtained chronic disease data set to obtain a data network set. The server can obtain the relevance of the user identifier of each vertex in the data network set to different disease conditions in different chronic disease information, for example, the user identifier may include detection item categories, detection data, and the like, and different user identifiers may correspond to different types of chronic diseases and the disease conditions of corresponding chronic disease symptoms. The server can divide the data network set into a common-level classification data set and a priority-level classification data set according to the obtained correlation result, wherein the disease level corresponding to the common-level classification data set is relatively slight, and the disease level corresponding to the priority-level classification data set is relatively serious. The common-level classification data set and the priority-level classification data set can be set to have no cross data range, so that the data processing rate and the disease analysis rate can be improved. A cross data range can be set between the common-level classification data set and the priority-level classification data set, namely, the corresponding disease condition in the cross data range is between the common level and the priority level, further judgment and processing are required by a server or medical staff, and the accuracy of disease condition judgment can be improved by setting the cross data range.
The server can further classify the obtained common-level classification data set and the priority-level classification data set according to different limiting conditions, wherein the limiting conditions comprise patient self conditions, external environment conditions related to the patient and the like, for example, the patient self conditions comprise sex, age, illness time and the like, the external environment conditions related to the patient comprise geographical position and geographical characteristics, and the geographical characteristics can comprise information of natural environment, eating habits, living habits and the like of the geographical area. The server can obtain a plurality of fine classification data sets through classification, and the obtained fine classification data sets are placed in a network to be trained respectively to obtain a training model.
When the illness state of a specific patient is specifically analyzed, after the patient is detected, user information of the patient can be input into the training model, wherein the user information of the patient comprises user identity information, geographical position information of the user, information related to the region where the user is located, chronic disease information of the user, information related to related chronic diseases of relatives of the user and the like. The training model can obtain feedback information according to the input information, can be associated with a third party within a preset range, and can judge whether the third party needs to be contacted according to the obtained feedback information. The third party can be related institutions or related personnel within a preset range with the position of the patient as the center, and the third party can be institutions such as hospitals, health centers, epidemic prevention centers, drug stores, emergency centers and the like, third party contact information reserved by the patient and the like. For example, when the training model determines that the detection result of the patient is serious, whether a third party needs to be contacted or not can be automatically determined, so that the danger of the patient is avoided.
When the third party is associated, the third party can be associated with the patient standing address, the map data and the positioning service, so that the information of the third party closest to the patient can be accurately acquired.
It should be noted that, in the AI chronic disease management method 100 according to the embodiment of the present invention, the patient can completely know about the chronic disease information through data interaction between the server and the mobile terminal and the detector, that is, the patient detects the chronic disease information through the detector, uploads the detection result to the server through the mobile terminal or directly, and the server automatically performs related operations after receiving the chronic disease information. When the patient's problem or the chronic disease information is a problem that the server cannot automatically recognize or process, the server can contact the relevant technical personnel through the background to manually answer, and the patient can also know the patient's own chronic disease information.
Therefore, according to the AI chronic disease management method 100 of the embodiment of the invention, after the patient detects the chronic disease information, the relevant information can be automatically uploaded and identified, and whether the patient is helped to contact a third party or not is judged according to the identification result, so that the occurrence of dangerous situations is reduced.
In some embodiments of the present invention, step S2 includes the following steps:
and S21, acquiring the user identification of each vertex in the data network set.
S22, acquiring the corresponding symptoms of the common disease and the priority disease in different chronic disease information and judging the numerical range of the disease.
S23, comparing the user identification with symptoms and numerical value ranges corresponding to different illness states, if the user identification is located in the symptoms and numerical value ranges corresponding to the ordinary illness states, dividing the user identification into an ordinary classified data set, and if the user identification is located in the symptoms and numerical value ranges corresponding to the priority illness states, dividing the user identification into a priority classified data set.
That is, in ranking a set of data networks, the following steps may be performed: firstly, user identifications of all vertexes in a data network set are obtained, and illness states in different chronic disease information are divided into common-level illness states and priority-level illness states respectively according to information such as symptoms and relevant data of the illness states, wherein the common-level illness states and the priority-level illness states are respectively provided with relevant numerical value range intervals. And then, judging the numerical range interval in which the relevant numerical value of the user identification falls, and dividing the user identification into a common-level classification data set and a priority-level classification data set according to the judgment result.
It should be noted that, where the user id may correspond to a plurality of chronic diseases and may have the same or different disease levels in the corresponding chronic disease conditions, the treatment may be performed according to a treatment order in which the priority disease conditions are better than the general disease conditions.
According to an embodiment of the present invention, in step S5, the chronic disease information includes blood sugar, blood pressure and blood fat, that is, the patient' S chronic disease information can be detected by a blood glucose meter, a blood pressure meter and a blood fat meter, and the detected information is uploaded. Therefore, the comprehensive arrangement of the information of the plurality of chronic diseases can facilitate the patients to know the plurality of chronic diseases, and the use is more convenient.
In some embodiments of the present invention, the step of training the generic class dataset of the method 100 in the network comprises:
s41, setting a hypothetical patient module, wherein the hypothetical patient module of the method 100 is internally provided with common reply information aiming at the common inquiry information and random identity information, geographic information and chronic disease information, and the hypothetical patient module of the method 100 can receive and send out interactive information.
S42, acquiring identity information, geographic information and chronic information of the hypothetical patient module of method 100, and matching the hypothetical patient module of method 100 with the method 100 fine classification dataset of the general class dataset of method 100 based on the acquired information.
S43, the refined classification dataset according to the matched method 100 sends corresponding general query information to the method 100 hypothetical patient module.
S44, method 100 assumes that the patient module replies to the method 100 with either a normal reply message or no reply message randomly according to the method 100 normal query message.
S45, when the method 100 assumes that the patient module replies to the normal reply message of the method 100, feeding back a corresponding reply according to the normal reply message of the method 100, and repeating the step S44; when the method 100 assumes that the patient module does not respond within the first preset time, the training is ended, and the training model of the method 100 is obtained.
According to one embodiment of the present invention, the general query information includes: diet information, exercise information and medication, the first preset time is 15s-30 s.
In some embodiments of the invention, the step of training the priority classification dataset in the network comprises:
s41', a hypothetical patient module is arranged, priority reply information aiming at the priority inquiry information, random identity information, geographic information and chronic disease information are arranged in the hypothetical patient module, and the hypothetical patient module can receive and send out interactive information;
s42', acquiring identity information, geographic information and chronic disease information of the hypothetical patient module, and matching the hypothetical patient module with the fine classification dataset of the priority classification dataset according to the acquired information;
s43', sending corresponding priority inquiry information to the hypothetical patient module according to the matched fine classification data set;
s44', the hypothetical patient module randomly replies a priority reply message or a non-reply message according to the priority inquiry message;
s45 ', when the hypothetical patient module replies the priority reply message, feeding back the corresponding reply according to the priority reply message, and repeating the step S44'; and when the hypothetical patient module does not reply within the second preset time, automatically contacting a third party to obtain the training model.
Optionally, in step S44', when the hypothetical patient module replies the priority reply message, it is determined whether there is trigger information in the priority reply message that needs to contact the third party, if so, it is determined to determine whether the third party needs to be contacted to the hypothetical patient module, and if so, it is determined to contact the third party.
According to one embodiment of the present invention, the priority query information includes: the second preset time is 30-60 s, and the third party is family members of the patient, family doctors, a hospital or a pharmacy within a preset range.
The AI chronic disease management method 100 according to the embodiment of the present invention will be described in detail below, taking chronic disease information as blood glucose information as an example.
In some embodiments of the present invention, the predetermined value is 3.0mmol/L to 11.0 mmol/L, and when the detection value is greater than the predetermined value range or smaller than the predetermined value range, the detection value is in the priority classification data set, and the disease level is determined as priority; and when the detection value is within the preset value range, the detection value is within the common grade classification data set, and the disease grade is judged to be a common grade. And then, acquiring identity information, geographic information and chronic disease information of the patient, matching the disease condition of the patient with the corresponding general-level classification data set or the fine classification data set of the priority-level classification data set, and sending corresponding inquiry information to the patient according to the matching result.
That is, when the chronic disease information is blood sugar information, a preset value, for example, 3.0mmol/L-11.0 mmol/L, can be preset by the system, the blood sugar value is a normal blood sugar value of a person under normal conditions, when the detection value is within a preset value range, the server considers that the blood sugar of the patient is normal, the disease level is judged to be a normal level, then the disease of the patient is further subdivided according to the identity information, the geographic information and the chronic disease information of the patient, and corresponding general inquiry information, for example, diet, exercise and medication conditions, is sent to the patient according to the subdivision result, for example, the family disease history of the patient is inquired according to the disease age of the patient. And automatically judging whether any problem exists according to the response information of the patient, and pushing a corresponding recipe and a corresponding exercise method, such as linking a third party for catering, medicine delivery service, accompany and the like.
When the blood sugar value is smaller than the preset value, the blood sugar of the patient is relatively low, the possibility of hypoglycemia exists, when the blood sugar value is larger than the preset value, the blood sugar value of the patient is relatively high, the possibility of hyperglycemia exists, under the two conditions, the server considers that the blood sugar of the patient is in an abnormal state, judges the disease level as priority, and sends priority inquiry information to the patient.
In the actual use process, the preset values can be further subdivided, for example, the hypoglycemia condition can be further layered, and the method specifically comprises the following steps:
(1) blood glucose alert value: the blood sugar is less than or equal to 3.9 mmol/L, in the case, the patient needs to take quick-acting carbohydrate and adjust the dosage of the blood sugar reduction scheme, and the server can provide relevant suggestions for the patient according to the detection result and the inquiry condition of the patient;
(2) clinically significant hypoglycemia: the blood sugar is less than 3.0mmol/L, and in the condition, the server prompts the patient to have serious and clinically significant hypoglycemia;
(3) severe hypoglycemia: blood glucose < 2.0 mmol/L, which range of blood glucose values has no specific blood glucose limit, in which case the patient may be accompanied by severe cognitive dysfunction and hypoglycemia that requires additional measures to help recovery, in which case the server may contact the third party urgently, reducing the risk.
The hyperglycemic condition can be further classified, and specifically includes:
(1) the control can be as follows: fasting glucose is <7mmol/L and postprandial glucose is <10mmol/L, in which case the server may recommend that the patient does not require human intervention on blood glucose;
(2) low risk situation: fasting blood glucose is between 7mmol/L and 11mmol/L, or postprandial blood glucose is between 10mmol/L and 14mmol/L, in which case the server may recommend that the patient be handled by the community physician alone;
(3) in the middle critical situation: fasting blood glucose is between 11mmol/L and 14mmol/L, or postprandial blood glucose is between 14mmol/L and 18mmol/L, in which case the server may recommend treatment by community physicians under the direction of specialist physicians;
(4) high-risk situations: fasting glucose is >14mmol/L, or postprandial glucose is >18mmol/L, in which case the server may recommend treatment, outpatient adjustment or hospitalization by a specialist.
On the basis of presetting the preset value, the server can feed back in real time according to the detection result of the patient, when the disease condition grade of the patient is judged to be a common grade, the server can further subdivide according to the fine classification data set of the common grade classification data set, push common inquiry information to the patient, identify whether reply information is received or not, reply according to the reply information if the reply information is received, and send the replied content to the patient. And if the reply message is not received within the first preset time, automatically ending the recognition state.
When the reply information is received, the consultation information in the reply information can be classified into grades, the grades of the answering personnel are correspondingly classified, and the AI can automatically classify the information according to the identified consultation information and transmit the information to the corresponding answering personnel.
According to one embodiment of the present invention, the general query information includes: diet information, exercise information and medication, and general inquiry information can be adjusted and modified according to requirements.
Optionally, the first preset time is 20s-30 s. That is, when the patient's disease level is judged to be normal, the mobile terminal or other device sends a normal inquiry message to the patient, and if the patient does not reply after 20s to 30s, the server automatically disconnects the contact with the patient, and the diagnosis and management of the chronic disease information are finished.
According to one embodiment of the present invention, the priority query information includes: physical comfort information and medical history information, it should be noted that the priority query information can be adjusted and modified as needed.
In some embodiments of the invention, the second predetermined time is 40s to 60 s.
Optionally, the third party is a patient's family member, a family doctor, a hospital within a predetermined range, or a pharmacy. That is, when the detected value of the detected chronic disease information is lower or higher than a preset value, for example, when a high-risk situation occurs, the server automatically triggers a serious warning message, and sends a priority inquiry message, for example, asking whether there is a problem such as dizziness, headache, etc. The patient sends the reply information, the database can judge the specific situation according to the question and answer result, trigger to family doctor, doctor to actively contact the patient, or directly link 120, and can trigger the function of up-down transfer to transfer the patient information from the primary hospital to the superior hospital. If the patient does not reply after 30-60 s, a warning message is triggered, and a WeChat or telephone alarm can be triggered to give family doctors or relatives of the patient.
In addition, in the AI chronic disease management method 100 according to the embodiment of the present invention, the chronic disease information may also be blood pressure or blood fat, and when the chronic disease information is blood pressure, the chronic disease management may be performed according to how to define blood pressure abnormality.
Specifically, the blood pressure abnormality includes hypotension and hypertension, the hypotension means that the blood pressure of the patient is less than 90/60mmhg, and the specific cases of the hypertension are shown in the following table 1:
TABLE 1 Classification of conditions of different blood pressure values
| Categories | Systolic pressure (mmhg) | Diastolic pressure (mmhg) |
| Ideal blood pressure | <120 and | <80 |
| normal high value | 120 to 139 and (or) | 80～89 |
| Hypertension (hypertension) | Not less than 140 and (or) | ≥90 |
| 1 st hypertension (mild) | 140 to 159 and (or) | 90～99 |
| Grade 2 hypertension (moderate) | 160 to 179 and (or)） | 100～109 |
| Grade 3 hypertension (severe) | Not less than 180 and (or) | ≥110 |
When the hypertension patient has continuous low pressure, under the condition, the server reminds the patient of needing to seek medical attention in time, when the blood pressure detection value of the patient is under the conditions of ideal blood pressure and normal high value, intervention is not needed, when the systolic pressure of the blood pressure detection value is 140-159 and/or the diastolic pressure is 90-99 mmhg, the server judges that the patient is the 1-grade high blood pressure, and the patient is recommended to be treated by a community doctor independently; when the systolic pressure of the blood pressure detection value is 160-179 mmhg or the diastolic pressure is 100-109 mmhg, the server judges that the patient is the level 2 high blood pressure, and the patient is recommended to be treated by a community doctor under the guidance of a specialist; when the systolic pressure of the blood pressure detection value is more than or equal to 180mmhg or the diastolic pressure is more than or equal to 110mmhg, the server judges that the patient is the 3-grade high blood pressure, and the diagnosis and treatment by a specialist, the adjustment of a treatment scheme by an outpatient service or hospitalization are recommended.
According to an embodiment of the present invention, further comprising S7: judging whether the identity information of the patient is stored in a database, if so, performing data management through a training model, and if not, the method 100 further comprises: steps S1-S4 are performed to store the identity information of the patient in a database. The intelligent analysis can be carried out through the database, corresponding questions are inquired for the patient according to the comparison and judgment results, and different questions are triggered by different detection results, such as common inquiry information and priority inquiry information.
When the database is established, information such as keywords, pictures, videos, related articles, recipes, motion schemes, suggestion schemes of corresponding diseases, training question and answer logics and the like of related chronic diseases can be input.
It should be noted that general query information and priority query information may be pushed to the patient through WeChat, telephone, community, and the like. And a user application platform can be established, such as a wechat robot (including public numbers, wechat groups and applets), a telephone robot (including short messages), a pc management end of the internet of things detection equipment, a cloud server and the like.
When the response information of the patient is identified, corresponding knowledge points or suggested schemes and the like can be fed back according to corresponding consultation information, for example, voice information or text information is identified, pictures are identified, key information can be extracted according to an identification result, and logic question answering is carried out on the extracted key information. When the logic question answering state is carried out, the database can be connected, and the corresponding condition triggered by the corresponding content is judged.
When the condition that the reply information cannot be identified occurs, the answer can be converted into manual work for answering, and the relevant consultation information can be input into the database to enable the AI to automatically learn.
In some embodiments of the present invention, after the reply message of the patient is identified, automatic reply and push can be performed, and manual reply and push can also be performed.
According to one embodiment of the invention, when the patient's chronic disease information is uploaded, historical chronic disease information of the patient in the database can be judged, if yes, the historical chronic disease information is called out, and a real-time chronic disease information detection result is compared with a historical chronic disease information detection result. If not, the personal information of the patient is newly created.
In summary, the AI lentigo management method 100 according to an embodiment of the present invention has the following advantages:
(1) the Internet of things technology is applied to collect and manage the chronic disease information of the patient, and meanwhile, the artificial intelligence technology is introduced, so that the efficiency of preventing and controlling the risk factors of the high risk group with the chronic disease is effectively improved;
(2) can carry out remote monitoring to the patient, be convenient for carry out intervention treatment.
In addition, an embodiment of the present invention further provides a computer storage medium, which includes one or more computer instructions, and when executed, the one or more computer instructions implement any one of the AI chronic disease management methods 100 described above.
That is, the computer storage medium stores a computer program that, when executed by a processor, causes the processor to execute any of the AI lentigo management methods 100 described above.
As shown in fig. 2, an embodiment of the present invention provides an electronic device 300, which includes a memory 310 and a processor 320, where the memory 310 is used for storing one or more computer instructions, and the processor 320 is used for calling and executing the one or more computer instructions, so as to implement any one of the methods 100 described above.
That is, the electronic device 300 includes: a processor 320 and a memory 310, in which memory 310 computer program instructions are stored, wherein the computer program instructions, when executed by the processor, cause the processor 320 to perform any of the methods 100 described above.
Further, as shown in fig. 2, the electronic device 300 further includes a network interface 330, an input device 340, a hard disk 350, and a display device 360.
The various interfaces and devices described above may be interconnected by a bus architecture. A bus architecture may be any architecture that may include any number of interconnected buses and bridges. Various circuits of one or more Central Processing Units (CPUs), represented in particular by processor 320, and one or more memories, represented by memory 310, are coupled together. The bus architecture may also connect various other circuits such as peripherals, voltage regulators, power management circuits, and the like. It will be appreciated that a bus architecture is used to enable communications among the components. The bus architecture includes a power bus, a control bus, and a status signal bus, in addition to a data bus, all of which are well known in the art and therefore will not be described in detail herein.
The network interface 330 may be connected to a network (e.g., the internet, a local area network, etc.), and may obtain relevant data from the network and store the relevant data in the hard disk 350.
The input device 340 may receive various commands input by an operator and send the commands to the processor 320 for execution. The input device 340 may include a keyboard or a pointing device (e.g., a mouse, a trackball, a touch pad, a touch screen, or the like).
The display device 360 may display the result of the instructions executed by the processor 320.
The memory 310 is used for storing programs and data necessary for operating the operating system, and data such as intermediate results in the calculation process of the processor 320.
It will be appreciated that memory 310 in embodiments of the invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile memory may be a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Programmable Read Only Memory (EPROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), or a flash memory. Volatile memory can be Random Access Memory (RAM), which acts as external cache memory. The memory 310 of the apparatus and methods described herein is intended to comprise, without being limited to, these and any other suitable types of memory.
In some embodiments, memory 310 stores the following elements, executable modules or data structures, or a subset thereof, or an expanded set thereof: an operating system 311 and application programs 312.
The operating system 311 includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, and is used for implementing various basic services and processing hardware-based tasks. The application programs 312 include various application programs, such as a Browser (Browser), and are used for implementing various application services. A program implementing methods of embodiments of the present invention may be included in application 312.
The processor 320, when invoking and executing the application program and data stored in the memory 310, specifically, the application program or the instructions stored in the application program 312, dispersedly sends one of the first set and the second set to the node distributed by the other one of the first set and the second set, where the other one is dispersedly stored in at least two nodes; and performing intersection processing in a node-by-node manner according to the node distribution of the first set and the node distribution of the second set.
The method disclosed by the above embodiment of the present invention can be applied to the processor 320, or implemented by the processor 320. Processor 320 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 320. The processor 320 may be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof, and may implement or perform the methods, steps, and logic blocks disclosed in the embodiments of the present invention. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in the memory 310, and the processor 320 reads the information in the memory 310 and completes the steps of the method in combination with the hardware.
It is to be understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or any combination thereof. For a hardware implementation, the processing units may be implemented within one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), general purpose processors, controllers, micro-controllers, microprocessors, other electronic units designed to perform the functions described herein, or a combination thereof.
For a software implementation, the techniques described herein may be implemented with modules (e.g., procedures, functions, and so on) that perform the functions described herein. The software codes may be stored in a memory and executed by a processor. The memory may be implemented within the processor or external to the processor.
In particular, the processor 320 is also configured to read the computer program and execute any of the methods 100 described above.
In the several embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be physically included alone, or two or more units may be integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) to execute some steps of the transceiving method according to various embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (8)
1. An AI chronic disease management method, characterized by comprising the following steps:
s1, acquiring a chronic disease data set, and processing the data set to obtain a data network set;
s2, obtaining the correlation degree between the user identification of each vertex in the data network set and different illness states in different chronic disease information, and dividing the data network set into a common-level classification data set and a priority-level classification data set according to the correlation degree;
s3, classifying the common-grade classified data sets and the priority-grade classified data sets according to different genders, different age groups, different regions and different disease times respectively to obtain a plurality of fine classification data sets;
s4, placing the common-level classification data set and the fine classification data sets of the priority-level classification data sets in a network for training respectively to obtain a training model,
the step of training the common-level classification dataset in the network comprises the following steps:
s41, setting a hypothetical patient module, wherein the hypothetical patient module is internally provided with common reply information aiming at common inquiry information, random identity information, geographic information and chronic disease information, and can receive and send out interactive information;
s42, acquiring identity information, geographic information and chronic disease information of the hypothetical patient module, and matching the hypothetical patient module with the fine classification dataset of the common-grade classification dataset according to the acquired information;
s43, sending corresponding common inquiry information to the hypothetical patient module according to the matched fine classification data set;
s44, the hypothetical patient module randomly replies the ordinary reply message or does not reply message according to the ordinary inquiry message;
s45, when the hypothetical patient module replies the ordinary reply information, feeding back a corresponding reply according to the ordinary reply information, and repeating the step S44; when the hypothetical patient module does not reply within a first preset time, ending the training to obtain the training model;
the step of training the priority classification dataset in the network comprises:
s41', setting a hypothetical patient module, wherein the hypothetical patient module is internally provided with priority reply information aiming at the priority inquiry information and random identity information, geographic information and chronic disease information, and can receive and send out interactive information;
s42', acquiring identity information, geographic information and chronic disease information of the hypothetical patient module, and matching the hypothetical patient module with the fine classification dataset of the priority classification dataset according to the acquired information;
s43', sending corresponding priority query information to the hypothetical patient module according to the matched fine classification dataset;
s44', the hypothetical patient module randomly replying to the priority reply message or not replying to the priority reply message according to the priority query message;
s45 ', when the hypothetical patient module replies the priority reply message, feeding back a corresponding reply according to the priority reply message, and repeating the step S44'; when the hypothetical patient module does not reply within a second preset time, automatically contacting a third party to obtain the training model;
s5, acquiring identity information, geographic information and chronic disease information of the user, and inputting the identity information, the geographic information and the chronic disease information into a training model;
and S6, the training model associates a third party in a preset range according to the identity information, the geographic information and the chronic disease information of the user, and determines whether the third party needs to be contacted according to the feedback information of the training model.
2. The method according to claim 1, wherein step S2 includes:
s21, acquiring user identifications of all vertexes in the data network set;
s22, acquiring symptoms corresponding to common-level illness states and priority illness states in different chronic disease information and judging the numerical range of the illness states;
s23, comparing the user identification with symptoms and numerical value ranges corresponding to different illness states, if the user identification is located in the symptoms and numerical value ranges corresponding to the ordinary illness states, dividing the user identification into an ordinary classified data set, and if the user identification is located in the symptoms and numerical value ranges corresponding to the priority illness states, dividing the user identification into a priority classified data set.
3. The method of claim 1, wherein the general query information comprises: diet information, exercise information and medication, and the first preset time is 15s-30 s.
4. The method according to claim 1, wherein in step S44', when the hypothetical patient module replies to the priority reply message, it is determined whether there is a trigger message for contacting a third party in the priority reply message, if so, it is determined to the hypothetical patient module whether there is a need to contact the third party, and if so, it is determined to contact the third party.
5. The method of claim 4, wherein the prior query message comprises: the second preset time is 30-60 s, and the third party is a family member of the patient, a family doctor, a hospital or a pharmacy within a preset range.
6. The method of claim 1, further comprising:
and S7, judging whether the identity information of the user exists in the training model, if so, performing data management through the training model, and if not, performing the steps S1-S4, and adding the identity information into the training model for training.
7. A computer storage medium comprising one or more computer instructions which, when executed, implement the method of any one of claims 1-6.
8. An electronic device comprising a memory and a processor, wherein,
the memory is to store one or more computer instructions;
the processor is configured to invoke and execute the one or more computer instructions to implement the method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911073552.4A CN110570945B (en) | 2019-11-06 | 2019-11-06 | AI chronic disease management method, computer storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911073552.4A CN110570945B (en) | 2019-11-06 | 2019-11-06 | AI chronic disease management method, computer storage medium and electronic device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110570945A CN110570945A (en) | 2019-12-13 |
| CN110570945B true CN110570945B (en) | 2020-02-14 |
Family
ID=68786070
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911073552.4A Active CN110570945B (en) | 2019-11-06 | 2019-11-06 | AI chronic disease management method, computer storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110570945B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111916213A (en) * | 2020-08-12 | 2020-11-10 | 广州驰兴通用技术研究有限公司 | Medical service method and device based on cloud computing |
| CN112509688B (en) * | 2020-09-25 | 2024-06-11 | 卫宁健康科技集团股份有限公司 | Automatic analysis system, method, equipment and medium for pressure sore picture |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109215754A (en) * | 2018-09-10 | 2019-01-15 | 平安科技（深圳）有限公司 | Medical record data processing method, device, computer equipment and storage medium |
| CN109599185A (en) * | 2018-11-14 | 2019-04-09 | 金色熊猫有限公司 | Disease data processing method, device, electronic equipment and computer-readable medium |
| CN109935319A (en) * | 2019-03-15 | 2019-06-25 | 南京邮电大学 | Chronic disease systematic management system |
-
2019
- 2019-11-06 CN CN201911073552.4A patent/CN110570945B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109215754A (en) * | 2018-09-10 | 2019-01-15 | 平安科技（深圳）有限公司 | Medical record data processing method, device, computer equipment and storage medium |
| CN109599185A (en) * | 2018-11-14 | 2019-04-09 | 金色熊猫有限公司 | Disease data processing method, device, electronic equipment and computer-readable medium |
| CN109935319A (en) * | 2019-03-15 | 2019-06-25 | 南京邮电大学 | Chronic disease systematic management system |
Non-Patent Citations (2)
| Title |
|---|
| 基于AI的慢病高危管理***研究与设计;帅仁俊等;《中国数字医学》;20190115;第21-23页 * |
| 基于移动医疗技术的家庭医生慢病管理***;邵祝燕等;《医学信息学杂志》;20190625;第40卷(第6期);第27-31页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110570945A (en) | 2019-12-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10162940B2 (en) | System and method of applying state of being to health care delivery | |
| EP3255573A1 (en) | Clinical decision supporting ensemble system and clinical decison supporting method using the same | |
| CN110827994B (en) | Myocardial infarction early warning method, device and equipment and storage medium | |
| US20150248537A1 (en) | Personalized Health Score Generator | |
| US9946840B1 (en) | Systems and methods for assessing staffing levels and predicting patient outcomes | |
| CN110570945B (en) | AI chronic disease management method, computer storage medium and electronic device | |
| KR101772918B1 (en) | Apparatus and method for providing nursing service | |
| US20140236627A1 (en) | Dynamic medical scheduling system and method of operation thereof | |
| CN112951414A (en) | Primary medical clinical assistant decision-making system | |
| US9978165B2 (en) | Dynamic presentation of waveform tracings in a central monitor perspective | |
| CN114974530A (en) | Post-diagnosis follow-up method, system and storage medium | |
| CN211243385U (en) | AI blood glucose meter | |
| Thomason et al. | Home telehealth and hospital readmissions: a retrospective OASIS-C data analysis | |
| US10431339B1 (en) | Method and system for determining relevant patient information | |
| KR20210117543A (en) | Patient-centered health management system | |
| US20120253842A1 (en) | Methods, apparatuses and computer program products for generating aggregated health care summaries | |
| US20230005603A1 (en) | Intelligent emergency triage system | |
| CN113963773A (en) | Diagnostic report display method and device, electronic equipment and storage medium | |
| CN114582506A (en) | Chronic disease early warning system and method | |
| CN110957031B (en) | Disease prevention information service platform | |
| CN212382608U (en) | Multifunctional AI detector | |
| CN110660456A (en) | Clinical decision support and model training method, device, terminal and medium thereof | |
| WO2007106458A2 (en) | Methods and systems for using practice management data | |
| CN112842302A (en) | Method and system for processing body information and storage medium | |
| Phanareth et al. | Revealing the Nature of Chronic Obstructive Pulmonary Disease Using Self-tracking and Analysis of Contact Patterns: Longitudinal Study |
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 |