CN111508618A - Perioperative period artificial intelligence auxiliary platform system - Google Patents
Perioperative period artificial intelligence auxiliary platform system Download PDFInfo
- Publication number
- CN111508618A CN111508618A CN202010285565.4A CN202010285565A CN111508618A CN 111508618 A CN111508618 A CN 111508618A CN 202010285565 A CN202010285565 A CN 202010285565A CN 111508618 A CN111508618 A CN 111508618A
- Authority
- CN
- China
- Prior art keywords
- module
- patient
- data
- information
- submodule
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a perioperative artificial intelligence auxiliary platform system, which comprises the following modules for data communication through a network: the user interaction module is used for providing a user interaction interface; a medical device docking module for docking a medical device to obtain surgical data; the operation video recording module is used for butting a video signal source to obtain a corresponding image; the operation video system docking module is used for docking the operation video system to acquire a corresponding image; the hospital information system docking module is used for docking corresponding information systems in a hospital; the patient information system storage module is used for storing patient information; and the data analysis server module is used for communicating with each module and analyzing the received data. The invention can store, analyze and apply data according to the visual angle of the operation patient, and the customized postoperative recovery scheme can improve the quality and efficiency of postoperative rehabilitation of the patient, thereby promoting the development of the medical industry and further improving the quality of clinical operations.
Description
Technical Field
The invention belongs to the technical field of intelligent medical systems, and particularly relates to a perioperative artificial intelligence auxiliary platform system.
Background
The current hospital information system is various, the switching operation among multiple systems is complex and tedious, and no information system completely takes an operation patient as a core to record data generated in the whole process from the decision of accepting an operation to discharging (namely perioperative period). Problems caused by the current situation include: the process of collecting data from multiple information systems when performing pre-operative consultation on a patient is cumbersome; the information of the preoperative consultation record, the intraoperative process record data, the postoperative follow-up visit data and the like cannot be completely bound with the information of the surgical patient, and the perioperative data analysis of the surgical patient cannot be carried out. If a platform which takes the operation patient as a core, records the data of the whole perioperative period of the operation patient and combines the artificial intelligence technology to realize the intelligent auxiliary patient postoperative recovery exists, the problems can be obviously improved.
Disclosure of Invention
The invention aims to overcome the problems in the prior art and provides a perioperative artificial intelligence auxiliary platform system which can integrate different information systems and medical equipment of a hospital and provide perioperative data records and schemes taking an operative patient as a visual angle for doctors and operative patients.
In order to solve the problems of the prior art, the invention discloses a perioperative artificial intelligence auxiliary platform system, which comprises the following modules for data communication through a network:
the user interaction module is used for providing a user interaction interface;
a medical device docking module for docking a medical device to obtain surgical data;
the operation video recording module is used for butting a video signal source to obtain a corresponding image;
the operation video system docking module is used for docking the operation video system to acquire a corresponding image;
the hospital information system docking module is used for docking corresponding information systems in a hospital;
the patient information system storage module is used for storing patient information; and
and the data analysis server module is used for communicating with each module and analyzing the received data.
Further, the air conditioner is provided with a fan,
the user interaction module includes:
the user authority management submodule is used for displaying different user interaction interfaces according to different authorities of users;
the preoperative consultation submodule is used for providing consultation service according to a consultation request of a user;
the intraoperative process recording submodule is used for recording relevant information in the surgical process;
the postoperative reply module is used for providing postoperative process review service according to a review request of a user; and
and the postoperative follow-up sub-module is used for recording the discharge condition of the patient.
Further, the air conditioner is provided with a fan,
the data analysis server module includes:
the interactive interface submodule is used for receiving the request sent by the user interactive module and sending the information corresponding to the request;
the information exchange sub-module is used for data interaction between the user interaction module and the patient information system storage module and data interaction between the hospital information system docking module and the patient information system storage module;
and the analysis submodule is used for analyzing the received data and giving out an analysis result.
Further, the air conditioner is provided with a fan,
the specific process of analyzing the received data and giving an analysis result by the analysis module is as follows:
establishing a data model of the patient information and the operation success index according to the operation data;
training a data model based on the data of the neural network and all patients in the system;
defining an index of success of the surgery;
and predicting the operation success index of the patient according to the input new patient information.
Further, the air conditioner is provided with a fan,
the specific process of establishing the data model related to the patient information and the operation success index according to the operation data comprises the following steps:
selecting M operation cases of a certain class in N years in a hospital, and taking patient information as input; outputting the result of the surgery of the patient; dividing M cases into a training data set, a verification data set and a test data set according to the proportion of X, Y and Z; wherein N is more than or equal to 5 and less than or equal to 20, N is more than or equal to 500 and less than or equal to 2000, and X + Y + Z is equal to M; the patient information comprises age, gender, illness and operation conditions in A year, body health index and insurance type, and A is less than or equal to 3; the patient's surgical outcome includes 5-year survival rate after surgery and postoperative self-care index of life;
the specific process of training the data model based on the data of all patients in the neural network and the system is as follows:
taking the patient information as an input layer, setting the number of nodes of the input layer to be 5, taking the operation result of the patient as an output layer, and setting the number of nodes of the output layer to be 2;
determining the number of nodes of the hidden layer by an empirical formula;
determining an input activation function and a damage function, and setting a target value of the loss function;
performing a first round of training using the training set data, calculating a loss function value using the validation data set, and determining to stop learning and continue learning according to whether the loss function value is less than a target value;
the accuracy of the data model is verified using the test data set.
Further, the air conditioner is provided with a fan,
the hospital information system docking module includes:
the communication submodule is used for analyzing the information sent by the data analysis server module and sending the information to the data analysis server module;
the docking sub-module is used for docking different hospital information systems to acquire related data;
the analysis submodule is used for analyzing the acquired data;
and the retrieval submodule is used for retrieving the patient information according to the hospitalization number of the patient and sending the patient information to the data analysis server module.
Further, the air conditioner is provided with a fan,
the surgery video recording module comprises:
the communication submodule is used for analyzing the information sent by the data analysis server module and sending the information to the data analysis server module; and
and the control submodule is used for generating a control signal for controlling the video recording equipment according to the received information so as to acquire a corresponding image.
Further, the air conditioner is provided with a fan,
the patient information system storage module includes:
the database submodule is used for storing the patient information;
the communication submodule is used for analyzing the information sent by the data analysis server module and sending the information to the data analysis server module;
the database management submodule is used for managing the patient information in the database submodule; and
and the disk array management submodule is used for managing the disk array information in the database submodule.
Further, the air conditioner is provided with a fan,
the database submodule includes:
the patient basic information table submodule is used for storing table fields comprising a patient hospitalization number, a patient identity card, a patient name, a sex, an age and a department;
the patient admission record table submodule is used for storing table fields comprising a patient admission number, an admission department, admission time and discharge time;
the patient operation record table is used for storing table fields including the hospitalization number of the patient, whether the preoperative consultation is performed or not, the consultation result, the operation scheduling time, the actual operation starting time, the actual operation ending time and the operation video record number; and
the patient operation video recording table is used for storing table fields including the hospitalization number of the patient, the operation video recording number and the operation video recording storage address.
Further, the air conditioner is provided with a fan,
the user interaction module is a client module or a webpage end module.
The invention has the following beneficial effects: the data can be stored, analyzed and applied by the visual angle of the operation patient, the customized postoperative recovery scheme can improve the postoperative rehabilitation quality and efficiency of the patient, and the scientific research data material provided for the doctor can further improve the scientific research output of the doctor, thereby promoting the development of the medical industry, further improving the clinical operation quality and finally benefiting the majority of patients.
Drawings
FIG. 1 is a system block diagram of a perioperative artificial intelligence assistance platform system of the present invention;
FIG. 2 is a system block diagram of a preferred embodiment of the perioperative artificial intelligence assistance platform system shown in FIG. 1;
FIG. 3 is a schematic diagram of the perioperative artificial intelligence assistance platform system of FIG. 1 for modeling data.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
As shown in FIG. 1, a perioperative artificial intelligence assistance platform system comprises the following modules in data communication via a network: the system comprises a user interaction module 1, a medical equipment docking module 2, a surgery video recording module 4, a surgery video recording system docking module 5, a hospital information system docking module 6, a patient information system storage module 7 and a data analysis server module 3.
The medical equipment docking module 4 IS deployed in an operating room, realizes docking with various signal sources in the operating room, such as an endoscope host, an operation field camera and the like, and realizes recording and screenshot functions of the signal sources, the operation video system docking module 5 IS deployed in the operating room, realizes docking with an operating room video system, the hospital information system docking module 6 IS deployed in a hospital information machine room, realizes docking with various information systems in the hospital, such as a hospital information system HIS, a hospital image archiving communication system PACS, an electronic medical record system EMR, a hospital pathology information system L IS and the like, and provides an expandable capacity storage system and a data analysis server module 3 which are deployed in the hospital information machine room and are used for communicating with the modules and analyzing received data.
The user interaction module 1 is a display module of a perioperative artificial intelligence auxiliary platform and comprises a user authority management sub-module, a preoperative consultation sub-module, an intraoperative process recording sub-module, an postoperative reply sub-module and an postoperative follow-up sub-module.
Specifically, the user authority management submodule is used for displaying different user interaction interfaces according to different authorities possessed by the user. When a patient logs on the platform, the user can only check diagnosis and operation information related to the user; when the main doctor logs in the platform, the main doctor can check the patient diagnosis and treatment information, consultation information and operation information arranged on the main doctor. The preoperative consultation submodule is used for providing consultation service according to a consultation request of a user, and realizes the functions of initiating consultation, receiving consultation, checking diagnosis information of a patient in the consultation process, recording the consultation result and finishing the consultation by a doctor user. The intraoperative process recording submodule is used for recording relevant information in the surgical process, such as video recording, screenshot, vital signs, intraoperative key events and intraoperative medication records of the surgical process. The postoperative re-tray module is used for providing postoperative process review service according to a review request of a user and realizing uniform display of data records of the process from preoperative diagnosis to discharge of an operation patient. And the postoperative follow-up sub-module is used for recording the discharge condition of the patient.
The data analysis server module 3 is a core module of the perioperative artificial intelligence auxiliary platform and comprises an interactive interface submodule, an information exchange submodule and an analysis submodule.
Specifically, the interactive interface sub-module is used for receiving a request sent by the user interaction module 1 and sending information corresponding to the request. The information exchange submodule is used for data interaction between the user interaction module 1 and the patient information system storage module 7 and data interaction between the hospital information system docking module and the patient information system storage module 7. The analysis submodule is used for analyzing the received data and giving an analysis result, and provides a preoperative discussion decision reference and a customized postoperative recovery scheme for the patient through the function, so that the postoperative recovery scheme is a scientific research material for typical case analysis and multi-dimensional case analysis.
For the analysis submodule, the specific process for realizing intelligent analysis is as follows:
and S1, establishing a data model of the patient information and the operation success index according to the operation data.
Specifically, M operation cases of a certain type in N years in a hospital are selected, and patient information is used as input; outputting the result of the surgery of the patient; dividing M cases into a training data set, a verification data set and a test data set according to the proportion of X, Y and Z; wherein N is more than or equal to 5 and less than or equal to 20, N is more than or equal to 500 and less than or equal to 2000, and X + Y + Z is equal to M; the patient information comprises age, gender, illness and operation conditions in A year, body health index and insurance type, and A is less than or equal to 3; the patient's surgical outcome includes the 5-year survival rate of the surgery and the postoperative self-care index of life.
S2, training the data model based on the data of the neural network and all patients in the system.
S21, using the patient information as an input layer, setting the number of nodes of the input layer to be 5, using the operation result of the patient as an output layer, and setting the number of nodes of the output layer to be 2.
And S22, determining the number of the hidden layer nodes by an empirical formula. The empirical formula is:
m is the number of input layer nodes, n is the number of output layer nodes, and a is the interval [1,10 ]]Constant, finally determining the hiddenThe number of the nodes containing the layers is 6.
And S23, determining an input activation function and a damage function, and setting a target value of the loss function. The activation function is:
the impairment function is:
wherein x isiRepresenting the calculated value of the output node and x representing the actual value of the output node.
S24, using the training set data to carry out the first round of training, using the verification data set to calculate the loss function value, and deciding to stop learning and continue learning according to whether the loss function value is smaller than the target value; and if the loss function value is smaller than the target value, stopping learning, and otherwise, continuing learning until stopping.
S25, verifying the accuracy of the data model using the test data set.
S26, defining an operation success index; the calculation formula of the operation success index is as follows:
wherein FYSR is the 5-year survival rate of operation, L CI is the self-care index of life after operation, when SSI>The procedure was considered successful at 0.75.
And S27, predicting the operation success index of the patient according to the input new patient information. For example, when a new patient needs a pre-operation consultation discussion, the patient information is input into the system to predict the patient operation success index SSI.
The hospital information system docking module 6 comprises a communication sub-module, a docking sub-module, an analysis sub-module and a retrieval sub-module.
Specifically, the communication sub-module is configured to parse information sent by the data analysis server module 3 and send the information to the data analysis server module 3, so as to achieve the purpose of establishing a communication mechanism based on HTTP with the data analysis server module. The docking sub-module is used for docking different hospital information systems to acquire related data, and the purpose of establishing a docking mechanism with the hospital information systems is achieved. Because the open interfaces provided by different hospital information are different, the docking mechanism comprises and is not limited to a WebService communication mechanism, a database view communication mechanism and a message queue communication mechanism so as to meet the requirements of docking different hospital information systems and acquiring data. The analysis submodule is used for analyzing the data fields which can be identified by the acquired data cost platform system and recombining the data fields, so that the purposes of acquiring and analyzing the patient information of different hospital information systems are achieved. The retrieval submodule is used for retrieving the patient information according to the patient hospitalization number and sending the patient information to the data analysis server module 3, and then the data analysis server module 3 can send the data to the user interaction module 1 and the patient information system storage module 7 respectively.
The operation video recording module 4 is a module related to perioperative artificial intelligence auxiliary platform and operating room video recording. The module receives video recording and screenshot commands sent by a user interaction module 1 through a data analysis server module, carries out standard H.264 coding on an operating room signal source through a coder arranged at the rear end of the operating room signal source, and then stores the coded video data in a patient information system through a data analysis server module 3. The operation video recording module 4 comprises a communication sub-module and a control sub-module.
Specifically, the communication sub-module is configured to parse information sent by the data analysis server module 3 and send the information to the data analysis server module 3, so as to achieve the purpose of establishing a communication mechanism based on HTTP with the data analysis server module. The control submodule is used for generating a control signal for controlling the video equipment according to the received information so as to control the operating room signal source encoder to perform encoding and screenshot based on H.264 and H.265, and the purpose of establishing a control mechanism of the surgical video equipment is achieved.
It should be noted that the operation video recording module 4 and the operation video recording docking module 5 are two optional modules for realizing the function of image acquisition in the operation process. When the operating room is implemented with the operation video system which is not the platform, the operation video system docking module 5 can be directly deployed. The module receives a video recording and screenshot instruction sent by the user interaction module 1 through the data analysis server module 3, and sends the video recording and screenshot instruction to the operating room video recording system, and the operating room video recording system stores the coded video data into the patient information system module 7 through the operating room video recording system docking module 5 and the data analysis server module 3.
The medical equipment docking module 2 is a module for docking the perioperative artificial intelligence auxiliary platform with the medical equipment in the operating room. The module is used for docking medical equipment in an operating room through physical connection modes such as a network and a serial port according to a docking interface opened by the medical equipment, so that the medical equipment in the operating room is controlled and the data of the medical equipment is acquired in real time.
The patient information system storage module 7 is a data storage module of the perioperative artificial intelligence auxiliary platform. The module creates a data storage list which takes the patient hospitalization number as a main index and takes the patient name, the patient department, the doctor of the main doctor, the operation name and other multidimensional indexes, and the data storage list comprises preoperative diagnosis data, intraoperative process record data and postoperative follow-up data of the patient. The module realizes the function of capacity expansion through an external disk array. The patient information system storage module 7 includes: the system comprises a database submodule, a communication submodule, a database management submodule and a disk array management submodule.
Specifically, the database sub-module is used for storing patient information, such as a patient basic information table, a patient admission record table, a patient operation record table and a patient operation video record table.
The communication sub-module is used for analyzing the information sent by the data analysis server module 3 and sending the information to the data analysis server module 3, so as to achieve the purpose of establishing a communication mechanism based on HTTP with the data analysis server module 3.
The database management submodule is used for managing the patient information in the database submodule and achieving the purpose of establishing a data processing mechanism for managing the database, such as connecting the database, writing data into the database, deleting the data, inquiring the data and modifying the data.
The disk array management submodule is used for managing disk array information in the database submodule and achieving the purpose of establishing a management mechanism of the disk array, such as setting the disk array and managing disk space.
The database submodule comprises a patient basic information table submodule, a patient admission record table submodule, a patient operation record table and a patient operation video record table.
The patient basic information table submodule is used for storing table fields including the hospitalization number of the patient, the identity card of the patient, the name, the sex, the age and the department of the patient. The patient admission record table submodule is used for storing table fields comprising the admission number, the admission department, the admission time and the discharge time of the patient. The patient operation record table is used for storing table fields comprising the hospitalization number of the patient, whether the pre-operation consultation is carried out or not, the consultation result, the operation scheduling time, the actual operation starting time, the actual operation ending time and the operation video record number. The patient operation video recording table is used for storing table fields including a patient hospitalization number, an operation video recording number and an operation video recording storage address.
As shown in fig. 2, in this embodiment, an perioperative artificial intelligence assistance platform system includes the following modules that perform data communication via a network: the system comprises a user interaction module 1, a medical equipment docking module 2, a surgery video system docking module 5, a hospital information system docking module 6, a patient information system storage module 7 and a data analysis server module 3.
A doctor and a patient user log in the perioperative period artificial intelligence auxiliary platform through the user interaction module 1, the user interaction module 1 requests user permission from the medical equipment docking module 2, and different operation entries are displayed for the user according to the permission.
The data analysis server module 3 receives the request of the user interaction module 1 and respectively sends instructions to the medical equipment docking module 2, the operation video recording module 4, the operation video recording system docking module 5 and the hospital information system docking module 6 according to different request types. Sending an instruction to the medical equipment docking module 2 to acquire real-time data of the medical equipment in the operating room; sending a control instruction to the operation video recording module 4 to realize video recording and screenshot of the intra-operation signal source, and storing the video recording and screenshot to the hospital information system docking module 6; sending a control instruction to the operation video system docking module 5 to acquire the diagnosis information of the patient; sending control and data instructions to the hospital information system docking module 6 for storing patient comprehensive information including patient diagnosis information, patient surgical procedure video and screenshot information, patient surgical procedure vital signs, key events, intraoperative medication information and postoperative follow-up information; sends a data request instruction to the hospital information system docking module 6 to retrieve the patient's stored information and returns it to the user interaction module 1. The data analysis server module 3 can perform global data analysis according to all the patient information stored by the module, and provide the doctor user with pre-operation consultation operation success index reference and scientific research materials about typical cases and special cases.
The medical equipment docking module 2 docks medical equipment such as life monitor equipment and surgical anesthesia equipment in an operating room, acquires real-time data of the medical equipment in the surgical process, receives a control instruction of the data analysis server module 3, and returns the acquired real-time data of the medical equipment to the data analysis server module 3.
The operation video recording module 4 is connected with the signal source of the equipment in the operation room, such as an operation field camera and endoscope equipment, and carries out H.264 standard coding on the signal source, and the module receives the control instruction of the data analysis server module 3 and returns the coded data to the data analysis server module 3.
The operation video system docking module 5 docks the hospital information system, acquires the patient diagnosis information from the hospital information system, receives the control instruction of the data analysis server module 3, and returns the patient diagnosis information to the data analysis server module 3.
The hospital information system docking module 6 stores patient information, receives control and data instructions of the data analysis server module 3, stores data acquired by the user interaction module 1, the medical equipment docking module 2, the surgery video recording module 4 and the surgery video recording system docking module 5, retrieves the stored data according to the control instructions, and returns the retrieved data to the user interaction module 1.
As shown in fig. 3, in this embodiment, the method for establishing the operation success index prediction module in the data analysis server module 3 specifically includes the following steps:
1000 cardiac bypass operations in 2009-2018 of a certain hospital are selected, input data sets are sorted according to the age, sex, illness and operation conditions in 3 years, body health indexes and insurance types of patients, the data format requires that each column is a group of input training sets, each row represents a type of input parameters, output data sets are sorted according to the 5-year survival rate of operation (FYSR) and the postoperative self-care index (L CI), the input data sets and the output data sets are grouped, wherein 700 training data sets are used for training, 200 verification data sets are used for verification, and 100 test data sets are used for testing.
Setting initial parameters of the three-layer BP neural network. Wherein the input node is 5, the output node is 2, the hidden layer node is 6, and the target value of the loss function is set to be 10-8。
And training the network model by using the training set data and the verification set data until a loss function target value is reached to obtain a training model.
The training model results are tested using a test data set.
When a new patient needs pre-operation consultation discussion, patient information is input into the system to predict the patient operation success index SSI.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (10)
1. The utility model provides a perioperative period artificial intelligence auxiliary platform system which characterized in that: the system comprises the following modules for data communication through a network:
a user interaction module (1) for providing a user interaction interface;
a medical device docking module (2) for docking a medical device to acquire surgical data;
the operation video recording module (4) is used for butting a video signal source to obtain a corresponding image;
the operation video system docking module (5) is used for docking the operation video system to acquire a corresponding image;
the hospital information system docking module (6) is used for docking corresponding information systems in the hospital;
a patient information system storage module (7) for storing patient information; and
and the data analysis server module (3) is used for communicating with each module and analyzing the received data.
2. The perioperative artificial intelligence assistance platform system according to claim 1, wherein:
the user interaction module (1) comprises:
the user authority management submodule is used for displaying different user interaction interfaces according to different authorities of users;
the preoperative consultation submodule is used for providing consultation service according to a consultation request of a user;
the intraoperative process recording submodule is used for recording relevant information in the surgical process;
the postoperative reply module is used for providing postoperative process review service according to a review request of a user; and
and the postoperative follow-up sub-module is used for recording the discharge condition of the patient.
3. The perioperative artificial intelligence assistance platform system according to claim 1, wherein:
the data analysis server module (3) comprises:
the interactive interface submodule is used for receiving the request sent by the user interactive module (1) and sending the information corresponding to the request;
the information exchange sub-module is used for data interaction between the user interaction module (1) and the patient information system storage module (7) and data interaction between the hospital information system docking module and the patient information system storage module (7);
and the analysis submodule is used for analyzing the received data and giving out an analysis result.
4. The perioperative artificial intelligence assistance platform system according to claim 3, wherein:
the specific process of analyzing the received data and giving an analysis result by the analysis module is as follows:
establishing a data model of the patient information and the operation success index according to the operation data;
training a data model based on the data of the neural network and all patients in the system;
defining an index of success of the surgery;
and predicting the operation success index of the patient according to the input new patient information.
5. The perioperative artificial intelligence assistance platform system according to claim 4, wherein:
the specific process of establishing the data model related to the patient information and the operation success index according to the operation data comprises the following steps:
selecting M operation cases of a certain class in N years in a hospital, and taking patient information as input; outputting the result of the surgery of the patient; dividing M cases into a training data set, a verification data set and a test data set according to the proportion of X, Y and Z; wherein N is more than or equal to 5 and less than or equal to 20, N is more than or equal to 500 and less than or equal to 2000, and X + Y + Z is equal to M; the patient information comprises age, gender, illness and operation conditions in A year, body health index and insurance type, and A is less than or equal to 3; the patient's surgical outcome includes 5-year survival rate after surgery and postoperative self-care index of life;
the specific process of training the data model based on the data of all patients in the neural network and the system is as follows:
taking the patient information as an input layer, setting the number of nodes of the input layer to be 5, taking the operation result of the patient as an output layer, and setting the number of nodes of the output layer to be 2;
determining the number of nodes of the hidden layer by an empirical formula;
determining an input activation function and a damage function, and setting a target value of the loss function;
performing a first round of training using the training set data, calculating a loss function value using the validation data set, and determining to stop learning and continue learning according to whether the loss function value is less than a target value;
the accuracy of the data model is verified using the test data set.
6. The perioperative artificial intelligence assistance platform system according to claim 1, wherein:
the hospital information system docking module (6) comprises:
the communication submodule is used for analyzing the information sent by the data analysis server module (3) and sending the information to the data analysis server module (3);
the docking sub-module is used for docking different hospital information systems to acquire related data;
the analysis submodule is used for analyzing the acquired data;
and the retrieval submodule is used for retrieving the patient information according to the hospitalization number of the patient and sending the patient information to the data analysis server module (3).
7. The perioperative artificial intelligence assistance platform system according to claim 1, wherein:
the surgery video module (4) comprises:
the communication submodule is used for analyzing the information sent by the data analysis server module (3) and sending the information to the data analysis server module (3); and
and the control submodule is used for generating a control signal for controlling the video recording equipment according to the received information so as to acquire a corresponding image.
8. The perioperative artificial intelligence assistance platform system according to claim 1, wherein:
the patient information system storage module (7) comprises:
the database submodule is used for storing the patient information;
the communication submodule is used for analyzing the information sent by the data analysis server module (3) and sending the information to the data analysis server module (3);
the database management submodule is used for managing the patient information in the database submodule; and
and the disk array management submodule is used for managing the disk array information in the database submodule.
9. The perioperative artificial intelligence assistance platform system according to claim 8, wherein:
the database submodule includes:
the patient basic information table submodule is used for storing table fields comprising a patient hospitalization number, a patient identity card, a patient name, a sex, an age and a department;
the patient admission record table submodule is used for storing table fields comprising a patient admission number, an admission department, admission time and discharge time;
the patient operation record table is used for storing table fields including the hospitalization number of the patient, whether the preoperative consultation is performed or not, the consultation result, the operation scheduling time, the actual operation starting time, the actual operation ending time and the operation video record number; and
the patient operation video recording table is used for storing table fields including the hospitalization number of the patient, the operation video recording number and the operation video recording storage address.
10. The perioperative artificial intelligence assistance platform system according to claim 1, wherein:
the user interaction module (1) is a client module or a webpage end module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010285565.4A CN111508618B (en) | 2020-04-13 | 2020-04-13 | Manual intelligent auxiliary platform system for perioperative period |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010285565.4A CN111508618B (en) | 2020-04-13 | 2020-04-13 | Manual intelligent auxiliary platform system for perioperative period |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111508618A true CN111508618A (en) | 2020-08-07 |
| CN111508618B CN111508618B (en) | 2023-09-15 |
Family
ID=71869203
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010285565.4A Active CN111508618B (en) | 2020-04-13 | 2020-04-13 | Manual intelligent auxiliary platform system for perioperative period |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111508618B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113782226A (en) * | 2021-09-16 | 2021-12-10 | 人工智能与数字经济广东省实验室(广州) | Intelligent case follow-up system based on deep learning |
| CN114882984A (en) * | 2022-06-30 | 2022-08-09 | 深圳市人民医院 | Operating room postoperative care information analysis management scheduling integration intelligent platform |
| CN115862896A (en) * | 2023-02-13 | 2023-03-28 | 深圳市汇健智慧医疗有限公司 | Perioperative period-based doctor-patient cooperative management method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150012299A1 (en) * | 2012-09-29 | 2015-01-08 | Navjot Kohli | Surgical Companion Computer Program Product, Method and System |
| CN105868541A (en) * | 2016-03-24 | 2016-08-17 | 苏州麦迪斯顿医疗科技股份有限公司 | A patient multimedia data control method and device |
| CN108198621A (en) * | 2018-01-18 | 2018-06-22 | 中山大学 | A kind of database data synthesis dicision of diagnosis and treatment method based on neural network |
-
2020
- 2020-04-13 CN CN202010285565.4A patent/CN111508618B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150012299A1 (en) * | 2012-09-29 | 2015-01-08 | Navjot Kohli | Surgical Companion Computer Program Product, Method and System |
| CN105868541A (en) * | 2016-03-24 | 2016-08-17 | 苏州麦迪斯顿医疗科技股份有限公司 | A patient multimedia data control method and device |
| CN108198621A (en) * | 2018-01-18 | 2018-06-22 | 中山大学 | A kind of database data synthesis dicision of diagnosis and treatment method based on neural network |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113782226A (en) * | 2021-09-16 | 2021-12-10 | 人工智能与数字经济广东省实验室(广州) | Intelligent case follow-up system based on deep learning |
| CN114882984A (en) * | 2022-06-30 | 2022-08-09 | 深圳市人民医院 | Operating room postoperative care information analysis management scheduling integration intelligent platform |
| CN115862896A (en) * | 2023-02-13 | 2023-03-28 | 深圳市汇健智慧医疗有限公司 | Perioperative period-based doctor-patient cooperative management method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111508618B (en) | 2023-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106570307B (en) | System and method for streaming patient information from a defibrillator | |
| CN111508618B (en) | Manual intelligent auxiliary platform system for perioperative period | |
| CN117238458B (en) | Critical care cross-mechanism collaboration platform system based on cloud computing | |
| US9268827B2 (en) | System and method for collecting data from data sources and using data collection tools | |
| CN106997421B (en) | Intelligent system and method for personalized medical information acquisition and health monitoring | |
| CN110457425B (en) | Case storage method, device, equipment and storage medium | |
| CN102687170A (en) | Systems and methods for collection, organization and display of EMS information | |
| Panda et al. | Big data in health care: A mobile based solution | |
| US20200251196A1 (en) | Systems and methods for sorting findings to medical coders | |
| CN1392995A (en) | Method and system of managing information for hospital | |
| CN111210884B (en) | Clinical medical data acquisition method, device, medium and equipment | |
| CN115101212A (en) | Kidney disease clinical diagnosis service system and method | |
| JP2006301760A (en) | Medical information providing device and medical information providing method | |
| CN102955901A (en) | Medical presentation creator | |
| RU2251965C2 (en) | Data analysis system in the field of telemedicine | |
| US20150006200A1 (en) | System and method for providing automated home-based health services | |
| CN114783557A (en) | Method and device for processing tumor patient data, storage medium and processor | |
| CN113793677A (en) | Electronic medical record management method and device, storage medium and electronic equipment | |
| CN111403023A (en) | Self-service adjuvant therapy chronic obstructive pulmonary disease system | |
| CN110575199A (en) | cloud image portable ultrasonic system and working method | |
| CN112509688B (en) | Automatic analysis system, method, equipment and medium for pressure sore picture | |
| CN114417033A (en) | Image data processing system, method, electronic terminal and storage medium | |
| WO2004025948A1 (en) | Information management method, information management system, and information transfer device included in the system | |
| WO2020153069A1 (en) | System for generating prognosis prediction information concerning blood disease, information processing device, server, program, or method | |
| CN116580827A (en) | Medical treatment full course management system |
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 |