Liver metastasis monitoring system based on big data

Abstract

The invention discloses a liver metastasis monitoring system based on big data, belongs to the technical field of medical treatment, and aims to solve the problems of high subjectivity, low accuracy and difficulty in meeting the requirements of clinical precision medical treatment when the clinical symptoms of a patient are pre-estimated, and the liver metastasis monitoring system comprises a data acquisition and integration module and a data preprocessing module, a liver metastasis risk prediction model construction module, a real-time risk assessment and early warning module and a decision assistance and suggestion module; through big data analysis and a machine learning algorithm, accurate prediction of the liver metastasis risk is realized, the diagnosis accuracy is improved, high-risk patients are found in time, accurate prediction and early warning of the liver metastasis risk of the patients are realized, and improvement of the early discovery rate and the treatment success rate of liver metastasis is facilitated; through an automatic processing flow, manual operation is reduced, unnecessary image examination is reduced, economic burden of a patient is reduced, doctor-patient contradiction is relieved, and patient management efficiency and service quality are improved.

Description

Technical Field

[0001] The present invention belongs to the field of medical technology, and in particular relates to a liver metastasis monitoring system based on big data. Background Art

[0002] Liver metastasis refers to the transfer of malignant tumors to the liver through the blood circulation. Tumors can occur in organs or tissues of the human body, including malignant tumors, mainly cancers and sarcomas, such as gastric cancer, colon cancer, etc., and also benign tumors, such as hemangiomas, hamartomas, etc. Malignant tumors may metastasize, including liver metastasis, lymph node metastasis, bone metastasis, etc., while benign tumors generally do not metastasize. When a malignant tumor appears in the body, the cells invade the surrounding tissues, which is called invasive growth. Malignant tumors have more blood vessels, and the blood vessels are relatively rich. Tumor cells may reach the liver through the blood circulation and cause liver metastasis. When liver metastasis occurs, tumors may appear in the liver, often multiple tumors, with an uneven surface and unclear boundaries. If enhanced CT or enhanced MRI examination is performed, liver metastases can be seen to show target signs or bull's eye signs. This is the characteristic of liver metastases and an important basis for judging liver metastasis.

[0003] Liver metastasis is a common complication of many malignant tumors. Its early detection and timely intervention are of great significance to improving the survival rate of patients. In addition, early prediction and detection of liver metastasis will effectively reduce the pain of patients and medical costs. However, when predicting whether liver metastasis will occur, it is mainly estimated based on the patient's clinical symptoms, which has the disadvantages of strong subjectivity and insufficient accuracy, and it is difficult to meet the needs of clinical precision medicine.

[0004] Therefore, a liver metastasis monitoring system based on big data is needed to solve the problem that the existing technology uses the patient's clinical symptoms to make predictions, which is highly subjective and inaccurate, and is difficult to meet the needs of clinical precision medicine. Summary of the invention

[0005] The purpose of the present invention is to provide a liver metastasis monitoring system based on big data to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: a liver metastasis monitoring system based on big data, comprising:

[0007] The data acquisition and integration module is used to collect multi-source heterogeneous data such as the patient's basic information, medical history, laboratory tests, and imaging examinations, and integrate molecular data such as biomarkers and genetic variations to form a comprehensive patient health record, which includes an information acquisition unit, a data integration unit, and a data storage unit;

[0008] The data preprocessing module is used to preprocess the data in the patient monitoring file to ensure the consistency of the data, including a data cleaning unit, a data conversion unit, and a feature selection unit;

[0009] The liver metastasis risk prediction model construction module builds a liver metastasis risk prediction model based on historical archive data, predicts the probability of liver metastasis, and obtains the liver metastasis risk prediction result, which includes a variable selection unit, a model construction unit, a model evaluation unit, and a result output unit;

[0010] A real-time risk assessment and early warning module, which assesses and warns the liver metastasis risk based on the predicted results, and includes a risk assessment unit and an early warning unit;

[0011] The decision assistance and advice module provides personalized treatment recommendations and decision support based on risk prediction results, provides a reference for doctors to formulate treatment plans, uses the clinical decision support system to further verify and optimize the treatment recommendations, and presents the treatment recommendations and decision support information to doctors in a clear and easy-to-understand manner. Doctors formulate specific treatment plans and put them into practice based on the treatment recommendations and decision support information.

[0012] It should be noted in the scheme that the information acquisition unit is used to obtain the patient's medical record data from the hospital information system;

[0013] The data integration unit is used to merge, associate and integrate the acquired medical record data according to certain rules to form a unified format and standard, including processing the problems of inconsistent data formats and timestamp alignment;

[0014] The data storage unit is used to store the integrated data in a suitable data warehouse or database for subsequent data processing and analysis.

[0015] It is further worth noting that the data cleaning unit is used to perform a deeper cleaning on the integrated data, including processing missing values, outliers, and noise data;

[0016] The data conversion unit is used to normalize the cleaned data;

[0017] The feature selection unit is used to select features useful for liver metastasis risk prediction from the normalized data.

[0018] Among them, normalization is a method of converting dimensional data into dimensionless data expression, which aims to simplify the calculation process so that indicators of different units or magnitudes can be compared and weighted. The core purpose of normalization is to summarize the statistical distribution of unified samples and ensure the consistency and comparability of data processing. Through normalization, data can be mapped to a specific range, such as between 0 and 1, or between -1 and 1, which helps to avoid unnecessary numerical problems in the data processing process, speed up the convergence of the program at runtime, and unify the evaluation criteria.

[0019] It should be further explained that the features useful for predicting the risk of liver metastasis selected from the normalized data include:

[0020] Clarify the meaning and type of each variable, including categorical variables such as sex and tumor type, and numerical variables such as age, tumor size, and laboratory test results;

[0021] For each categorical variable, a chi-square test was used to assess whether it was significantly associated with liver metastasis, including calculating the observed frequency and expected frequency; calculating the P value of the chi-square statistic; judging whether the categorical variable was significantly associated with liver metastasis based on the P value, usually P < 0.05 was considered significant; recording the P value and significance judgment results of each categorical variable;

[0022] For numerical variables, they were converted into categorical variables based on quartiles and then the chi-square test was applied;

[0023] By judging which variables are significantly associated with liver metastasis based on the P value, features useful for predicting the risk of liver metastasis can be selected.

[0024] In practical applications, the P value is usually compared with the significance level (such as 0.05 or 0.01). If the P value is less than the significance level, the result is considered statistically significant, that is, the observed difference is unlikely to be caused by chance factors, but has some substantial significance. On the contrary, if the P value is greater than the significance level, the result is usually considered insignificant, that is, the observed difference may be caused by random errors or accidental factors.

[0025] As a preferred embodiment, the variable selection unit is used to define dependent variables and independent variables, the dependent variable is a binary variable, indicating whether liver metastasis occurs (1) or not (0), and the independent variables may include age, gender, tumor type, tumor size, tumor grade, blood biochemical indicators, etc.;

[0026] The model building unit is used to fit the logistic regression model using statistical software. The software automatically calculates the coefficient β of each independent variable. These coefficients reflect the direction and intensity of the influence of the independent variable on the risk of liver metastasis. The form of the logistic regression model is as follows:

[0027]

[0028] Where, (p) is the probability of liver metastasis, (x1, x2...x m ) is the independent variable, (β1, β2...β m ) are the coefficients of the model (regression coefficients);

[0029] The model evaluation unit is used to evaluate the goodness of fit of the model, that is, the consistency between the model prediction value and the actual observation value, by the Hosmer-Lemeshow test method;

[0030] The result output unit is used to explain the coefficient of each independent variable and explain how it affects the risk of liver metastasis. A positive coefficient indicates that the factor increases the risk of liver metastasis, and a negative coefficient indicates that the risk is reduced. The model is used to calculate the probability of liver metastasis under given patient characteristics, that is, the patient's independent variable value is substituted into the model to calculate the corresponding probability value.

[0031] As a preferred embodiment, the goodness of fit of the model evaluated by the Hosmer-Lemeshow test method includes:

[0032] Arrange the predicted probabilities in the data set in ascending order and divide them into n groups;

[0033] For each group, the actual number of liver metastases observed and the average probability predicted by the model are calculated to obtain the expected number of liver metastases. The following statistical formula is usually used for testing:

[0034]

[0035] Where oi is the number of liver metastases actually observed in group i, e i is the expected number of liver metastases in group i, and n is the number of groups;

[0036] The calculated statistic X should be compared with a chi-square distribution with n-2 degrees of freedom, since there are two parameters estimated in the model, usually the intercept and a probability. If the calculated X is significantly less than the chi-square critical value, it means that the model fits the observed data well, i.e., there are no significant differences.

[0037] As a preferred embodiment, the risk assessment unit automatically generates a risk level assessment report including risk probability and risk level information based on the risk prediction result obtained by inputting the prediction model into the data of the current patient;

[0038] Early warning unit: When a high risk is predicted, the system automatically sends out an early warning signal to remind doctors and patients to pay close attention and take appropriate medical measures.

[0039] As a preferred implementation, the warning method may be, but is not limited to, text messages, emails, or message push.

[0040] Compared with the prior art, the liver metastasis monitoring system based on big data provided by the present invention has at least the following beneficial effects:

[0041] Through big data analysis and machine learning algorithms, accurate prediction of liver metastasis risk can be achieved, diagnostic accuracy can be improved, and high-risk patients can be identified in a timely manner. Accurate prediction and early warning of liver metastasis risk can be achieved, which will help improve the early detection rate and treatment success rate of liver metastasis. Automated processing can reduce manual operations, unnecessary imaging examinations, and the economic burden on patients, alleviate doctor-patient conflicts, and improve patient management efficiency and service quality. At the same time, it can also provide doctors with objective and quantitative risk prediction results to assist them in formulating more scientific and reasonable treatment plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is a block diagram of a liver metastasis monitoring system based on big data of the present invention; DETAILED DESCRIPTION

[0043] The present invention will be further described below in conjunction with the embodiments.

[0044] Reference Figure 1 As shown, the present invention provides a liver metastasis monitoring system based on big data, comprising:

[0045] The data acquisition and integration module is used to collect multi-source heterogeneous data such as the patient's basic information, medical history, laboratory tests, and imaging examinations, and integrate molecular data such as biomarkers and genetic variations to form a comprehensive patient health record, which includes an information acquisition unit, a data integration unit, and a data storage unit;

[0046] The data preprocessing module is used to preprocess the data in the patient monitoring file to ensure the consistency of the data, including a data cleaning unit, a data conversion unit, and a feature selection unit;

[0047] The liver metastasis risk prediction model construction module builds a liver metastasis risk prediction model based on historical archive data, predicts the probability of liver metastasis, and obtains the liver metastasis risk prediction result, which includes a variable selection unit, a model construction unit, a model evaluation unit, and a result output unit;

[0048] A real-time risk assessment and early warning module, which assesses and warns the liver metastasis risk based on the predicted results, and includes a risk assessment unit and an early warning unit;

[0049] The decision assistance and advice module provides personalized treatment recommendations and decision support based on risk prediction results, provides a reference for doctors to formulate treatment plans, uses the clinical decision support system to further verify and optimize the treatment recommendations, and presents the treatment recommendations and decision support information to doctors in a clear and easy-to-understand manner. Doctors formulate specific treatment plans and put them into practice based on the treatment recommendations and decision support information.

[0050] Specifically, the information acquisition unit is used to acquire the patient's medical record data from the hospital information system;

[0051] The data integration unit is used to merge, associate and integrate the acquired medical record data according to certain rules to form a unified format and standard, including processing the problems of inconsistent data formats and timestamp alignment;

[0052] The data storage unit is used to store the integrated data in a suitable data warehouse or database for subsequent data processing and analysis.

[0053] Specifically, the data cleaning unit is used to perform more in-depth cleaning on the integrated data, including processing missing values, outliers, and noise data;

[0054] The data conversion unit is used to normalize the cleaned data;

[0055] The feature selection unit is used to select features useful for liver metastasis risk prediction from the normalized data.

[0056] Among them, normalization is a method of converting dimensional data into dimensionless data expression, which aims to simplify the calculation process so that indicators of different units or magnitudes can be compared and weighted. The core purpose of normalization is to summarize the statistical distribution of unified samples and ensure the consistency and comparability of data processing. Through normalization, data can be mapped to a specific range, such as between 0 and 1, or between -1 and 1, which helps to avoid unnecessary numerical problems in the data processing process, speed up the convergence of the program at runtime, and unify the evaluation criteria.

[0057] It can be understood that the features useful for predicting the risk of liver metastasis selected from the normalized data include:

[0058] Clarify the meaning and type of each variable, including categorical variables such as sex and tumor type, and numerical variables such as age, tumor size, and laboratory test results;

[0059] For each categorical variable, a chi-square test was used to assess whether it was significantly associated with liver metastasis, including calculating the observed frequency and expected frequency; calculating the P value of the chi-square statistic; judging whether the categorical variable was significantly associated with liver metastasis based on the P value, usually P < 0.05 was considered significant; recording the P value and significance judgment results of each categorical variable;

[0060] For numerical variables, they were converted into categorical variables based on quartiles and then the chi-square test was applied;

[0061] By judging which variables are significantly associated with liver metastasis based on the P value, features useful for predicting the risk of liver metastasis can be selected.

[0062] Among them, the P value, also known as the assumed value or hypothesis probability, is an important parameter used in statistics to determine the results of hypothesis testing. It was first proposed by R.A. Fisher and used in inferential statistics, especially in hypothesis testing. The definition of the P value is: the probability of the observed sample results and more extreme situations occurring under the premise that the original hypothesis (null hypothesis) is true.

[0063] In practical applications, the P value is usually compared with the significance level (such as 0.05 or 0.01). If the P value is less than the significance level, the result is considered statistically significant, that is, the observed difference is unlikely to be caused by chance factors, but has some substantial significance. On the contrary, if the P value is greater than the significance level, the result is usually considered insignificant, that is, the observed difference may be caused by random errors or accidental factors.

[0064] The chi-square test is a statistical method used to determine whether the difference between observed data and expected data is significant. It is suitable for the analysis of categorical data, especially for comparing the difference between observed frequency and expected frequency.

[0065] When performing a chi-square test, a statistic is usually calculated, called the chi-square statistic. This statistic measures the degree of deviation between the observed frequency and the expected frequency. If the difference between the observed frequency and the expected frequency is significantly greater than the expected random error, it can be concluded that the two sets of data are statistically significantly different.

[0066] Specifically, the variable selection unit is used to identify dependent variables and independent variables, the dependent variable is a binary variable, indicating whether liver metastasis occurs (1) or not (0), and the independent variables may include age, gender, tumor type, tumor size, tumor grade, blood biochemical indicators, etc.;

[0067] The model building unit is used to fit the logistic regression model using statistical software. The software automatically calculates the coefficient β of each independent variable. These coefficients reflect the direction and intensity of the influence of the independent variable on the risk of liver metastasis. The form of the logistic regression model is as follows:

[0068]

[0069] Where, (p) is the probability of liver metastasis, (x1, x2...x m ) is the independent variable, (β1, β2...β m ) are the coefficients of the model (regression coefficients);

[0070] The model evaluation unit is used to evaluate the goodness of fit of the model, that is, the consistency between the model prediction value and the actual observation value, by the Hosmer-Lemeshow test method;

[0071] The result output unit is used to explain the coefficient of each independent variable and explain how it affects the risk of liver metastasis. A positive coefficient indicates that the factor increases the risk of liver metastasis, and a negative coefficient indicates that the risk is reduced. The model is used to calculate the probability of liver metastasis under given patient characteristics, that is, the patient's independent variable value is substituted into the model to calculate the corresponding probability value.

[0072] Specifically, the goodness of fit of the model evaluated by the Hosmer-Lemeshow test method includes:

[0073] Arrange the predicted probabilities in the data set in ascending order and divide them into n groups;

[0074] For each group, the actual number of liver metastases observed and the average probability predicted by the model are calculated to obtain the expected number of liver metastases. The following statistical formula is usually used for testing:

[0075]

[0076] Among them, is the number of liver metastases actually observed in group i, is the expected number of liver metastases in group i, and n is the number of groups;

[0077] The calculated statistic X should be compared with a chi-square distribution with n-2 degrees of freedom, since there are two parameters estimated in the model, usually the intercept and a probability. If the calculated X is significantly less than the chi-square critical value, it means that the model fits the observed data well, i.e., there are no significant differences.

[0078] Among them, the Hosmer-Lemeshow test (HL test) is a commonly used method to evaluate the goodness of fit of the logistic regression model on the observed data. It mainly focuses on the difference between the model predicted value and the actual observed value, especially the difference at different risk levels.

[0079] It is understandable that the risk assessment unit automatically generates a risk level assessment report including risk probability and risk level information based on the risk prediction result obtained by inputting the prediction model into the data of the current patient;

[0080] The early warning unit is used to automatically send out an early warning signal when a high risk is predicted, so as to remind doctors and patients to pay close attention and take corresponding medical measures.

[0081] The warning method may be, but is not limited to, text messages, emails, message push, or voice calls.

[0082] The early warning methods can be very flexible and diverse in the liver metastasis risk prediction and monitoring system based on big data, far more than SMS, email and message push. SMS notifications have the characteristics of high penetration rate and stable reception rate, which can ensure that most users can receive early warning information in time. Emails are suitable for sending detailed reports or periodic summaries, but the real-time reception is weak. It is suitable for users who have installed relevant applications or logged in to the online platform, and can achieve instant and personalized notifications. Voice calls are suitable for emergency situations where patients or doctors need to be contacted immediately.

[0083] The usage process of the above-mentioned liver metastasis monitoring system based on big data is as follows:

[0084] Step 1: The data collection and integration module receives instructions and obtains the patient's medical record data from the hospital information system through the information acquisition unit. The data integration unit merges, associates and integrates the obtained medical record data according to certain rules to form a unified format and standard. The data storage unit is then used to store the integrated data in a suitable database for subsequent data processing and analysis.

[0085] Step 2: The integrated data is transmitted to the data preprocessing module, and the integrated data is further cleaned by the data cleaning unit, and then the cleaned data is normalized by the data conversion unit. The normalized data is filtered out by the feature rotation unit to obtain features useful for liver metastasis risk prediction;

[0086] Step 3: Input the features related to liver metastasis risk prediction into the liver metastasis risk prediction model, calculate the corresponding probability value, and output the corresponding risk prediction result;

[0087] Step 4: Based on the risk prediction results, a risk level assessment report is automatically generated through the risk assessment unit. When a high risk is predicted, the early warning unit automatically sends out an early warning signal to remind doctors and patients to pay close attention and take corresponding medical measures.

[0088] In summary, the advantages of the present invention are: through big data analysis and machine learning algorithms, accurate prediction of liver metastasis risk can be achieved, diagnostic accuracy can be improved, high-risk patients can be discovered in time, and accurate prediction and early warning of liver metastasis risk can be achieved, which will help improve the early detection rate and treatment success rate of liver metastasis; through automated processing procedures, manual operations can be reduced, unnecessary imaging examinations can be reduced, the economic burden on patients can be reduced, doctor-patient conflicts can be alleviated, patient management efficiency and service quality can be improved, and at the same time, objective and quantitative risk prediction results can be provided to doctors to assist them in formulating more scientific and reasonable treatment plans.

[0089] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. Liver metastasis monitoring system based on big data, characterized by: include: The data acquisition and integration module is used to collect multi-source heterogeneous data such as the patient's basic information, medical history, laboratory tests, and imaging examinations, and integrate molecular data such as biomarkers and genetic variations to form a comprehensive patient health record, which includes an information acquisition unit, a data integration unit, and a data storage unit; The data preprocessing module is used to preprocess the data in the patient monitoring file to ensure the consistency of the data, including a data cleaning unit, a data conversion unit, and a feature selection unit; The liver metastasis risk prediction model construction module builds a liver metastasis risk prediction model based on historical archive data, predicts the probability of liver metastasis, and obtains the liver metastasis risk prediction result, which includes a variable selection unit, a model construction unit, a model evaluation unit, and a result output unit; A real-time risk assessment and early warning module, which assesses and warns the liver metastasis risk based on the predicted results, and includes a risk assessment unit and an early warning unit; The decision assistance and advice module provides personalized treatment recommendations and decision support based on risk prediction results, provides a reference for doctors to formulate treatment plans, uses the clinical decision support system to further verify and optimize the treatment recommendations, and presents the treatment recommendations and decision support information to doctors in a clear and easy-to-understand manner. Doctors formulate specific treatment plans and put them into practice based on the treatment recommendations and decision support information.

2. The liver metastasis monitoring system based on big data according to claim 1, characterized in that: The information acquisition unit is used to acquire the patient's medical record data from the hospital information system; The data integration unit is used to merge, associate and integrate the acquired medical record data according to certain rules to form a unified format and standard, including processing the problems of inconsistent data formats and timestamp alignment; The data storage unit is used to store the integrated data in a suitable data warehouse or database for subsequent data processing and analysis.

3. The liver metastasis monitoring system based on big data according to claim 2, characterized in that: The data cleaning unit is used to perform more in-depth cleaning on the integrated data, including processing missing values, outliers, and noise data; The data conversion unit is used to normalize the cleaned data; The feature selection unit is used to select features useful for liver metastasis risk prediction from the normalized data.

4. The liver metastasis monitoring system based on big data according to claim 3, characterized in that: The features useful for predicting the risk of liver metastasis selected from the normalized data include: Clarify the meaning and type of each variable, including categorical variables such as sex and tumor type, and numerical variables such as age, tumor size, and laboratory test results; For each categorical variable, a chi-square test was used to assess whether it was significantly associated with liver metastasis, including calculating the observed frequency and expected frequency; calculating the P value of the chi-square statistic; judging whether the categorical variable was significantly associated with liver metastasis based on the P value, usually P < 0.05 was considered significant; recording the P value and significance judgment results of each categorical variable; For numerical variables, they were converted into categorical variables based on quartiles and then the chi-square test was applied; By judging which variables are significantly associated with liver metastasis based on the P value, features useful for predicting the risk of liver metastasis can be selected.

5. The liver metastasis monitoring system based on big data according to claim 4, characterized in that: The variable selection unit is used to identify dependent variables and independent variables, the dependent variable is a binary variable, indicating whether liver metastasis occurs (1) or not (0), and the independent variables may include age, gender, tumor type, tumor size, tumor grade, blood biochemical indicators, etc.; The model building unit is used to fit the logistic regression model using statistical software. The software automatically calculates the coefficient β of each independent variable. These coefficients reflect the direction and intensity of the influence of the independent variable on the risk of liver metastasis. The form of the logistic regression model is as follows: Where, (p) is the probability of liver metastasis, (x1, x2...x m ) is the independent variable, (β1, β2...β m ) are the coefficients of the model (regression coefficients); The model evaluation unit is used to evaluate the goodness of fit of the model, that is, the consistency between the model prediction value and the actual observation value, by the Hosmer-Lemeshow test method; The result output unit is used to explain the coefficient of each independent variable and explain how it affects the risk of liver metastasis. A positive coefficient indicates that the factor increases the risk of liver metastasis, and a negative coefficient indicates that the risk is reduced. The model is used to calculate the probability of liver metastasis under given patient characteristics, that is, the patient's independent variable value is substituted into the model to calculate the corresponding probability value.

6. The liver metastasis monitoring system based on big data according to claim 5, characterized in that: The Hosmer-Lemeshow test method is used to evaluate the goodness of fit of the model, including: Arrange the predicted probabilities in the data set in ascending order and divide them into n groups; For each group, the actual number of liver metastases observed and the average probability predicted by the model are calculated to obtain the expected number of liver metastases. The following statistical formula is usually used for testing: Among them, i is the number of liver metastases actually observed in group i, e i is the expected number of liver metastases in group i, and n is the number of groups; The calculated statistic X should be compared with a chi-square distribution with n-2 degrees of freedom, since there are two parameters estimated in the model, usually the intercept and a probability. If the calculated X is significantly less than the chi-square critical value, it means that the model fits the observed data well, i.e., there are no significant differences.

7. The liver metastasis monitoring system based on big data according to claim 6, characterized in that: The risk assessment unit automatically generates a risk level assessment report including risk probability and risk level information based on the risk prediction result obtained by inputting the prediction model into the data of the current patient; The early warning unit is used to automatically send out an early warning signal when a high risk is predicted, so as to remind doctors and patients to pay close attention and take corresponding medical measures.

8. The liver metastasis monitoring system based on big data according to claim 7, characterized in that: The warning method may be, but is not limited to, text messages, emails, message push, or voice calls.

Images