A method, device, computer equipment and storage medium for determining risk level

Abstract

The present application provides a risk level determination method, device, computer equipment and storage medium, wherein the user's abdominal B-ultrasound information is input into a B-ultrasound analysis model to obtain the user's liver space-occupying information; the user's liver reserve function information is graded using the Child-Pugh grading standard to obtain a first grade for representing the target user's liver reserve function grade; the age-Male-ALBI-Platelets scoring algorithm is used to obtain a first score for representing the possibility of the target user suffering from hepatocellular carcinoma; the first risk level is determined according to the target user's serum marker content; and the target risk level for describing the possibility of the user suffering from liver cancer is determined according to the first grade, the first score and the first risk level. The above method is used to analyze various physical indicators of the user to improve the accuracy of risk level determination.

Description

Technical Field

[0001] The present invention relates to the field of biomedicine, and in particular to a method, device, computer equipment and storage medium for determining a risk level. Background Art

[0002] Liver cancer is an insidious disease. It takes about two years for the first cancer cell to form in the liver until the patient develops symptoms. In general, early symptoms are not obvious and are difficult to be taken seriously. Patients will not seek medical attention until they have obvious symptoms, such as abdominal distension or pain in the liver area, and by then they are often in the late stage of liver cancer. In order to reduce the incidence of liver cancer in people at high risk of liver cancer, it is essential to conduct regular liver cancer screening for these people at high risk of liver cancer, determine the possibility of liver cancer, and provide targeted treatment as early as possible.

[0003] In the prior art, the method for judging the possibility of liver cancer in a high-risk group of people is usually to adopt manual screening, that is, a clinician judges whether the screening subject has liver cancer or the possibility of liver cancer based on the basic information of the screening subject and the data indicators of the examination; and due to the influence of experience, different doctors may reach different conclusions after analyzing the data indicators, thereby affecting the accuracy of determining the risk level used to describe the possibility of liver cancer in a high-risk group of people. Summary of the invention

[0004] In view of this, an object of the present invention is to provide a risk level determination method, apparatus, computer equipment and storage medium to improve the accuracy of risk level determination.

[0005] In a first aspect, an embodiment of the present application provides a method for determining a risk level, the method comprising:

[0006] Inputting the target user's abdominal B-ultrasound information into the trained B-ultrasound analysis model to obtain description information for describing the target user's liver lesions;

[0007] When the description information is used to indicate that the target user does not have liver mass occupation, the liver function information used to describe the liver reserve function of the target user is graded using the Child-Pugh grading standard for determining the liver reserve function to obtain a first grade for indicating the liver reserve function level of the target user;

[0008] Using the age-Male-ALBI-Platelets scoring algorithm for predicting the possibility of chronic liver disease patients suffering from hepatocellular carcinoma, the numerical value of the non-virological indicator used to evaluate the possibility of the target user suffering from hepatocellular carcinoma is calculated to obtain a first score used to represent the possibility of the target user suffering from hepatocellular carcinoma, wherein the possibility of the target user suffering from hepatocellular carcinoma is directly proportional to the first score;

[0009] Determining a first risk level according to the serum marker content of the target user, wherein the first risk level is used to describe the possibility of the target user suffering from liver cancer obtained after analyzing the serum marker of the target user;

[0010] A target risk level for describing the possibility that the target user suffers from liver cancer is determined according to the first classification, the first score, and the first risk level.

[0011] Optionally, after inputting the abdominal B-ultrasound information of the target user into a trained B-ultrasound analysis model to obtain description information for describing the liver space-occupying portion of the target user, the method includes:

[0012] When the description information is used to indicate that the target user has a liver mass, the major axis and the minor axis of the liver mass are output according to the abdominal B-ultrasound information, and a second risk level for describing the possibility that the target user suffers from liver cancer is determined according to the major axis and the minor axis of the liver mass.

[0013] Optionally, determining the first risk level according to the serum marker content of the target user includes:

[0014] When the first content of alpha-fetoprotein in the serum marker is less than a first threshold value and the first percentage of alpha-fetoprotein isomers in the serum marker is less than a second threshold value, determining the first risk level as low risk;

[0015] When the first content is less than the first threshold but the first percentage is greater than or equal to the second threshold, or the first content is greater than the first threshold but the first percentage is less than the second threshold, continue to determine whether the second content of abnormal prothrombin in the serum marker is less than the third threshold; if the second content is less than the third threshold, the first risk level is determined as medium risk; if the second content is greater than the third threshold, the first risk level is determined as high risk.

[0016] Optionally, after determining a target risk level for describing the possibility of the target user suffering from liver cancer according to the first classification, the first score and the first risk level, the method further includes:

[0017] Searching for liver cancer medical information having the same level identifier as the target risk level from a medical database storing liver cancer medical information;

[0018] The liver cancer medical information is displayed to the target user.

[0019] In a second aspect, an embodiment of the present application provides a risk level determination device, the device comprising:

[0020] A B-ultrasound information analysis module, used to input the target user's abdominal B-ultrasound information into a trained B-ultrasound analysis model to obtain description information for describing the target user's liver lesions;

[0021] A first grading determination module is used to grade the liver function information used to describe the liver reserve function of the target user using the Child-Pugh grading standard used to determine the liver reserve function when the description information is used to indicate that the target user does not have liver mass occupation, so as to obtain a first grading used to indicate the liver reserve function level of the target user;

[0022] A first score determination module is used to calculate the value of a non-virological indicator used to evaluate the possibility of the target user suffering from hepatocellular carcinoma using an age-Male-ALBI-Platelets scoring algorithm used to predict the possibility of chronic liver disease patients suffering from hepatocellular carcinoma, so as to obtain a first score used to represent the possibility of the target user suffering from hepatocellular carcinoma, wherein the possibility of the target user suffering from hepatocellular carcinoma is directly proportional to the first score;

[0023] A first risk level determination module, used to determine a first risk level according to the serum marker content of the target user, wherein the first risk level is used to describe the possibility of the target user suffering from liver cancer obtained after analyzing the serum marker of the target user;

[0024] A target risk level determination module is used to determine a target risk level for describing the possibility that the target user suffers from liver cancer according to the first classification, the first score and the first risk level.

[0025] Optionally, the device comprises:

[0026] The second risk level determination module is used to input the abdominal B-ultrasound information of the target user into the trained B-ultrasound analysis model to obtain description information for describing the liver space-occupying object of the target user. When the description information is used to indicate that the target user has a liver space-occupying object, the module outputs the major diameter and minor diameter of the liver space-occupying object according to the abdominal B-ultrasound information, and determines a second risk level for describing the possibility of the target user suffering from liver cancer according to the major diameter and minor diameter of the liver space-occupying object.

[0027] Optionally, when the first risk level determination module is used to determine the first risk level according to the serum marker content of the target user, it is specifically used to:

[0028] When the first content of alpha-fetoprotein in the serum marker is less than a first threshold value and the first percentage of alpha-fetoprotein isomers in the serum marker is less than a second threshold value, determining the first risk level as low risk;

[0029] When the first content is less than the first threshold but the first percentage is greater than or equal to the second threshold, or the first content is greater than the first threshold but the first percentage is less than the second threshold, continue to determine whether the second content of abnormal prothrombin in the serum marker is less than the third threshold; if the second content is less than the third threshold, the first risk level is determined as medium risk; if the second content is greater than the third threshold, the first risk level is determined as high risk.

[0030] Optionally, the device comprises:

[0031] a medical information display module, configured to, after determining a target risk level for describing the possibility of the target user suffering from liver cancer according to the first classification, the first score and the first risk level, search for liver cancer medical information having the same level identifier as the target risk level from a medical database storing liver cancer medical information;

[0032] The liver cancer medical information is displayed to the target user.

[0033] In a third aspect, an embodiment of the present application provides a computer device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the risk level determination method described in any optional implementation manner of the first aspect are performed.

[0034] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, executes the steps of the risk level determination method described in any optional implementation manner in the first aspect above.

[0035] The technical solution provided by this application includes but is not limited to the following beneficial effects:

[0036] The embodiments of the present invention provide a method, device, computer equipment and storage medium for determining a risk level, wherein the abdominal B-ultrasound information of a target user is input into a trained B-ultrasound analysis model to obtain description information for describing the target user's liver mass. Through the above steps, it is possible to avoid judgment or analysis by the naked eye of a doctor, thereby avoiding the influence of human factors. When the description information is used to indicate that the target user does not have a liver mass, the liver function information used to describe the target user's liver reserve function is graded using the Child-Pugh grading standard for determining the liver reserve function to obtain a first grade for indicating the target user's liver reserve function grade. Through the above steps, the user's liver function grade can be obtained after analyzing the user's objective physical indicators, thereby eliminating the need to judge the liver function based on the doctor's experience, which is conducive to improving the accuracy of determining the liver function grade. The age-Male-A grade for predicting the possibility of chronic liver disease patients suffering from hepatocellular carcinoma is used. The LBI-Platelets scoring algorithm calculates the numerical value of the non-virological indicator used to evaluate the possibility of the target user suffering from hepatocellular carcinoma, and obtains a first score used to represent the possibility of the target user suffering from hepatocellular carcinoma, wherein the possibility of the target user suffering from hepatocellular carcinoma is directly proportional to the first score. Through the above steps, the possibility of the user suffering from hepatocellular carcinoma can be obtained after analyzing the non-virological indicators of the user, so that the probability does not need to be judged based on the doctor's experience, which is conducive to improving the accuracy of determining the possibility of the user suffering from hepatocellular carcinoma; the first risk level is determined according to the serum marker content of the target user, wherein the first risk level is used to describe the possibility of the target user suffering from liver cancer obtained after analyzing the serum marker of the target user; the target risk level used to describe the possibility of the target user suffering from liver cancer is determined according to the first classification, the first score and the first risk level. By adopting the above method, there is no need to judge the possibility of a user suffering from liver cancer based on the doctor's experience, thereby avoiding the possibility that different conclusions may be drawn after analyzing the data indicators due to the different experiences of different doctors. Instead, the risk level used to describe the possibility of a user suffering from liver cancer is confirmed using a unified analysis model and judgment criteria, which is conducive to improving the accuracy of risk level determination.

[0037] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0039] Figure 1 A flow chart of a risk level determination method provided by the first embodiment of the present invention is shown;

[0040] Figure 2 A flow chart of a method for determining a first risk level provided in Embodiment 1 of the present invention is shown;

[0041] Figure 3 A schematic diagram showing the structure of a risk level determination device provided by Embodiment 2 of the present invention is shown;

[0042] Figure 4 A schematic diagram of the structure of a computer device provided in Embodiment 3 of the present invention is shown. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present invention.

[0044] Embodiment 1

[0045] To facilitate understanding of this application, Figure 1 The contents described in the flowchart of a risk level determination method provided in the first embodiment of the present invention are described in detail in the first embodiment of the present application.

[0046] See also Figure 1 As stated, Figure 1 A flow chart of a risk level determination method provided in the first embodiment of the present invention is shown, and the method comprises steps S101 to S105:

[0047] S101: Inputting the target user's abdominal B-ultrasound information into a trained B-ultrasound analysis model to obtain description information for describing the target user's liver lesions.

[0048] Specifically, the abdominal B-ultrasound of the target screening user or the B-ultrasound report including the target user's liver information is input into a pre-trained analysis model that uses natural language processing technology to process and analyze the B-ultrasound report, so as to obtain an output result of whether there is a liver mass in the B-ultrasound report, or to obtain descriptive information for describing the liver mass situation of the target user.

[0049] S102: When the description information is used to indicate that the target user does not have liver mass occupancy, the liver function information used to describe the liver reserve function of the target user is graded using the Child-Pugh grading standard for determining liver reserve function to obtain a first grade for indicating the liver reserve function level of the target user.

[0050] Specifically, usually there are two possibilities for whether there is a liver mass. When B-ultrasound shows that there is no liver mass, it can be regarded that the target user has not yet suffered from liver cancer. However, whether the target user has the possibility of suffering from liver cancer and the degree of the possibility of suffering from liver cancer need to be judged in the next step.

[0051] First, since the target users who need to determine the risk are usually those at high risk of liver cancer, the medical records of the target users usually include laboratory data of medical indicators related to liver disease, including the patient's hepatic encephalopathy grade, ascites severity, serum bilirubin concentration, serum albumin concentration and prothrombin time; the different states of the above five indicators of the target users are divided into three levels, recorded as 1 point, 2 points and 3 points respectively, and the scores of the five indicators are added together, with the lowest total score of 5 points and the highest score of 15 points. According to the amount of the total, the liver reserve function is divided into three levels of A, B, and C, indicating three different degrees of liver damage (the higher the score, the worse the liver reserve function).

[0052] The score values ​​corresponding to each state of the above five indicators are shown in the following table:

[0053] Fraction 1 point 2 points 3 points Hepatic encephalopathy none 1~2 degrees 3~4 degrees Severity of ascites none Mild Moderate to severe Total bilirubin concentration (umol / L) <34 34-51 >51 Serum albumin concentration (g / L) >35 28-35 <28 Prothrombin time (s) <4 4-6 >6

[0054] According to the status of each of the above five indicators, a total score can be obtained by adding up the scores corresponding to each status. When the total score is 5 or 6 points, the current first grade is determined as A according to the Child-Pugh grading standard. When the total score is 7, 8, or 9 points, the current first grade is determined as B according to the Child-Pugh grading standard. When the total score is 10, 11, 12, 13, 14, or 15 points, the current first grade is determined as C according to the Child-Pugh grading standard. Among them, the first grades corresponding to the liver reserve function from high to low are A, B, and C, respectively.

[0055] For example, when the target user's hepatic encephalopathy is grade 2 (score is 2 points), the severity of ascites is moderate to severe (score is 3 points), the total bilirubin concentration is 30umol / L (score is 1 point), the serum albumin concentration is 32g / L (score is 2 points), and the prothrombin time is 7 (score is 3 points), the total score is 2+3+1+2+3=11 points, then the first classification is grade C, indicating that the liver reserve function of the target user is poor.

[0056] S103: Calculate the numerical value of the non-virological indicator used to assess the possibility of the target user suffering from hepatocellular carcinoma using the age-Male-ALBI-Platelets scoring algorithm for predicting the possibility of chronic liver disease patients suffering from hepatocellular carcinoma, and obtain a first score for indicating the possibility of the target user suffering from hepatocellular carcinoma, wherein the possibility of the target user suffering from hepatocellular carcinoma is directly proportional to the first score.

[0057] Specifically, the non-virological indicators include age, gender, albumin, total bilirubin (ALBI) and platelets. The scoring range of the age-Male-ALBI-Platelets scoring algorithm (aMAP scoring algorithm) is standardized to 1-100. For the target user, the first score of the target user is calculated according to the age, gender, albumin concentration, total bilirubin concentration and platelet concentration of the target user according to the following calculation rules:

[0058] ((0.06×age+0.89×sex+0.48×((log 10 C ×0.66)+(albumin×-0.085))-0.01×platelet concentration)+7.4) / 14.77×100, where C is the total bilirubin concentration, when the gender is male, the value of gender is 1, when the gender is female, the value of gender is 0), age is in years, and the units of other test indicators are total bilirubin concentration (μmol / L), albumin concentration (g / L) and platelet concentration (103 / mm 3 ).

[0059] When calculating the first score, the calculation method can be first adjusted according to whether the target user carries hepatitis B virus (HBV) and hepatitis C virus (HCV). If the target user carries hepatitis B virus and hepatitis C virus, the first score is calculated according to the above-mentioned aMAP scoring algorithm. If the target user does not carry hepatitis B virus and hepatitis C virus, the first score may not be calculated, or the first score may be regarded as 0 for subsequent risk level determination.

[0060] When the target user carries hepatitis B virus and hepatitis C virus, the target user is regarded as a chronic liver disease user, and after the first score is calculated according to the above-mentioned aMAP scoring algorithm, the chronic liver disease user is stratified into low, medium and high risk groups of chronic liver disease developing liver cancer according to the first score, wherein the stratification standard can be determined according to actual conditions. Here, an optional stratification standard is provided: when the first score is 1-50 points, the chronic liver disease user is determined as having a low risk of developing hepatocellular carcinoma, when the first score is 51-60 points, the chronic liver disease user is determined as having a medium risk of developing hepatocellular carcinoma, and when the first score is 61-100 points, the chronic liver disease user is determined as having a high risk of developing hepatocellular carcinoma.

[0061] S104: Determine a first risk level according to the serum marker content of the target user, wherein the first risk level is used to describe the possibility of the target user suffering from liver cancer after analyzing the serum marker of the target user.

[0062] Specifically, the serum markers used to determine the first risk level include alpha-fetoprotein (AFP), alpha-fetoprotein isoform percentage (AFP-L3%) and abnormal prothrombin (DCP), that is, the possibility of the target user suffering from liver cancer obtained after analyzing the first pair of serum markers is determined based on the alpha-fetoprotein content (concentration), alpha-fetoprotein isoform percentage and abnormal prothrombin content (concentration) in the target user's body, and the first risk level includes low risk, medium risk and high risk.

[0063] S105: Determine a target risk level for describing the possibility of the target user suffering from liver cancer according to the first classification, the first score, and the first risk level.

[0064] Specifically, a target risk level for describing the possibility of the target user suffering from liver cancer is determined based on the first classification for indicating the liver reserve function level of the target user obtained in step S102, the first score for indicating the possibility of the target user suffering from hepatocellular carcinoma obtained in step S103, and the first risk level for describing the possibility of the target user suffering from liver cancer obtained after analyzing the serum markers of the target user obtained in step S104. The target risk level can analyze the possibility of suffering from liver cancer more comprehensively based on the basic information and physical condition of the human body.

[0065] It is worth noting that the corresponding relationship between the first classification, the first score, the first risk level and the target risk level can be set according to actual needs, and is not specifically limited here. An optional implementation scheme is provided here for reference. The determination rule of the target risk level in this implementation scheme can be found in the following table:

[0066]

[0067] In a feasible implementation, after inputting the abdominal B-ultrasound information of the target user into a trained B-ultrasound analysis model to obtain description information for describing the liver mass of the target user, the method includes: when the description information is used to indicate that the target user has a liver mass, outputting the major axis and minor axis of the liver mass according to the abdominal B-ultrasound information, and determining a second risk level for describing the possibility of the target user suffering from liver cancer according to the major axis and minor axis of the liver mass.

[0068] Specifically, since the presence of a placeholder means the presence of a tumor, and a tumor means a high probability of cancer, when the description information for describing the target user's liver placeholder indicates that the target user has a liver placeholder, it is necessary to output the size of the placeholder (usually the size is reflected by the major diameter and minor diameter of the placeholder), and determine the second risk level for describing the possibility of the target user suffering from liver cancer based on the major diameter and minor diameter of the placeholder, wherein a larger product of the major diameter and the minor diameter means a higher second risk level, and the specific correspondence between the product of the major diameter and the minor diameter and the second risk level can be set according to medical common sense and is not specifically limited here.

[0069] In one possible embodiment, Figure 2 A flowchart of a method for determining a first risk level provided by the first embodiment of the present invention is shown. Figure 2As shown, determining the first risk level according to the serum marker content of the target user includes: when the first content of alpha-fetoprotein in the serum marker is less than a first threshold and the first percentage of alpha-fetoprotein isomers in the serum marker is less than a second threshold, determining the first risk level as low risk.

[0070] Specifically, the unit of the first content of alpha-fetoprotein is ng / ml. The specific values ​​of the first threshold value and the second threshold value can be set according to actual needs or medical common sense. No specific limitation is made here. An optional example is provided here as a reference: the first threshold value is set to 400 and the second threshold value is set to 10%. It can be obtained that when the first content of alpha-fetoprotein is less than 400 ng / ml (which can be regarded as negative) and the first percentage of alpha-fetoprotein isomers in the serum marker is less than 10% (which can be regarded as negative), the first risk level is determined to be low risk.

[0071] When the first content is less than the first threshold but the first percentage is greater than or equal to the second threshold, or the first content is greater than the first threshold but the first percentage is less than the second threshold, continue to determine whether the second content of abnormal prothrombin in the serum marker is less than the third threshold; if the second content is less than the third threshold, the first risk level is determined as medium risk; if the second content is greater than the third threshold, the first risk level is determined as high risk.

[0072] Specifically, the second content unit of the abnormal prothrombin is mAu / ml. The specific values ​​of the first threshold, the second threshold and the third threshold can be set according to actual needs or medical common sense. No specific limitation is made here. An optional example is provided here as a reference: the first threshold is set to 400, the second threshold is set to 10%, and the third threshold is set to 40. Then, when the first content of alpha-fetoprotein is greater than or equal to 400 ng / ml (which can be regarded as positive) or the first percentage of alpha-fetoprotein isomers in the serum marker is greater than 10% (which can be regarded as positive) (that is, when one of the two values ​​of the first content of alpha-fetoprotein and the first percentage of alpha-fetoprotein isomers is greater than the corresponding threshold), it is further determined whether the second content of the abnormal prothrombin is less than 40 mAu / ml. When the second content is less than 40 mAu / ml (which can be regarded as negative), the first risk level is determined as medium risk. When the second content is greater than 40 mAu / ml (which can be regarded as positive), the first risk level is determined as high risk.

[0073] In a feasible implementation scheme, after determining the target risk level used to describe the possibility of the target user suffering from liver cancer based on the first classification, the first score and the first risk level, the method also includes: searching for liver cancer medical information with the same level identifier as the target risk level from a medical database storing liver cancer medical information; and displaying the liver cancer medical information to the target user.

[0074] Specifically, according to the level identifier of the target risk level, liver cancer medical information with the same level identifier as the target risk level is determined from a medical database storing liver cancer medical information, wherein the liver cancer medical information includes but is not limited to: examination recommendations, such as imaging examinations, pathological examinations, blood laboratory tests, etc.; treatment methods, such as surgical treatment, drug treatment, etc.; lifestyle, such as eating habits, sleep recommendations, and drinking recommendations, etc.

[0075] After obtaining the target risk level for describing the possibility of the target user suffering from liver cancer, the present application can also adjust the judgment thresholds for determining the serum marker content of the first risk level, including the first threshold, the second threshold and the third threshold, according to the target risk level and the doctor's final diagnosis and treatment results of the target user, so that the first risk level of other users obtained by judging other users according to the first threshold, the second threshold and the third threshold and the target risk level of other users determined according to the first risk level of other users are more accurate. The specific modification method includes:

[0076] At least 2,000 user medical records related to liver disease are retrieved from the hospital information system as a user medical record set. For each user in the user medical record set, the liver space-occupying information of the user is determined according to step S101 in a risk level determination method disclosed in the present application, a first grade used to represent the liver reserve function level of the user is determined according to step S102, a first score used to represent the possibility of the user suffering from hepatocellular carcinoma is determined according to step S103, a first risk level used to describe the possibility of the user suffering from liver cancer obtained after analyzing the serum markers of the user is determined according to step S104, and a target risk level used to describe the possibility of the user suffering from liver cancer is determined according to step S105.

[0077] After obtaining the target risk level of at least 2000 medical records, the final diagnosis result of each medical record in the at least 2000 medical records is compared with the target risk level of each user. For each medical record and the user to which each medical record belongs, when the final diagnosis result of the medical record is the same as the target risk level of the user, the risk level determination result of the user is deemed qualified; when the final diagnosis result of the medical record is different from the target risk level of the user, the risk level determination result of the user is deemed unqualified; the number of users with qualified risk level determination results is divided by the total number of users to which the at least 2000 medical records belong to obtain an accuracy rate used to describe the accuracy of the risk level determination.

[0078] When the accuracy is greater than or equal to a preset threshold (for example, 90%), the accuracy is regarded as satisfactory, and the first threshold, the second threshold and the third threshold used to determine the first risk level in step S104 are used as thresholds for determining the first risk level of other users; when the accuracy is less than the preset threshold (for example, 90%), the accuracy is regarded as unsatisfactory, and the first threshold, the second threshold and the third threshold used to determine the first risk level in step S104 are modified and adjusted to obtain a fourth threshold, a fifth threshold and a sixth threshold, and the first risk level and the target risk level are determined again for each of the at least 2000 medical records according to step S104 and the fourth threshold, the fifth threshold and the sixth threshold, and the accuracy of the risk level determination is calculated. When the accuracy is unsatisfactory, the above modification steps are repeated until the result is satisfactory, and the target risk level of other users is determined using the threshold in step S104 finally obtained in combination with steps S101, step S102, step S103, step S104 and step S105.

[0079] Embodiment 2

[0080] See also Figure 3 As shown, Figure 3 FIG. 4 shows a schematic diagram of a risk level determination device provided by Embodiment 2 of the present invention, wherein: Figure 3 As shown, a risk level determination device 300 provided in the second embodiment of the present invention includes:

[0081] The B-ultrasound information analysis module 301 is used to input the abdominal B-ultrasound information of the target user into the trained B-ultrasound analysis model to obtain description information for describing the liver lesion of the target user;

[0082] A first grading determination module 302 is configured to, when the description information is used to indicate that the target user does not have liver mass occupation, grade the liver function information used to describe the liver reserve function of the target user using the Child-Pugh grading standard used to determine the liver reserve function, to obtain a first grade used to indicate the liver reserve function level of the target user;

[0083] A first score determination module 303 is used to calculate the value of the non-virological indicator used to evaluate the possibility of the target user suffering from hepatocellular carcinoma using the age-Male-ALBI-Platelets scoring algorithm used to predict the possibility of chronic liver disease patients suffering from hepatocellular carcinoma, so as to obtain a first score used to represent the possibility of the target user suffering from hepatocellular carcinoma, wherein the possibility of the target user suffering from hepatocellular carcinoma is directly proportional to the first score;

[0084] A first risk level determination module 304 is used to determine a first risk level according to the serum marker content of the target user, wherein the first risk level is used to describe the possibility of the target user suffering from liver cancer obtained after analyzing the serum marker of the target user;

[0085] The target risk level determination module 305 is used to determine a target risk level for describing the possibility that the target user suffers from liver cancer according to the first classification, the first score and the first risk level.

[0086] In one possible embodiment, the device comprises:

[0087] The second risk level determination module 306 is used to input the abdominal B-ultrasound information of the target user into the trained B-ultrasound analysis model to obtain description information for describing the liver mass of the target user. When the description information is used to indicate that the target user has a liver mass, the module outputs the major diameter and minor diameter of the liver mass according to the abdominal B-ultrasound information, and determines a second risk level for describing the possibility of the target user suffering from liver cancer according to the major diameter and minor diameter of the liver mass.

[0088] In a feasible embodiment, when the first risk level determination module 304 is used to determine the first risk level according to the serum marker content of the target user, it is specifically used to:

[0089] When the first content of alpha-fetoprotein in the serum marker is less than a first threshold value and the first percentage of alpha-fetoprotein isomers in the serum marker is less than a second threshold value, determining the first risk level as low risk;

[0090] When the first content is less than the first threshold but the first percentage is greater than or equal to the second threshold, or the first content is greater than the first threshold but the first percentage is less than the second threshold, continue to determine whether the second content of abnormal prothrombin in the serum marker is less than the third threshold; if the second content is less than the third threshold, the first risk level is determined as medium risk; if the second content is greater than the third threshold, the first risk level is determined as high risk.

[0091] In one possible embodiment, the device comprises:

[0092] The medical information display module 307 is used to search for liver cancer medical information having the same level identifier as the target risk level from a medical database storing liver cancer medical information after determining a target risk level for describing the possibility of the target user suffering from liver cancer according to the first classification, the first score and the first risk level;

[0093] The liver cancer medical information is displayed to the target user.

[0094] Embodiment 3

[0095] Based on the same application concept, see Figure 4 As shown, Figure 4 FIG. 4 shows a schematic diagram of the structure of a computer device provided by Embodiment 3 of the present invention, wherein: Figure 4 As shown, a computer device 400 provided in Embodiment 3 of the present application includes:

[0096] A processor 401, a memory 402 and a bus 403, wherein the memory 402 stores machine-readable instructions executable by the processor 401. When the computer device 400 is running, the processor 401 communicates with the memory 402 via the bus 403. When the processor 401 is running, the machine-readable instructions execute the steps of a risk level determination method shown in the above-mentioned embodiment 1.

[0097] Embodiment 4

[0098] Based on the same application concept, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of a risk level determination method described in any one of the above embodiments are executed.

[0099] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0100] The computer program product for determining risk levels provided in an embodiment of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the previous method embodiments. The specific implementation can be found in the method embodiments and will not be repeated here.

[0101] A risk level determination device provided in an embodiment of the present invention may be specific hardware on a device or software or firmware installed on the device. The implementation principle and technical effects of the device provided in an embodiment of the present invention are the same as those of the aforementioned method embodiment. For the sake of brief description, reference may be made to the corresponding contents in the aforementioned method embodiment for matters not mentioned in the device embodiment. Technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, the specific working processes of the aforementioned systems, devices and units can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

[0102] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0103] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0104] In addition, each functional unit in the embodiment provided by the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0105] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0106] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0107] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can still modify the technical solutions described in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or perform equivalent replacements on some of the technical features thereof; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention. They should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for determining a risk level, characterized in that: The method comprises: Inputting the target user's abdominal B-ultrasound information into the trained B-ultrasound analysis model to obtain description information for describing the target user's liver lesions; When the description information is used to indicate that the target user does not have liver mass occupation, the liver function information used to describe the liver reserve function of the target user is graded using the Child-Pugh grading standard for determining the liver reserve function to obtain a first grade for indicating the liver reserve function level of the target user; Using the age-Male-ALBI-Platelets scoring algorithm for predicting the possibility of chronic liver disease patients suffering from hepatocellular carcinoma, the numerical value of the non-virological indicator used to evaluate the possibility of the target user suffering from hepatocellular carcinoma is calculated to obtain a first score used to represent the possibility of the target user suffering from hepatocellular carcinoma, wherein the possibility of the target user suffering from hepatocellular carcinoma is directly proportional to the first score; Determining a first risk level according to the serum marker content of the target user, wherein the first risk level is used to describe the possibility of the target user suffering from liver cancer obtained after analyzing the serum marker of the target user; Determining a target risk level for describing the possibility that the target user suffers from liver cancer according to the first classification, the first score, and the first risk level; When the description information is used to indicate that the target user has a liver mass, outputting the major axis and the minor axis of the liver mass according to the abdominal B-ultrasound information, and determining a second risk level for describing the possibility that the target user suffers from liver cancer according to the major axis and the minor axis of the liver mass; Determining the first risk level according to the serum marker content of the target user includes: When the first content of alpha-fetoprotein in the serum marker is less than a first threshold value and the first percentage of alpha-fetoprotein isomers in the serum marker is less than a second threshold value, determining the first risk level as low risk; When the first content is less than the first threshold but the first percentage is greater than or equal to the second threshold, or the first content is greater than the first threshold but the first percentage is less than the second threshold, continue to determine whether the second content of abnormal prothrombin in the serum marker is less than the third threshold; if the second content is less than the third threshold, the first risk level is determined as medium risk; if the second content is greater than the third threshold, the first risk level is determined as high risk.

2. The method according to claim 1, characterized in that After determining a target risk level for describing the possibility that the target user suffers from liver cancer according to the first classification, the first score, and the first risk level, the method further includes: Searching for liver cancer medical information having the same level identifier as the target risk level from a medical database storing liver cancer medical information; The liver cancer medical information is displayed to the target user.

3. A risk level determination device, characterized in that: The device comprises: A B-ultrasound information analysis module, used to input the target user's abdominal B-ultrasound information into a trained B-ultrasound analysis model to obtain description information for describing the target user's liver lesions; A first grading determination module is used to grade the liver function information used to describe the liver reserve function of the target user using the Child-Pugh grading standard used to determine the liver reserve function when the description information is used to indicate that the target user does not have liver mass occupation, so as to obtain a first grading used to indicate the liver reserve function level of the target user; A first score determination module is used to calculate the value of a non-virological indicator used to evaluate the possibility of the target user suffering from hepatocellular carcinoma using an age-Male-ALBI-Platelets scoring algorithm used to predict the possibility of chronic liver disease patients suffering from hepatocellular carcinoma, so as to obtain a first score used to represent the possibility of the target user suffering from hepatocellular carcinoma, wherein the possibility of the target user suffering from hepatocellular carcinoma is directly proportional to the first score; A first risk level determination module, used to determine a first risk level according to the serum marker content of the target user, wherein the first risk level is used to describe the possibility of the target user suffering from liver cancer obtained after analyzing the serum marker of the target user; a target risk level determination module, configured to determine a target risk level for describing the possibility that the target user suffers from liver cancer according to the first classification, the first score, and the first risk level; a second risk level determination module, configured to, after inputting the target user's abdominal B-ultrasound information into a trained B-ultrasound analysis model to obtain description information for describing a liver mass of the target user, output a major diameter and a minor diameter of the liver mass according to the abdominal B-ultrasound information when the description information is used to indicate that the target user has a liver mass, and determine a second risk level for describing the possibility of the target user suffering from liver cancer according to the major diameter and the minor diameter of the liver mass; When the first risk level determination module is used to determine the first risk level according to the serum marker content of the target user, it is specifically used to: When the first content of alpha-fetoprotein in the serum marker is less than a first threshold value and the first percentage of alpha-fetoprotein isomers in the serum marker is less than a second threshold value, determining the first risk level as low risk; When the first content is less than the first threshold but the first percentage is greater than or equal to the second threshold, or the first content is greater than the first threshold but the first percentage is less than the second threshold, continue to determine whether the second content of abnormal prothrombin in the serum marker is less than the third threshold; if the second content is less than the third threshold, the first risk level is determined as medium risk; if the second content is greater than the third threshold, the first risk level is determined as high risk.

4. The device according to claim 3, characterized in that The device comprises: a medical information display module, configured to, after determining a target risk level for describing the possibility of the target user suffering from liver cancer according to the first classification, the first score and the first risk level, search for liver cancer medical information having the same level identifier as the target risk level from a medical database storing liver cancer medical information; The liver cancer medical information is displayed to the target user.

5. A computer device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the risk level determination method as described in any one of claims 1 to 2 are performed.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the risk level determination method as claimed in any one of claims 1 to 2.

Images