Orthopedic case information storage method and system

Abstract

The invention provides an orthopedics department case information storage method and system, and belongs to the technical field of data processing.The method comprises the steps that patient attribute information in multiple pieces of orthopedics department case information is classified, and multiple classification results are obtained; the attribute information of the patient comprises age information, a body weight index and basic disease data; based on the classification result, labels are added to the multiple pieces of orthopedic case information; and storing the plurality of pieces of orthopedic case information added with the labels. According to the orthopedic case information storage method and system provided by the invention, the data query efficiency can be improved.

Description

Technical Field

[0001] The present disclosure belongs to the field of data processing technology, and more specifically, to an orthopedic case information storage method and system. Background Art

[0002] By analyzing a large amount of orthopedic case information, we can understand the pathogenesis, treatment effects and prognostic factors of orthopedic diseases, and provide a basis for further improving the level of orthopedic diagnosis and treatment. For example, researchers can determine the best treatment plan by analyzing the cure rate and complication rate of different treatment methods for a certain fracture. Standardized and complete case information can be used as an important part of academic exchanges and shared with other doctors and researchers to promote knowledge dissemination and technological progress in the field of orthopedics.

[0003] As more and more orthopedic case information is collected, the burden of data storage becomes heavier. Moreover, as the amount of data increases, when users query orthopedic case information, the amount of data returned may be very large, and users need to spend a lot of time screening and evaluating these results to find the information they really need. Summary of the invention

[0004] The purpose of the present disclosure is to provide an orthopedic case information storage method and system to improve data query efficiency.

[0005] A first aspect of the embodiments of the present disclosure provides an orthopedic case information storage method, comprising: Classifying patient attribute information in multiple orthopedic case information to obtain multiple classification results; the patient attribute information includes age information, body mass index and basic disease data; Based on the classification results, labels are respectively added to the multiple pieces of orthopedic case information; The multiple pieces of orthopedic case information after adding tags are stored.

[0006] A second aspect of the embodiments of the present disclosure provides an orthopedic case information storage system, comprising: A data classification module is used to classify patient attribute information in multiple orthopedic case information to obtain multiple classification results; the patient attribute information includes age information, body mass index and basic disease data; A label adding module, used for adding labels to the plurality of orthopedic case information respectively based on the classification results; The data storage module is used to store the multiple pieces of orthopedic case information after adding tags.

[0007] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned orthopedic case information storage method when executing the computer program.

[0008] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned orthopedic case information storage method are implemented.

[0009] The beneficial effects of the orthopedic case information storage method and system provided by the embodiments of the present disclosure are: The disclosed embodiment takes into account that the existing orthopedic case information storage method only directly stores multiple orthopedic case information, resulting in a huge amount of data returned when the user queries the orthopedic case information. Therefore, before storing multiple orthopedic case information, the present embodiment classifies the patient attribute information in the multiple orthopedic case information, and adds labels to the multiple orthopedic case information based on the classification results. Each classification has the same age group, body mass index range and underlying disease. When the user's data query instruction is received, it can be queried based on the label from the orthopedic case information with the same age group, body mass index range and underlying disease as the user input, thereby narrowing the query scope; at the same time, the treatment methods of patients with the same age group, body mass index range and underlying disease are more referenceable. That is, the query efficiency can be improved by adding labels, and the data query results can be made more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A schematic diagram of a flow chart of a method for storing orthopedic case information provided in an embodiment of the present disclosure; Figure 2 A structural block diagram of an orthopedic case information storage system provided by an embodiment of the present disclosure; Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0012] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.

[0013] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0014] Please refer to Figure 1 , Figure 1 A flowchart of a method for storing orthopedic case information provided by an embodiment of the present disclosure is provided, and the method comprises: S101: Classify patient attribute information in multiple orthopedic case information to obtain multiple classification results; the patient attribute information includes age information, body mass index and basic disease data.

[0015] In this embodiment, multiple orthopedic case information can come from the hospital's electronic medical record system, database or other data sources, including patient attribute information, diagnosis information and treatment information, etc. Patient attribute information includes age information, body mass index and underlying disease data, diagnosis information can include disease name, diagnosis time, detailed description of diagnosis results, etc. Treatment information can include treatment method, treatment time, treatment effect, etc.

[0016] Considering that doctors consider the patient's age, body mass index, and underlying disease data when determining treatment methods, patients can be divided into different categories based on their age, body mass index, and underlying disease data. For example, patients can be divided into categories such as children (0-12 years old), adolescents (13-18 years old), early adulthood (19-35 years old), middle-aged (36-60 years old), and elderly (61 years old and above) based on age range; patients can be divided into categories such as underweight (<18.5), normal weight (18.5-24.9), overweight (25.0-29.9), and obese (≥30) based on the range of body mass index (BMI); patients can be divided into categories such as those with cardiovascular disease, diabetes, and respiratory diseases based on the type of underlying disease. Different combinations of the above categories can result in multiple classifications of patient attribute information. For example, one classification result may be "middle-aged, body mass index of 18.5-24.9, with diabetes"; another classification result may be "elderly, body mass index greater than 30, with cardiovascular disease".

[0017] S102: Add labels to the multiple orthopedic case information based on the classification results.

[0018] In this embodiment, for each orthopedic case information, a corresponding label can be added according to the classification result to which its patient attribute information belongs. The label can concisely summarize the patient's attribute information and is easy to understand and use. For example, labels such as "middle-aged overweight diabetic patients" and "elderly obese cardiovascular disease patients" can be used.

[0019] S103: storing the plurality of orthopedic case information after adding tags.

[0020] In this embodiment, multiple orthopedic case information and corresponding tags can be stored together, and the age group, body mass index range and underlying diseases of the corresponding orthopedic case information can be quickly obtained according to the tags. Therefore, after the orthopedic case information with tags is stored, it can be quickly retrieved and queried by the tags. For example, the orthopedic case information of all "elderly obese cardiovascular disease patients" can be queried for targeted research and treatment.

[0021] It can be concluded from the above that this embodiment takes into account that the existing orthopedic case information storage method only directly stores multiple orthopedic case information, resulting in a huge amount of data returned when the user queries the orthopedic case information. Therefore, before storing multiple orthopedic case information, this embodiment classifies the patient attribute information in the multiple orthopedic case information, and adds labels to the multiple orthopedic case information based on the classification results. Each classification has the same age group, body mass index range and underlying disease. When the user's data query instruction is received, it can be queried based on the label from the orthopedic case information with the same age group, body mass index range and underlying disease as the user input, thereby narrowing the query scope; at the same time, the treatment methods of patients with the same age group, body mass index range and underlying disease are more referenceable. That is, the query efficiency can be improved by adding labels, and the data query results can be made more accurate.

[0022] In one embodiment of the present disclosure, the patient attribute information in multiple orthopedic case information is classified to obtain multiple classification results, including: The patient attribute information is input into the trained decision tree model to obtain multiple classification results; the training process of the decision tree model includes: A training set is constructed based on historical orthopedic case information; the historical orthopedic case information is historical data of orthopedic case information.

[0023] Construct feature columns based on the age information, body mass index, and underlying disease data corresponding to each patient attribute information in the training set. Train a decision tree model based on the feature columns and the set target classification.

[0024] In this embodiment, a series of judgments can be made on the characteristics of age information, body mass index and basic disease data based on the decision tree model to perform classification. Starting from the root node, branches are made according to different characteristic conditions until a leaf node is reached, and each leaf node represents a classification result.

[0025] Specifically, a portion of data can be selected from the historical data of orthopedic case information (ie, historical orthopedic case information) as a training set. The historical orthopedic case information contains the patient attribute information of previous patients, and a corresponding target classification can be set for each patient attribute information by manual labeling.

[0026] Furthermore, the age information, body mass index and basic disease data in the patient attribute information can be extracted, and this information can be combined to construct a feature column as the input feature of the decision tree model. At the same time, the set target classification is used as the output result of the decision tree model, and the decision tree model is trained based on the feature column and the set target classification.

[0027] It can be concluded from the above that this embodiment automatically classifies patient attribute information based on the decision tree model, and can achieve rapid classification of patient attribute information.

[0028] In one embodiment of the present disclosure, a feature column is constructed based on the age information, body mass index and underlying disease data corresponding to each patient attribute information in the data set, including: The age information is assigned a value based on the age information and a set age range to obtain a first value corresponding to the age information.

[0029] The body weight index is assigned a value based on the body weight index and a set body weight index range to obtain a second value corresponding to the body weight index.

[0030] The basic disease data is encoded based on the basic disease data and a specified encoding rule to obtain a first code corresponding to the basic disease data.

[0031] A feature column is constructed based on the first value, the second value, and the first code.

[0032] In this embodiment, a specific implementation method of constructing a feature column based on age information, body mass index and basic disease data is provided.

[0033] First, the age information is compared with the set age range, and the age information belonging to different age ranges is assigned different first values. Specifically, the set age range may include a first age range, a second age range, and a third age range, and each age range has corresponding assignment data. If any age information belongs to the first age range, the assignment data corresponding to the first age range is determined as the first value corresponding to the any age information; if the any age information belongs to the second age range, the assignment data corresponding to the second age range is determined as the first value corresponding to the any age information; if the age information belongs to the third age range, the assignment data corresponding to the third age range is determined as the first value corresponding to the any age information.

[0034] For example, the set age range includes [0-12] years old, [13-18] years old, [19-35] years old, [36-60] years old, and [61 years old and above], and the corresponding assigned data are 1, 2, 3, 4, and 5 respectively. If the age information corresponding to a certain patient attribute information is 40 years old, the age information belongs to the age range of 36-60 years old, so the first value corresponding to the age information is 4.

[0035] Similarly, the body mass index can be compared with the set body mass index range, and body mass indexes belonging to different body mass index ranges are assigned different second values. Specifically, the set body mass index range can include a first body mass index range, a second body mass index range, and a third body mass index range, each body mass index range has corresponding assignment data, if any body mass index belongs to the first body mass index range, the assignment data corresponding to the first body mass index range is determined as the second value corresponding to the any body mass index; if any body mass index belongs to the second body mass index range, the assignment data corresponding to the second body mass index range is determined as the second value corresponding to the any body mass index; if any body mass index belongs to the third body mass index range, the assignment data corresponding to the third body mass index range is determined as the second value corresponding to the any body mass index.

[0036] For example, the body mass index range is set to include underweight (<18.5), normal weight (18.5-24.9), overweight (25.0-29.9) and obese (≥30), and the corresponding assigned data are 1, 2, 3, and 4. If the body mass index corresponding to a patient attribute information is 20 years old, the body mass index belongs to the range of normal weight (18.5-24.9), so the second value corresponding to the body mass index is 2.

[0037] When encoding the basic disease data based on the basic disease data and the specified coding rules, the specified coding rules can be used to encode the multiple diseases included in the basic disease data. For example, a three-digit decimal code can be used. When there is no basic disease, the corresponding first code is 000, when the basic disease data only includes hypertension, the corresponding first code is 002, ..., when the basic disease data includes hypertension, diabetes, and pneumonia, the corresponding first code is 022, and so on.

[0038] On the basis of obtaining the first value, the second value and the first code, the first value, the second value and the first code may be stored in sequence in the same list to form a feature vector, and the feature vector is used as a feature column.

[0039] In order to keep the data format consistent, the multi-digit numbers in the first code can be split into single-digit numbers and then stored. Assuming that the first value is 1, the second value is 2, and the first code is 005, the first code can be split into [0, 0, 5], and the first value, the second value, and the first code are stored in sequence, and the feature column is [1, 2, 0, 0, 5].

[0040] It can be concluded from the above that this embodiment converts the original age information, body mass index and underlying disease data into feature columns in numerical format, which can be easily processed by various machine learning algorithms to improve the accuracy and efficiency of the model.

[0041] In one embodiment of the present disclosure, encoding the basic disease data based on the basic disease data and a specified encoding rule to obtain a first code corresponding to the basic disease data includes: In response to the fact that the types of diseases included in the basic disease data are greater than a third threshold, a first disease, a second disease and a third disease are selected from the basic disease data, and the first disease, the second disease and the third disease are encoded based on a specified coding rule to obtain a first code corresponding to the basic disease data.

[0042] The first disease is the most serious disease among the multiple disease types included in the basic disease data, the second disease is the most urgent disease among the multiple disease types included in the basic disease data, and the third disease is the disease with the greatest correlation with orthopedic treatment among the multiple disease types included in the basic disease data.

[0043] In this embodiment, when the types of basic diseases included in the basic disease data are large (greater than the third threshold), there will be too many classifications, and too many classifications will cause the depth of the decision tree to be too large and make the decision tree model too complicated. To avoid this problem, when the types of basic diseases included in the basic disease data are greater than the third threshold, the most serious first disease, the most urgent second disease, and the third disease with the greatest correlation with orthopedic treatment are selected from the basic disease data, and the basic disease data are assigned values ​​based on the first disease, the second disease, and the third disease to reasonably control the number of classifications and avoid the depth of the decision tree being too large. Among them, the third threshold is a preset constant, and those skilled in the art can design the specific value of the third threshold according to actual needs, such as 3, 4, 5, etc.

[0044] Specifically, a first list may be constructed in advance based on the severity of common diseases, the first list including common disease types and their corresponding first priorities, and the higher the first priority, the higher the severity of the disease. For example, among common diseases, cancer is considered to have the highest severity, and its first priority is set to the highest. On this basis, the disease with the highest first priority may be selected from the multiple disease types included in the basic disease data as the first disease.

[0045] At the same time, the urgency of each disease type can be determined based on the stages of multiple disease types included in the basic disease data. For example, a disease in an early stage has a lower urgency, while a disease in a late stage has a higher urgency. For multiple diseases in the same stage, the disease with the highest first priority can be selected.

[0046] Similarly, a second list can be constructed in advance based on the correlation between common diseases and orthopedic treatments. The second list contains common disease types and their corresponding second priorities. The higher the second priority of a disease, the higher its correlation with orthopedic treatment. For example, among common diseases, osteoporosis may increase the risk of fractures, and diabetes may affect the healing of fractures. Therefore, osteoporosis is set to a higher second priority, followed by diabetes. On this basis, the disease with the highest second priority can be selected as the third disease from the multiple disease types contained in the basic disease data.

[0047] From the above, it can be concluded that in this embodiment, when there are many types of basic diseases included in the basic disease data, the first disease, the second disease and the third disease are screened for the construction of the feature column in the decision tree, which can reasonably control the number of classifications and avoid the depth of the decision tree being too large.

[0048] In one embodiment of the present disclosure, training a decision tree model based on a feature column and a set target classification includes: In response to the total number of first codes being greater than a first threshold, the age information, underlying disease data and body mass index in the feature column are sequentially determined as feature conditions of a decision tree to train a decision tree model; the total number of first codes is the total number of different first codes among multiple first codes corresponding to multiple pieces of orthopedic case information.

[0049] In response to the total number of the first codes being less than or equal to the first threshold, the age information, body mass index and underlying disease data in the feature column are sequentially determined as feature conditions of the decision tree to train the decision tree model.

[0050] In this embodiment, considering that some underlying diseases are more common in specific age groups, classifying by age first in the process of building the decision tree will make the subsequent classification based on the underlying disease more targeted; otherwise, if the underlying disease is classified first, the distribution of patients in different age groups will be more dispersed, affecting the subsequent age-based classification effect.

[0051] On this basis, if the total number of first codes is large (that is, the distribution of underlying diseases is more dispersed), patients can be classified according to the underlying diseases first, so as to better disperse the patients into different categories, and then further subdivided according to body mass index; otherwise, if they are classified according to body mass index first, it may lead to too many patients in certain weight ranges, making the subsequent classification based on underlying diseases not detailed enough.

[0052] On the contrary, if the total number of the first codes is small (i.e., the distribution of the underlying diseases is concentrated), considering that the body mass index may also have a certain impact on the occurrence and development of certain diseases, the classification of the underlying diseases can be further refined based on the age information and body mass index, based on the previous two characteristics. Among them, the first threshold is a preset constant, and those skilled in the art can design a specific value of the first threshold according to actual needs, such as 10, 20, etc.

[0053] It can be concluded from the above that in the process of building the decision tree in this embodiment, the best feature is selected for splitting based on the distribution of patient attribute information, which is conducive to improving the classification effect.

[0054] In one embodiment of the present disclosure, before constructing a feature column based on the age information, body mass index and basic disease data corresponding to each patient attribute information in the training set, the method further includes: In response to the fact that the proportion of the first sample information in the training set is less than the second threshold, multiple sample expansion operations are performed until the set condition is met; the first sample information is historical orthopedic case information corresponding to any target classification in the data set; the sample expansion operation includes: The first sample information is randomly sampled to obtain second sample information.

[0055] The first sample information is expanded based on the second sample information.

[0056] The setting condition is: the proportion of the quantity of the first sample information is greater than or equal to the second threshold.

[0057] In this embodiment, if the distribution of sample information corresponding to different target classifications is uneven, for example, the number of patients with a certain disease combination (corresponding to a certain first code) is far less than that of healthy people (the corresponding first code is 000), the constructed decision tree will tend to favor the majority class, while the classification effect on the minority class will be poor. To solve this problem, the sample information with a small amount (that is, the first sample information) can be repeatedly sampled to achieve the expansion operation of the first sample information.

[0058] Specifically, the first sample information can be randomly sampled to obtain the second sample information, and then the second sample information is added to the first sample information, thereby increasing the number of samples of the target classification. Repeating the above random sampling operation, the proportion of the first sample information will gradually increase. When the proportion of the number of the first sample information is greater than or equal to the second threshold, it means that the sample expansion has reached the set condition, and the sample expansion operation can be stopped at this time. Among them, the second threshold is a preset constant, and those skilled in the art can design the specific value of the second threshold according to actual needs, such as 5%, 10%, etc.

[0059] It can be concluded from the above that this embodiment expands sample information with a smaller proportion based on the random sampling method, and trains the decision tree model based on the expanded training set, which is conducive to improving the training accuracy of the decision tree model.

[0060] In one embodiment of the present disclosure, multiple pieces of orthopedic case information after adding tags are stored, including: The patient attribute information and labels in the plurality of orthopedic case information are stored in the first data table.

[0061] The diagnosis information in the plurality of orthopedic case information is stored in the second data table, and an association relationship between the second data table and the first data table is established.

[0062] The treatment information in the plurality of orthopedic case information is stored in a third data table; and an association relationship between the third data table and the first data table is established.

[0063] In this embodiment, patient attribute information, diagnosis information and treatment information are stored in the first data table, the second data table and the third data table respectively, and an association relationship between the first data table and the second data table, as well as an association relationship between the first data table and the third data table are established based on the same fields (for example, the same "patient ID"). Different personnel can be responsible for entering and updating the first data table, the second data table, and the third data table. For example, the patient information can be entered by the front desk staff when the patient first visits the doctor, the diagnosis information can be filled in by the doctor during the diagnosis process, and the treatment information can be gradually updated as the treatment progresses, thus avoiding repeated entry of information and errors.

[0064] In addition, when you need to query specific information, you can directly access the corresponding table to improve the query speed. For example, if you want to query the diagnosis information of a patient, you only need to query in the diagnosis information table instead of searching in the entire case information, which can save time and improve work efficiency.

[0065] Furthermore, different access permissions can be set for each data table. For example, the first data table contains the user's privacy information. Managers who perform statistical analysis and other tasks can only view diagnosis information and treatment information, but cannot access patient attribute information. Doctors can view the attribute information of the patients they are responsible for, as well as the associated diagnosis information and treatment information, but cannot access the attribute information of other doctors' patients, as well as the associated diagnosis information and treatment information.

[0066] In one embodiment of the present disclosure, before storing the plurality of orthopedic case information after adding tags, the orthopedic case information storage method further includes: Encrypt multiple pieces of orthopedic case information.

[0067] In this embodiment, considering that the orthopedic case information contains the patient's personal privacy and sensitive medical data, it needs to be encrypted and stored. Specifically, the existing symmetric encryption or asymmetric encryption algorithm can be used to encrypt the multiple orthopedic case information.

[0068] Corresponding to the orthopedic case information storage method of the above embodiment, Figure 2 This is a structural block diagram of an orthopedic case information storage system provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 2 The orthopedic case information storage system 20 includes: a data classification module 21, a label adding module 22 and a data storage module 23. The data classification module 21 is used to classify the patient attribute information in the multiple orthopedic case information to obtain multiple classification results; the patient attribute information includes age information, body mass index and basic disease data; A label adding module 22, used to add labels to the plurality of orthopedic case information based on the classification results; The data storage module 23 is used to store a plurality of orthopedic case information after adding tags.

[0069] In one embodiment of the present disclosure, the data classification module 21 is specifically used for: The patient attribute information is input into the trained decision tree model to obtain multiple classification results; the training process of the decision tree model includes: A training set is constructed based on historical orthopedic case information; the historical orthopedic case information is historical data of orthopedic case information; Construct feature columns based on the age information, body mass index, and underlying disease data corresponding to each patient attribute information in the training set. Train a decision tree model based on the feature columns and the set target classification.

[0070] In one embodiment of the present disclosure, the data classification module 21 is further configured to: The age information is assigned a value based on the age information and a set age range to obtain a first value corresponding to the age information.

[0071] The body weight index is assigned a value based on the body weight index and a set body weight index range to obtain a second value corresponding to the body weight index.

[0072] The basic disease data is encoded based on the basic disease data and a specified encoding rule to obtain a first code corresponding to the basic disease data.

[0073] A feature column is constructed based on the first value, the second value, and the first code.

[0074] In one embodiment of the present disclosure, the data classification module 21 is further configured to: In response to the total number of first codes being greater than a first threshold, the age information, underlying disease data and body mass index in the feature column are sequentially determined as feature conditions of a decision tree to train a decision tree model; the total number of first codes is the total number of different first codes among multiple first codes corresponding to multiple pieces of orthopedic case information.

[0075] In response to the total number of the first codes being less than or equal to the first threshold, the age information, body mass index and underlying disease data in the feature column are sequentially determined as feature conditions of the decision tree to train the decision tree model.

[0076] In one embodiment of the present disclosure, the data classification module 21 is specifically used for: In response to the fact that the proportion of the first sample information in the training set is less than the second threshold, multiple sample expansion operations are performed until the set condition is met; the first sample information is historical orthopedic case information corresponding to any target classification in the data set; the sample expansion operation includes: The first sample information is randomly sampled to obtain second sample information.

[0077] The first sample information is expanded based on the second sample information.

[0078] The setting condition is: the proportion of the quantity of the first sample information is greater than or equal to the second threshold.

[0079] In one embodiment of the present disclosure, the data storage module 23 is specifically used for: storing patient attribute information and labels in a plurality of orthopedic case information in a first data table; The diagnosis information in the plurality of orthopedic case information is stored in the second data table, and an association relationship between the second data table and the first data table is established.

[0080] The treatment information in the plurality of orthopedic case information is stored in a third data table; and an association relationship between the third data table and the first data table is established.

[0081] In one embodiment of the present disclosure, the data storage module 23 is specifically used for: Encrypt multiple pieces of orthopedic case information.

[0082] See also Figure 3 , Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 3 The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processors 301, input devices 302, output devices 303 and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above-mentioned device embodiments, such as Figure 2 The functions of modules 21 to 23 are shown.

[0083] It should be understood that in the embodiment of the present disclosure, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0084] The input device 302 may include a touch panel, a fingerprint collection sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.

[0085] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0086] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of the orthopedic case information storage method provided in the embodiments of the present disclosure, and can also execute the implementation methods of the electronic device described in the embodiments of the present disclosure, which will not be repeated here.

[0087] In another embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by the processor, all or part of the processes in the above-mentioned embodiment method are implemented, and the computer program can also be completed by instructing the relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0088] The computer-readable storage medium may be an internal storage unit of the electronic device of any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0089] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0090] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0091] In the several embodiments provided in the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or it can be an electrical, mechanical or other form of connection.

[0092] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present disclosure.

[0093] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0094] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present disclosure, and these modifications or replacements should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A method for storing orthopedic case information, characterized in that: include: Classify the patient attribute information in multiple orthopedic case information to obtain multiple classification results; The patient attribute information includes age information, body mass index and underlying disease data; Based on the classification results, labels are respectively added to the multiple pieces of orthopedic case information; The multiple pieces of orthopedic case information after adding tags are stored.

2. The orthopedic case information storage method according to claim 1, characterized in that: The patient attribute information in the plurality of orthopedic case information is classified to obtain a plurality of classification results, including: The patient attribute information is input into the trained decision tree model to obtain multiple classification results; the training process of the decision tree model includes: Constructing a training set based on historical orthopedic case information; the historical orthopedic case information is historical data of the orthopedic case information; Constructing a feature column based on the age information, body mass index and underlying disease data corresponding to each patient attribute information in the training set; A decision tree model is trained based on the feature columns and the set target classification.

3. The orthopedic case information storage method according to claim 2, characterized in that: The constructing of feature columns based on age information, body mass index and underlying disease data corresponding to each patient attribute information in the data set includes: assigning a value to the age information based on the age information and a set age range to obtain a first value corresponding to the age information; Assigning a value to the body mass index based on the body mass index and a set body mass index range to obtain a second value corresponding to the body mass index; Encoding the basic disease data based on the basic disease data and a specified encoding rule to obtain a first code corresponding to the basic disease data; A feature column is constructed based on the first value, the second value, and the first code.

4. The orthopedic case information storage method according to claim 3, characterized in that: The decision tree model is trained based on the feature column and the set target classification, including: In response to the total number of first codes being greater than a first threshold, the age information, the underlying disease data, and the body mass index in the feature column are sequentially determined as feature conditions of a decision tree to train a decision tree model; the total number of the first codes is the total number of different first codes among the multiple first codes corresponding to the multiple pieces of orthopedic case information; In response to the total number of the first codes being less than or equal to a first threshold, the age information, body mass index and underlying disease data in the feature column are sequentially determined as feature conditions of a decision tree to train a decision tree model.

5. The orthopedic case information storage method according to claim 2, characterized in that: Before constructing the feature column based on the age information, body mass index and basic disease data corresponding to each patient attribute information in the training set, the method further includes: In response to the proportion of the first sample information in the training set being less than the second threshold, performing multiple sample expansion operations until a set condition is met; the first sample information is historical orthopedic case information corresponding to any target classification in the data set; the sample expansion operation includes: Randomly sampling the first sample information to obtain second sample information; Expanding the first sample information based on the second sample information; The setting condition is: the proportion of the quantity of the first sample information is greater than or equal to a second threshold.

6. The orthopedic case information storage method according to claim 5, characterized in that: The plurality of orthopedic case information after adding tags is stored, including: Storing the patient attribute information and labels in the plurality of orthopedic case information in a first data table; storing the diagnosis information in the plurality of orthopedic case information into a second data table, and establishing an association relationship between the second data table and the first data table; The treatment information in the plurality of orthopedic case information is stored in a third data table; and an association relationship between the third data table and the first data table is established.

7. The orthopedic case information storage method according to claim 1, characterized in that: Before storing the plurality of pieces of orthopedic case information after adding tags, the orthopedic case information storage method further includes: The multiple pieces of orthopedic case information are encrypted.

8. An orthopedic case information storage system, characterized in that: include: A data classification module is used to classify patient attribute information in multiple orthopedic case information to obtain multiple classification results; The patient attribute information includes age information, body mass index and underlying disease data; A label adding module, used for adding labels to the plurality of orthopedic case information respectively based on the classification results; The data storage module is used to store the multiple pieces of orthopedic case information after adding tags.

9. The orthopedic case information storage system according to claim 8, characterized in that: The data classification module is specifically used for: The patient attribute information is input into the trained decision tree model to obtain multiple classification results; the training process of the decision tree model includes: Constructing a training set based on historical orthopedic case information; the historical orthopedic case information is historical data of the orthopedic case information; Constructing a feature column based on the age information, body mass index and underlying disease data corresponding to each patient attribute information in the training set; A decision tree model is trained based on the feature columns and the set target classification.

10. The orthopedic case information storage system according to claim 9, characterized in that: The data classification module is also specifically used for: assigning a value to the age information based on the age information and a set age range to obtain a first value corresponding to the age information; Assigning a value to the body mass index based on the body mass index and a set body mass index range to obtain a second value corresponding to the body mass index; Encoding the basic disease data based on the basic disease data and a specified encoding rule to obtain a first code corresponding to the basic disease data; A feature column is constructed based on the first value, the second value, and the first code.

Images