An associated disease analysis method, device, equipment and storage medium

Abstract

Embodiments of the present application provide a kind of associated disease analysis method, device, equipment and storage medium, it is related to medical auxiliary technical field.The associated disease analysis method contains the following steps: S1, the disease information of multiple patients is acquired. Wherein, disease information contains the disease symptom and the disease category of patient.S2, according to disease information, the association table of disease symptom and disease category is acquired.S3, according to association table, the concatenation degree of disease combination including the disease category of predetermined number is calculated by layered mining mode.S4, according to concatenation degree, associated disease combination is acquired.S5, according to associated disease combination, generate diagnosis auxiliary information. By layered mining mode, associated disease combination can be well identified from medical data, so as to assist doctor diagnosis.Early prevention or discovery complication has good practical significance.

Description

Technical Field

[0001] This invention relates to the field of medical auxiliary technology, and more specifically, to a method, apparatus, device, and storage medium for analyzing related diseases. Background Technology

[0002] With societal development, hospitals have widely adopted electronic medical records, thereby acquiring a vast amount of patient information. However, this data is generally only used for record-keeping and stored in the background, without being effectively utilized.

[0003] Due to factors such as years of experience and professional background, the skill levels of medical professionals vary. Therefore, utilizing the large amount of existing data to help medical professionals better assess patients' conditions, thereby improving the overall level of healthcare in society, has significant practical implications.

[0004] In view of this, the applicant hereby submits this application after studying the existing technology. Summary of the Invention

[0005] This invention provides a method, apparatus, device, and storage medium for disease association analysis, in order to improve the problem of how to use existing medical data to assist doctors in diagnosing patients' conditions in related technologies.

[0006] First aspect

[0007] This invention provides a method for analyzing associated diseases, which includes the following steps:

[0008] S1. Obtain disease information from multiple patients. This disease information includes the patient's symptoms and the type of disease.

[0009] S2. Based on the disease information, obtain the association table between disease symptoms and disease types.

[0010] S3. Based on the association table, calculate the degree of coherence of disease combinations including a predetermined number of disease types through hierarchical mining. The number of disease types included in different levels of mining varies, and higher-level mining data sources are based on the mining results of lower-level mining preceding them.

[0011] S4. Based on the degree of cascading, obtain the combination of related diseases.

[0012] S5. Generate diagnostic auxiliary information based on the combination of related diseases.

[0013] In an optional embodiment, the disease information includes the patient's chief complaint of symptoms and the doctor's diagnosis of the disease.

[0014] Based on the disease information, obtain a table relating disease symptoms to disease types, specifically including:

[0015] Based on the patient's chief complaint of symptoms, words are extracted and matched with keywords in the chief complaint symptom dictionary to obtain the symptoms of the disease.

[0016] Based on the doctor's diagnosis information, words are extracted and matched with keywords in the diagnosis dictionary to obtain the type of disease.

[0017] Obtain the association table based on the symptoms and type of disease.

[0018] In one optional embodiment, the chief complaint symptom dictionary is a medical symptom dictionary. The diagnostic disease dictionary is an ICD-10 disease classification dictionary.

[0019] Based on the patient's chief complaint of symptoms, vocabulary is extracted and matched with keywords in a chief complaint symptom dictionary to determine the patient's symptoms. Similarly, based on the doctor's diagnosis information, vocabulary is extracted and matched with keywords in a diagnosis disease dictionary to determine the disease type. Specifically, this includes:

[0020] Based on the patient's chief complaint of symptoms, individual sentences are extracted and then segmented into words to obtain the vocabulary from the patient's chief complaint of symptoms.

[0021] The words in the patient's chief complaint of symptoms are matched with keywords in the medical symptom dictionary to obtain the symptoms of the disease.

[0022] Based on the doctor's diagnosis information, individual sentences are broken down and then segmented into words to obtain the vocabulary in the doctor's diagnosis information.

[0023] The vocabulary in the doctor's disease diagnosis information is matched with keywords in the ICD-10 disease classification dictionary to obtain the types of diseases.

[0024] In an optional embodiment, the degree of cascading of disease combinations, including a predetermined number of disease types, is calculated using a hierarchical mining method based on an association table. Specifically, this includes:

[0025] Based on the association table, retrieve all disease types.

[0026] Repeat the following steps until the current mining level reaches the preset level or no matching disease combination is found:

[0027] Obtain the current mining level X and the mining data source. The initial mining data source is all disease types. x is initially set to 1.

[0028] Based on the mining level and data source, disease combinations are determined through permutation and combination. Each disease combination contains X disease types.

[0029] The degree of cascading of disease combinations containing X disease types is determined based on the association table.

[0030] In an optional embodiment, obtaining the current mining level X and the mining data source specifically includes:

[0031] Obtain the current mining level X and the mining data source. Where:

[0032] When the current mining level X is 1, the mining data source is all disease types.

[0033] When the current mining level X is greater than 1, the mining data source is the disease types contained in all disease combinations that contain X minus 1 disease types and have a seriality greater than the preset value.

[0034] In an optional embodiment, the associated disease combination is obtained based on the degree of cascading, specifically including:

[0035] Based on the degree of coherence, disease combinations with a predetermined number of disease types are extracted if the degree of coherence is greater than a preset value, in order to obtain related disease combinations.

[0036] The default level is 3. The default value is 0.5.

[0037] The degree of coherence is the proportion of disease combinations that occur among all disease symptoms in the association table, including a predetermined number of disease types.

[0038] The second aspect

[0039] This invention provides a disease association analysis device, which includes:

[0040] The disease information acquisition module is used to acquire disease information from multiple patients; wherein, the disease information includes the patient's disease symptoms and disease type;

[0041] The association table acquisition module is used to acquire an association table of disease symptoms and disease types based on the disease information.

[0042] The concurrency calculation module is used to calculate the concurrency of disease combinations including a predetermined number of disease types based on the association table through hierarchical mining; wherein, the number of disease types included in different levels of mining is different, and the data source of higher-level mining is based on the mining results of the lower-level mining that precedes it.

[0043] The combination acquisition module is used to acquire combinations of related diseases based on the degree of cascading.

[0044] The information generation module is used to generate diagnostic auxiliary information based on the associated disease combination.

[0045] In an optional embodiment, the disease information includes the patient's chief complaint and the doctor's diagnosis. The association table retrieval module includes:

[0046] The symptom acquisition unit is used to extract words based on the patient's chief complaint symptom information and match them with keywords in the chief complaint symptom dictionary to obtain the patient's symptoms.

[0047] The disease type acquisition unit is used to extract words based on the doctor's disease diagnosis information and match them with keywords in the disease diagnosis dictionary to obtain the disease type.

[0048] The association table retrieval unit is used to retrieve association tables based on disease symptoms and disease types.

[0049] Third aspect

[0050] This invention provides a disease association analysis device, which includes a processor, a memory, and a computer program stored in the memory. The computer program can be executed by the processor to implement the disease association analysis method as described in the first aspect.

[0051] Fourth aspect

[0052] This invention provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is running, it controls the device where the computer-readable storage medium is located to execute the disease association analysis method as described in the first aspect.

[0053] By adopting the above technical solution, the present invention can achieve the following technical effects:

[0054] Layered data mining can effectively identify related disease combinations from medical data, thereby assisting doctors in diagnosis and enabling early prevention or detection of complications, which has significant practical implications.

[0055] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0056] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0057] Figure 1 This is a flowchart illustrating a method for analyzing related diseases provided in the first embodiment of the present invention.

[0058] Figure 2 This is a logic block diagram of a disease association analysis method provided in the first embodiment of the present invention.

[0059] Figure 3 This is a schematic diagram of a disease association analysis method provided in the first embodiment of the present invention.

[0060] Figure 4 This is a schematic diagram of the structure of a disease association analysis device provided in the second embodiment of the present invention. Detailed Implementation

[0061] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0062] To better understand the technical solution of the present invention, the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0063] It should be understood that the described embodiments are merely some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0064] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0065] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0066] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0067] The use of "first" and "second" in the embodiments is merely to distinguish similar objects and does not represent a specific ordering of objects. It is understood that "first" and "second" can be interchanged in a specific order or sequence where permitted. It should be understood that the objects distinguished by "first" and "second" can be interchanged where appropriate so that the embodiments described herein can be implemented in an order other than those illustrated or described herein.

[0068] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments:

[0069] Example 1:

[0070] Please see Figures 1 to 3 The first embodiment of the present invention provides a method for disease association analysis, which can be executed by a disease association analysis device. In particular, it is executed by one or more processors in the disease association analysis device to implement steps S1 to S5.

[0071] S1. Obtain disease information from multiple patients. This disease information includes the patient's symptoms and the type of disease.

[0072] Specifically, the patient's medical information consists of raw, multi-faceted data from third-party systems such as the HIS system. This raw, multi-faceted data primarily comprises medical record data. Each patient's medical record data consists of a description of the patient's chief complaint and a description of the doctor's diagnosis. This basic data is multi-faceted and may be in text, tables, etc. The patient's chief complaint includes the patient's described symptoms. The doctor's diagnosis includes the type of illness described by the doctor.

[0073] It should be noted that the disease association analysis device can be implemented using electronic devices with computing power, such as personal computers, tablets, smartphones, industrial control computers, and large computing servers.

[0074] S2. Based on the disease information, obtain the association table between disease symptoms and disease types.

[0075] The disease information is raw information, and semantic analysis of the language descriptions is required to perform word matching and extract useful information.

[0076] Specifically: The multi-representation language description is broken down into individual sentences. Then, the content of each sentence, such as the language in the chief complaint / diagnosis, is segmented into words. The segmented words are then matched with the corresponding keyword database. If a match is found, the system will match the sentence content with the keywords.

[0077] For example:

[0078] Statement a: I have a headache.

[0079] Chief Complaint Symptoms Core Terminology: 01 Headache 02 Abdominal Pain

[0080] System-splitting words: I feel a headache / I feel a headache / I feel a headache / ...

[0081] At this point, the keyword matched by statement 'a' is: 01 headache.

[0082] Based on the above embodiments, in an optional embodiment of the present invention, the disease information includes the patient's chief complaint and the doctor's diagnosis. Step S2 specifically includes steps S21 to S23:

[0083] S21. Based on the patient's chief complaint symptom information, extract vocabulary and match it with keywords in the chief complaint symptom dictionary to obtain the symptoms of the disease.

[0084] Based on the above embodiments, in an optional embodiment of the present invention, the chief complaint symptom dictionary is a medical symptom dictionary. S21 specifically includes:

[0085] Based on the patient's chief complaint of symptoms, individual sentences are extracted and then segmented into words to obtain the vocabulary from the patient's chief complaint of symptoms.

[0086] The words in the patient's chief complaint of symptoms are matched with keywords in the medical symptom dictionary to obtain the symptoms of the disease.

[0087] S22. Based on the doctor's disease diagnosis information, extract vocabulary and match it with keywords in the disease diagnosis dictionary to obtain the disease type.

[0088] Based on the above embodiments, in an optional embodiment of the present invention, the diagnostic disease dictionary is an ICD-10 disease classification dictionary. S22 specifically involves:

[0089] Based on the doctor's diagnosis information, individual sentences are broken down and then segmented into words to obtain the vocabulary in the doctor's diagnosis information.

[0090] The vocabulary in the doctor's disease diagnosis information is matched with keywords in the ICD-10 disease classification dictionary to obtain the types of diseases.

[0091] S23. Obtain the association table based on the symptoms and types of the disease.

[0092] like Figure 3As shown, in this invention, a medical symptom dictionary and a disease classification ICD-10 dictionary are first imported from a third-party database to construct a chief complaint symptom dictionary and a diagnostic disease dictionary. It is understood that in other embodiments, the chief complaint symptom dictionary and the diagnostic disease dictionary can import other types of dictionary databases, and this invention does not specifically limit this.

[0093] After constructing the chief complaint symptom dictionary and the diagnostic disease dictionary, each set of collected medical record data (patient chief complaint symptoms + doctor's diagnosed disease) is matched with keywords for the patient's chief complaint symptoms and with keywords for the doctor's corresponding diagnostic disease description and performance. This results in the basic mapping relationship between symptom keywords and disease keywords, i.e., the association table between disease symptoms and disease types.

[0094] S3. Based on the association table, calculate the degree of coherence of disease combinations including a predetermined number of disease types through hierarchical mining. The number of disease types included in different levels of mining varies, and higher-level mining data sources are based on the mining results of lower-level mining preceding them.

[0095] Understandably, after obtaining the association table, it is necessary to identify the correlations between different symptoms. In this embodiment, this is done through hierarchical data mining. Specifically, the transmission difficulty of disease combinations at different levels is calculated. By setting a minimum effective coherence degree (i.e., identifying correlation between diseases), and then through multiple rounds of combination filtering, the final most accurate result is selected. The coherence degree is the proportion of disease combinations that include a predetermined number of disease types among all the symptoms in the association table.

[0096] It should be noted that hierarchical mining refers to first calculating the frequency (i.e., the degree of concurrency) of a single disease type appearing in the association table. Then, disease types with a frequency greater than a preset value (effective degree of concurrency) are extracted, and their combinations are arranged to obtain disease combinations with one more disease type. The degree of concurrency of these disease combinations is then calculated again until the number of diseases in a combination reaches a preset number (i.e., a preset level). The preset level is 3, and the preset value is 0.5. In other embodiments, the prediction level and preset value can be other values, and this invention does not specifically limit them.

[0097] Based on the above embodiments, in an optional embodiment of the present invention, step S3 specifically includes:

[0098] S31. Based on the association table, obtain all disease types.

[0099] S32. Repeat steps A to C until the current mining level reaches the preset level or there is no matching disease combination:

[0100] A. Obtain the current mining level X and the mining data source. The initial mining data source is all disease types. x is initially set to 1.

[0101] B. Based on the mining level and data source, determine the disease combination through permutation and combination. Each disease combination contains X disease types.

[0102] C. Determine the degree of cascading of disease combinations containing X disease types based on the association table.

[0103] Specifically, the mining level X is the number of times steps A to C are repeated. X=1 for the first execution, X=2 for the second execution, and X=3 for the third execution. Using a layered mining approach can significantly reduce the computational load and has great practical significance.

[0104] Based on the above embodiments, in an optional embodiment of the present invention, step A specifically includes:

[0105] Obtain the current mining level X and the mining data source. Where:

[0106] When the current mining level X is 1, the mining data source is all disease types.

[0107] When the current mining level X is greater than 1, the mining data source is the disease types contained in all disease combinations containing X minus 1 disease types with a seriality greater than a preset value.

[0108] Specifically, since the data source is obtained from the results of low-level mining, the higher the level, the less data is available from the data source, which can greatly reduce the amount of computation required for mining and has great practical significance.

[0109] This process involves continuous accumulation and updating of sample data, therefore the mapping table is constantly being updated and calculated. Furthermore, the higher the degree of contiguity in the extraction of combinations, the greater the correlation between diseases, and the more accurate the data obtained. Additionally, the larger the base number of diseases in each round, the broader the range of diseases that can be combined in the response analysis.

[0110] S4. Based on the degree of cascading, obtain the combination of related diseases.

[0111] Specifically, after the stratified data mining is completed, the disease combination with the highest level and the degree of coherence greater than the preset value is the associated disease combination.

[0112] Based on the above embodiments, in an optional embodiment of the present invention, step S4 specifically includes:

[0113] Based on the degree of coherence, disease combinations with a predetermined number of disease types are extracted if the degree of coherence is greater than a preset value, in order to obtain related disease combinations.

[0114] S5. Generate diagnostic auxiliary information based on the combination of related diseases.

[0115] After obtaining the associated disease combination, diagnostic auxiliary information is generated during the doctor's diagnosis process to remind the doctor to pay attention to whether the patient has complications, thereby enabling more effective diagnosis and prevention of the patient.

[0116] The final cascaded disease results are then applied in specific medical scenarios, for example:

[0117] The hypothesis is that [common cold, high blood pressure, intracranial tumor] are highly correlated diseases.

[0118] Application in disease prevention: Patients with hypertension have a higher risk of catching a cold and developing intracranial tumors, so they need to take relevant disease prevention interventions in their daily lives.

[0119] Application of expert consultation: When patients with intracranial tumors undergo expert consultation, doctors from the chronic disease department (hypertension) and the general internal medicine department (common cold) need to participate in the consultation together.

[0120] Layered data mining can effectively identify related disease combinations from medical data, thereby assisting doctors in diagnosis and enabling early prevention or detection of complications, which has significant practical implications.

[0121] The following is a specific example to illustrate this:

[0122] Step 1

[0123] Because each set of collected medical record data includes the patient's chief complaint and the doctor's diagnosis, steps S1 and S2 can extract the core keyword associations from each set of data.

[0124] For example: The collected medical record data 1 is as follows:

[0125] Patient's chief complaint: I feel a headache ---> Keywords: headache.

[0126] Doctor's diagnosis: The patient is suspected of having a cold and high blood pressure ---> Keywords: cold, high blood pressure.

[0127] Therefore, the mapping relationship is: headache <--> cold, high blood pressure.

[0128]

[0129] By analyzing a large amount of medical record data through steps S1 and S2, a basic table of mapping relationships can be obtained, for example:

[0130]

[0131] Step Two

[0132] We need to analyze the basic relationship table to identify which diseases are related in a synergistic manner. (Synergy refers to the probability of having the disease simultaneously.)

[0133] Calculate the coherence degree of a single disease (p=1) in the above dataset: Coherence degree: calculates the probability of a disease appearing in the basic mapping table. We see that "common cold" appears as a suspected disease 4 times out of 5 symptoms. Therefore, for its single disease case (p=1), the coherence degree C(common cold) = 4 / 5. Similarly, we obtain the coherence degrees of each disease when p=1 as shown in the table below.

[0134] Serial Number Diseases C1 (Series Degree) 1 cold 4 / 5 2 hypertension 4 / 5 3 Intracranial tumor 1 4 Cervical spondylosis 2 / 5 5 meningitis 3 / 5 6 appendicitis 1 / 5

[0135] We assume a minimum concurrency threshold of 0.5. Data combinations exceeding this threshold are considered valuable. Therefore, after the first round of filtering, the following effective concurrency data (i.e., data exceeding 0.5) are obtained:

[0136]

[0137] Based on the results of the first round of data mining, p=2 is calculated, which means calculating the cascading relationship between the two diseases.

[0138]

[0139]

[0140] After filtering out invalid combinations using a series threshold C = 0.5, the valid series data is obtained.

[0141] Serial Number Diseases C2 (Series Degree) 1 cold, high blood pressure 3 / 5 2 Common cold, intracranial tumor 4 / 5 4 Hypertension, intracranial tumor 4 / 5

[0142] Based on the results of the second round of data mining, p=3 is calculated, which means calculating the cascading relationship between the three disease combinations.

[0143] Serial Number Diseases C3 (Series Degree) 1 Common cold, high blood pressure, intracranial tumor 3 / 5

[0144] When the data mining reaches a preset level, and the results contain disease combinations with a synergy greater than a preset value, these disease combinations with a synergy greater than the preset value are deemed valid.

[0145] Therefore, after multiple rounds of combined analysis, it was found that there is a strong correlation between the three diseases: [common cold], [hypertension], and [intracranial tumor]. That is, people with hypertension are more likely to also have a common cold and an intracranial tumor.

[0146] Example 2

[0147] Please see Figure 4This invention provides a disease association analysis device, which includes:

[0148] The disease information acquisition module 1 is used to acquire disease information of multiple patients; wherein, the disease information includes the patient's disease symptoms and disease type;

[0149] The association table acquisition module 2 is used to acquire an association table of disease symptoms and disease types based on the disease information.

[0150] The seriality calculation module 3 is used to calculate the seriality of disease combinations including a predetermined number of disease types by means of hierarchical mining based on the association table; wherein, the number of disease types included in different levels of mining is different, and the data source of higher-level mining is based on the mining results of the lower-level mining that precedes it.

[0151] The combination acquisition module 4 is used to acquire the combination of related diseases based on the degree of cascading.

[0152] Information generation module 5 is used to generate diagnostic auxiliary information based on the associated disease combination.

[0153] In an optional embodiment, the disease information includes the patient's chief complaint of symptoms and the doctor's diagnosis of the disease.

[0154] Module 2 for retrieving related tables includes:

[0155] The symptom acquisition unit is used to extract words based on the patient's chief complaint symptom information and match them with keywords in the chief complaint symptom dictionary to obtain the patient's symptoms.

[0156] The disease type acquisition unit is used to extract words based on the doctor's disease diagnosis information and match them with keywords in the disease diagnosis dictionary to obtain the disease type.

[0157] The association table retrieval unit is used to retrieve association tables based on disease symptoms and disease types.

[0158] In one optional embodiment, the chief complaint symptom dictionary is a medical symptom dictionary. The diagnostic disease dictionary is an ICD-10 disease classification dictionary.

[0159] The symptom acquisition unit is specifically used for...

[0160] Based on the patient's chief complaint of symptoms, individual sentences are extracted and then segmented into words to obtain the vocabulary from the patient's chief complaint of symptoms.

[0161] The words in the patient's chief complaint of symptoms are matched with keywords in the medical symptom dictionary to obtain the symptoms of the disease.

[0162] Disease type acquisition unit, specifically used for

[0163] Based on the doctor's diagnosis information, individual sentences are broken down and then segmented into words to obtain the vocabulary in the doctor's diagnosis information.

[0164] The vocabulary in the doctor's disease diagnosis information is matched with keywords in the ICD-10 disease classification dictionary to obtain the types of diseases.

[0165] In an optional embodiment, the seriality calculation module 3 specifically includes:

[0166] The Disease Type unit is used to retrieve all disease types based on the association table.

[0167] The seriality calculation unit is used to repeat the following steps until the current mining level reaches the preset level or there is no matching disease combination:

[0168] Obtain the current mining level X and the mining data source. The initial mining data source is all disease types. x is initially set to 1.

[0169] Based on the mining level and data source, disease combinations are determined through permutation and combination. Each disease combination contains X disease types.

[0170] The degree of cascading of disease combinations containing X disease types is determined based on the association table.

[0171] In an optional embodiment, obtaining the current mining level X and the mining data source specifically includes:

[0172] Obtain the current mining level X and the mining data source. Where:

[0173] When the current mining level X is 1, the mining data source is all disease types.

[0174] When the current mining level X is greater than 1, the mining data source is the disease types contained in all disease combinations that contain X minus 1 disease types and have a seriality greater than the preset value.

[0175] In an optional embodiment, the combined acquisition module 4 is specifically used for

[0176] Based on the degree of coherence, disease combinations with a predetermined number of disease types are extracted if the degree of coherence is greater than a preset value, in order to obtain related disease combinations.

[0177] In an optional embodiment, the preset level is 3.

[0178] In an optional embodiment, the preset value is 0.5.

[0179] In an optional embodiment, the degree of cascading is the proportion of disease combinations, including a predetermined number of disease types, that occur among all disease symptoms in the association table.

[0180] Example 3

[0181] This invention provides a disease association analysis device, which includes a processor, a memory, and a computer program stored in the memory. The computer program can be executed by the processor to implement the disease association analysis method as described in Embodiment 1.

[0182] Example 4

[0183] This invention provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is running, it controls the device where the computer-readable storage medium is located to execute the disease association analysis method as described in Embodiment 1.

[0184] In the several embodiments provided in this invention, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus and method embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0185] In addition, the functional modules in the various embodiments of the present invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0186] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, electronic device, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks. It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further restrictions, an element defined by the phrase "comprising a..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0187] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for analyzing related diseases, characterized in that, Include: Obtain disease information from multiple patients; wherein, the disease information includes the patient's symptoms and the type of disease; Based on the disease information, obtain the association table between disease symptoms and disease types; Based on the association table, the degree of contiguity of disease combinations including a predetermined number of disease types is calculated through hierarchical mining; wherein, the number of disease types in the disease combinations included in different levels of mining is different, and the data source of higher-level mining is based on the mining results of the lower-level mining that precedes it. Based on the degree of cascading, obtain the combination of related diseases; Based on the aforementioned combinations of related diseases, diagnostic auxiliary information is generated; Based on the aforementioned association table, the degree of cascading of disease combinations, including a predetermined number of disease types, is calculated using hierarchical mining; specifically, this includes: Based on the association table, obtain all disease types; Repeat the following steps until the current mining level reaches the preset level or no matching disease combination is found: Obtain the current mining level X and the mining data source; where the initial mining data source is all disease types; x is initially 1; Based on the mining levels and data sources, disease combinations are determined through permutation and combination; each disease combination contains X disease types. The degree of cascading of disease combinations containing X disease types is determined based on the association table. Obtain the current mining level X and the mining data source, specifically including: When the current mining level X is 1, the mining data source is all the disease types; When the current mining level X is greater than 1, the mining data source is the disease types contained in all disease combinations containing X minus 1 disease types with a seriality greater than a preset value. Based on the cascading degree, the associated disease combination is obtained, specifically including: based on the cascading degree, extracting the disease combination that includes a predetermined number of disease types with a cascading degree greater than a preset value, so as to obtain the associated disease combination; The degree of coherence is the proportion of disease combinations, including a predetermined number of disease types, that occur among all the disease symptoms in the association table.

2. The method for analyzing related diseases according to claim 1, characterized in that, The disease information includes the patient's chief complaint of symptoms and the doctor's diagnosis of the disease; Based on the described disease information, a correlation table between disease symptoms and disease types is obtained, specifically including: Based on the patient's chief complaint symptom information, words are extracted and matched with keywords in the chief complaint symptom dictionary to obtain the disease symptoms; Based on the doctor's disease diagnosis information, words are extracted and matched with keywords in the disease diagnosis dictionary to obtain the disease type; Based on the disease symptoms and the disease type, obtain the association table.

3. The method for analyzing related diseases according to claim 2, characterized in that, The chief complaint symptom dictionary is a medical symptom dictionary; the diagnostic disease dictionary is an ICD-10 disease classification dictionary. Based on the patient's chief complaint symptom information, words are extracted and matched with keywords in the chief complaint symptom dictionary to obtain the disease symptoms; And, based on the doctor's disease diagnosis information, extract words and match them with keywords in the disease diagnosis dictionary to obtain the disease type; Specifically, it includes: Based on the patient's chief complaint information, individual sentences are extracted and word segmentation is performed on each sentence to obtain the vocabulary in the patient's chief complaint information; The words in the patient's chief complaint symptom information are matched with the keywords in the medical symptom dictionary to obtain the disease symptoms; Based on the doctor's disease diagnosis information, individual sentences are extracted and word segmentation is performed on the individual sentences to obtain the vocabulary in the doctor's disease diagnosis information; The vocabulary in the doctor's disease diagnosis information is matched with the keywords in the disease classification ICD-10 dictionary to obtain the disease type.

4. The method for analyzing related diseases according to claim 1, characterized in that, The preset level is 3; the preset value is 0.

5.

5. A disease association analysis device, characterized in that, Used to perform the disease association analysis method according to any one of claims 1 to 4; The associated disease analysis device includes: The disease information acquisition module is used to acquire disease information from multiple patients; wherein, the disease information includes the patient's disease symptoms and disease type; The association table acquisition module is used to acquire an association table of disease symptoms and disease types based on the disease information. The concurrency calculation module is used to calculate the concurrency of disease combinations including a predetermined number of disease types based on the association table through hierarchical mining; wherein, the number of disease types in the disease combinations included in different levels of mining is different, and the data source of higher-level mining is based on the mining results of the lower-level mining that precedes it. The combination acquisition module is used to acquire combinations of related diseases based on the degree of cascading. The information generation module is used to generate diagnostic auxiliary information based on the associated disease combination.

6. The disease association analysis device according to claim 5, characterized in that, The disease information includes the patient's chief complaint of symptoms and the doctor's diagnosis of the disease; The association table retrieval module includes: The symptom acquisition unit is used to extract words based on the patient's chief complaint symptom information and match them with keywords in the chief complaint symptom dictionary to obtain the symptom. The disease type acquisition unit is used to extract words based on the doctor's disease diagnosis information and match them with keywords in the disease diagnosis dictionary to obtain the disease type; The association table acquisition unit is used to acquire the association table based on the disease symptoms and the disease type.

7. A disease association analysis device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory; the computer program can be executed by the processor to implement the disease association analysis method as described in any one of claims 1 to 4.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device on which the computer-readable storage medium is located to perform the disease association analysis method as described in any one of claims 1 to 4.

Images