CN113823372A - Data collection and processing system for liver cancer recurrence prediction - Google Patents
Data collection and processing system for liver cancer recurrence prediction Download PDFInfo
- Publication number
- CN113823372A CN113823372A CN202111150834.7A CN202111150834A CN113823372A CN 113823372 A CN113823372 A CN 113823372A CN 202111150834 A CN202111150834 A CN 202111150834A CN 113823372 A CN113823372 A CN 113823372A
- Authority
- CN
- China
- Prior art keywords
- data
- standard
- patient
- parameter
- preprocessing
- 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.)
- Withdrawn
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
- 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
- G16H50/50—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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention is suitable for the technical field of medical data processing, provides a data collecting and processing system for liver cancer recurrence prediction, is used for processing liver cancer recurrence data, and solves the problems that the existing recurrence prediction method is mainly judged by the experience of doctors, has larger error and inconsistent prediction results of different doctors; the method comprises the following steps: the parameter acquisition module is used for acquiring pathological data of the liver cancer patient, integrating physical examination data of the patient, extracting the pathological data and the physical examination data of the liver cancer patient and preprocessing the data to obtain preprocessing parameters; a standard parameter presetting module; a parameter analysis comparison module; the invention comprises a parameter acquisition module, a standard parameter presetting module and a parameter analysis comparison module, wherein the recurrence prediction model is obtained by the parameter acquisition module, the standard parameter presetting module and the parameter analysis comparison module, so that the patient and a doctor are assisted to predict the postoperative recurrence probability of the patient, and a periodic recurrence probability report is given.
Description
Technical Field
The invention belongs to the technical field of medical data processing, and particularly relates to a data collection and processing system for liver cancer recurrence prediction.
Background
Hepatocellular carcinoma (HCC) is the most common primary liver cancer and the second leading cause of cancer-related death worldwide. At present, diagnosis and operation technologies of liver cancer are gradually mature, but a large number of liver cancer patients frequently relapse after an operation and further progress to late-stage liver cancer, which finally causes poor overall prognosis of liver cancer, and as is known, liver cancer relapse is divided into early-stage relapse and late-stage relapse by taking 2 years after the operation as a boundary, wherein the early-stage relapse is considered as 'real relapse' and accounts for more than 70% of the liver cancer relapse, and is a main reason for low postoperative survival rate of the liver cancer patients.
However, after a primary liver cancer patient passes treatment, many patients often relapse, and prognosis and survival period of the patients are seriously affected, so that the body of the patient needs to be checked regularly, the body state of the patient can be grasped in time, and timely diagnosis is facilitated during relapse.
Disclosure of Invention
The invention provides a data collection and processing system for liver cancer recurrence prediction, and aims to solve the problems that the existing recurrence prediction method is mainly judged by the experience of doctors, the error is large, and the prediction results of different doctors are inconsistent.
The present invention is achieved in this way, and a data collection and processing system for liver cancer recurrence prediction, which is used for processing liver cancer recurrence data, the data collection and processing system for liver cancer recurrence prediction includes:
the parameter acquisition module is used for acquiring pathological data of the liver cancer patient, integrating physical examination data of the patient, extracting the pathological data and the physical examination data of the liver cancer patient and preprocessing the data to obtain preprocessing parameters;
the standard parameter presetting module is used for acquiring standard sample data, constructing a standard presetting model based on the standard sample data, testing the standard presetting model and adjusting the standard presetting model;
and the parameter analysis and comparison module extracts the preprocessing parameters, runs the extracted preprocessing parameters based on the standard preset model to obtain a response result, traverses the cloud early warning library to evaluate the postoperative recurrence risk of the patient, and feeds the risk value back to the parameter acquisition module.
Preferably, the parameter obtaining module includes:
the pathological data acquisition unit is used for acquiring pathological data of a liver cancer patient, sorting the pathological data and classifying and screening the pathological data based on different time periods of the patient;
the physical examination data integration unit is used for integrating the physical examination data of the patient and filtering irrelevant data, wherein the irrelevant data comprises abnormal data and irrelevant data, and feature selection is carried out on the basis of Pearson product moment correlation coefficients to obtain data with high relevance for influencing postoperative recurrence in the physical examination data;
and the data information extraction unit is used for extracting pathological information and physical examination data of the liver cancer patient and preprocessing the data to obtain preprocessing parameters.
Preferably, the integrated patient health data is obtained by at least one sensing unit, the sensing unit comprising:
the abdominal magnetic resonance image sensor is used for acquiring liver magnetic resonance images of a patient in multiple time periods and multiple angles;
the in-vivo organ image sensor is used for acquiring external textures of the liver, images of liver wounds, the number of tumors in the body, the maximum tumor size and the tumor position data of the patient;
the conventional index sensor is used for collecting sex, age, lymphatic metastasis history, recurrence frequency, recurrence history, lymphocyte ratio and neutrophil ratio of a patient.
Preferably, the method for extracting pathological data and physical examination data of a liver cancer patient and preprocessing the data specifically comprises the following steps:
extracting data with high recurrence correlation degree, and performing feature comparison on the data with high recurrence correlation degree based on Pearson product moment correlation coefficient;
extracting data with high recurrence correlation degree by the risk margin layer, and performing computational analysis on the data with high recurrence correlation degree to obtain the responsiveness of the data with high recurrence correlation degree;
extracting the responsivity, and determining the response difference between the responsivity of the data with high correlation and a preset responsivity;
and screening out data materials with large response difference, storing the data materials with small response difference to obtain a preprocessed data set, and packaging and sending the preprocessed data set to a standard parameter presetting module.
Preferably, the standard parameter presetting module comprises:
the standard sample acquisition unit is used for acquiring standard sample data and test sample data;
the standard preset model building unit is used for building a standard preset model, wherein the standard preset model is built based on standard sample data;
the standard preset model testing unit is used for testing the standard preset model and comparing the optimal prediction result of the standard preset model with the lesion detection result of the sample;
and the preset model adjusting unit is used for adjusting the standard preset model to obtain an optimal response result.
Preferably, the method for constructing the standard preset model specifically includes:
obtaining standard sample data, wherein the standard sample data comprises pathological data of postoperative patients with recurrent liver cancer and physical examination data of integrated patients;
extracting postoperative recurrent patient data, inputting the postoperative recurrent patient data into a basic standard preset network, comparing the postoperative recurrent patient data with a network parameter response value preset by the basic standard preset network, and extracting the significance of the postoperative recurrent patient data based on the network parameter response value;
judging whether the significance of the data of the postoperative recurrent patients is greater than a preset potential recurrent significance threshold value or not;
when the significance of the data of the recurrent patients is judged to be smaller than a preset potential recurrent significance threshold value, reducing the significance threshold value according to a preset significance threshold value reduction rule; or
And when the significance of the data of the recurrent patients is judged to be not less than the preset potential recurrent significance threshold value, expanding the significance threshold value according to a preset significance threshold value reduction rule.
Preferably, the adjusting the standard preset model to obtain the optimal response result includes:
obtaining test sample data;
extracting postoperative recurrent patient data, inputting the postoperative recurrent patient data into a standard preset model, comparing the postoperative recurrent patient data with a network parameter response value preset by a base standard preset model, extracting the significance of the postoperative recurrent patient data based on the network parameter response value, and judging whether the significance of the recurrent patient data is smaller than a preset potential recurrent significance threshold value or not;
when the significance of the data of the recurrent patients is judged to be smaller than a preset potential recurrent significance threshold value, reducing the significance threshold value according to a preset significance threshold value reduction rule; or
When the significance of the data of the recurrent patients is judged to be smaller than a preset potential recurrent significance threshold value, expanding the significance threshold value according to a preset significance threshold value reduction rule;
and obtaining an optimal response result based on the adjustment of the reduced significance threshold or the expanded significance threshold.
Preferably, the parameter analysis comparison module comprises:
a preprocessing parameter extraction unit for extracting preprocessing parameters;
the preprocessing parameter operation unit is used for operating the extracted preprocessing parameters based on the standard preset model to obtain a response result;
and the cloud early warning library traversal unit is used for traversing the response result, evaluating the risk of postoperative recurrence of the patient and feeding the risk value back to the parameter acquisition module.
Preferably, the specific implementation step of obtaining the response result based on the extracted preprocessing parameter run by the standard preset model includes:
sequentially preprocessing a preprocessing parameter set between an initial time and an end time point in the preprocessing parameters, and acquiring a readable preprocessing parameter identification code when judging that a traversable preprocessing parameter exists in the preprocessing parameter set;
running a preprocessing parameter identification code based on the standard preset model to obtain a response result;
traversing the response result, calling a set threshold of the cloud early warning library, comparing the response result with the set threshold, judging a response risk value, and feeding the risk value back to the parameter acquisition module.
Preferably, the parameter analysis and comparison module further comprises an inverse operation assisting unit, the inverse operation assisting unit comprising:
the read operation module is used for writing, reading or deleting the preprocessing parameters, wherein the writing, reading or deleting operation of the preprocessing parameters is used for writing, reading or deleting the unique preprocessing parameter identification codes recorded in the preprocessing parameter set;
and the analysis display module is used for displaying the risk value fed back by the cloud early warning library traversal unit and displaying the analysis report.
Compared with the prior art, the embodiment of the application mainly has the following beneficial effects:
the invention provides a data collection and processing system for liver cancer recurrence prediction, which comprises a parameter acquisition module, a standard parameter presetting module and a parameter analysis and comparison module, wherein a recurrence prediction model is obtained by executing the parameter acquisition module, the standard parameter presetting module and the parameter analysis and comparison module, so that a patient and a doctor are assisted in predicting postoperative recurrence probability of the patient, and a periodic recurrence probability report is given.
Drawings
FIG. 1 is a schematic diagram of a data collection and processing system for liver cancer recurrence prediction according to the present invention.
Fig. 2 is a schematic structural diagram of a parameter obtaining module provided in the present invention.
Fig. 3 is a schematic structural diagram of a sensing unit provided by the present invention.
FIG. 4 is a flowchart of the method for extracting pathological data and physical examination data of a liver cancer patient and preprocessing the data according to the present invention.
Fig. 5 is a schematic structural diagram of a standard parameter presetting module provided by the present invention.
FIG. 6 is a flowchart illustrating a method for constructing a standard default model according to the present invention.
Fig. 7 is a schematic structural diagram of a parameter analysis comparison module provided by the present invention.
Fig. 8 is a flowchart of a specific implementation of obtaining a response result based on the preprocessing parameters extracted by the standard preset model.
Fig. 9 is a schematic structural diagram of the reverse operation assisting unit provided by the present invention.
FIG. 10 is a flowchart of the data collection and processing method for liver cancer recurrence prediction according to the present invention.
Description of reference numerals: 100-a parameter acquisition module, 110-a pathological data acquisition unit, 120-a physical examination data integration unit, 130-a data extraction unit, 140-a sensing unit, 141-an abdominal magnetic resonance image sensor, 142-an in-vivo organ image sensor, 143-a conventional index sensor, 200-a standard parameter presetting module, 210-a standard sample acquisition unit, 220-a standard preset model construction unit, 230-a standard preset model testing unit, 240-a preset model adjustment unit, 300-a parameter analysis comparison module, 310-a preprocessing parameter extraction unit, 320-a preprocessing parameter operation unit, 330-a cloud early warning library traversal unit, 340-a reading operation module and 350-an analysis display module.
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "including" and "having," and any variations thereof, in the description and claims of this application and the description of the above figures are intended to cover non-exclusive inclusions. The terms "first," "second," and the like in the description and claims of this application or in the above-described drawings are used for distinguishing between different objects and not for describing a particular order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
An embodiment of the present invention provides a data collecting and processing system for liver cancer recurrence prediction, which is used for processing liver cancer recurrence data, and as shown in fig. 1, the data collecting and processing system for liver cancer recurrence prediction includes:
the parameter acquiring module 100 is configured to acquire pathological data of a liver cancer patient, integrate physical examination data of the patient, extract the pathological data and the physical examination data of the liver cancer patient, and preprocess the data to obtain preprocessing parameters.
In the embodiment of the invention, the pathological data of the patient are clinical representation, biochemical test data, abdominal shooting data, postoperative rehabilitation scheme, operation scheme and treatment and diagnosis method of the patient, wherein the physical examination data of the patient are age, sex, electrocardiogram, electroencephalogram, biochemical analysis result of liver wound and tumor state data of the patient.
The standard parameter presetting module 200 is configured to obtain standard sample data, construct a standard preset model based on the standard sample data, test the standard preset model, and adjust the standard preset model.
In the embodiment of the invention, n standard samples are obtained in the standard preset model building process, wherein n is larger than 100, and the characteristic data of the standard samples are input in the standard data testing process, wherein the characteristic data of the standard samples comprise but are not limited to the size of a tumor, tumor resection historical data, PLT, AFP, abnormal thrombin and AST.
The parameter analysis and comparison module 300 extracts the preprocessing parameters, runs the extracted preprocessing parameters based on the standard preset model to obtain a response result, traverses the cloud early warning library to evaluate the risk of postoperative recurrence of the patient, and feeds the risk value back to the parameter acquisition module 100.
In this embodiment, after the preprocessing parameters are extracted, the cloud early warning library integrates statistical analysis means and doctor treatment experience to collect data to obtain a set of treatment schemes, each treatment scheme is divided into a training set, a verification set and a test set according to a ratio of 3:4:3, then the GBDT model is used for predicting the recurrence probability of a patient to obtain a recurrence prediction model, the patient and the doctor are assisted in predicting the postoperative recurrence probability of the patient, and a periodic recurrence probability report is given.
In a further preferred embodiment of the present invention, as shown in fig. 2, the parameter obtaining module 100 includes:
the pathological data acquiring unit 110 is configured to acquire pathological data of a liver cancer patient, sort the pathological data, and screen the pathological data based on different time periods of the patient.
In the embodiment of the invention, pathological data of a liver cancer patient are screened out and used for simplifying a parameter set, the initial parameter set is a domain, the screened out simplified parameter set is a domain, and data are screened out based on a two-dimensional axisymmetric model to obtain the simplified parameter set.
The physical examination data integration unit 120 is configured to integrate the patient physical examination data, filter the irrelevant data, wherein the irrelevant data includes abnormal data and irrelevant data, and perform feature selection based on Pearson product moment correlation coefficient to obtain data with high correlation degree affecting postoperative recurrence in the physical examination data.
The data extraction unit 130 extracts pathological data and physical examination data of the liver cancer patient and preprocesses the data to obtain preprocessing parameters.
In a further preferred embodiment of the present invention, as shown in fig. 3, the sensing unit 140 includes:
the abdominal magnetic resonance image sensor 141 is used for acquiring liver magnetic resonance images of the patient in multiple time periods and multiple angles.
In this embodiment, the abdominal magnetic resonance image sensor 141 is connected to a nuclear magnetic resonance device and is displayed by a display device, the display device may be a touch display screen, the acquired multi-angle liver magnetic resonance image is based on images of included angles of 10 °, 20 °, 30 °, 45 °, 60 ° and 80 ° of a vertical central axis of the liver, and image feature points are extracted.
And the in-vivo organ image sensor 142 is used for acquiring external textures of the liver, images of the liver wound, the number of tumors in the body, the maximum tumor size and the tumor position data of the patient.
And the conventional index sensor 143 is used for collecting sex, age, lymphatic metastasis history, recurrence frequency, recurrence history, lymphocyte ratio and neutrophil ratio of the patient.
In a further preferred embodiment of the present invention, as shown in fig. 4, the method for extracting pathological data and physical examination data of a liver cancer patient and preprocessing the data specifically comprises:
step S101, extracting data with high recurrence correlation degree, and performing characteristic comparison on the data with high recurrence correlation degree based on Pearson product moment correlation coefficient;
step S102, extracting data with high recurrence correlation degree by a risk margin layer, and executing calculation analysis on the data with high recurrence correlation degree to obtain the responsiveness of the data with high recurrence correlation degree;
step S103, extracting the responsivity, and determining a response difference between the responsivity of the data with high correlation and a preset responsivity;
and step S104, screening out data materials with large response difference, storing the data materials with small response difference to obtain a preprocessed data set, and packaging and sending the preprocessed data set to the standard parameter presetting module 200.
In a further preferred embodiment of the present invention, as shown in fig. 5, the standard parameter presetting module 200 comprises:
a standard sample obtaining unit 210, configured to obtain standard sample data and test sample data;
a standard preset model constructing unit 220, configured to construct a standard preset model, where the standard preset model is constructed based on standard sample data;
a standard preset model testing unit 230, configured to test the standard preset model, and compare an optimal prediction result of the standard preset model with a sample lesion detection result;
and a preset model adjusting unit 240, configured to adjust the standard preset model to obtain an optimal response result.
In a further preferred embodiment of the present invention, as shown in fig. 6, the method for constructing the standard default model specifically includes:
step S201, obtaining standard sample data, wherein the standard sample data comprises pathological data of a postoperative patient with recurrent liver cancer and integrated patient physical examination data;
step S202, extracting data of the postoperative relapsed patients, inputting the data of the postoperative relapsed patients into a basic standard preset network, comparing the data of the postoperative relapsed patients with a network parameter response value preset by the basic standard preset network, and extracting the significance of the data of the postoperative relapsed patients based on the network parameter response value;
step S203, judging whether the significance of the data of the postoperative recurrence patients is larger than a preset potential recurrence significance threshold value;
step S204, when the significance of the data of the recurrent patient is judged to be smaller than a preset potential recurrence significance threshold, reducing the significance threshold according to a preset significance threshold reduction rule; or
In step S205, when it is determined that the significance of the data of the relapsing patients is not less than the preset potential relapse significance threshold, the significance threshold is expanded according to the preset significance threshold reduction rule.
In a further preferred embodiment of the present invention, the adjusting the standard preset model to obtain the optimal response result includes:
obtaining test sample data;
extracting postoperative recurrent patient data, inputting the postoperative recurrent patient data into a standard preset model, comparing the postoperative recurrent patient data with a network parameter response value preset by a base standard preset model, extracting the significance of the postoperative recurrent patient data based on the network parameter response value, and judging whether the significance of the recurrent patient data is smaller than a preset potential recurrent significance threshold value or not;
when the significance of the data of the recurrent patients is judged to be smaller than a preset potential recurrent significance threshold value, reducing the significance threshold value according to a preset significance threshold value reduction rule; or
When the significance of the data of the recurrent patients is judged to be smaller than a preset potential recurrent significance threshold value, expanding the significance threshold value according to a preset significance threshold value reduction rule;
and obtaining an optimal response result based on the adjustment of the reduced significance threshold or the expanded significance threshold.
In a further preferred embodiment of the present invention, as shown in fig. 7, the parameter analysis and comparison module 300 comprises:
a preprocessing parameter extracting unit 310 for extracting preprocessing parameters;
a preprocessing parameter operation unit 320 for operating the extracted preprocessing parameters based on the standard preset model to obtain a response result;
and the cloud early warning library traversing unit 330 is configured to traverse the response result, evaluate the risk of postoperative recurrence of the patient, and feed a risk value back to the parameter acquiring module 100.
In a further preferred embodiment of the present invention, as shown in fig. 8, the specific implementation steps of obtaining the response result based on the extracted preprocessing parameter executed by the standard preset model include:
step S301, sequentially preprocessing a set of parameters between an initial time and an end time point in the preprocessing parameters, and acquiring a readable preprocessing parameter identification code when judging that a traversable preprocessing parameter exists in the set of preprocessing parameters;
step S302, operating a preprocessing parameter identification code based on the standard preset model to obtain a response result;
step S303, traversing the response result, calling a set threshold of the cloud early warning library, comparing the response result with the set threshold, determining a response risk value, and feeding back the risk value to the parameter obtaining module 100.
In a further preferred embodiment of the present invention, as shown in fig. 9, the parameter analysis and comparison module 300 further comprises an inverse operation auxiliary unit, and the inverse operation auxiliary unit comprises:
a read operation module 340, configured to perform a write, read, or delete operation on the preprocessing parameter, where the write, read, or delete operation on the preprocessing parameter is to write, read, or delete a unique preprocessing parameter identification code recorded in the set of preprocessing parameters;
and the analysis display module 350 is configured to display the risk value fed back by the cloud early warning library traversal unit 330, and display an analysis report.
The embodiment of the present invention further provides a data collection and processing method for liver cancer recurrence prediction, and fig. 10 shows a work flow chart of the data collection and processing method for liver cancer recurrence prediction, where the data collection and processing method for liver cancer recurrence prediction specifically includes the steps of:
step S100, pathological data of the liver cancer patient are obtained, physical examination data of the patient are integrated, the pathological data and the physical examination data of the liver cancer patient are extracted, and the data are preprocessed to obtain preprocessing parameters.
Step S200, obtaining standard sample data, constructing a standard preset model based on the standard sample data, testing the standard preset model, and adjusting the standard preset model.
Step S300, extracting preprocessing parameters, operating the extracted preprocessing parameters based on the standard preset model to obtain a response result, traversing the cloud early warning library by the response result, evaluating the risk of postoperative recurrence of the patient, and feeding the risk value back to the parameter acquisition module 100.
The invention also provides a readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the processor executes the steps of the data collection processing method for liver cancer recurrence prediction.
Illustratively, a computer program can be partitioned into one or more modules, which are stored in memory and executed by a processor to implement the present invention. One or more of the modules may be a series of computer program instruction segments capable of performing certain functions, which are used to describe the execution of the computer program in the terminal device.
Those skilled in the art will appreciate that the above description of the terminal device is merely exemplary and not limiting, and that more or fewer components than those described above may be included, or certain components may be combined, or different components may be included, such as input output devices, network access devices, buses, etc.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is the control center of the terminal equipment and connects the various parts of the entire user terminal using various interfaces and lines.
The memory may be used to store computer programs and/or modules, and the processor may implement various functions of the terminal device by operating or executing the computer programs and/or modules stored in the memory and calling data stored in the memory. The memory mainly comprises a storage program area and a storage data area, wherein the storage program area can store an operating system, application programs (such as an information acquisition template display function, a product information publishing function and the like) required by at least one function and the like; in addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
In summary, the present invention provides a data collection processing system for liver cancer recurrence prediction, which includes a parameter obtaining module 100, a standard parameter presetting module 200 and a parameter analysis and comparison module 300, wherein the parameter obtaining module 100, the standard parameter presetting module 200 and the parameter analysis and comparison module 300 are executed to obtain a recurrence prediction model, so as to assist patients and doctors in predicting postoperative recurrence probability of patients and give periodic recurrence probability reports.
It should be noted that, for simplicity of description, the above-mentioned embodiments are described as a series of acts, but those skilled in the art will recognize that the present invention is not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the above-described division of the units is only one type of division of logical functions, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or communication connection may be an indirect coupling or communication connection between devices or units through some interfaces, and may be in a telecommunication or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
The above examples are only used to illustrate the technical solutions of the present invention, and do not limit the scope of the present invention. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from these embodiments without making any inventive step, fall within the scope of the present invention. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art may still make various combinations, additions, deletions or other modifications of the features of the embodiments of the present invention according to the situation without conflict, so as to obtain different technical solutions without substantially departing from the spirit of the present invention, and these technical solutions also fall within the protection scope of the present invention.
Claims (10)
1. A data collection and processing system for liver cancer recurrence prediction is used for liver cancer recurrence data processing, and is characterized in that the data collection and processing system for liver cancer recurrence prediction comprises:
the parameter acquisition module is used for acquiring pathological data of the liver cancer patient, integrating physical examination data of the patient, extracting the pathological data and the physical examination data of the liver cancer patient and preprocessing the data to obtain preprocessing parameters;
the standard parameter presetting module is used for acquiring standard sample data, constructing a standard presetting model based on the standard sample data, testing the standard presetting model and adjusting the standard presetting model;
and the parameter analysis and comparison module extracts the preprocessing parameters, runs the extracted preprocessing parameters based on the standard preset model to obtain a response result, traverses the cloud early warning library to evaluate the postoperative recurrence risk of the patient, and feeds the risk value back to the parameter acquisition module.
2. The data collection and processing system for liver cancer recurrence prediction of claim 1, wherein the parameter acquisition module comprises:
the pathological data acquisition unit is used for acquiring pathological data of a liver cancer patient, sorting the pathological data and classifying and screening the pathological data based on different time periods of the patient;
the physical examination data integration unit is used for integrating the physical examination data of the patient and filtering irrelevant data, wherein the irrelevant data comprises abnormal data and irrelevant data, and feature selection is carried out on the basis of Pearson product moment correlation coefficients to obtain data with high relevance for influencing postoperative recurrence in the physical examination data;
and the data information extraction unit is used for extracting pathological information and physical examination data of the liver cancer patient and preprocessing the data to obtain preprocessing parameters.
3. The data collection and processing system of claim 2, wherein the integrated patient health data is obtained from at least one sensor unit, the sensor unit comprising:
the abdominal magnetic resonance image sensor is used for acquiring liver magnetic resonance images of a patient in multiple time periods and multiple angles;
the in-vivo organ image sensor is used for acquiring external textures of the liver, images of liver wounds, the number of tumors in the body, the maximum tumor size and the tumor position data of the patient;
the conventional index sensor is used for collecting sex, age, lymphatic metastasis history, recurrence frequency, recurrence history, lymphocyte ratio and neutrophil ratio of a patient.
4. The data collecting and processing system for liver cancer recurrence prediction as claimed in claim 2, wherein the method for extracting pathological data and physical examination data of liver cancer patients and preprocessing the data specifically comprises:
extracting data with high recurrence correlation degree, and performing feature comparison on the data with high recurrence correlation degree based on Pearson product moment correlation coefficient;
extracting data with high recurrence correlation degree by the risk margin layer, and performing computational analysis on the data with high recurrence correlation degree to obtain the responsiveness of the data with high recurrence correlation degree;
extracting the responsivity, and determining the response difference between the responsivity of the data with high correlation and a preset responsivity;
and screening out data materials with large response difference, storing the data materials with small response difference to obtain a preprocessed data set, and packaging and sending the preprocessed data set to a standard parameter presetting module.
5. The data collection and processing system of claim 4, wherein the standard parameter presetting module comprises:
the standard sample acquisition unit is used for acquiring standard sample data and test sample data;
the standard preset model building unit is used for building a standard preset model, wherein the standard preset model is built based on standard sample data;
the standard preset model testing unit is used for testing the standard preset model and comparing the optimal prediction result of the standard preset model with the lesion detection result of the sample;
and the preset model adjusting unit is used for adjusting the standard preset model to obtain an optimal response result.
6. The data collection and processing system for liver cancer recurrence prediction of claim 5, wherein the construction method of the standard predetermined model specifically comprises:
obtaining standard sample data, wherein the standard sample data comprises pathological data of postoperative patients with recurrent liver cancer and physical examination data of integrated patients;
extracting postoperative recurrent patient data, inputting the postoperative recurrent patient data into a basic standard preset network, comparing the postoperative recurrent patient data with a network parameter response value preset by the basic standard preset network, and extracting the significance of the postoperative recurrent patient data based on the network parameter response value;
judging whether the significance of the data of the postoperative recurrent patients is greater than a preset potential recurrent significance threshold value or not;
when the significance of the data of the recurrent patients is judged to be smaller than a preset potential recurrent significance threshold value, reducing the significance threshold value according to a preset significance threshold value reduction rule; or
And when the significance of the data of the recurrent patients is judged to be not less than the preset potential recurrent significance threshold value, expanding the significance threshold value according to a preset significance threshold value reduction rule.
7. The data collection and processing system of claim 6, wherein the step of adjusting the predetermined standard model to obtain the optimal response comprises:
obtaining test sample data;
extracting postoperative recurrent patient data, inputting the postoperative recurrent patient data into a standard preset model, comparing the postoperative recurrent patient data with a network parameter response value preset by a base standard preset model, extracting the significance of the postoperative recurrent patient data based on the network parameter response value, and judging whether the significance of the recurrent patient data is smaller than a preset potential recurrent significance threshold value or not;
when the significance of the data of the recurrent patients is judged to be smaller than a preset potential recurrent significance threshold value, reducing the significance threshold value according to a preset significance threshold value reduction rule; or
When the significance of the data of the recurrent patients is judged to be smaller than a preset potential recurrent significance threshold value, expanding the significance threshold value according to a preset significance threshold value reduction rule;
and obtaining an optimal response result based on the adjustment of the reduced significance threshold or the expanded significance threshold.
8. The data collection and processing system of claim 7, wherein the parameter analysis and comparison module comprises:
a preprocessing parameter extraction unit for extracting preprocessing parameters;
the preprocessing parameter operation unit is used for operating the extracted preprocessing parameters based on the standard preset model to obtain a response result;
and the cloud early warning library traversal unit is used for traversing the response result, evaluating the risk of postoperative recurrence of the patient and feeding the risk value back to the parameter acquisition module.
9. The data collection and processing system for liver cancer recurrence prediction of claim 8, wherein the specific implementation steps for obtaining the response result based on the extracted pre-processing parameters run by the standard pre-set model comprise:
sequentially preprocessing a preprocessing parameter set between an initial time and an end time point in the preprocessing parameters, and acquiring a readable preprocessing parameter identification code when judging that a traversable preprocessing parameter exists in the preprocessing parameter set;
running a preprocessing parameter identification code based on the standard preset model to obtain a response result;
traversing the response result, calling a set threshold of the cloud early warning library, comparing the response result with the set threshold, judging a response risk value, and feeding the risk value back to the parameter acquisition module.
10. The data collection and processing system of claim 9, wherein the parameter analysis and comparison module further comprises an inverse operation assisting unit, the inverse operation assisting unit comprises:
the read operation module is used for writing, reading or deleting the preprocessing parameters, wherein the writing, reading or deleting operation of the preprocessing parameters is used for writing, reading or deleting the unique preprocessing parameter identification codes recorded in the preprocessing parameter set;
and the analysis display module is used for displaying the risk value fed back by the cloud early warning library traversal unit and displaying the analysis report.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111150834.7A CN113823372A (en) | 2021-09-29 | 2021-09-29 | Data collection and processing system for liver cancer recurrence prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111150834.7A CN113823372A (en) | 2021-09-29 | 2021-09-29 | Data collection and processing system for liver cancer recurrence prediction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113823372A true CN113823372A (en) | 2021-12-21 |
Family
ID=78921708
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111150834.7A Withdrawn CN113823372A (en) | 2021-09-29 | 2021-09-29 | Data collection and processing system for liver cancer recurrence prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113823372A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114613491A (en) * | 2022-03-09 | 2022-06-10 | 曜立科技(北京)有限公司 | Diagnostic decision system for echocardiogram measurement results |
| CN115612743A (en) * | 2022-12-14 | 2023-01-17 | 中国医学科学院北京协和医院 | HPV integration gene combination and application thereof in prediction of cervical cancer recurrence and metastasis |
-
2021
- 2021-09-29 CN CN202111150834.7A patent/CN113823372A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114613491A (en) * | 2022-03-09 | 2022-06-10 | 曜立科技(北京)有限公司 | Diagnostic decision system for echocardiogram measurement results |
| CN115612743A (en) * | 2022-12-14 | 2023-01-17 | 中国医学科学院北京协和医院 | HPV integration gene combination and application thereof in prediction of cervical cancer recurrence and metastasis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101742961B (en) | Diagnosis support device and system | |
| Billups | Algorithms for complementarity problems and generalized equations | |
| CN113823372A (en) | Data collection and processing system for liver cancer recurrence prediction | |
| AU670938B2 (en) | Method for identifying normal biomedical specimens | |
| JP7264486B2 (en) | Image analysis method, image analysis apparatus, image analysis system, image analysis program, recording medium | |
| CN110175978B (en) | Liver cancer imaging omics data processing method, system, device and storage medium | |
| CN108805858A (en) | Hepatopathy CT image computers assistant diagnosis system based on data mining and method | |
| US20190087693A1 (en) | Predicting recurrence in early stage non-small cell lung cancer (nsclc) using spatial arrangement of clusters of tumor infiltrating lymphocytes and cancer nuclei | |
| US20210077009A1 (en) | Predicting response to therapy for adult and pediatric crohn's disease using radiomic features of mesenteric fat regions on baseline magnetic resonance enterography | |
| CN113096109A (en) | Lung medical image analysis method, device and system | |
| CN114663735B (en) | Dual-bone age assessment method based on joint global and local convolutional neural network characteristics | |
| CN115862857A (en) | Tumor immune subtype prediction method, system and computer equipment | |
| Eun et al. | Applications of artificial intelligence in urological setting: a hopeful path to improved care | |
| CN110223772A (en) | A kind for the treatment of endocrine diseases diagnostic device and data information processing method | |
| CN113435469A (en) | Kidney tumor enhanced CT image automatic identification system based on deep learning and training method thereof | |
| CN111528918B (en) | Tumor volume change trend graph generation device after ablation, equipment and storage medium | |
| CN115762788A (en) | Tumor cell detection-based tumor recurrence and metastasis risk assessment system | |
| CN109800820B (en) | Classification method based on ultrasound contrast image uniformity degree | |
| CN113936005A (en) | DNA index calculation method and device, computer equipment and storage medium | |
| Saputri et al. | Enhancing Skin Cancer Classification Using Optimized InceptionV3 Model | |
| US20230206432A1 (en) | Method and apparatus for tumor purity based on pathaological slide image | |
| Mangla | Brain tumor detection and classification by MRI images using deep learning techniques | |
| EP3633603A1 (en) | Tissue density analysis method and system | |
| CN109907730A (en) | A kind of data processing method, device and storage medium and computer equipment | |
| CN116740609A (en) | Classification method, device, equipment and storage medium for kidney tumor ultrasonic video |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20211221 |
|
| WW01 | Invention patent application withdrawn after publication |