A nephrology patient electronic medical record generation method and system

Abstract

The present application relates to the technical field of electronic medical record, and particularly relates to a nephrology patient electronic medical record generation method and system, the method comprising: obtaining current illness symptom information and current medical history information of a to-be-detected patient under nephrology, and historical medical history information of each historical patient under nephrology and historical illness symptom information of each historical nephrology examination; performing keyword extraction on each illness symptom information, and determining illness condition similarity corresponding to each historical nephrology examination; determining illness condition extension performance degree and medical history matching degree corresponding to each historical patient; determining target matching degree corresponding to each historical nephrology examination of each historical patient; screening out matched nephrology examinations, and generating current electronic medical record corresponding to the to-be-detected patient based on electronic medical records corresponding to the matched nephrology examinations. The present application realizes adaptive generation of patient electronic medical records, thereby improving the rationality of nephrology patient electronic medical record generation.

Description

Technical Field

[0001] This invention relates to the field of electronic medical record technology, specifically to a method and system for generating electronic medical records for nephrology patients. Background Technology

[0002] With the continuous development of medical informatization, electronic medical records (EMRs) have become an important component of modern hospital management and clinical treatment. In the field of nephrology, the application of EMRs is particularly significant. The diagnosis and treatment of kidney diseases typically require multifaceted data support, including the integration of information from hematology, imaging, urinalysis, and renal function tests. Therefore, accurately generating EMRs for nephrology patients is crucial. Currently, the method for generating patient EMRs typically involves recording changes in the patient's condition based on the physician's subjective experience.

[0003] However, when recording changes in a patient's condition based on a doctor's subjective experience to generate an electronic medical record, the following technical problems often arise:

[0004] Because the disease progression of different nephrology patients often varies, the specific conditions that need to be recorded and monitored for different nephrology patients also vary. Furthermore, the level of experience of different doctors often differs. If electronic medical records are generated directly based on the doctor's subjective experience, the generated electronic medical records for nephrology patients may be greatly influenced by the doctor's subjective factors, resulting in poor rationality of the generated electronic medical records for nephrology patients. Summary of the Invention

[0005] To address the technical problem of poor reliability in the generation of electronic medical records for nephrology patients, this invention proposes a method and system for generating electronic medical records for nephrology patients.

[0006] In a first aspect, the present invention provides a method for generating electronic medical records for nephrology patients, the method comprising:

[0007] Obtain the current condition and symptoms information and current medical history information of the patients to be tested under the nephrology department, as well as the historical medical history information and the historical condition and symptoms information of each historical nephrology examination for each historical patient under the nephrology department;

[0008] Keyword extraction is performed on each symptom information to obtain the keyword sequence corresponding to each symptom information. Based on the similarity between the keyword sequences corresponding to the current symptom information and each historical symptom information, and the intersection distribution between them, the similarity of the disease condition corresponding to the historical nephrology examination to which each historical symptom information belongs is determined.

[0009] determine a condition extension performance degree corresponding to each historical patient according to a difference between historical illness symptom information of all historical nephrology department examinations of each historical patient;

[0010] determine a history matching degree corresponding to each historical patient according to a similarity between the current history information and the historical history information corresponding to each historical patient;

[0011] determine a target matching degree corresponding to each historical nephrology department examination of each historical patient according to the condition similarity corresponding to each historical nephrology department examination of each historical patient, the history matching degree corresponding to each historical patient, and the condition extension performance degree;

[0012] screen a matching nephrology department examination from all historical nephrology department examinations according to the target matching degree, and generate a current electronic medical record corresponding to the patient to be detected based on an electronic medical record corresponding to the matching nephrology department examination.

[0013] In a possible implementation manner of the first aspect, the determination of the condition similarity corresponding to the historical nephrology department examination to which the historical illness symptom information belongs based on the similarity between the keyword sequence corresponding to the current illness symptom information and each historical illness symptom information, and the intersection distribution between them comprises:

[0014] determine a keyword similarity corresponding to each historical illness symptom information as a jaccard correlation coefficient between the keyword sequence corresponding to the current illness symptom information and the keyword sequence corresponding to each historical illness symptom information;

[0015] determine a target intersection corresponding to each historical illness symptom information as an intersection between the keyword sequence corresponding to the current illness symptom information and the keyword sequence corresponding to each historical illness symptom information;

[0016] determine a potential commonality index corresponding to each historical illness symptom information according to a presence of the target intersection corresponding to each historical illness symptom information in the keyword sequence corresponding to all historical illness symptom information;

[0017] determine the condition similarity corresponding to the historical nephrology department examination to which each historical illness symptom information belongs according to the keyword similarity corresponding to each historical illness symptom information and the potential commonality index, wherein the keyword similarity and the potential commonality index are positively correlated with the condition similarity;

[0018] A formula corresponding to the condition similarity of the historical nephrology department examination to which the historical illness symptom information belongs is:

[0019] ; wherein, is the first The condition similarity corresponding to the historical nephrology examination to which the historical disease symptom information belongs; is the serial number of the historical disease symptom information; is the serial number of the historical disease symptom information; is the keyword similarity corresponding to the historical disease symptom information; is the serial number of the historical disease symptom information; is the latent commonality index corresponding to the historical disease symptom information.

[0020] In a possible implementation manner of the first aspect, the latent commonality index corresponding to each historical disease symptom information is determined according to whether the target intersection corresponding to each historical disease symptom information exists in the keyword sequence corresponding to all historical disease symptom information, and the determination comprises:

[0021] Any one of the historical disease symptom information is determined as a marked disease symptom information, and the target intersection corresponding to the marked disease symptom information is determined as a marked intersection;

[0022] The keyword sequence in which the marked intersection exists is screened out from the keyword sequence corresponding to all historical disease symptom information as a reference word sequence, and a reference word sequence set corresponding to the marked disease symptom information is obtained;

[0023] All keywords in the keyword sequence corresponding to the marked disease symptom information except the marked intersection constitute a first candidate word set corresponding to the marked disease symptom information;

[0024] All keywords in the keyword sequence corresponding to the current disease symptom information except the marked intersection constitute a second candidate word set corresponding to the marked disease symptom information;

[0025] The latent commonality index corresponding to the marked disease symptom information is determined according to the number of times that the keywords in the first candidate word set and the second candidate word set corresponding to the marked disease symptom information appear in the reference word sequence set corresponding thereto.

[0026] In a possible implementation manner of the first aspect, the formula corresponding to the latent commonality index corresponding to the historical disease symptom information is:

[0027] ;

[0028] ;

[0029] ; wherein, is the latent commonality index corresponding to the historical disease symptom information; is the serial number of the historical disease symptom information; is the serial number of the historical disease symptom information; is a normalization function; It is an absolute value function; It is the first The average number of times all keywords in the first candidate word set corresponding to a historical disease symptom information appear in its corresponding reference word sequence set; It is the first The average number of times all keywords in the second candidate word set corresponding to a historical medical condition and symptom information appear in its corresponding reference word sequence set; It is the first The number of keywords in the first candidate word set corresponding to each historical medical symptom information; It is the first The index of the keyword in the first candidate word set corresponding to each historical medical symptom information; It is the first In the first candidate word set corresponding to each historical symptom information, the first... The keyword in the first The number of times it appears in the reference word sequence set corresponding to each historical symptom; It is the first The number of reference word sequences in the set of reference word sequences corresponding to each historical symptom; It is the first The number of keywords in the second candidate word set corresponding to each historical medical symptom information; It is the first The sequence number of the keywords in the second candidate word set corresponding to each historical medical symptom information; It is the first In the second candidate word set corresponding to historical medical symptom information, the first The keyword in the first The number of times a historical symptom information appears in the reference word sequence set.

[0030] In conjunction with the first aspect above, in one possible implementation, determining the disease extension manifestation degree for each historical patient based on the differences in historical nephrology examination information across all historical nephrology examinations includes:

[0031] Any historical patient is identified as a marker patient, and each historical nephrology examination of the marker patient, except for the first historical nephrology examination, is identified as a candidate nephrology examination. Any candidate nephrology examination is identified as a marker nephrology examination.

[0032] The union of the keyword sequences corresponding to the historical symptom information of all historical nephrology examinations prior to the marked nephrology examination of the marked patient is determined as the temporary keyword information corresponding to the marked nephrology examination;

[0033] The number of keywords in the keyword sequence corresponding to the marked nephrology examination that do not belong to the corresponding temporary keyword information is determined as the number of new conditions corresponding to the marked nephrology examination. The number of new conditions corresponding to the marked nephrology examination represents the difference between the marked nephrology examination and the historical symptom information of its previous historical nephrology examination.

[0034] The extent of disease extension for the marked patient is determined based on the number of new lesions corresponding to all candidate nephrology examinations.

[0035] In conjunction with the first aspect above, in one possible implementation, determining the extent of disease extension for the marked patient based on the number of new conditions corresponding to all candidate nephrology examinations includes:

[0036] The mean of the number of new lesions corresponding to all candidate nephrology examinations is determined as the lesion extension performance degree for the labeled patient.

[0037] In conjunction with the first aspect above, in one possible implementation, determining the medical history matching degree for each historical patient based on the similarity between the current medical history information and the historical medical history information corresponding to each historical patient includes:

[0038] The Jaccard correlation coefficient between the current medical history information and the historical medical history information corresponding to each historical patient is used to determine the medical history matching degree for each historical patient.

[0039] In conjunction with the first aspect above, in one possible implementation, the formula for the target matching degree corresponding to the historical nephrology examinations of historical patients is:

[0040] ;in, It is the first The first historical patient The target matching degree corresponding to each historical nephrology examination; These are the serial numbers of historical patients; It is the first The order of nephrology examinations for a patient with a history of nephrology. It is the first The first historical patient Similarity of medical conditions between previous nephrology examinations; It is a preset factor, and its value range is (0.5, 1). It is a normalization function; It is the first The extent of disease progression corresponding to each historical patient; It is the first The degree of matching of medical history with each historical patient.

[0041] With the first aspect above, in a possible implementation, the filtering, according to the target matching degree, the matching nephrology examination from all the historical nephrology examinations comprises:

[0042] filtering, from all the historical nephrology examinations, a historical nephrology examination corresponding to the largest target matching degree as the matching nephrology examination.

[0043] The second aspect provides a nephrology patient electronic medical record generation system, which comprises:

[0044] a data acquisition module configured to acquire current illness symptom information and current medical history information of a patient to be detected under nephrology, and historical medical history information of each historical patient under nephrology and historical illness symptom information of each historical nephrology examination;

[0045] a keyword extraction and determination module configured to extract keywords from each illness symptom information to obtain a keyword sequence corresponding to each illness symptom information, and determine illness condition similarity of a historical nephrology examination corresponding to each historical illness symptom information based on similarity between the current illness symptom information and the keyword sequence corresponding to each historical illness symptom information, and intersection distribution between them;

[0046] an illness condition extension performance degree determination module configured to determine illness condition extension performance degree of each historical patient according to difference between the historical illness symptom information of all the historical nephrology examinations of each historical patient;

[0047] a medical history matching degree determination module configured to determine medical history matching degree of each historical patient according to similarity between the current medical history information and the historical medical history information of each historical patient;

[0048] a target matching degree determination module configured to determine target matching degree of each historical nephrology examination of each historical patient according to the illness condition similarity of each historical nephrology examination of each historical patient, the medical history matching degree and the illness condition extension performance degree of each historical patient;

[0049] a screening medical record generation module configured to filter, according to the target matching degree, the matching nephrology examination from all the historical nephrology examinations, and generate the current electronic medical record of the patient to be detected based on the electronic medical record corresponding to the matching nephrology examination.

[0050] The third aspect provides a server comprising a memory and a processor. The memory is configured to store executable program code, and the processor is configured to call and run the executable program code from the memory, so that the device executes the method in the first aspect or any possible implementation of the first aspect.

[0051] In a fourth aspect, a computer program product is provided, which comprises computer program code, which, when executed on a computer, causes the computer to perform the method according to the first aspect or any possible implementation of the first aspect.

[0052] In a fifth aspect, a computer-readable storage medium is provided, which stores computer program code, which, when executed on a computer, causes the computer to perform the method according to the first aspect or any possible implementation of the first aspect.

[0053] The present application has the following beneficial effects:

[0054] The electronic medical record generation method for a nephrology department patient of the present application realizes adaptive generation of the electronic medical record of the patient, solves the technical problem of poor rationality of the electronic medical record generation for the nephrology department patient, and thus improves the rationality of the electronic medical record generation for the nephrology department patient. Compared with directly generating the electronic medical record based on the subjective experience of the doctor, when generating the electronic medical record of the nephrology department patient, the present application comprehensively analyzes the matching condition between the current condition, symptom and medical history of the to-be-detected patient and the condition, symptom and medical history of different historical patients corresponding to different historical nephrology department examinations, thereby quantifying a plurality of features related to the matching condition, such as condition similarity, condition extension performance, medical history matching degree and target matching degree, and further screening the historical nephrology department examination representing the matching of the nephrology department examination of the to-be-detected patient, i.e., the matching nephrology department examination. Since the nephrology department examination of the to-be-detected patient is similar to the matching nephrology department examination, the electronic medical record corresponding to the matching nephrology department examination can be referred to when generating the electronic medical record of the to-be-detected patient, thereby assisting the doctor to better design the electronic medical record of the to-be-detected patient, and thus improving the rationality of the electronic medical record generation for the nephrology department patient. BRIEF DESCRIPTION OF DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, and the advantages thereof, a brief introduction will be given to the drawings needed in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0056] Figure 1 The flow chart of the electronic medical record generation method for a nephrology department patient of the present application;

[0057] Figure 2 The composition structure schematic diagram of the electronic medical record generation system for a nephrology department patient of the present application;

[0058] Figure 3 FIG. 1 is a structural schematic diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to further clarify the technical means and effects of the present application adopted to achieve the predetermined inventive objectives, the specific implementation, structure, features and effects of the technical solutions according to the present application are described in detail below in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0060] 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 the present application belongs.

[0061] Reference Figure 1 FIG. 1 is a flowchart illustrating some embodiments of a method for generating an electronic medical record of a nephrology patient according to the present application. The method for generating an electronic medical record of a nephrology patient includes the following steps:

[0062] Step S1, obtaining current illness symptom information and current medical history information of a to-be-detected patient under nephrology, and historical medical history information of each historical patient under nephrology and historical illness symptom information of each historical nephrology examination.

[0063] The to-be-detected patient can be a nephrology patient to be generated an electronic medical record. The historical patient can be a patient who has been treated by nephrology examination. The current illness symptom information can be illness symptom information obtained by the to-be-detected patient in the last nephrology examination. The historical illness symptom information can be illness symptom information obtained by the historical patient in each historical nephrology examination. The illness symptom information can represent the illness symptoms of the patient. For example, the illness symptom information can include but is not limited to edema, proteinuria and hematuria. The historical nephrology examination can be a nephrology examination that has been performed on the historical patient. The current medical history information can be medical history information representing the past medical history of the patient, which is counted when the to-be-detected patient is examined by nephrology in the last time. The historical medical history information can be medical history information representing the past medical history of the corresponding historical patient, which is counted when the historical patient is examined by nephrology in the last time. The medical history information can be composed of the name of the past medical history.

[0064] It's important to note that nephrology typically treats kidney-related diseases, most of which are chronic. Nephrology patients often have complex and diverse conditions, many of which are chronic and progressive. They experience long-term health impacts from their condition, and their clinical manifestations vary at different stages. For example, patients may have no obvious symptoms in the early stages, while as the disease progresses, they may experience various symptoms such as fatigue, nausea, and edema. Therefore, obtaining information about the patient's symptoms is crucial for subsequent analysis of the severity of their illness.

[0065] Meanwhile, nephrology patients are often prone to multiple complications during disease progression, such as cardiovascular diseases like hypertension, coronary heart disease, and heart failure. Furthermore, treatment often requires multidisciplinary collaboration, adding to the complexity of the process. Therefore, obtaining the patient's past medical history can, to some extent, help analyze potential complications.

[0066] As an example, firstly, the patient's medical history and symptoms from their most recent nephrology examination can be recorded, serving as current medical history and current symptom information, respectively. Next, the name of each patient's past medical history from their last nephrology examination can be recorded, forming the historical medical history for each patient. Finally, the symptom information from each subsequent nephrology examination can be recorded, serving as historical symptom information.

[0067] Step S2: Extract keywords for each symptom information to obtain the keyword sequence corresponding to each symptom information. Based on the similarity between the keyword sequences corresponding to the current symptom information and each historical symptom information, and the intersection distribution between them, determine the similarity of the condition to the historical nephrology examination to which each historical symptom information belongs.

[0068] As an example, this step may include the following steps:

[0069] The first step is to extract keywords from each symptom information to obtain the keyword sequence corresponding to each symptom information.

[0070] For example, the jieba word segmentation technology can be used to segment each symptom information, resulting in a word set corresponding to each symptom. Words representing nephrology symptoms can then be selected from these sets as keywords. All keywords in the word set corresponding to each symptom can be combined to form a keyword sequence for that symptom. This keyword sequence can be obtained by randomly sorting the keywords.

[0071] Secondly, the Jaccard correlation coefficient between the keyword sequence corresponding to the current illness symptom information and the keyword sequence corresponding to each historical illness symptom information is determined as the keyword similarity corresponding to each historical illness symptom information.

[0072] It should be noted that the greater the keyword similarity corresponding to the historical illness symptom information, the more similar the keyword sequence corresponding to the current illness symptom information and the keyword sequence corresponding to the historical illness symptom information, and the more similar the nephrology examination result corresponding to the current illness symptom information and the nephrology examination result corresponding to the historical illness symptom information.

[0073] Thirdly, the intersection between the keyword sequence corresponding to the current illness symptom information and the keyword sequence corresponding to each historical illness symptom information is determined as the target intersection corresponding to each historical illness symptom information.

[0074] Fourthly, according to the existence of the target intersection corresponding to each historical illness symptom information in the keyword sequence corresponding to all historical illness symptom information, the potential commonality index corresponding to each historical illness symptom information can include the following sub-steps:

[0075] Firstly, any one historical illness symptom information is determined as a marked illness symptom information, and the target intersection corresponding to the marked illness symptom information is determined as a marked intersection.

[0076] Secondly, the keyword sequence in which the marked intersection exists is screened out from the keyword sequence corresponding to all historical illness symptom information as a reference word sequence, and a reference word sequence set corresponding to the marked illness symptom information is obtained.

[0077] Thirdly, all keywords in the keyword sequence corresponding to the marked illness symptom information except the marked intersection constitute a first candidate word set corresponding to the marked illness symptom information.

[0078] Fourthly, all keywords in the keyword sequence corresponding to the current illness symptom information except the marked intersection constitute a second candidate word set corresponding to the marked illness symptom information.

[0079] Fifthly, according to the number of times of the keywords in the first candidate word set and the second candidate word set corresponding to the marked illness symptom information appearing in the reference word sequence set corresponding thereto, the potential commonality index corresponding to the marked illness symptom information is determined.

[0080] Wherein, any one keyword in the first candidate word set and the second candidate word set corresponding to the marked illness symptom information is recorded as the first keyword, the first reference word sequence set corresponding to the marked illness symptom information is recorded as the first reference word sequence set, and the acquisition method of the number of times of occurrence of the first keyword in the first reference word sequence set can be: filtering the reference word sequence containing the first keyword from the first reference word sequence set as a temporary reference word sequence, and recording the number of temporary reference word sequences as the number of times of occurrence of the first keyword in the first reference word sequence set.

[0081] For example, the formula corresponding to the potential commonality index of the historical illness symptom information can be:

[0082] ;

[0083] ;

[0084] ; wherein, is the potential commonality index corresponding to the i-th historical illness symptom information. is the serial number of the historical illness symptom information. is a normalization function. is an absolute value function. is the average number of times of occurrence of all keywords in the first candidate word set corresponding to the i-th historical illness symptom information in the reference word sequence set corresponding thereto. is the average number of times of occurrence of all keywords in the second candidate word set corresponding to the i-th historical illness symptom information in the reference word sequence set corresponding thereto. is the number of keywords in the first candidate word set corresponding to the i-th historical illness symptom information. is the serial number of the keyword in the first candidate word set corresponding to the i-th historical illness symptom information. is the number of times of occurrence of the j-th keyword in the first candidate word set corresponding to the i-th historical illness symptom information in the reference word sequence set corresponding to the i-th historical illness symptom information. is the number of times of occurrence of the j-th keyword in the first candidate word set corresponding to the i-th historical illness symptom information in the reference word sequence set corresponding to the i-th historical illness symptom information. is the number of keywords in the second candidate word set corresponding to the i-th historical illness symptom information. is the serial number of the keyword in the second candidate word set corresponding to the i-th historical illness symptom information. is the number of times of occurrence of the j-th keyword in the second candidate word set corresponding to the i-th historical illness symptom information in the reference word sequence set corresponding to the i-th historical illness symptom information. is the number of times of occurrence of the j-th keyword in the second candidate word set corresponding to the i-th historical illness symptom information in the reference word sequence set corresponding to the i-th historical illness symptom information. is the number of reference word sequences in the reference word sequence set corresponding to the i-th historical illness symptom information. is the number of reference word sequences in the reference word sequence set corresponding to the i-th historical illness symptom information. is the number of reference word sequences in the reference word sequence set corresponding to the i-th historical illness symptom information. is the number of reference word sequences in the reference word sequence set corresponding to the i-th historical illness symptom information. is the number of reference word sequences in the reference word sequence set corresponding to the i-th historical illness symptom information. is the number of reference word sequences in the reference word sequence set corresponding to the i-th historical illness symptom information. is the number of reference word sequences in the reference word sequence set corresponding to the i-th historical illness symptom information. is the number of reference word sequences in the reference word sequence set corresponding to the i-th historical illness symptom information. The sequence number of the keywords in the second candidate word set corresponding to each historical medical symptom information. It is the first In the second candidate word set corresponding to historical medical symptom information, the first The keyword in the first The number of times a historical symptom information appears in the reference word sequence set.

[0085] It should be noted that, in reality, for the same condition, individual differences often lead to different symptoms. For example, acute kidney injury may present with different symptoms such as low urine output, high urine specific gravity, or kidney enlargement in different patients, even though they are essentially presenting the same condition. Furthermore, these symptoms tend to occur at similar frequencies under the same condition. It can characterize the first The occurrence of symptoms that differ from the current symptoms in historical medical records. It can characterize the current symptoms and information related to the first... The symptoms appear differently depending on the historical medical history. Therefore, when The larger the value, the more likely it is to indicate the current symptoms and the stage of the illness. The more similar the occurrence of different symptoms among historical medical records, the more likely it is that the current symptoms are related to the previous ones. The more historical medical symptom information is likely to represent the same condition, the more likely it is that the current medical symptom information and the first... There is a certain potential connection between historical medical symptom information.

[0086] The fifth step is to determine the similarity of the disease condition to the historical nephrology examination corresponding to each historical symptom information based on the keyword similarity and potential common indicators.

[0087] Among them, keyword similarity and potential common indicators can both be positively correlated with disease similarity.

[0088] For example, the formula for determining the similarity of historical symptom information to corresponding historical nephrology examinations can be:

[0089] ;in, It is the first The similarity of the patient's historical symptoms to the corresponding historical nephrology examination. It is the serial number of the historical medical condition and symptoms information. It is the first Keyword similarity corresponding to historical medical symptom information. It is the first The potential commonality index corresponding to the historical illness symptom information of the first historical nephrology examination.

[0090] It should be noted that, when is larger, it often indicates that the current illness symptom information and the historical illness symptom information of the first historical nephrology examination are more likely to represent the same illness, and that there is a certain potential relationship between the current illness symptom information and the historical illness symptom information of the first historical nephrology examination. is larger, it often indicates that the current illness symptom information and the historical illness symptom information of the first historical nephrology examination are more similar. is larger, it often indicates that the current illness symptom information and the historical illness symptom information of the first historical nephrology examination are more likely to represent the same illness, and that there is a certain potential relationship between the current illness symptom information and the historical illness symptom information of the first historical nephrology examination. is larger, it often indicates that the current illness symptom information and the historical illness symptom information of the first historical nephrology examination are more similar. is larger, it often indicates that the current illness symptom information and the historical illness symptom information of the first historical nephrology examination are more likely to represent the same illness, and that there is a certain potential relationship between the current illness symptom information and the historical illness symptom information of the first historical nephrology examination. is larger, it often indicates that the current illness symptom information and the historical illness symptom information of the first historical nephrology examination are more similar. is larger, it often indicates that the current illness symptom information and the historical illness symptom information of the first historical nephrology examination are more likely to represent the same illness, and that there is a certain potential relationship between the current illness symptom information and the historical illness symptom information of the first historical nephrology examination. is larger, it often indicates that the current illness symptom information and the historical illness symptom information of the first historical nephrology examination are more similar. is larger, it often indicates that the current illness symptom information and the historical illness symptom information of the first historical nephrology examination are more likely to represent the same illness, and that there is a certain potential relationship between the current illness symptom information and the historical illness symptom information of the first historical nephrology examination.

[0091] Step S3, according to the difference between the historical illness symptom information of all historical nephrology examinations of each historical patient, determine the disease extension performance degree corresponding to each historical patient.

[0092] As an example, the present step can include the following steps:

[0093] Firstly, any one historical patient is determined as a marker patient, and all historical nephrology examinations of the marker patient except the first historical nephrology examination are determined as candidate nephrology examinations, and any one candidate nephrology examination is determined as a marker nephrology examination.

[0094] Secondly, the union of the keyword sequences corresponding to the historical illness symptom information of all historical nephrology examinations before the marker nephrology examination of the marker patient is determined as the temporary keyword information corresponding to the marker nephrology examination.

[0095] Thirdly, the number of keywords in the keyword sequence corresponding to the marker nephrology examination which do not belong to the keywords in the temporary keyword information corresponding to the marker nephrology examination is determined as the number of new diseases corresponding to the marker nephrology examination.

[0096] The number of new diseases corresponding to the marker nephrology examination can represent the difference between the marker nephrology examination and the historical illness symptom information of the historical nephrology examination before it.

[0097] Fourthly, according to the number of new diseases corresponding to all candidate nephrology examinations, determine the disease extension performance degree corresponding to the marker patient.

[0098] For example, the average of the number of new conditions corresponding to all candidate nephrology examinations can be determined as the condition extension performance degree corresponding to the marked patient.

[0099] For example, the formula corresponding to the condition extension performance degree of the historical patient can be:

[0100] , wherein, is the condition extension performance degree corresponding to the historical patient. is the serial number of the historical patient. is the number of historical nephrology examinations of the historical patient. is the serial number of the historical nephrology examination of the historical patient. is the number of new conditions corresponding to the historical nephrology examination of the historical patient. is the serial number of the historical nephrology examination of the historical patient. is the number of new conditions corresponding to the historical nephrology examination of the historical patient. is the number of new conditions corresponding to the historical nephrology examination of the historical patient. It should be noted that when is larger, it often means that the

[0101] historical patient has more new symptoms at the historical nephrology examination, which often means that the historical nephrology examination of the historical patient is more meaningful. Therefore, when is larger, it often means that the historical patient has more new symptoms at multiple historical nephrology examinations, which often means that the condition development of the historical patient is more meaningful.

[0102] Step S4, according to the similarity between the current medical history information and the historical medical history information corresponding to each historical patient, determine the medical history matching degree corresponding to each historical patient.

[0103] As an example, the jaccard correlation coefficient between the current medical history information and the historical medical history information corresponding to each historical patient can be determined as the medical history matching degree corresponding to each historical patient.

[0104] ​​It's important to note that different conditions often influence each other, so a patient's past medical history frequently affects the development of their nephrological diseases. For example, a history of hypertension can damage renal blood vessels, leading to glomerulosclerosis and decreased renal function. Conversely, heart failure can impair blood circulation, reducing renal blood flow and affecting filtration and excretion, potentially causing acute kidney injury or worsening chronic kidney disease. Therefore, a higher match between a patient's medical history and the patient being tested generally indicates a greater likelihood that the patient with that history has the same nephrological disease.

[0105] Step S5: Based on the similarity of the condition corresponding to each historical nephrology examination of each historical patient, the matching degree of the medical history corresponding to each historical patient, and the extension of the condition, determine the target matching degree corresponding to each historical nephrology examination of each historical patient.

[0106] As an example, the formula for determining the target match degree for a patient's historical nephrology examinations can be:

[0107] ;in, It is the first The first historical patient The target matching degree corresponding to each historical nephrology examination. It is the serial number of the patient in history. It is the first The order of nephrology examinations for a patient with a history of illness. It is the first The first historical patient Similarity of the disease conditions corresponding to the previous nephrology examinations. This is a preset factor, and its value range can be (0.5, 1), for example, It can be 0.6. It is a normalization function. It is the first The extent of disease progression corresponding to each historical patient. It is the first The degree of matching of medical history with each historical patient.

[0108] It should be noted that when The larger the value, the more likely it is to indicate the first The first historical patient The more similar the composite symptoms obtained from previous nephrology examinations are to the composite symptoms obtained from the patient's most recent nephrology examination, the better. yes The weight. yes The weight. When The larger the value, the more likely it is to indicate the first The more new symptoms that appear in multiple historical nephrology examinations of a historical patient, the more indicative of the development of the disease of the first historical patient is. The greater the value of the first historical patient, the more similar the current medical history information of the patient to be detected is to the historical medical history information of the first historical patient, the more similar the medical history between the patient to be detected and the first historical patient is, and the greater the possibility that the first historical patient and the patient to be detected have the same nephrology disease. The greater the value of the first historical patient, the more similar the current medical history information of the patient to be detected is to the historical medical history information of the first historical patient, the more similar the medical history between the patient to be detected and the first historical patient is, and the greater the possibility that the first historical patient and the patient to be detected have the same nephrology disease. The greater the value of the first historical patient, the more similar the current medical history information of the patient to be detected is to the historical medical history information of the first historical patient, the more similar the medical history between the patient to be detected and the first historical patient is, and the greater the possibility that the first historical patient and the patient to be detected have the same nephrology disease. The greater the value of the first historical patient, the more similar the current medical history information of the patient to be detected is to the historical medical history information of the first historical patient, the more similar the medical history between the patient to be detected and the first historical patient is, and the greater the possibility that the first historical patient and the patient to be detected have the same nephrology disease. The greater the value of the first historical patient, the more similar the current medical history information of the patient to be detected is to the historical medical history information of the first historical patient, the more similar the medical history between the patient to be detected and the first historical patient is, and the greater the possibility that the first historical patient and the patient to be detected have the same nephrology disease. The greater the value of the first historical patient, the more similar the current medical history information of the patient to be detected is to the historical medical history information of the first historical patient, the more similar the medical history between the patient to be detected and the first historical patient is, and the greater the possibility that the first historical patient and the patient to be detected have the same nephrology disease. The greater the value of the first historical patient, the more similar the current medical history information of the patient to be detected is to the historical medical history information of the first historical patient, the more similar the medical history between the patient to be detected and the first historical patient is, and the greater the possibility that the first historical patient and the patient to be detected have the same nephrology disease. The greater the value of the first historical patient, the more similar the current medical history information of the patient to be detected is to the historical medical history information of the first historical patient, the more similar the medical history between the patient to be detected and the first historical patient is, and the greater the possibility that the first historical patient and the patient to be detected have the same nephrology disease. The greater the value of the first historical patient, the more similar the current medical history information of the patient to be detected is to the historical medical history information of the first historical patient, the more similar the medical history between the patient to be detected and the first historical patient is, and the greater the possibility that the first historical patient and the patient to be detected have the same nephrology disease. The greater the value of the first historical patient, the more similar the current medical history information of the patient to be detected is to the historical medical history information of the first historical patient, the more similar the medical history between the patient to be detected and the first historical patient is, and the greater the possibility that the first historical patient and the patient to be detected have the same nephrology disease.

[0109] Step S6: According to the target matching degree, the matching nephrology examination is screened from all historical nephrology examinations, and the current electronic medical record corresponding to the patient to be detected is generated based on the electronic medical record corresponding to the matching nephrology examination.

[0110] It should be noted that after each historical nephrology examination, the doctor will record an electronic medical record about the nephrology diagnosis of the patient.

[0111] As an example, the present step can include the following steps:

[0112] First, the historical nephrology examination corresponding to the greatest target matching degree is screened from all historical nephrology examinations as the matching nephrology examination.

[0113] Second, the current electronic medical record corresponding to the patient to be detected is generated based on the electronic medical record corresponding to the matching nephrology examination.

[0114] For example, the electronic medical record corresponding to the matching nephrology examination can be recommended to the doctor to assist the doctor in generating the electronic medical record of the patient to be detected at the recent nephrology examination as the current electronic medical record.

[0115] Alternatively, the method of generating the current electronic medical record corresponding to the patient to be detected can also be: the matching nephrology examination of the historical patient and the electronic medical record corresponding to the historical nephrology examination before the matching nephrology examination are recommended to the doctor to assist the doctor in generating the electronic medical record of the patient to be detected at the recent nephrology examination as the current electronic medical record.

[0116] Reference Figure 2, based on the same inventive concept as the method embodiments described above, the present application provides a nephrology patient electronic medical record generation system, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the computer program implements the steps of a nephrology patient electronic medical record generation method when executed by the processor, and can specifically include:

[0117] The data acquisition module 201 is configured to acquire current illness symptom information and current medical history information of a patient to be detected under nephrology, and historical medical history information and historical illness symptom information of each historical patient under nephrology and each historical nephrology examination;

[0118] The keyword extraction and determination module 202 is configured to extract keywords from each illness symptom information to obtain a keyword sequence corresponding to each illness symptom information, and determine a condition similarity of a historical nephrology examination corresponding to each historical illness symptom information based on a similarity between the current illness symptom information and the keyword sequence corresponding to each historical illness symptom information, and a distribution of an intersection therebetween.

[0119] The condition extension performance degree determination module 203 is configured to determine a condition extension performance degree corresponding to each historical patient according to a difference between the historical illness symptom information of all historical nephrology examinations of each historical patient.

[0120] The medical history matching degree determination module 204 is configured to determine a medical history matching degree corresponding to each historical patient according to a similarity between the current medical history information and the historical medical history information corresponding to each historical patient.

[0121] The target matching degree determination module 205 is configured to determine a target matching degree corresponding to each historical nephrology examination of each historical patient according to the condition similarity corresponding to each historical nephrology examination of each historical patient, the medical history matching degree and the condition extension performance degree corresponding to each historical patient.

[0122] The screened medical record generation module 206 is configured to screen a matching nephrology examination from all historical nephrology examinations according to the target matching degree, and generate a current electronic medical record corresponding to the patient to be detected based on an electronic medical record corresponding to the matching nephrology examination.

[0123] Figure 3 is a structural schematic diagram of a computer device provided by an embodiment of the present application. As shown in Figure 3 the computer device 300 includes a memory 301, a processor 302 and a computer program 303 stored in the memory 301 and running on the processor 302, wherein the processor 302 executes the computer program 303, so that the computer device can execute any one of the nephrology patient electronic medical record generation methods introduced above.

[0124] Based on the same inventive concept as the above method embodiments, the present application provides a server comprising a memory and a processor. The memory is configured to store executable program code, and the processor is configured to call and run the executable program code from the memory, so that the device executes any one of the above-mentioned nephrology patient electronic medical record generation methods.

[0125] Based on the same inventive concept as the above method embodiments, the present application provides a computer program product comprising: computer program code, which, when executed on a computer, causes the computer to execute any one of the above-mentioned nephrology patient electronic medical record generation methods.

[0126] Based on the same inventive concept as the above method embodiments, the present application provides a computer-readable storage medium storing computer program code, which, when executed on a computer, causes the computer to execute any one of the above-mentioned nephrology patient electronic medical record generation methods.

[0127] In summary, compared with directly generating an electronic medical record based on the subjective experience of a doctor, in the present application, when generating an electronic medical record of a nephrology patient, the matching conditions between the current condition, symptoms and medical history of the patient to be detected and the condition, symptoms and medical history of different historical patients corresponding to different historical nephrology examinations are comprehensively analyzed, thereby quantifying a plurality of features related to the matching conditions, such as condition similarity, condition extension performance, medical history matching degree and target matching degree, and then screening out historical nephrology examinations representing the matching of the nephrology examination of the patient to be detected, i.e. matching nephrology examinations. Since the nephrology examination of the patient to be detected is similar to the matching nephrology examination, when generating the electronic medical record of the patient to be detected, the electronic medical record corresponding to the matching nephrology examination can be referred to, thereby assisting the doctor to better design the electronic medical record of the patient to be detected, and thereby improving the rationality of the nephrology patient electronic medical record generation.

[0128] The above embodiments are only used to illustrate the technical solutions of the present application, but not limit it; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for generating an electronic medical record for a patient in a nephrology department, characterized by, The method comprises the following steps: obtaining current illness symptom information and current medical history information of a patient to be detected under a nephrology department, and historical medical history information and historical illness symptom information of each historical patient under the nephrology department; extracting keywords from each illness symptom information to obtain a keyword sequence corresponding to each illness symptom information, and determining a condition similarity corresponding to each historical illness symptom information based on a similarity between the current illness symptom information and the keyword sequence corresponding to each historical illness symptom information, and a distribution of an intersection between them; determining a condition extension performance degree corresponding to each historical patient based on a difference between the historical illness symptom information of all historical nephrology examinations of each historical patient; determining a medical history matching degree corresponding to each historical patient based on a similarity between the current medical history information and the historical medical history information corresponding to each historical patient; determining a target matching degree corresponding to each historical nephrology examination of each historical patient based on the condition similarity corresponding to each historical nephrology examination of each historical patient, the medical history matching degree corresponding to each historical patient, and the condition extension performance degree; generating a current electronic medical record corresponding to the patient to be detected based on the matching nephrology examination and the electronic medical record corresponding to the matching nephrology examination; The method further comprises the following steps: determining any one historical patient as a marker patient, and determining each historical nephrology examination of the marker patient except for the first historical nephrology examination as a candidate nephrology examination, and determining any one candidate nephrology examination as a marker nephrology examination; determining a union set of the keyword sequences corresponding to the historical illness symptom information of all historical nephrology examinations before the marker nephrology examination of the marker patient as temporary keyword information corresponding to the marker nephrology examination; determining a number of keywords in the keyword sequence corresponding to the marker nephrology examination that do not belong to the temporary keyword information corresponding to the marker nephrology examination as a number of new conditions corresponding to the marker nephrology examination, wherein the number of new conditions corresponding to the marker nephrology examination represents a difference between the marker nephrology examination and the historical illness symptom information of the historical nephrology examination before the marker nephrology examination; determining a condition extension performance degree corresponding to the marker patient based on the number of new conditions corresponding to all candidate nephrology examinations.

2. The method of claim 1, wherein, The method further comprises the following steps: determining a keyword similarity corresponding to each historical illness symptom information as a Jaccard correlation coefficient between the keyword sequence corresponding to the current illness symptom information and the keyword sequence corresponding to each historical illness symptom information; An intersection between the keyword sequence corresponding to the current illness symptom information and the keyword sequence corresponding to each historical illness symptom information is determined as a target intersection corresponding to each historical illness symptom information; A potential commonality index corresponding to each historical illness symptom information is determined according to a presence of the target intersection corresponding to each historical illness symptom information in the keyword sequence corresponding to all historical illness symptom information; A condition similarity corresponding to the historical nephrology examination to which the historical illness symptom information belongs is determined according to the keyword similarity and the potential commonality index corresponding to each historical illness symptom information, wherein the keyword similarity and the potential commonality index are positively correlated with the condition similarity; A formula corresponding to the condition similarity corresponding to the historical nephrology examination to which the historical illness symptom information belongs is: ; wherein, is a condition similarity corresponding to a historical nephrology examination of the th historical illness symptom information; is a serial number of the historical illness symptom information; is a condition similarity corresponding to a historical nephrology examination of the th historical illness symptom information; is a keyword similarity corresponding to the th historical illness symptom information.

3. The method of claim 2, wherein the method further comprises: The determination of the potential commonality index corresponding to each historical illness symptom information according to the presence of the target intersection corresponding to each historical illness symptom information in the keyword sequence corresponding to all historical illness symptom information includes: Any one historical illness symptom information is determined as a marker illness symptom information, and a target intersection corresponding to the marker illness symptom information is determined as a marker intersection; A keyword sequence in which the marker intersection exists is screened out from the keyword sequence corresponding to all historical illness symptom information as a reference word sequence, to obtain a reference word sequence set corresponding to the marker illness symptom information; All keywords in the keyword sequence corresponding to the marker illness symptom information except the marker intersection constitute a first candidate word set corresponding to the marker illness symptom information; All keywords in the keyword sequence corresponding to the current illness symptom information except the marker intersection constitute a second candidate word set corresponding to the marker illness symptom information; A potential commonality index corresponding to the marker illness symptom information is determined according to a number of times that the keywords in the first candidate word set and the second candidate word set corresponding to the marker illness symptom information appear in the reference word sequence set corresponding thereto.

4. The method of claim 3, wherein, A formula corresponding to the potential commonality index corresponding to the historical illness symptom information is: ； ； ; wherein, is the th latent commonality indicator corresponding to the th historical illness symptom information; is a normalization function; is an absolute value function; ; wherein, is the average number of occurrences of all keywords in the first candidate word set corresponding to the th historical illness symptom information in the reference word sequence set corresponding thereto; is the average number of occurrences of all keywords in the second candidate word set corresponding to the th historical illness symptom information in the reference word sequence set corresponding thereto; is the number of keywords in the first candidate word set corresponding to the th historical illness symptom information; is the sequence number of a keyword in the first candidate word set corresponding to the th historical illness symptom information; is the number of occurrences of the th keyword in the first candidate word set corresponding to the th historical illness symptom information in the reference word sequence set corresponding thereto; is the number of reference word sequences in the reference word sequence set corresponding to the th historical illness symptom information; is the number of keywords in the second candidate word set corresponding to the th historical illness symptom information; is the sequence number of a keyword in the second candidate word set corresponding to the th historical illness symptom information; is the number of occurrences of the th keyword in the second candidate word set corresponding to the th historical illness symptom information in the reference word sequence set corresponding thereto; and is the number of reference word sequences in the reference word sequence set corresponding to the th historical illness symptom information.

5. The method of claim 1, wherein the method further comprises: The determination of the condition extension performance degree corresponding to the marker patient according to the number of new conditions corresponding to all candidate nephrology examinations includes: An average of the number of new conditions corresponding to all candidate nephrology examinations is determined as the condition extension performance degree corresponding to the marker patient.

6. The method of claim 1, wherein the method further comprises: The determination of the medical history matching degree corresponding to each historical patient according to a similarity between the current medical history information and the historical medical history information corresponding to each historical patient includes: A Jaccard correlation coefficient between the current medical history information and the historical medical history information corresponding to each historical patient is determined as the medical history matching degree corresponding to each historical patient.

7. The method of claim 1, wherein the method further comprises: A formula corresponding to the target matching degree corresponding to the historical nephrology examination of the historical patient is: ;in, It is the first The first historical patient The target matching degree corresponding to each historical nephrology examination; These are the serial numbers of historical patients; It is the first The order of nephrology examinations for a patient with a history of nephrology. It is the first The first historical patient Similarity of medical conditions between previous nephrology examinations; It is a preset factor, and its value range is (0.5, 1). It is a normalization function; It is the first The extent of disease progression corresponding to each historical patient; It is the first The degree of matching of medical history with each historical patient.

8. The method of claim 1, wherein, The screening of the matching nephrology examination from all historical nephrology examinations according to the target matching degree includes: A historical nephrology examination corresponding to the maximum target matching degree is screened out from all historical nephrology examinations as the matching nephrology examination.

9. A nephrology patient electronic medical record generation system, comprising: A nephrology patient electronic medical record generation method comprising a processor for processing instructions stored in a memory to implement any one of claims 1-8.

Images