CN110752035A - Health data processing method and device, computer equipment and storage medium - Google Patents
Health data processing method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110752035A CN110752035A CN201910842462.0A CN201910842462A CN110752035A CN 110752035 A CN110752035 A CN 110752035A CN 201910842462 A CN201910842462 A CN 201910842462A CN 110752035 A CN110752035 A CN 110752035A
- Authority
- CN
- China
- Prior art keywords
- health
- user
- preset
- target disease
- 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.)
- Pending
Links
- 230000036541 health Effects 0.000 title claims abstract description 218
- 238000003672 processing method Methods 0.000 title claims abstract description 28
- 201000010099 disease Diseases 0.000 claims abstract description 120
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 120
- 238000003745 diagnosis Methods 0.000 claims abstract description 50
- 238000000034 method Methods 0.000 claims abstract description 22
- 238000012545 processing Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 14
- 230000002265 prevention Effects 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 5
- 239000010749 BS 2869 Class C1 Substances 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 description 6
- 230000036772 blood pressure Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 235000005911 diet Nutrition 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000003449 preventive effect Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000037213 diet Effects 0.000 description 2
- 230000003862 health status Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000036387 respiratory rate Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000004617 sleep duration Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 208000007502 anemia Diseases 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 206010012601 diabetes mellitus Diseases 0.000 description 1
- 230000000378 dietary effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 208000015210 hypertensive heart disease Diseases 0.000 description 1
- 230000033001 locomotion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 235000019633 pungent taste Nutrition 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Pathology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a health data processing method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring health data of a user from preset block link points; respectively extracting preset attribute contents of characteristic attributes from hospital diagnosis records, health application data and life application data, and forming an individual data set to be processed according to the extracted attribute contents of each characteristic attribute according to a preset dimension; classifying the individual data set based on a naive Bayes classifier according to a sample data set of a target disease in a preset sample database to obtain a classification result of a user corresponding to the individual data set; and carrying out health early warning on the user according to the classification result. According to the technical scheme, on the basis that the individual data set contains comprehensive and complete health data of the user, the probability of the target disease risk of the user is accurately calculated by adopting a naive Bayes classifier, so that the accuracy of individual health early warning is effectively improved.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method and an apparatus for processing health data, a computer device, and a storage medium.
Background
At present, data related to personal health relate to aspects of daily life, such as examination data and medical records in hospitals, data related to health and living habits collected by various applications on intelligent terminal equipment or wearable intelligent equipment, and the like.
However, these information and data are often in scattered and dispersed states, and some data are restricted by personal privacy, written forms, and the like, and cannot acquire comprehensive personal health data, so that health early warning for individual disease risk lacks an effective data base, and accuracy of personal health early warning is affected.
Disclosure of Invention
The embodiment of the invention provides a health data processing method and device, computer equipment and a storage medium, and aims to solve the problems that the existing health data are dispersed, comprehensive health data cannot be acquired, and an effective analysis early warning model is lacked, so that the accuracy of performing personal health early warning according to the health data is low.
A health data processing method, comprising:
acquiring health data of a user from preset block link points, wherein the health data comprises hospital diagnosis records, health application data and life application data;
respectively extracting preset attribute contents of characteristic attributes from the hospital diagnosis record, the health application data and the life application data, and forming an individual data set to be processed by the extracted attribute contents of each characteristic attribute according to a preset dimension;
classifying the individual data set based on a naive Bayes classifier according to a sample data set of a target disease in a preset sample database to obtain a classification result of the user corresponding to the individual data set, wherein the naive Bayes classifier is used for analyzing the risk of the target disease existing in the user corresponding to the individual data set;
and carrying out health early warning on the user according to the classification result.
A health data processing apparatus comprising:
the data acquisition module is used for acquiring health data of a user from preset block link points, wherein the health data comprises hospital diagnosis records, health application data and life application data;
the attribute extraction module is used for respectively extracting preset attribute contents of characteristic attributes from the hospital diagnosis record, the health application data and the life application data, and forming an individual data set to be processed according to preset dimensions by using the extracted attribute contents of each characteristic attribute;
the system comprises a user classification module, a classification module and a classification module, wherein the user classification module is used for classifying the individual data set based on a naive Bayesian classifier according to a sample data set of a target disease in a preset sample data base to obtain a classification result of the user corresponding to the individual data set, and the naive Bayesian classifier is used for analyzing the risk of the target disease existing in the user corresponding to the individual data set;
and the health early warning module is used for carrying out health early warning on the user according to the classification result.
A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the above health data processing method when executing the computer program.
A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned health data processing method.
In the health data processing method, the device, the computer equipment and the storage medium, the hospital diagnosis record, the health application data and the life application data of the user are obtained from the preset block chain link points, so that the health data dispersed in various channels of the user are timely stored in the block chain nodes, the comprehensive health data of the user are obtained through the block chain network, the attribute contents of the preset characteristic attributes are extracted, the extracted attribute contents of each characteristic attribute form an individual data set to be processed according to the preset dimension, the individual data set covers the inspection result and the diagnosis result of the user when the user visits in the hospital, the body index detection data and the health data related to the life habit in daily life, the individual data set can comprehensively reflect the health condition of the user, and further, according to the sample data set of the target diseases in the preset sample database, the method comprises the steps of classifying an individual data set based on a naive Bayes classifier to obtain a classification result of a user corresponding to the individual data set, and carrying out health early warning on the user according to the classification result, so that the probability of the risk of the user corresponding to the individual data set of the user to the target disease can be accurately calculated according to a sample data set of the target disease by adopting the naive Bayes classifier on the basis that the individual data set contains comprehensive and complete health data of the user, and the accuracy of the personal health early warning is effectively improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
FIG. 1 is a diagram illustrating an application environment of a health data processing method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a health data processing method according to an embodiment of the present invention;
FIG. 3 is a flowchart of step S3 of the health data processing method according to an embodiment of the present invention;
FIG. 4 is a flowchart of step S4 of the health data processing method according to an embodiment of the present invention;
FIG. 5 is a flowchart of a health data processing method for monitoring health status of a user according to hospital diagnostic records and performing health pre-warning according to an embodiment of the present invention;
FIG. 6 is a flowchart of step S1 of the health data processing method according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a health data processing apparatus according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of a computer device according to an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The health data processing method provided by the application can be applied to an application environment shown in fig. 1, where the application environment includes a server, a client and a block chain node, where the server and the block chain node, and the client and the block chain node are connected by a network, the network may be a wired network or a wireless network, the client specifically includes but is not limited to various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices, and the server may be implemented by an independent server or a server cluster formed by multiple servers. The client uploads the health data of the user to the block chain node, the server acquires the health data from the block chain node, and the personal health early warning is completed through comprehensive analysis of various types of health data.
In an embodiment, as shown in fig. 2, a health data processing method is provided, which is described by taking the method applied to the server in fig. 1 as an example, and specifically includes steps S1 to S4, which are detailed as follows:
s1: and acquiring health data of the user from the preset block link points, wherein the health data comprises hospital diagnosis records, health application data and life application data.
In this embodiment, the health data of the user is stored in the blockchain node, and the client may upload the health data of the user to the preset blockchain node periodically or in real time. Furthermore, the client can also encrypt and chain the health data in a preset encryption mode so as to enhance the confidentiality of the health data and avoid the privacy disclosure of the user.
Specifically, the server acquires the health data from the block link points, and if the health data stored in the block link points is encrypted, the server decrypts the health data according to a preset decryption mode to obtain the decrypted health data.
The health data includes hospital diagnostic records, health application data, and life application data. The hospital diagnosis record comprises a test result of various body index tests performed by a user in the hospital visiting process and a disease diagnosis result prescribed by a doctor for the user; the health Application data is recorded information of various health Applications (APPs) or wearable devices in a client used by a user, and includes but is not limited to age, respiratory rate, heartbeat, blood pressure, sleep duration, motion records and other data; the life application data is specifically information recorded by various life APPs in a client used by a user, and includes, but is not limited to, catering information, trip information, and the like, such as date, time length, frequency of trip vacation, catering preference, list, or spiciness, which may affect the health of the user.
Because the data standard of records such as different hospitals, healthy APP, life APP and wearable equipment is different, the unit is different, consequently, the client needs to carry out standardized conversion to healthy data according to unified data format requirement before uploading user's healthy data to predetermined block chain node, obtains the structured data of unified format after, uploads this structured data to predetermined block chain node again. The structured data in the unified format may specifically be a data set composed of feature attributes, each feature attribute is composed of a preset group of attribute units, and each attribute unit is used to describe definition, identification, or value of the feature attribute.
It should be noted that the preset block link points may be one or more, and when a plurality of block link nodes are used, each block link node may store one or more types of health data.
Further, the preset block link points may include a diagnosis information block link node, a health information block link node, and a life information block link node, where the diagnosis information block link node is configured to store hospital diagnosis records of each user, the health information block link point is configured to store health application data of each user, and the life information block link point is configured to store life application data of each user.
S2: and respectively extracting preset attribute contents of the characteristic attributes from the hospital diagnosis records, the health application data and the life application data, and forming an individual data set to be processed according to the extracted attribute contents of each characteristic attribute according to a preset dimension.
Specifically, the hospital diagnosis record, the health application data and the life application data are structured data in a unified format, the structured data is a data set composed of characteristic attributes, each characteristic attribute is composed of a set of preset attribute units, the characteristic attributes may specifically include, but are not limited to, age, respiratory rate, heartbeat, blood pressure, sleep duration, exercise duration, takeaway times, vacation times and the like, the attribute contents may specifically include contents of the attribute units preset in the characteristic attributes, for example, the attribute contents of the exercise duration may be total exercise duration per day in one month, and the attribute contents of the vacation times may be total vacation times in six months, where the total number of vacation times may be obtained from trip information recorded in a trip-related APP.
The health data of different channels may have the same characteristic attributes, so that after the server side extracts the attribute contents of the characteristic attributes from the hospital diagnostic record, the health application data and the life application data respectively, the attribute contents of the same characteristic attributes are merged, and the attribute contents of each characteristic attribute form an individual data set to be processed according to a preset dimension.
In this embodiment, the preset dimension may specifically be a time dimension, the server uses the attribute content of each feature attribute at the same time point as a vector component of the time point, and forms vector components of different time points into a vector matrix, where the vector matrix is an individual data set to be processed.
For example, if the number of preset feature attributes is 3, which are the blood pressure a, the heartbeat b, and the takeaway number c, the individual data set may be the vector matrix X ═ (X ═ X)1,x2,...,xn)，xj＝(a(tj),b(tj),c(tj))TWherein n is the time point number of the preset time period, xjIs a vector component composed of the attribute content of each characteristic attribute at the jth time point in a preset time period, a (t)j) For blood pressure at time point tjValue of b (t)j) For heart beat at time point tjValue of c (t)j) At time t for takeout timesjThe value of (a).
S3: and classifying the individual data set based on a naive Bayes classifier according to a sample data set of the target disease in a preset sample database to obtain a classification result of the user corresponding to the individual data set, wherein the naive Bayes classifier is used for analyzing the risk of the target disease existing in the user corresponding to the individual data set.
Specifically, a sample data set of the target disease is stored in the preset sample data base, the sample data set comprises a sample with the target disease and a sample without the target disease, the sample is derived from health data of a large number of users stored in the block chain nodes, and the data format of the sample is the same as that of the individual data set.
A naive bayes classifier is a simple probabilistic classifier based on the use of bayesian theorem under the assumption of strong independence between feature attributes. In this embodiment, on the basis of a sample data set in a sample database, a naive bayesian classifier is used to calculate the probability that a user suffers from a target disease and the probability that the user does not suffer from the target disease under a data condition in an individual data set of the user, and the classification result at least includes two results of the risk of suffering from the target disease and the risk of not suffering from the target disease of the user corresponding to the individual data set by comparing the two probabilities.
One or more target diseases may be used, and a corresponding classification result may be obtained for each target disease.
S4: and carrying out health early warning on the user according to the classification result.
Specifically, the server determines whether the user corresponding to the individual data set has a risk of the target disease according to the classification result obtained in step S3, and if so, performs a health early warning on the user.
The health early warning method may specifically be sending an illness risk prompt message of the target disease to the user through an instant message such as a short message or a WeChat, or a communication method such as an email, or a preventive measure for the target disease.
For example, aiming at target diseases such as hypertensive heart disease and the like, the illness risk prompt information sent by the server side can suggest that the diet is low in salt, sugar and exercise, and unreasonable diet data can be synchronously sent to the user to remind the user of paying attention.
In the embodiment, hospital diagnosis records, health application data and life application data of a user are obtained from preset block chain nodes, the health data of the user scattered in various channels are timely stored in the block chain nodes, comprehensive health data of the user are obtained through a block chain network, attribute contents of preset characteristic attributes are extracted from the comprehensive health data, the extracted attribute contents of each characteristic attribute form an individual data set to be processed according to preset dimensions, the individual data set covers inspection results and diagnosis results of the user when the user visits a hospital, body index detection data in daily life and health data related to living habits, the individual data set can comprehensively and comprehensively reflect the health condition of the user, and then the individual data set is classified based on a Bayesian classifier according to a sample data set of a target disease in a preset sample database, the classification result of the user corresponding to the individual data set is obtained, health early warning is conducted on the user according to the classification result, and on the basis that the individual data set contains comprehensive and complete health data of the user, the probability of the target disease suffering risk of the user corresponding to the individual data set can be accurately calculated according to the sample data set of the target disease by adopting a naive Bayesian classifier, so that the accuracy of the individual health early warning is effectively improved.
In an embodiment, as shown in fig. 3, in step S3, classifying the individual data set based on a naive bayes classifier according to a sample data set of a target disease in a preset sample data base to obtain a classification result of a user corresponding to the individual data set, which specifically includes steps S31 to S36, which are detailed as follows:
s31: calculating class C from the sample data set of the target diseaseiA priori probability P (C) ofi) Wherein i is 0 or 1, class C0Class C for the presence of risk of target disease1Is the absence of risk of the target disease.
In particular, class CiA priori probability P (C) ofi) The method is to calculate only the class C without considering the attribute content of the characteristic attribute in the sample data setiThe probability of occurrence. For example, if the total number of samples in the sample data set of the target disease is 1000, wherein the number of samples with the target disease is 400 and the number of samples without the target disease is 600, the category C is determined0A priori probability P (C) of0) 400/1000 ═ 0.4, class C1A priori probability P (C) of1) 600/1000 ═ 0.6.
S32: calculating the category C of the individual data set X according to the following formula (1)iProbability P (C)i|X)：
Wherein X is (X)1,x2,...,xn)，xj＝(a1(tj),a2(tj),...,am(tj))TN is the number of time points of a preset time period, xjFor the vector component composed of the attribute content of each characteristic attribute at the jth time point in the preset time period, tjIs the jth time point in the preset time period, ak(tj) As a characteristic attribute akAt a point in time tjM is the number of characteristic attributes, k belongs to [1, m ∈]。
Specifically, the individual data set is a vector matrix composed of vector components, and with time as a preset dimension, the attribute content of each characteristic attribute at each preset time point in a preset time period is taken as a vector component. Calculating in known occurrence class CiIn the case of (1), condition xjConditional probability of occurrence P (x)j|Ci) N conditional probabilities are obtained, and the n conditional probabilities and the prior probability P (C) obtained in step S31 are calculatedi) As an individual data set X in class CiProbability P (C)i|X)。
As can be appreciated, class CiComprising C0And C1Two cases, therefore, two probability values, one for each individual data set X in category C, can be obtained from step S31 and step S320Probability P (C)0| X), and the individual data set X is in category C1Probability P (C)1I X), wherein P (C)0| X) represents the probability that the user corresponding to the individual data set has the risk of the target disease, P (C)1| X) represents the probability that the user corresponding to the individual data set does not have the risk of the target disease.
S33: calculating P (C)0I X) and P (C)1| X) absolute difference between the values.
Specifically, P (C) obtained according to step S320I X) and P (C)1| X), the absolute difference between the two is calculated.
S34: and if the absolute difference value is smaller than or equal to a preset deviation threshold value, determining that the classification result is that the user belongs to the potential risk group of the target disease.
Specifically, it is determined whether the absolute difference obtained in step S33 is less than or equal to a preset deviation threshold, and if the absolute difference is less than or equal to the preset deviation threshold, it indicates that the probability that the user corresponding to the individual data set has the risk of the target disease is closer to the probability that the user does not have the risk of the target disease, and at this time, the user is taken as a potentially-risky group of the target disease to perform periodic prevention and screening reminding, that is, the classification result is that the user belongs to the potentially-risky group of the target disease.
S35: if the absolute difference is greater than the preset deviation threshold, and P (C)0| X) is greater than P (C)1And | X), confirming that the classification result is that the user has the risk of the target disease.
Specifically, if the absolute difference obtained in step S33 is greater than the preset deviation threshold, then the method further depends on P (C)0I X) and P (C)1| X) to determine whether the user is at risk of the target disease.
If P (C)0| X) is greater than P (C)1If the probability that the user has the risk of the target disease is far greater than the probability that the user does not have the risk of the target disease, the classification result indicates that the user has the risk of the target disease.
S36: if the absolute difference is greater than the preset deviation threshold, and P (C)0| X) is less than P (C)1| X), confirming that the classification result is that the user does not have the risk of the target disease.
Specifically, if P (C) is greater than the preset deviation threshold value under the condition that the absolute difference obtained in step S33 is greater than the preset deviation threshold value0| X) is less than P (C)1If the probability that the user has the risk of the target disease is far less than the probability that the user does not have the risk of the target disease, the classification result is that the user does not have the risk of the target disease.
In this embodiment, first, the category C is calculated according to the sample data set of the target disease0A priori probability P (C) of0) And class C1Prior summary ofRate P (C)1) Then, the individual data set X in category C is calculated according to formula (1)0Probability P (C)0| X), and the individual data set X is in category C1Probability P (C)1| X), then by pair P (C)0I X) and P (C)1I X) to determine whether the user has the classification result of the disease risk of the target disease, so that the individual data set is accurately classified based on a naive Bayes classifier, an accurate data base is provided for the subsequent health early warning according to the classification result, and the accuracy of the individual health early warning is improved.
In an embodiment, as shown in fig. 4, in step S4, the method for performing health warning on the user according to the classification result specifically includes steps S41 to S42, which are detailed as follows:
s41: and if the classification result is that the user belongs to the potential risk group of the target disease, sending prevention prompt information of the target disease to the user.
Specifically, if the server obtains the classification result according to step S34 that the user belongs to the potentially risky group of the target disease, the server sends the user a prevention prompt message containing the preventive measures, dietary advice, exercise advice, and the like of the target disease, and may send a screening prompt for the target disease to the user in a regular prompt manner, so as to prompt the user to go to the hospital in time for regular examination.
S42: and if the classification result indicates that the user has the risk of the target disease, pre-disease early warning is carried out on the user.
Specifically, if the server determines that the user has a risk of the target disease according to the classification result obtained in step S35, the server sends pre-disease warning information to the user, where the pre-disease warning information includes a prompt that the user has a risk of the target disease and the calculated probability of the risk of the target disease.
Further, the server presets different early warning levels, and sets a corresponding relation between the classification result and the early warning levels. Each early warning level corresponds to a preset message sending mode, for example, for a low-level early warning level, the corresponding message sending mode may be a mail or short message mode, and for a high-level early warning level, the corresponding message sending mode may be an instant message or telephone mode.
For example, for the classification result of the potentially risky population with the target disease belonging to the user, the corresponding early warning level may be a first-level early warning, and for the classification result of the risk of the target disease existing in the user, the corresponding early warning level may be a second-level early warning, the message sending mode corresponding to the first-level early warning is an email mode, and the message sending mode corresponding to the second-level early warning is an instant message mode.
In the embodiment, for users belonging to potential risk groups of the target disease, the server side sends the prevention prompt information of the target disease, and for users with the risk of the target disease, the server side sends the pre-disease early warning information, so that different health early warning strategies are adopted according to different classification results, and the intelligence level of personal health early warning is enhanced.
In an embodiment, as shown in fig. 5, after step S1, the health status of the user may be monitored according to the hospital diagnostic record and a health pre-warning is performed, which specifically includes steps S51 to S53, which are detailed as follows:
s51: and acquiring the medical diagnosis result of the user from the hospital diagnosis record.
Specifically, the attribute content of the characteristic attribute of the medical diagnosis result is obtained from the hospital diagnosis record, and the attribute content records whether the medical diagnosis result of a certain disease is suffered by the user.
S52: and acquiring a target health index corresponding to the medical diagnosis result according to the corresponding relation between the preset diseases and the health indexes.
Specifically, the server presets a health index corresponding to each disease, the health index is an index definition of body index detection data and life habit related health data in daily life, and the index definition comprises index items and reasonable parameter values thereof.
For different diseases, the corresponding health indexes may contain the same index items, but correspond to different reasonable parameter values. For example, the health indicators for anemia and diabetes both include the indicator of blood pressure, but the values of the corresponding reasonable parameters are different.
The server extracts the disease information of the user from the medical diagnosis result, and obtains a health index corresponding to the extracted disease information, namely a target health index, according to the corresponding relation between the disease and the health index.
S53: and if the health application data or the life application data do not meet the requirements of the target health indexes, performing health early warning on the user.
Specifically, the server extracts the same characteristic attribute and the attribute content as the index item included in the target health index from the characteristic attributes of the health application data and the life application data obtained in step S1, and determines whether the attribute content belongs to the range of the reasonable parameter value corresponding to the index item in the target health index, if the attribute content belongs to the range of the reasonable parameter value corresponding to the index item in the target health index, it is determined that the health application data or the life application data meets the requirement of the target health index, and if the attribute content does not belong to the range of the reasonable parameter value corresponding to the index item in the target health index, it is determined that the health application data or the life application data meets the requirement of the non-target health index.
And if the server judges that the health application data or the life application data do not meet the requirements of the target health indexes, health early warning is carried out on the user. The health early warning method may specifically be sending a risk prompting message of a disease recorded in the medical diagnosis result to the user through an instant message such as a short message or a WeChat, or a communication method such as an email, or a preventive measure for the disease.
In this embodiment, the server obtains a medical diagnosis result of the user from a hospital diagnosis record stored in the block chain, obtains a target health index corresponding to the medical diagnosis result according to a preset correspondence between a disease and a health index, and determines whether to perform health early warning on the user by judging whether the health application data or the life application data meets the requirement of the target health index, so that the health index is determined in a targeted manner in combination with the actual disease condition of the user, and reasonable health indexes corresponding to different diseases are set for the different diseases, so that the monitoring accuracy on the health condition of the user is improved, and the accuracy of the health early warning is further improved.
In one embodiment, the block link points include diagnostic information block link nodes, health information block link nodes, and life information block link nodes.
The diagnosis information block chain node is used for storing hospital diagnosis records of each user, the health information block chain link point is used for storing health application data of each user, and the life information block chain link point is used for storing life application data of each user.
Further, as shown in fig. 6, in step S1, the method for acquiring the health data of the user from the preset block link point specifically includes steps S11 to S12, which are detailed as follows:
s11: and acquiring the identity identification information of the user.
Specifically, the server acquires the identity information of a user who needs to perform health early warning. The identity information is used to uniquely identify the user, and may specifically be an identification number of the user, a mobile phone number, or other information capable of uniquely identifying the user.
S12: hospital diagnosis records corresponding to the identity identification information are obtained from diagnosis information blockchain nodes, health application data corresponding to the identity identification information are obtained from health information blockchain nodes, and life application data corresponding to the identity identification information are obtained from life information blockchain nodes.
Specifically, in each block chain node, the identity information of the user is stored in correspondence with the health data of the user, and the health data corresponding to the identity information can be queried through the identity information.
The server side uses the user identification information obtained in step S11 to obtain a hospital diagnosis record corresponding to the identification information from the diagnosis information block chain node in a serial or parallel manner, obtain health application data corresponding to the identification information from the health information block chain node, and obtain life application data corresponding to the identification information from the life information block chain node.
And the server takes the acquired hospital diagnosis record, the acquired health application data and the acquired life application data as health data corresponding to the identity identification information of the user.
In this embodiment, a plurality of different block chain link points are used for storing different types of health data respectively, so that the different types of health data can be stored independently, unified centralized management is facilitated, corresponding health data are obtained from each block chain node according to the identity identification information of a user, a server can be used as a unified platform to perform comprehensive and credible health monitoring service, and comprehensive analysis and health early warning on the obtained health data stored in each block chain node are accurately completed.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
In one embodiment, a health data processing device is provided, and the health data processing device corresponds to the health data processing method in the above embodiments one to one. As shown in fig. 7, the health data processing apparatus includes: the system comprises a data acquisition module 10, an attribute extraction module 20, a user classification module 30 and a health early warning module 40. The functional modules are explained in detail as follows:
the data acquisition module 10 is used for acquiring health data of a user from preset block link points, wherein the health data comprises hospital diagnosis records, health application data and life application data;
the attribute extraction module 20 is configured to extract preset attribute contents of feature attributes from the hospital diagnostic record, the health application data and the life application data, and form an individual data set to be processed according to preset dimensions from the extracted attribute contents of each feature attribute;
the user classification module 30 is configured to classify the individual data set according to a sample data set of a target disease in a preset sample data base based on a naive bayesian classifier, and obtain a classification result of a user corresponding to the individual data set, where the naive bayesian classifier is configured to analyze a risk of the target disease existing in the user corresponding to the individual data set;
and the health early warning module 40 is used for carrying out health early warning on the user according to the classification result.
Further, the user classification module 30 includes:
a first probability computation submodule 301 for computing a class C based on the sample data set of the target diseaseiA priori probability P (C) ofi) Wherein i is 0 or 1, class C0Class C for the presence of risk of target disease1In the absence of risk of the target disease;
a second probability calculation submodule 302 for calculating the category C of the individual data set X according to the following formulaiProbability P (C)i|X)：
Wherein X is (X)1,x2,...,xn)，xj＝(a1(tj),a2(tj),...,am(tj))TN is the number of time points of a preset time period, xjFor the vector component composed of the attribute content of each characteristic attribute at the jth time point in the preset time period, tjIs the jth time point in the preset time period, ak(tj) As a characteristic attribute akAt a point in time tjM is the number of characteristic attributes, k belongs to [1, m ∈]；
Probability difference operator module 303 for calculating P (C)0I X) and P (C)1| X) absolute difference value;
the first classification submodule 304 is configured to determine that the classification result is a potentially risky group where the user belongs to the target disease if the absolute difference is smaller than or equal to a preset deviation threshold;
a second classification submodule 305 for classifying if the absolute difference is greater than a predetermined deviation threshold, and P: (C0| X) is greater than P (C)1I X), confirming that the classification result is that the user has the risk of the target disease;
a third classification submodule 306 for classifying P (C) if the absolute difference is greater than a predetermined deviation threshold0| X) is less than P (C)1| X), confirming that the classification result is that the user does not have the risk of the target disease.
Further, the health-warning module 40 includes:
the prevention prompting submodule 401 is configured to send a prevention prompting message for the target disease to the user if the classification result indicates that the user belongs to a potential risk group of the target disease;
and the pre-disease early warning submodule 402 is configured to perform pre-disease early warning on the user if the classification result indicates that the user has a risk of the target disease.
Further, the health data processing apparatus further includes:
a medical data acquisition module 51, configured to acquire a medical diagnosis result of the user from a hospital diagnosis record;
the health index determining module 52 is configured to obtain a target health index corresponding to the medical diagnosis result according to a preset correspondence between the disease and the health index;
and the early warning judgment module 53 is configured to perform a health early warning on the user if the health application data or the life application data does not meet the requirement of the target health index.
Further, the block link point includes a diagnosis information block link node, a health information block link node, and a life information block link node, and the data obtaining module 10 includes:
an identification obtaining submodule 101, configured to obtain identity identification information of a user;
the partition extraction submodule 102 is configured to obtain a hospital diagnostic record corresponding to the identity information from the diagnostic information block chain node, obtain health application data corresponding to the identity information from the health information block chain node, and obtain life application data corresponding to the identity information from the life information block chain node.
For the specific definition of the health data processing device, reference may be made to the above definition of the health data processing method, which is not described herein again. The respective modules in the health data processing apparatus described above may be implemented in whole or in part by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a health data processing method.
In an embodiment, a computer device is provided, which includes a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the steps of the health data processing method in the above embodiments, such as the steps S1 to S4 shown in fig. 2. Alternatively, the processor, when executing the computer program, implements the functions of the respective modules/units of the health data processing apparatus in the above-described embodiments, such as the functions of the modules 10 to 40 shown in fig. 7. To avoid repetition, further description is omitted here.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when being executed by a processor, implements the method for processing health data in the above-mentioned method embodiment, or which, when being executed by a processor, implements the functions of the modules/units in the health data processing apparatus in the above-mentioned apparatus embodiment. To avoid repetition, further description is omitted here.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. A health data processing method, characterized in that the health data processing method comprises:
acquiring health data of a user from preset block link points, wherein the health data comprises hospital diagnosis records, health application data and life application data;
respectively extracting preset attribute contents of characteristic attributes from the hospital diagnosis record, the health application data and the life application data, and forming an individual data set to be processed by the extracted attribute contents of each characteristic attribute according to a preset dimension;
classifying the individual data set based on a naive Bayes classifier according to a sample data set of a target disease in a preset sample database to obtain a classification result of the user corresponding to the individual data set, wherein the naive Bayes classifier is used for analyzing the risk of the target disease existing in the user corresponding to the individual data set;
and carrying out health early warning on the user according to the classification result.
2. The method of claim 1, wherein the classifying the individual data set according to a sample data set of a target disease in a preset sample data base based on a naive bayes classifier to obtain a classification result of the individual data set comprises:
calculating class C according to the sample data set of the target diseaseiA priori probability P (C) ofi) Wherein i is 0 or 1, class C0For the presence of risk of said target disease, class C1Is not at risk of developing the target disease;
calculating the individual data set X in category C as followsiProbability P (C)i|X)：
Wherein X is (X)1,x2,...,xn)，xj＝(a1(tj),a2(tj),...,am(tj))TN is the number of time points of a preset time period, xjFor the vector component composed of the attribute content of each characteristic attribute at the jth time point in the preset time period, tjIs the jth time point, a, in the preset time periodk(tj) As a characteristic attribute akAt a point in time tjM is the number of the characteristic attributes, k belongs to [1, m ∈]；
Calculating P (C)0I X) and P (C)1| X) absolute difference value;
if the absolute difference is smaller than or equal to a preset deviation threshold, confirming that the classification result is that the user belongs to the potential risk group of the target disease;
if the absolute difference is greater than the preset deviation threshold, and P (C)0| X) is greater than P (C)1If the classification result is confirmed to be the risk of the target disease existing in the user;
if the absolute difference is greater than the preset deviation threshold, and P (C)0| X) is less than P (C)1| X), confirming that the classification result is that the user does not have the risk of the target disease.
3. The health data processing method of claim 2, wherein the pre-warning of the health of the user according to the classification result comprises:
if the classification result is that the user belongs to the potential risk group of the target disease, sending a prevention prompt message of the target disease to the user;
and if the classification result indicates that the user has the risk of the target disease, pre-disease early warning is carried out on the user.
4. The health data processing method according to claim 1, wherein after acquiring the health data of the user from the preset block link point, the health data processing method further comprises:
acquiring medical diagnosis results of the user from the hospital diagnosis records;
acquiring a target health index corresponding to the medical diagnosis result according to a preset corresponding relation between the disease and the health index;
and if the health application data or the life application data do not meet the requirements of the target health indexes, performing health early warning on the user.
5. The health data processing method according to claim 1, wherein the blockchain node includes a diagnosis information blockchain node, a health information blockchain node, and a life information blockchain node, and the acquiring the health data of the user from the preset blockchain node includes:
acquiring the identity identification information of the user;
acquiring the hospital diagnosis record corresponding to the identity identification information from the diagnosis information block chain node, acquiring the health application data corresponding to the identity identification information from the health information block chain node, and acquiring the life application data corresponding to the identity identification information from the life information block chain node.
6. A health data processing apparatus, characterized in that the health data processing apparatus comprises:
the data acquisition module is used for acquiring health data of a user from preset block link points, wherein the health data comprises hospital diagnosis records, health application data and life application data;
the attribute extraction module is used for respectively extracting preset attribute contents of characteristic attributes from the hospital diagnosis record, the health application data and the life application data, and forming an individual data set to be processed according to preset dimensions by using the extracted attribute contents of each characteristic attribute;
the system comprises a user classification module, a classification module and a classification module, wherein the user classification module is used for classifying the individual data set based on a naive Bayesian classifier according to a sample data set of a target disease in a preset sample data base to obtain a classification result of the user corresponding to the individual data set, and the naive Bayesian classifier is used for analyzing the risk of the target disease existing in the user corresponding to the individual data set;
and the health early warning module is used for carrying out health early warning on the user according to the classification result.
7. The health data processing apparatus of claim 6, wherein the user classification module comprises:
a first probability calculation submodule for calculating a class C according to the sample data set of the target diseaseiA priori probability P (C) ofi) Wherein i is 0 or 1, class C0For the presence of risk of said target disease, class C1Is not at risk of developing the target disease;
a second probability calculation submodule for calculating the category C of the individual data set X according to the following formulaiProbability P (C)i|X)：
Wherein X is (X)1,x2,...,xn)，xj＝(a1(tj),a2(tj),...,am(tj))TN is the number of time points of a preset time period, xjFor the vector component composed of the attribute content of each characteristic attribute at the jth time point in the preset time period, tjIs the jth time point, a, in the preset time periodk(tj) As a characteristic attribute akAt a point in time tjM is the characteristic genusNumber of sex, k ∈ [1, m ]]；
A probability difference value calculation submodule for calculating P (C)0I X) and P (C)1| X) absolute difference value;
the first classification submodule is used for confirming that the classification result is the potential risk group of the user belonging to the target disease if the absolute difference value is smaller than or equal to a preset deviation threshold value;
a second classification submodule for classifying if the absolute difference is greater than the preset deviation threshold, and P (C)0| X) is greater than P (C)1If the classification result is confirmed to be the risk of the target disease existing in the user;
a third classification submodule for classifying the absolute difference value as being greater than the preset deviation threshold value, and P (C)0| X) is less than P (C)1| X), confirming that the classification result is that the user does not have the risk of the target disease.
8. The health data processing apparatus of claim 7, wherein the health alert module comprises:
the prevention prompting submodule is used for sending prevention prompting information of the target disease to the user if the classification result is that the user belongs to the potential risk group of the target disease;
and the pre-disease early warning sub-module is used for performing pre-disease early warning on the user if the classification result indicates that the user has the risk of the target disease.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the health data processing method according to any one of claims 1 to 5 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, implements the health data processing method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910842462.0A CN110752035A (en) | 2019-09-06 | 2019-09-06 | Health data processing method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910842462.0A CN110752035A (en) | 2019-09-06 | 2019-09-06 | Health data processing method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110752035A true CN110752035A (en) | 2020-02-04 |
Family
ID=69276120
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910842462.0A Pending CN110752035A (en) | 2019-09-06 | 2019-09-06 | Health data processing method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110752035A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111370115A (en) * | 2020-03-10 | 2020-07-03 | 武汉诶唉智能科技有限公司 | Large health artificial intelligence prevention management method and system based on block chain |
| CN111370125A (en) * | 2020-03-10 | 2020-07-03 | 武汉诶唉智能科技有限公司 | Big health AI (AI) prevention management system and method based on 5G and block chain |
| CN111708820A (en) * | 2020-06-17 | 2020-09-25 | 中国银行股份有限公司 | Travel data query method |
| CN111899872A (en) * | 2020-06-16 | 2020-11-06 | 东南大学 | Health risk control method based on intelligent health identification code and block chain integration technology |
| CN112133434A (en) * | 2020-09-17 | 2020-12-25 | 吾征智能技术(北京)有限公司 | Dietary habit-based hyperlipidemia auxiliary diagnosis system, device and storage medium |
| CN112465231A (en) * | 2020-12-01 | 2021-03-09 | 平安医疗健康管理股份有限公司 | Method, apparatus and readable storage medium for predicting regional population health status |
| CN112527902A (en) * | 2020-12-08 | 2021-03-19 | 李桂梅 | Catering personnel body data sharing system based on block chain |
| CN113436725A (en) * | 2021-06-24 | 2021-09-24 | 平安国际智慧城市科技股份有限公司 | Data processing method, system, computer device and computer readable storage medium |
| WO2021238460A1 (en) * | 2020-05-29 | 2021-12-02 | 华为技术有限公司 | Risk pre-warning method, risk behavior information acquisition method, and electronic device |
| CN113823412A (en) * | 2021-09-29 | 2021-12-21 | 康键信息技术（深圳）有限公司 | Health management plan generation method and device, electronic equipment and storage medium |
| WO2022062353A1 (en) * | 2020-09-23 | 2022-03-31 | 康键信息技术（深圳）有限公司 | Medical data processing method and apparatus, and computer device and storage medium |
| CN114694355A (en) * | 2020-12-30 | 2022-07-01 | 深圳融昕医疗科技有限公司 | Remote early warning method and system |
| CN115662643A (en) * | 2022-10-27 | 2023-01-31 | *** | Diabetes health medical big data acquisition system |
| CN115910339A (en) * | 2022-11-25 | 2023-04-04 | 浙江大学 | Weight monitoring method, system, computer device and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103955703A (en) * | 2014-04-25 | 2014-07-30 | 杭州电子科技大学 | Medical image disease classification method based on naive Bayes |
| CN108922623A (en) * | 2018-07-12 | 2018-11-30 | 中国铁道科学研究院集团有限公司 | A kind of health risk assessment and Disease Warning Mechanism information system |
| KR20190070430A (en) * | 2017-12-13 | 2019-06-21 | (주)엔텔스 | Estimation method and apparatus for name of disease based on big data analysis |
| CN110033866A (en) * | 2019-03-08 | 2019-07-19 | 平安科技（深圳）有限公司 | Healthalert method, apparatus, computer equipment and storage medium |
-
2019
- 2019-09-06 CN CN201910842462.0A patent/CN110752035A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103955703A (en) * | 2014-04-25 | 2014-07-30 | 杭州电子科技大学 | Medical image disease classification method based on naive Bayes |
| KR20190070430A (en) * | 2017-12-13 | 2019-06-21 | (주)엔텔스 | Estimation method and apparatus for name of disease based on big data analysis |
| CN108922623A (en) * | 2018-07-12 | 2018-11-30 | 中国铁道科学研究院集团有限公司 | A kind of health risk assessment and Disease Warning Mechanism information system |
| CN110033866A (en) * | 2019-03-08 | 2019-07-19 | 平安科技（深圳）有限公司 | Healthalert method, apparatus, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| QXWONLY: "机器学习实战（五）朴素贝叶斯算法", pages 9, Retrieved from the Internet <URL:https://blog.csdn.net/qs17809259715/article/details/96153630> * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111370125A (en) * | 2020-03-10 | 2020-07-03 | 武汉诶唉智能科技有限公司 | Big health AI (AI) prevention management system and method based on 5G and block chain |
| CN111370115A (en) * | 2020-03-10 | 2020-07-03 | 武汉诶唉智能科技有限公司 | Large health artificial intelligence prevention management method and system based on block chain |
| WO2021238460A1 (en) * | 2020-05-29 | 2021-12-02 | 华为技术有限公司 | Risk pre-warning method, risk behavior information acquisition method, and electronic device |
| CN111899872A (en) * | 2020-06-16 | 2020-11-06 | 东南大学 | Health risk control method based on intelligent health identification code and block chain integration technology |
| CN111708820A (en) * | 2020-06-17 | 2020-09-25 | 中国银行股份有限公司 | Travel data query method |
| CN112133434A (en) * | 2020-09-17 | 2020-12-25 | 吾征智能技术(北京)有限公司 | Dietary habit-based hyperlipidemia auxiliary diagnosis system, device and storage medium |
| WO2022062353A1 (en) * | 2020-09-23 | 2022-03-31 | 康键信息技术（深圳）有限公司 | Medical data processing method and apparatus, and computer device and storage medium |
| CN112465231B (en) * | 2020-12-01 | 2023-02-03 | 深圳平安医疗健康科技服务有限公司 | Method, apparatus and readable storage medium for predicting regional population health status |
| CN112465231A (en) * | 2020-12-01 | 2021-03-09 | 平安医疗健康管理股份有限公司 | Method, apparatus and readable storage medium for predicting regional population health status |
| CN112527902A (en) * | 2020-12-08 | 2021-03-19 | 李桂梅 | Catering personnel body data sharing system based on block chain |
| CN112527902B (en) * | 2020-12-08 | 2023-01-10 | 苏州鱼得水电气科技有限公司 | Catering personnel body data sharing system based on block chain |
| CN114694355A (en) * | 2020-12-30 | 2022-07-01 | 深圳融昕医疗科技有限公司 | Remote early warning method and system |
| CN114694355B (en) * | 2020-12-30 | 2024-02-23 | 深圳融昕医疗科技有限公司 | Remote early warning method and system |
| CN113436725A (en) * | 2021-06-24 | 2021-09-24 | 平安国际智慧城市科技股份有限公司 | Data processing method, system, computer device and computer readable storage medium |
| CN113823412A (en) * | 2021-09-29 | 2021-12-21 | 康键信息技术（深圳）有限公司 | Health management plan generation method and device, electronic equipment and storage medium |
| CN113823412B (en) * | 2021-09-29 | 2024-04-12 | 康键信息技术（深圳）有限公司 | Health management plan generation method and device, electronic equipment and storage medium |
| CN115662643A (en) * | 2022-10-27 | 2023-01-31 | *** | Diabetes health medical big data acquisition system |
| CN115910339A (en) * | 2022-11-25 | 2023-04-04 | 浙江大学 | Weight monitoring method, system, computer device and storage medium |
| CN115910339B (en) * | 2022-11-25 | 2023-07-07 | 浙江大学 | Weight monitoring method, system, computer device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110752035A (en) | Health data processing method and device, computer equipment and storage medium | |
| KR101873926B1 (en) | Method for providing medical counseling service between insurance organization and specialist based on bigdata | |
| US20190279363A1 (en) | Medical evaluation machine learning workflows and processes | |
| US9955869B2 (en) | System and method for supporting health management services | |
| CN111145910A (en) | Abnormal case identification method and device based on artificial intelligence and computer equipment | |
| US20170147777A1 (en) | Method and apparatus for predicting health data value through generation of health data pattern | |
| KR20180002234A (en) | A smart examination apparatus for dementia early diagnosis and the method by using the same | |
| CN117238458B (en) | Critical care cross-mechanism collaboration platform system based on cloud computing | |
| DE112014000897T5 (en) | Learning health systems and procedures | |
| Sreejith et al. | A real time patient monitoring system for heart disease prediction using random forest algorithm | |
| CN110729054B (en) | Abnormal diagnosis behavior detection method and device, computer equipment and storage medium | |
| US11676704B2 (en) | Systems and methods for processing electronic images for health monitoring and forecasting | |
| KR102342770B1 (en) | A health management counseling system using the distribution of predicted disease values | |
| CN109598302B (en) | Method, device and equipment for predicting treatment cost and computer readable storage medium | |
| CN108766584A (en) | disease pre-warning method and system | |
| Chakraborty et al. | Identification of chronic wound status under tele-wound network through smartphone | |
| CN113990482A (en) | Health data processing system and method | |
| CN112131277A (en) | Medical data anomaly analysis method and device based on big data and computer equipment | |
| CN111742372A (en) | Learning filter for detecting indicators in healthcare data | |
| CN111221876A (en) | Data dimension reduction processing method and device, computer equipment and storage medium | |
| Kavitha et al. | IoT-cloud-based health care system framework to detect breast abnormality | |
| Jersak et al. | A systematic review on mobile health care | |
| Melnykova et al. | Anomalies detecting in medical metrics using machine learning tools | |
| CN109003193B (en) | Method, device, computer equipment and storage medium for predicting insurance risk | |
| KR20180002229A (en) | An agent apparatus for constructing database for dementia information and the operating method by using the same |
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 |