Detection system for prognosis risk of liver cirrhosis

Abstract

The invention relates to the technical field of medical information processing, in particular to a liver cirrhosis prognosis risk detection system. After the system detects the liver of the patient every time, the image cirrhosis risk can be quantified from the morphological change of the liver area by using the image data. And determining the disease progress index according to the difference between the actual detection data and the prediction data and the non-standardization degree of the prognosis response. And determining the drug adjustment degree by using the drug adjustment data so as to obtain the liver cirrhosis progression index. And quantizing the data hysteresis lag and liver cirrhosis progression index to jointly adjust the detection frequency of the system. The system can effectively respond to the illness state of a patient, and an effective early warning signal is generated when detection is needed to remind medical staff to conduct liver detection.

Description

Technical Field

[0001] The present invention relates to the technical field of medical information processing, and in particular to a liver cirrhosis prognosis risk detection system. Background Art

[0002] The prognosis assessment for cirrhosis requires comprehensive consideration of multiple data including the patient's clinical presentation, laboratory test results, imaging studies, and pathological changes. Existing cirrhosis prognosis management systems can assess and provide early warnings for patients through processes such as data collection, data preprocessing, feature extraction, and dynamic monitoring and early warning. However, due to inappropriate settings for patient testing frequency, key liver lesion data is not promptly detected, leading to an inaccurate assessment of the patient's risk of an abnormal cirrhosis prognosis, which is not conducive to improving patient prognosis and reducing the risk of complications. Summary of the Invention

[0003] In order to solve the technical problem in existing liver cirrhosis prognosis risk assessment and early warning systems, where unreasonable detection frequency settings lead to failure to timely detect key liver lesion data, thereby incorrectly assessing the patient's abnormal liver cirrhosis prognosis risk, the present invention aims to provide a liver cirrhosis prognosis risk detection system. The technical solutions adopted are as follows:

[0004] The present invention proposes a liver cirrhosis prognosis risk detection system, which includes:

[0005] A liver image data analysis module is used to obtain the risk of liver cirrhosis in each detection process based on the area change and edge roughness of the liver region in the liver image between adjacent detection processes;

[0006] A cirrhosis disease progression analysis module is used to obtain the patient's test data during each test process; use a pre-trained prediction neural network to obtain predicted data corresponding to the test data; obtain the patient's state deviation index during each test process based on the difference between the predicted data and the test data; obtain the complication risk of each test process based on the state deviation index and the prognostic response irregularity calculated in the prognostic follow-up system, and obtain the disease progression index of each test process in combination with the image cirrhosis risk;

[0007] A drug adjustment impact analysis module is used to obtain a drug adjustment degree based on the difference in drug types before each test process compared to the drug types in the previous test process; and to obtain a liver cirrhosis malignancy progression index under each test process based on the drug adjustment degree and the disease progression index;

[0008] The system data hysteresis analysis module is used to calculate the changes in the cirrhosis progression index and the detection frequency between all adjacent historical detection processes during each detection process; the system data hysteresis is obtained based on the asynchrony between the changes in the cirrhosis progression index and the changes in the detection frequency;

[0009] The system detection frequency correction module is used to adjust the system detection frequency according to the liver cirrhosis progression index and the data hysteresis in each detection process.

[0010] Furthermore, the detection data includes a physiological data sequence and a physiological data health score; the predicted data includes a predicted physiological data sequence and a predicted physiological data health score; the Euclidean distance between the physiological data sequence and the predicted physiological data sequence is obtained; the score difference between the predicted physiological health score and the physiological data health score is obtained, and the product of the score difference and the Euclidean distance is used as the state deviation index.

[0011] Furthermore, the method for obtaining the risk of liver cirrhosis by imaging includes:

[0012] For the current detection process, the liver area of ​​the current detection process is used as the denominator, and the liver area of ​​the previous detection process is used as the numerator to obtain the area contrast feature; the edge roughness of the liver area of ​​the current detection process is used as the numerator, and the edge roughness of the liver area of ​​the previous detection process is used as the denominator to obtain the edge roughness contrast feature; the imaging cirrhosis risk is obtained based on the area contrast feature and the edge roughness contrast feature.

[0013] Furthermore, the method for obtaining the drug adjustment degree includes:

[0014] The number of drug types in the current detection process is used as the numerator, and the number of drug types that are the same between the current detection process and the previous detection process is used as the denominator to obtain the drug adjustment degree.

[0015] Furthermore, the method for obtaining the liver cirrhosis progression index includes:

[0016] The difference in disease progression index between each detection process and the previous detection process is obtained, and after normalizing the difference in disease progression index, the sum of the difference and the normalized drug adjustment degree is used as the liver cirrhosis malignant progression index.

[0017] Furthermore, the method for obtaining data hysteresis includes:

[0018] Selecting a preset number of consecutive historical detection processes from the current detection process forward; for each group of adjacent historical detection processes, obtaining the difference in liver cirrhosis malignant progression index and detection frequency between the two historical detection processes;

[0019] The difference in the average liver cirrhosis progression index of adjacent historical detection processes of all groups is used as the numerator, and the sum of the average detection frequency difference and the preset hyperparameter is used as the denominator, and the obtained ratio is the data hysteresis.

[0020] Furthermore, the adjusting of the system detection frequency according to the liver cirrhosis progression index and the data hysteresis in each detection process includes:

[0021] The cirrhosis progression index in each detection process and the data hysteresis are multiplied and normalized to obtain a correction coefficient;

[0022] If the correction coefficient is less than the preset threshold, the detection frequency is not adjusted; otherwise, an increase coefficient is obtained according to the correction coefficient, and the detection frequency is increased using the increase coefficient.

[0023] Furthermore, obtaining a growth coefficient according to the correction coefficient and increasing the detection frequency by using the growth coefficient includes:

[0024] The sum of the positive integer 1 and the correction coefficient is used as the growth coefficient, and the product of the growth coefficient and the detection frequency is used as the increased detection frequency.

[0025] Furthermore, the method for obtaining the prognostic response irregularity includes:

[0026] The patient's behavior execution record sequence counted in the follow-up system during each detection process is counted; each element in the behavior execution record sequence represents the patient's execution degree of the will behavior, and the element value includes valid execution and invalid execution, and the number of invalid executions is counted as the prognostic response irregularity.

[0027] Furthermore, the method for obtaining the disease progression index includes:

[0028] The relative difference between the imaging liver cirrhosis risk and the historical average imaging liver cirrhosis risk in each detection process is obtained, and the product of the relative difference and the complication risk is used as the disease progression index.

[0029] The present invention has the following beneficial effects:

[0030] After each liver scan, the present invention uses imaging data to quantify the risk of cirrhosis based on morphological changes in the liver region. The difference between the actual test data and the expected predicted data is used to determine a state deviation index. This is further combined with the prognostic response irregularity in the prognostic follow-up system to quantify the patient's prognostic data and behavioral abnormalities during each test. Furthermore, considering that medication adjustments during the patient's prognosis are crucial information, the medication adjustment data is used to determine the degree of medication adjustment, thereby obtaining a cirrhosis progression index. The cirrhosis progression index can be used to assess the patient's cirrhosis risk after each test, providing a reference for adjusting the system's testing frequency. Furthermore, considering the potential for system response lag, the slower the test frequency update, the greater the lag. Therefore, the quantified data lag and the cirrhosis progression index are used together to adjust the system's testing frequency, enabling the system to effectively respond to the patient's condition and generate an effective early warning signal to alert medical staff to perform liver tests when testing is necessary. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0032] Figure 1 This is a block diagram of a liver cirrhosis prognosis risk detection system provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0033] To further illustrate the technical means and effectiveness of the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementation, structure, features, and effectiveness of a liver cirrhosis prognosis risk detection system proposed in accordance with the present invention. In the following description, references to different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0034] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0035] The specific scheme of the liver cirrhosis prognosis risk detection system provided by the present invention is described in detail below with reference to the accompanying drawings.

[0036] See also Figure 1 , which shows a block diagram of a liver cirrhosis prognosis risk detection system provided by an embodiment of the present invention. The system includes: a liver imaging data analysis module 101, a liver cirrhosis disease progression analysis module 102, a drug adjustment impact analysis module 103, a system data hysteresis analysis module 104, and a system detection frequency correction module 105.

[0037] It should be noted that the embodiment of the present invention is intended to adjust the system's testing frequency based on the liver data collected during each test. Therefore, other modules in the system, such as data acquisition and data transmission, will not be described further. Existing data acquisition modules can be used to directly access the medical data obtained from each patient test in the hospital. The details will not be repeated here. The embodiment of the present invention primarily analyzes bilirubin indicators, transaminase levels, and liver images. Therefore, these three types of data can be directly accessed and processed in the system of the embodiment of the present invention.

[0038] Imaging examinations can provide non-invasive information on the anatomical structure and pathological changes of the liver, including liver size, liver surface smoothness, vascular conditions, and possible liver nodules or complications. The liver imaging data analysis module 101 analyzes the morphology of the liver region in the liver imaging data, selects the liver region area and the liver region edge roughness as imaging features for analysis, and can obtain the imaging cirrhosis risk under each detection process based on the area change of the liver region in the liver image between adjacent detection processes and the edge roughness. That is, the imaging cirrhosis risk represents the risk level of morphological changes in the liver region. If the liver is more atrophic and has irregular jagged edges in this detection compared to the previous detection, it means that the patient's cirrhosis is more advanced in this detection, and the imaging cirrhosis risk is greater.

[0039] The liver imaging data analysis module 101 obtains preliminary assessment results regarding changes in liver structure and function. These imaging features, such as reduced liver volume, surface irregularities, and portal vein dilation, indicate the progression of cirrhosis. However, the progression of liver disease is influenced not only by its own pathological changes but also by significant interference from the patient's medications, potentially leading to false positives in the assessment of cirrhosis progression.

[0040] This embodiment of the present invention further considers that the prognosis management system should pay attention to the orderly changes in the patient's condition. If the liver condition shows obvious malignant progression and irregular fluctuations during the prognosis process, it also indicates that the system's testing frequency needs to be increased and the patient needs more attention. Therefore, this embodiment of the present invention provides a cirrhosis disease progression analysis module 102, which obtains the patient's test data during each test process and uses a pre-trained predictive neural network to obtain predicted data corresponding to the test data. Based on the difference between the predicted data and the test data, the patient's state deviation index for each test process is calculated. In other words, the greater the difference between the two data, the more the patient's condition exceeds expectations during the actual process. The larger the state deviation index, the more frequent the patient's attention needs. The prognosis response irregularity in the prognosis follow-up system is further calculated. The prognosis response irregularity is the patient's compliance with the doctor's orders during the prognosis process. The greater the prognosis response irregularity, the less effective the patient's compliance with the doctor's orders, and the greater the risk. Therefore, the complication risk during each test process can be further calculated. Combined with the imaging cirrhosis risk, the disease progression index for each test process can be obtained. The larger the disease progression index, the more frequent the system's attention is needed.

[0041] During the patient's prognosis process, the patient's medication is usually adjusted based on the test results. The intensity of the drug adjustment can represent the patient's state stability at the current moment. The greater the intensity of the drug adjustment, the faster the response speed required for the detection system. Therefore, the drug adjustment impact analysis module 103 obtains the drug adjustment degree based on the difference in the type of drug before each detection process compared with the type of drug in the previous detection process. Further combined with the disease progression index, the liver cirrhosis progression index under each detection process can be obtained. That is, the liver cirrhosis progression index simultaneously represents the risk of liver excretion function, liver morphology risk, and the impact of drug adjustment. The larger the liver cirrhosis progression index, the more the detection system needs to increase the detection frequency for the patient.

[0042] In practical applications, the system may experience a response lag. This lag effect may prevent changes in the patient's condition from being promptly reflected in the early warning system, thus impacting clinical decision-making and timely intervention. For example, when a patient experiences changes in liver function due to medication adjustments, the system may not immediately capture these changes, resulting in a delay in the early warning signal. Furthermore, a patient's physiological state can fluctuate rapidly. If the system cannot quickly adapt to these changes, risk assessment may be inaccurate and untimely. Therefore, during each test, the system data lag analysis module 104 calculates the changes in the cirrhosis progression index between all adjacent historical test processes, as well as the changes in the detection frequency between adjacent historical test processes. The greater the asynchrony between these two changes, meaning the detection frequency fails to effectively respond to the larger changes in the cirrhosis progression index, the greater the system data lag during that test process. Therefore, the data lag is further quantified, allowing the system detection frequency correction module 105 to adjust the system detection frequency based on the cirrhosis progression index and data lag during each test process. A reasonable and effective detection frequency can avoid missed detections of patients' liver data and improve prognosis.

[0043] In summary, after each test of the patient's liver by the system, the present invention can quantify the risk of imaging cirrhosis from the morphological changes in the liver area using imaging data. The disease progression index is determined based on the difference between the actual test data and the predicted data, as well as the degree of irregularity in the prognostic response. The drug adjustment degree is determined using the drug adjustment data, and then the cirrhosis malignant progression index is obtained. The data hysteresis hysteresis and the cirrhosis malignant progression index are quantified to jointly adjust the detection frequency of the system. The present invention enables the system to effectively respond to the patient's condition and generate an effective early warning signal to remind medical staff to perform liver testing when testing is required.

[0044] Preferably, in an embodiment of the present invention, the detection data includes a physiological data sequence and a physiological data health score; the predicted data includes a predicted physiological data sequence and a predicted physiological data health score; the Euclidean distance between the physiological data sequence and the predicted physiological data sequence is obtained; the score difference between the predicted physiological health score and the physiological data health score is obtained, and the product of the score difference and the Euclidean distance is used as the state deviation index.

[0045] As a specific example, the physiological data sequence in the embodiment of the present invention may specifically include various biochemical indicators of the liver, laboratory test data, medical behavior, clinical time and other types, such as bilirubin, transaminase content, heart rate, blood pressure, etc., which can be set according to the system requirements and will not be elaborated here. It should be noted that the physiological data health score is also a score obtained by the system using an existing scoring system or a doctor's judgment. The larger the physiological data health score, the better the patient's liver function has recovered. These scoring systems can quantify the state of liver function, help identify high-risk patients, and help doctors estimate the prognosis of patients, thereby providing more reliable data support for treatment plans or intervention plans. The specific details are also well known to those skilled in the art and will not be elaborated or limited here.

[0046] The neural network used in the embodiment of the present invention is an LSTM neural network. In other embodiments of the present invention, a Transformer network model may also be used. The specific model training method is well known to those skilled in the art and is not described in detail here. The input of the prediction neural network is the physiological data sequence and physiological data health score obtained during a single test process, and the output is the predicted physiological data sequence and predicted physiological data health score.

[0047] As a specific example, the state deviation index in the embodiment of the present invention is expressed by the formula:

[0048] Among them, d a is the state deviation index under the a-th detection process, M' a is the predicted physiological health score of the ath detection process, M a is the physiological health score of the ath detection process, H' a is the predicted physiological data sequence under the a-th detection process, H a is the physiological data sequence of the ath detection process, ||H' a -H a || represents the Euclidean distance between the two sequences. In this formula, the score difference is expressed as a ratio. A larger ratio indicates that the predicted physiological health score is significantly greater than the actual physiological health score, indicating that the patient's postoperative condition has not met expectations, and the state deviation index is larger. A larger Euclidean distance also indicates that the patient's postoperative condition has not met expectations, and the state deviation index is larger.

[0049] Preferably, in an embodiment of the present invention, the method for obtaining the risk of liver cirrhosis by imaging includes:

[0050] For the current test, the liver area during the current test is used as the denominator, and the liver area during the previous test is used as the numerator to obtain the area contrast feature. A larger area contrast feature indicates that the area during the current test is smaller than that during the previous test, indicating liver atrophy and a higher risk of cirrhosis.

[0051] The edge roughness of the liver region during the current test is used as the numerator, and the edge roughness of the liver region during the previous test is used as the denominator to obtain the edge roughness contrast feature. A larger edge roughness contrast feature indicates that the edge roughness of the liver region during the current test is rougher than that during the previous test, and the risk of liver cirrhosis is expected to be greater.

[0052] The risk of liver cirrhosis of the image is obtained based on the area contrast feature and the edge roughness contrast feature. In the embodiment of the present invention, the product of the area contrast feature and the edge roughness contrast feature is used as the risk of liver cirrhosis of the image.

[0053] Preferably, in an embodiment of the present invention, the method for obtaining edge roughness includes:

[0054] The curvature of each edge point on the edge of the liver region is obtained, and the variance of the curvature is used as the edge roughness. The variance represents the uniformity of the data distribution. Therefore, a larger variance indicates a more uneven curvature distribution, a more obvious jagged feature, and a greater edge roughness.

[0055] Preferably, in an embodiment of the present invention, the method for obtaining the prognostic response irregularity includes:

[0056] The patient's behavior execution record sequence counted in the follow-up system during each detection process is counted; each element in the behavior execution record sequence represents the patient's execution degree of the will behavior, and the element value includes valid execution and invalid execution, and the number of invalid executions is counted as the prognostic response irregularity.

[0057] As a specific example, in an embodiment of the present invention, the execution record sequence is obtained by statistics of the follow-up system, which can record various data during the patient follow-up process. For example, during the current patient's prognosis monitoring process (including historical data), the doctor's order execution time series (such as prescription issuance time, medication check-in record) is obtained, and the data can be obtained by the smart medicine box or the follow-up platform; the biochemical examination execution rate (whether the necessary examinations are completed on time) can be obtained by the LIS inspection system or the physical examination center data interface; the physical sign measurement record (whether weight, ascites, and blood pressure are measured regularly) can be uploaded by a home device or the follow-up platform; the doctor-patient interaction response delay (whether the patient responds promptly after the doctor issues a reminder / inquiry) can be obtained from the corresponding log of the doctor-patient system; and then each record is converted into a binary sequence to obtain the execution record sequence. In the embodiment of the present invention, the element value of the effective execution is set to 1, and the element value of the invalid execution is set to 0. That is, the prognostic response irregularity is the number of elements with a value of 0 in the execution record sequence.

[0058] In the embodiment of the present invention, the product of the state deviation index and the prognostic response irregularity can be directly used as the complication risk of each detection process.

[0059] Preferably, in one embodiment of the present invention, the method for obtaining the disease progression index includes:

[0060] The relative difference between the imaging cirrhosis risk and the historical average imaging cirrhosis risk for each test procedure is obtained, and the product of the relative difference and the complication risk is used as the disease progression index. The historical average imaging cirrhosis risk is the average imaging cirrhosis risk for the patient's other historical test procedures, excluding the current test procedure.

[0061] It should be noted that the relative difference in the embodiment of the present invention can also be quantified in the form of a ratio, where the numerator is the imaging cirrhosis risk during this detection process, and the denominator is the historical average imaging cirrhosis risk. The larger the relative difference, the greater the change in the patient's liver morphology during this detection process, which means that the patient's condition progresses faster, and the larger the disease progression index. Similarly, the greater the risk of complications, the greater the disease progression index, so the two indicators are fused and quantified by multiplication.

[0062] Preferably, in one embodiment of the present invention, the method for obtaining the drug adjustment degree includes:

[0063] The number of drug types in the current test process is used as the numerator, and the number of drug types that are the same between the current test process and the previous test process is used as the denominator to obtain the drug adjustment degree. The drug adjustment degree is a ratio. The smaller the denominator, the greater the drug adjustment of the patient in this test process compared to the previous one. It should be noted that the embodiment of the present invention is aimed at drug types, not drug brands. In the process of liver cirrhosis prognosis, certain types of drugs are essential drugs, so the denominator of the drug adjustment degree will not be 0.

[0064] Preferably, the method for obtaining the liver cirrhosis progression index in the embodiment of the present invention includes:

[0065] The difference in disease progression index between each test process and the previous test process is obtained, and after normalizing the difference in disease progression index, the sum of the normalized drug adjustment degree is used as the liver cirrhosis malignancy progression index. It should be noted that in this embodiment of the present invention, the difference in disease progression index between each test process and the previous test process can also be quantified in the form of a ratio, that is, the numerator is the disease progression index of the current test process, and the denominator is the disease progression index of the previous test process.

[0066] The normalization operation in the embodiment of the present invention can be implemented by using range normalization to normalize the data value range under the data dimension, or by using a function mapping method such as a hyperbolic tangent function mapping, which will not be described in detail.

[0067] Preferably, in an embodiment of the present invention, the method for obtaining data hysteresis includes:

[0068] A preset number of consecutive historical testing processes are selected from the current testing process. For each set of adjacent historical testing processes, the difference in cirrhosis progression index and testing frequency between the two historical testing processes is obtained. It should be noted that the number of historical testing processes selected here is the same as that selected in the first cirrhosis risk acquisition process, which is three.

[0069] The numerator is the difference in the average cirrhosis progression index across all adjacent historical testing processes, and the denominator is the sum of the average testing frequency difference and a preset hyperparameter. The resulting ratio represents the data hysteresis. A larger numerator and a smaller denominator indicate that within a certain time series, the cirrhosis progression index has significantly changed, but the testing frequency has not been significantly adjusted. The hyperparameter is a positive integer of 1 to prevent the denominator from being zero.

[0070] Preferably, in an embodiment of the present invention, adjusting the system detection frequency according to the liver cirrhosis progression index and the data hysteresis during each detection process includes:

[0071] The cirrhosis progression index and the data hysteresis in each test process are multiplied and then normalized to obtain a correction coefficient. It should be noted that the normalization method here is the same as the normalization method described above, and both can adopt range normalization, which will not be described in detail.

[0072] If the correction factor is less than the preset threshold, indicating a high data update frequency, the system is able to obtain new data in a timely manner to reflect the latest patient status, and the system is able to frequently update data and promptly identify changes in patient status, then there is no need to adjust the testing frequency at this time. Otherwise, it means that the system's data update frequency is low, and historical data may no longer be highly valid in the current situation. This is because a low update frequency means that clinical data is lagging, which may result in risks not being identified in a timely manner. It is necessary to derive a growth factor based on the correction factor and use this growth factor to increase the testing frequency.

[0073] In the embodiment of the present invention, considering that the correction coefficient has been normalized, the threshold is set to 0.6, and the growth coefficient is a positive integer 1 plus the correction coefficient. The increase can be achieved by multiplying the growth coefficient by the original detection frequency.

[0074] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0075] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A liver cirrhosis prognosis risk detection system, characterized in that: The system comprises: A liver image data analysis module is used to obtain the risk of liver cirrhosis in each detection process based on the area change and edge roughness of the liver region in the liver image between adjacent detection processes; A cirrhosis disease progression analysis module is used to obtain the patient's test data during each test process; use a pre-trained prediction neural network to obtain predicted data corresponding to the test data; obtain the patient's state deviation index during each test process based on the difference between the predicted data and the test data; obtain the complication risk of each test process based on the state deviation index and the prognostic response irregularity calculated in the prognostic follow-up system, and obtain the disease progression index of each test process in combination with the image cirrhosis risk; A drug adjustment impact analysis module is used to obtain a drug adjustment degree based on the difference in drug types before each test process compared to the drug types in the previous test process; and to obtain a liver cirrhosis malignancy progression index under each test process based on the drug adjustment degree and the disease progression index; The system data hysteresis analysis module is used to calculate the changes in the cirrhosis progression index and the detection frequency between all adjacent historical detection processes during each detection process; the system data hysteresis is obtained based on the asynchrony between the changes in the cirrhosis progression index and the changes in the detection frequency; The system detection frequency correction module is used to adjust the system detection frequency according to the liver cirrhosis progression index and the data hysteresis in each detection process.

2. A liver cirrhosis prognosis risk detection system according to claim 1, characterized in that: The detection data includes a physiological data sequence and a physiological data health score; the prediction data includes a predicted physiological data sequence and a predicted physiological data health score; Obtaining the Euclidean distance between the physiological data sequence and the predicted physiological data sequence; obtaining the score difference between the predicted physiological health score and the physiological data health score, and taking the product of the score difference and the Euclidean distance as the state deviation index.

3. A liver cirrhosis prognosis risk detection system according to claim 1, characterized in that: The method for obtaining the imaging liver cirrhosis risk includes: For the current detection process, the liver area of ​​the current detection process is used as the denominator, and the liver area of ​​the previous detection process is used as the numerator to obtain the area contrast feature; the edge roughness of the liver area of ​​the current detection process is used as the numerator, and the edge roughness of the liver area of ​​the previous detection process is used as the denominator to obtain the edge roughness contrast feature; the imaging cirrhosis risk is obtained based on the area contrast feature and the edge roughness contrast feature.

4. A liver cirrhosis prognosis risk detection system according to claim 1, characterized in that: The method for obtaining the drug adjustment degree includes: The number of drug types in the current detection process is used as the numerator, and the number of drug types that are the same between the current detection process and the previous detection process is used as the denominator to obtain the drug adjustment degree.

5. A liver cirrhosis prognosis risk detection system according to claim 1, characterized in that: The method for obtaining the liver cirrhosis progression index includes: The difference in disease progression index between each detection process and the previous detection process is obtained, and after normalizing the difference in disease progression index, the sum of the difference and the normalized drug adjustment degree is used as the liver cirrhosis malignant progression index.

6. A liver cirrhosis prognosis risk detection system according to claim 1, characterized in that: The method for obtaining the data hysteresis includes: Selecting a preset number of consecutive historical detection processes from the current detection process forward; for each group of adjacent historical detection processes, obtaining the difference in liver cirrhosis malignant progression index and detection frequency between the two historical detection processes; The difference in the average liver cirrhosis progression index of adjacent historical detection processes of all groups is used as the numerator, and the sum of the average detection frequency difference and the preset hyperparameter is used as the denominator, and the obtained ratio is the data hysteresis.

7. A liver cirrhosis prognosis risk detection system according to claim 1, characterized in that: The adjusting of the system detection frequency according to the liver cirrhosis progression index and the data hysteresis during each detection process includes: The cirrhosis progression index in each detection process and the data hysteresis are multiplied and normalized to obtain a correction coefficient; If the correction coefficient is less than the preset threshold, the detection frequency is not adjusted; otherwise, an increase coefficient is obtained according to the correction coefficient, and the detection frequency is increased using the increase coefficient.

8. A liver cirrhosis prognosis risk detection system according to claim 7, characterized in that: Obtaining a growth coefficient according to the correction coefficient, and increasing the detection frequency by using the growth coefficient, includes: The sum of the positive integer 1 and the correction coefficient is used as the growth coefficient, and the product of the growth coefficient and the detection frequency is used as the increased detection frequency.

9. A liver cirrhosis prognosis risk detection system according to claim 1, characterized in that: The method for obtaining the prognostic response irregularity comprises: The patient's behavior execution record sequence counted in the follow-up system during each detection process is counted; each element in the behavior execution record sequence represents the patient's execution degree of the will behavior, and the element value includes valid execution and invalid execution, and the number of invalid executions is counted as the prognostic response irregularity.

10. The liver cirrhosis prognosis risk detection system according to claim 1, characterized in that: The method for obtaining the disease progression index includes: The relative difference between the imaging liver cirrhosis risk and the historical average imaging liver cirrhosis risk in each detection process is obtained, and the product of the relative difference and the complication risk is used as the disease progression index.

Images