Postoperative prognosis prediction system for liver cancer liver transplantation

Abstract

The invention belongs to the field of liver cancer liver transplantation, and provides a liver cancer liver transplantation post-operation prognosis prediction system, which comprises a data acquisition module used for acquiring clinical data of a liver cancer patient from a plurality of data sources, including patient basic information, disease diagnosis information, drug use information and patient body function information; the data processing module is used for preprocessing the collected data, including data cleaning, missing value filling, data standardization and data integration, so as to ensure the quality and consistency of the data; by integrating multi-source data and combining advanced algorithms and models, accurate prediction of prognosis of patients after liver cancer liver transplantation is achieved, warning is automatically given out when a risk threshold value is reached, timely and accurate early warning information is provided for medical staff, and by collecting medicine use information and patient body function information, the patient prognosis is accurately predicted. And the physical condition of the patient can be obtained in real time through long-term monitoring, so that the prognosis prediction result is more accurate.

Description

Technical Field

[0001] The invention belongs to the field of liver transplantation for liver cancer, and in particular is a prognosis prediction system after liver transplantation for liver cancer. Background Art

[0002] Liver cancer, as one of the most common malignant tumors in the world, has no obvious early symptoms and is often in the middle and late stages when diagnosed, which poses great challenges to treatment. Liver transplantation is one of the key technologies for the treatment of liver cancer. It removes the diseased liver that has lost its function and transplants it into a healthy liver. The background of this technology is based on the development and integration of multiple disciplines. After years of development, the survival time of liver transplant patients has been continuously extended, and the incidence of complications has also been reduced, which has brought significant hope of survival to patients. However, the prognosis of patients after surgery varies from individual to individual. Accurately predicting the prognosis after surgery is crucial to formulating subsequent treatment plans and improving patient survival rates.

[0003] In the Chinese patent with publication number CN110634571A, a system for predicting the prognosis after liver transplantation is mentioned, which includes a data acquisition module for acquiring clinical data; a database for storing clinical data, which includes the patient's basic information, clinical indicators, intraoperative treatment measures and prognosis after liver transplantation; a factor statistics module for performing statistical tests on the clinical data and obtaining significant influencing factors; and a correlation analysis module for analyzing and testing the correlation between the influencing factors and the prognosis after liver transplantation, and obtaining risk factors that have significant statistical correlation with the prognosis after liver transplantation.

[0004] However, existing prognosis prediction systems mostly rely on the evaluation of a single or a few clinical indicators. This method is often difficult to fully reflect the patient's overall condition. When the predicted results are abnormal, the warning information cannot be pushed in the first time, which can easily lead to missing the best time for treatment due to the time difference in information acquisition. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a prognosis prediction system for liver cancer after liver transplantation, so as to solve the problem in the prior art that when the predicted results are abnormal, the warning information cannot be pushed in the first time, thereby easily missing the best time for treatment due to the time difference in information acquisition.

[0006] A prognosis prediction system for liver cancer after liver transplantation, comprising:

[0007] Data collection module: used to obtain clinical data of liver cancer patients from multiple data sources, including basic information of patients, disease diagnosis information, drug use information and patient physical function information;

[0008] Data processing module: pre-process the collected data, including data cleaning, missing value filling, data standardization and data integration to ensure data quality and consistency;

[0009] Prognosis prediction and training module: used to establish a prediction model, use machine learning or deep learning algorithms, establish a prognosis prediction model based on the extracted key features, and train and optimize the model through a training data set. The model can predict the prognosis of patients after liver transplantation for liver cancer and output the prediction results;

[0010] Risk threshold setting and warning module: The prognostic risk threshold is set based on clinical experience and professional knowledge. When the prediction result reaches or exceeds the threshold, the system automatically triggers an alarm;

[0011] Terminal: The entire system is operated through the terminal, which stores the data generated during the system's prognosis prediction process, provides an intuitive patient information display interface, inputs patient data according to actual conditions, views prediction results, and performs other related operations.

[0012] The present invention establishes a prediction model by centrally collecting and processing various clinical information generated during various treatment processes of patients, uses the prediction model to combine currently received patient data information and related medical information to predict patients, and uses a terminal to present the predicted results. During the prediction process, various patient data are continuously monitored, and an early warning can be sent to the corresponding medical staff when abnormalities in patient data are detected, so as to quickly find out the causes, treat patients in time, adjust treatment plans, and optimize the use process.

[0013] Preferably, the basic patient information includes the patient's age, gender, liver cancer stage, tumor size, metastasis, liver function indexes before and after surgery, pathological histological type, and liver transplantation details. By collecting the patient's basic information and uploading it to the terminal for storage, the doctor can perform corresponding treatment according to the patient's condition.

[0014] Preferably, the basic patient information also includes the collection of the patient's genomic data, proteomic data, metabolomics data and the interface of the imaging diagnosis system, automatic data synchronization and real-time update. Through high-throughput sequencing technology, the genome sequence of liver cancer patients can be detected, and mutant genes related to the occurrence and development of liver cancer can be found. By analyzing the patient's genomic characteristics, the prognosis after liver transplantation can be predicted. Through proteomic data, protein markers related to liver cancer can be screened and identified, and the differences in protein expression between liver cancer tissue and normal liver tissue can be compared. Through metabolomics research, metabolites related to allogeneic rejection can be identified, and the recovery after liver transplantation can be assessed. The patient's body condition can be displayed through the imaging diagnosis system to facilitate liver treatment.

[0015] Preferably, the drug use information includes the time and type of drugs taken by the patient before and after the operation and the patient's diet, and detects and records the changes in the patient's body functions after taking the drugs and food. By recording the patient's diet and drug taking, it is possible to determine the cause of the changes in body functions within the corresponding time.

[0016] Preferably, the data acquisition module further includes a data privacy protection unit to ensure that all data processing processes comply with medical data privacy protection regulations. The data privacy protection unit can prevent the patient's information from being leaked during use.

[0017] Preferably, the data cleaning includes autonomously identifying obviously erroneous data, determining the value range, judging abnormal values, and processing them according to the actual situation. By determining the value range, when the entered content exceeds the range, such as the patient's age appears as a negative number, the system actively identifies the error position and marks it, reminding medical staff to correct the information.

[0018] Preferably, the data integration includes data merging, data deduplication and data consistency check to ensure that the data between different data sources are consistent. The accuracy of the results generated by the prediction model for the patient is ensured by checking the consistency of the data, avoiding the prediction effect being affected by the uncertainty of the patient data.

[0019] Preferably, the warning module sends warning information to medical staff or patients through a user interface, text messages, emails, etc., reminding them to pay attention in time and take corresponding intervention measures. By using a variety of information transmission methods to push the patient's information to medical staff, medical staff can be reminded to treat the patient when in use, shortening the patient's waiting time for treatment.

[0020] Preferably, the warning module also includes timing and reminding the patient to take the medicine to ensure that the patient takes the medicine within the specified time range. By pushing the time when the patient takes the medicine to the medical staff, it can ensure that the patient can take the specified medicine within a specific time during the treatment process, avoid changes in the patient's physical function due to incorrect medication during the treatment process, and improve the treatment effect.

[0021] Preferably, the prognosis prediction results in the prognosis prediction and training module include the patient's survival rate within a specific period of time, the risk of tumor recurrence, and the overall survival situation, etc. By reading the prognosis prediction results, it is convenient for medical staff to judge the patient's physical condition and apply corresponding treatment to prolong the patient's life.

[0022] Preferably, the prognosis prediction and training module also includes a continuous learning and updating module, which can regularly update and optimize the model based on newly collected data to adapt to changes in disease characteristics and advances in medical technology. The prediction model is updated with newly collected data, and after the update, the prediction model can more accurately predict the patient's condition, thereby improving the accuracy of the system's prediction results.

[0023] A method for predicting the prognosis of liver cancer after liver transplantation by a prognosis prediction system comprises the following steps:

[0024] Step 1: Collect clinical data of predicted patients;

[0025] Step 2: The collected clinical data of the patients are transmitted to the data processing module for data preprocessing;

[0026] Step 3: Using machine learning or deep learning algorithms, based on the data preprocessing results, extract key features to establish a prognosis prediction model and obtain the patient prognosis prediction results;

[0027] Step 4: Set the prognostic risk threshold based on clinical experience and professional knowledge. When the prediction result reaches or exceeds the threshold, the system automatically triggers an alert;

[0028] Step 5: Operate the entire system through the terminal to provide an intuitive patient information display interface and display the prognosis prediction results.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] 1. The present invention integrates multi-source data and combines advanced algorithms and models to achieve accurate prediction of the prognosis of patients after liver transplantation for liver cancer. It automatically issues an alarm when the risk threshold is reached, providing timely and accurate early warning information for medical staff. By collecting information on drug use and patient physical function, long-term monitoring can obtain the patient's physical condition in real time, making the prognosis prediction results more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 This is a schematic diagram of Embodiment 1 of the prognosis prediction system for liver cancer after liver transplantation according to the present invention;

[0032] Figure 2 The present invention is a flowchart of the prognosis prediction system for liver cancer after liver transplantation. DETAILED DESCRIPTION

[0033] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0034] As attached Figure 1 To Attachment Figure 2 As shown:

[0035] Embodiment 1: The present invention provides a system for predicting the prognosis of liver cancer after liver transplantation, comprising:

[0036] Data collection module: used to obtain clinical data of liver cancer patients from multiple data sources, including basic information of patients, disease diagnosis information, drug use information and patient physical function information;

[0037] Data processing module: pre-process the collected data, including data cleaning, missing value filling, data standardization and data integration to ensure data quality and consistency;

[0038] Prognosis prediction and training module: used to establish a prediction model. It uses machine learning or deep learning algorithms to establish a prognosis prediction model based on the extracted key features, and trains and optimizes the model through training data sets. The model can predict the prognosis of patients with liver cancer after liver transplantation and output the prediction results.

[0039] Risk threshold setting and warning module: The prognostic risk threshold is set based on clinical experience and professional knowledge. When the prediction result reaches or exceeds the threshold, the system automatically triggers an alarm;

[0040] Terminal: The entire system is operated through the terminal, which stores the data generated during the system's prognosis prediction process, provides an intuitive patient information display interface, inputs patient data according to actual conditions, views prediction results, and performs other related operations.

[0041] From the above, we can see that by integrating multi-source data and combining advanced algorithms and models, we can achieve accurate prediction of the prognosis of patients after liver transplantation for liver cancer. The predicted results can be used to reversely deduce the results based on the collected data, summarize technical experience, and improve the prediction model. When the risk threshold is reached, an alarm will be automatically issued, providing medical staff with timely and accurate early warning information. By collecting information on drug use and patient physical function, long-term monitoring can obtain the patient's physical condition in real time, thereby improving the accuracy of prognosis prediction results.

[0042] Regarding the above-mentioned data collection module, the basic information of the patient includes the patient's age, gender, liver cancer stage, tumor size, whether it has metastasized, liver function indicators before and after the operation, pathological histological type, and liver transplantation operation details; specifically, the basic information of the patient is collected and uploaded to the terminal for storage, so that the doctor can provide corresponding treatment according to the patient's condition.

[0043] Regarding the above-mentioned data collection module, the basic information of the patient also includes the collection of the patient's genomic data, proteomic data, metabolomics data and the interface of the imaging diagnosis system, automatic data synchronization and real-time update;

[0044] Specifically, through high-throughput sequencing technology, the genome sequence of liver cancer patients can be detected, and mutant genes related to the occurrence and development of liver cancer can be discovered. By analyzing the patient's genomic characteristics, the prognosis after liver transplantation can be predicted. Through proteomics data, protein markers related to liver cancer can be screened and identified, and the differences in protein expression between liver cancer tissue and normal liver tissue can be compared. Through metabolomics research, metabolites related to allogeneic rejection can be identified, and the recovery after liver transplantation can be evaluated. The imaging diagnostic system can display the patient's internal conditions for liver treatment.

[0045] Regarding the above-mentioned data collection module, the drug usage information includes the time and type of drugs taken by the patient before and after the operation and the patient's diet, and detects and records the changes in the patient's body functions after taking the drugs and food; specifically, by recording the patient's diet and drug intake, it is possible to judge the causes of the changes in body functions within the corresponding time.

[0046] The data collection module also includes a data privacy protection unit to ensure that all data processing processes comply with medical data privacy protection regulations; specifically, the data privacy protection unit can prevent the leakage of patient information during use.

[0047] Regarding the above-mentioned data processing module, data cleaning includes autonomously identifying obviously erroneous data, determining the range of values, judging abnormal values, and processing them according to actual conditions; specifically, by determining the range of values, when the filled-in content exceeds the range, such as the patient's age appears as a negative number, the system actively identifies the error position and marks it, reminding medical staff to correct the information.

[0048] Regarding the above-mentioned data processing module, data integration includes data merging, data deduplication and data consistency checking to ensure that the data between different data sources are consistent; specifically, the accuracy of the results generated by the prediction model for patients is ensured by checking the data consistency to avoid the prediction effect being affected by the uncertainty of patient data.

[0049] Regarding the above-mentioned risk threshold setting and warning module, the warning module sends warning information to medical staff or patients through various means such as user interface, text messages, emails, etc., reminding medical staff or patients to pay attention in time and take corresponding intervention measures; specifically, by adopting various information transmission methods to push the patient's information to medical staff, it can remind medical staff to treat the patient when in use, shortening the patient's waiting time for treatment.

[0050] Regarding the above-mentioned risk threshold setting and warning module, the warning module also includes timing and reminding the patient's medication time to ensure that the patient takes the medication within the specified time range; specifically, by pushing the time when the patient takes the medication to medical staff, it can ensure that the patient can take the designated medication within a specific time during the treatment process, avoiding changes in the patient's physical function due to incorrect medication during the treatment process, thereby improving the treatment effect.

[0051] Regarding the above-mentioned prognosis prediction and training module, the prognosis prediction results in the prognosis prediction and training module include the patient's survival rate within a specific period of time, the risk of tumor recurrence, and the overall survival status, etc.; specifically, by reading the prognosis prediction results, it is convenient for medical staff to judge the patient's physical condition and apply corresponding treatment to prolong the patient's life.

[0052] Regarding the above-mentioned prognosis prediction and training module, the prognosis prediction and training module also includes a continuous learning and updating module, which can regularly update and optimize the model based on newly collected data to adapt to changes in disease characteristics and advances in medical technology; specifically, the prediction model is updated through newly collected data, and after the update, the prediction model can more accurately predict the patient's condition, thereby improving the accuracy of the system's prediction results.

[0053] Embodiment 2: This embodiment provides a method for predicting the prognosis of liver cancer after liver transplantation by a system for predicting the prognosis, comprising the following steps:

[0054] Step 1: Collect clinical data of predicted patients;

[0055] Step 2: The collected clinical data of the patients are transmitted to the data processing module for data preprocessing;

[0056] Step 3: Using machine learning or deep learning algorithms, based on the data preprocessing results, extract key features to establish a prognosis prediction model and obtain the patient prognosis prediction results;

[0057] Step 4: Set the prognostic risk threshold based on clinical experience and professional knowledge. When the prediction result reaches or exceeds the threshold, the system automatically triggers an alert;

[0058] Step 5: Operate the entire system through the terminal to provide an intuitive patient information display interface and display the prognosis prediction results.

[0059] From the above, it can be seen that the present invention establishes a prediction model by centrally collecting and processing various clinical information generated during various treatment processes of patients, uses the prediction model in combination with the currently received patient data information and related medical information to predict the patient, and uses the terminal to present the predicted results. During the prediction process, various patient data are continuously monitored, and an early warning can be sent to the corresponding medical staff when abnormalities are detected in the patient data, so as to quickly find out the cause, treat the patient in time and adjust the treatment plan, thereby optimizing the use process.

[0060] The standard equipment and modules used in the present invention can be purchased from the market, and the special-shaped parts can be customized according to the description and the drawings. The specific connection methods of each structure adopt conventional means such as mature bolts, rivets, welding, etc. in the prior art. The machinery, parts and equipment all adopt conventional models in the prior art, and the circuit connection adopts the conventional connection method in the prior art, which will not be described in detail here. The contents not described in detail in this specification belong to the prior art known to professional and technical personnel in this field.

[0061] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention.

[0062] In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other.

[0063] The embodiments of the present invention are provided for the purpose of illustration and description. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present invention. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A prognosis prediction system for liver cancer after liver transplantation, characterized in that: include: Data collection module: used to obtain clinical data of liver cancer patients from multiple data sources, including basic information of patients, disease diagnosis information, drug use information and patient physical function information; Data processing module: pre-process the collected data, including data cleaning, missing value filling, data standardization and data integration to ensure data quality and consistency; Prognosis prediction and training module: used to establish a prediction model, use machine learning or deep learning algorithms, establish a prognosis prediction model based on the extracted key features, and train and optimize the model through a training data set. The model can predict the prognosis of patients after liver transplantation for liver cancer and output the prediction results; Risk threshold setting and warning module: The prognostic risk threshold is set based on clinical experience and professional knowledge. When the prediction result reaches or exceeds the threshold, the system automatically triggers an alarm; Terminal: The entire system is operated through the terminal, which stores the data generated during the system's prognosis prediction process, provides an intuitive patient information display interface, inputs patient data according to actual conditions, views prediction results, and performs other related operations.

2. The system for predicting prognosis after liver transplantation for liver cancer according to claim 1, characterized in that: The patient's basic information includes the patient's age, gender, liver cancer stage, tumor size, whether it has metastasized, liver function indicators before and after surgery, pathological histological type, and liver transplantation surgery details.

3. The system for predicting prognosis after liver transplantation for liver cancer according to claim 2, characterized in that: The patient basic information also includes the collection of the patient's genomic data, proteomic data, metabolomics data and the interface of the imaging diagnosis system, automatic data synchronization and real-time update.

4. The system for predicting prognosis after liver transplantation for liver cancer according to claim 1, characterized in that: The drug use information includes the time and type of drugs taken by the patient before and after the operation and the patient's diet, and detects and records the changes in the patient's body functions after taking the drugs and food.

5. The system for predicting prognosis after liver transplantation for liver cancer according to claim 1, characterized in that: The data acquisition module also includes a data privacy protection unit to ensure that all data processing processes comply with medical data privacy protection regulations.

6. The system for predicting prognosis after liver transplantation for liver cancer according to claim 1, characterized in that: The data cleaning includes autonomously identifying obviously erroneous data, determining the value range, judging abnormal values, and processing them according to actual conditions. The data integration includes data merging, data deduplication, and consistency checking of data to ensure that data between different data sources are consistent. The warning module sends warning information to medical staff or patients through user interface, text messages, emails, etc., reminding medical staff or patients to pay attention in time and take corresponding intervention measures.

7. The prognosis prediction system for liver cancer after liver transplantation according to claim 6, characterized in that: The warning module also includes timing and reminding the patient of the time to take the medicine, ensuring that the patient takes the medicine within the specified time range.

8. The system for predicting prognosis after liver transplantation for liver cancer according to claim 1, characterized in that: The prognosis prediction results in the prognosis prediction and training module include the patient's survival rate within a specific period of time, the risk of tumor recurrence, and the overall survival status.

9. The system for predicting prognosis after liver transplantation for liver cancer according to claim 8, characterized in that: The prognosis prediction and training module also includes a continuous learning and updating module, which can regularly update and optimize the model based on newly collected data to adapt to changes in disease characteristics and advances in medical technology.

10. A method for predicting the prognosis of liver cancer after liver transplantation according to any one of claims 1 to 9, comprising the following steps: Step 1: Collect clinical data of predicted patients; Step 2: The collected clinical data of the patients are transmitted to the data processing module for data preprocessing; Step 3: Using machine learning or deep learning algorithms, based on the data preprocessing results, extract key features to establish a prognosis prediction model and obtain the patient prognosis prediction results; Step 4: Set the prognostic risk threshold based on clinical experience and professional knowledge. When the prediction result reaches or exceeds the threshold, the system automatically triggers an alert; Step 5: Operate the entire system through the terminal to provide an intuitive patient information display interface and display the prognosis prediction results.

Images