Establishment method of hepatitis B liver cirrhosis liver cancer risk prediction model

Abstract

The invention discloses a method for establishing a hepatitis B cirrhosis liver cancer risk prediction model, and relates to the technical field of risk prediction, and the method comprises the following implementation steps: entering a multi-factor consideration module, and analyzing a risk prediction result in real time through combining different races and territorial ranges of a variety of people, judging whether risk prediction under various factors has prediction deviation or not in real time; entering a recessive risk analysis module, setting a risk prediction standard model in real time, and predicting whether the liver cancer risk prediction model deviates or not in real time in a multi-factor manner by combining the health condition, the lifestyle, the diet condition and the genetic factors of the patient; and entering an early-warning evaluation module for early warning whether liver cancer occurs or not according to the physical condition of the patient. According to the establishment method of the hepatitis B cirrhosis liver cancer risk prediction model, the accuracy of risk prediction model establishment is improved, whether a patient has the liver cancer risk or not is predicted in time according to multiple factors, and the patient possibly having the liver cancer risk is corrected and guided in advance.

Description

Technical Field

[0001] The present invention relates to the technical field of risk prediction, and in particular to a method for establishing a risk prediction model for liver cancer development in patients with hepatitis B cirrhosis. Background Art

[0002] Predicting the risk of liver cancer in patients with hepatitis B cirrhosis is an important clinical issue, because hepatitis B virus infection is one of the main causes of cirrhosis and liver cancer. Patients with hepatitis B cirrhosis are at high risk of liver cancer. Early prediction of liver cancer risk can help develop individualized monitoring plans, such as regular ultrasound examinations and alpha-fetoprotein testing, and timely intervention, such as antiviral treatment and lifestyle adjustments, to improve early diagnosis rates and treatment outcomes.

[0003] Currently, there are some deficiencies in predicting the risk of liver cancer in patients with hepatitis B cirrhosis: 1. Risk prediction models are usually based on data from a specific population, but that specific population may not be fully applicable to all patients, resulting in a narrow scope of applicability of the risk prediction model; 2. Existing risk prediction models often focus on known liver cancer risk factors, such as age, gender, and hepatitis B virus load, but may not fully consider the patient's overall health status, lifestyle, and genetic factors. Therefore, there may be limitations in predicting the progression of liver cancer.

[0004] Therefore, a method for establishing a risk prediction model for liver cancer in patients with hepatitis B cirrhosis is proposed to solve the above problems. Summary of the Invention

[0005] The main purpose of the present invention is to provide a method for establishing a risk prediction model for liver cancer in patients with hepatitis B cirrhosis, so as to solve the problems raised in the above background.

[0006] To achieve the above-mentioned purpose, the technical solution adopted by the present invention is: a method for establishing a risk prediction model for liver cancer in patients with hepatitis B cirrhosis, the method comprising the following steps: Step 1: Enter the multi-factor consideration module, collect data on hepatitis B cirrhosis risk warnings from various populations, analyze risk prediction results in real time based on the different ethnicities and geographical ranges of these populations, and determine in real time whether there are any prediction biases in risk predictions under various factors; Step 2: Enter the latent risk analysis module and set a risk prediction standard model in real time based on liver cancer risk factors, age, gender, and hepatitis B virus load. Combined with the patient's health status, lifestyle, diet, and genetic factors, a real-time multi-factor prediction is performed to determine if the liver cancer risk prediction model is biased. Step 3: Enter the early warning assessment module and receive the risk prediction model combining explicit and implicit factors in real time. When predicting the risk of liver cancer, it will provide early warning of whether liver cancer will occur based on the patient's physical condition, and conduct real-time risk assessment of the physical conditions of different patients.

[0007] The multi-factor consideration module includes a multi-population data collection unit, a real-time risk analysis unit, and a multi-factor judgment unit; The multiple population data acquisition unit is used to collect data for hepatitis B cirrhosis risk warning from multiple populations in real time through a data acquisition instrument. The multiple populations include people of different races and people from different geographical areas. The data for hepatitis B cirrhosis risk warning from people of different races and people from different geographical areas include age, gender and hepatitis B virus load, and are recorded in real time through a data recorder.

[0008] The real-time risk analysis unit is used to analyze in real time whether the risk prediction results are different according to the different races and geographical ranges of multiple populations, and obtain the difference value of the risk prediction results of two different races and geographical ranges. , the calculation formula is as follows: ; in, Indicates the difference in risk prediction results between two different races and geographical ranges, Represents risk data for different ethnic and geographic areas, and Represents the risk standard deviation of two different ethnic groups and geographical ranges, and Represents two different races and geographical ranges of recorded data, including age, gender and hepatitis B virus load, recorded data represents dominant factors, set the risk prediction result standard difference threshold, if If the absolute value of is greater than the standard difference threshold, it means that the risk prediction results of the two different races and geographical ranges are different. If not, it means that the risk prediction results of the two different races and geographical ranges are the same.

[0009] The multi-factor judgment unit is used to judge in real time whether there is a prediction deviation in the risk prediction under multiple factors based on the results. The prediction method is as follows: Step 1: Calculate the risk prediction deviation value under various factors , the calculation formula is as follows: ; in, Indicates the risk prediction deviation value under multiple factors. represents the number of factors, Indicates averaging the total absolute deviations, represents the sum of the absolute deviations of all factors, Indicates the The predicted value of a factor, It is The actual value of the factor, It is The absolute deviation of each factor sets the standard difference threshold. If the absolute value of is greater than the standard difference threshold, it means that the risk prediction under multiple factors has a prediction bias. If not, it means that the risk prediction under multiple factors has no prediction bias.

[0010] The implicit risk analysis module includes a standard risk prediction model unit, an implicit factor unit and an implicit factor prediction unit; The standard risk prediction model unit is used to combine historical data and multiple liver cancer risk factors, and to set a risk prediction standard model based on age, gender and hepatitis B virus load. The risk prediction standard model is determined based on different ages, different genders and different hepatitis B virus loads.

[0011] The latent factor cycle unit is used to predict liver cancer risk in combination with the life cycle of latent factors, where the latent factors include the patient's health status, lifestyle, diet and genetic factors.

[0012] The latent factor prediction unit is used to calculate the predicted risk value of liver cancer in the life cycle at different ages by combining the latent factors. , the calculation formula is as follows: ; in, Represents the life cycle at different ages, that is, the length of the time stage, T represents different ages, It represents the instantaneous risk rate of liver cancer at stage length t. The patient's health status, lifestyle, diet and genetic factors are combined to calculate whether the life cycle liver cancer prediction risk values under multiple factors are the same. If the difference is greater than the standard threshold, it means that there is a deviation in the multi-factor prediction model of liver cancer risk and there is a risk of liver cancer. If not, it means that there is no deviation in the multi-factor prediction model of liver cancer risk and there is no risk of liver cancer. The life cycle liver cancer prediction risk results at different ages are recorded and stored in real time through a data recorder.

[0013] The early warning assessment module includes a data receiving unit, a multi-factor early warning risk unit and a risk assessment guidance unit; The data receiving unit is used to receive risk prediction results combining explicit factors and implicit factors in real time through a data receiver.

[0014] The multi-factor early warning risk unit is used to warn the patient in advance of whether he or she is at risk of developing liver cancer based on the patient's physical condition. The early warning method is as follows: Dynamically monitor the patient's risk of liver cancer by combining the patient's age, gender, AFP (alpha-fetoprotein), AFP-L3%, and abnormal prothrombin data; The data recorder records the patient's risk value for liver cancer under dynamic monitoring in real time, and sets a risk value greater than or equal to 5 and less than or equal to 8 as low risk, a risk value greater than 8 and less than or equal to 10 as medium risk, and a risk value greater than 10 as high risk.

[0015] The risk assessment guidance unit is used to provide real-time risk assessment guidance based on the risk value. The guidance includes monitoring liver function, AFP and ultrasound operations every 6-12 months for low risk, monitoring AFP, ultrasound and CT / MRI operations every 3-6 months for medium risk, and CT / MRI and liver biopsy operations for high risk.

[0016] The present invention has the following beneficial effects: 0. In the present invention, by setting up a multi-factor consideration module, when establishing a risk prediction model for liver cancer in patients with hepatitis B cirrhosis, the risk prediction results are analyzed in real time by different races and geographical ranges of various populations to see whether they are different. Based on the results, it is determined in real time whether there is a prediction bias in the risk prediction under various factors, thereby reducing the limitations of the risk prediction model and further increasing the accuracy of the risk prediction model by combining the special risk factors of patients of specific races or regions; 1. The present invention provides a latent risk analysis module. When establishing a liver cancer risk prediction model for hepatitis B cirrhosis, the model takes into account the patient's health status, lifestyle, diet, and genetic factors. This eliminates the existing risk prediction model's focus solely on known liver cancer risk factors, including age, gender, and hepatitis B viral load. It also fully considers the patient's overall health status, lifestyle, and genetic factors, and combines latent factors to predict the patient's liver cancer risk in real time. This allows for timely prediction of whether a patient is at risk of liver cancer based on multiple factors. 2. In the present invention, by setting up an early warning assessment module, when establishing a risk prediction model for liver cancer caused by hepatitis B cirrhosis, an early warning can be given to the patient based on the patient's physical condition to determine whether the patient is at risk of developing liver cancer, and risk assessment can be performed on the physical conditions of different patients in real time. When predicting the risk of liver cancer, an early warning can be given to the patient based on the patient's physical condition to determine whether the patient is at risk of developing liver cancer, and corrective guidance can be given to patients who are at risk of liver cancer in advance, thereby further reducing the possibility of the risk of liver cancer. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is an overall flow chart of a method for establishing a risk prediction model for liver cancer in patients with hepatitis B cirrhosis according to the present invention; Figure 2 This is a schematic diagram of the architecture of a multi-factor consideration module for a method for establishing a risk prediction model for liver cancer in patients with hepatitis B cirrhosis according to the present invention; Figure 3This is a schematic diagram of the architecture of a latent risk analysis module of a method for establishing a risk prediction model for liver cancer in patients with hepatitis B cirrhosis according to the present invention; Figure 4 This is a schematic diagram of the framework of an early warning assessment module of a method for establishing a risk prediction model for liver cancer caused by hepatitis B cirrhosis according to the present invention. DETAILED DESCRIPTION

[0018] In order to make the technical means, creative features, objectives and effects achieved by the present invention easier to understand, the present invention is further described below in conjunction with specific implementation methods.

[0019] Example 1, please refer to Figures 1 to 2 A method for establishing a risk prediction model for liver cancer in patients with hepatitis B cirrhosis is shown, comprising the following steps: Step 1: Enter the multi-factor consideration module, collect data on hepatitis B cirrhosis risk warnings from various populations, analyze risk prediction results in real time based on the different ethnicities and geographical ranges of these populations, and determine in real time whether there are any prediction biases in risk predictions under various factors; Step 2: Enter the latent risk analysis module and set a risk prediction standard model in real time based on liver cancer risk factors, age, gender, and hepatitis B virus load. Combined with the patient's health status, lifestyle, diet, and genetic factors, a real-time multi-factor prediction is performed to determine if the liver cancer risk prediction model is biased. Step 3: Enter the early warning assessment module and receive the risk prediction model combining explicit and implicit factors in real time. When predicting the risk of liver cancer, it will provide early warning of whether liver cancer will occur based on the patient's physical condition, and conduct real-time risk assessment of the physical conditions of different patients.

[0020] The multi-factor consideration module includes a multi-population data collection unit, a real-time risk analysis unit, and a multi-factor judgment unit; The multiple population data acquisition unit is used to collect data for hepatitis B cirrhosis risk warning from multiple populations in real time through a data acquisition instrument. The multiple populations include people of different races and people from different geographical areas. The data for hepatitis B cirrhosis risk warning from people of different races and people from different geographical areas include age, gender and hepatitis B virus load, and are recorded in real time through a data recorder.

[0021] The real-time risk analysis unit is used to analyze in real time whether the risk prediction results are different according to the different races and geographical ranges of multiple populations, and obtain the difference value of the risk prediction results of two different races and geographical ranges. , the calculation formula is as follows: ; in, Indicates the difference in risk prediction results between two different races and geographical ranges, Represents risk data for different ethnic and geographic areas, and Represents the risk standard deviation of two different ethnic groups and geographical ranges, and Represents two different races and geographical ranges of recorded data, including age, gender and hepatitis B virus load, recorded data represents dominant factors, set the risk prediction result standard difference threshold, if If the absolute value of is greater than the standard difference threshold, it means that the risk prediction results of the two different races and geographical ranges are different. If not, it means that the risk prediction results of the two different races and geographical ranges are the same.

[0022] The multi-factor judgment unit is used to judge in real time whether there is a prediction deviation in the risk prediction under multiple factors based on the results. The prediction method is as follows: Step 1: Calculate the risk prediction deviation value under various factors , the calculation formula is as follows: ; in, Indicates the risk prediction deviation value under multiple factors. represents the number of factors, Indicates averaging the total absolute deviations, represents the sum of the absolute deviations of all factors, Indicates the The predicted value of a factor, It is The actual value of the factor, It is The absolute deviation of each factor sets the standard difference threshold. If the absolute value of is greater than the standard difference threshold, it means that the risk prediction under multiple factors has a prediction bias. If not, it means that the risk prediction under multiple factors has no prediction bias. According to the results, it is judged in real time whether the risk prediction under multiple factors has a prediction bias, so that the model can be applied according to different races and geographical ranges. The model can be fully applicable to all patients, reducing the limitations of the use of the risk prediction model, and combining the special risk factors of patients of specific races or regions to further increase the accuracy of the risk prediction model.

[0023] Example 2, please refer to Figure 3 As shown: Based on the first embodiment, the implicit risk analysis module includes a standard risk prediction model unit, an implicit factor unit and an implicit factor prediction unit; The standard risk prediction model unit is used to combine historical data and multiple liver cancer risk factors, and to set a risk prediction standard model based on age, gender and hepatitis B virus load. The risk prediction standard model is determined according to different ages, different genders and different hepatitis B virus loads. The standard risk prediction model can also be set based on the liver hardness index of patients with cirrhosis. The liver hardness index includes LSM and hepatitis B markers, such as HBcrAg, HBV RNA and other key indicators for predicting liver cancer.

[0024] The latent factor cycle unit is used to predict liver cancer risk in combination with the life cycle of latent factors, where the latent factors include the patient's health status, lifestyle, diet and genetic factors.

[0025] The latent factor prediction unit is used to calculate the predicted risk value of liver cancer in the life cycle at different ages by combining the latent factors. , the calculation formula is as follows: ; in, Represents the life cycle at different ages, that is, the length of the time stage, T represents different ages, It represents the instantaneous risk rate of liver cancer at stage length t, and combines the patient's health status, lifestyle, diet and genetic factors to calculate whether the life cycle liver cancer prediction risk values under multiple factors are the same. If the difference is greater than the standard threshold, it means that there is a deviation in the multi-factor prediction model of liver cancer risk, and there is a risk of liver cancer. If not, it means that there is no deviation in the multi-factor prediction model of liver cancer risk, and there is no risk of liver cancer. The life cycle liver cancer prediction risk results at different ages are recorded and stored in real time through a data recorder. According to whether there is a deviation in the multi-factor prediction model of liver cancer risk, the existing risk prediction model no longer focuses solely on known liver cancer risk factors, including age, gender and hepatitis B virus load, but can also fully consider the patient's overall health status, lifestyle, genetic factors, and combine hidden factors to predict the patient's liver cancer risk in real time, and can timely predict whether the patient has a risk of liver cancer based on multiple factors.

[0026] Example 3, please refer to Figure 4 As shown: Based on the first embodiment, the early warning assessment module includes a data receiving unit, a multi-factor early warning risk unit and a risk assessment guidance unit; The data receiving unit is used to receive risk prediction results combining explicit factors and implicit factors in real time through a data receiver.

[0027] The multi-factor early warning risk unit is used to warn the patient in advance of whether he or she is at risk of developing liver cancer based on the patient's physical condition. The early warning method is as follows: The patient's risk of liver cancer is dynamically monitored based on age, gender, AFP (alpha-fetoprotein), AFP-L3%, and abnormal prothrombin data. The dynamic monitoring calculation formula is: GALAD Score = 0.07 × age + 0.09 × (male = 1, female = 0) + 0.04 × AFP + 0.11 × AFP-L3% + 0.04 × abnormal prothrombin data; The data recorder records the patient's risk value for liver cancer under dynamic monitoring in real time, and sets a risk value greater than or equal to 5 and less than or equal to 8 as low risk, a risk value greater than 8 and less than or equal to 10 as medium risk, and a risk value greater than 10 as high risk.

[0028] The risk assessment guidance unit is used to provide real-time risk assessment guidance based on the risk value. The guidance includes monitoring liver function, AFP and ultrasound operations every 6-12 months for low risk, monitoring AFP, ultrasound and CT / MRI operations every 3-6 months for medium risk, and CT / MRI and liver biopsy operations for high risk (the guidance operation here is only one of the means of liver cancer risk examination in the existing technology, and different examination means can be combined for assessment guidance here). It provides early warning of whether the patient is at risk of liver cancer based on the patient's physical condition, and performs real-time risk assessment on the physical conditions of different patients. When predicting the risk of liver cancer, it can provide early warning of whether the patient is at risk of liver cancer based on the patient's physical condition, and can perform real-time risk assessment on the physical conditions of different patients, so that the system can further reduce the limitations of use in predicting the progression of liver cancer.

[0029] In the present invention, a method for establishing a risk prediction model for liver cancer caused by hepatitis B cirrhosis first enters a multi-factor consideration module, collects data on hepatitis B cirrhosis risk warning from multiple populations, analyzes risk prediction results in real time based on different races and geographical ranges of multiple populations, and judges in real time whether there is a prediction deviation in risk prediction under multiple factors. When establishing a risk prediction model for liver cancer caused by hepatitis B cirrhosis, data on hepatitis B cirrhosis risk warning from multiple populations are collected, analyzes in real time whether risk prediction results are different based on different races and geographical ranges of multiple populations, and judges in real time whether there is a prediction deviation in risk prediction under multiple factors based on the results, so that the model is applicable according to different races and geographical ranges, the model can be fully applicable to all patients, reducing the limitations of the use of the risk prediction model, and combining the special risk factors of patients of specific races or regions to further increase the accuracy of the risk prediction model establishment; enters the latent risk analysis module, sets the risk prediction standard model in real time based on age, gender and hepatitis B virus load through liver cancer risk factors, and predicts liver cancer in real time based on the patient's health status, lifestyle, diet and genetic factors. Whether the cancer risk prediction model is biased, combined with the patient's health status, lifestyle, diet and genetic factors, the existing risk prediction model no longer focuses solely on known liver cancer risk factors, including age, gender and hepatitis B virus load, but can also fully consider the patient's overall health status, lifestyle, genetic factors, and combine hidden factors to predict the patient's liver cancer risk in real time, and can timely predict whether the patient has liver cancer risk based on multiple factors; enter the early warning assessment module, receive the risk prediction model combining explicit factors and latent factors in real time, and when predicting liver cancer risk, give early warning of whether liver cancer will occur based on the patient's physical condition, and perform real-time risk assessment on the physical conditions of different patients, when predicting liver cancer risk, give early warning of whether the patient has the risk of liver cancer based on the patient's physical condition, and perform real-time risk assessment on the physical conditions of different patients, so that the system can further reduce the limitations of use in predicting the progression of liver cancer, and can provide early corrective guidance to patients who may be at risk of liver cancer, further reducing the possibility of liver cancer risk.

[0030] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for establishing a risk prediction model for liver cancer in patients with hepatitis B cirrhosis, characterized in that: The method comprises the following steps: Step 1: Enter the multi-factor consideration module, collect data on hepatitis B cirrhosis risk warnings from various populations, analyze risk prediction results in real time based on the different ethnicities and geographical ranges of these populations, and determine in real time whether there are any prediction biases in risk predictions under various factors; Step 2: Enter the latent risk analysis module and set a risk prediction standard model in real time based on liver cancer risk factors, age, gender, and hepatitis B virus load. Combined with the patient's health status, lifestyle, diet, and genetic factors, a real-time multi-factor prediction is performed to determine if the liver cancer risk prediction model is biased. Step 3: Enter the early warning assessment module and receive the risk prediction model combining explicit and implicit factors in real time. When predicting the risk of liver cancer, it will provide early warning of whether liver cancer will occur based on the patient's physical condition, and conduct real-time risk assessment of the physical conditions of different patients.

2. The method according to claim 1, wherein: The multi-factor consideration module includes a multi-population data collection unit, a real-time risk analysis unit, and a multi-factor judgment unit; The multiple population data collection unit is used to collect data for hepatitis B cirrhosis risk warning from multiple populations in real time through a data collector. The multiple populations include people of different races and people from different geographical areas. The data for hepatitis B cirrhosis risk warning from people of different races and people from different geographical areas include age, gender and hepatitis B virus load, and are recorded in real time through a data recorder.

3. The method according to claim 2, wherein: The real-time risk analysis unit is used to analyze in real time whether the risk prediction results are different according to the different races and geographical ranges of multiple populations, and obtain the difference value of the risk prediction results of two different races and geographical ranges. , the calculation formula is as follows: ； in, Indicates the difference in risk prediction results between two different races and geographical ranges, Represents risk data for different ethnic and geographic areas, and Represents the risk standard deviation of two different ethnic groups and geographical ranges, and Represents two different races and geographical ranges of recorded data, including age, gender and hepatitis B virus load, recorded data represents dominant factors, set the risk prediction result standard difference threshold, if If the absolute value of is greater than the standard difference threshold, it means that the risk prediction results of the two different races and geographical ranges are different. If not, it means that the risk prediction results of the two different races and geographical ranges are the same.

4. The method according to claim 3, wherein: The multi-factor judgment unit is used to judge in real time whether there is a prediction deviation in the risk prediction under multiple factors based on the results. The prediction method is as follows: Step 1: Calculate the risk prediction deviation value under various factors , the calculation formula is as follows: ； in, Indicates the risk prediction deviation value under multiple factors. represents the number of factors, Indicates averaging the total absolute deviations, represents the sum of the absolute deviations of all factors, Indicates the The predicted value of a factor, It is The actual value of the factor, It is The absolute deviation of each factor sets the standard difference threshold. If If the absolute value of is greater than the standard difference threshold, it means that the risk prediction under multiple factors has a prediction bias. If not, it means that the risk prediction under multiple factors has no prediction bias.

5. The method according to claim 1, wherein: The implicit risk analysis module includes a standard risk prediction model unit, an implicit factor unit and an implicit factor prediction unit; The standard risk prediction model unit is used to combine historical data and multiple liver cancer risk factors, and to set a risk prediction standard model based on age, gender and hepatitis B virus load. The risk prediction standard model is determined based on different ages, different genders and different hepatitis B virus loads.

6. The method according to claim 5, characterized in that: The latent factor cycle unit is used to predict liver cancer risk in combination with the life cycle of latent factors, where the latent factors include the patient's health status, lifestyle, diet and genetic factors.

7. The method according to claim 6, characterized in that: The latent factor prediction unit is used to calculate the predicted risk value of liver cancer in the life cycle at different ages by combining the latent factors. , the calculation formula is as follows: ； in, Represents the life cycle at different ages, that is, the length of the time stage, T represents different ages, It represents the instantaneous risk rate of liver cancer at stage length t. The patient's health status, lifestyle, diet and genetic factors are combined to calculate whether the life cycle liver cancer prediction risk values under multiple factors are the same. If the difference is greater than the standard threshold, it means that there is a deviation in the multi-factor prediction model of liver cancer risk and there is a risk of liver cancer. If not, it means that there is no deviation in the multi-factor prediction model of liver cancer risk and there is no risk of liver cancer. The life cycle liver cancer prediction risk results at different ages are recorded and stored in real time through a data recorder.

8. The method according to claim 1, wherein: The early warning assessment module includes a data receiving unit, a multi-factor early warning risk unit and a risk assessment guidance unit; The data receiving unit is used to receive risk prediction results combining explicit factors and implicit factors in real time through a data receiver.

9. The method according to claim 8, characterized in that: The multi-factor early warning risk unit is used to warn the patient in advance of whether he or she is at risk of developing liver cancer based on the patient's physical condition. The early warning method is as follows: Dynamically monitor the patient's risk of liver cancer by combining the patient's age, gender, AFP, AFP-L3% and abnormal prothrombin data; The data recorder records the patient's risk value for liver cancer under dynamic monitoring in real time, and sets a risk value greater than or equal to 5 and less than or equal to 8 as low risk, a risk value greater than 8 and less than or equal to 10 as medium risk, and a risk value greater than 10 as high risk.

10. The method according to claim 9, characterized in that: The risk assessment guidance unit is used to provide risk assessment guidance in real time according to the risk value.

Images