Method for predicting upper gastrointestinal hemorrhage in combination with previous medical history analysis of patient

Abstract

The invention relates to the technical field of medical data processing based on an intelligent chip, in particular to an upper gastrointestinal hemorrhage prediction method combined with past medical history analysis of a patient. According to the method, the previous medical history similarity of a to-be-analyzed patient and a historical patient is determined according to the correlation degree of medical history characteristics between the to-be-analyzed patient and the historical patient and upper gastrointestinal hemorrhage; analyzing deviation conditions of different upper digestive tract condition characteristics of the to-be-analyzed patient and the historical patient, and determining the similarity of the upper digestive tract condition of the to-be-analyzed patient and the historical patient; and determining the disease condition matching degree of the to-be-analyzed patient and the historical patient in combination with the past medical history similarity, the upper digestive tract disease condition similarity and the disease condition repetition frequency of the to-be-analyzed patient and the historical patient, screening out a feature convergence patient corresponding to the to-be-analyzed patient, and taking the upper digestive tract disease condition features of the feature convergence patient as prediction data of the to-be-analyzed patient. According to the method, the accuracy of data prediction is improved by analyzing factor characteristics in different aspects.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing based on smart chips, and in particular to a method for predicting upper gastrointestinal bleeding in combination with analysis of a patient's past medical history. Background Art

[0002] The prediction of upper gastrointestinal bleeding is mainly to identify and assess potential risks early, and to help doctors and patients take appropriate preventive and treatment measures, such as regular endoscopic examinations and medication adjustments. Medication adjustments are intended to avoid the use of certain anti-inflammatory drugs that may cause bleeding, thereby reducing the possibility of bleeding.

[0003] In recent years, the application of machine learning and artificial intelligence technologies in medical prediction has become increasingly widespread. By analyzing patients' clinical manifestations and laboratory data, the prediction of upper gastrointestinal bleeding is developing in a data-driven, personalized, and intelligent direction.

[0004] Currently, when doctors conduct data analysis and use the predicted data after analysis to teach medical students, when predicting patients' upper gastrointestinal bleeding, they usually predict the bleeding situation based on the patient's current upper gastrointestinal condition test status. Although this can infer the future degree of bleeding based on the actual condition of the current disease, the causes of upper gastrointestinal bleeding are complex. This means that the patient's long-term medical history, such as chronic liver disease, cirrhosis, etc., will significantly increase the risk of upper gastrointestinal bleeding, which will affect the judgment result of the patient's upper gastrointestinal bleeding prediction. Summary of the Invention

[0005] In order to solve the technical problem of low prediction accuracy when bleeding is predicted based solely on the patient's current upper gastrointestinal condition, the present invention aims to provide a method for predicting upper gastrointestinal bleeding that combines analysis of the patient's past medical history. The technical solution adopted is as follows:

[0006] In a first aspect, an embodiment of the present invention provides a method for predicting upper gastrointestinal bleeding in combination with analysis of a patient's medical history, the method comprising:

[0007] Obtain the patient's medical records and past medical history, including: medical history characteristics and upper gastrointestinal disease characteristics;

[0008] Analyze the simultaneous occurrence of each medical history feature of each patient with other medical history features to determine the degree of association with upper gastrointestinal bleeding; determine the similarity of the medical history of the patient to be analyzed and the historical patients based on the degree of association between the medical history features of the patient to be analyzed and the historical patients;

[0009] Analyze the deviation of different upper gastrointestinal tract disease characteristics between the patients to be analyzed and historical patients, and determine the similarity of the upper gastrointestinal tract disease characteristics between the patients to be analyzed and historical patients;

[0010] The matching degree of the patient's condition between the patient to be analyzed and the historical patients is determined by combining the similarity of their medical history, the similarity of their upper gastrointestinal conditions, and the recurrence frequency of the patient's condition. Based on the matching degree of the condition, patients with similar characteristics corresponding to the patient to be analyzed are screened from the historical patients, and the upper gastrointestinal condition characteristics of the patients with similar characteristics are used as the prediction data for the patient to be analyzed.

[0011] Furthermore, the analysis of the simultaneous occurrence of each medical history feature of each patient with other medical history features to determine the degree of association with upper gastrointestinal bleeding includes:

[0012] Taking any medical history feature of the patient as the target medical history feature, obtain the occurrence frequency of the target medical history feature in the patient's medical history features, and determine the medical history feature that appears the most times with the target medical history feature as the synchronous medical history feature;

[0013] Obtaining the frequency of occurrence of synchronous medical history features in the patient's medical history features;

[0014] According to the occurrence frequency of the target medical history feature in the patient's medical history features and the occurrence frequency of the synchronous medical history feature in the patient's medical history features, the degree of association between the target medical history feature and upper gastrointestinal bleeding is determined.

[0015] Furthermore, determining the degree of association between the target medical history feature and upper gastrointestinal bleeding based on the frequency of occurrence of the target medical history feature in the patient's medical history features and the frequency of occurrence of the synchronized medical history feature in the patient's medical history features includes:

[0016] The product of the frequency of occurrence of the target medical history feature in the patient's medical history features and the frequency of occurrence of the synchronous medical history feature in the patient's medical history features is normalized, and the normalized result value is used as the degree of association between the target medical history feature and upper gastrointestinal bleeding.

[0017] Furthermore, the method of determining the similarity of the medical history of the patient to be analyzed and the historical patients based on the degree of correlation between the medical history characteristics of the patient to be analyzed and the historical patients and upper gastrointestinal bleeding includes:

[0018] Obtain the number of features in the union set of medical history features of the patient to be analyzed and the historical patients as the number of medical history unions;

[0019] Obtain the number of features in the intersection set of the medical history features of the patient to be analyzed and the historical patients as the number of medical history intersections;

[0020] The ratio of the number of medical history intersections to the number of medical history unions is taken as the medical history feature intersection-union ratio;

[0021] Sum the correlation between the medical history features of the patient to be analyzed and the upper gastrointestinal bleeding, belonging to the medical history union set, to obtain the initial value of the medical history features;

[0022] The normalized value of the product of the intersection-and-union ratio of the medical record features and the initial value of the medical record features is used as the similarity between the medical history of the patient to be analyzed and the historical patients.

[0023] Furthermore, analyzing the deviation of different upper gastrointestinal condition characteristics of the patient to be analyzed and the historical patients to determine the similarity of the upper gastrointestinal condition of the patient to be analyzed and the historical patients includes:

[0024] Obtain the intersection-over-union ratio of the upper gastrointestinal tract disease characteristics of the patient to be analyzed and the historical patients, recorded as the intersection-over-union ratio of the upper gastrointestinal tract disease characteristics;

[0025] The deviation between the data monitoring value of the upper gastrointestinal condition characteristic of the patient to be analyzed and the standard monitoring range is used as the monitoring deviation value of the upper gastrointestinal condition characteristic of the patient to be analyzed;

[0026] The product of the intersection-and-union ratio of the upper gastrointestinal condition characteristics and the mean of the monitoring deviation values of all upper gastrointestinal condition characteristics of the patient to be analyzed is taken as the upper gastrointestinal condition similarity between the patient to be analyzed and the historical patients.

[0027] Furthermore, the method for obtaining the intersection-and-union ratio of the upper digestive tract condition characteristics is:

[0028] Obtaining the number of features in the union set of upper gastrointestinal condition features of the patient to be analyzed and the historical patients as the number of upper gastrointestinal condition unions;

[0029] Obtaining the number of features in the intersection set of the upper gastrointestinal condition features of the patient to be analyzed and the historical patients as the upper gastrointestinal condition intersection number;

[0030] The ratio of the number of intersections of upper gastrointestinal conditions and the number of unions of upper gastrointestinal conditions was taken as the intersection-union ratio of upper gastrointestinal condition characteristics.

[0031] Furthermore, the method for obtaining the recurrence frequency of the patient's condition to be analyzed is: standardizing the number of visits for upper gastrointestinal bleeding in the patient's medical records to be analyzed, and the standardized result value is the recurrence frequency of the patient's condition to be analyzed.

[0032] Furthermore, the determination of the matching degree of the condition of the patient to be analyzed and the historical patients by combining the similarity of the medical history of the patient to be analyzed and the historical patients, the similarity of the upper gastrointestinal condition, and the recurrence frequency of the condition of the patient to be analyzed includes:

[0033] The recurrence frequency of the patient's condition is used as the weight of the similarity between the patient's medical history and that of the historical patients.

[0034] The difference between the preset threshold and the recurrence frequency of the patient to be analyzed is used as the weight of the similarity between the upper gastrointestinal conditions of the patient to be analyzed and the historical patients;

[0035] The similarity of the medical history and upper gastrointestinal condition of the patient to be analyzed and historical patients is weighted and summed to obtain the condition matching degree of the patient to be analyzed and historical patients.

[0036] Furthermore, the method for acquiring the medical history features is: performing word segmentation processing on the past medical history, extracting medical feature words from the word segmentation based on the hospital term library, and recording them as medical history features.

[0037] Furthermore, the method for acquiring the upper gastrointestinal condition characteristics is: performing word segmentation processing on the past medical history, extracting medical feature words from the word segmentation based on the upper gastrointestinal condition feature library, and recording them as upper gastrointestinal condition characteristics.

[0038] In a second aspect, a system for predicting upper gastrointestinal bleeding based on analysis of a patient's medical history is provided, the system comprising the following modules:

[0039] An acquisition module is used to obtain the patient's medical records and past medical history, wherein the past medical history includes: medical history characteristics and upper gastrointestinal disease characteristics;

[0040] The overall medical history analysis module is used to analyze the simultaneous occurrence of each medical history feature of each patient with other medical history features to determine the degree of correlation with upper gastrointestinal bleeding; based on the degree of correlation between the medical history features of the patient to be analyzed and the historical patients and upper gastrointestinal bleeding, the similarity of the medical history of the patient to be analyzed and the historical patients is determined;

[0041] The disease condition analysis module is used to analyze the deviation of different upper gastrointestinal disease characteristics between the patient to be analyzed and the historical patients, and determine the similarity of the upper gastrointestinal disease characteristics of the patient to be analyzed and the historical patients;

[0042] The prediction module is used to determine the matching degree of the patient's condition between the patient to be analyzed and the historical patients by combining the similarity of their past medical history, the similarity of their upper gastrointestinal conditions, and the recurrence frequency of the patient's condition; based on the matching degree of the conditions, patients with similar characteristics corresponding to the patient to be analyzed are screened out from the historical patients, and the upper gastrointestinal condition characteristics of the patients with similar characteristics are used as the prediction data for the patient to be analyzed.

[0043] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, various possible implementations of the first aspect are implemented.

[0044] In a fourth aspect, an embodiment of the present invention provides a computer program product, which includes: computer program code, which, when running on a computer, enables the computer to execute the method in the above-mentioned first aspect or any possible implementation of the first aspect.

[0045] In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed in a computer, the computer is caused to execute various possible implementations of the first aspect.

[0046] The embodiments of the present invention have at least the following beneficial effects:

[0047] The present invention can determine the corresponding historical patients based on the upper gastrointestinal bleeding condition, and thus analyze the degree of correlation between individual medical history feature information and upper gastrointestinal bleeding in the past medical history based on the patients with recurrent conditions, and define the past medical history similarity between the patient to be analyzed and the historical patients based on this; and determine the upper gastrointestinal condition similarity based on the upper gastrointestinal condition characteristics and condition descriptions of the current patient and the historical patients; finally, based on the recurrence frequency of the upper gastrointestinal bleeding of the patient to be analyzed, the above two similarity features are comprehensively weighed to determine the condition matching degree between the patient to be analyzed and the historical patients, and then determine the patient with the most similar condition in history as the patient with convergent characteristics, and use the upper gastrointestinal condition characteristics of the patient with convergent characteristics as the predicted data for the patient to be analyzed. This process is based on the possibility that the past medical history may lead to recurrence of upper gastrointestinal bleeding for analysis, thereby avoiding the problem that the temporary data detection results cannot fully reflect the patient's subsequent bleeding condition, and improving the accuracy of data prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 A flowchart of a method for predicting upper gastrointestinal bleeding in combination with analysis of a patient's medical history, provided by one embodiment of the present invention;

[0050] Figure 2 This is a system block diagram of an upper gastrointestinal bleeding prediction system combined with analysis of a patient's medical history, provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementation method, structure, characteristics and effects of a method for predicting upper gastrointestinal bleeding based on the analysis of the patient's previous medical history proposed by the present invention.

[0052] In the following description, different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0053] In the description of the embodiments of the present invention, unless otherwise specified, " / " means or, for example, A / B can mean A or B: "and / or" in the text is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present invention, "multiple" refers to two or more than two.

[0054] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0055] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0056] The embodiments of the present invention are described below with reference to the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided by the embodiments of the present invention are also applicable to similar technical problems.

[0057] The embodiment of the present invention provides a specific implementation method of a method for predicting upper gastrointestinal bleeding in combination with analysis of a patient's past medical history. The method is suitable for scenarios where medical students predict upper gastrointestinal bleeding. In this scenario, in order to solve the problem of low prediction accuracy when bleeding is predicted only based on the patient's current upper gastrointestinal condition detection status. The present invention proposes a method for predicting upper gastrointestinal bleeding in combination with analysis of a patient's past medical history. By taking the patient's past medical history as the core to consider the impact on the condition of upper gastrointestinal bleeding, the recurrence of the condition is used to comprehensively determine the patient who is most similar to the current patient's condition as a patient with similar features, thereby avoiding the situation where the bleeding prediction is inaccurate due to the inability of the temporary data detection results to accurately present the patient's subsequent true condition.

[0058] The following describes in detail a specific scheme of a method for predicting upper gastrointestinal bleeding combined with analysis of a patient's past medical history provided by the present invention with reference to the accompanying drawings.

[0059] See also Figure 1 , which shows a flowchart of a method for predicting upper gastrointestinal bleeding combined with analysis of a patient's medical history, provided by one embodiment of the present invention. The method comprises the following steps:

[0060] Step S100: Obtain the patient's medical records and past medical history, wherein the past medical history includes: medical history characteristics and upper gastrointestinal condition characteristics.

[0061] For the current patient to be analyzed and the historical patients in the historical database, electronic medical records are obtained, which include the patient's basic information, condition description, examination results, past medical history, and medical records. It should be noted that the electronic medical record information of the patient must be authorized by the patient.

[0062] Among them, the patient's upper gastrointestinal tract disease characteristics include hemoglobin, hematocrit and other test results, which are used to analyze the degree of upper gastrointestinal bleeding in the patient.

[0063] The description of the condition is usually the doctor's conclusion on the cause of the disease based on the patient's comprehensive examination results. It reflects the source and cause of the upper gastrointestinal bleeding. The past medical history usually includes the patient's long-term history of diseases related to upper gastrointestinal bleeding or related medications, such as a history of ulcers, liver disease, and medication history.

[0064] Step S200, analyze the synchronous occurrence of each medical history feature of each patient with other medical history features to determine the degree of correlation with upper gastrointestinal bleeding; based on the degree of correlation between the medical history features of the patient to be analyzed and the historical patients and upper gastrointestinal bleeding, determine the similarity of the medical history of the patient to be analyzed and the historical patients.

[0065] For patients with upper gastrointestinal bleeding, the causes of the disease are complex and may involve recurrent upper gastrointestinal bleeding due to the patient's long-term medical history.

[0066] Therefore, the number of times a patient visits a doctor due to upper gastrointestinal bleeding can be used to reflect whether the patient may have recurrent upper gastrointestinal bleeding due to a long-term medical history.

[0067] Based on each patient's hospital visit record, the frequency of each patient's disease recurrence can be determined. The recurrence degree of the disease can be defined by the number of times the patient visited the hospital for upper gastrointestinal bleeding. Specifically, the number of times each patient visited the hospital for upper gastrointestinal bleeding is obtained, recorded as M i, the number of visits for upper gastrointestinal bleeding in the medical records of the patient to be analyzed is standardized, and the result value after standardization is the recurrence frequency of the patient's condition to be analyzed. In the embodiments of the present invention, standardization can also be understood as normalization. In some embodiments, the maximum number of visits for upper gastrointestinal bleeding of all patients in the same time period is used as the denominator, and the number of visits for upper gastrointestinal bleeding of each patient is used as the numerator. The ratio formed by the numerator and denominator is the recurrence frequency of each patient's condition.

[0068] After determining the recurrence frequency of each patient's condition, a recurrence threshold is preset, and patients whose upper gastrointestinal bleeding recurrence frequency is greater than or equal to the preset recurrence threshold are screened. Subsequent processing is based on analysis of the screened patients. It is believed that the recurrence frequency of upper gastrointestinal bleeding in the screened patients is too high, and it may be caused by the patient's own long-term medical history. The screened patients can be historical patients or patients to be analyzed. In the embodiment of the present invention, the preset recurrence threshold is 0.68, and in other embodiments, it can be set by the implementer according to actual conditions.

[0069] Therefore, we can analyze the medical history characteristics that may be related to upper gastrointestinal bleeding based on the past medical history of these screened historical patients.

[0070] First, the patient's medical history information in the electronic medical record is segmented using JIEBA. Based on the hospital's terminology database, medical feature terms are extracted from the analysis and recorded as medical history features. Medical feature terms include disease names and medication names. This generates a medical history feature sequence for each patient. Each item in the medical history feature sequence is a patient's medical history feature. It should be noted that the medical history feature sequence is sorted in the chronological order of acquisition.

[0071] For the u-th medical history feature, the number of occurrences is obtained based on the past medical history feature sequence of all patients, recorded as s u .

[0072] Because the medical history characteristics reflect the patient's historical or long-term chronic diseases and related medications, especially hypertension, liver disease, cardiovascular disease, etc., which may cause vascular fragility or bleeding tendency; the use of anticoagulants, antiplatelet drugs, non-steroidal anti-inflammatory drugs (NSAIDs), etc. may also increase the risk of bleeding.

[0073] Therefore, in this process, when determining the degree of correlation between each medical history feature and upper gastrointestinal bleeding, it is taken into account that the medical history and the drugs appear in correspondence. Therefore, the more times a certain medical history feature appears, the more times other medical history features that appear at the same time appear, indicating that the degree of correlation between this medical history feature and upper gastrointestinal bleeding is higher.

[0074] Taking any medical history feature of the patient as the target medical history feature, the occurrence frequency of the target medical history feature in the patient's medical history features is obtained, and the medical history feature that appears the most times with the target medical history feature is determined as the synchronous medical history feature.

[0075] For example, for the u-th medical history feature, take the u-th medical history feature as the target medical history feature, traverse the medical history feature sequence of all patients to obtain the medical history feature that appears the most times with the u-th medical history feature as the synchronous medical history feature, and record the number of occurrences of the synchronous medical history feature as s′ u .

[0076] Obtain the frequency of occurrence of the target medical history feature in the patient's medical history features, that is, the ratio of the number of occurrences of the target medical history feature to the number of all medical history features. Obtain the frequency of occurrence of the synchronized medical history feature in the patient's medical history features, that is, the ratio of the number of occurrences of the synchronized medical history feature to the number of all medical history features.

[0077] According to the occurrence frequency of the target medical history feature in the patient's medical history features and the occurrence frequency of the synchronous medical history feature in the patient's medical history features, the degree of association between the target medical history feature and upper gastrointestinal bleeding is determined.

[0078] More specifically: the product of the frequency of occurrence of the target medical history feature in the patient's medical history features and the frequency of occurrence of the synchronous medical history feature in the patient's medical history features is normalized, and the normalized result value is used as the degree of association between the target medical history feature and upper gastrointestinal bleeding.

[0079] In the embodiment of the present invention, the uth medical history feature is used as the target medical history feature, and the correlation degree S between the target medical history feature and upper gastrointestinal bleeding is u The calculation formula is:

[0080]

[0081] Among them, norm is the linear normalization function; s u is the number of occurrences of the u-th medical history feature; s ′ u The number of occurrences of synchronized medical history features; s1 is the number of all medical history features.

[0082] This can be used to obtain the degree of association between each medical history feature and upper gastrointestinal bleeding, which reflects the extent to which each medical history feature may affect the occurrence of upper gastrointestinal bleeding.

[0083] The degree of correlation between each medical history feature and upper gastrointestinal bleeding determined through the above process can then be used to analyze the similarity between the current patient to be analyzed and each historical patient's medical history. In other words, the similarity between the patient to be analyzed and the historical patients' medical history can be determined based on the degree of correlation between the medical history features of the patient to be analyzed and the historical patients' medical history.

[0084] Take the i-th patient to be analyzed and the j-th historical patient as an example to analyze and determine the similarity of the medical history between the patient to be analyzed and the historical patient:

[0085] Get the number of features in the union set of the medical history features of the patient to be analyzed and the historical patients as the number of medical history unions u i ∪u j ; It should be noted that the union set of medical history features here can actually be understood as all medical history features of the patient to be analyzed and historical patients.

[0086] Get the number of features in the intersection set of the medical history features of the patient to be analyzed and the historical patients as the medical history intersection number u i ∩u j ; It should be noted that the intersection set of medical history features here can actually be understood as the medical history features of both the patient to be analyzed and the historical patients.

[0087] The number of intersections of medical histories u i ∩u j and the number of medical history sets u i ∪u j The ratio of the medical history characteristics was used as the intersection and intersection ratio

[0088] Sum the correlation between the medical history features of the patient to be analyzed and the upper gastrointestinal bleeding, belonging to the medical history union set, to obtain the initial value of the medical history features;

[0089] The normalized value of the product of the intersection-and-union ratio of the medical record features and the initial value of the medical record features is used as the similarity between the medical history of the patient to be analyzed and the historical patients.

[0090] In some embodiments, the similarity W between the medical history of the i-th patient to be analyzed and the j-th historical patient is i,j The calculation formula is:

[0091]

[0092] Among them, norm is linear normalization; u iis the number of medical history characteristics of the i-th patient to be analyzed; u j is the number of medical history features of the jth historical patient; u i ∩u j is the number of intersections between the medical histories of the i-th patient to be analyzed and the j-th historical patient; u i ∪u j is the union number of medical histories of the i-th patient to be analyzed and the j-th historical patient; Equivalent to u i ∪u j , which is the union of the medical histories of the i-th patient to be analyzed and the j-th historical patient; S p is the degree of correlation between the pth medical history feature in the intersection of the medical history of the i-th patient to be analyzed and the j-th historical patient and upper gastrointestinal bleeding.

[0093] Determine the similarity between the patient to be analyzed and each historical patient's past medical history.

[0094] Step S300 , analyzing the deviation of different upper gastrointestinal tract condition characteristics of the patient to be analyzed and historical patients, and determining the similarity of the upper gastrointestinal tract condition of the patient to be analyzed and historical patients.

[0095] Patients in the hospital usually undergo tests such as hemoglobin and hematocrit to analyze and determine the extent of their bleeding and other conditions. Doctors will also analyze the cause of the patient's upper gastrointestinal bleeding in the description of the condition in the electronic medical record based on the patient's overall examination results.

[0096] Here, the direct manifestation of the condition of the current patient to be analyzed can be determined by the patient's description of the condition and the degree of bleeding, so that the actual upper gastrointestinal tract examination results of the patient to be analyzed can be compared with those of historical patients in this way.

[0097] First, the medical history in the patient's electronic medical record information is processed through JIEBA word segmentation, and based on the upper gastrointestinal disease feature library, the disease feature nouns used by the doctor to describe the patient's condition are screened to obtain the disease feature sequence of each patient.

[0098] Based on the test results in the patient's electronic medical record information, the corresponding data of the hemoglobin, hematocrit and other related tests are obtained. These data are also the characteristics of the upper gastrointestinal tract condition.

[0099] Analyze the deviation of different upper gastrointestinal tract disease characteristics between the patient to be analyzed and the historical patients, and determine the similarity of the upper gastrointestinal tract disease characteristics between the patient to be analyzed and the historical patients. Specifically:

[0100] Obtain the intersection-and-union ratio of the upper gastrointestinal condition characteristics of the patient to be analyzed and those of historical patients, recorded as the intersection-and-union ratio of the upper gastrointestinal condition characteristics; use the deviation value between the data monitoring value of the upper gastrointestinal condition characteristics of the patient to be analyzed and the standard monitoring range as the monitoring deviation value of the upper gastrointestinal condition characteristics of the patient to be analyzed; use the product of the intersection-and-union ratio of the upper gastrointestinal condition characteristics and the mean of the monitoring deviation values of all upper gastrointestinal condition characteristics of the patient to be analyzed as the upper gastrointestinal condition similarity between the patient to be analyzed and historical patients. Specifically, for example, if the standard monitoring range is 10 to 20, if the corresponding data monitoring value of the upper gastrointestinal condition characteristics is 25 at this time, then the corresponding monitoring deviation value of the upper gastrointestinal condition characteristics is 5; if the corresponding data monitoring value of the upper gastrointestinal condition characteristics is 1 at this time, then the corresponding monitoring deviation value of the upper gastrointestinal condition characteristics is 9. It should be noted that in order to avoid the problem of inconsistent fluctuations in different deviation values, the maximum and minimum values of the deviation values between the data monitoring values of the upper gastrointestinal condition characteristics of the patient to be analyzed and the standard monitoring range can be normalized and used as the monitoring deviation value of the upper gastrointestinal condition characteristics of the patient to be analyzed.

[0101] Among them, the method for obtaining the upper gastrointestinal tract condition characteristic ratio is:

[0102] Get the number of features in the union set of the upper gastrointestinal condition features of the patient to be analyzed and the historical patients as the number of upper gastrointestinal condition unions X i ∪X j ; Get the number of features in the intersection set of the upper gastrointestinal condition characteristics of the patient to be analyzed and the historical patients as the upper gastrointestinal condition intersection number X i ∩X j The ratio of the intersection number of upper gastrointestinal conditions and the union number of upper gastrointestinal conditions is used as the intersection-union ratio of upper gastrointestinal conditions.

[0103] In some embodiments, the similarity E between the upper gastrointestinal condition of the i-th patient to be analyzed and the j-th historical patient is i,j The calculation formula is:

[0104]

[0105] Among them, X i ∪X j is the number of upper gastrointestinal diseases; X i ∩X j is the number of intersections of upper gastrointestinal conditions; Δf a is the monitoring deviation value of the ath upper gastrointestinal condition in the intersection of upper gastrointestinal conditions; A is equivalent to X i ∩X j , which is the number of intersections of upper gastrointestinal conditions.

[0106] Step S400, combining the similarity of the medical history of the patient to be analyzed and the historical patients, the similarity of the upper gastrointestinal conditions and the recurrence frequency of the patient to be analyzed, determines the condition matching degree of the patient to be analyzed and the historical patients; based on the condition matching degree, screen out patients with similar characteristics corresponding to the patient to be analyzed from the historical patients, and use the upper gastrointestinal condition characteristics of the patients with similar characteristics as the prediction data of the patient to be analyzed.

[0107] When the patient's upper gastrointestinal bleeding recurrence rate is higher, it means that the patient may be overly affected by the long-term medical history, so more attention should be paid to the similarity of the patient's medical history with other patients in the past; when the patient's upper gastrointestinal bleeding recurrence rate is lower, it means that the patient may not have had upper gastrointestinal bleeding before, so more attention should be paid to the current actual test results.

[0108] The recurrence frequency of the patient's condition being analyzed is used as the weight for the similarity between the patient's medical history and that of the historical patient. The difference between the preset threshold and the recurrence frequency of the patient's condition being analyzed is used as the weight for the similarity between the patient's upper gastrointestinal condition and that of the historical patient. The weighted sum of the similarity between the patient's medical history and the similarity between the upper gastrointestinal condition and that of the historical patient is used to obtain the degree of condition matching between the patient's condition and the historical patient. In this embodiment of the present invention, the preset threshold is set to 1; in other embodiments, the value can be adjusted by the implementer based on actual conditions.

[0109] The method for obtaining the recurrence frequency of the disease has been specifically described in step S200 and will not be explained here.

[0110] In some embodiments, the matching degree Y between the i-th patient to be analyzed and the j-th historical patient is i,j The calculation formula is:

[0111] Y i,j =Q i *W i,j +(1-Q i )*E i,j ;

[0112] Among them, W i,j is the similarity between the medical history of the i-th patient to be analyzed and the j-th historical patient; E i,j Q is the similarity between the upper gastrointestinal conditions of the i-th patient to be analyzed and the j-th historical patient; i is the recurrence frequency of the i-th patient to be analyzed; 1-Q i is the weight of the similarity between the upper gastrointestinal condition of the i-th patient to be analyzed and the j-th historical patient.

[0113] The comprehensive condition matching degree between the current patient to be analyzed and each historical patient can be determined, and the patient with the highest condition matching degree with the patient to be analyzed can be selected as the patient with the most similar historical condition to the patient to be analyzed, and is called the characteristic convergence patient corresponding to the patient to be analyzed.

[0114] Through the process of steps S100 to S400, patients with similar characteristics to the patient to be analyzed can be determined. This is determined comprehensively based on the medical history and actual test results of the patient to be analyzed and historical patients. Since the two have similar medical conditions, their upper gastrointestinal bleeding conditions will also show the same trend.

[0115] In this way, the subsequent bleeding conditions and upper gastrointestinal condition characteristics in the medical records of the electronic medical records of patients with similar characteristics determined by the current patient can be used as upper gastrointestinal bleeding prediction data for the patient to be analyzed for reference analysis by medical students.

[0116] See also Figure 2 , which shows a system block diagram of an upper gastrointestinal bleeding prediction system combined with analysis of a patient's medical history, provided by an embodiment of the present invention. The system includes the following modules:

[0117] An acquisition module is used to obtain the patient's medical records and past medical history, wherein the past medical history includes: medical history characteristics and upper gastrointestinal disease characteristics;

[0118] The overall medical history analysis module is used to analyze the simultaneous occurrence of each medical history feature of each patient with other medical history features to determine the degree of correlation with upper gastrointestinal bleeding; based on the degree of correlation between the medical history features of the patient to be analyzed and the historical patients and upper gastrointestinal bleeding, the similarity of the medical history of the patient to be analyzed and the historical patients is determined;

[0119] The disease condition analysis module is used to analyze the deviation of different upper gastrointestinal disease characteristics between the patient to be analyzed and the historical patients, and determine the similarity of the upper gastrointestinal disease characteristics of the patient to be analyzed and the historical patients;

[0120] The prediction module is used to determine the matching degree of the patient's condition between the patient to be analyzed and the historical patients by combining the similarity of their past medical history, the similarity of their upper gastrointestinal conditions, and the recurrence frequency of the patient's condition; based on the matching degree of the conditions, patients with similar characteristics corresponding to the patient to be analyzed are screened out from the historical patients, and the upper gastrointestinal condition characteristics of the patients with similar characteristics are used as the prediction data for the patient to be analyzed.

[0121] The chip type used to implement data processing in this system can be FPGA, ASIC, or digital signal processor (DSP).

[0122] Optionally, the transmission medium can be a wired link, such as but not limited to coaxial cable, optical fiber and digital subscriber line, or a wireless link, such as but not limited to Wireless Fidelity (WIFI), Bluetooth and mobile device network.

[0123] It should be noted that the device provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above.

[0124] An embodiment of the present invention provides a computer device structure. Exemplarily, the computer device includes: a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the computer device can execute any of the aforementioned methods for predicting upper gastrointestinal bleeding that incorporate analysis of a patient's medical history.

[0125] In addition, an embodiment of the present invention also protects a device, which may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to execute the upper gastrointestinal bleeding prediction method provided by an embodiment of the present invention combined with analysis of the patient's previous medical history.

[0126] In embodiments of the present invention, the device may be divided into functional modules based on the above-described method examples. For example, these modules may correspond to individual functional modules, or two or more functions may be integrated into a single processing module. The integrated modules may be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and represents only a logical functional division. In actual implementation, other division methods may be employed.

[0127] In the case of dividing each module into modules corresponding to each function, the device may further include a signal uploading module, a determination module, an adjustment module, etc. It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module and will not be repeated here.

[0128] It should be understood that the device provided in the embodiment of the present invention is used to execute the above-mentioned upper gastrointestinal bleeding prediction method combined with the analysis of the patient's previous medical history, and thus can achieve the same effect as the above-mentioned implementation method.

[0129] In the case of an integrated unit, the device may include a processing module and a storage module. When the device is applied to a device, the processing module may be used to control and manage the operation of the device. The storage module may be used to support the device in executing mutual program codes, etc. The processing module may be a processor or a controller that may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the present disclosure. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module may be a memory.

[0130] In addition, the device provided in an embodiment of the present invention can specifically be a chip, component or module, and the chip may include a connected processor and memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute the upper gastrointestinal bleeding prediction method provided in the above embodiment combined with the analysis of the patient's previous medical history.

[0131] An embodiment of the present invention also provides a computer-readable storage medium, which stores computer program code. When the computer program code is run on a computer, the computer executes the above-mentioned related method steps to implement the upper gastrointestinal bleeding prediction method provided in the above embodiment combined with the analysis of the patient's previous medical history.

[0132] An embodiment of the present invention also provides a computer program product. When the computer program product is run on a computer, it enables the computer to execute the above-mentioned related steps to implement the upper gastrointestinal bleeding prediction method provided in the above embodiment in combination with the analysis of the patient's previous medical history.

[0133] Among them, the device, computer-readable storage medium, computer program product or chip provided in the embodiments of the present invention are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, and will not be repeated here. Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In the embodiments provided by the present invention, it should be understood that the disclosed device and method can be implemented in other ways.

[0134] The device embodiments described above are merely illustrative. For example, the division into modules or units represents only one logical functional division. Actual implementations may employ alternative divisions, such as combining or integrating multiple units or components into another device, or omitting or disabling certain features. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through an interface, or indirect coupling or communication connection between devices or units may be electrical, mechanical, or otherwise.

[0135] It should also be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or terminal device comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or terminal device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or terminal device comprising the element.

[0136] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0137] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0138] The above content is only a specific implementation method of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for predicting upper gastrointestinal bleeding combined with analysis of a patient's medical history, characterized in that: The method comprises the following steps: Obtain the patient's medical records and past medical history, including: medical history characteristics and upper gastrointestinal disease characteristics; Analyze the simultaneous occurrence of each medical history feature of each patient with other medical history features to determine the degree of association with upper gastrointestinal bleeding; determine the similarity of the medical history of the patient to be analyzed and the historical patients based on the degree of association between the medical history features of the patient to be analyzed and the historical patients; Analyze the deviation of different upper gastrointestinal tract disease characteristics between the patients to be analyzed and historical patients, and determine the similarity of the upper gastrointestinal tract disease characteristics between the patients to be analyzed and historical patients; The matching degree of the patient's condition between the patient to be analyzed and the historical patients is determined by combining the similarity of their medical history, the similarity of their upper gastrointestinal conditions, and the recurrence frequency of the patient's condition. Based on the matching degree of the condition, patients with similar characteristics corresponding to the patient to be analyzed are screened from the historical patients, and the upper gastrointestinal condition characteristics of the patients with similar characteristics are used as the prediction data for the patient to be analyzed.

2. The method for predicting upper gastrointestinal bleeding based on analysis of the patient's medical history according to claim 1, characterized in that: The analysis of each patient's medical history characteristics and the simultaneous occurrence of other medical history characteristics to determine the degree of association with upper gastrointestinal bleeding includes: Taking any medical history feature of the patient as the target medical history feature, obtain the occurrence frequency of the target medical history feature in the patient's medical history features, and determine the medical history feature that appears the most times with the target medical history feature as the synchronous medical history feature; Obtaining the frequency of occurrence of synchronous medical history features in the patient's medical history features; According to the occurrence frequency of the target medical history feature in the patient's medical history features and the occurrence frequency of the synchronous medical history feature in the patient's medical history features, the degree of association between the target medical history feature and upper gastrointestinal bleeding is determined.

3. The method for predicting upper gastrointestinal bleeding based on analysis of the patient's medical history according to claim 2, characterized in that: Determining the degree of association between the target medical history feature and upper gastrointestinal bleeding according to the frequency of occurrence of the target medical history feature in the patient's medical history features and the frequency of occurrence of the synchronized medical history feature in the patient's medical history features includes: The product of the frequency of occurrence of the target medical history feature in the patient's medical history features and the frequency of occurrence of the synchronous medical history feature in the patient's medical history features is normalized, and the normalized result value is used as the degree of association between the target medical history feature and upper gastrointestinal bleeding.

4. The method for predicting upper gastrointestinal bleeding based on analysis of the patient's medical history according to claim 1, characterized in that: Determining the similarity of the medical history of the patient to be analyzed and the historical patients based on the degree of correlation between the medical history characteristics of the patient to be analyzed and the historical patients and upper gastrointestinal bleeding includes: Obtain the number of features in the union set of medical history features of the patient to be analyzed and the historical patients as the number of medical history unions; Obtain the number of features in the intersection set of the medical history features of the patient to be analyzed and the historical patients as the number of medical history intersections; The ratio of the number of medical history intersections to the number of medical history unions is taken as the medical history feature intersection-union ratio; Sum the correlation between the medical history features of the patient to be analyzed and the upper gastrointestinal bleeding, belonging to the medical history union set, to obtain the initial value of the medical history features; The normalized value of the product of the intersection-and-union ratio of the medical record features and the initial value of the medical record features is used as the similarity between the medical history of the patient to be analyzed and the historical patients.

5. The method for predicting upper gastrointestinal bleeding based on analysis of the patient's medical history according to claim 1, characterized in that: The analyzing the deviation of different upper gastrointestinal condition characteristics of the patient to be analyzed and the historical patients, and determining the similarity of the upper gastrointestinal condition of the patient to be analyzed and the historical patients, includes: Obtain the intersection-over-union ratio of the upper gastrointestinal tract disease characteristics of the patient to be analyzed and the historical patients, recorded as the intersection-over-union ratio of the upper gastrointestinal tract disease characteristics; The deviation between the data monitoring value of the upper gastrointestinal condition characteristic of the patient to be analyzed and the standard monitoring range is used as the monitoring deviation value of the upper gastrointestinal condition characteristic of the patient to be analyzed; The product of the intersection-and-union ratio of the upper gastrointestinal condition characteristics and the mean of the monitoring deviation values of all upper gastrointestinal condition characteristics of the patient to be analyzed is taken as the upper gastrointestinal condition similarity between the patient to be analyzed and the historical patients.

6. The method for predicting upper gastrointestinal bleeding based on analysis of the patient's medical history according to claim 5, characterized in that: The method for obtaining the intersection-combination ratio of the upper digestive tract condition characteristics is: Obtaining the number of features in the union set of upper gastrointestinal condition features of the patient to be analyzed and the historical patients as the number of upper gastrointestinal condition unions; Obtaining the number of features in the intersection set of the upper gastrointestinal condition features of the patient to be analyzed and the historical patients as the upper gastrointestinal condition intersection number; The ratio of the number of intersections of upper gastrointestinal conditions and the number of unions of upper gastrointestinal conditions was taken as the intersection-union ratio of upper gastrointestinal condition characteristics.

7. The method for predicting upper gastrointestinal bleeding based on analysis of the patient's medical history according to claim 1, characterized in that: The method for obtaining the recurrence frequency of the patient's condition to be analyzed is: standardizing the number of visits for upper gastrointestinal bleeding in the patient's medical records to be analyzed, and the result value after standardization is the recurrence frequency of the patient's condition to be analyzed.

8. The method for predicting upper gastrointestinal bleeding based on analysis of the patient's medical history according to claim 1, characterized in that: The determination of the matching degree of the condition of the patient to be analyzed and the historical patients by combining the similarity of the medical history of the patient to be analyzed and the historical patients, the similarity of the upper gastrointestinal condition, and the recurrence frequency of the condition of the patient to be analyzed includes: The recurrence frequency of the patient's condition is used as the weight of the similarity between the patient's medical history and that of the historical patients. The difference between the preset threshold and the recurrence frequency of the patient to be analyzed is used as the weight of the similarity between the upper gastrointestinal conditions of the patient to be analyzed and the historical patients; The similarity of the medical history and upper gastrointestinal condition of the patient to be analyzed and historical patients is weighted and summed to obtain the condition matching degree of the patient to be analyzed and historical patients.

9. The method for predicting upper gastrointestinal bleeding in combination with analysis of the patient's medical history according to claim 1, characterized in that: The method for acquiring the medical history features is as follows: performing word segmentation processing on the past medical history, extracting medical feature words from the word segmentation based on a hospital term library, and recording them as medical history features.

10. The method for predicting upper gastrointestinal bleeding in combination with analysis of the patient's medical history according to claim 1, characterized in that: The method for acquiring the upper gastrointestinal condition characteristics is: performing word segmentation processing on the past medical history, extracting medical feature words from the word segmentation based on the upper gastrointestinal condition characteristic library, and recording them as the upper gastrointestinal condition characteristics.

Images