Big data analysis-based hepatobiliary surgery treatment scheme screening method and system

Abstract

The invention relates to a hepatobiliary surgery treatment scheme screening method and system based on big data analysis, and relates to the field of medical data processing, and the method comprises the steps: obtaining a general index detection value and a hepatobiliary index detection value of a target patient, the liver and gall index detection values comprise alanine aminotransferase concentration, total bilirubin concentration, albumin concentration and globulin concentration, and constructing primary and secondary screening constraint conditions; searching a first hepatobiliary surgery treatment scheme set which simultaneously meets the first-level screening constraint condition and the second-level screening constraint condition, and carrying out recovery sample statistics to obtain a recovery probability set; and extracting a second hepatobiliary surgery treatment scheme with the recovery probability set greater than or equal to a recovery probability threshold from the first hepatobiliary surgery treatment scheme set, and sending the second hepatobiliary surgery treatment scheme to the medical terminal. The technical problem that the efficiency of the decision making process cannot be guaranteed due to the fact that repeated question and answer decisions are needed for determining the surgical treatment scheme in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and in particular, to a screening method and system for hepatobiliary surgery treatment plans based on big data analysis. Background Art

[0002] In the field of hepatobiliary surgery treatment, currently when a medical terminal formulates a treatment plan for a patient, it mainly relies on the experience of doctors. Doctors comprehensively judge the patient's situation based on their professional knowledge and past clinical experience, and then provide corresponding treatment plans. The disadvantage is that it is relatively dependent on the experience of doctors, and the decision-making efficiency is unstable.

[0003] Although existing medical Q&A platforms can provide certain auxiliary decision-making support for doctors, a large number of prompt words need to be given by doctors, and doctors also need to receive special prompt word training to effectively complete the auxiliary decision-making of hepatobiliary surgery treatment plans. This not only increases the workload of doctors, but also makes the efficiency of the entire decision-making process unable to be guaranteed, and it is difficult to meet the need for quickly and efficiently formulating treatment plans.

[0004] How to quickly and effectively screen out suitable treatment plans from big data when doctors make decisions on hepatobiliary surgery treatment plans, without the need for doctors to input cumbersome prompt words and receive training, but only through simple input of patient test data, so as to improve the decision-making efficiency of doctors and optimize medical human resources has become a technical problem that urgently needs to be solved. Summary of the Invention

[0005] In view of the technical problem in the prior art that the efficiency of the decision-making process cannot be guaranteed due to the need for repeated question-and-answer decisions in determining surgical treatment plans, the present invention provides a screening method and system for hepatobiliary surgery treatment plans based on big data analysis to solve this problem.

[0006] The technical solution of the present invention to solve the above technical problems is as follows:

[0007] In a first aspect, the present invention provides a method for screening hepatobiliary surgery treatment plans based on big data analysis, including: obtaining the general index detection values and hepatobiliary index detection values of a target patient, where the hepatobiliary index detection values include alanine aminotransferase concentration, total bilirubin concentration, albumin concentration, and globulin concentration; constructing a primary screening constraint condition based on the general index detection values; constructing a secondary screening constraint condition based on the alanine aminotransferase concentration, the total bilirubin concentration, the albumin concentration, and the globulin concentration; retrieving a first set of hepatobiliary surgery treatment plans that simultaneously meet the primary screening constraint condition and the secondary screening constraint condition; traversing the first set of hepatobiliary surgery treatment plans to perform recovery sample statistics and obtaining a set of recovery probabilities; extracting a second set of hepatobiliary surgery treatment plans from the first set of hepatobiliary surgery treatment plans where the set of recovery probabilities is greater than or equal to a recovery probability threshold and sending them to a medical terminal.

[0008] In a second aspect, the present invention provides a system for screening hepatobiliary surgery treatment plans based on big data analysis, including: a detection value receiving module for obtaining the general index detection values and hepatobiliary index detection values of a target patient, where the hepatobiliary index detection values include alanine aminotransferase concentration, total bilirubin concentration, albumin concentration, and globulin concentration; a primary constraint configuration module for constructing a primary screening constraint condition based on the general index detection values; a secondary constraint configuration module for constructing a secondary screening constraint condition based on the alanine aminotransferase concentration, the total bilirubin concentration, the albumin concentration, and the globulin concentration; a primary screening module for retrieving a first set of hepatobiliary surgery treatment plans that simultaneously meet the primary screening constraint condition and the secondary screening constraint condition; a recovery probability evaluation module for traversing the first set of hepatobiliary surgery treatment plans to perform recovery sample statistics and obtaining a set of recovery probabilities; a secondary screening module for extracting a second set of hepatobiliary surgery treatment plans from the first set of hepatobiliary surgery treatment plans where the set of recovery probabilities is greater than or equal to a recovery probability threshold and sending them to a medical terminal.

[0009] The beneficial effects of the present invention are as follows: By obtaining the general index detection values and hepatobiliary index detection values of a target patient, constructing a primary screening constraint condition and a secondary screening constraint condition, retrieving a first set of hepatobiliary surgery treatment plans that meet the conditions from big data, and then through recovery sample statistical analysis, extracting a second set of hepatobiliary surgery treatment plans where the set of recovery probabilities is greater than or equal to a recovery probability threshold and sending them to a medical terminal. Compared with the prior art, this method does not require doctors to repeatedly input prompt words and undergo training. Only by inputting the patient's test data can the screening and output of treatment plans be quickly completed, effectively solving the problem of low doctor decision-making efficiency in the prior art, improving the doctor's decision-making efficiency when formulating hepatobiliary surgery treatment plans, and optimizing the utilization of medical human resources. Description of the Drawings

[0010] Figure 1 Schematic flow chart of a method for screening hepatobiliary surgery treatment plans based on big data analysis provided by the present invention;

[0011] Figure 2 Schematic structural diagram of a system for screening hepatobiliary surgery treatment plans based on big data analysis provided by the present invention. Detailed implementation manners

[0012] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present invention.

[0013] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes, and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality of" means two or more, unless otherwise specifically defined.

[0014] In the description of the present invention, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily construed as being more preferred or having more advantages than other embodiments. The following description is provided to enable any person skilled in the art to implement and use the present invention. Details are set forth for purposes of explanation in the following description. It should be understood that those skilled in the art can recognize that the present invention can be implemented without these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

[0015] Embodiment 1:

[0016] As Figure 1 shown, the embodiment of the present invention provides a method for screening hepatobiliary surgery treatment plans based on big data analysis, including the steps of:

[0017] S10: Obtain the general index detection values and hepatobiliary index detection values of the target patient, where the hepatobiliary index detection values include alanine aminotransferase concentration, total bilirubin concentration, albumin concentration, and globulin concentration;

[0018] Specifically, after the patient detection is completed, the detection data will be transmitted to a medical terminal, such as a computer, a mobile phone, or other operation interfaces. Then, if medical staff believes that the hepatobiliary status of the patient is abnormal, they can upload the general index detection values and hepatobiliary index detection values of the target patient through the terminal. The general index detection values cover the patient's basic physiological indexes, such as age, gender, weight, blood pressure, blood sugar, etc. These indexes can reflect the overall health status of the patient. The hepatobiliary index detection values include alanine aminotransferase (ALT) concentration, total bilirubin (TBIL) concentration, albumin (ALB) concentration, and globulin (GLO) concentration. These indexes directly reflect the functional status of the hepatobiliary system and are key data for evaluating the severity of hepatobiliary diseases and formulating treatment plans. For example, an increase in ALT concentration usually indicates liver cell damage, an abnormality in TBIL concentration may be related to biliary obstruction or liver failure, and the ALB and GLO concentrations reflect the synthetic function and immune status of the liver.

[0019] S20: Construct a first-level screening constraint condition based on the general index detection values;

[0020] Furthermore, constructing a first-level screening constraint condition based on the general index detection values includes:

[0021] Receive the general index deviation threshold configured by the medical terminal;

[0022] When the deviation between the general index recorded value of the patient with the sample to be analyzed and the general index detection value is less than or equal to the general index deviation threshold, it is considered to meet the first-level screening constraint condition; otherwise, it is considered not to meet the first-level screening constraint condition.

[0023] Specifically, the first-level screening constraint conditions refer to using the patient's basic physiological indicators, such as age, gender, weight, blood pressure, blood sugar, etc., to set preliminary screening rules. To construct the first-level screening constraint conditions, it is necessary to first receive the general index deviation threshold configured by the medical terminal. For example, for the general index of age, the medical terminal may set a deviation threshold of about 5 years. When the deviation between the recorded value of the general index of the sample patient to be analyzed (such as the recorded age value) and the detected value of the general index of the target patient (such as the detected age value) is less than or equal to the set deviation threshold (such as 5 years), the age of this sample patient is considered to match well with the target patient and meets the first-level screening constraint conditions. Conversely, if the deviation exceeds this threshold, for example, the age difference between the sample patient and the target patient exceeds 5 years, it is regarded as not meeting the conditions. In this way, treatment plans that are too different from the target patient in terms of general indicators can be quickly excluded, significantly reducing the amount of data to be processed subsequently and improving the efficiency of the entire method. At the same time, this preliminary screening based on general indicators lays the foundation for subsequent more complex liver and gall index analyses, ensuring that the treatment plans entering the next screening are at least similar to the patient in terms of basic health characteristics.

[0024] S30: Construct a second-level screening constraint condition based on the alanine aminotransferase concentration, the total bilirubin concentration, the albumin concentration, and the globulin concentration;

[0025] Furthermore, constructing a second-level screening constraint condition based on the alanine aminotransferase concentration, the total bilirubin concentration, the albumin concentration, and the globulin concentration includes:

[0026] Traverse the alanine aminotransferase concentration, the total bilirubin concentration, the albumin concentration, and the globulin concentration to perform a liver and gall health correlation analysis to obtain the alanine aminotransferase correlation, the total bilirubin correlation, the albumin correlation, and the globulin correlation;

[0027] According to the alanine aminotransferase correlation, the total bilirubin correlation, the albumin correlation, and the globulin correlation, construct a distance evaluation function based on the alanine aminotransferase concentration, the total bilirubin concentration, the albumin concentration, and the globulin concentration:

[0028]

[0029] Among them, D(X 1 ,X 0 ) represents the distance of the liver and gall index status between two patients, X 0 represents the alanine aminotransferase concentration, the total bilirubin concentration, the albumin concentration, and the globulin concentration, X 1Characterize the recorded values of alanine aminotransferase concentration, total bilirubin concentration, albumin concentration, and globulin concentration in the input, where Δi represents the deviation threshold of the i-th attribute index, and ξ ( i ) Characterize the correlation degree of the i-th attribute index, X 1i Characterize the recorded value of the i-th attribute index in the input, X 0i Characterize the detected value of the i-th attribute index;

[0030] When the distance evaluation value is less than or equal to the distance evaluation threshold, it is considered to meet the secondary screening constraint condition; otherwise, it is considered not to meet the secondary screening constraint condition.

[0031] Furthermore, traverse the alanine aminotransferase concentration, the total bilirubin concentration, the albumin concentration, and the globulin concentration to perform an analysis of the liver and gallbladder health correlation degree, and obtain the alanine aminotransferase correlation degree, the total bilirubin correlation degree, the albumin correlation degree, and the globulin correlation degree, including:

[0032] Statistically analyze the proportion of liver and gallbladder abnormal samples with the alanine aminotransferase concentration as the only abnormal index to obtain the alanine aminotransferase correlation degree;

[0033] Statistically analyze the proportion of liver and gallbladder abnormal samples with the total bilirubin concentration as the only abnormal index to obtain the total bilirubin correlation degree;

[0034] Statistically analyze the proportion of liver and gallbladder abnormal samples with the albumin concentration as the only abnormal index to obtain the albumin concentration correlation degree;

[0035] Statistically analyze the proportion of liver and gallbladder abnormal samples with the globulin concentration as the only abnormal index to obtain the globulin concentration correlation degree.

[0036] Specifically, the secondary screening constraint condition refers to setting more stringent screening rules using these specific liver and gallbladder indicators, which directly reflect the functional status of the liver and gallbladder system and are key data for evaluating the severity of liver and gallbladder diseases. For example, an increase in the alanine aminotransferase (ALT) concentration usually indicates liver cell damage, an abnormality in the total bilirubin (TBIL) concentration may be related to biliary obstruction or liver failure, and the albumin (ALB) and globulin (GLO) concentrations reflect the synthetic function and immune status of the liver. Through these indicators, a more precise treatment plan suitable for the patient can be screened out.

[0037] Specifically, by traversing each hepatobiliary index, a hepatobiliary health correlation analysis is carried out, and the proportion of hepatobiliary abnormal samples is statistically analyzed with each hepatobiliary index as the only abnormal index. For example, taking the alanine aminotransferase concentration as the only abnormal index, retrieve patients in the historical samples with only ALT abnormal and other indexes normal, and count the proportion of these patients diagnosed with hepatobiliary diseases. This proportion is the correlation degree of ALT. The same method is used to calculate the correlation degrees of total bilirubin, albumin, and globulin. For example, assume that among 1000 historical samples, 100 samples have only ALT abnormal, and 80 of them are diagnosed with hepatobiliary diseases. Then the correlation degree of ALT is 80%. Then, based on these correlation degrees, a distance evaluation function is constructed: This function can quantify the gap between the hepatobiliary index status of the patient and that of the sample patient to be retrieved. For example, assume that the ALT concentration of the target patient is X1, the TBIL concentration is X2, the ALB concentration is X3, and the GLO concentration is X4, while the recorded values of the sample patient corresponding to a certain treatment plan are ALT concentration Y1, TBIL concentration Y2, ALB concentration Y3, and GLO concentration Y4 respectively. The distance value calculated by the distance evaluation function can reflect the difference between the two: when the distance evaluation value is less than or equal to the set threshold, it is considered that this treatment plan meets the secondary screening conditions.

[0038] S40: Retrieve the first set of hepatobiliary surgery treatment plans that simultaneously meet the primary screening constraint conditions and the secondary screening constraint conditions;

[0039] Specifically, first, select from the big data the first set of hepatobiliary surgery treatment plans that simultaneously meet the primary screening constraint conditions and the secondary screening constraint conditions. Preferably, first filter out the treatment plans that do not meet the general indicators according to the primary screening constraint conditions, and then, among the remaining data, further screen out the plans with matching hepatobiliary indicators according to the secondary screening constraint conditions. For example, assume that 1000 treatment plans are filtered out by the general indicator conditions, and then narrowed down to 100 by means of the hepatobiliary indicator conditions.

[0040] Comprehensively consider the primary screening constraint conditions and the secondary screening constraint conditions to ensure that the selected treatment plans are highly matched with the patient in terms of both general indicators and hepatobiliary indicators.

[0041] S50: Traverse the first set of hepatobiliary surgery treatment plans to conduct a recovery sample statistics and obtain a set of recovery probabilities;

[0042] Further, traversing the first set of hepatobiliary surgery treatment plans to conduct a recovery sample statistics and obtain a set of recovery probabilities includes:

[0043] Delete the outlier plans from the first set of hepatobiliary surgery treatment plans to obtain a concentrated set of hepatobiliary surgery treatment plans;

[0044] Extract the first hepatobiliary surgery treatment plan from the set of centralized hepatobiliary surgery treatment plans;

[0045] Retrieve several patient follow-up information of the first hepatobiliary surgery treatment plan, where the patient follow-up information includes a patient recovery identifier;

[0046] Statistically analyze the proportion of the patient recovery identifier in the several patient follow-up information, set it as the recovery probability of the first hepatobiliary surgery treatment plan, and add it to the set of recovery probabilities.

[0047] Furthermore, delete the outlier plans from the set of the first hepatobiliary surgery treatment plans to obtain the set of centralized hepatobiliary surgery treatment plans, including:

[0048] Obtain the first hepatobiliary surgery treatment plan of the set of the first hepatobiliary surgery treatment plans, where the first hepatobiliary surgery treatment plan includes a first set of treatment element types;

[0049] Obtain the second hepatobiliary surgery treatment plan of the set of the first hepatobiliary surgery treatment plans, where the first hepatobiliary surgery treatment plan includes a second set of treatment element types;

[0050] Statistically analyze the number of non-intersecting elements between the first set of treatment element types and the second set of treatment element types;

[0051] Statistically analyze the number of union elements between the first set of treatment element types and the second set of treatment element types;

[0052] Calculate the ratio of the number of non-intersecting elements to the number of union elements, set it as the plan distribution distance, and add it to the set of plan distribution distances;

[0053] Obtain the LOF outlier factor threshold, and based on the set of plan distribution distances, perform LOF outlier plan deletion on the set of the first hepatobiliary surgery treatment plans to obtain the set of centralized hepatobiliary surgery treatment plans.

[0054] Specifically, the set of recovery probabilities refers to the parameters obtained by further analyzing the initially screened treatment plans and statistically analyzing the recovery situations of each plan in historical applications. The recovery samples refer to the patients who have recovered after receiving the treatment plan, and the recovery probability is the proportion of the recovered patients among all the patients who have received the treatment of this plan. Analyze each plan in the set of the first hepatobiliary surgery treatment plans one by one.

[0055] An example of the recovery probability process is as follows: For a certain treatment plan A, retrieve the records of all patients who have received this treatment plan, and count the number of patients who have recovered. Suppose a total of 100 patients have received treatment plan A, and among them, the follow-up information of the patients shows that 80 patients have recovered. Then the recovery probability of plan A is 80%. In this way, a recovery probability is calculated for each treatment plan, and these probabilities are collected into a recovery probability set. The role of this step is to provide objective data support for subsequent screening to ensure that the treatment plan finally recommended to the doctor has a high success rate.

[0056] Preferably, before performing the above recovery probability evaluation process, in order to avoid including plans with low application frequencies in the final selection, the outlier plans are deleted from the first hepatobiliary surgery treatment plan set, and the concentrated hepatobiliary surgery treatment plan set is obtained for sorting. The detailed process is as follows: Obtain the set of treatment element types for each plan in the first hepatobiliary surgery treatment plan set. The treatment element type refers to the specific treatment content, for example, the dosage of a certain type of drug, the type of surgery, etc. all belong to a treatment element type. Exemplarily, assume that a certain treatment plan includes two treatment elements, drug A and drug B, and another plan includes two elements, drug B and surgery C. Next, calculate the number of non-intersecting elements (i.e., the number of different elements) and the number of union elements (i.e., the total number of elements) of the treatment elements between every two plans.

[0057] By calculating the ratio of the number of non-intersecting elements to the number of union elements, the plan distribution distance is obtained. For example, if the number of non-intersecting elements between plan A and plan B is 5, and the number of union elements is 10, the plan distribution distance is 50%. Then, the LOF (Local Outlier Factor) outlier factor algorithm is used. According to the data in the plan distribution distance set, first calculate the reciprocal of the mean of the distribution distances of each plan to at least 7 adjacent plans, which is set as the local density of each plan; calculate the mean of the local densities of all plans; divide the mean of the local densities by the local density of each plan respectively to obtain the LOF outlier factor of each plan. Delete the plans whose outlier factors are greater than or equal to the LOF outlier factor threshold. Preferably, the LOF outlier factor threshold is 1.5 - 3. The advantage of doing this is to reduce the interference of abnormal or irrelevant plans on the recovery probability statistics and ensure the data quality and accuracy of subsequent analysis.

[0058] S60: Extract the second hepatobiliary surgery treatment plans from the first hepatobiliary surgery treatment plan set whose recovery probability set is greater than or equal to the recovery probability threshold and send them to the medical terminal.

[0059] Specifically, from all treatment plans, those with a recovery probability reaching or exceeding a preset threshold are screened out. These plans are considered relatively more effective treatment plans and will be sent to the medical terminal for doctors' reference. Here, the recovery probability threshold is a preset standard uploaded by the medical terminal. If not uploaded, the default is 80%, which is used to judge the effectiveness of the treatment plan.

[0060] Exemplarily, according to the previously statistically collected set of recovery probabilities, those treatment plans with a recovery probability greater than or equal to the recovery probability threshold are screened out. For example, if the recovery probability threshold is set at 80%, then only those treatment plans with a recovery rate reaching or exceeding 80% in the historical data will be selected. These plans are defined as the second hepatobiliary surgery treatment plans, which are considered relatively more effective treatment plans. These plans are sent to the medical terminal for doctors to refer to when formulating treatment plans. The role of this step is to provide doctors with data-verified efficient treatment plans, helping doctors make decisions quickly and improving the success rate and efficiency of treatment.

[0061] Further, retrieve the first hepatobiliary surgery treatment plan set that simultaneously meets the first-level screening constraint conditions and the second-level screening constraint conditions, including:

[0062] Retrieve the first-level sample patient set that simultaneously meets the first-level screening constraint conditions and the second-level screening constraint conditions. Among them, the first-level sample patient set has a first-level hepatobiliary surgery treatment plan label set, a general index record value set, and a hepatobiliary index record value set;

[0063] When the number of the first-level sample patient set is less than or equal to the convergence number threshold, update the first-level screening constraint conditions and the second-level screening constraint conditions based on the general index record value set and the hepatobiliary index record value set to obtain the first-level screening constraint update conditions and the second-level screening constraint update conditions;

[0064] Retrieve the second-level sample patient set that simultaneously meets the first-level screening constraint update conditions and the second-level screening constraint update conditions;

[0065] Until the number of the first-level sample patient set, the second-level sample patient set until the M-level sample patient set is greater than the convergence number threshold, add the first-level hepatobiliary surgery treatment plan label set, the second-level hepatobiliary surgery treatment plan label set until the N-level hepatobiliary surgery treatment plan label set into the first hepatobiliary surgery treatment plan set.

[0066] Specifically, the set of labels for the primary hepatobiliary surgery treatment plan refers to the recorded treatment plans of the sampled patients retrieved; the set of recorded values of general indicators and the set of recorded values of hepatobiliary indicators refer to the measured values of indicators corresponding one-to-one to the set of labels for the primary hepatobiliary surgery treatment plan of the sampled patients retrieved.

[0067] Retrieve the set of primary sampled patients according to the primary and secondary screening constraint conditions. If the number of this set is less than the convergence number threshold (for example, preset to 100 samples), extract the recorded values of general indicators and hepatobiliary indicators of these samples, and reconstruct the primary and secondary screening constraint conditions with these benchmark indicators to obtain the updated primary screening constraint conditions and the updated secondary screening constraint conditions.

[0068] Next, retrieve the big data again based on the updated screening conditions to obtain the set of secondary sampled patients. If the number of primary sampled patients and the number of the set of secondary sampled patients are still insufficient, this process will continue to be repeated, gradually relaxing the screening conditions until the number of the set of primary sampled patients, the set of secondary sampled patients until the set of M-level sampled patients is greater than the convergence number threshold by more than the convergence number threshold.

[0069] In this way, the retrieval scope can be gradually expanded to obtain a sufficient number of sampled patients, ensuring that there is sufficient data support for the subsequent recovery probability statistics.

[0070] A method for screening hepatobiliary surgery treatment plans based on big data analysis provided by an embodiment of the present invention has at least the following technical effects:

[0071] By obtaining the measured values of general indicators and hepatobiliary indicators of the target patients, constructing the primary screening constraint conditions and the secondary screening constraint conditions, retrieving the first set of hepatobiliary surgery treatment plans that meet the conditions from the big data, and then through the statistical analysis of the recovery samples, extracting the second set of hepatobiliary surgery treatment plans with a recovery probability set greater than or equal to the recovery probability threshold and sending them to the medical terminal. Compared with the prior art, this method does not require doctors to repeatedly input prompt words and receive training. Only by inputting the test data of the patients can the screening and output of the treatment plan be quickly completed, effectively solving the problem of low decision-making efficiency of doctors in the prior art, improving the decision-making efficiency of doctors when formulating hepatobiliary surgery treatment plans, and optimizing the utilization of medical human resources.

[0072] Embodiment 2:

[0073] As Figure 2 shown, based on the same inventive concept as the method for screening hepatobiliary surgery treatment plans based on big data analysis provided in Embodiment 1, an embodiment of the present invention further provides a system for screening hepatobiliary surgery treatment plans based on big data analysis, including:

[0074] A detection value receiving module, which is used to obtain the general index detection value and the hepatobiliary index detection value of a target patient, wherein the hepatobiliary index detection value includes alanine aminotransferase concentration, total bilirubin concentration, albumin concentration, and globulin concentration;

[0075] A primary constraint configuration module, which is used to construct a primary screening constraint condition based on the general index detection value;

[0076] A secondary constraint configuration module, which is used to construct a secondary screening constraint condition based on the alanine aminotransferase concentration, the total bilirubin concentration, the albumin concentration, and the globulin concentration;

[0077] A primary screening module, which is used to retrieve a first set of hepatobiliary surgery treatment plans that simultaneously meet the primary screening constraint condition and the secondary screening constraint condition;

[0078] A recovery probability evaluation module, which is used to traverse the first set of hepatobiliary surgery treatment plans to perform recovery sample statistics and obtain a set of recovery probabilities;

[0079] A secondary screening module, which is used to extract a second set of hepatobiliary surgery treatment plans with the set of recovery probabilities greater than or equal to a recovery probability threshold from the first set of hepatobiliary surgery treatment plans and send them to a medical terminal.

[0080] Further, constructing a primary screening constraint condition based on the general index detection value includes:

[0081] Receiving a general index deviation threshold configured by the medical terminal;

[0082] When the deviation between the general index recorded value of the patient of the sample to be analyzed and the general index detection value is less than or equal to the general index deviation threshold, it is regarded as meeting the primary screening constraint condition; otherwise, it is regarded as not meeting the primary screening constraint condition.

[0083] Further, constructing a secondary screening constraint condition based on the alanine aminotransferase concentration, the total bilirubin concentration, the albumin concentration, and the globulin concentration includes:

[0084] Traversing the alanine aminotransferase concentration, the total bilirubin concentration, the albumin concentration, and the globulin concentration to perform hepatobiliary health correlation analysis, and obtaining alanine aminotransferase correlation, total bilirubin correlation, albumin correlation, and globulin correlation;

[0085] According to the alanine aminotransferase correlation, the total bilirubin correlation, the albumin correlation, and the globulin correlation, based on the alanine aminotransferase concentration, the total bilirubin concentration, the albumin concentration, and the globulin concentration, construct a distance evaluation function:

[0086]

[0087] Among them, D(X 1 , X 0 ) characterizes the distance of the hepatobiliary index status between two patients. X 0 characterizes the alanine aminotransferase concentration, total bilirubin concentration, albumin concentration, and globulin concentration. X 1 characterizes the recorded values of alanine aminotransferase concentration, total bilirubin concentration, albumin concentration, and globulin concentration input. Δi represents the deviation threshold of the i-th attribute index, and ξ ( i ) represents the correlation degree of the i-th attribute index. X 1i represents the recorded value of the i-th attribute index input. X 0i represents the measured value of the i-th attribute index;

[0088] When the distance evaluation value is less than or equal to the distance evaluation threshold, it is regarded as meeting the secondary screening constraint condition; otherwise, it is regarded as not meeting the secondary screening constraint condition.

[0089] Furthermore, traverse the alanine aminotransferase concentration, the total bilirubin concentration, the albumin concentration, and the globulin concentration to perform hepatobiliary health correlation analysis, and obtain the alanine aminotransferase correlation degree, total bilirubin correlation degree, albumin correlation degree, and globulin correlation degree, including:

[0090] Statistically analyze the proportion of hepatobiliary abnormal samples with the alanine aminotransferase concentration as the only abnormal index to obtain the alanine aminotransferase correlation degree;

[0091] Statistically analyze the proportion of hepatobiliary abnormal samples with the total bilirubin concentration as the only abnormal index to obtain the total bilirubin correlation degree;

[0092] Statistically analyze the proportion of hepatobiliary abnormal samples with the albumin concentration as the only abnormal index to obtain the albumin concentration correlation degree;

[0093] Statistically analyze the proportion of hepatobiliary abnormal samples with the globulin concentration as the only abnormal index to obtain the globulin concentration correlation degree.

[0094] Furthermore, retrieve the first set of hepatobiliary surgery treatment plans that simultaneously meet the primary screening constraint condition and the secondary screening constraint condition, including:

[0095] Retrieve the set of primary sample patients that simultaneously meet the primary screening constraint condition and the secondary screening constraint condition. Among them, the set of primary sample patients has a set of primary hepatobiliary surgery treatment plan labels, a set of general index recorded values, and a set of hepatobiliary index recorded values;

[0096] When the number of patients in the first-level sample patient set is less than or equal to the convergence number threshold, update the first-level screening constraint condition and the second-level screening constraint condition based on the general index record value set and the hepatobiliary index record value set, and obtain the first-level screening constraint update condition and the second-level screening constraint update condition;

[0097] Retrieve the second-level sample patient set that simultaneously meets the first-level screening constraint update condition and the second-level screening constraint update condition;

[0098] Until the number of patients in the first-level sample patient set, the second-level sample patient set until the M-level sample patient set is greater than the convergence number threshold, add the first-level hepatobiliary surgery treatment plan label set, the second-level hepatobiliary surgery treatment plan label set until the N-level hepatobiliary surgery treatment plan label set into the first hepatobiliary surgery treatment plan set.

[0099] Further, traverse the first hepatobiliary surgery treatment plan set to perform recovery sample statistics and obtain a recovery probability set, including:

[0100] Delete the outlier plans from the first hepatobiliary surgery treatment plan set to obtain a concentrated hepatobiliary surgery treatment plan set;

[0101] Extract the first concentrated hepatobiliary surgery treatment plan from the concentrated hepatobiliary surgery treatment plan set;

[0102] Retrieve several patient review information of the first concentrated hepatobiliary surgery treatment plan, where the patient review information includes a patient recovery identifier;

[0103] Statistically calculate the proportion of the patient recovery identifier in the several patient review information, set it as the recovery probability of the first concentrated hepatobiliary surgery treatment plan, and add it to the recovery probability set.

[0104] Further, deleting the outlier plans from the first hepatobiliary surgery treatment plan set to obtain a concentrated hepatobiliary surgery treatment plan set includes:

[0105] Obtain the first hepatobiliary surgery treatment plan of the first hepatobiliary surgery treatment plan set, where the first hepatobiliary surgery treatment plan includes a first treatment element type set;

[0106] Obtain the second hepatobiliary surgery treatment plan of the first hepatobiliary surgery treatment plan set, where the first hepatobiliary surgery treatment plan includes a second treatment element type set;

[0107] Statistically calculate the number of non-intersecting elements in the first treatment element type set and the second treatment element type set;

[0108] Count the number of union elements in the first set of treatment element types and the second set of treatment element types;

[0109] Calculate the ratio of the number of non - intersection elements to the number of union elements, set it as the scheme distribution distance, and add it to the set of scheme distribution distances;

[0110] Based on the LOF outlier factor threshold and the set of scheme distribution distances, perform LOF outlier scheme deletion on the first hepatobiliary surgery treatment scheme set to obtain the centralized hepatobiliary surgery treatment scheme set.

[0111] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer - usable storage media (including but not limited to disk storage, CD - ROM, optical storage, etc.) containing computer - usable program code.

[0112] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented. These computer program instructions can be provided to the processor of a general - purpose computer, a special - purpose computer, an embedded computer, or other programmable data - processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data - processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0113] These computer program instructions can also be stored in a computer - readable memory that can direct a computer or other programmable data - processing device to work in a specific manner, so that the instructions stored in the computer - readable memory generate a manufactured article including instruction means, and the instruction means implements the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0114] These computer program instructions can also be loaded onto a computer or other programmable data - processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer - implemented process. Thus, the instructions executed on the computer or other programmable device provide means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1Steps of the functions specified in one or more boxes.

[0115] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they learn the basic inventive concept.

[0116] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A method for screening hepatobiliary surgical treatment plans based on big data analysis, characterized in that: include: Obtaining the common index test values ​​and hepatobiliary index test values ​​of the target patient, wherein the hepatobiliary index test values ​​include alanine aminotransferase concentration, total bilirubin concentration, albumin concentration and globulin concentration; Based on the general indicator detection value, construct a first-level screening constraint condition; constructing secondary screening constraints based on the alanine aminotransferase concentration, the total bilirubin concentration, the albumin concentration, and the globulin concentration; Retrieving a first hepatobiliary surgical treatment plan set that satisfies both the primary screening constraint condition and the secondary screening constraint condition; Traversing the first hepatobiliary surgical treatment plan set to perform recovery sample statistics and obtain a recovery probability set; A second hepatobiliary surgical treatment plan whose recovery probability set is greater than or equal to a recovery probability threshold is extracted from the first hepatobiliary surgical treatment plan set and sent to the medical terminal.

2. The method according to claim 1, characterized in that Based on the general indicator detection value, a first-level screening constraint condition is constructed, including: Receiving a general indicator deviation threshold configured by the medical terminal; When the deviation between the common index record value of the sample patient to be analyzed and the common index detection value is less than or equal to the common index deviation threshold, it is deemed that the primary screening constraint condition is met; otherwise, it is deemed that the primary screening constraint condition is not met.

3. The method according to claim 1, characterized in that Based on the alanine aminotransferase concentration, the total bilirubin concentration, the albumin concentration and the globulin concentration, a secondary screening constraint condition is constructed, including: Traversing the alanine aminotransferase concentration, the total bilirubin concentration, the albumin concentration and the globulin concentration to perform liver and gallbladder health correlation analysis, and obtaining the alanine aminotransferase correlation, the total bilirubin correlation, the albumin correlation and the globulin correlation; According to the alanine aminotransferase association degree, the total bilirubin association degree, the albumin association degree and the globulin association degree, based on the alanine aminotransferase concentration, the total bilirubin concentration, the albumin concentration and the globulin concentration, a distance evaluation function is constructed: Among them, D X1,X0) represents the distance between the liver and gallbladder index states of two patients, X0 represents the concentration of alanine aminotransferase, total bilirubin, albumin and globulin, X1 represents the input alanine aminotransferase concentration record value, total bilirubin concentration record value, albumin concentration record value and globulin concentration record value, Δi represents the deviation threshold of the i-th attribute index, ξi represents the correlation degree of the i-th attribute index, X 1i The recorded value of the i-th attribute index representing the input, X 0i Characterizes the detection value of the i-th attribute indicator; When the distance evaluation value is less than or equal to the distance evaluation threshold, it is considered that the secondary screening constraint condition is met; otherwise, it is considered that the secondary screening constraint condition is not met.

4. The method according to claim 3, characterized in that Traversing the alanine aminotransferase concentration, the total bilirubin concentration, the albumin concentration, and the globulin concentration to perform liver and gallbladder health correlation analysis, and obtaining the alanine aminotransferase correlation, the total bilirubin correlation, the albumin correlation, and the globulin correlation, including: The alanine aminotransferase concentration is used as the only abnormal indicator to perform statistics on the proportion of liver and gallbladder abnormalities to obtain the alanine aminotransferase correlation degree; Taking the total bilirubin concentration as the only abnormal indicator, the percentage of liver and gallbladder abnormal samples is counted to obtain the total bilirubin correlation degree; The albumin concentration is used as the only abnormal indicator to perform statistics on the proportion of liver and gallbladder abnormalities to obtain the albumin concentration correlation; The globulin concentration was used as the only abnormal indicator to calculate the percentage of abnormal liver and gallbladder samples, and the correlation degree of the globulin concentration was obtained.

5. The method according to claim 1, characterized in that Retrieving a first hepatobiliary surgical treatment plan set that satisfies both the primary screening constraint condition and the secondary screening constraint condition, including: Retrieve a first-level sample patient set that satisfies both the first-level screening constraint condition and the second-level screening constraint condition, wherein the first-level sample patient set has a first-level hepatobiliary surgical treatment plan label set, a general indicator record value set, and a hepatobiliary indicator record value set; When the number of the first-level sample patient set is less than or equal to the convergence number threshold, the first-level screening constraint condition and the second-level screening constraint condition are updated based on the general indicator record value set and the hepatobiliary indicator record value set to obtain the first-level screening constraint update condition and the second-level screening constraint update condition; Retrieving a set of secondary sample patients that simultaneously satisfies the primary screening constraint update condition and the secondary screening constraint update condition; Until the number of the first-level sample patient set, the second-level sample patient set, and up to the M-level sample patient set is greater than the convergence quantity threshold, the first-level hepatobiliary surgery treatment plan label set, the second-level hepatobiliary surgery treatment plan label set, and up to the N-level hepatobiliary surgery treatment plan label set are added to the first hepatobiliary surgery treatment plan set.

6. The method according to claim 1, characterized in that The first hepatobiliary surgery treatment plan set is traversed to perform recovery sample statistics to obtain a recovery probability set, including: Deleting outliers from the first hepatobiliary surgery treatment plan set to obtain a centralized hepatobiliary surgery treatment plan set; Extracting a first centralized hepatobiliary surgical treatment plan from the centralized hepatobiliary surgical treatment plan set; Retrieving a plurality of patient review information of the hepatobiliary surgery treatment plan in the first set, wherein the patient review information includes a patient recovery identifier; The proportion of the patient recovery mark in the review information of the plurality of patients is counted, set as the recovery probability of the first concentrated hepatobiliary surgical treatment plan, and added into the recovery probability set.

7. The method according to claim 6, characterized in that The outlier solutions are deleted from the first hepatobiliary surgery treatment plan set to obtain a centralized hepatobiliary surgery treatment plan set, including: Obtaining a first hepatobiliary surgical treatment plan of the first hepatobiliary surgical treatment plan set, wherein the first hepatobiliary surgical treatment plan includes a first treatment element type set; Obtaining a second hepatobiliary surgical treatment plan of the first hepatobiliary surgical treatment plan set, wherein the first hepatobiliary surgical treatment plan includes a second treatment element type set; Counting the number of non-intersecting elements of the first treatment element type set and the second treatment element type set; Counting the number of elements in the union of the first treatment element type set and the second treatment element type set; Calculate the ratio of the number of non-intersection elements to the number of union elements, set it as the solution distribution distance, and add it to the solution distribution distance set; A LOF outlier factor threshold is obtained, and based on the plan distribution distance set, LOF outlier plans are deleted from the first hepatobiliary surgery treatment plan set to obtain the centralized hepatobiliary surgery treatment plan set.

8. A hepatobiliary surgery treatment plan screening system based on big data analysis, characterized in that: include: A test value receiving module, used to obtain the general index test values ​​and hepatobiliary index test values ​​of the target patient, wherein the hepatobiliary index test values ​​include alanine aminotransferase concentration, total bilirubin concentration, albumin concentration and globulin concentration; A primary constraint configuration module, used to construct a primary screening constraint condition based on the general indicator detection value; A secondary constraint configuration module, for constructing secondary screening constraint conditions based on the alanine aminotransferase concentration, the total bilirubin concentration, the albumin concentration and the globulin concentration; A primary screening module, used to retrieve a first set of hepatobiliary surgical treatment plans that simultaneously meet the primary screening constraint condition and the secondary screening constraint condition; A recovery probability evaluation module, used to traverse the first hepatobiliary surgical treatment plan set to perform recovery sample statistics and obtain a recovery probability set; The secondary screening module is used to extract a second hepatobiliary surgical treatment plan whose recovery probability set is greater than or equal to the recovery probability threshold from the first hepatobiliary surgical treatment plan set and send it to the medical terminal.

Images