CN115966292A - Data automatic management system and method based on intelligent hospital - Google Patents
Data automatic management system and method based on intelligent hospital Download PDFInfo
- Publication number
- CN115966292A CN115966292A CN202310012103.9A CN202310012103A CN115966292A CN 115966292 A CN115966292 A CN 115966292A CN 202310012103 A CN202310012103 A CN 202310012103A CN 115966292 A CN115966292 A CN 115966292A
- Authority
- CN
- China
- Prior art keywords
- diagnosis
- treatment
- historical
- data
- doctor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention relates to the technical field of intelligent hospital data management, in particular to an automatic data management system and method based on an intelligent hospital, which comprises the steps of respectively constructing historical diagnosis and treatment databases corresponding to doctors; splitting all historical diagnosis and treatment records in each historical diagnosis and treatment database respectively based on the record information distribution characteristics of all historical diagnosis and treatment records in each historical diagnosis and treatment database; extracting characteristic diagnosis and treatment data for each diagnosis and treatment event of a doctor to obtain an event attribute of each diagnosis and treatment event; classifying all diagnosis and treatment events based on event attributes; constructing a diagnosis and treatment experience dimensional model for each doctor; the user registers and logs in the intelligent hospital platform to input pre-hung department information, matching doctors are pushed to the user based on the department information, meanwhile, data display is carried out on diagnosis and treatment experience dimensional models of the matching doctors, and the user is assisted to select proper diagnosis and treatment doctors based on the disease conditions of the user.
Description
Technical Field
The invention relates to the technical field of intelligent hospital data management, in particular to an intelligent hospital-based data automatic management system and method.
Background
For the patient, how to find a proper doctor for the doctor to visit is the biggest problem; under the current large environment, a part of patients usually tend to select a plurality of large-brand expert numbers to carry out hanging diagnosis in a hospital no matter the size or severity of the symptoms, so that the patients feel more stable, the phenomenon of 'small size and use' is avoided, the phenomenon that the expert numbers are reserved and hung in the hospital is caused, or the phenomenon that the patients need to be rescued because the hospitals need to release the expert numbers is caused is frequent; some patients can make a selection based on public praise and surrounding public praise of the patients through network search before treatment, and because of the internet era, huge information amount can cause people to be indiscriminate, so that the phenomenon that people 'take a lot' is avoided; for the above situations, medical resources are wasted or the time for the user to visit a doctor is wasted to a certain extent; in the present general environment, the user needs to understand that the suitable doctor is not particularly the doctor in the largest hospital or the largest brand of doctor, but rather the doctor who has considerable experience in treating his own disease and has convenient visit.
Disclosure of Invention
The invention aims to provide a data automatic management system and a data automatic management method based on an intelligent hospital, so as to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: a data automatic management method based on an intelligent hospital comprises the following steps:
step S100: calling historical diagnosis and treatment data of each doctor in a big database of the intelligent hospital, and respectively constructing historical diagnosis and treatment databases corresponding to each doctor, wherein the historical diagnosis and treatment data refers to data formed by collecting diagnosis and treatment data generated in each historical diagnosis and treatment record; the diagnosis and treatment data comprises self symptom description data of the patient, inquiry data of the doctor and diagnosis data prescribed by the doctor; the data types in the historical diagnosis and treatment database comprise audio and video data and text data;
step S200: splitting all historical diagnosis and treatment records in each historical diagnosis and treatment database respectively based on the record information distribution characteristics of all historical diagnosis and treatment records in each historical diagnosis and treatment database to obtain a plurality of independent diagnosis and treatment record subsets and a plurality of independent historical diagnosis and treatment records;
step S300: respectively taking the diagnosis and treatment data generated in each independent diagnosis and treatment record subset or each independent diagnosis and treatment record in each historical diagnosis and treatment database as the diagnosis and treatment data generated by a doctor corresponding to each historical diagnosis and treatment database under one diagnosis and treatment event; extracting characteristic diagnosis and treatment data for each diagnosis and treatment event of a doctor to obtain an event attribute of each diagnosis and treatment event;
step S400: in a historical diagnosis and treatment database of each doctor, classifying all diagnosis and treatment events based on event attributes; constructing a diagnosis and treatment experience dimensional model for each doctor;
step S500: the user registers and logs in the intelligent hospital platform, pre-hung department information is input into the intelligent hospital platform, the intelligent hospital platform pushes matched doctors to the user based on the department information, meanwhile, data display is carried out on diagnosis and treatment experience dimensional models of the matched doctors, and the user is assisted to select proper diagnosis and treatment doctors based on the disease conditions of the user.
Further, step S200 includes:
step S201: respectively extracting the generation time of records and the identity information of the patient to be diagnosed from all historical diagnosis and treatment records in all historical diagnosis and treatment databases; capturing the longest re-diagnosis period proposed by doctors diagnosing the same disease type to the patients who see a doctor from all historical diagnosis and treatment databases, and setting the longest re-diagnosis period as the re-diagnosis period corresponding to each disease type;
step S202: acquiring a re-diagnosis period T corresponding to each historical diagnosis and treatment database according to the disease types which correspond to each historical diagnosis and treatment database and are diagnosed by doctors; in each historical diagnosis and treatment database, collecting the historical diagnosis and treatment records with the same identity information of the patients to be diagnosed according to the sequence of record generation, and splitting each historical diagnosis and treatment database into a plurality of diagnosis and treatment record sets and a plurality of independent historical diagnosis and treatment records; wherein, each diagnosis and treatment record set corresponds to the identity information of a patient to be treated;
step S203: capturing interval record generation time between every two adjacent historical diagnosis and treatment records in each diagnosis and treatment record set in sequence; sequentially comparing the generation time of each interval record with the re-diagnosis period T corresponding to each historical diagnosis and treatment database;
step S204: when in a certain diagnosis record set, capturing the ith historical diagnosis record L i And the (i + 1) th historical diagnosis and treatment record L i+1 Interval between records generation time
And T satisfies->
If i =1, the 1 st historical diagnosis and treatment record L is recorded 1 Removing from a certain diagnosis and treatment record set to obtain a new diagnosis and treatment record set, and adding L 1 As a historical diagnostic record independent of each corresponding historical diagnosis and treatment database; if i is more than or equal to 2, integrating the 1 st historical diagnosis and treatment record L 1 Obtaining a diagnosis and treatment record subset { L } from the ith historical diagnosis and treatment record 1 ,…,L i Removing all historical diagnosis and treatment records in the diagnosis and treatment record subset from a certain diagnosis and treatment record set to obtain a new diagnosis and treatment record set, and collecting the diagnosis and treatment record subset { L } 1 ,…,L i The historical diagnosis records are set independently in each corresponding historical diagnosis and treatment database;
the steps are to avoid independent analysis of a plurality of diagnosis and treatment records belonging to one disease treatment course, and improve the accuracy of data adopted in the subsequent diagnosis and treatment experience dimensional model construction process of each doctor;
step S205: and (S203) circulating to step S204, and dividing each historical diagnosis and treatment database into a plurality of independent diagnosis and treatment record subsets and a plurality of independent historical diagnosis and treatment records.
Further, step S300 includes:
step S301: if an independent diagnosis record subset is extracted from a historical diagnosis database of a doctor, the independent diagnosis record subset comprises { W } 1 ,W 2 ,…,W n Extracting independent historical diagnosis and treatment records including { F } 1 ,F 2 ,…,F m }; wherein, W 1 ,…,W n Representing 1 st, 2 nd, \ 8230n independent diagnosis and treatment record subsets in a historical diagnosis and treatment database; f 1 ,F 2 ,…,F m The method comprises the steps of representing 1 st, 2 nd, \8230ina historical diagnosis and treatment database, and m independent historical diagnosis and treatment records; judging the total number K = n + m of diagnosis and treatment events existing in a historical diagnosis and treatment database of a doctor;
step S302: extracting key information of self-symptom description data of the patient, inquiry data of the doctor and diagnosis data prescribed by the doctor generated in each historical diagnosis and treatment record in each diagnosis and treatment record subset; setting key information extracted from self-symptom description data of a patient as first characteristic diagnosis and treatment data; setting key information extracted from the inquiry data of the doctor as second characteristic diagnosis and treatment data; setting key information extracted from diagnosis data prescribed by a doctor as third characteristic diagnosis and treatment data;
step S303: respectively summarizing all first characteristic diagnosis and treatment data, all second characteristic diagnosis and treatment data and all third characteristic diagnosis and treatment data extracted from all historical diagnosis and treatment records in each independent diagnosis and treatment record subset according to the generation sequence of corresponding records, and respectively correspondingly obtaining a first characteristic diagnosis and treatment data sequence, a second characteristic diagnosis and treatment data sequence and a third characteristic diagnosis and treatment data sequence; respectively corresponding the first characteristic diagnosis and treatment data sequence, the second characteristic diagnosis and treatment data sequence and the third characteristic diagnosis and treatment data sequence as a first event attribute, a second event attribute and a third event attribute of a diagnosis and treatment event corresponding to each independent diagnosis and treatment record subset;
step S304: and respectively corresponding the first characteristic diagnosis and treatment data, the second characteristic diagnosis and treatment data and the third characteristic diagnosis and treatment data extracted from each independent historical diagnosis and treatment record to be used as a first event attribute, a second event attribute and a third event attribute of the diagnosis and treatment event corresponding to each independent historical diagnosis and treatment record.
Further, the key information extracted from the patient's self-symptom describing data and the inquiry data of the doctor includes key information about the body part, key information about the symptom description, and key information about the symptom degree description; the key information extracted from the diagnosis data issued by the doctor comprises key information about diagnosis conclusion, medicine type information in the prescription order and medicine taking notice information in the prescription order.
Further, step S400 includes:
step S401: randomly selecting a diagnosis and treatment event as a similar center in a historical diagnosis and treatment database of a doctor; respectively carrying out similarity calculation of the first event attribute, the second event attribute and the third event attribute on other diagnosis and treatment events in the historical diagnosis and treatment database and the diagnosis and treatment events serving as the similar centers to respectively obtain the cumulative similarity value between the other diagnosis and treatment events in the historical diagnosis and treatment database and the diagnosis and treatment events serving as the similar centers: r = a R 1 +b*r 2 +c*r 3 (ii) a Wherein r is 1 、r 2 、r 3 Respectively representing the similarity of the other diagnosis and treatment events in the historical diagnosis and treatment database and the diagnosis and treatment events serving as the similarity center on the first event attribute, the second event attribute and the third event attribute; wherein a is r 1 B is r 2 C is r 3 The weight value of (2); wherein, a>b>c；
Will r is 1 ，r 2 ，r 3 The corresponding weight values a, b and c are set to satisfy a>b>The diagnosis and treatment experience dimension of the doctor is analyzed, namely historical diagnosis and treatment records of the doctor are analyzed from the data perspective, if the difference between the two diagnosis and treatment records is larger, the repeated diagnosis and treatment reference information in the two diagnosis and treatment records is less, the experience value of the doctor is required to be higher, and conversely, if the number of the diagnosis and treatment records is more in the historical diagnosis and treatment records of the doctor, the diagnosis and treatment experience of the doctor can be reflected to be richer to a certain extent, and the doctor can be more skilled to provide the most suitable diagnosis and treatment scheme for the patient with individual difference; since the diagnosis level of a doctor is improved along with the increase of the working time or the increase of the number of patients receiving a diagnosis, the doctor can objectively follow the diagnosis plan, i.e. follow the doctorThe developed diagnosis data is reflected by some medication habits or diagnosis and treatment habits, so that when the similarity of diagnosis and treatment events is calculated, a smaller weight value is given to the similarity of the third event attribute related to the inquiry data of a doctor with a larger variable, and a higher weight value is given to the similarity of the first event attribute and the similarity of the second event attribute which can present disease difference, so that the accuracy of classifying the diagnosis and treatment events can be improved to a certain extent;
step S402: respectively classifying other diagnosis and treatment events with the cumulative similarity value larger than the similarity threshold value with the diagnosis and treatment events serving as the similarity center into the same kind of diagnosis and treatment events with the diagnosis and treatment events serving as the similarity center; respectively finishing event classification on all diagnosis and treatment events contained in a historical diagnosis and treatment database of a doctor;
step S403: respectively taking each diagnosis and treatment event appearing in a historical diagnosis and treatment database of a doctor as a diagnosis and treatment experience dimension of the doctor, respectively capturing the total number Q of the diagnosis and treatment events contained in each diagnosis and treatment experience dimension, and respectively calculating an experience value corresponding to each diagnosis and treatment experience dimension
And K represents the total number K of diagnosis and treatment events existing in the historical diagnosis and treatment database of a certain doctor, and a diagnosis and treatment experience dimensional model corresponding to each doctor is respectively constructed and obtained.
In order to better realize the method, a data automation management system is also provided, and the system comprises: the system comprises a historical diagnosis and treatment database building module, a historical diagnosis and treatment database management module, a characteristic diagnosis and treatment data extraction management module, a diagnosis and treatment experience dimension model building module and an intelligent hospital platform pushing management module;
the historical diagnosis and treatment database building module is used for calling the historical diagnosis and treatment data of each doctor in a big database of the intelligent hospital and respectively building a historical diagnosis and treatment database corresponding to each doctor;
the historical diagnosis and treatment database management module is used for receiving the data in the historical diagnosis and treatment database construction module, splitting all the historical diagnosis and treatment records in each historical diagnosis and treatment database respectively based on the record information distribution characteristics of all the historical diagnosis and treatment records in each historical diagnosis and treatment database, and obtaining a plurality of independent diagnosis and treatment record subsets and a plurality of independent historical diagnosis and treatment records;
the characteristic diagnosis and treatment data extraction management module is used for receiving data in the historical diagnosis and treatment database management module, and respectively taking diagnosis and treatment data generated in each independent diagnosis and treatment record subset or each independent diagnosis and treatment record in each historical diagnosis and treatment database as diagnosis and treatment data generated by a doctor corresponding to each historical diagnosis and treatment database under one diagnosis and treatment event; extracting characteristic diagnosis and treatment data for each diagnosis and treatment event of a doctor to obtain an event attribute of each diagnosis and treatment event;
the diagnosis and treatment experience dimensional model building module is used for classifying all diagnosis and treatment events based on event attributes in a historical diagnosis and treatment database of each doctor; constructing a diagnosis and treatment experience dimensional model for each doctor;
the intelligent hospital platform pushing management module pushes matched doctors to the user according to pre-hung department information input by the user in the intelligent hospital platform, and meanwhile, data display is carried out on diagnosis and treatment experience dimensional models of the matched doctors to assist the user in selecting proper diagnosis and treatment doctors based on own disease conditions.
Furthermore, the characteristic diagnosis and treatment data extraction management module comprises a characteristic diagnosis and treatment data extraction unit and a diagnosis and treatment event attribute extraction unit;
the characteristic diagnosis and treatment data extraction unit is used for extracting characteristic diagnosis and treatment data for each diagnosis and treatment event of a doctor;
and the diagnosis and treatment event attribute extraction unit is used for receiving the data in the characteristic diagnosis and treatment data extraction unit and extracting corresponding event attributes for each diagnosis and treatment event respectively.
Furthermore, the diagnosis and treatment experience dimensional model building module comprises an event classification processing unit and a diagnosis and treatment experience dimensional model building unit;
the event classification processing unit is used for classifying all diagnosis and treatment events based on event attributes in a historical diagnosis and treatment database of each doctor;
and the diagnosis and treatment experience dimension model building unit is used for receiving the data in the event classification processing unit, calculating an experience value for each diagnosis and treatment experience dimension and building a diagnosis and treatment experience dimension model corresponding to each doctor.
Compared with the prior art, the invention has the following beneficial effects: the invention can analyze data based on all the historical diagnosis records of each doctor, judge the types of the diagnosis diseases existing in all the historical diagnosis records of each doctor based on the difference between the historical diagnosis records, reflect the meridian value of each doctor to each disease type by building a diagnosis and treatment experience dimensional model for each doctor, and display the data of the diagnosis and treatment experience dimensional model of each doctor to a user so that the user can select the most suitable doctor based on the self condition, thereby reducing the phenomenon that the patient blindly selects a specialist number for hanging diagnosis because of the psychology that the patient pursues the steady text, and reducing the waste of medical resources to a certain extent.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic flow chart of a method for automated data management based on intelligent hospitals according to the present invention;
fig. 2 is a schematic structural diagram of an intelligent hospital-based data automation management system according to the present 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 only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
Referring to fig. 1-2, the present invention provides a technical solution: a data automatic management method based on an intelligent hospital comprises the following steps:
step S100: calling historical diagnosis and treatment data of each doctor in a big database of the intelligent hospital, and respectively constructing historical diagnosis and treatment databases corresponding to each doctor, wherein the historical diagnosis and treatment data refers to data formed by collecting diagnosis and treatment data generated in each historical diagnosis and treatment record; the diagnosis and treatment data comprises self symptom description data of the patient, inquiry data of the doctor and diagnosis data prescribed by the doctor; the data types in the historical diagnosis and treatment database comprise audio and video data and text data;
step S200: splitting all historical diagnosis and treatment records in each historical diagnosis and treatment database respectively based on the record information distribution characteristics of all historical diagnosis and treatment records in each historical diagnosis and treatment database to obtain a plurality of independent diagnosis and treatment record subsets and a plurality of independent historical diagnosis and treatment records;
wherein, step S200 includes:
step S201: respectively extracting the generation time of records and the identity information of the patient to be diagnosed from all historical diagnosis and treatment records in all historical diagnosis and treatment databases; capturing the longest re-diagnosis period proposed by doctors diagnosing the same disease type to the patient from all historical diagnosis and treatment databases, and respectively setting the longest re-diagnosis period as the re-diagnosis period corresponding to each disease type;
step S202: acquiring a re-diagnosis period T corresponding to each historical diagnosis and treatment database according to the disease types which correspond to each historical diagnosis and treatment database and are diagnosed by doctors; in each historical diagnosis and treatment database, collecting the historical diagnosis and treatment records with the same identity information of the patients to be diagnosed according to the sequence of record generation, and splitting each historical diagnosis and treatment database into a plurality of diagnosis and treatment record sets and a plurality of independent historical diagnosis and treatment records; wherein, each diagnosis and treatment record set corresponds to the identity information of a patient to be treated;
step S203: in each diagnosis and treatment record set, capturing interval record generation time between every two adjacent historical diagnosis and treatment records in sequence; comparing the interval record generation time with the re-diagnosis period T corresponding to each historical diagnosis and treatment database in sequence;
step S204: when in a certain diagnosis record set, capturing the ith historical diagnosis record L i And the (i + 1) th historical diagnosis and treatment record L i+1 Interval between them record the generation time
And T satisfies >>
If i =1, the 1 st historical diagnosis and treatment record L is recorded 1 Removing from a certain diagnosis and treatment record set to obtain a new diagnosis and treatment record set, and adding L 1 As a historical diagnostic record independent of each corresponding historical diagnosis and treatment database; if i is more than or equal to 2, integrating the 1 st historical diagnosis and treatment record L 1 Obtaining a diagnosis and treatment record subset { L } from the ith historical diagnosis and treatment record 1 ,…,L i Removing all historical diagnosis and treatment records in the diagnosis and treatment record subset from a certain diagnosis and treatment record set to obtain a new diagnosis and treatment record set, and collecting the diagnosis and treatment record subset { L } 1 ,…,L i Independent of the historical diagnosis record set in each corresponding historical diagnosis and treatment database;
for example, in a historical diagnosis record set in a historical diagnosis database U, { L } is included 1 ,L 2 ,L 3 ,L 4 ,L 5 And capture L 2 And L 3 Interval between records generation time
Satisfied between day and T =7 day>
Since i =2, L will be 1 ,L 2 Integrating to obtain a subset of diagnosis and treatment records { L 1 ,L 2 And will L 1 ,L 2 From { L 1 ,L 2 ,L 3 ,L 4 ,L 5 Removing the new diagnosis and treatment records from the data, and collecting the new diagnosis and treatment records as { L } 3 ,L 4 ,L 5 }; will { L 1 ,L 2 As a set of historical diagnostic records independent of U;
step S205: the loop step S203-step S204 is that each historical diagnosis and treatment database is divided into a plurality of independent diagnosis and treatment record subsets and a plurality of independent historical diagnosis and treatment records;
step S300: respectively taking the diagnosis and treatment data generated in each independent diagnosis and treatment record subset or each independent diagnosis and treatment record in each historical diagnosis and treatment database as the diagnosis and treatment data generated by a doctor corresponding to each historical diagnosis and treatment database under one diagnosis and treatment event; extracting characteristic diagnosis and treatment data for each diagnosis and treatment event of a doctor to obtain an event attribute of each diagnosis and treatment event;
wherein, step S300 includes:
step S301: if an independent diagnosis record subset is extracted from a historical diagnosis database of a doctor, the independent diagnosis record subset comprises { W } 1 ,W 2 ,…,W n Extracting independent historical diagnosis and treatment records including { F } 1 ,F 2 ,…,F m }; wherein, W 1 ,…,W n Representing 1 st, 2 nd, \ 8230n independent diagnosis and treatment record subsets in a historical diagnosis and treatment database; f 1 ,F 2 ,…,F m The method comprises the steps of representing 1 st, 2 nd, \8230ina historical diagnosis and treatment database, and m independent historical diagnosis and treatment records; judging the total number K = n + m of diagnosis and treatment events existing in a historical diagnosis and treatment database of a certain doctor;
step S302: extracting key information of self-symptom description data of the patient, inquiry data of the doctor and diagnosis data prescribed by the doctor generated in each historical diagnosis and treatment record in each diagnosis and treatment record subset; setting key information extracted from self-symptom description data of a patient as first characteristic diagnosis and treatment data; setting key information extracted from the inquiry data of the doctor as second characteristic diagnosis and treatment data; setting key information extracted from diagnosis data prescribed by a doctor as third characteristic diagnosis and treatment data;
wherein the key information extracted from the patient's self-symptom descriptive data and the physician's inquiry data includes key information about the body part, key information about the symptom description, and key information about the symptom degree description; the key information extracted from the diagnosis data issued by the doctor comprises key information related to a diagnosis conclusion, medicine type information in the prescription order and medicine taking notice information in the prescription order;
for example, key information pertaining to the relevant body part includes, but is not limited to: head, stomach, abdomen, liver, knee, arm; key information pertaining to the description of the relevant symptoms includes, but is not limited to: pain, itching, numbness, soreness, and dizziness; key information pertaining to the description of the extent of the symptoms includes, but is not limited to: an array, urge, very, slight and very;
step S303: respectively summarizing all first characteristic diagnosis and treatment data, all second characteristic diagnosis and treatment data and all third characteristic diagnosis and treatment data extracted from all historical diagnosis and treatment records in each independent diagnosis and treatment record subset according to the generation sequence of corresponding records, and respectively correspondingly obtaining a first characteristic diagnosis and treatment data sequence, a second characteristic diagnosis and treatment data sequence and a third characteristic diagnosis and treatment data sequence; respectively corresponding the first characteristic diagnosis and treatment data sequence, the second characteristic diagnosis and treatment data sequence and the third characteristic diagnosis and treatment data sequence to be used as a first event attribute, a second event attribute and a third event attribute of a diagnosis and treatment event corresponding to each independent diagnosis and treatment record subset;
step S304: respectively corresponding first characteristic diagnosis and treatment data, second characteristic diagnosis and treatment data and third characteristic diagnosis and treatment data extracted from each independent historical diagnosis and treatment record to be used as a first event attribute, a second event attribute and a third event attribute of a diagnosis and treatment event corresponding to each independent historical diagnosis and treatment record;
step S400: in a historical diagnosis and treatment database of each doctor, classifying all diagnosis and treatment events based on event attributes; constructing a diagnosis and treatment experience dimensional model for each doctor;
step S500: the method comprises the steps that a user registers and logs in a smart hospital platform, pre-hung department information is input into the smart hospital platform, the smart hospital platform pushes matched doctors to the user based on the department information, meanwhile, data display is conducted on diagnosis and treatment experience dimensional models of the matched doctors, and the user is assisted in selecting proper diagnosis and treatment doctors based on the disease conditions of the user;
wherein, step S400 includes:
step S401: randomly selecting a diagnosis and treatment event as a similar center in a historical diagnosis and treatment database of a doctor; respectively carrying out similarity calculation on the first event attribute, the second event attribute and the third event attribute on other diagnosis and treatment events in the historical diagnosis and treatment database and the diagnosis and treatment events serving as the similar centers to respectively obtain the cumulative similarity value between the other diagnosis and treatment events in the historical diagnosis and treatment database and the diagnosis and treatment events serving as the similar centers: r = a R 1 +b*r 2 +c*r 3 (ii) a Wherein r is 1 、r 2 、r 3 Respectively representing the similarity of the other diagnosis and treatment events in the historical diagnosis and treatment database and the diagnosis and treatment events serving as the similarity center on the first event attribute, the second event attribute and the third event attribute; wherein a is r 1 B is r 2 C is r 3 The weight value of (2); wherein, a>b>c；
Step S402: respectively classifying other diagnosis and treatment events with the cumulative similarity value larger than the similarity threshold value with the diagnosis and treatment events serving as the similarity center into the same kind of diagnosis and treatment events with the diagnosis and treatment events serving as the similarity center; respectively finishing event classification on all diagnosis and treatment events contained in a historical diagnosis and treatment database of a doctor;
step S403: respectively taking each diagnosis and treatment event appearing in a historical diagnosis and treatment database of a certain doctor as a diagnosis and treatment experience dimension of the certain doctor, respectively capturing the total number Q of the diagnosis and treatment events contained in each diagnosis and treatment experience dimension, and respectively calculating an experience value corresponding to each diagnosis and treatment experience dimension
And K represents the total number K of diagnosis and treatment events existing in the historical diagnosis and treatment database of a certain doctor, and a diagnosis and treatment experience dimensional model corresponding to each doctor is respectively constructed and obtained.
In order to better realize the method, a data automation management system is also provided, and the system comprises: the system comprises a historical diagnosis and treatment database building module, a historical diagnosis and treatment database management module, a characteristic diagnosis and treatment data extraction management module, a diagnosis and treatment experience dimension model building module and an intelligent hospital platform pushing management module;
the historical diagnosis and treatment database building module is used for calling the historical diagnosis and treatment data of each doctor in a big database of the intelligent hospital and respectively building a historical diagnosis and treatment database corresponding to each doctor;
the historical diagnosis and treatment database management module is used for receiving the data in the historical diagnosis and treatment database construction module, splitting all the historical diagnosis and treatment records in each historical diagnosis and treatment database respectively based on the record information distribution characteristics of all the historical diagnosis and treatment records in each historical diagnosis and treatment database, and obtaining a plurality of independent diagnosis and treatment record subsets and a plurality of independent historical diagnosis and treatment records;
the characteristic diagnosis and treatment data extraction management module is used for receiving data in the historical diagnosis and treatment database management module, and respectively taking diagnosis and treatment data generated in each independent diagnosis and treatment record subset or each independent diagnosis and treatment record in each historical diagnosis and treatment database as diagnosis and treatment data generated by a doctor corresponding to each historical diagnosis and treatment database under one diagnosis and treatment event; extracting characteristic diagnosis and treatment data for each diagnosis and treatment event of a doctor to obtain an event attribute of each diagnosis and treatment event;
the diagnosis and treatment experience dimensional model building module is used for classifying all diagnosis and treatment events based on event attributes in a historical diagnosis and treatment database of each doctor; constructing a diagnosis and treatment experience dimensional model for each doctor;
the intelligent hospital platform pushing management module pushes matched doctors to the user according to pre-hung department information input by the user in the intelligent hospital platform, and meanwhile, data display is carried out on diagnosis and treatment experience dimensional models of the matched doctors to assist the user in selecting proper diagnosis and treatment doctors based on own disease conditions.
The characteristic diagnosis and treatment data extraction management module comprises a characteristic diagnosis and treatment data extraction unit and a diagnosis and treatment event attribute extraction unit;
the characteristic diagnosis and treatment data extraction unit is used for extracting characteristic diagnosis and treatment data for each diagnosis and treatment event of a doctor;
and the diagnosis and treatment event attribute extraction unit is used for receiving the data in the characteristic diagnosis and treatment data extraction unit and extracting corresponding event attributes for each diagnosis and treatment event respectively.
The diagnosis and treatment experience dimensional model building module comprises an event classification processing unit and a diagnosis and treatment experience dimensional model building unit;
the event classification processing unit is used for classifying all diagnosis and treatment events based on event attributes in a historical diagnosis and treatment database of each doctor;
and the diagnosis and treatment experience dimension model building unit is used for receiving the data in the event classification processing unit, calculating an experience value for each diagnosis and treatment experience dimension and building a diagnosis and treatment experience dimension model corresponding to each doctor.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. An automatic data management method based on an intelligent hospital is characterized by comprising the following steps:
step S100: calling historical diagnosis and treatment data of each doctor in a big database of the intelligent hospital, and respectively constructing historical diagnosis and treatment databases corresponding to each doctor, wherein the historical diagnosis and treatment data are data formed by collecting diagnosis and treatment data generated in each historical diagnosis and treatment record; the diagnosis and treatment data comprises self symptom description data of the patient, inquiry data of a doctor and diagnosis data prescribed by the doctor; the data types in the historical diagnosis and treatment database comprise audio and video data and text data;
step S200: splitting all historical diagnosis and treatment records in each historical diagnosis and treatment database respectively based on the record information distribution characteristics of all historical diagnosis and treatment records in each historical diagnosis and treatment database to obtain a plurality of independent diagnosis and treatment record subsets and a plurality of independent historical diagnosis and treatment records;
step S300: respectively taking the diagnosis and treatment data generated in each independent diagnosis and treatment record subset or each independent diagnosis and treatment record in each historical diagnosis and treatment database as the diagnosis and treatment data generated by a doctor corresponding to each historical diagnosis and treatment database under one diagnosis and treatment event; extracting characteristic diagnosis and treatment data for each diagnosis and treatment event of the doctor to obtain an event attribute of each diagnosis and treatment event;
step S400: in a historical diagnosis and treatment database of each doctor, classifying all diagnosis and treatment events based on event attributes; constructing a diagnosis and treatment experience dimensional model for each doctor;
step S500: the method comprises the steps that a user logs in a smart hospital platform, pre-hung department information is input into the smart hospital platform, the smart hospital platform pushes matched doctors to the user based on the department information, meanwhile, data display is conducted on diagnosis and treatment experience dimensional models of the matched doctors, and the user is assisted to select proper diagnosis and treatment doctors based on own disease conditions.
2. The method for automated data management based on intelligent hospital according to claim 1, wherein said step S200 includes:
step S201: respectively extracting the generation time of records and the identity information of the patient to be diagnosed from all historical diagnosis and treatment records in all historical diagnosis and treatment databases; capturing the longest re-diagnosis period proposed by doctors diagnosing the same disease type to a patient from all historical diagnosis and treatment databases, and setting the longest re-diagnosis period as the re-diagnosis period corresponding to each disease type;
step S202: acquiring a re-diagnosis period T corresponding to each historical diagnosis and treatment database according to the disease type which is responsible for diagnosis of the doctor corresponding to each historical diagnosis and treatment database; in each historical diagnosis and treatment database, collecting the historical diagnosis and treatment records with the same identity information of the patients to be diagnosed according to the sequence of record generation, and splitting each historical diagnosis and treatment database into a plurality of diagnosis and treatment record sets and a plurality of independent historical diagnosis and treatment records; wherein, each diagnosis and treatment record set corresponds to the identity information of a patient to be treated;
step S203: capturing interval record generation time between every two adjacent historical diagnosis and treatment records in each diagnosis and treatment record set in sequence; comparing the generation time of each interval record with the re-diagnosis period T corresponding to each historical diagnosis and treatment database in sequence;
step S204: when in a certain diagnosis record set, capturing the ith historical diagnosis record L i And the (i + 1) th historical diagnosis and treatment record L i+1 Interval between records generation time
And T satisfies->
If i =1, the 1 st historical diagnosis and treatment record L is recorded 1 Removing the diagnosis record set to obtain a new diagnosis record set, andmixing L with 1 As a historical diagnosis record independent of each corresponding historical diagnosis and treatment database; if i is more than or equal to 2, integrating the 1 st historical diagnosis and treatment record L 1 Obtaining a diagnosis and treatment record subset { L } from the ith historical diagnosis and treatment record 1 ,…,L i Removing all historical diagnosis and treatment records in the diagnosis and treatment record subset from a certain diagnosis and treatment record set to obtain a new diagnosis and treatment record set, and combining the diagnosis and treatment record subset { L } 1 ,…,L i The historical diagnosis records are independent of each corresponding historical diagnosis and treatment database;
step S205: and (S203) to S204, dividing each historical diagnosis and treatment database into a plurality of independent diagnosis and treatment record subsets and a plurality of independent historical diagnosis and treatment records.
3. The method for automated data management based on intelligent hospital according to claim 1, wherein said step S300 includes:
step S301: if an independent diagnosis record subset is extracted from a historical diagnosis database of a doctor, the independent diagnosis record subset comprises { W } 1 ,W 2 ,…,W n Extracting independent historical diagnosis and treatment records including { F } 1 ,F 2 ,…,F m }; wherein, W 1 ,…,W n Representing 1 st, 2 nd, \ 8230n independent diagnosis and treatment record subsets in the historical diagnosis and treatment database; f 1 ,F 2 ,…,F m The 1 st, 2 nd, \ 8230th and m independent historical diagnosis and treatment records in the historical diagnosis and treatment database are represented; judging the total number K = n + m of diagnosis and treatment events existing in a historical diagnosis and treatment database of a certain doctor;
step S302: extracting key information of self-symptom description data of the patient, inquiry data of the doctor and diagnosis data prescribed by the doctor generated in each historical diagnosis and treatment record in each diagnosis and treatment record subset; setting key information extracted from self-symptom description data of a patient as first characteristic diagnosis and treatment data; setting key information extracted from inquiry data of a doctor as second characteristic diagnosis and treatment data; setting key information extracted from diagnosis data prescribed by a doctor as third characteristic diagnosis and treatment data;
step S303: respectively summarizing all first characteristic diagnosis and treatment data, all second characteristic diagnosis and treatment data and all third characteristic diagnosis and treatment data extracted from all historical diagnosis and treatment records in each independent diagnosis and treatment record subset according to the generation sequence of corresponding records, and respectively and correspondingly obtaining a first characteristic diagnosis and treatment data sequence, a second characteristic diagnosis and treatment data sequence and a third characteristic diagnosis and treatment data sequence; respectively corresponding the first characteristic diagnosis and treatment data sequence, the second characteristic diagnosis and treatment data sequence and the third characteristic diagnosis and treatment data sequence to be used as a first event attribute, a second event attribute and a third event attribute of the diagnosis and treatment event corresponding to each independent diagnosis and treatment record subset;
step S304: and respectively corresponding first characteristic diagnosis and treatment data, second characteristic diagnosis and treatment data and third characteristic diagnosis and treatment data extracted from each independent historical diagnosis and treatment record to be used as a first event attribute, a second event attribute and a third event attribute of the diagnosis and treatment event corresponding to each independent historical diagnosis and treatment record.
4. The intelligent hospital-based data automation management method according to claim 3, wherein the key information extracted from the patient's self-symptom description data and the doctor's inquiry data includes key information about body parts, key information about symptom description, and key information about symptom degree description; the key information extracted from the diagnosis data issued by the doctor comprises key information about diagnosis conclusion, medicine type information in the prescription order and medicine taking notice information in the prescription order.
5. The method for automatically managing data based on intelligent hospital according to claim 4, wherein the step S400 comprises:
step S401: randomly selecting a diagnosis and treatment event as a similar center in a historical diagnosis and treatment database of a doctor; respectively comparing other diagnosis and treatment events in the historical diagnosis and treatment database with the operationSimilarity calculation of the first event attribute, the second event attribute and the third event attribute is carried out on the diagnosis and treatment events of the similarity center, and the cumulative similarity value between other diagnosis and treatment events in the historical diagnosis and treatment database and the diagnosis and treatment events serving as the similarity center is respectively obtained: r = a R 1 +b*r 2 +c*r 3 (ii) a Wherein r is 1 、r 2 、r 3 Respectively representing the similarity of other diagnosis and treatment events in the historical diagnosis and treatment database and the diagnosis and treatment events serving as the similarity center on a first event attribute, a second event attribute and a third event attribute; wherein a is r 1 B is r 2 C is r 3 The weight value of (2); wherein, a>b>c；
Step S402: respectively classifying other diagnosis and treatment events with the cumulative similarity value larger than the similarity threshold value with the diagnosis and treatment events serving as the similarity center into the same kind of diagnosis and treatment events with the diagnosis and treatment events serving as the similarity center; respectively finishing event classification on all diagnosis and treatment events contained in the historical diagnosis and treatment database of a certain doctor;
step S403: respectively taking each diagnosis and treatment event appearing in a historical diagnosis and treatment database of a certain doctor as a diagnosis and treatment experience dimension of the certain doctor, respectively capturing the total number Q of the diagnosis and treatment events contained in each diagnosis and treatment experience dimension, and respectively calculating an experience value corresponding to each diagnosis and treatment experience dimension
And K represents the total number K of diagnosis and treatment events existing in the historical diagnosis and treatment database of a certain doctor, and a diagnosis and treatment experience dimensional model corresponding to each doctor is respectively constructed and obtained.
6. A data automation management system applying the intelligent hospital-based data automation management method of any one of claims 1 to 5, characterized in that the system comprises: the system comprises a historical diagnosis and treatment database building module, a historical diagnosis and treatment database management module, a characteristic diagnosis and treatment data extraction management module, a diagnosis and treatment experience dimension model building module and an intelligent hospital platform pushing management module;
the historical diagnosis and treatment database building module is used for calling the historical diagnosis and treatment data of each doctor in a big database of the intelligent hospital and respectively building a historical diagnosis and treatment database corresponding to each doctor;
the historical diagnosis and treatment database management module is used for receiving the data in the historical diagnosis and treatment database building module, splitting all the historical diagnosis and treatment records in each historical diagnosis and treatment database respectively based on the record information distribution characteristics of all the historical diagnosis and treatment records in each historical diagnosis and treatment database, and obtaining a plurality of independent diagnosis and treatment record subsets and a plurality of independent historical diagnosis and treatment records;
the characteristic diagnosis and treatment data extraction management module is used for receiving the data in the historical diagnosis and treatment database management module, and respectively taking diagnosis and treatment data generated in each independent diagnosis and treatment record subset or each independent diagnosis and treatment record in each historical diagnosis and treatment database as diagnosis and treatment data generated by a doctor corresponding to each historical diagnosis and treatment database under one diagnosis and treatment event; extracting characteristic diagnosis and treatment data for each diagnosis and treatment event of the doctor to obtain an event attribute of each diagnosis and treatment event;
the diagnosis and treatment experience dimensional model building module is used for classifying all diagnosis and treatment events based on event attributes in a historical diagnosis and treatment database of each doctor; constructing a diagnosis and treatment experience dimensional model for each doctor;
the pushing management module of the intelligent hospital platform pushes matched doctors to the user according to pre-hung department information input by the user in the intelligent hospital platform, and meanwhile, data display is carried out on diagnosis and treatment experience dimensional models of the matched doctors, so that the intelligent hospital platform assists the user to select a proper diagnosis and treatment doctor based on the disease condition of the user.
7. The automated data management system according to claim 6, wherein the characteristic diagnosis and treatment data extraction management module comprises a characteristic diagnosis and treatment data extraction unit and a diagnosis and treatment event attribute extraction unit;
the characteristic diagnosis and treatment data extraction unit is used for extracting characteristic diagnosis and treatment data for each diagnosis and treatment event of a doctor;
the diagnosis and treatment event attribute extraction unit is used for receiving the data in the characteristic diagnosis and treatment data extraction unit and extracting corresponding event attributes for each diagnosis and treatment event respectively.
8. The automated data management system according to claim 6, wherein the clinical empirical dimensional model building module comprises an event classification processing unit and a clinical empirical dimensional model building unit;
the event classification processing unit is used for classifying all diagnosis and treatment events based on event attributes in a historical diagnosis and treatment database of each doctor;
the diagnosis and treatment experience dimensional model building unit is used for receiving the data in the event classification processing unit, calculating an experience value for each diagnosis and treatment experience dimension and building a diagnosis and treatment experience dimensional model corresponding to each doctor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310012103.9A CN115966292B (en) | 2023-01-05 | 2023-01-05 | Intelligent hospital-based data automation management system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310012103.9A CN115966292B (en) | 2023-01-05 | 2023-01-05 | Intelligent hospital-based data automation management system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115966292A true CN115966292A (en) | 2023-04-14 |
| CN115966292B CN115966292B (en) | 2023-09-15 |
Family
ID=87361314
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310012103.9A Active CN115966292B (en) | 2023-01-05 | 2023-01-05 | Intelligent hospital-based data automation management system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115966292B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050108052A1 (en) * | 2003-11-03 | 2005-05-19 | Omaboe Nortey J. | Proces for diagnosic system and method applying artificial intelligence techniques to a patient medical record and that combines customer relationship management (CRM) and enterprise resource planning (ERP) software in a revolutionary way to provide a unique-and uniquely powerful and easy-to-use-tool to manage veterinary or human medical clinics and hospitals |
| WO2016101351A1 (en) * | 2014-12-26 | 2016-06-30 | 深圳市前海安测信息技术有限公司 | Network hospital based general practitioner auxiliary diagnosis and treatment system and method |
| CN109961841A (en) * | 2019-03-28 | 2019-07-02 | 广州麦迪森在线医疗科技有限公司 | A kind of optimal doctor's matching system and method towards mobile diagnosis and treatment |
| CN112164451A (en) * | 2020-09-18 | 2021-01-01 | 中国建设银行股份有限公司 | Intelligent diagnosis guiding and registering method, device, equipment and storage medium |
| CN112530604A (en) * | 2020-12-18 | 2021-03-19 | 陈少雄 | Remote intelligent medical system based on cloud platform |
| WO2021151351A1 (en) * | 2020-09-04 | 2021-08-05 | 平安科技（深圳）有限公司 | Data processing method and apparatus, computer device, and storage medium |
| WO2021174788A1 (en) * | 2020-03-02 | 2021-09-10 | 平安科技（深圳）有限公司 | Information matching analysis method and apparatus, and computer system and readable storage medium |
| CN113592345A (en) * | 2021-08-10 | 2021-11-02 | 康键信息技术（深圳）有限公司 | Medical triage method, system, equipment and storage medium based on clustering model |
| CN114065856A (en) * | 2021-11-16 | 2022-02-18 | 北京和兴创联健康科技有限公司 | Doctor recommendation method, device and equipment based on doctor portrait and storage medium |
| US20220068454A1 (en) * | 2020-09-01 | 2022-03-03 | RCR BioPharma | System and method for medical research data processing, acquisition and analysis |
| KR102444145B1 (en) * | 2022-01-17 | 2022-09-16 | 주식회사 프릭스헬스케어 | Apparatus and method for providing of remote medical service using infant health information |
-
2023
- 2023-01-05 CN CN202310012103.9A patent/CN115966292B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050108052A1 (en) * | 2003-11-03 | 2005-05-19 | Omaboe Nortey J. | Proces for diagnosic system and method applying artificial intelligence techniques to a patient medical record and that combines customer relationship management (CRM) and enterprise resource planning (ERP) software in a revolutionary way to provide a unique-and uniquely powerful and easy-to-use-tool to manage veterinary or human medical clinics and hospitals |
| WO2016101351A1 (en) * | 2014-12-26 | 2016-06-30 | 深圳市前海安测信息技术有限公司 | Network hospital based general practitioner auxiliary diagnosis and treatment system and method |
| CN109961841A (en) * | 2019-03-28 | 2019-07-02 | 广州麦迪森在线医疗科技有限公司 | A kind of optimal doctor's matching system and method towards mobile diagnosis and treatment |
| WO2021174788A1 (en) * | 2020-03-02 | 2021-09-10 | 平安科技（深圳）有限公司 | Information matching analysis method and apparatus, and computer system and readable storage medium |
| US20220068454A1 (en) * | 2020-09-01 | 2022-03-03 | RCR BioPharma | System and method for medical research data processing, acquisition and analysis |
| WO2021151351A1 (en) * | 2020-09-04 | 2021-08-05 | 平安科技（深圳）有限公司 | Data processing method and apparatus, computer device, and storage medium |
| CN112164451A (en) * | 2020-09-18 | 2021-01-01 | 中国建设银行股份有限公司 | Intelligent diagnosis guiding and registering method, device, equipment and storage medium |
| CN112530604A (en) * | 2020-12-18 | 2021-03-19 | 陈少雄 | Remote intelligent medical system based on cloud platform |
| CN113592345A (en) * | 2021-08-10 | 2021-11-02 | 康键信息技术（深圳）有限公司 | Medical triage method, system, equipment and storage medium based on clustering model |
| CN114065856A (en) * | 2021-11-16 | 2022-02-18 | 北京和兴创联健康科技有限公司 | Doctor recommendation method, device and equipment based on doctor portrait and storage medium |
| KR102444145B1 (en) * | 2022-01-17 | 2022-09-16 | 주식회사 프릭스헬스케어 | Apparatus and method for providing of remote medical service using infant health information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115966292B (en) | 2023-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101911077B (en) | For the method and apparatus of hierarchical search | |
| US8670997B2 (en) | Quality metric extraction and editing for medical data | |
| JP6907831B2 (en) | Context-based patient similarity methods and equipment | |
| WO2017147552A9 (en) | Multi-format, multi-domain and multi-algorithm metalearner system and method for monitoring human health, and deriving health status and trajectory | |
| CN103559637A (en) | Method and system for recommending doctor for patient | |
| CN106919804A (en) | Medicine based on clinical data recommends method, recommendation apparatus and server | |
| KR101565331B1 (en) | Analyzing system for medical informations using patterns and the method thereof | |
| CN114416967A (en) | Method, device and equipment for intelligently recommending doctors and storage medium | |
| Frize et al. | Suggested criteria for successful deployment of a Clinical Decision Support System (CDSS) | |
| CN113851220A (en) | Disease condition trend prediction method and system based on time sequence medical health data | |
| Chou et al. | Extracting drug utilization knowledge using self-organizing map and rough set theory | |
| CN117275660A (en) | Full-link AI auxiliary method for inquiry to prescription | |
| CN112102956A (en) | Method and system for improving compliance of diabetic patient | |
| WO2022229964A1 (en) | Method of generating a diseases database, usage of the diseases database, and system therefor | |
| Duhamel et al. | A preprocessing method for improving data mining techniques. Application to a large medical diabetes database | |
| CN117476217A (en) | Chronic heart disease state of illness trend prediction system | |
| Ledley | Practical problems in the use of computers in medical diagnosis | |
| JP2009031900A (en) | Medical checkup data processor | |
| Antonelli et al. | MeTA: Characterization of medical treatments at different abstraction levels | |
| CN107066816A (en) | Medical treatment guidance method, device and server based on clinical data | |
| Razali et al. | Generating treatment plan in medicine: A data mining approach | |
| CN115966292A (en) | Data automatic management system and method based on intelligent hospital | |
| CN112309519B (en) | Electronic medical record medication structured processing system based on multiple models | |
| CN114300075A (en) | Exercise medical health data management system based on big data | |
| CN113517044A (en) | Clinical data processing method and system for evaluating citicoline based on pharmacokinetics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |