A method for predicting upper gastrointestinal bleeding by combining patient medical history analysis

Abstract

This invention relates to the field of medical data processing technology based on intelligent chips, specifically to a method for predicting upper gastrointestinal bleeding by combining analysis of a patient's past medical history. The method determines the similarity of the past medical history of the patient to be analyzed and historical patients based on the correlation between the characteristics of their medical history and upper gastrointestinal bleeding; it analyzes the deviation of different upper gastrointestinal disease characteristics between the patient to be analyzed and historical patients to determine the similarity of their upper gastrointestinal disease conditions; and it combines the similarity of the past medical history, the similarity of their upper gastrointestinal disease conditions, and the frequency of disease recurrence to determine the matching degree of their conditions. Patients with similar characteristics to the patient to be analyzed are then selected, and their upper gastrointestinal disease characteristics are used as predictive data for the patient to be analyzed. This invention improves the accuracy of data prediction by analyzing different aspects of the characteristics.

Description

Technical Field

[0001] This invention relates to the field of medical data processing technology based on smart chips, and specifically to a method for predicting upper gastrointestinal bleeding by combining analysis of a patient's past medical history. Background Technology

[0002] The prediction of upper gastrointestinal bleeding is mainly for the early identification and assessment of potential risks, helping doctors and patients to take appropriate preventive and treatment measures, such as regular endoscopy and medication adjustment. Medication adjustment is to avoid the use of certain anti-inflammatory drugs that may cause bleeding, thereby reducing the likelihood of bleeding.

[0003] In recent years, machine learning and artificial intelligence technologies have been increasingly used in medical prediction. 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 to teach and demonstrate to medical students based on the analyzed predictive data, the prediction of upper gastrointestinal bleeding is usually based on the patient's current condition and the detection status of the upper gastrointestinal tract. Although this can infer the future extent of bleeding based on the actual condition of the patient, the causes of upper gastrointestinal bleeding are complex. This refers to the patient's long-term medical history, such as chronic liver disease and cirrhosis, which can significantly increase the risk of upper gastrointestinal bleeding. This will affect the judgment result of the upper gastrointestinal bleeding prediction. Summary of the Invention

[0005] To address the issue of low prediction accuracy when predicting bleeding solely based on a patient's current upper gastrointestinal condition, this invention aims to provide a method for predicting upper gastrointestinal bleeding that incorporates analysis of the patient's past medical history. The specific technical solution employed is as follows:

[0006] In a first aspect, embodiments of the present invention provide a method for predicting upper gastrointestinal bleeding by combining analysis of a patient's past medical history, the method comprising:

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

[0008] Analyze the synchronous occurrence of each medical history feature with other medical history features in each patient to determine the degree of association of upper gastrointestinal bleeding; determine the similarity of past medical history between 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 deviations in upper gastrointestinal tract disease characteristics between the patient to be analyzed and historical patients to determine the similarity of upper gastrointestinal tract disease between the patient to be analyzed and historical patients;

[0010] By combining the similarity of past medical history, upper gastrointestinal condition, and recurrence frequency of the patient's condition with those of historical patients, the matching degree of the patient's condition with that of historical patients is determined. Based on the matching degree, patients with similar characteristics to the patient to be analyzed are selected from historical patients, and the upper gastrointestinal condition characteristics of these patients are used as predictive data for the patient to be analyzed.

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

[0012] Using any medical history feature of a patient as the target medical history feature, the frequency of occurrence of the target medical history feature in the patient's medical history features is obtained, and the medical history feature that appears most frequently at the same time as the target medical history feature is identified as the synchronous medical history feature.

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

[0014] The degree of association between the target medical history feature and upper gastrointestinal bleeding is determined by the frequency of occurrence of the target medical history feature and the frequency of occurrence of concurrent medical history features in the patient's medical history features.

[0015] Furthermore, determining the correlation between the target medical history feature and upper gastrointestinal bleeding based on the frequency of occurrence of the target medical history feature and the frequency of occurrence of concurrent medical history features 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 concurrent medical history feature in the patient's medical history features was normalized, and the normalized result was used as the degree of association between the target medical history feature and upper gastrointestinal bleeding.

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

[0018] The number of features in the union of the medical history features of the patient to be analyzed and the historical patients is obtained as the number of medical history unions.

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

[0020] The ratio of the number of intersections to the number of unions in medical histories is used as the intersection-union ratio of medical history features.

[0021] The initial values ​​of the medical history features are obtained by summing the correlation between the medical history features belonging to the union of medical history sets of the patients to be analyzed and the upper gastrointestinal bleeding.

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

[0023] Furthermore, the analysis of deviations in the characteristics of different upper gastrointestinal conditions between the patient to be analyzed and historical patients, and the determination of the similarity of upper gastrointestinal conditions between the patient to be analyzed and historical patients, includes:

[0024] Obtain the crossover ratio of upper gastrointestinal condition characteristics between the patient to be analyzed and historical patients, and denot it as the crossover ratio of upper gastrointestinal condition characteristics;

[0025] The deviation between the data monitoring value of the upper gastrointestinal tract condition characteristics of the patient to be analyzed and the standard monitoring range is taken as the monitoring deviation value of the upper gastrointestinal tract condition characteristics of the patient to be analyzed.

[0026] The product of the crossover ratio of upper gastrointestinal tract condition features and the mean of the monitoring deviation values ​​of all upper gastrointestinal tract condition features of the patient to be analyzed is used as the similarity of upper gastrointestinal tract condition between the patient to be analyzed and historical patients.

[0027] Furthermore, the method for obtaining the crossover ratio of upper gastrointestinal lesion characteristics is as follows:

[0028] The number of features in the union of the upper gastrointestinal tract condition features of the patient to be analyzed and historical patients is used as the number of upper gastrointestinal tract condition unions.

[0029] Obtain the number of features in the intersection set of upper gastrointestinal tract condition features of the patient to be analyzed and historical patients, and use it as the upper gastrointestinal tract condition intersection number;

[0030] The ratio of the number of intersections of upper gastrointestinal lesions to the number of unions of upper gastrointestinal lesions is used as the feature intersection-union ratio of upper gastrointestinal lesions.

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

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

[0033] The frequency of disease recurrence in the patients to be analyzed was used as the weight for the similarity of past medical history between the patients to be analyzed and historical patients;

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

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

[0036] Furthermore, the method for obtaining the medical history features is as follows: the past medical history is segmented into words, and medical feature words are extracted from the segmented words based on the hospital terminology database, and recorded as medical history features.

[0037] Furthermore, the method for obtaining the upper gastrointestinal condition features is as follows: the past medical history is segmented into words, and medical feature words are extracted from the segmented words based on the upper gastrointestinal condition feature database, which are recorded as upper gastrointestinal condition features.

[0038] Secondly, an upper gastrointestinal bleeding prediction system that combines analysis of a patient's past medical history is provided, the system comprising the following modules:

[0039] The acquisition module is used to acquire the patient's medical records and past medical history, including: medical history characteristics and upper gastrointestinal tract condition characteristics;

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

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

[0042] The prediction module is used to determine the degree of matching between the patient to be analyzed and historical patients by combining the similarity of past medical history, the similarity of upper gastrointestinal tract conditions, and the frequency of disease recurrence of the patient to be analyzed. Based on the degree of matching, patients with similar characteristics to the patient to be analyzed are selected from the historical patients, and the upper gastrointestinal tract conditions of the patients with similar characteristics are used as the prediction data for the patient to be analyzed.

[0043] Thirdly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, it implements the various possible implementations of the first aspect.

[0044] Fourthly, embodiments of the present invention provide a computer program product comprising: computer program code, which, when executed on a computer, causes the computer to perform the method described in the first aspect or any possible implementation thereof.

[0045] Fifthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the various possible implementations of the first aspect.

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

[0047] This invention identifies historical patients based on their upper gastrointestinal bleeding symptoms. It then analyzes the correlation between past medical history features and upper gastrointestinal bleeding in patients with recurrent bleeding, defining the similarity between the patient's and historical patients' past medical histories. Furthermore, it determines the similarity between the current and historical patients' upper gastrointestinal conditions based on their symptoms and descriptions. Finally, it comprehensively weighs the frequency of recurrent upper gastrointestinal bleeding in the patient to be analyzed against these two similarity features to determine the degree of matching between the patient and historical patients. The patient with the most similar historical condition is then identified as a convergent patient, and their upper gastrointestinal condition features are used as predictive data for the patient to be analyzed. This process is based on the possibility that past medical history may lead to recurrent upper gastrointestinal bleeding, avoiding the problem that temporary data detection results cannot fully reflect the patient's subsequent bleeding status, thus improving the accuracy of data prediction. Attached Figure Description

[0048] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

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

[0050] Figure 2 This is a system block diagram of an upper gastrointestinal bleeding prediction system that combines patient medical history analysis, as provided in one embodiment of the present invention. Detailed Implementation

[0051] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a method for predicting upper gastrointestinal bleeding based on the analysis of a patient's past medical history, proposed according to the present invention.

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

[0053] In the description of the embodiments of the present invention, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of the present invention, "multiple" means two or more.

[0054] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0055] Unless otherwise defined, 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 pertains.

[0056] The embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art will recognize that, with technological advancements 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] This invention provides a specific implementation method for predicting upper gastrointestinal bleeding by combining patient's past medical history analysis. This method is applicable to scenarios where medical students need to predict upper gastrointestinal bleeding. In this scenario, to address the problem of low prediction accuracy when predicting bleeding solely based on the patient's current upper gastrointestinal condition, this invention proposes a method for predicting upper gastrointestinal bleeding by combining patient's past medical history analysis. By considering the impact of the patient's past medical history on the condition, and utilizing the recurrence of the condition, it comprehensively identifies patients with the most similar condition to the current patient as those with converging characteristics. This avoids inaccurate bleeding predictions caused by the inability of temporary data to accurately reflect the patient's subsequent true condition.

[0058] The following description, in conjunction with the accompanying drawings, details a specific scheme for a method for predicting upper gastrointestinal bleeding based on analysis of a patient's past medical history, provided by this invention.

[0059] Please see Figure 1 The diagram illustrates a flowchart of a method for predicting upper gastrointestinal bleeding by combining patient medical history analysis, according to an embodiment of the present invention. The method includes the following steps:

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

[0061] Electronic medical record information is retrieved from both the current patient being analyzed and historical patients in the database. This information includes the patient's basic information, description of their condition, examination results, past medical history, and consultation records. It should be noted that access to the patient's electronic medical record information requires the patient's authorization.

[0062] Among the patient's upper gastrointestinal condition characteristics are test results such as hemoglobin and hematocrit, which are used to analyze the degree of upper gastrointestinal bleeding.

[0063] The description of the illness is usually the doctor's conclusion on the cause of the upper gastrointestinal bleeding based on the patient's comprehensive examination results. This reflects the source of the upper gastrointestinal bleeding and the cause of the lesion. Past medical history usually refers to the patient's long-term history of diseases or medications related to upper gastrointestinal bleeding, such as a history of peptic ulcer disease, liver disease, or 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 association of upper gastrointestinal bleeding; determine the similarity of past medical history between 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.

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

[0066] Therefore, the number of times a patient seeks medical attention for upper gastrointestinal bleeding can be used to reflect whether the patient may have recurrent upper gastrointestinal bleeding due to a long history of the disease.

[0067] Based on each patient's hospital visit records, the frequency of each patient's condition recurrence is determined. This recurrence can be defined by the number of times a patient visits the hospital for upper gastrointestinal bleeding. Specifically: the number of times each patient visits the hospital for upper gastrointestinal bleeding is recorded. The number of visits for upper gastrointestinal bleeding in the patient's medical records is standardized, and the standardized result is the recurrence frequency of the patient's condition. In this embodiment of the invention, standardization can also be understood as normalization. In some embodiments, the maximum number of visits for upper gastrointestinal bleeding among all patients within the same time period is used as the denominator, and the number of visits for upper gastrointestinal bleeding for each patient is used as the numerator. The ratio of 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. Patients with a recurrence frequency of upper gastrointestinal bleeding greater than or equal to this threshold are screened. Subsequent processing is based on the analysis of these screened patients, who are considered to have excessively high recurrence rates of upper gastrointestinal bleeding, possibly due to a long-term medical history. Screened patients can be either historical patients or patients awaiting analysis. In this embodiment, the preset recurrence threshold is 0.68; in other embodiments, it can be set by the implementer according to actual circumstances.

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

[0070] First, for the patient's past medical history information in the electronic medical record, the past medical history is processed using JIEBA word segmentation, and based on the hospital's terminology database, medical feature words are extracted from the analysis and recorded as medical history features. Medical feature words include disease names, drug names, etc. This yields a past medical history feature sequence for each patient, where each item in the sequence represents a patient's medical history feature. It should be noted that the past medical history feature sequences are ordered according to the chronological order of acquisition.

[0071] For the u-th medical history feature, based on the sequence of past medical history features of all patients, the frequency of its occurrence is obtained and denoted as . .

[0072] Because the medical history reflects the patient's historical or long-term chronic diseases and related medications, especially hypertension, liver disease, and cardiovascular disease, which may lead to fragile blood vessels or bleeding tendencies; the use of anticoagulants, antiplatelet drugs, and nonsteroidal anti-inflammatory drugs (NSAIDs) may also increase the risk of bleeding.

[0073] Therefore, in determining the correlation between each medical history feature and upper gastrointestinal bleeding during this process, considering that medical history and medications appear in a corresponding manner, the more frequently a certain medical history feature appears, the more frequently other medical history features appear at the same time, indicating that the correlation between that medical history feature and upper gastrointestinal bleeding is higher.

[0074] Using any patient's medical history feature as the target medical history feature, the frequency of occurrence of the target medical history feature in the patient's medical history features is obtained, and the medical history feature that appears most frequently at the same time as the target medical history feature is identified as the synchronous medical history feature.

[0075] For example, for the u-th type of medical history feature, using the u-th type of medical history feature as the target medical history feature, we iterate through the sequence of past medical history features of all patients to find the medical history feature that appears most frequently alongside the u-th type of medical history feature as the concurrent medical history feature, and record the frequency of occurrence of the concurrent medical history feature as . .

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

[0077] The degree of association between the target medical history feature and upper gastrointestinal bleeding is determined by the frequency of occurrence of the target medical history feature and the frequency of occurrence of concurrent medical history features in the patient's medical history features.

[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 concurrent medical history feature in the patient's medical history features is normalized, and the normalized result is used as the degree of association between the target medical history feature and upper gastrointestinal bleeding.

[0079] In this embodiment of the invention, the u-th medical history feature is used as the target medical history feature, and the degree of correlation between the target medical history feature and upper gastrointestinal bleeding is determined. The calculation formula is:

[0080] ;

[0081] Where norm is a linear normalization function; The number of times the u-th medical history feature appears; The frequency of occurrence of synchronous medical history features; The number of all medical history characteristics.

[0082] This allows us to determine the degree of association between each medical history feature and upper gastrointestinal bleeding, reflecting the extent to which each medical history feature may contribute to upper gastrointestinal bleeding.

[0083] By determining the correlation between each medical history feature and upper gastrointestinal bleeding through the above process, we can then analyze the similarity of the past medical history between the current patient being analyzed and various historical patients. In other words, the similarity of the past medical history between the current patient being analyzed and historical patients is determined based on the correlation between the medical history features and upper gastrointestinal bleeding between the two patients.

[0084] Taking the i-th patient to be analyzed and the j-th historical patient as examples, the analysis is performed to determine the similarity of the past medical history between the patient to be analyzed and the historical patient:

[0085] The number of features in the union of the medical history features of the patient to be analyzed and those of historical patients is obtained as the number of medical history unions. It should be noted that the union of medical history features here can actually be understood as all the medical history features of the patient to be analyzed and all historical patients.

[0086] The number of features in the intersection set of the medical history features of the patient to be analyzed and those of historical patients is taken as the number of medical history intersections. It should be noted that the intersection of medical history features here can actually be understood as the medical history features that are present in both the patient to be analyzed and the historical patients.

[0087] Number of medical history intersections Number of cases and medical history The ratio of the two values ​​is used as a cross-comparison of medical history characteristics. ;

[0088] The initial values ​​of the medical history features are obtained by summing the correlation between the medical history features belonging to the union of medical history sets of the patients to be analyzed and the upper gastrointestinal bleeding.

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

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

[0091] ;

[0092] Where norm is linear normalization; The number of medical history features for the i-th patient to be analyzed; The number of medical history features for the j-th historical patient; Let be the number of intersections in the medical histories of the i-th patient to be analyzed and the j-th historical patient; Let be the number of medical histories of the i-th patient to be analyzed and the j-th historical patient; Equivalent to That is, the number of medical histories of the i-th patient to be analyzed and the j-th historical patient; The degree of association between the p-th medical history feature and upper gastrointestinal bleeding in the intersection of the medical histories of the i-th patient to be analyzed and the j-th historical patient.

[0093] Determine the similarity of the patient’s medical history to that of each historical patient.

[0094] Step S300: Analyze the deviations of different upper gastrointestinal tract disease characteristics between the patient to be analyzed and historical patients, and determine the similarity of upper gastrointestinal tract disease between the patient to be analyzed and historical patients.

[0095] In hospitals, patients typically undergo tests such as hemoglobin and hematocrit to analyze and determine the extent of their bleeding. Doctors will then analyze the cause of the upper gastrointestinal bleeding in the electronic medical record based on the patient's total test results.

[0096] Here, the patient's condition description and the degree of bleeding can be used to determine the direct manifestation of the current patient's condition, so that the patient to be analyzed can be compared with the actual upper gastrointestinal examination of historical patients.

[0097] First, the patient's past medical history in the electronic medical record is processed by JIEBA word segmentation, and based on the upper gastrointestinal tract condition feature database, condition feature terms in the doctor's description of the patient's condition are filtered out to obtain the condition feature sequence of each patient.

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

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

[0100] The crossover ratio (CVR) of upper gastrointestinal tract (EGT) characteristics between the patient being analyzed and historical patients is recorded as the EGT. The deviation between the monitored data value of the EGT characteristic of the patient being analyzed and the standard monitoring range is used as the monitoring deviation value of the EGT characteristic of the patient being analyzed. The product of the EGT and the mean of the monitoring deviation values ​​of all EGT characteristics of the patient being analyzed is used as the similarity between the patient being analyzed and historical patients regarding their EGT characteristics. Specifically, for example, if the standard monitoring range is 10-20, and the monitored data value of the corresponding EGT characteristic is 25, then the monitoring deviation value of the corresponding EGT characteristic is 5; if the monitored data value of the corresponding EGT characteristic is 1, then the monitoring deviation value of the corresponding EGT characteristic is 9. It should be noted that, in order to avoid the problem that different deviation values ​​may have inconsistent magnitudes, the maximum and minimum values ​​of the deviation between the data monitoring values ​​of the upper gastrointestinal tract 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 tract condition characteristics of the patient to be analyzed.

[0101] The method for obtaining the upper gastrointestinal condition characteristic ratio is as follows:

[0102] The number of features in the union of upper gastrointestinal condition features of the patient to be analyzed and historical patients is obtained as the union count of upper gastrointestinal condition features. ; Obtain the number of features in the intersection set of upper gastrointestinal tract condition features of the patient to be analyzed and historical patients, and use this as the upper gastrointestinal tract condition intersection count. The ratio of the number of intersections of upper gastrointestinal lesions to the number of unions of upper gastrointestinal lesions is used as the characteristic intersection-union ratio of upper gastrointestinal lesions. .

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

[0104] ;

[0105] in, The number of cases involving the upper gastrointestinal tract; The number of overlapping conditions in the upper gastrointestinal tract; The monitoring deviation value for the a-th upper gastrointestinal condition in the intersection of upper gastrointestinal conditions; Equivalent to This refers to the number of overlapping conditions in the upper gastrointestinal tract.

[0106] Step S400: Combine the similarity of past medical history, upper gastrointestinal condition, and recurrence frequency of the patient's condition to determine the matching degree of the patient's condition and the historical patients; based on the matching degree, select patients with similar characteristics to the patient to be analyzed from the historical patients, and use the upper gastrointestinal condition characteristics of the patients with similar characteristics as predictive data for the patient to be analyzed.

[0107] When a patient's upper gastrointestinal bleeding recurrence rate is high, it indicates that the patient may be overly influenced by a long-term medical history. In this case, more attention should be paid to the similarity of the patient's medical history among different patients. On the other hand, when a patient's upper gastrointestinal bleeding recurrence rate is low, it indicates that the patient may not have had upper gastrointestinal bleeding before. In this case, more attention should be paid to the current test results.

[0108] The frequency of disease recurrence in the patient to be analyzed is used as the weight for the similarity of the past medical history between the patient to be analyzed and historical patients; the difference between a preset threshold and the frequency of disease recurrence in the patient to be analyzed is used as the weight for the similarity of the upper gastrointestinal tract conditions between the patient to be analyzed and historical patients; the weighted sum of the similarity of the past medical history and the similarity of the upper gastrointestinal tract conditions between the patient to be analyzed and historical patients is used to obtain the disease matching degree between the patient to be analyzed and historical patients. In this embodiment of the invention, the preset threshold is set to 1; in other embodiments, the implementer may adjust this value according to the actual situation.

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

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

[0111] ;

[0112] in, The similarity of past medical histories between the i-th patient to be analyzed and the j-th historical patient; Let represent the similarity of the upper gastrointestinal tract conditions between the i-th patient to be analyzed and the j-th historical patient; Let be the recurrence frequency of the i-th patient's condition; is the weight of the similarity of the upper gastrointestinal tract conditions between the i-th patient to be analyzed and the j-th historical patient.

[0113] The overall disease matching degree between the current patient to be analyzed and each historical patient can be determined. From this, the patient with the highest disease matching degree with the patient to be analyzed can be selected as the patient with the most similar disease in history to the patient to be analyzed. This patient is called the characteristic convergent patient corresponding to the patient to be analyzed.

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

[0115] In this way, the subsequent bleeding status and upper gastrointestinal tract disease characteristics in the electronic medical records of patients with similar characteristics identified by the current patient can be used as predictive data for upper gastrointestinal bleeding in the patient to be analyzed, for medical students to refer to and analyze.

[0116] Please see Figure 2 The diagram illustrates a system block diagram of an upper gastrointestinal bleeding prediction system based on an embodiment of the present invention, which combines analysis of a patient's past medical history. The system includes the following modules:

[0117] The acquisition module is used to acquire the patient's medical records and past medical history, including: medical history characteristics and upper gastrointestinal tract condition characteristics;

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

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

[0120] The prediction module is used to determine the degree of matching between the patient to be analyzed and historical patients by combining the similarity of past medical history, the similarity of upper gastrointestinal tract conditions, and the frequency of disease recurrence of the patient to be analyzed. Based on the degree of matching, patients with similar characteristics to the patient to be analyzed are selected from the historical patients, and the upper gastrointestinal tract conditions of the patients with similar characteristics are used as the prediction data for the patient to be analyzed.

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

[0122] Alternatively, the transmission medium may be a wired link, such as, but not limited to, coaxial cable, fiber optic cable and digital subscriber line, or a wireless link, such as, but not limited to, wireless Fidelity (WIFI), Bluetooth and mobile device networks.

[0123] It should be noted that the device provided in the above embodiments is only an example of 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] This invention provides an embodiment of 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 perform any of the aforementioned methods for predicting upper gastrointestinal bleeding by combining analysis of the patient's past medical history.

[0125] Furthermore, embodiments of the present invention also protect an apparatus that 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 perform the upper gastrointestinal bleeding prediction method combined with patient medical history analysis provided in embodiments of the present invention.

[0126] In this embodiment of the invention, the device can be divided into functional modules according to the above method example. For example, each module can correspond to a separate function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and is only a logical functional division. In actual implementation, there may be other division methods.

[0127] When each module is divided according to its function, the device may also include a signal uploading module, a determination module, and an adjustment module. It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional descriptions of the corresponding functional modules, and will not be repeated here.

[0128] It should be understood that the device provided in this embodiment of the invention is used to perform the above-described method for predicting upper gastrointestinal bleeding by combining analysis of the patient's past medical history, and therefore can achieve the same effect as the above-described implementation method.

[0129] When using integrated units, the device may include a processing module and a storage module. When applied to a device, the processing module can be used to control and manage the device's operations. The storage module can be used to support the device in executing program code, etc. The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits as described in this 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., and the storage module may be a memory.

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

[0131] This invention also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer, the computer executes the aforementioned method steps to implement the upper gastrointestinal bleeding prediction method based on the patient's past medical history analysis provided in the above embodiments.

[0132] This invention also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned steps to achieve the upper gastrointestinal bleeding prediction method based on the analysis of the patient's past medical history provided in the above embodiments.

[0133] In this invention, the apparatus, computer-readable storage medium, computer program product, or chip provided in the embodiments are all used to execute the corresponding methods described above. Therefore, the beneficial effects they achieve can be referred to the beneficial effects in the corresponding methods described above, and will not be repeated here. Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In the embodiments provided by this invention, it should be understood that the disclosed apparatus and method can be implemented in other ways.

[0134] The device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical functional division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0135] It should also be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0136] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some 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. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0138] The above content is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the protection scope of the present invention.

Claims

1. A method for predicting upper gastrointestinal bleeding by combining analysis of a patient's past medical history, characterized in that, The method includes the following steps: Obtain the patient's medical records and past medical history, including: medical history characteristics and upper gastrointestinal tract condition characteristics; Analyze the synchronous occurrence of each medical history feature with other medical history features in each patient to determine the degree of association of upper gastrointestinal bleeding; determine the similarity of past medical history between 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 deviations in upper gastrointestinal tract disease characteristics between the patient to be analyzed and historical patients to determine the similarity of upper gastrointestinal tract disease between the patient to be analyzed and historical patients; By combining the similarity of past medical history, upper gastrointestinal tract condition, and recurrence frequency of the patient's condition, the matching degree of the patient's condition and the historical patients is determined. Based on the matching degree, patients with similar characteristics to the patient to be analyzed are selected from the historical patients. The upper gastrointestinal tract condition characteristics of the patients with similar characteristics are used as predictive data for the patient to be analyzed. The matching degree between the analyzed patient and historical patients is determined by combining the similarity of their past medical history, the similarity of their upper gastrointestinal conditions, and the frequency of disease recurrence in the analyzed patient. This includes: The frequency of disease recurrence in the patients to be analyzed was used as the weight for the similarity of past medical history between the patients to be analyzed and historical patients; The difference between the preset threshold and the frequency of disease recurrence in the patient to be analyzed is used as the weight for the similarity of the upper gastrointestinal tract conditions between the patient to be analyzed and historical patients. The similarity of past medical history and upper gastrointestinal tract conditions between the patients to be analyzed and historical patients is weighted and summed to obtain the matching degree of the conditions between the patients to be analyzed and historical patients.

2. The method for predicting upper gastrointestinal bleeding by combining patient's past medical history analysis according to claim 1, characterized in that, The analysis examines the synchronous occurrence of each patient's medical history feature with other medical history features to determine the degree of association between upper gastrointestinal bleeding, including: Using any medical history feature of a patient as the target medical history feature, the frequency of occurrence of the target medical history feature in the patient's medical history features is obtained, and the medical history feature that appears most frequently at the same time as the target medical history feature is identified as the synchronous medical history feature. Obtain the frequency of occurrence of synchronous medical history features in the patient's medical history features; The degree of association between the target medical history feature and upper gastrointestinal bleeding is determined by the frequency of occurrence of the target medical history feature and the frequency of occurrence of concurrent medical history features in the patient's medical history features.

3. The method for predicting upper gastrointestinal bleeding by combining patient's past medical history analysis according to claim 2, characterized in that, The determination of the correlation between the target medical history feature and upper gastrointestinal bleeding based on the frequency of occurrence of the target medical history feature and the frequency of occurrence of concurrent medical history features in the patient's medical history 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 concurrent medical history feature in the patient's medical history features was normalized, and the normalized result was used as the degree of association between the target medical history feature and upper gastrointestinal bleeding.

4. The method for predicting upper gastrointestinal bleeding by combining patient's past medical history analysis according to claim 1, characterized in that, The determination of the similarity of past medical history between the patient to be analyzed and historical patients based on the correlation between the characteristics of their medical history and upper gastrointestinal bleeding includes: The number of features in the union of the medical history features of the patient to be analyzed and the historical patients is obtained as the number of medical history unions. The number of features in the intersection set of the medical history features of the patient to be analyzed and the historical patients is obtained as the number of medical history intersections; The ratio of the number of intersections to the number of unions in medical histories is used as the intersection-union ratio of medical history features. The initial values ​​of the medical history features are obtained by summing the correlation between the medical history features belonging to the union of medical history sets of the patients to be analyzed and the upper gastrointestinal bleeding. The normalized value of the product of the intersection-union ratio of the medical history features and the initial value of the medical history features is used as the similarity of the past medical history between the patient to be analyzed and historical patients.

5. The method for predicting upper gastrointestinal bleeding by combining patient's past medical history analysis according to claim 1, characterized in that, The analysis examines the deviations in upper gastrointestinal tract disease characteristics between the patient under analysis and historical patients to determine the similarity of upper gastrointestinal tract disease between the patient under analysis and historical patients, including: Obtain the crossover ratio of upper gastrointestinal condition characteristics between the patient to be analyzed and historical patients, and denot it as the crossover ratio of upper gastrointestinal condition characteristics; The deviation between the data monitoring value of the upper gastrointestinal tract condition characteristics of the patient to be analyzed and the standard monitoring range is taken as the monitoring deviation value of the upper gastrointestinal tract condition characteristics of the patient to be analyzed. The product of the crossover ratio of upper gastrointestinal tract condition features and the mean of the monitoring deviation values ​​of all upper gastrointestinal tract condition features of the patient to be analyzed is used as the similarity of upper gastrointestinal tract condition between the patient to be analyzed and historical patients.

6. The method for predicting upper gastrointestinal bleeding by combining patient's past medical history analysis according to claim 5, characterized in that, The method for obtaining the crossover ratio of the upper gastrointestinal tract condition features is as follows: The number of features in the union of the upper gastrointestinal tract condition features of the patient to be analyzed and historical patients is used as the number of upper gastrointestinal tract condition unions. Obtain the number of features in the intersection set of upper gastrointestinal tract condition features of the patient to be analyzed and historical patients, and use it as the upper gastrointestinal tract condition intersection number; The ratio of the number of intersections of upper gastrointestinal lesions to the number of unions of upper gastrointestinal lesions is used as the feature intersection-union ratio of upper gastrointestinal lesions.

7. The method for predicting upper gastrointestinal bleeding by combining patient's past medical history analysis according to claim 1, characterized in that, The method for obtaining the recurrence frequency of the patient's condition to be analyzed is as follows: the number of times the patient visited the doctor for upper gastrointestinal bleeding in the medical records of the patient to be analyzed is standardized, and the standardized result value is the recurrence frequency of the patient's condition to be analyzed.

8. The method for predicting upper gastrointestinal bleeding by combining patient's past medical history analysis according to claim 1, characterized in that, The method for obtaining the medical history features is as follows: the past medical history is segmented into words, and medical feature words are extracted from the segmented words based on the hospital terminology database, and recorded as medical history features.

9. The method for predicting upper gastrointestinal bleeding by combining patient's past medical history analysis according to claim 1, characterized in that, The method for obtaining the upper gastrointestinal condition features is as follows: the past medical history is segmented into words, and medical feature words are extracted from the segmented words based on the upper gastrointestinal condition feature database, which are recorded as upper gastrointestinal condition features.

Images