CN108154928A - A kind of methods for the diagnosis of diseases and device - Google Patents
A kind of methods for the diagnosis of diseases and device Download PDFInfo
- Publication number
- CN108154928A CN108154928A CN201711448095.3A CN201711448095A CN108154928A CN 108154928 A CN108154928 A CN 108154928A CN 201711448095 A CN201711448095 A CN 201711448095A CN 108154928 A CN108154928 A CN 108154928A
- Authority
- CN
- China
- Prior art keywords
- disease
- diagnosis
- knowledge
- medical
- treatment
- 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
Abstract
This application discloses a kind of methods for the diagnosis of diseases and devices, pre-establish disease model, and the disease model is used for the learning outcome realization medical diagnosis on disease for having electronic health record and/or existing medical knowledge according to machine learning and obtaining;Based on this, when carrying out medical diagnosis on disease for certain electronic health record, first obtain target electronic case history to be diagnosed, the medical record information in the target electronic case history is analyzed further according to the disease model, to generate disease list of probabilities, the medical record information includes the available information for being used to implement medical diagnosis on disease, and the disease list of probabilities includes the authenticity probability of at least one suspected disease and the suspected disease.Since the disease model has learnt existing electronic health record and/or medical knowledge, to disease knowledge covering more fully, therefore, when carrying out medical diagnosis on disease using the disease model, diagnostic result will be more accurate.
Description
Technical field
This application involves field of computer technology more particularly to a kind of methods for the diagnosis of diseases and devices.
Background technology
Clinician provides diagnostic service for patient at work, depends on learnt professional knowledge and personal doctor
The accumulation for the treatment of experience, professional vocational study approach are generally clinical guidelines, and clinical guidelines refer to the medical speciality committee and pass through power
Prestige medical journals publish for certain disease newest diagnose and treat guide document, can be expressed as clinical guidelines, specially
Family's common recognition and recommendation opinion etc..Case is difficult or common in clinician's routine work, it is possible that artificial
Mistake;In addition, the medical knowledge update of the possible higher speed development of the renewal of knowledge of doctor itself is slow, the diagnosis implemented is caused to be arranged
It applies and is unable to reach newest diagnostic level or even situations such as mistake is examined, failed to pinpoint a disease in diagnosis occur.
Therefore, there is an urgent need to a kind of auxiliary tools to assist to solve the problems in work for clinical workers, therefore, form
Clinical Decision Support Systems (Clinical Decision Support System, CDSS) based on expert system.
CDSS based on expert system reduces malpractice to a certain extent, but to depend on medicine special for its diagnostic method
Therefore the personal medical level of family, when the CDSS based on expert system is used to assist a physician as patient's progress medical diagnosis on disease, is examined
Disconnected result may be not accurate enough.
Invention content
In view of this, the main purpose of the embodiment of the present application is to provide a kind of methods for the diagnosis of diseases and device, Neng Gouti
The accuracy of high diagnostic result.
In a first aspect, this application provides a kind of methods for the diagnosis of diseases, including:
Obtain target electronic case history;
Medical record information in the target electronic case history is analyzed according to the disease model built in advance, to generate disease probability
List;Wherein, the disease model is used for having the study that electronic health record and/or existing medical knowledge obtain according to machine learning
As a result medical diagnosis on disease is realized, the medical record information includes the available information for being used to implement medical diagnosis on disease, the disease list of probabilities
Authenticity probability including at least one suspected disease and the suspected disease.
Optionally, the machine learning has electronic health record, including:
Collect different existing electronic health records;
Medical record information in the existing electronic health record is learnt using machine learning mode, forms case history learning outcome, institute
Case history learning outcome is stated to include in the existing corresponding diagnosed disease of electronic health record and the existing electronic health record about institute
State the corresponding disease reaction information of diagnosed disease.
Optionally, it after the generation disease list of probabilities, further includes:
According to the case history learning outcome, the case history similar to the suspected disease is provided.
Optionally, the machine learning has medical knowledge, including:
The disease knowledge having in medical information is obtained, forms disease knowledge library;
Disease knowledge in the disease knowledge library is learnt using machine learning mode, forms knowledge learning as a result, described
Knowledge learning result includes at least one actual disease and the corresponding disease reaction information of the actual disease.
Optionally, the disease model is additionally operable to the diagnosis and treatment knowledge in disease knowledge library described in machine learning, forms diagnosis and treatment
Learning outcome, the diagnosis and treatment learning outcome include the corresponding diagnosis and treatment scheme of the actual disease;
Then, it after the generation disease list of probabilities, further includes:
If the suspected disease is a kind of actual disease in the knowledge learning result, according to the diagnosis and treatment learning outcome
Diagnosis and treatment scheme is provided for each suspected disease in the disease list of probabilities.
Optionally, it after the generation disease list of probabilities, further includes:
According to the knowledge learning as a result, providing and the relevant Evidence-based Medicine Literature of the suspected disease.
Optionally, the method further includes:
According to the disease knowledge that clinical guidelines are recorded, diagnosis and treatment rule base is formed, the diagnosis and treatment rule base includes the clinic
The corresponding diagnosis and treatment rule of each disease that guide is recorded, the diagnosis and treatment rule includes the diagnostic rule of corresponding disease and treatment is advised
Then;
Then, after the disease model that the basis is built in advance analyzes the medical record information in the target electronic case history, also
Including:
Judge whether the medical record information in the target electronic case history meets the diagnosis and treatment rule in the diagnosis and treatment rule base
Then, if it is not, then carrying out early warning.
Second aspect, this application provides a kind of medical diagnosis on disease device, including:
Electronic health record acquiring unit, for obtaining target electronic case history;
Medical record information analytic unit, for analyzing the disease in the target electronic case history according to the disease model built in advance
Information is gone through, to generate disease list of probabilities;Wherein, the disease model be used for according to machine learning have electronic health record and/or
The learning outcome that existing medical knowledge obtains realizes medical diagnosis on disease, and the medical record information includes being used to implement the available of medical diagnosis on disease
Information, the disease list of probabilities include the authenticity probability of at least one suspected disease and the suspected disease.
Optionally, described device further includes:
Electronic health record collection device, for collecting different existing electronic health records;
Medical record information unit, for learning the case history letter in the existing electronic health record using machine learning mode
Breath, forms case history learning outcome, and the case history learning outcome includes the corresponding diagnosed disease of the existing electronic health record and institute
It states in existing electronic health record about the corresponding disease reaction information of the diagnosed disease.
Optionally, described device further includes:
Similar case history provides unit, according to the case history learning outcome, provides the case history similar to the suspected disease.
Optionally, described device further includes:
Disease knowledge acquiring unit for obtaining the disease knowledge in existing medical information, forms disease knowledge library;
Disease knowledge unit, for learning the disease knowledge in the disease knowledge library using machine learning mode,
Knowledge learning is formed as a result, the knowledge learning result includes at least one actual disease and the corresponding disease of the actual disease
Sick reaction information.
Optionally, described device further includes:
Diagnosis and treatment knowledge learning unit for the diagnosis and treatment knowledge in disease knowledge library described in machine learning, forms diagnosis and treatment study
As a result, the diagnosis and treatment learning outcome includes the corresponding diagnosis and treatment scheme of the actual disease;
Then, described device further includes:
Diagnosis and treatment scheme provides unit, if being a kind of actual disease in the knowledge learning result for the suspected disease,
Then diagnosis and treatment scheme is provided for each suspected disease in the disease list of probabilities according to the diagnosis and treatment learning outcome.
Optionally, described device further includes:
Medical literature provides unit, for according to the knowledge learning as a result, providing and the suspected disease is relevant follows
Demonstrate,prove medical literature.
Optionally, described device further includes:
Diagnosis and treatment rule forms unit, for the disease knowledge recorded according to clinical guidelines, forms diagnosis and treatment rule base, described to examine
It treats rule base and includes the corresponding diagnosis and treatment rule of each disease that the clinical guidelines are recorded, the diagnosis and treatment rule includes corresponding disease
Diagnostic rule and treatment rule;
Then, described device further includes:
Medical record information judging unit, for judging whether the medical record information in the target electronic case history meets the diagnosis and treatment
A diagnosis and treatment rule in rule base, if it is not, then carrying out early warning.
A kind of methods for the diagnosis of diseases provided by the embodiments of the present application and device pre-establish disease model, the disease mould
Type is used for the learning outcome realization medical diagnosis on disease for having electronic health record and/or existing medical knowledge according to machine learning and obtaining;Base
In this, when carrying out medical diagnosis on disease for certain electronic health record, target electronic case history to be diagnosed first is obtained, further according to the disease
Medical record information in target electronic case history described in model analysis, to generate disease list of probabilities, the medical record information includes being used for
Realize the available information of medical diagnosis on disease, the disease list of probabilities includes at least one suspected disease and the suspected disease
Authenticity probability.Since the disease model has learnt existing electronic health record and/or medical knowledge, to disease knowledge covering more
To be comprehensive, therefore, when carrying out medical diagnosis on disease using the disease model, diagnostic result will be more accurate.
Description of the drawings
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or it will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is the application
Some embodiments, for those of ordinary skill in the art, without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 is a kind of flow chart of methods for the diagnosis of diseases provided by the embodiments of the present application;
Fig. 2 a are the exemplary plot provided by the embodiments of the present application that early warning is carried out according to diagnosis and treatment rule base;
Fig. 2 b are the exemplary plot that machine learning provided by the embodiments of the present application has medical knowledge;
Fig. 3 is the exemplary plot that the case history learning outcome that the application implementation provides is dissolved into disease model;
Fig. 4 a are the exemplary plot that knowledge based provided by the embodiments of the present application study structure disease model carries out medical diagnosis on disease;
Fig. 4 b are carried out disease and are examined to be provided by the embodiments of the present application based on case history study and knowledge learning structure disease model
Disconnected exemplary plot;
Fig. 5 is the method flow diagram that a kind of machine learning provided by the embodiments of the present application has electronic health record;
Fig. 6 is the exemplary plot that machine learning provided by the embodiments of the present application has electronic health record;
Fig. 7 is the method exemplary plot that a kind of machine learning provided by the embodiments of the present application has medical information;
Fig. 8 is a kind of schematic diagram for collecting medical knowledge provided by the embodiments of the present application;
Fig. 9 recommends exemplary plot for diagnosis and treatment scheme provided by the embodiments of the present application;
Figure 10 recommends schematic diagram for medical literature provided by the embodiments of the present application and similar case history;
Figure 11 is a kind of structure diagram of medical diagnosis on disease device provided by the embodiments of the present application.
Specific embodiment
Purpose, technical scheme and advantage to make the embodiment of the present application are clearer, below in conjunction with the embodiment of the present application
In attached drawing, the technical solution in the embodiment of the present application is clearly and completely described, it is clear that described embodiment is
Some embodiments of the present application, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art
All other embodiments obtained without making creative work shall fall in the protection scope of this application.
Through applicants have found that, the diagnostic method of the existing CDSS based on expert system depends primarily on medical expert
Personal medical level, due to the limitation of the personal medical level of medical expert, the CDSS for the expert system established may be caused
Inaccuracy so that use the CDSS based on expert system assist a physician for patient carry out medical diagnosis on disease when, diagnostic result is not
It is enough accurate.
To solve the above problems, the embodiment of the present application provides a kind of methods for the diagnosis of diseases and device, to certain electronic health record
When carrying out medical diagnosis on disease, target electronic case history to be diagnosed first is obtained, the target electronic is analyzed further according to the disease model
Medical record information in case history, to generate disease list of probabilities.Since the disease model is by learning existing electronic health record
And/or medical knowledge obtains, and to disease knowledge covering more fully, therefore, is examined when carrying out disease using the disease model
When disconnected, diagnostic result will be more accurate.
A kind of methods for the diagnosis of diseases shown in the application exemplary embodiment is introduced below in conjunction with attached drawing.
Be a kind of flow chart of methods for the diagnosis of diseases provided by the embodiments of the present application referring to Fig. 1, this method can include with
Lower step:
S101:Obtain target electronic case history.
In the present embodiment, certain electronic health record of pending medical diagnosis on disease is known as target electronic case history, wherein, electronic health record
It can be the medical records that patient is preserved, manages, transmitting, reappeared with electronic equipment, it can be understood as the number of traditionally on paper case history
Word version.
It can be examined in electronic health record including admission records, admission diagnosis, progress note, audit report, survey report, discharge
It is disconnected to wait documents, wherein, admission records can include the parts such as present illness history, past medical history, personal history, family history, auxiliary examination.
S102:Medical record information in the target electronic case history is analyzed according to the disease model built in advance, to generate disease
Sick list of probabilities.
Wherein, the disease model is used to having an electronic health record according to machine learning and/or existing medical knowledge obtains
Learning outcome realizes medical diagnosis on disease, and the medical record information includes the available information for being used to implement medical diagnosis on disease, the disease probability
List includes the authenticity probability of at least one suspected disease and the suspected disease.
In the present embodiment, the disease model can extract symptom information, the inspection letter in the target electronic case history
The medical record informations such as breath, checking information, and the medical record information and above-mentioned learning outcome are subjected to information matches, it is true according to matching result
The possibility size (i.e. authenticity probability) of fixed each suspected disease and each suspected disease.
It should be noted that when building disease model, under normal circumstances, can have medical knowledge by machine learning
In disease knowledge obtain disease model, obtained in this way, can have medical knowledge according to machine learning using disease model
Learning outcome realize medical diagnosis on disease.Wherein, the realization method that machine learning has medical knowledge will subsequently be introduced.
In the present embodiment, clinical guidelines can also be segmented, obtains word segmentation result, which can examine
Rule is treated, and the diagnosis and treatment rule is dissolved into disease model, so as to after suspected disease is determined according to disease model, Ke Yigen
Further the suspected disease is made a definite diagnosis according to diagnosis and treatment rule.
Wherein, disease knowledge has been recorded in clinical guidelines, and has specified the diagnosis and treatment rule of each disease, diagnosis and treatment rule packet
Include the diagnostic rule of corresponding disease and treatment rule.For example, for disease A, the corresponding diagnostic rules of disease A is meet item simultaneously
Part 1, condition 2, condition 3 and condition 4, that is to say, that only meet condition 1, condition 2, condition 3 and condition 4 simultaneously, can just make a definite diagnosis
For disease A, likewise, the treatment rule of disease A should equally meet one or more conditions.
Therefore, in the present embodiment, the disease knowledge that can be recorded according to clinical guidelines forms diagnosis and treatment rule base, described
Diagnosis and treatment rule base includes the corresponding diagnosis and treatment rule of each disease that the clinical guidelines are recorded, and the diagnosis and treatment rule includes being diagnosed as
The condition that the corresponding disease of condition and treatment that corresponding disease is met is met.Then further included after S102:Described in judgement
Whether the medical record information in target electronic case history meets a diagnosis and treatment rule in the diagnosis and treatment rule base, if the target electronic
Medical record information in case history is unsatisfactory for a diagnosis and treatment rule in the diagnosis and treatment rule base, then carries out early warning, specifically,
For the medical record information in the target electronic case history, wherein for diagnosing the information and/or the doubtful disease of the suspected disease
The corresponding treatment information of disease if it is unsatisfactory for preset diagnosis and treatment rule, is then prompted.For example, about input CDSS systems
Medical record information in target electronic case history, existing disease information including patient and the medical measure carried out in advance, if the case history
Information is not consistent with preset diagnosis and treatment rule, then is prompted, such as an instability mode myocardial infarction patient, has been accompanied by
Pulmonary edema, which, which shows, to use a kind of medicine for being diltiazem to patient, because diltiazem can aggravate pulmonary edema,
It is not suitable for the patient, then can provides early warning.Referring to Fig. 2 a, Fig. 2 a are shown carries out early warning according to diagnosis and treatment rule base
Exemplary plot.
Due to not only including disease knowledge in medical knowledge, further including drug knowledge and checking knowledge etc., therefore, this implementation
Example, can also obtain drug model, in this way, drug model can be utilized by the drug knowledge in machine learning medical knowledge
It the learning outcome that medical knowledge obtains is had according to machine learning realizes and use corresponding drug for disease.Similar, may be used also
To obtain inspection model by the inspection knowledge in machine learning medical knowledge, in this way, inspection model can be utilized according to machine
Device study has the learning outcome realization that medical knowledge obtains and is checked accordingly for disease.
Referring to Fig. 2 b, Fig. 2 b show that machine learning has the exemplary plot of medical knowledge, it can be seen from the figure that disease is known
Knowledge forms disease model after machine learning, drug knowledge forms drug model after machine learning, checks knowledge
Inspection model is formd after machine learning, incorporates disease model by segmenting the clinical guidelines diagnosis and treatment rule decomposed and obtained.
It is understood that in order to enable the disease knowledge covering needed for structure disease model more fully, makes disease mould
Type can carry out medical diagnosis on disease according to more comprehensive learning outcome, so as to obtain more accurate diagnostic result.In this implementation
It is shown in Figure 3 in example, machine learning can be had to the learning outcome that electronic health record obtains and be dissolved into disease model, from
And abundant disease model, disease model is allow to have the study that electronic health record and existing medical knowledge obtain according to machine learning
As a result medical diagnosis on disease is realized.
In the case where the disease knowledge in having medical knowledge by machine learning obtains disease model, the realization of S102
Mode may refer to shown in Fig. 4 a, wherein, A branches into the learning outcome progress disease for having electronic health record using machine learning and examines
Disconnected, B branches into the learning outcome that disease model has medical knowledge according to machine learning and carries out medical diagnosis on disease.In this way, obtaining
After medical record information in target electronic case history, disease model can analyze the medical record information, be had according to machine learning
The learning outcome of electronic health record determines the possible corresponding disease of the medical record information, meanwhile, which can also pass through machine
Study has learning outcome acquisition and the possible corresponding disease of the medical record information that electronic health record obtains, so as to according to A branches and B
The medical record information that branch respectively obtains may corresponding disease generation disease list of probabilities.
At this point, due in disease list of probabilities suspected disease determined jointly by A branches and B branches,
In order to determine the authenticity probability of suspected disease in disease list of probabilities, can be set according to actual conditions for A branches and B branches
Weight, so as to obtain the authenticity probability of each suspected disease, the corresponding weight of branch is bigger, and the branch is for determining doubtful disease
The authenticity of disease is more important.
In the case where machine learning to be had to the learning outcome that electronic health record obtains and is dissolved into disease model, the reality of S102
Existing mode may refer to shown in Fig. 4 b, at this point, machine learning has electronic health record and machine learning has the common structure of medical knowledge
Build out disease model.In this way, after the medical record information in obtaining target electronic case history, disease model can be according to machine learning
There is the learning outcome that medical knowledge and existing electronic health record obtain to obtain the possible corresponding disease of the medical record information, so as to generate disease
Sick list of probabilities.
A kind of methods for the diagnosis of diseases provided by the embodiments of the present application, pre-establishes disease model, and the disease model is used for
The learning outcome that electronic health record and/or existing medical knowledge obtain is had according to machine learning and realizes medical diagnosis on disease;Based on this, when
When carrying out medical diagnosis on disease for certain electronic health record, target electronic case history to be diagnosed first is obtained, further according to the disease model point
The medical record information in the target electronic case history is analysed, to generate disease list of probabilities, the medical record information includes being used to implement disease
The available information of disease diagnosis, the disease list of probabilities include the authenticity of at least one suspected disease and the suspected disease
Probability.Since the disease model has learnt existing electronic health record and/or medical knowledge, disease knowledge is covered more complete
Face, therefore, when carrying out medical diagnosis on disease using the disease model, diagnostic result will be more accurate.
Below in conjunction with the accompanying drawings, have electronic health record to the machine learning involved in S102 and obtain learning outcome and be introduced.
Referring to Fig. 5, Fig. 5 shows that a kind of machine learning has the flow chart of electronic health record method, the method includes:
S501:Collect different existing electronic health records.
In the present embodiment, a large amount of, different existing electronic health records can be collected so that electric based on machine learning
Sub- case history can cover various diseases comprehensively, to be applied to disease machine learning is had the learning outcome that electronic health record obtains
When in disease diagnosis, the accuracy of medical diagnosis on disease result can be improved.
S502:Medical record information in the existing electronic health record is learnt using machine learning mode, forms case history study knot
Fruit.
Case history learning outcome can include the corresponding diagnosed disease of the existing electronic health record and the existing electronics disease
About the corresponding disease reaction information of the diagnosed disease in going through, so that S102 is carrying out medical diagnosis on disease to target electronic case history
When, the corresponding suspected disease of target electronic case history can be determined according to case history learning outcome.
By previous embodiment it is found that the medical record information having in electronic health record for example can include admission records, the course of disease is remembered
Record checks main diagnosis of data, inspection data, discharge diagnosis etc., and disease can be extracted from the medical record information in existing electronic health record
Sick reaction information, the disease reflection information can include symptom, inspection data, inspection data of the performance of certain disease etc., from
Diagnosed disease can be extracted by having in the medical record information in electronic health record, then, the medical record information having in electronic health record can be with
Reflect the correspondence of the corresponding diagnosed disease of the electronic health record and disease reaction information.
For example, certain medical record information having in electronic health record has recorded some patient with chest paroxysmal, squeezing property pain
Etc. symptoms, in the patient carries out treatment process, ECG examination has been carried out to the patient and has obtained inspection result, final determine should
Patient suffers from myocardial infarction.In this has electronic health record, the symptoms such as chest paroxysmal, squeezing property pain and ECG examination obtain
The inspection result arrived can be used as disease reaction information, and myocardial infarction can be used as diagnosed disease, therefore, by machine learning side
Formula learns the medical record information in the existing electronic health record, forms case history learning outcome, which can include cardiac muscle
About the corresponding disease reaction information of myocardial infarction in infarct and the existing electronic health record.
It is shown in Figure 6, admission records, admission diagnosis, the course of disease note on the left of Fig. 6 to be extracted from existing electronic health record
Record checks the medical record informations such as data, inspection data, and right side is the main diagnosis of discharge diagnosis, can by learning to having electronic health record
To obtain the case history learning outcome for including diagnosed disease and the corresponding disease reaction information of the diagnosed disease.In this way, when into
It, can be by the disease in the disease reaction information and case history learning outcome if obtaining disease reaction information during row medical diagnosis on disease
Reaction information is matched, if successful match, speculates that the disease reaction information may be corresponding according to the case history learning outcome
Disease.
Below in conjunction with the accompanying drawings, have the learning outcome that medical knowledge obtains to the machine learning involved in S102 to be situated between
It continues.
Referring to Fig. 7, Fig. 7 shows that a kind of machine learning has the flow chart of medical knowledge method, the method includes:
S701:The disease knowledge having in medical information is obtained, forms disease knowledge library.
The existing medical information can be had medical book, have Network Medicine knowledge etc., have in medical information
It can include a large amount of disease knowledge, drug knowledge, check knowledge and Evidence-based Medicine Literature etc..
In the present embodiment, the disease knowledge having in medical information can be obtained by crawler technology, it should so as to utilize
Disease knowledge forms disease knowledge library.Wherein, the disease knowledge can include at least one existing actual disease and every
The corresponding disease reaction information of kind actual disease.The disease reaction information and the disease provided in the embodiment corresponding to Fig. 5
Reaction information is identical, and details are not described herein again.
Shown in Figure 8, Fig. 8 shows the example for being obtained using crawler technology and having the disease knowledge in medical information
Figure, it can be seen from the figure that can not only obtain the disease knowledge in existing medical information by crawler technology, can also obtain
Drug knowledge checks knowledge and Evidence-based Medicine Literature etc..Further, since examining for the disease can also be included in disease knowledge
Knowledge is treated, further, the diagnosis and treatment knowledge in disease knowledge can also be obtained by crawler technology, it can be with by the diagnosis and treatment knowledge
Determine a kind of corresponding diagnosis and treatment scheme of actual disease.
S702:Disease knowledge in the disease knowledge library is learnt using machine learning mode, form knowledge learning as a result,
The knowledge learning result includes at least one actual disease and the corresponding disease reaction information of the actual disease.
By the discussion in S701 it is found that the disease knowledge can include existing true disease and the actual disease
Corresponding disease reaction information, in this way, the disease knowledge obtained in S701 is learnt using machine learning mode, it can be with shape
It, can be true according to knowledge learning result into knowledge learning as a result, so that S102 to target electronic case history when carrying out medical diagnosis on disease
The corresponding suspected disease of the electronic health record that sets the goal.
In many cases, when carrying out medical diagnosis on disease to target electronic case history, purpose is not only to determine the mesh
Mark the corresponding suspected disease of electronic health record, it is also necessary to the diagnosis and treatment scheme for the suspected disease is determined, with to the suspected disease
It is treated.
It is understood that in S701 other than it can obtain disease knowledge, diagnosis and treatment knowledge can also be obtained, therefore,
In the present embodiment, machine learning mode can also be used in and learn diagnosis and treatment knowledge in the disease knowledge library, form diagnostics
It practises as a result, the diagnosis and treatment learning outcome includes the corresponding diagnosis and treatment scheme of the actual disease.In this way, S102 is in generation disease probability
It, can basis if the suspected disease in disease list of probabilities is a kind of actual disease in the knowledge learning result after list
The diagnosis and treatment learning outcome provides diagnosis and treatment scheme for each suspected disease in the disease list of probabilities.
Shown in Figure 9, Fig. 9 shows the exemplary plot for the method for providing diagnosis and treatment scheme, and the disease model in figure can be
It is built by the corresponding embodiments of Fig. 7, in this way, including the corresponding diagnosis and treatment scheme of actual disease in the disease model, utilized
The disease model generates Fig. 1 disease list of probabilities in corresponding embodiment is analyzed, and is the disease according to analysis result
Each suspected disease in list of probabilities provides diagnosis and treatment scheme.
Further, after disease list of probabilities is generated, in order to can be according to more examples or evidence to disease
Suspected disease in list further determines that, so that it is determined that it is in list of diseases on earth to go out the corresponding disease of target electronic case history
Which kind of suspected disease or determine how the corresponding disease of target electronic case history is treated, in the present embodiment
In, the case history similar to the suspected disease can be provided and according to the knowledge learning according to the case history learning outcome
As a result offer and the relevant Evidence-based Medicine Literature of the suspected disease, to provide more ginsengs for medical diagnosis on disease and disease treatment
It examines.Shown in Figure 10, Figure 10 shows a kind of exemplary plot that reference is provided for suspected disease.
A kind of methods for the diagnosis of diseases based on aforementioned offer, referring to Figure 11, Figure 11 shows a kind of medical diagnosis on disease device, described
Device, including:Electronic health record acquiring unit 1101, for obtaining target electronic case history;
Medical record information analytic unit 1102, for being analyzed in the target electronic case history according to the disease model built in advance
Medical record information, to generate disease list of probabilities;Wherein, the disease model is used for having electronic health record according to machine learning
And/or the learning outcome that existing medical knowledge obtains realizes medical diagnosis on disease, the medical record information includes being used to implement medical diagnosis on disease
Available information, the disease list of probabilities includes the authenticity probability of at least one suspected disease and the suspected disease.
Optionally, described device further includes:
Electronic health record collection device, for collecting different existing electronic health records;
Medical record information unit, for learning the case history letter in the existing electronic health record using machine learning mode
Breath, forms case history learning outcome, and the case history learning outcome includes the corresponding diagnosed disease of the existing electronic health record and institute
It states in existing electronic health record about the corresponding disease reaction information of the diagnosed disease.
Optionally, described device further includes:
Similar case history provides unit, according to the case history learning outcome, provides the case history similar to the suspected disease.
Optionally, described device further includes:
Disease knowledge acquiring unit for obtaining the disease knowledge in existing medical information, forms disease knowledge library;
Disease knowledge unit, for learning the disease knowledge in the disease knowledge library using machine learning mode,
Knowledge learning is formed as a result, the knowledge learning result includes at least one actual disease and the corresponding disease of the actual disease
Sick reaction information.
Optionally, described device further includes:
Diagnosis and treatment knowledge learning unit for the diagnosis and treatment knowledge in disease knowledge library described in machine learning, forms diagnosis and treatment study
As a result, the diagnosis and treatment learning outcome includes the corresponding diagnosis and treatment scheme of the actual disease;
Then, described device further includes:
Diagnosis and treatment scheme provides unit, if being a kind of actual disease in the knowledge learning result for the suspected disease,
Then diagnosis and treatment scheme is provided for each suspected disease in the disease list of probabilities according to the diagnosis and treatment learning outcome.
Optionally, described device further includes:
Medical literature provides unit, for according to the knowledge learning as a result, providing and the suspected disease is relevant follows
Demonstrate,prove medical literature.
Optionally, described device further includes:
Diagnosis and treatment rule forms unit, for the disease knowledge recorded according to clinical guidelines, forms diagnosis and treatment rule base, described to examine
It treats rule base and includes the corresponding diagnosis and treatment rule of each disease that the clinical guidelines are recorded, the diagnosis and treatment rule includes corresponding disease
Diagnostic rule and treatment rule;
Then, described device further includes:
Medical record information judging unit, for judging whether the medical record information in the target electronic case history meets the diagnosis and treatment
A diagnosis and treatment rule in rule base, if it is not, then carrying out early warning.
A kind of medical diagnosis on disease device provided by the embodiments of the present application, pre-establishes disease model, and the disease model is used for
The learning outcome that electronic health record and/or existing medical knowledge obtain is had according to machine learning and realizes medical diagnosis on disease;Based on this, when
When carrying out medical diagnosis on disease for certain electronic health record, target electronic case history to be diagnosed first is obtained, further according to the disease model point
The medical record information in the target electronic case history is analysed, to generate disease list of probabilities, the medical record information includes being used to implement disease
The available information of disease diagnosis, the disease list of probabilities include the authenticity of at least one suspected disease and the suspected disease
Probability.Since the disease model has learnt existing electronic health record and/or medical knowledge, disease knowledge is covered more complete
Face, therefore, when carrying out medical diagnosis on disease using the disease model, diagnostic result will be more accurate.
As seen through the above description of the embodiments, those skilled in the art can be understood that above-mentioned implementation
All or part of step in example method can add the mode of required general hardware platform to realize by software.Based on such
Understand, the part that the technical solution of the application substantially in other words contributes to the prior art can be in the form of software product
It embodies, which can be stored in storage medium, such as ROM/RAM, magnetic disc, CD, including several
Instruction is used so that computer equipment (can be personal computer, the network communications such as server or Media Gateway
Equipment, etc.) perform method described in certain parts of each embodiment of the application or embodiment.
It should be noted that each embodiment is described by the way of progressive in this specification, each embodiment emphasis is said
Bright is all difference from other examples, and just to refer each other for identical similar portion between each embodiment.For reality
For applying device disclosed in example, since it is corresponded to the methods disclosed in the examples, so description is fairly simple, related part
Referring to method part illustration.
It should also be noted that, herein, relational terms such as first and second and the like are used merely to one
Entity or operation are distinguished with another entity or operation, without necessarily requiring or implying between these entities or operation
There are any actual relationship or orders.Moreover, term " comprising ", "comprising" or its any other variant are intended to contain
Lid non-exclusive inclusion, so that process, method, article or equipment including a series of elements not only will including those
Element, but also including other elements that are not explicitly listed or further include as this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
Also there are other identical elements in process, method, article or equipment including the element.
The foregoing description of the disclosed embodiments enables professional and technical personnel in the field to realize or using the application.
A variety of modifications of these embodiments will be apparent for those skilled in the art, it is as defined herein
General Principle can in other embodiments be realized in the case where not departing from spirit herein or range.Therefore, the application
The embodiments shown herein is not intended to be limited to, and is to fit to and the principles and novel features disclosed herein phase one
The most wide range caused.
Claims (14)
1. a kind of methods for the diagnosis of diseases, which is characterized in that including:
Obtain target electronic case history;
Medical record information in the target electronic case history is analyzed according to the disease model built in advance, to generate disease probability column
Table;Wherein, the disease model is used for the study knot for having electronic health record and/or existing medical knowledge according to machine learning and obtaining
Fruit shows medical diagnosis on disease, and the medical record information includes the available information for being used to implement medical diagnosis on disease, the disease list of probabilities packet
Include the authenticity probability of at least one suspected disease and the suspected disease.
2. according to the method described in claim 1, it is characterized in that, the machine learning has electronic health record, including:
Collect different existing electronic health records;
Medical record information in the existing electronic health record is learnt using machine learning mode, forms case history learning outcome, the disease
Learning outcome is gone through to include in the existing corresponding diagnosed disease of electronic health record and the existing electronic health record about described true
Examine the corresponding disease reaction information of disease.
3. according to the method described in claim 2, it is characterized in that, after the generation disease list of probabilities, further include:
According to the case history learning outcome, the case history similar to the suspected disease is provided.
4. according to the method described in claim 1, it is characterized in that, the machine learning has medical knowledge, including:
The disease knowledge having in medical information is obtained, forms disease knowledge library;
Disease knowledge in the disease knowledge library is learnt using machine learning mode, forms knowledge learning as a result, the knowledge
Learning outcome includes at least one actual disease and the corresponding disease reaction information of the actual disease.
5. according to the method described in claim 4, it is characterized in that, the disease model is additionally operable to disease described in machine learning knows
Know the diagnosis and treatment knowledge in library, form diagnosis and treatment study as a result, the diagnosis and treatment learning outcome includes the corresponding diagnosis and treatment of the actual disease
Scheme;
Then, it after the generation disease list of probabilities, further includes:
It is institute according to the diagnosis and treatment learning outcome if the suspected disease is a kind of actual disease in the knowledge learning result
The each suspected disease stated in disease list of probabilities provides diagnosis and treatment scheme.
6. according to the method described in claim 4, it is characterized in that, after the generation disease list of probabilities, further include:
According to the knowledge learning as a result, providing and the relevant Evidence-based Medicine Literature of the suspected disease.
7. method according to any one of claims 1 to 6, which is characterized in that the method further includes:
According to the disease knowledge that clinical guidelines are recorded, diagnosis and treatment rule base is formed, the diagnosis and treatment rule base includes the clinical guidelines
The corresponding diagnosis and treatment rule of each disease recorded, the diagnosis and treatment rule include the diagnostic rule of corresponding disease and treatment rule;
Then, it after the disease model that the basis is built in advance analyzes the medical record information in the target electronic case history, further includes:
Judge whether the medical record information in the target electronic case history meets a diagnosis and treatment rule in the diagnosis and treatment rule base, if
It is no, then carry out early warning.
8. a kind of medical diagnosis on disease device, which is characterized in that including:
Electronic health record acquiring unit, for obtaining target electronic case history;
Medical record information analytic unit, for analyzing the case history letter in the target electronic case history according to the disease model built in advance
Breath, to generate disease list of probabilities;Wherein, the disease model is used to have electronic health record according to machine learning and/or have
The learning outcome that medical knowledge obtains realizes medical diagnosis on disease, and the medical record information includes the available letter for being used to implement medical diagnosis on disease
Breath, the disease list of probabilities include the authenticity probability of at least one suspected disease and the suspected disease.
9. device according to claim 8, which is characterized in that described device further includes:
Electronic health record collection device, for collecting different existing electronic health records;
Medical record information unit, for learning the medical record information in the existing electronic health record, shape using machine learning mode
Into case history learning outcome, the case history learning outcome includes the corresponding diagnosed disease of the existing electronic health record and described has
About the corresponding disease reaction information of the diagnosed disease in electronic health record.
10. device according to claim 9, which is characterized in that described device further includes:
Similar case history provides unit, according to the case history learning outcome, provides the case history similar to the suspected disease.
11. device according to claim 8, which is characterized in that described device further includes:
Disease knowledge acquiring unit for obtaining the disease knowledge in existing medical information, forms disease knowledge library;
Disease knowledge unit for being learnt the disease knowledge in the disease knowledge library using machine learning mode, is formed
Knowledge learning is as a result, the knowledge learning result includes at least one actual disease and the corresponding disease of the actual disease is anti-
Answer information.
12. according to the devices described in claim 11, which is characterized in that described device further includes:
Diagnosis and treatment knowledge learning unit, for the diagnosis and treatment knowledge in disease knowledge library described in machine learning, form diagnosis and treatment study as a result,
The diagnosis and treatment learning outcome includes the corresponding diagnosis and treatment scheme of the actual disease;
Then, described device further includes:
Diagnosis and treatment scheme provides unit, if being a kind of actual disease in the knowledge learning result for the suspected disease, root
According to the diagnosis and treatment learning outcome diagnosis and treatment scheme is provided for each suspected disease in the disease list of probabilities.
13. according to the devices described in claim 11, which is characterized in that described device further includes:
Medical literature provides unit, for being cured according to the knowledge learning as a result, providing with the relevant evidence-based of the suspected disease
Learn document.
14. according to claim 8 to 13 any one of them device, which is characterized in that described device further includes:
Diagnosis and treatment rule forms unit, for the disease knowledge recorded according to clinical guidelines, forms diagnosis and treatment rule base, the diagnosis and treatment rule
Then library includes the corresponding diagnosis and treatment rule of each disease that the clinical guidelines are recorded, and the diagnosis and treatment rule includes examining for corresponding disease
Disconnected rule and treatment rule;
Then, described device further includes:
Medical record information judging unit, for judging whether the medical record information in the target electronic case history meets the diagnosis and treatment rule
A diagnosis and treatment rule in library, if it is not, then carrying out early warning.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711448095.3A CN108154928A (en) | 2017-12-27 | 2017-12-27 | A kind of methods for the diagnosis of diseases and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711448095.3A CN108154928A (en) | 2017-12-27 | 2017-12-27 | A kind of methods for the diagnosis of diseases and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108154928A true CN108154928A (en) | 2018-06-12 |
Family
ID=62462573
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711448095.3A Pending CN108154928A (en) | 2017-12-27 | 2017-12-27 | A kind of methods for the diagnosis of diseases and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108154928A (en) |
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109192299A (en) * | 2018-08-13 | 2019-01-11 | 中国科学院计算技术研究所 | A kind of medical analysis auxiliary system based on convolutional neural networks |
CN109493926A (en) * | 2018-10-30 | 2019-03-19 | 中山大学肿瘤防治中心 | Processing method, device, medium and the electronic equipment of colorectal cancer medical data |
CN109545388A (en) * | 2018-10-27 | 2019-03-29 | 平安医疗健康管理股份有限公司 | A kind of medicine risk control method, server and storage medium |
CN109754880A (en) * | 2019-01-07 | 2019-05-14 | 四川大学华西医院 | Clinic diagnosis output method and device |
CN109754886A (en) * | 2019-01-07 | 2019-05-14 | 广州达美智能科技有限公司 | Therapeutic scheme intelligent generating system, method and readable storage medium storing program for executing, electronic equipment |
CN109801705A (en) * | 2018-12-12 | 2019-05-24 | 平安科技(深圳)有限公司 | Treat recommended method, system, device and storage medium |
CN109859841A (en) * | 2019-03-01 | 2019-06-07 | 中国科学院上海高等研究院 | Diagnosis for liver cancer system, method, equipment and medium neural network based |
CN110232957A (en) * | 2019-06-06 | 2019-09-13 | 深圳市第三人民医院 | A kind of diagnosis and therapy system and its construction method based on artificial intelligence, equipment and storage medium |
CN110277147A (en) * | 2019-04-25 | 2019-09-24 | 胡盛寿 | A kind of system and method for realizing medical record intelligent diagnosis cataloguing |
CN110379507A (en) * | 2019-06-27 | 2019-10-25 | 南京市卫生信息中心 | A kind of aided diagnosis method based on patient's vector-valued image |
CN110752027A (en) * | 2019-10-21 | 2020-02-04 | 卓尔智联(武汉)研究院有限公司 | Electronic medical record data pushing method and device, computer equipment and storage medium |
CN111199801A (en) * | 2018-11-19 | 2020-05-26 | 零氪医疗智能科技(广州)有限公司 | Construction method and application of model for identifying disease types of medical records |
CN111292852A (en) * | 2020-03-12 | 2020-06-16 | 陕西领创精准医疗科技有限公司 | Encephalitis and meningitis intelligent auxiliary diagnosis system based on random forest algorithm |
CN111429985A (en) * | 2020-03-02 | 2020-07-17 | 北京嘉和海森健康科技有限公司 | Electronic medical record data processing method and system |
CN111445993A (en) * | 2020-03-25 | 2020-07-24 | 北京嘉和海森健康科技有限公司 | Disease hierarchical relation processing method and device and electronic equipment |
CN111599427A (en) * | 2020-05-14 | 2020-08-28 | 郑州大学第一附属医院 | Recommendation method and device for unified diagnosis, electronic equipment and storage medium |
CN111681728A (en) * | 2020-06-09 | 2020-09-18 | 北京嘉和海森健康科技有限公司 | Content quality control method and device for electronic medical record |
CN111724873A (en) * | 2020-06-18 | 2020-09-29 | 北京嘉和海森健康科技有限公司 | Data processing method and device |
CN112185564A (en) * | 2020-10-20 | 2021-01-05 | 福州数据技术研究院有限公司 | Ophthalmic disease prediction method based on structured electronic medical record and storage device |
CN112201350A (en) * | 2020-11-11 | 2021-01-08 | 北京嘉和海森健康科技有限公司 | Intelligent triage method and device and electronic equipment |
CN112309580A (en) * | 2020-11-26 | 2021-02-02 | 微医云(杭州)控股有限公司 | Method and device for determining disease type, electronic equipment and storage medium |
CN113509185A (en) * | 2021-04-25 | 2021-10-19 | 安徽十锎信息科技有限公司 | Myocardial infarction classification method based on multi-modal patient information attention modeling |
CN113990495A (en) * | 2021-12-27 | 2022-01-28 | 之江实验室 | Disease diagnosis prediction system based on graph neural network |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100794516B1 (en) * | 2007-12-03 | 2008-01-14 | 한국정보통신대학교 산학협력단 | System and method for diagnosis and clinical test selection using case based machine learning inference |
CN103268349A (en) * | 2013-05-29 | 2013-08-28 | 美合实业(苏州)有限公司 | Central clinical case database system based on cloud services |
CN104573350A (en) * | 2014-12-26 | 2015-04-29 | 深圳市前海安测信息技术有限公司 | System and method for general practitioner auxiliary diagnosis and therapy based on network hospital |
CN106934223A (en) * | 2017-02-28 | 2017-07-07 | 思派(北京)网络科技有限公司 | A kind of blood disease intelligent classification system and method based on big data |
CN107038343A (en) * | 2017-04-10 | 2017-08-11 | 荣科科技股份有限公司 | Construction method and constructing system, the clinical diagnosing system of clinical diagnosis model |
CN107145744A (en) * | 2017-05-08 | 2017-09-08 | 合肥工业大学 | Construction method, device and the aided diagnosis method of medical knowledge collection of illustrative plates |
CN107256427A (en) * | 2017-06-08 | 2017-10-17 | 成都深泉科技有限公司 | Medical knowledge drawing generating method, device and diagnostic data obtain system, method |
CN107491630A (en) * | 2016-06-10 | 2017-12-19 | 韩国电子通信研究院 | Clinical decision support integrated system and use its clinical decision support method |
-
2017
- 2017-12-27 CN CN201711448095.3A patent/CN108154928A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100794516B1 (en) * | 2007-12-03 | 2008-01-14 | 한국정보통신대학교 산학협력단 | System and method for diagnosis and clinical test selection using case based machine learning inference |
CN103268349A (en) * | 2013-05-29 | 2013-08-28 | 美合实业(苏州)有限公司 | Central clinical case database system based on cloud services |
CN104573350A (en) * | 2014-12-26 | 2015-04-29 | 深圳市前海安测信息技术有限公司 | System and method for general practitioner auxiliary diagnosis and therapy based on network hospital |
CN107491630A (en) * | 2016-06-10 | 2017-12-19 | 韩国电子通信研究院 | Clinical decision support integrated system and use its clinical decision support method |
CN106934223A (en) * | 2017-02-28 | 2017-07-07 | 思派(北京)网络科技有限公司 | A kind of blood disease intelligent classification system and method based on big data |
CN107038343A (en) * | 2017-04-10 | 2017-08-11 | 荣科科技股份有限公司 | Construction method and constructing system, the clinical diagnosing system of clinical diagnosis model |
CN107145744A (en) * | 2017-05-08 | 2017-09-08 | 合肥工业大学 | Construction method, device and the aided diagnosis method of medical knowledge collection of illustrative plates |
CN107256427A (en) * | 2017-06-08 | 2017-10-17 | 成都深泉科技有限公司 | Medical knowledge drawing generating method, device and diagnostic data obtain system, method |
Non-Patent Citations (1)
Title |
---|
杨丽琴等: ""基于临床实践指南的诊疗过程建模方法"", 《计算机集成制造系统》 * |
Cited By (33)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109192299A (en) * | 2018-08-13 | 2019-01-11 | 中国科学院计算技术研究所 | A kind of medical analysis auxiliary system based on convolutional neural networks |
CN109545388A (en) * | 2018-10-27 | 2019-03-29 | 平安医疗健康管理股份有限公司 | A kind of medicine risk control method, server and storage medium |
CN109493926A (en) * | 2018-10-30 | 2019-03-19 | 中山大学肿瘤防治中心 | Processing method, device, medium and the electronic equipment of colorectal cancer medical data |
CN111199801B (en) * | 2018-11-19 | 2023-08-08 | 零氪医疗智能科技(广州)有限公司 | Construction method and application of model for identifying disease types of medical records |
CN111199801A (en) * | 2018-11-19 | 2020-05-26 | 零氪医疗智能科技(广州)有限公司 | Construction method and application of model for identifying disease types of medical records |
CN109801705A (en) * | 2018-12-12 | 2019-05-24 | 平安科技(深圳)有限公司 | Treat recommended method, system, device and storage medium |
CN109754880A (en) * | 2019-01-07 | 2019-05-14 | 四川大学华西医院 | Clinic diagnosis output method and device |
CN109754886A (en) * | 2019-01-07 | 2019-05-14 | 广州达美智能科技有限公司 | Therapeutic scheme intelligent generating system, method and readable storage medium storing program for executing, electronic equipment |
CN109754880B (en) * | 2019-01-07 | 2023-05-30 | 四川大学华西医院 | Clinical diagnosis and treatment output method and device |
CN109859841A (en) * | 2019-03-01 | 2019-06-07 | 中国科学院上海高等研究院 | Diagnosis for liver cancer system, method, equipment and medium neural network based |
CN110277147A (en) * | 2019-04-25 | 2019-09-24 | 胡盛寿 | A kind of system and method for realizing medical record intelligent diagnosis cataloguing |
CN110232957A (en) * | 2019-06-06 | 2019-09-13 | 深圳市第三人民医院 | A kind of diagnosis and therapy system and its construction method based on artificial intelligence, equipment and storage medium |
CN110379507B (en) * | 2019-06-27 | 2023-03-14 | 南京市卫生信息中心 | Auxiliary diagnosis method based on patient vector image |
CN110379507A (en) * | 2019-06-27 | 2019-10-25 | 南京市卫生信息中心 | A kind of aided diagnosis method based on patient's vector-valued image |
CN110752027A (en) * | 2019-10-21 | 2020-02-04 | 卓尔智联(武汉)研究院有限公司 | Electronic medical record data pushing method and device, computer equipment and storage medium |
CN110752027B (en) * | 2019-10-21 | 2023-05-23 | 卓尔智联(武汉)研究院有限公司 | Electronic medical record data pushing method, device, computer equipment and storage medium |
CN111429985A (en) * | 2020-03-02 | 2020-07-17 | 北京嘉和海森健康科技有限公司 | Electronic medical record data processing method and system |
CN111429985B (en) * | 2020-03-02 | 2023-10-27 | 北京嘉和海森健康科技有限公司 | Electronic medical record data processing method and system |
CN111292852A (en) * | 2020-03-12 | 2020-06-16 | 陕西领创精准医疗科技有限公司 | Encephalitis and meningitis intelligent auxiliary diagnosis system based on random forest algorithm |
CN111445993A (en) * | 2020-03-25 | 2020-07-24 | 北京嘉和海森健康科技有限公司 | Disease hierarchical relation processing method and device and electronic equipment |
CN111445993B (en) * | 2020-03-25 | 2023-08-08 | 北京嘉和海森健康科技有限公司 | Hierarchical relationship processing method and device for diseases and electronic equipment |
CN111599427A (en) * | 2020-05-14 | 2020-08-28 | 郑州大学第一附属医院 | Recommendation method and device for unified diagnosis, electronic equipment and storage medium |
CN111599427B (en) * | 2020-05-14 | 2023-03-31 | 郑州大学第一附属医院 | Recommendation method and device for unified diagnosis, electronic equipment and storage medium |
CN111681728A (en) * | 2020-06-09 | 2020-09-18 | 北京嘉和海森健康科技有限公司 | Content quality control method and device for electronic medical record |
CN111681728B (en) * | 2020-06-09 | 2023-10-24 | 北京嘉和海森健康科技有限公司 | Content quality control method and device for electronic medical records |
CN111724873B (en) * | 2020-06-18 | 2024-01-09 | 北京嘉和海森健康科技有限公司 | Data processing method and device |
CN111724873A (en) * | 2020-06-18 | 2020-09-29 | 北京嘉和海森健康科技有限公司 | Data processing method and device |
CN112185564A (en) * | 2020-10-20 | 2021-01-05 | 福州数据技术研究院有限公司 | Ophthalmic disease prediction method based on structured electronic medical record and storage device |
CN112201350A (en) * | 2020-11-11 | 2021-01-08 | 北京嘉和海森健康科技有限公司 | Intelligent triage method and device and electronic equipment |
CN112309580A (en) * | 2020-11-26 | 2021-02-02 | 微医云(杭州)控股有限公司 | Method and device for determining disease type, electronic equipment and storage medium |
CN113509185A (en) * | 2021-04-25 | 2021-10-19 | 安徽十锎信息科技有限公司 | Myocardial infarction classification method based on multi-modal patient information attention modeling |
CN113990495B (en) * | 2021-12-27 | 2022-04-29 | 之江实验室 | Disease diagnosis prediction system based on graph neural network |
CN113990495A (en) * | 2021-12-27 | 2022-01-28 | 之江实验室 | Disease diagnosis prediction system based on graph neural network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108154928A (en) | A kind of methods for the diagnosis of diseases and device | |
US8073713B2 (en) | Method and system for managing medical professionals | |
Coleman et al. | From patient care to research: a validation study examining the factors contributing to data quality in a primary care electronic medical record database | |
EP3312748A1 (en) | Method for aiding a diagnosis, program and apparatus | |
JP2006500075A (en) | Patient data mining for lung cancer discrimination | |
EP3739596A1 (en) | Clinical predictive analytics system | |
JP2008532104A (en) | A method, system, and computer program product for generating and applying a prediction model capable of predicting a plurality of medical-related outcomes, evaluating an intervention plan, and simultaneously performing biomarker causality verification | |
US20030097279A1 (en) | Systems and methods for evaluating patient-specific information and providing patient management recommendations for healthcare providers | |
CN102483815A (en) | Clinical decision support | |
Shin et al. | Electrodiagnosis support system for localizing neural injury in an upper limb | |
Prabhushankar et al. | Olives dataset: Ophthalmic labels for investigating visual eye semantics | |
WO2012032441A2 (en) | Clinical state timeline. | |
GB2555381A (en) | Method for aiding a diagnosis, program and apparatus | |
US20230060794A1 (en) | Diagnostic Tool | |
CN116864104A (en) | Chronic thromboembolic pulmonary artery high-pressure risk classification system based on artificial intelligence | |
US20130238364A1 (en) | System for Differentiation and Analysis of Recorded Clinical Data | |
KR20150070892A (en) | Standardized clinical decision support device using Rockall Risk Score of upper gastrointestinal bleeding | |
Sathish Kumar et al. | Artificial intelligence based health indicator extraction and disease symptoms identification using medical hypothesis models | |
CN112562857A (en) | Method, device, processor and storage medium for realizing high-risk operation prediction based on K-means clustering | |
Alghadier et al. | A study of various applications of artificial intelligence (AI) and machine learning (ML) for healthcare services | |
Sanchez et al. | AI-clinician collaboration via disagreement prediction: A decision pipeline and retrospective analysis of real-world radiologist-AI interactions | |
Feng et al. | A Hybrid Data Mining Approach for Generalizing Characteristics of Emergency Department Visits Causing Overcrowding. | |
Pines et al. | Clinical decision rules | |
US20230298690A1 (en) | Genetic information processing system with unbounded-sample analysis mechanism and method of operation thereof | |
SCHREIER | Predictive Modelling and ts Visualization for Telehealth Data–Concept and Implementation of an Interactive Viewer |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20190729 Address after: Room 2307, 3 storeys, No. 7 Pioneer Road, Shangdi Information Industry Base, Haidian District, Beijing 100085 Applicant after: Beijing Jiahesen Health Technology Co., Ltd. Address before: 100085 Haidian District city on the base of the information industry base, Pioneer Road, building No. 7, section I, layer three, layer Applicant before: Goodwill Information Technology Co., Ltd. |
|
TA01 | Transfer of patent application right | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180612 |
|
RJ01 | Rejection of invention patent application after publication |