Method and system for generating electronic medical record of nephrology department patient

Abstract

The invention relates to the technical field of electronic medical record recording, in particular to a nephrology department patient electronic medical record generation method and system, and the method comprises the steps: obtaining current illness symptom information and current medical history information corresponding to a to-be-detected patient in the nephrology department, obtaining historical medical history information corresponding to each historical patient in the nephrology department and historical disease symptom information of each historical nephrology department examination; keyword extraction is carried out on each piece of disease symptom information, and the disease condition similarity corresponding to each historical nephrology department examination is determined; determining a disease condition extension expression degree and a medical history matching degree corresponding to each historical patient; determining a target matching degree corresponding to each historical nephrology examination of each historical patient; screening out the matched nephrology examination, and generating a current electronic medical record corresponding to the to-be-detected patient based on the electronic medical record corresponding to the matched nephrology examination. According to the invention, self-adaptive generation of the electronic medical record of the patient is realized, so that the rationality of generation of the electronic medical record of the nephrology department patient is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic medical record recording, and particularly to a method and system for generating an electronic medical record for patients in the nephrology department. Background Art

[0002] With the continuous development of medical informatization, electronic medical records have become an important part of modern hospital management and clinical treatment. In the field of nephrology, the application of electronic medical records is of particular significance. The diagnosis and treatment of kidney diseases usually require multi-faceted data support, including the integration of information in multiple fields such as hematology, imaging, urine analysis, and renal function testing. Therefore, accurately generating an electronic medical record for patients in the nephrology department is crucial. Currently, the method for generating a patient's electronic medical record is usually: based on the doctor's subjective experience, recording the changes in the patient's condition, and thus generating the patient's electronic medical record.

[0003] However, when generating a patient's electronic medical record based on the doctor's subjective experience by recording the changes in the patient's condition, there are often the following technical problems: Since the development of the condition of different nephrology patients often varies, the conditions that need to be recorded and concerned for different nephrology patients often differ. Moreover, the experience levels of different doctors often vary. If directly generating an electronic medical record based on the doctor's subjective experience, the generated result of the electronic medical record for nephrology patients may be greatly affected by the doctor's subjective factors, resulting in poor rationality in the generation of the electronic medical record for nephrology patients. Summary of the Invention

[0004] To solve the technical problem of poor rationality in the generation of the electronic medical record for nephrology patients, the present invention proposes a method and system for generating an electronic medical record for nephrology patients.

[0005] In a first aspect, the present invention provides a method for generating an electronic medical record for nephrology patients, the method comprising: Obtaining the current condition symptom information and current medical history information corresponding to the patient to be detected under nephrology, as well as the historical medical history information corresponding to each historical patient under nephrology and the historical condition symptom information of each historical nephrology examination; Extracting keywords from each condition symptom information to obtain a keyword sequence corresponding to each condition symptom information, and determining the disease condition similarity corresponding to each historical nephrology examination to which each historical condition symptom information belongs based on the similarity between the current condition symptom information and the keyword sequences corresponding to each historical condition symptom information, and the intersection distribution therebetween; Determining the disease condition extension manifestation degree corresponding to each historical patient according to the difference situation between the historical condition symptom information of all historical nephrology examinations of each historical patient; Determine the medical history matching degree corresponding to each historical patient according to the similarity between the current medical history information and the historical medical history information corresponding to each historical patient; Determine the target matching degree corresponding to each historical nephrology examination of each historical patient according to the disease condition similarity corresponding to each historical nephrology examination of each historical patient, the medical history matching degree corresponding to each historical patient, and the disease condition extension performance degree; According to the target matching degree, screen out the matching nephrology examinations from all historical nephrology examinations, and generate the current electronic medical record corresponding to the patient to be tested based on the electronic medical record corresponding to the matching nephrology examination.

[0006] Combined with the first aspect above, in a possible implementation manner, the determining the disease condition similarity corresponding to the historical nephrology examination to which each historical disease condition symptom information belongs according to the similarity between the current disease condition symptom information and the keyword sequence corresponding to each historical disease condition symptom information, and the intersection distribution therebetween includes: Determine the keyword similarity corresponding to each historical disease condition symptom information as the Jaccard correlation coefficient between the keyword sequence corresponding to the current disease condition symptom information and the keyword sequence corresponding to each historical disease condition symptom information; Determine the target intersection corresponding to each historical disease condition symptom information as the intersection between the keyword sequence corresponding to the current disease condition symptom information and the keyword sequence corresponding to each historical disease condition symptom information; Determine the potential common index corresponding to each historical disease condition symptom information according to the existence of the target intersection corresponding to each historical disease condition symptom information in the keyword sequences corresponding to all historical disease condition symptom information; Determine the disease condition similarity corresponding to the historical nephrology examination to which each historical disease condition symptom information belongs according to the keyword similarity and the potential common index corresponding to each historical disease condition symptom information, where both the keyword similarity and the potential common index are positively correlated with the disease condition similarity; The formula for the disease condition similarity corresponding to the historical nephrology examination to which the historical disease condition symptom information belongs is: ; where is the disease condition similarity corresponding to the historical nephrology examination to which the th historical disease condition symptom information belongs; is the serial number of the historical disease condition symptom information; is the th keyword similarity corresponding to the historical disease condition symptom information; is the th potential common index corresponding to the historical disease condition symptom information.

[0007] Combined with the above first aspect, in a possible implementation manner, determining the potential commonality index corresponding to each historical disease symptom information according to the presence of the target intersection corresponding to each historical disease symptom information in the keyword sequence corresponding to all historical disease symptom information includes: Determine any one piece of historical disease symptom information as the marked disease symptom information, and determine the target intersection corresponding to the marked disease symptom information as the marked intersection; Screen out the keyword sequences in which the marked intersection exists from the keyword sequences corresponding to all historical disease symptom information as the reference word sequences to obtain the reference word sequence set corresponding to the marked disease symptom information; All keywords in the keyword sequence corresponding to the marked disease symptom information except the marked intersection form the first candidate word set corresponding to the marked disease symptom information; All keywords in the keyword sequence corresponding to the current disease symptom information except the marked intersection form the second candidate word set corresponding to the marked disease symptom information; Determine the potential commonality index corresponding to the marked disease symptom information according to the number of times the keywords in the first candidate word set and the second candidate word set corresponding to the marked disease symptom information appear in their corresponding reference word sequence sets.

[0008] Combined with the above first aspect, in a possible implementation manner, the formula corresponding to the potential commonality index of historical disease symptom information is: ; ; ; where, is the potential commonality index corresponding to the th piece of historical disease symptom information; is the serial number of the historical disease symptom information; is the normalization function; is the absolute value function; is the average number of times all keywords in the first candidate word set corresponding to the th piece of historical disease symptom information appear in their corresponding reference word sequence sets; is the average number of times all keywords in the second candidate word set corresponding to the th piece of historical disease symptom information appear in their corresponding reference word sequence sets; is the number of keywords in the first candidate word set corresponding to the th piece of historical disease symptom information; is the The serial number of the keyword in the first candidate word set corresponding to the historical disease symptom information; is the in the first candidate word set corresponding to the th historical disease symptom information, the number of times the th keyword appears in the reference word sequence set corresponding to the th historical disease symptom information; is the number of reference word sequences in the reference word sequence set corresponding to the th historical disease symptom information; is the number of keywords in the second candidate word set corresponding to the th historical disease symptom information; is the serial number of the keyword in the second candidate word set corresponding to the th historical disease symptom information; in the second candidate word set corresponding to the th historical disease symptom information, the number of times the th keyword appears in the reference word sequence set corresponding to the

[0009] Combined with the above first aspect, in a possible implementation manner, the determining the disease condition extension manifestation degree corresponding to each historical patient according to the difference situation between the historical disease symptom information of all historical nephrology examinations of each historical patient includes: Determine any historical patient as a marked patient, and determine each historical nephrology examination except the first historical nephrology examination among all historical nephrology examinations of the marked patient as a candidate nephrology examination, and determine any candidate nephrology examination as a marked nephrology examination; Determine the union of the keyword sequences corresponding to the historical disease symptom information of all historical nephrology examinations before the marked nephrology examination of the marked patient as the temporary keyword information corresponding to the marked nephrology examination; Determine the number of keywords in the keyword sequence corresponding to the marked nephrology examination that do not belong to the keywords in its corresponding temporary keyword information as the number of new disease conditions corresponding to the marked nephrology examination, where the number of new disease conditions corresponding to the marked nephrology examination represents the difference situation between the marked nephrology examination and the historical disease symptom information of its previous historical nephrology examinations; Determine the disease condition extension manifestation degree corresponding to the marked patient according to the number of new disease conditions corresponding to all candidate nephrology examinations.

[0010] Combined with the above first aspect, in a possible implementation manner, the determining the disease condition extension manifestation degree corresponding to the marked patient according to the number of new disease conditions corresponding to all candidate nephrology examinations includes: The mean value of the number of new conditions corresponding to all candidate nephrology examinations is determined as the condition extension manifestation degree corresponding to the marked patient.

[0011] Combined with the first aspect above, in a possible implementation manner, the determining the medical history matching degree corresponding to each historical patient according to the similarity between the current medical history information and the historical medical history information corresponding to each historical patient includes: The 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.

[0012] Combined with the first aspect above, in a possible implementation manner, the formula for the target matching degree corresponding to the historical nephrology examination of a historical patient is: ; where is the target matching degree corresponding to the th historical nephrology examination of the th historical patient; is the serial number of the historical patient; is the examination order of the historical nephrology examination of the th historical patient; is the condition similarity corresponding to the th historical nephrology examination of the th historical patient; is a preset factor, and its value range is (0.5, 1); is a normalization function; is the condition extension manifestation degree corresponding to the th historical patient; is the medical history matching degree corresponding to the th historical patient.

[0013] Combined with the first aspect above, in a possible implementation manner, the screening of the matching nephrology examination from all historical nephrology examinations according to the target matching degree includes: The historical nephrology examination with the largest corresponding target matching degree is screened out from all historical nephrology examinations as the matching nephrology examination.

[0014] In a second aspect, the present invention provides a nephrology patient electronic medical record generation system, and the system includes: A data acquisition module, configured to acquire the current condition symptom information and current medical history information of the patient to be detected under nephrology, as well as the historical medical history information of each historical patient under nephrology and the historical condition symptom information of each historical nephrology examination. A keyword extraction and determination module, configured to extract keywords for each disease symptom information, obtain a keyword sequence corresponding to each disease symptom information, and determine the disease condition similarity corresponding to each historical nephrology examination based on the similarity between the current disease symptom information and the keyword sequences corresponding to each historical disease symptom information, as well as the intersection distribution therebetween; A disease condition extension manifestation degree determination module, configured to determine the disease condition extension manifestation degree corresponding to each historical patient according to the difference between the historical disease symptom information of all historical nephrology examinations of each historical patient; A medical history matching degree determination module, configured to determine the medical history matching degree corresponding to each historical patient according to the similarity between the current medical history information and the historical medical history information corresponding to each historical patient; A target matching degree determination module, configured to determine the target matching degree corresponding to each historical nephrology examination of each historical patient according to the disease condition similarity corresponding to each historical nephrology examination of each historical patient, the medical history matching degree corresponding to each historical patient, and the disease condition extension manifestation degree; A screened medical record generation module, configured to screen out matching nephrology examinations from all historical nephrology examinations according to the target matching degree, and generate the current electronic medical record corresponding to the patient to be detected based on the electronic medical record corresponding to the matching nephrology examination.

[0015] In a third aspect, a server is provided, including a memory and a processor. The memory is used to store executable program code, and the processor is used 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 manner of the first aspect above.

[0016] In a fourth aspect, a computer program product is provided, including: computer program code, when the computer program code runs on a computer, enabling the computer to execute the method in the first aspect or any possible implementation manner of the first aspect above.

[0017] In a fifth aspect, a computer-readable storage medium is provided, storing computer program code, when the computer program code runs on a computer, enabling the computer to execute the method in the first aspect or any possible implementation manner of the first aspect above.

[0018] The present invention has the following beneficial effects: An electronic medical record generation method for nephrology patients of the present invention realizes the adaptive generation of patients' electronic medical records, solves the technical problem of poor rationality in the generation of electronic medical records for nephrology patients, and thus improves the rationality of the generation of electronic medical records for nephrology patients. Compared with directly generating electronic medical records based on doctors' subjective experience, when generating electronic medical records for nephrology patients, the present invention comprehensively analyzes the matching situation between the current disease symptoms and medical history of the patient to be detected and the disease symptoms and medical history of different historical patients corresponding to different historical nephrology examinations, thereby quantifying multiple features related to the matching situation, such as disease condition similarity, disease condition extension manifestation degree, medical history matching degree, and target matching degree, etc. Furthermore, historical nephrology examinations that match the nephrology examinations of the patient to be detected are screened out, that is, matching nephrology examinations. Since the nephrology examinations of the patient to be detected are similar to the matching nephrology examinations, 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, so as to assist doctors in better designing the electronic medical record of the patient to be detected, and thus improve the rationality of the generation of electronic medical records for nephrology patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0020] Figure 1 It is a flowchart of an electronic medical record generation method for nephrology patients of the present invention; Figure 2 It is a schematic diagram of the composition structure of an electronic medical record generation system for nephrology patients of the present invention; Figure 3 It is a schematic diagram of the structure of a computer device of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following will, in conjunction with the drawings and preferred embodiments, describe in detail the specific implementation manners, structures, features, and effects of the technical solutions proposed according to the present invention. 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.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0023] Reference Figure 1 shows the flow of some embodiments of an electronic medical record generation method for patients in the department of nephrology according to the present invention. The electronic medical record generation method for patients in the department of nephrology includes the following steps: Step S1, obtain the current condition symptom information and current medical history information corresponding to the patient to be tested in the department of nephrology, as well as the historical medical history information corresponding to each historical patient in the department of nephrology and the historical condition symptom information of each historical nephrology examination.

[0024] Among them, the patient to be tested can be a patient in the department of nephrology for whom an electronic medical record is to be generated. The historical patient can be a patient who has undergone nephrology examination and treatment. The current condition symptom information can be the condition symptom information obtained from the most recent nephrology examination of the patient to be tested. The historical condition symptom information can be the condition symptom information obtained by the historical patient in each historical nephrology examination. The condition symptom information can characterize the patient's condition symptoms. For example, the condition symptom information can include, but is not limited to: edema, proteinuria, and hematuria. The historical nephrology examination can be a nephrology examination that the historical patient has undergone. The current medical history information can be the medical history information that characterizes the patient's past medical history and is counted during the most recent nephrology examination of the patient to be tested. The historical medical history information can be the medical history information that characterizes the patient's past medical history and is counted during the last historical nephrology examination of the corresponding historical patient. The medical history information can be composed of the names of past medical histories.

[0025] It should be noted that the department of nephrology usually deals with diseases related to the kidneys, and most of them are chronic diseases. For patients in the department of nephrology, their conditions are complex and diverse and mostly have chronic progression. Patients will be affected by their conditions in terms of health for a long time, and there are differences in clinical manifestations at different stages. For example, patients in the early stage of the disease may not have any obvious symptoms, and as the disease progresses, patients may develop various symptoms such as fatigue, nausea, and edema. Therefore, obtaining the patient's condition symptom information can facilitate subsequent analysis of the degree of the patient's illness.

[0026] At the same time, for patients in the department of nephrology, during the process of disease development, they are often prone to multiple complications, such as being prone to cardiovascular diseases, such as hypertension, coronary heart disease, and heart failure, etc., and during the treatment process, they often also need the joint cooperation and research of multiple departments, and there will be a certain degree of treatment complexity. Therefore, obtaining the patient's past medical history information can, to a certain extent, analyze the possible complication situation of the patient.

[0027] As an example, first, the medical history information of the patient to be examined can be recorded, as well as the disease symptom information obtained during his / her most recent nephrology examination, which are respectively used as the current medical history information and the current disease symptom information. Next, the names of the past medical histories of each historical patient during their last historical nephrology examination can be recorded to form the historical medical history information corresponding to each historical patient. Finally, the disease symptom information obtained by each historical patient during each historical nephrology examination can be recorded as the historical disease symptom information.

[0028] Step S2: Extract keywords from each disease symptom information to obtain the keyword sequence corresponding to each disease symptom information, and determine the disease condition similarity corresponding to the historical nephrology examination to which each historical disease symptom information belongs based on the similarity between the current disease symptom information and the keyword sequences corresponding to each historical disease symptom information, as well as the intersection distribution therebetween.

[0029] As an example, this step may include the following steps: The first step: Extract keywords from each disease symptom information to obtain the keyword sequence corresponding to each disease symptom information.

[0030] For example, through the jieba word segmentation technology, each disease symptom information can be segmented to obtain the word segmentation set corresponding to each disease symptom information, and the words that characterize the nephrology disease symptoms can be selected from the word segmentation set corresponding to each disease symptom information as keywords, and all the keywords in the word segmentation set corresponding to each disease symptom information can form the keyword sequence corresponding to each disease symptom information. Among them, the keyword sequence can be a sequence randomly sorted by keywords.

[0031] The second step: Determine the Jaccard correlation coefficient between the keyword sequence corresponding to the current disease symptom information and the keyword sequences corresponding to each historical disease symptom information as the keyword similarity corresponding to each historical disease symptom information.

[0032] It should be noted that when the keyword similarity corresponding to the historical disease symptom information is larger, it often indicates that the keyword sequence corresponding to the current disease symptom information and the keyword sequence corresponding to the historical disease symptom information are more similar, and it often indicates that the nephrology examination results corresponding to the current disease symptom information and the nephrology examination results corresponding to the historical disease symptom information are more similar.

[0033] The third step: Determine the intersection between the keyword sequence corresponding to the current disease symptom information and the keyword sequences corresponding to each historical disease symptom information as the target intersection corresponding to each historical disease symptom information.

[0034] Fourthly, according to the presence of the target intersection corresponding to each historical disease symptom information in the keyword sequences corresponding to all historical disease symptom information, determining the potential common indicators corresponding to each historical disease symptom information may include the following sub-steps: In the first sub-step, any historical disease symptom information is determined as the marked disease symptom information, and the target intersection corresponding to the above-mentioned marked disease symptom information is determined as the marked intersection.

[0035] In the second sub-step, the keyword sequences containing the above-mentioned marked intersection are screened out from the keyword sequences corresponding to all historical disease symptom information as the reference word sequences, and the set of reference word sequences corresponding to the above-mentioned marked disease symptom information is obtained.

[0036] In the third sub-step, all keywords in the keyword sequence corresponding to the above-mentioned marked disease symptom information except the above-mentioned marked intersection are used to form the first candidate word set corresponding to the above-mentioned marked disease symptom information.

[0037] In the fourth sub-step, all keywords in the keyword sequence corresponding to the current disease symptom information except the above-mentioned marked intersection are used to form the second candidate word set corresponding to the above-mentioned marked disease symptom information.

[0038] In the fifth sub-step, according to the number of times the keywords in the first candidate word set and the second candidate word set corresponding to the above-mentioned marked disease symptom information appear in their corresponding set of reference word sequences, the potential common indicators corresponding to the above-mentioned marked disease symptom information are determined.

[0039] Among them, any keyword in the first candidate word set and the second candidate word set corresponding to the marked disease symptom information is denoted as the first keyword, and the set of reference word sequences corresponding to the marked disease symptom information is denoted as the first set of reference word sequences. The method for obtaining the number of times the first keyword appears in the first set of reference word sequences can be: screening out the reference word sequences containing the first keyword from the first set of reference word sequences as the temporary reference word sequences, and denoting the number of the temporary reference word sequences as the number of times the first keyword appears in the first set of reference word sequences.

[0040] For example, the formula for determining the potential common indicators corresponding to the historical disease symptom information can be: ; ; ; where, is the potential common indicator corresponding to the th historical disease symptom information. is the serial number of the historical disease symptom information. is the normalization function. is the absolute value function. is the average number of occurrences of all keywords in the first candidate word set corresponding to the th historical disease symptom information in their corresponding reference word sequence sets. is the average number of occurrences of all keywords in the second candidate word set corresponding to the th historical disease symptom information in their corresponding reference word sequence sets. is the number of keywords in the first candidate word set corresponding to the th historical disease symptom information. is the number of the th keyword in the first candidate word set corresponding to the th historical disease symptom information in the corresponding reference word sequence set of the th historical disease symptom information. is the number of keywords in the second candidate word set corresponding to the th historical disease symptom information. is the number of the th keyword in the second candidate word set corresponding to the th historical disease symptom information in the

[0041] It should be noted that in actual situations, for the same disease, different individual differences often present different symptoms. For example, in acute kidney injury, it may present different symptom manifestations such as low urine output, high urine specific gravity, or kidney enlargement among different patients, while the essence is the same disease. And the number of occurrences of these symptom manifestations under the same disease is often relatively close. can characterize the occurrence of symptoms different from the current disease symptom information in the th historical disease symptom information. can characterize the occurrence of symptoms different from the th historical disease symptom information in the current disease symptom information. Therefore, when is larger, it often indicates that the current disease symptom information and the The closer the occurrences of different symptoms among the historical disease condition symptom information are to each other, it often indicates that the current disease condition symptom information and the th historical disease condition symptom information are more likely to represent the same disease condition, and it often indicates that there is a certain potential connection between the current disease condition symptom information and the th historical disease condition symptom information.

[0042] Step 5: Determine the similarity of the disease condition corresponding to each historical nephrology examination based on the keyword similarity and potential commonality index corresponding to each historical disease condition symptom information.

[0043] Among them, both the keyword similarity and the potential commonality index can have a positive correlation with the disease condition similarity.

[0044] For example, the formula for determining the similarity of the disease condition corresponding to the historical nephrology examination to which the historical disease condition symptom information belongs can be: ; where is the similarity of the disease condition corresponding to the historical nephrology examination to which the th historical disease condition symptom information belongs. is the serial number of the historical disease condition symptom information. is the th keyword similarity corresponding to the historical disease condition symptom information. is the th potential commonality index corresponding to the historical disease condition symptom information.

[0045] It should be noted that when is larger, it often indicates that the current disease condition symptom information and the th historical disease condition symptom information are more likely to represent the same disease condition, and it often indicates that there is a certain potential connection between the current disease condition symptom information and the th historical disease condition symptom information. When is larger, it often indicates that the current disease condition symptom information and the th historical disease condition symptom information are more similar. Therefore, when is larger, it often indicates that the current disease condition symptom information and the th historical disease condition symptom information are more likely to represent the same disease condition, it often indicates that the current disease condition symptom information and the th historical disease condition symptom information are more similar, and it often indicates that the comprehensive symptoms represented by the current disease condition symptom information and the th historical disease condition symptom information are more similar.

[0046] Step S3: Determine the degree of disease condition extension manifestation corresponding to each historical patient according to the difference situation among the historical disease condition symptom information of all historical nephrology examinations of each historical patient.

[0047] As an example, this step may include the following steps: In the first step, any historical patient is determined as a marked patient, and each historical nephrology examination except the first historical nephrology examination among all the historical nephrology examinations of the above-mentioned marked patient is determined as a candidate nephrology examination, and any one of the candidate nephrology examinations is determined as a marked nephrology examination.

[0048] In the second step, the union of the keyword sequences corresponding to the historical disease symptom information of all the historical nephrology examinations before the marked nephrology examination of the above-mentioned marked patient is determined as the temporary keyword information corresponding to the above-mentioned marked nephrology examination.

[0049] In the third step, the number of keywords in the keyword sequence corresponding to the above-mentioned marked nephrology examination that do not belong to the keywords in its corresponding temporary keyword information is determined as the number of new conditions corresponding to the above-mentioned marked nephrology examination.

[0050] Among them, the number of new conditions corresponding to the marked nephrology examination can characterize the difference between the marked nephrology examination and the historical disease symptom information of its previous historical nephrology examinations.

[0051] In the fourth step, according to the number of new conditions corresponding to all the candidate nephrology examinations, the disease condition extension manifestation degree corresponding to the above-mentioned marked patient is determined.

[0052] For example, the mean value of the number of new conditions corresponding to all the candidate nephrology examinations can be determined as the disease condition extension manifestation degree corresponding to the above-mentioned marked patient.

[0053] For instance, the formula for determining the disease condition extension manifestation degree corresponding to a historical patient can be: ; where is the disease condition extension manifestation degree corresponding to the th 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 the th historical nephrology examination of the

[0054] It should be noted that when is larger, it often indicates that more new symptoms appear in the th historical nephrology examination of the th historical patient, and it often indicates that the The history of patients The more historical nephrology examinations are, the more reference value they have. The larger the Patients with a history of multiple nephrology examinations have experienced a large number of new symptoms, which often indicates that the first The more historical the patient's condition is, the more reference it has.

[0055] Step S4, determining the medical history matching degree corresponding to each historical patient based on the similarity between the current medical history information and the historical medical history information corresponding to each historical patient.

[0056] As an example, the jaccard correlation coefficient between the current medical history information and the historical medical history information corresponding to each historical patient may be determined as the medical history matching degree corresponding to each historical patient.

[0057] It should be noted that, because different medical conditions often affect each other, the patient's past medical history often affects the development of the patient's renal disease. For example, if the patient's past medical history includes high blood pressure, it may cause damage to the renal blood vessels, leading to glomerular sclerosis and renal dysfunction. For example, heart failure, such as heart failure, can lead to poor blood circulation, reduce blood flow to the kidneys, and affect their filtering and excretion functions, which may lead to acute kidney injury or worsening of chronic kidney disease. Therefore, the greater the matching degree of the medical history corresponding to the historical patient, it often indicates that the historical patient is more likely to suffer from the same renal disease as the patient to be tested.

[0058] Step S5, determining the target matching degree corresponding to each historical nephrology examination of each historical patient according to the medical condition similarity corresponding to each historical nephrology examination of each historical patient, the medical history matching degree corresponding to each historical patient, and the medical condition extension expression degree.

[0059] As an example, the formula for determining the target matching degree corresponding to the historical renal examination of the historical patient can be: ;in, It is The history of patients The target matching degree corresponding to the historical nephrology examination. It is the serial number of the historical patient. It is The order of historical nephrology examinations for each patient. It is The history of patients The similarity of the conditions corresponding to the historical nephrology examinations. is a preset factor, and its value range can be (0.5, 1), for example, It can be 0.6. is a normalization function. is the degree of disease condition extension corresponding to the th historical patient. is the medical history matching degree corresponding to the

[0060] It should be noted that when is larger, it often indicates that the th historical patient's th comprehensive symptoms obtained from the historical nephrology examination are more similar to the comprehensive symptoms obtained from the most recent nephrology examination of the patient to be tested. is 's weight. is 's weight. When is larger, it often indicates that the th historical patient had more new symptoms during multiple historical nephrology examinations, often indicating that the th historical patient's disease development is more reference-worthy. When is larger, it often indicates that the current medical history information is more similar to the th historical patient's corresponding historical medical history information, often indicating that the patient to be tested and the th historical patient have more similar medical histories, often indicating that the th historical patient and the patient to be tested have a greater likelihood of having the same nephrology disease. Therefore, when is larger, it often indicates that the results obtained from the most recent nephrology examination of the patient to be tested are more similar to the th historical patient's th historical nephrology examination results, often indicating that the most recent nephrology examination of the patient to be tested is more matched with the th historical patient's th historical nephrology examination.

[0061] Step S6, according to the target matching degree, screen out the matching nephrology examinations from all historical nephrology examinations, and generate the current electronic medical record corresponding to the patient to be tested based on the electronic medical records corresponding to the matching nephrology examinations.

[0062] It should be noted that after each historical nephrology examination, doctors often record an electronic medical record regarding the patient's nephrology diagnosis.

[0063] As an example, this step may include the following steps: The first step is to screen out the historical nephrology examination with the largest corresponding target matching degree from all historical nephrology examinations as the matching nephrology examination.

[0064] In the second step, based on the electronic medical records corresponding to the matched nephrology examinations, the current electronic medical records corresponding to the patient to be tested are generated.

[0065] For example, the electronic medical records corresponding to the matched nephrology examinations can be recommended to the doctor to assist the doctor in generating the electronic medical records of the patient to be tested during the most recent nephrology examination as the current electronic medical records.

[0066] Optionally, the acquisition method for generating the current electronic medical records corresponding to the patient to be tested can also be: recommending the electronic medical records corresponding to the matched nephrology examinations and the previous historical nephrology examinations of the historical patients who have undergone the matched nephrology examinations to the doctor to assist the doctor in generating the electronic medical records of the patient to be tested during the most recent nephrology examination as the current electronic medical records.

[0067] Reference Figure 2 , based on the same inventive concept as the above method embodiments, the present invention provides a nephrology patient electronic medical record generation system, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the above computer program is executed by the processor, it implements the steps of a nephrology patient electronic medical record generation method, which may specifically include: A data acquisition module 201, configured to acquire the current disease symptom information and current medical history information corresponding to the patient to be tested under nephrology, as well as the historical medical history information corresponding to each historical patient under nephrology and the historical disease symptom information of each historical nephrology examination; A keyword extraction and determination module 202, configured to extract keywords from each disease symptom information to obtain a keyword sequence corresponding to each disease symptom information, and determine the disease condition similarity corresponding to each historical nephrology examination to which each historical disease symptom information belongs based on the similarity between the current disease symptom information and the keyword sequences corresponding to each historical disease symptom information and the intersection distribution therebetween; A disease condition extension manifestation degree determination module 203, configured to determine the disease condition extension manifestation degree corresponding to each historical patient according to the difference between the historical disease symptom information of all historical nephrology examinations of each historical patient; A medical history matching degree determination module 204, configured to determine the medical history matching degree corresponding to each historical patient according to the similarity between the current medical history information and the historical medical history information corresponding to each historical patient; A target matching degree determination module 205, configured to determine the target matching degree corresponding to each historical nephrology examination of each historical patient according to the disease condition similarity corresponding to each historical nephrology examination of each historical patient, the medical history matching degree corresponding to each historical patient, and the disease condition extension manifestation degree; The screening medical record generation module 206 is configured to screen out the matched nephrology examinations from all historical nephrology examinations according to the target matching degree, and generate the current electronic medical record corresponding to the patient to be detected based on the electronic medical records corresponding to the matched nephrology examinations.

[0068] Figure 3 It is a schematic structural diagram of a computer device provided by an embodiment of the present invention. Exemplarily, as Figure 3 shown, 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. When the processor 302 executes the computer program 303, the computer device can execute any of the nephrology patient electronic medical record generation methods introduced above.

[0069] Based on the same inventive concept as the above method embodiments, the present invention provides a server, including a memory and a processor. The memory is used to store executable program codes, and the processor is used to call and run the executable program codes from the memory, so that the device executes any of the nephrology patient electronic medical record generation methods described above.

[0070] Based on the same inventive concept as the above method embodiments, the present invention provides a computer program product, which includes: computer program codes. When the computer program codes run on a computer, the computer executes any of the nephrology patient electronic medical record generation methods described above.

[0071] Based on the same inventive concept as the above method embodiments, the present invention provides a computer-readable storage medium, which stores computer program codes. When the computer program codes run on a computer, the computer executes any of the nephrology patient electronic medical record generation methods described above.

[0072] In summary, compared with directly generating electronic medical records based on doctors' subjective experience, when generating electronic medical records for nephrology patients, the present invention comprehensively analyzes the matching situation between the current disease symptoms and medical history of the patient to be detected and the disease symptoms and medical history of different historical patients corresponding to different historical nephrology examinations, thereby quantifying multiple features related to the matching situation, such as disease condition similarity, disease condition extension manifestation degree, medical history matching degree, target matching degree, etc. Furthermore, it screens out the historical nephrology examinations that are characterized as matching the nephrology examinations of the patient to be detected, that is, the matched nephrology examinations. Since the nephrology examinations of the patient to be detected are similar to the matched nephrology examinations, when generating the electronic medical record of the patient to be detected, the electronic medical record corresponding to the matched nephrology examination can be referred to, so as to assist doctors in better designing the electronic medical record of the patient to be detected, and further improve the rationality of generating electronic medical records for nephrology patients.

[0073] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the various embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. An electronic medical record generation method for nephrology patients, characterized in that, Including the following steps: Obtain the current disease symptom information and current medical history information corresponding to the patient to be tested under the nephrology department, as well as the historical medical history information corresponding to each historical patient under the nephrology department and the historical disease symptom information of each historical nephrology examination; Extract keywords from each disease symptom information to obtain a keyword sequence corresponding to each disease symptom information, and determine the disease condition similarity corresponding to each historical nephrology examination to which each historical disease symptom information belongs based on the similarity between the current disease symptom information and the keyword sequences corresponding to each historical disease symptom information, as well as the intersection distribution therebetween; Determine the disease condition extension manifestation degree corresponding to each historical patient according to the difference situation between the historical disease symptom information of all historical nephrology examinations of each historical patient; Determine the medical history matching degree corresponding to each historical patient according to the similarity between the current medical history information and the historical medical history information corresponding to each historical patient; Determine the target matching degree corresponding to each historical nephrology examination of each historical patient according to the disease condition similarity corresponding to each historical nephrology examination of each historical patient, the medical history matching degree corresponding to each historical patient, and the disease condition extension manifestation degree; According to the target matching degree, screen out the matching nephrology examinations from all historical nephrology examinations, and generate the current electronic medical record corresponding to the patient to be tested based on the electronic medical record corresponding to the matching nephrology examination; 2. The electronic medical record generation method for nephrology patients according to claim 1, wherein The determining the disease condition similarity corresponding to each historical nephrology examination to which each historical disease symptom information belongs based on the similarity between the current disease symptom information and the keyword sequences corresponding to each historical disease symptom information, as well as the intersection distribution therebetween, includes: Determine the keyword similarity corresponding to each historical disease symptom information as the Jaccard correlation coefficient between the keyword sequence corresponding to the current disease symptom information and the keyword sequence corresponding to each historical disease symptom information; Determine the target intersection corresponding to each historical disease symptom information as the intersection between the keyword sequence corresponding to the current disease symptom information and the keyword sequence corresponding to each historical disease symptom information; Determine the potential common index corresponding to each historical disease symptom information according to the existence situation of the target intersection corresponding to each historical disease symptom information in the keyword sequences corresponding to all historical disease symptom information; Determine the disease condition similarity corresponding to each historical nephrology examination to which each historical disease symptom information belongs according to the keyword similarity and potential common index corresponding to each historical disease symptom information, wherein both the keyword similarity and the potential common index are positively correlated with the disease condition similarity; The formula for the disease condition similarity corresponding to each historical nephrology examination to which the historical disease symptom information belongs is: ; wherein, is the disease condition similarity corresponding to the historical nephrology examination to which the th historical disease condition symptom information belongs; is the serial number of the historical disease condition symptom information; is the keyword similarity corresponding to the th historical disease condition symptom information; is the potential common index corresponding to the th historical disease condition symptom information.

3. The electronic medical record generation method for nephrology patients according to claim 2, characterized in that, The determining the potential common index corresponding to each historical disease symptom information according to the existence situation of the target intersection corresponding to each historical disease symptom information in the keyword sequences corresponding to all historical disease symptom information includes: Determine any one historical disease symptom information as the marked disease symptom information, and determine the target intersection corresponding to the marked disease symptom information as the marked intersection; Screen out the keyword sequences with the intersection of the said markers from all the keyword sequences corresponding to the historical disease symptom information as the reference keyword sequences, and obtain the set of reference keyword sequences corresponding to the said marked disease symptom information; Form the first candidate word set corresponding to the said marked disease symptom information with all the keywords in the keyword sequence corresponding to the said marked disease symptom information except for the intersection of the said markers; Form the second candidate word set corresponding to the said marked disease symptom information with all the keywords in the keyword sequence corresponding to the current disease symptom information except for the intersection of the said markers; Determine the potential commonality index corresponding to the said marked disease symptom information according to the number of times the keywords in the first candidate word set and the second candidate word set corresponding to the said marked disease symptom information appear in their corresponding reference keyword sequence sets.

4. A method for generating an electronic medical record of a nephrology patient according to claim 3, characterized in that, The formula for the potential commonality index corresponding to the historical disease symptom information is: ； ； ; where, is the potential common index corresponding to the th historical disease symptom information; is the serial number of the historical disease symptom information; is the normalization function; is the absolute value function; is the average number of occurrences of all keywords in the first candidate word set corresponding to the th historical disease symptom information in their corresponding reference word sequence sets; is the average number of occurrences of all keywords in the second candidate word set corresponding to the th historical disease symptom information in their corresponding reference word sequence sets; is the number of keywords in the first candidate word set corresponding to the th historical disease symptom information; is the serial number of the keyword in the first candidate word set corresponding to the th historical disease symptom information; is the number of occurrences of the th keyword in the first candidate word set corresponding to the th historical disease symptom information in the reference word sequence set corresponding to the th historical disease symptom information; is the number of reference word sequences in the reference word sequence set corresponding to the th historical disease symptom information; is the number of keywords in the second candidate word set corresponding to the th historical disease symptom information; is the serial number of the keyword in the second candidate word set corresponding to the th historical disease symptom information; is the number of occurrences of the th keyword in the second candidate word set corresponding to the th historical disease symptom information in the reference word sequence set corresponding to the th historical disease symptom information.

5. A method for generating an electronic medical record of a nephrology patient according to claim 1, characterized in that, Determine the disease condition extension manifestation degree corresponding to each historical patient according to the difference situation between the historical disease symptom information of all historical nephrology examinations of each historical patient, including: Determine any one historical patient as the marked patient, and determine each historical nephrology examination except the first historical nephrology examination among all the historical nephrology examinations of the marked patient as the candidate nephrology examination, and determine any one candidate nephrology examination as the marked nephrology examination; Determine the union of the keyword sequences corresponding to the historical disease symptom information of all the historical nephrology examinations before the marked nephrology examination of the marked patient as the temporary keyword information corresponding to the marked nephrology examination; Determine the number of new disease conditions corresponding to the marked nephrology examination as the number of keywords in the keyword sequence corresponding to the marked nephrology examination that do not belong to the keywords in its corresponding temporary keyword information, where the number of new disease conditions corresponding to the marked nephrology examination represents the difference situation between the marked nephrology examination and the historical disease symptom information of its previous historical nephrology examinations; Determine the disease condition extension manifestation degree corresponding to the marked patient according to the number of new disease conditions corresponding to all candidate nephrology examinations.

6. The electronic medical record generation method for nephrology patients according to claim 5, wherein Determine the disease condition extension manifestation degree corresponding to the marked patient according to the number of new disease conditions corresponding to all candidate nephrology examinations, including: Determine the average value of the number of new disease conditions corresponding to all candidate nephrology examinations as the disease condition extension manifestation degree corresponding to the marked patient.

7. A method for generating an electronic medical record for a nephrology patient according to claim 1, characterized in that, Determine the medical history matching degree corresponding to each historical patient according to the similarity situation between the current medical history information and the historical medical history information corresponding to each historical patient, including: Determine the Jaccard correlation coefficient between the current medical history information and the historical medical history information corresponding to each historical patient as the medical history matching degree corresponding to each historical patient.

8. The method for generating an electronic medical record for a nephrology patient according to claim 1, wherein The formula for the target matching degree corresponding to the historical nephrology examination of a historical patient is: ;in, It is The history of patients The target matching degree corresponding to the historical nephrology examination; It is the serial number of the historical patient; It is The order of historical nephrology examinations for each patient; It is The history of patients Similarity of the conditions corresponding to the historical nephrology examinations; is a preset factor, and its value range is (0.5, 1); is the normalization function; It is The extended expression of the disease corresponding to each historical patient; It is The medical history matching degree corresponding to each historical patient.

9. The electronic medical record generation method for nephrology patients according to claim 1, wherein Screen out the matching nephrology examinations from all historical nephrology examinations according to the target matching degree, including: Screen out the historical nephrology examination with the largest corresponding target matching degree from all historical nephrology examinations as the matching nephrology examination.

10. An electronic medical record generation system for nephrology patients, characterized in that, It includes a processor and a memory, and the processor is used to process the instructions stored in the memory to implement an electronic medical record generation method for nephrology patients described in any one of claims 1-9.

Images