CN112967813A - Surgical incision infection monitoring model training method and surgical incision infection monitoring method - Google Patents

Surgical incision infection monitoring model training method and surgical incision infection monitoring method Download PDF

Info

Publication number
CN112967813A
CN112967813A CN202110467953.9A CN202110467953A CN112967813A CN 112967813 A CN112967813 A CN 112967813A CN 202110467953 A CN202110467953 A CN 202110467953A CN 112967813 A CN112967813 A CN 112967813A
Authority
CN
China
Prior art keywords
surgical incision
surgical
incision infection
data
weight
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110467953.9A
Other languages
Chinese (zh)
Inventor
欧高文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
QINGYUAN PEOPLE'S HOSPITAL
Original Assignee
QINGYUAN PEOPLE'S HOSPITAL
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by QINGYUAN PEOPLE'S HOSPITAL filed Critical QINGYUAN PEOPLE'S HOSPITAL
Priority to CN202110467953.9A priority Critical patent/CN112967813A/en
Publication of CN112967813A publication Critical patent/CN112967813A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • Pathology (AREA)
  • Databases & Information Systems (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Surgical Instruments (AREA)

Abstract

The invention relates to a surgical incision infection monitoring model training method and a surgical incision infection monitoring method. And finally, correcting neurons in all layers until the neural network converges to obtain a surgical incision infection monitoring model. Based on the method, the trained surgical incision infection monitoring model can be used for monitoring the surgical incision infection condition, predicting the probability of surgical incision infection of a surgical patient, exploring measures for preventing and controlling surgical incision infection, and providing a basis for effectively controlling surgical incision infection.

Description

Surgical incision infection monitoring model training method and surgical incision infection monitoring method
Technical Field
The invention relates to the technical field of information medical treatment, in particular to a training method of a surgical incision infection monitoring model and a surgical incision infection monitoring method.
Background
The surgical operation is an injury to human tissues, not only destroys the function of a local barrier, but also has a serious impact on the body once, reduces the resistance of the body and creates conditions for infection caused by invasion of pathogenic microorganisms into the human body. Therefore, surgical site infection monitoring is an important item in targeted monitoring of nosocomial infections.
The traditional monitoring of surgical incision infection is mainly based on the national hospital infection monitoring system (NNIS) established by the American disease monitoring agency in 1970, and the surgical incision infection is evaluated and monitored by classifying the surgery into four grades, namely NNIS0 grade, NNIS1 grade, NNIS2 grade and NNIS3 grade, according to three key variables of surgical incision cleanliness, anesthesia grade and surgical duration. However, due to the variability in population characteristics among patients in various regions and the development of surgical medical science and technology, the risk factors for the occurrence of surgical incision infections have changed greatly. The traditional operation incision infection monitoring mode has too simple evaluation variables, is difficult to meet the infection monitoring requirements of various operation incisions, and cannot comprehensively evaluate the infection conditions of the operation incisions.
Therefore, the traditional method for monitoring the infection of the surgical incision has the defects.
Disclosure of Invention
Therefore, it is necessary to provide a surgical incision infection monitoring model training method and a surgical incision infection monitoring method for overcoming the defects of the conventional surgical incision infection monitoring method.
A training method for a surgical incision infection monitoring model comprises the following steps:
acquiring operation history data of an operation patient;
converting the operation historical data into an initial weight;
substituting the initial weight into a neural network to perform calculation to obtain the weight of each layer of neurons;
and (5) correcting neurons in all layers until the neural network converges, and obtaining a surgical incision infection monitoring model.
According to the surgical incision infection monitoring model training method, after surgical history data of a surgical patient are obtained, the surgical history data are converted into initial weights, the initial weights are substituted into a neural network to perform calculation, and weights of neurons in all layers are obtained. And finally, correcting neurons in all layers until the neural network converges to obtain a surgical incision infection monitoring model. Based on the method, the trained surgical incision infection monitoring model can be used for monitoring the surgical incision infection condition, predicting the probability of surgical incision infection of a surgical patient, exploring measures for preventing and controlling surgical incision infection, and providing a basis for effectively controlling surgical incision infection.
In one embodiment, the surgical history data includes current medical history data, nutritional status data, antibiotic usage data, skin condition data, time of surgery data, incision cleanliness data, anesthesia grading data, or post-surgical dressing change data.
In one embodiment, the process of converting the surgical history data into an initial weight includes the steps of:
determining a grade weight corresponding to the operation historical data of each grade according to the grade of the operation historical data;
and determining an initial weight according to the weights of all levels.
In one embodiment, the neural network comprises a BP neural network.
In one embodiment, the excitation function of each node of the neural network is a sigmoid function.
In one embodiment, the process of substituting the initial weights into the neural network to perform calculation to obtain weights of neurons in each layer includes the steps of:
substituting the initial weight into a neural network to execute forward process calculation and reverse process calculation to obtain a calculation value of each layer of the neural network;
and determining the weight of the neuron according to the calculated value.
A surgical incision infection monitoring model training device, comprising:
the data acquisition module is used for acquiring operation history data of an operation patient;
the weight conversion module is used for converting the operation historical data into an initial weight;
the weight calculation module is used for substituting the initial weight into the neural network to execute calculation to obtain the weight of each layer of neurons;
and the model acquisition module is used for correcting neurons in all layers until the neural network converges to obtain the surgical incision infection monitoring model.
After the surgical incision infection monitoring model training device obtains surgical history data of a surgical patient, the surgical history data are converted into initial weights, the initial weights are substituted into a neural network to execute calculation, and weights of neurons in all layers are obtained. And finally, correcting neurons in all layers until the neural network converges to obtain a surgical incision infection monitoring model. Based on the method, the trained surgical incision infection monitoring model can be used for monitoring the surgical incision infection condition, predicting the probability of surgical incision infection of a surgical patient, exploring measures for preventing and controlling surgical incision infection, and providing a basis for effectively controlling surgical incision infection.
A computer storage medium having computer instructions stored thereon, the computer instructions when executed by a processor implement the surgical incision infection monitoring model training method of any of the above embodiments.
After the operation history data of the operation patient is obtained, the operation history data is converted into initial weights, and the initial weights are substituted into the neural network to execute calculation, so that the weights of all layers of neurons are obtained. And finally, correcting neurons in all layers until the neural network converges to obtain a surgical incision infection monitoring model. Based on the method, the trained surgical incision infection monitoring model can be used for monitoring the surgical incision infection condition, predicting the probability of surgical incision infection of a surgical patient, exploring measures for preventing and controlling surgical incision infection, and providing a basis for effectively controlling surgical incision infection.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the surgical incision infection monitoring model training method of any of the above embodiments when executing the program.
After the computer equipment obtains the operation history data of the operation patient, the operation history data is converted into initial weights, and the initial weights are substituted into the neural network to execute calculation, so that weights of neurons in each layer are obtained. And finally, correcting neurons in all layers until the neural network converges to obtain a surgical incision infection monitoring model. Based on the method, the trained surgical incision infection monitoring model can be used for monitoring the surgical incision infection condition, predicting the probability of surgical incision infection of a surgical patient, exploring measures for preventing and controlling surgical incision infection, and providing a basis for effectively controlling surgical incision infection.
A method of monitoring surgical incision infection comprising the steps of:
acquiring surgical data of a surgical patient;
converting the operation data into a monitoring weight;
and substituting the monitoring weight into the surgical incision infection monitoring model to obtain a surgical incision infection risk index for representing the surgical incision infection condition.
According to the method for monitoring the surgical incision infection, after the surgical data of the surgical patient are obtained, the surgical data are converted into the monitoring weight, and finally the monitoring weight is substituted into the surgical incision infection monitoring model to obtain the surgical incision infection risk index for representing the surgical incision infection condition. Based on the method, the surgical incision infection risk index is obtained through the surgical incision infection monitoring model, the probability of surgical incision infection of a surgical patient is predicted, measures for preventing and controlling surgical incision infection are explored, and a basis is provided for effectively controlling surgical incision infection.
A surgical incision infection monitoring device comprising:
the data acquisition module is used for acquiring surgical data of a surgical patient;
the weight calculation module is used for converting the operation data into a monitoring weight by the weight;
and the index calculation module is used for substituting the monitoring weight into the surgical incision infection monitoring model to obtain a surgical incision infection risk index for representing the surgical incision infection condition.
According to the surgical incision infection monitoring device, after surgical data of a surgical patient are obtained, the surgical data are converted into monitoring weights, and finally the monitoring weights are substituted into a surgical incision infection monitoring model to obtain a surgical incision infection risk index for representing the surgical incision infection condition. Based on the method, the surgical incision infection risk index is obtained through the surgical incision infection monitoring model, the probability of surgical incision infection of a surgical patient is predicted, measures for preventing and controlling surgical incision infection are explored, and a basis is provided for effectively controlling surgical incision infection.
A computer storage medium having computer instructions stored thereon which, when executed by a processor, implement the surgical incision infection monitoring method of any of the above embodiments.
After the operation data of the operation patient are obtained, the operation data are converted into the monitoring weight, and finally the monitoring weight is substituted into the operation incision infection monitoring model to obtain the operation incision infection risk index for representing the operation incision infection condition. Based on the method, the surgical incision infection risk index is obtained through the surgical incision infection monitoring model, the probability of surgical incision infection of a surgical patient is predicted, measures for preventing and controlling surgical incision infection are explored, and a basis is provided for effectively controlling surgical incision infection.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor when executing the program implementing the method of monitoring infection in a surgical incision according to any of the embodiments described above.
After the computer equipment obtains the operation data of the operation patient, the operation data is converted into a monitoring weight, and finally the monitoring weight is substituted into the operation incision infection monitoring model to obtain an operation incision infection risk index for representing the operation incision infection condition. Based on the method, the surgical incision infection risk index is obtained through the surgical incision infection monitoring model, the probability of surgical incision infection of a surgical patient is predicted, measures for preventing and controlling surgical incision infection are explored, and a basis is provided for effectively controlling surgical incision infection.
Drawings
FIG. 1 is a flow chart of a surgical incision infection monitoring model training method according to an embodiment;
FIG. 2 is a flow chart of another embodiment of a surgical incision infection monitoring model training method;
FIG. 3 is a block diagram of an embodiment of a surgical incision infection monitoring model training apparatus;
FIG. 4 is a schematic diagram of the internal structure of a computer according to an embodiment;
FIG. 5 is a flow chart of a method for monitoring infection in a surgical incision, according to one embodiment;
FIG. 6 is a block diagram of an embodiment of a surgical incision infection monitoring device;
fig. 7 is a schematic diagram of the internal structure of a computer according to another embodiment.
Detailed Description
For better understanding of the objects, technical solutions and effects of the present invention, the present invention will be further explained with reference to the accompanying drawings and examples. Meanwhile, the following described examples are only for explaining the present invention, and are not intended to limit the present invention.
The embodiment of the invention provides a training method of a surgical incision infection monitoring model.
Fig. 1 is a flowchart illustrating a training method of a surgical incision infection monitoring model according to an embodiment, and as shown in fig. 1, the training method of the surgical incision infection monitoring model according to an embodiment includes steps S100 to S103:
s100, acquiring operation history data of an operation patient;
the operation history data of the operation patients comprises characterization data of operation conditions, medication conditions, physical conditions or nursing conditions and the like of the operation patients after the preoperative operation.
In one embodiment, the surgical history data includes current medical history data, nutritional status data, antibiotic usage data, skin condition data, time of surgery data, incision cleanliness data, anesthesia grading data, or post-surgical dressing change data.
S101, converting operation historical data into an initial weight;
the operation history data can be converted into weight data, namely an initial weight, according to the preset corresponding relation. Wherein, the same operation historical data can be divided into different grades, different degrees or different types according to the difference of operation patients. And determining the corresponding relation between the operation historical data and the weight data according to the difference of the operation historical data.
In one embodiment, fig. 2 is a flowchart of a surgical incision infection monitoring model training method according to another embodiment, and as shown in fig. 2, a process of converting surgical history data into initial weight values in step S101 includes steps S200 and S201:
s200, determining a level weight corresponding to the operation historical data of each level according to the grading of the operation historical data;
s201, determining an initial weight according to each level of weight.
To better explain step S200 and step S201, the following is explained as a specific application example, as shown in the following table:
Figure BDA0003044042910000071
Figure BDA0003044042910000081
as shown in the above table, the items corresponding to the operation history data include, but are not limited to, table lists, and the grades of the items corresponding to the operation history data can be converted into corresponding grade weights.
In step S201, an initial weight is determined according to the level weights, including using an average value of the level weights corresponding to each item as the initial weight, or using a sum of the level weights as the initial weight.
S102, substituting the initial weight into a neural network to execute calculation to obtain the weight of each layer of neurons;
the neural network is an artificial neural network, and comprises a plurality of nodes (neurons) which are connected with each other. In one embodiment, the artificial neural network is a BP neural network. As a preferred embodiment, the excitation function of each node of the neural network is an S-shaped function. The sigmoid function is given by:
Figure BDA0003044042910000082
in one embodiment, as shown in fig. 2, the process of substituting the initial weights into the neural network in step S102 to perform calculation to obtain neuron weights of each layer includes step S202 and step S203:
s202, substituting the initial weight into a neural network to execute forward process calculation and reverse process calculation to obtain calculated values of each layer of the neural network;
and S203, determining the weight of the neuron according to the calculated value.
Wherein after determining the initial weights, k is1, 2, N for each layer of neurons based on the determined BP neural network. Calculating the calculated values of neurons in each layer Oik、netjkAnd
Figure BDA0003044042910000091
to complete the forward process calculation.
The inverse process calculation from M to 2 for each layer of neurons is as follows:
for the same node j ∈ M, the formula
Figure BDA0003044042910000092
And formula
Figure BDA0003044042910000093
Calculating the error deltajk。
S103, correcting neurons in all layers until the neural network converges, and obtaining a surgical incision infection monitoring model.
And correcting the weight of each layer of neuron according to the error correction until the neural network converges. In one embodiment, the compound is represented by the formula
Figure BDA0003044042910000094
Mu is greater than 0, wherein,
Figure BDA0003044042910000095
and correcting the weight of each layer of neuron.
The operation incision infection monitoring model obtained by convergence can complete calculation according to the input corresponding weight, and the operation incision infection risk index is output as a probability index to represent the operation incision infection condition.
In the method for training the surgical incision infection monitoring model according to any embodiment, after the surgical history data of the surgical patient is obtained, the surgical history data is converted into the initial weight, and the initial weight is substituted into the neural network to perform calculation, so that the weights of neurons in each layer are obtained. And finally, correcting neurons in all layers until the neural network converges to obtain a surgical incision infection monitoring model. Based on the method, the trained surgical incision infection monitoring model can be used for monitoring the surgical incision infection condition, predicting the probability of surgical incision infection of a surgical patient, exploring measures for preventing and controlling surgical incision infection, and providing a basis for effectively controlling surgical incision infection.
The embodiment of the invention also provides a training device for the surgical incision infection monitoring model.
Fig. 3 is a block diagram of a training device for an infection monitoring model of a surgical incision, which includes a module 100, a module 101, a module 102, and a module 103:
a data acquisition module 100 for acquiring surgical history data of a surgical patient;
a weight value conversion module 101, configured to convert the operation history data into an initial weight value;
a weight calculation module 102, configured to substitute the initial weight into a neural network to perform calculation, so as to obtain weights of neurons in each layer;
and the model acquisition module 103 is used for correcting neurons in all layers until the neural network converges to obtain a surgical incision infection monitoring model.
After the surgical incision infection monitoring model training device obtains surgical history data of a surgical patient, the surgical history data are converted into initial weights, the initial weights are substituted into a neural network to execute calculation, and weights of neurons in all layers are obtained. And finally, correcting neurons in all layers until the neural network converges to obtain a surgical incision infection monitoring model. Based on the method, the trained surgical incision infection monitoring model can be used for monitoring the surgical incision infection condition, predicting the probability of surgical incision infection of a surgical patient, exploring measures for preventing and controlling surgical incision infection, and providing a basis for effectively controlling surgical incision infection.
The embodiment of the invention also provides a computer storage medium, on which computer instructions are stored, and the instructions are executed by a processor to implement the surgical incision infection monitoring model training method of any one of the above embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, the computer program can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a terminal, or a network device) to execute all or part of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a RAM, a ROM, a magnetic or optical disk, or various other media that can store program code.
Corresponding to the computer storage medium, in one embodiment, there is also provided a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for training the surgical incision infection monitoring model in any one of the embodiments.
The computer device may be a terminal, and its internal structure diagram may be as shown in fig. 4. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a surgical incision infection monitoring model training method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
After the operation history data of the operation patient is obtained, the computer equipment converts the operation history data into initial weights, substitutes the initial weights into a neural network to execute calculation, and obtains weights of neurons in each layer. And finally, correcting neurons in all layers until the neural network converges to obtain a surgical incision infection monitoring model. Based on the method, the trained surgical incision infection monitoring model can be used for monitoring the surgical incision infection condition, predicting the probability of surgical incision infection of a surgical patient, exploring measures for preventing and controlling surgical incision infection, and providing a basis for effectively controlling surgical incision infection.
The embodiment of the invention also provides a method for monitoring the infection of the surgical incision.
Fig. 5 is a flowchart illustrating a surgical incision infection monitoring method according to an embodiment, and as shown in fig. 5, the surgical incision infection monitoring method according to an embodiment includes steps S300 and S302:
s300, acquiring surgical data of a surgical patient;
s301, converting the operation data into a monitoring weight;
the manner of converting the operation data into the monitoring weight is the same as the manner of converting the operation historical data into the initial weight.
And S302, substituting the monitoring weight into the surgical incision infection monitoring model to obtain a surgical incision infection risk index for representing the surgical incision infection condition.
Wherein, the infection risk index of the surgical incision can be used for representing the infection probability or the infection degree of the surgical incision. And outputting the surgical incision infection risk index in a probability data form or a weight data form according to the adjustment of the surgical incision infection monitoring model.
According to the method for monitoring the surgical incision infection, after the surgical data of the surgical patient are obtained, the surgical data are converted into the monitoring weight, and finally the monitoring weight is substituted into the surgical incision infection monitoring model to obtain the surgical incision infection risk index for representing the surgical incision infection condition. Based on the method, the surgical incision infection risk index is obtained through the surgical incision infection monitoring model, the probability of surgical incision infection of a surgical patient is predicted, measures for preventing and controlling surgical incision infection are explored, and a basis is provided for effectively controlling surgical incision infection.
The embodiment of the invention also provides a device for monitoring the infection of the surgical incision.
FIG. 6 is a block diagram of an embodiment of a surgical incision infection monitoring device, including a module 200, a module 201, and a module 202:
a data acquisition module 200 for acquiring surgical data of a surgical patient;
a weight calculation module 201, configured to convert the surgical data into a monitoring weight;
and the index calculation module 202 is used for substituting the monitoring weight into the surgical incision infection monitoring model to obtain a surgical incision infection risk index for representing the surgical incision infection condition.
According to the surgical incision infection monitoring device, after surgical data of a surgical patient are obtained, the surgical data are converted into monitoring weights, and finally the monitoring weights are substituted into a surgical incision infection monitoring model to obtain a surgical incision infection risk index for representing the surgical incision infection condition. Based on the method, the surgical incision infection risk index is obtained through the surgical incision infection monitoring model, the probability of surgical incision infection of a surgical patient is predicted, measures for preventing and controlling surgical incision infection are explored, and a basis is provided for effectively controlling surgical incision infection.
Embodiments of the present invention further provide a computer storage medium having computer instructions stored thereon, where the computer instructions, when executed by a processor, implement the method for monitoring infection in a surgical incision according to any of the above embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, the computer program can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a terminal, or a network device) to execute all or part of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a RAM, a ROM, a magnetic or optical disk, or various other media that can store program code.
Corresponding to the computer storage medium, in one embodiment, there is also provided a computer device including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement any one of the above-described surgical incision infection monitoring methods.
The computer device may be a terminal, and its internal structure diagram may be as shown in fig. 7. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a surgical incision infection monitoring method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
After the operation data of the operation patient are obtained, the operation data are converted into the monitoring weight, and finally the monitoring weight is substituted into the operation incision infection monitoring model to obtain the operation incision infection risk index for representing the operation incision infection condition. Based on the method, the surgical incision infection risk index is obtained through the surgical incision infection monitoring model, the probability of surgical incision infection of a surgical patient is predicted, measures for preventing and controlling surgical incision infection are explored, and a basis is provided for effectively controlling surgical incision infection.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only show some embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (10)

1. A training method for an infection monitoring model of a surgical incision is characterized by comprising the following steps:
acquiring operation history data of an operation patient;
converting the operation historical data into an initial weight;
substituting the initial weight into a neural network to perform calculation to obtain the weight of each layer of neurons;
and correcting neurons in all layers until the neural network converges to obtain a surgical incision infection monitoring model.
2. The surgical incision infection monitoring model training method of claim 1, wherein the surgical history data comprises current medical history data, nutritional status data, antibiotic usage data, skin condition data, surgical time data, incision cleanliness data, anesthesia grading data, or post-surgical dressing change condition data.
3. The method for training the surgical incision infection monitoring model according to claim 1 or 2, wherein the process of converting the surgical history data into the initial weight comprises the steps of:
determining a grade weight corresponding to the operation historical data of each grade according to the grade of the operation historical data;
and determining the initial weight according to each level weight.
4. The surgical incision infection monitoring model training method of claim 1, wherein the neural network comprises a BP neural network.
5. The method for training the surgical incision infection monitoring model according to claim 4, wherein the excitation function of each node of the neural network is an S-shaped function.
6. The method for training the surgical incision infection monitoring model according to claim 4, wherein the process of substituting the initial weights into the neural network to perform calculation to obtain weights of neurons in each layer comprises the steps of:
substituting the initial weight into a neural network to execute forward process calculation and reverse process calculation to obtain calculated values of each layer of the neural network;
and determining the neuron weight according to the calculated value.
7. A surgical incision infection monitoring model training device, comprising:
the data acquisition module is used for acquiring operation history data of an operation patient;
the weight conversion module is used for converting the operation historical data into an initial weight;
the weight calculation module is used for substituting the initial weight into a neural network to execute calculation to obtain the weight of each layer of neurons;
and the model acquisition module is used for correcting neurons in all layers until the neural network converges to obtain a surgical incision infection monitoring model.
8. A computer storage medium having computer instructions stored thereon, wherein the computer instructions, when executed by a processor, implement a surgical incision infection monitoring model training method according to any one of claims 1 to 6.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements a surgical incision infection monitoring model training method according to any one of claims 1 to 6.
10. A method of monitoring infection in a surgical incision, comprising the steps of:
acquiring surgical data of a surgical patient;
converting the operation data into a monitoring weight;
and substituting the monitoring weight into the surgical incision infection monitoring model to obtain a surgical incision infection risk index for representing the surgical incision infection condition.
CN202110467953.9A 2021-04-28 2021-04-28 Surgical incision infection monitoring model training method and surgical incision infection monitoring method Pending CN112967813A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110467953.9A CN112967813A (en) 2021-04-28 2021-04-28 Surgical incision infection monitoring model training method and surgical incision infection monitoring method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110467953.9A CN112967813A (en) 2021-04-28 2021-04-28 Surgical incision infection monitoring model training method and surgical incision infection monitoring method

Publications (1)

Publication Number Publication Date
CN112967813A true CN112967813A (en) 2021-06-15

Family

ID=76281314

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110467953.9A Pending CN112967813A (en) 2021-04-28 2021-04-28 Surgical incision infection monitoring model training method and surgical incision infection monitoring method

Country Status (1)

Country Link
CN (1) CN112967813A (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190188587A1 (en) * 2017-12-20 2019-06-20 Sandeep Gupta Model guided deep learning approach towards prediction of physical system behavior
CN111899837A (en) * 2020-08-17 2020-11-06 江苏达实久信数字医疗科技有限公司 Operation report coordination method and system based on digital operating room

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190188587A1 (en) * 2017-12-20 2019-06-20 Sandeep Gupta Model guided deep learning approach towards prediction of physical system behavior
CN111899837A (en) * 2020-08-17 2020-11-06 江苏达实久信数字医疗科技有限公司 Operation report coordination method and system based on digital operating room

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
冯月静: "某综合三甲医院老年手术患者医院感染风险预测研究", 《中国优秀博硕士学位论文全文数据库(硕士)医药卫生科技辑》 *
欧高文: "手术切口感染风险评估工具的构建及其临床应用研究", 《中国优秀硕士学位论文全文数据库 医药卫生科技辑》 *

Similar Documents

Publication Publication Date Title
Sanz et al. Medical diagnosis of cardiovascular diseases using an interval-valued fuzzy rule-based classification system
Betechuoh et al. Autoencoder networks for HIV classification
CN110033866B (en) Health reminding method, device, computer equipment and storage medium
CA2671501A1 (en) Automatic priorization of instances of medical care
CN112773356B (en) Sitting posture detection method, system, terminal and storage medium
CN113362952A (en) Model-based risk prediction method and device, computer equipment and storage medium
CN114512235A (en) Fracture and wound information processing method and system
US20110137670A1 (en) Methods, apparatuses, and computer program products for facilitating development and execution of a clinical care plan
CN112967813A (en) Surgical incision infection monitoring model training method and surgical incision infection monitoring method
Wang et al. An optimal learning method for developing personalized treatment regimes
JP5291625B2 (en) Method and apparatus for deriving a probabilistic model from a deterministic model
Chai et al. A profile similarity-based personalized federated learning method for wearable sensor-based human activity recognition
Fricker Jr et al. Optimizing biosurveillance systems that use threshold-based event detection methods
WO2017037581A1 (en) Automated controlled-case studies and root-cause analysis for hospital quality improvement
CN113066531B (en) Risk prediction method, risk prediction device, computer equipment and storage medium
CN113053482B (en) Physical sign monitoring and analyzing system and method for nephrology department patient
JP7409384B2 (en) Information processing method
Batyuk et al. Algorithm for making decisions based on fuzzy network models in problems of medical diagnostics and forecasting
JP7406881B2 (en) Information processing device, information processing method and program
CN117809811B (en) Artificial intelligence-based weight-reduction operation postoperative management method and system
US12020789B1 (en) Systems and methods enabling baseline prediction correction
CN117558408A (en) Ablation simulation method based on data fitting
JP7367767B2 (en) Information processing method
US20230293023A1 (en) Prenatal monitoring system
Ganz et al. Procedure to improve the accuracy of dental implant failures by data science techniques

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20210615