Microbial information interpretation method, device, equipment and storage medium

Abstract

The embodiment of the present invention discloses a method and device, equipment and storage medium for interpreting microbial information, the method comprising: obtaining microbial information and specimen information input by a user on a client; determining microbial classification information in the microbial information using a preset logical classification tree, microbial information and specimen information; if the microbial classification information includes possible pathogens, determining the questions to be asked corresponding to the target microorganisms in the logical classification tree according to the target microorganisms corresponding to the possible pathogens, and returning the questions to be asked to the client; classifying the target microorganisms according to the answers and the logical classification tree, and determining the target classification information of the target microorganisms; determining the microbial classification results corresponding to each microorganism in the microbial information according to the microbial classification information and the target classification information, and returning the microbial classification results to the client. Through the above method, the accuracy of microbial classification can be improved.

Description

Technical Field

[0001] The present invention relates to the field of microbial testing technology, and in particular to a method and device for interpreting microbial information, equipment and storage medium. Background Art

[0002] Using high-throughput gene sequencing technology, DNA and / or RNA sequencing is performed on all microorganisms in various specimens of patients with difficult and serious infections. Through comparison with microbial-specific databases and intelligent algorithm analysis, the species information of the microorganisms is obtained to guide clinical treatment in a more targeted manner, which helps to achieve precise treatment of infectious diseases.

[0003] Taking metagenomic testing (mNGS) as an example, from the technical principle of mNGS, the data filtering of bioinformatics technology and the construction of various databases cannot solve the problem of simultaneous detection of multiple pathogens in most cases, that is, it is impossible to distinguish the real pathogens in the test report.

[0004] At present, the accuracy of interpreting mNGS reports still depends more on the doctor's experience and is time-consuming. Clinical doctors, especially primary care doctors, lack the ability to comprehensively interpret the metagenetic test reports and necessary clinical information. Summary of the invention

[0005] The main purpose of the present invention is to provide a method and device, equipment and storage medium for interpreting microbial information, which can solve the problem of insufficient ability of doctors to interpret microorganisms in the prior art.

[0006] To achieve the above object, the present invention provides a method for interpreting microbial information in a first aspect, the method comprising:

[0007] Obtain the microbial information and specimen information entered by the user on the client;

[0008] Using a preset logical classification tree, the microorganism information and the specimen information, determining microorganism classification information in the microorganism information, wherein the microorganism classification information includes a correspondence between each microorganism in the microorganism information and a microorganism category, wherein the microorganism category includes pathogenic bacteria, possible pathogenic bacteria or background bacteria, and the logical classification tree includes a number of classification rules constructed based on expert knowledge and clinical experience;

[0009] If the microorganism classification information includes possible pathogenic bacteria, determining the question to be asked corresponding to the target microorganism in the logical classification tree according to the target microorganism corresponding to the possible pathogenic bacteria, and returning the question to be asked to the client;

[0010] receiving the answer given by the user based on the question to be asked and returned by the client, and classifying the target microorganism according to the answer and the logical classification tree to determine the target classification information of the target microorganism;

[0011] According to the microorganism classification information and the target classification information, a microorganism classification result corresponding to each microorganism in the microorganism information is determined, and the microorganism classification result is returned to the client.

[0012] In a feasible implementation, the question to be asked includes at least test report information, and the step of classifying the target microorganism according to the answer and the logical classification tree to determine the target classification information of the target microorganism includes:

[0013] Performing semantic analysis on the answer, extracting target inspection report information corresponding to the target microorganism in the answer, wherein the target detection information includes one or more of the number of specific sequences, relative abundance and coverage;

[0014] The target microorganism is classified according to the target inspection report information and the logical classification tree to determine the target classification information of the target microorganism.

[0015] In a feasible implementation, the question to be asked includes at least clinical examination information, and the step of classifying the target microorganism according to the answer and the logical classification tree to determine the target classification information of the target microorganism includes:

[0016] Performing semantic analysis on the answer to extract target clinical examination information in the answer, wherein the target clinical examination information at least includes examination information of one or more of clinical physical examination items, instrument physical examination items or laboratory physical examination items;

[0017] The target microorganism is classified according to the target clinical examination information and the logical classification tree to determine target classification information of the target microorganism.

[0018] In a feasible implementation, the question to be asked at least includes the source of infection, and the step of classifying the target microorganism according to the answer and the logical classification tree to determine the target classification information of the target microorganism includes:

[0019] Performing semantic analysis on the answer to extract the target infection source corresponding to the target microorganism in the answer, wherein the target infection source includes at least nosocomial infection or community infection;

[0020] The target microorganism is classified according to the target infection source and the logical classification tree to determine target classification information of the target microorganism.

[0021] In a feasible implementation, the question to be asked at least includes clinical manifestations, and the step of classifying the target microorganism according to the answer and the logical classification tree to determine the target classification information of the target microorganism includes:

[0022] Performing semantic analysis on the answer to extract target clinical manifestations in the answer, wherein the target clinical manifestations include one or more abnormal changes occurring in the body;

[0023] The target microorganism is classified according to the target clinical manifestation and the logical classification tree to determine target classification information of the target microorganism.

[0024] In a feasible implementation, the method further includes:

[0025] If the microbial classification result of the microorganism includes a microbial category of pathogenic bacteria, determining a first diagnosis and treatment recommendation for the microorganism corresponding to the pathogenic bacteria according to the microorganism corresponding to the pathogenic bacteria, the microbial classification result, and clinical information input by the user;

[0026] If the microbial classification result of the microorganism includes a microbial category of possible pathogenic bacteria, then based on the microorganism corresponding to the possible pathogenic bacteria, the microbial classification result and the clinical information input by the user, a second diagnosis and treatment recommendation for the microorganism corresponding to the possible pathogenic bacteria is determined, and the second diagnosis and treatment recommendation at least includes the pathogenicity probability of the microorganism corresponding to the possible pathogenic bacteria.

[0027] In a feasible implementation, the method further includes:

[0028] Receiving feedback information of the user returned by the client, wherein the feedback information includes correct interpretation feedback or incorrect interpretation feedback;

[0029] Performing data statistics on the correct interpretation feedback and the incorrect interpretation feedback to determine the interpretation accuracy rate;

[0030] If the interpretation accuracy is less than a preset accuracy threshold, a correction prompt is output to the administrator backend, wherein the correction prompt is used to prompt the administrator to determine whether to update the classification rules of the logical classification tree according to the user's feedback information and the interpretation accuracy;

[0031] If the interpretation accuracy is greater than or equal to a preset accuracy threshold, it is determined not to update the logical classification tree.

[0032] To achieve the above-mentioned object, the second aspect of the present invention provides a device for interpreting microbial information, the device comprising:

[0033] Information acquisition module: used to obtain the microbial information and specimen information entered by the user on the client;

[0034] The first classification module is used to determine the microbial classification information in the microbial information by using a preset logical classification tree, the microbial information and the specimen information, wherein the microbial classification information includes the corresponding relationship between each microorganism in the microbial information and the microbial category, and the microbial category includes pathogenic bacteria, possible pathogenic bacteria or background bacteria, and the logical classification tree includes a number of classification rules constructed based on expert knowledge and clinical experience;

[0035] Question consultation module: for determining the question to be asked corresponding to the target microorganism in the logic classification tree according to the target microorganism corresponding to the possible pathogenic bacteria if the microorganism classification information includes possible pathogenic bacteria, and returning the question to be asked to the client;

[0036] A second classification module is used for receiving the answer given by the user based on the question to be asked and returned by the client, and classifying the target microorganism according to the answer and the logical classification tree to determine the target classification information of the target microorganism;

[0037] Classification determination module: used to determine the microbial classification result corresponding to each microorganism in the microbial information according to the microbial classification information and the target classification information, and return the microbial classification result to the client.

[0038] To achieve the above-mentioned purpose, the third aspect of the present invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the steps shown in the first aspect or any feasible implementation method.

[0039] To achieve the above-mentioned purpose, the fourth aspect of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps shown in the first aspect or any feasible implementation method.

[0040] The embodiments of the present invention have the following beneficial effects:

[0041] The present invention provides a method for interpreting microbial information, the method comprising: obtaining microbial information and specimen information input by a user on a client; determining microbial classification information in the microbial information by using a preset logical classification tree, microbial information and specimen information, the microbial classification information comprising a correspondence between each microorganism in the microbial information and a microbial category, the microbial category comprising pathogenic bacteria, possible pathogenic bacteria or background bacteria, the logical classification tree comprising a number of classification rules constructed based on expert knowledge and clinical experience; if the microbial classification information includes possible pathogenic bacteria, determining a question to be asked corresponding to the target microorganism in the logical classification tree according to the target microorganism corresponding to the possible pathogenic bacteria, and returning the question to be asked to the client; receiving an answer returned by the client based on the question to be asked by the user, and classifying the target microorganism according to the answer and the logical classification tree, and determining the target classification information of the target microorganism; determining a microbial classification result corresponding to each microorganism in the microbial information according to the microbial classification information and the target classification information, and returning the microbial classification result to the client. Through the above method, after the preliminary classification of microorganisms using specimens, further classification of questions to be asked obtained from the classification rules constructed based on clinical experience for possible pathogens can be achieved, thereby improving the accuracy of the classification of microorganisms corresponding to possible pathogens. This can help improve the report interpretation ability of primary care doctors, maximize the clinical value of high-throughput projects for pathogenic microorganisms, and assist in accurate diagnosis and effective treatment of patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, 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 invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] in:

[0044] Figure 1 is a flow chart of a method for interpreting microbial information in an embodiment of the present invention;

[0045] Figure 2 This is a schematic diagram of a target classification result displayed on a client in an embodiment of the present invention;

[0046] Figure 3 is another flow chart of a method for interpreting microbial information in an embodiment of the present invention;

[0047] FIG4 is a schematic diagram of a diagnosis and treatment suggestion in an embodiment of the present invention, Figure 4a is a schematic diagram of a first diagnosis and treatment suggestion in an embodiment of the present invention, Figure 4bA schematic diagram of a second diagnosis and treatment suggestion in an embodiment of the present invention;

[0048] Figure 5 A schematic diagram of a user feedback interface in an embodiment of the present invention;

[0049] Figure 6 It is a structural block diagram of a device for interpreting microbial information in an embodiment of the present invention;

[0050] Figure 7 4 is a structural block diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] See also Figure 1 , Figure 1 FIG. 1 is a flow chart of a method for interpreting microbial information in an embodiment of the present invention. Figure 1 The method shown can be applied to a client or a server. This embodiment is described by taking application to a client as an example. The method for interpreting microbial information includes the following steps:

[0053] 101. Obtaining microbial information and specimen information input by the user on the client;

[0054] It should be noted that this embodiment is an improvement made in the face of the doctor's insufficient ability to interpret the test results of high-throughput gene sequencing technology, such as the lack of ability to classify and interpret the microorganisms in the test report. Therefore, in this embodiment, it is necessary to first obtain relevant information of the test results (such as a test report), such as by obtaining the microbial information and specimen information input by the user (doctor or patient) on the client. The client can be an electronic device such as an intelligent terminal carrying the method for interpreting the microbial information in this implementation, and the input method includes but is not limited to scanning, inputting text or selecting a preset text information box, etc., and the distance is not limited. Among them, taking mNGS inspection as an example, the microbial information includes the name of the microorganism, such as: Streptococcus pneumoniae, cytomegalovirus, Acinetobacter baumannii, etc. The microorganisms listed on the mNGS inspection sheet, and the specimen information includes the name of the inspection specimen, such as: alveolar lavage fluid, sputum, blood or cerebrospinal fluid, etc. specimens. This example is not limited. Among them, the user can enter one or more microorganisms at the same time on the client and classify them together, which is not limited in this embodiment.

[0055] 102. Determine microbial classification information in the microbial information by using a preset logical classification tree, the microbial information, and the specimen information, wherein the microbial classification information includes a correspondence between each microorganism in the microbial information and a microbial category, wherein the microbial category includes pathogenic bacteria, possible pathogenic bacteria, or background bacteria, and the logical classification tree includes a number of classification rules constructed based on expert knowledge and clinical experience;

[0056] Furthermore, each microorganism in the obtained microbial information is classified to distinguish different categories of microorganisms. In this embodiment, each microorganism in the obtained microbial information is classified by a preset logical classification tree. The logical classification tree is composed of multiple branches, each branch has multiple branch nodes, each branch has different classification logics, and each node has different classification rules. Therefore, the logical classification tree includes several classification rules based on expert knowledge and clinical experience. The last branch node of each branch of the logical tree corresponds to the classification result of each microorganism. Among them, due to the characteristics of the microorganism itself, different manifestations exist in different specimens. For example, the pathogenic risk of the same microorganism in different specimen types may be different. For example, Elizabeth meningitis septicemia detected in cerebrospinal fluid will be judged as a "definite pathogenic bacterium", and detected in alveolar lavage fluid will be judged as a "possible pathogenic bacterium". Therefore, the first branch node of the logical classification tree is designed to classify microorganisms according to specimen information. This embodiment determines the microbial classification information in the microbial information through a preset logical classification tree, microbial information, and specimen information, and obtains the corresponding relationship between each microorganism and the microbial category, wherein the microbial category includes pathogenic bacteria, possible pathogenic bacteria, or background bacteria. Exemplarily, "definite pathogenic bacteria" are relatively strict pathogenic bacteria in clinical practice, such as Mycobacterium tuberculosis detected in alveolar lavage fluid, and it is recommended that clinical attention and active intervention be given; "possible pathogenic bacteria" are opportunistic / conditional pathogenic bacteria, such as Pseudomonas aeruginosa detected in sputum, which need to be determined in combination with more clinical information or other detection methods; "background bacteria" are microorganisms with little clinical significance in this clinical case, such as the detection of circovirus in alveolar lavage fluid, and it is recommended that the possibility of pathogenicity be ignored. Clinical experts uniformly formulate interpretation rules (classification rules), combine microbial characteristics, and transform the clinical interpretation experience of mNGS reports into system language. After being solidified through the information system, the standardization and intelligence of the test report are realized, helping clinical customers to quickly and accurately interpret the results of macrogene detection.

[0057] Through step 102, the types of microorganisms detected by the pathogenic microorganism metagenome can be searched and input in the client, and the input microorganisms can be directly preliminarily classified based on the test specimen type, rather than simply listing the microorganism detection situation to narrow the diagnosis range. Step 102 can be considered as a preliminary classification, and the implementation method of the preliminary classification is realized through the dictionary of microorganisms in the logic tree, wherein each microorganism in the dictionary of microorganisms has a corresponding classification rule path corresponding to different specimen types (such as microorganism O corresponding to specimen type A / B / C / D has corresponding positive / possible pathogenic bacteria / background bacteria classification), and the corresponding classification results can be given in the user interface of the client through the user input combined with this association relationship. Each time the user uses it, he can input multiple microorganisms based on the actual test results and get the preliminary classification results with one click. Furthermore, the search for the name of the microorganism has also established a standardized pool management. There are multiple nicknames for the same microorganism in clinical practice, and the system can also support the search of the nickname associated with the corresponding standard microorganism classification logic tree branch.

[0058] 103. If the microorganism classification information includes possible pathogenic bacteria, determine the question to be asked corresponding to the target microorganism in the logical classification tree according to the target microorganism corresponding to the possible pathogenic bacteria, and return the question to be asked to the client;

[0059] It should be noted that for possible pathogens, it is necessary to further determine the accuracy of their classification judgment, that is, whether they are really pathogenic. Therefore, if the microbial classification information includes possible pathogens, the questions to be asked corresponding to the target microorganisms in the logical classification tree are determined according to the target microorganisms corresponding to the possible pathogens, and the questions to be asked are returned to the client, where the questions to be asked are related to the classification rules of the branch nodes in the logical tree, and different microorganisms correspond to different questions to be asked. For example, for the "possible pathogen" cytomegalovirus, the question to be asked can be "What are the imaging results?" Different microorganisms have different classification rules, and the corresponding questions to be asked are also different.

[0060] 104. Receive the answer given by the user based on the question to be asked and returned by the client, and classify the target microorganism according to the answer and the logical classification tree to determine the target classification information of the target microorganism;

[0061] Furthermore, the user can input the answer to the question to be asked on the client, and by receiving the answer based on the question to be asked by the user returned by the client, the target microorganism is classified according to the answer and the logical classification tree, and the target classification information of the target microorganism is determined. For example, the question to be asked for the "possible pathogen" cytomegalovirus may be "What are the imaging results?", and the user's possible answers may be "pulmonary interstitial lesions", "others (exudative, large consolidation, cavitary lesions)", "no imaging examination". Therefore, the target classification information of the target microorganism can be determined according to the different answers of the user combined with the classification rules of the logical tree. The target classification information includes the correspondence between the target microorganism and the microorganism category.

[0062] 105. Determine a microbial classification result corresponding to each microorganism in the microbial information according to the microbial classification information and the target classification information, and return the microbial classification result to the client.

[0063] After the above steps, the microbial classification information and target classification information can be obtained, which can help users interpret the test report, know the categories of each microorganism, and provide help for diagnosis and treatment. Therefore, the microbial classification results corresponding to each microorganism in the microbial information can be determined according to the microbial classification information and target classification information, and the microbial classification results can be returned to the client, so that the user can view the classification results on the client. Figure 2 , Figure 2 Schematic diagram of target classification results displayed on a client in an embodiment of the present invention. The detection results refer to the detection results of high-throughput gene sequencing technology, such as multiple pathogen targeted sequencing results, microbial third-generation sequencing results, mNGS conventional metagene sequencing results, etc. Figure 2 The mNGS conventional macrogene report shows a list of microorganisms detected. The mNGS conventional macrogene report shows that "the sample was positive after DNA-pathogen microorganism macrogene detection, and the sequence number of Streptococcus pneumoniae was 2055, the sequence number of Streptococcus mitis was 1862, the sequence number of CMV was 12, and some suspected background microorganisms were detected. Please make a comprehensive judgment based on the patient's clinical manifestations and other auxiliary diagnosis results." The auxiliary diagnosis result is the microorganism classification result obtained by using this embodiment. Figure 2 The auxiliary diagnosis results shown are: definite pathogens: Streptococcus pneumoniae; possible pathogens: cytomegalovirus and Acinetobacter baumannii; background bacteria: parvovirus.

[0064] The present invention provides a method for interpreting microbial information, the method comprising: obtaining microbial information and specimen information input by a user on a client; determining microbial classification information in the microbial information by using a preset logical classification tree, microbial information and specimen information, the microbial classification information comprising a correspondence between each microorganism in the microbial information and a microbial category, the microbial category comprising pathogenic bacteria, possible pathogenic bacteria or background bacteria, the logical classification tree comprising a number of classification rules constructed based on expert knowledge and clinical experience; if the microbial classification information includes possible pathogenic bacteria, determining a question to be asked corresponding to the target microorganism in the logical classification tree according to the target microorganism corresponding to the possible pathogenic bacteria, and returning the question to be asked to the client; receiving an answer returned by the client based on the question to be asked by the user, and classifying the target microorganism according to the answer and the logical classification tree, and determining the target classification information of the target microorganism; determining a microbial classification result corresponding to each microorganism in the microbial information according to the microbial classification information and the target classification information, and returning the microbial classification result to the client. Through the above method, after the preliminary classification of microorganisms using specimens, further classification of questions to be asked obtained from the classification rules constructed based on clinical experience for possible pathogens can be achieved, thereby improving the accuracy of the classification of microorganisms corresponding to possible pathogens. This can help improve the report interpretation ability of primary care doctors, maximize the clinical value of high-throughput projects for pathogenic microorganisms, and assist in accurate diagnosis and effective treatment of patients.

[0065] See also Figure 3 , Figure 3 Another flow chart of a method for interpreting microbial information in an embodiment of the present invention is shown in FIG. Figure 3 The method shown comprises the following steps:

[0066] 301. Obtaining microbial information and specimen information input by the user on the client;

[0067] 302. Determine microbial classification information in the microbial information by using a preset logical classification tree, the microbial information, and the specimen information, wherein the microbial classification information includes a correspondence between each microorganism in the microbial information and a microbial category, wherein the microbial category includes pathogenic bacteria, possible pathogenic bacteria, or background bacteria, and the logical classification tree includes a number of classification rules constructed based on expert knowledge and clinical experience;

[0068] 303. If the microorganism classification information includes possible pathogenic bacteria, determine the question to be asked corresponding to the target microorganism in the logical classification tree according to the target microorganism corresponding to the possible pathogenic bacteria, and return the question to be asked to the client;

[0069] 304. Receive the answer given by the user based on the question to be asked and returned by the client, and classify the target microorganism according to the answer and the logical classification tree to determine the target classification information of the target microorganism;

[0070] It should be noted that the contents shown in steps 301, 302, 303 and 304 are the same as Figure 1 The contents shown in steps 101, 102, 103 and 104 are similar. To avoid repetition, they are not described here. For details, please refer to the contents shown in the aforementioned steps 101, 102, 103 and 104. Further, for positive pathogens and background bacteria, clinical specimen information is sufficient to quickly obtain corresponding diagnostic results and treatment recommendations. Possible pathogens will also give the possibility of preliminary suspicion, but more clinical information can be input to obtain more accurate auxiliary diagnosis recommendations. This situation is achieved by configuring the logic classification tree (logic judgment decision tree) in the background, that is, steps 303 and 304. For different microorganisms, there are different decision trees (multiple microorganisms can also share a set of decision trees). The questions and answer options of each branch can be customized in the administrator background. After the logic tree is published, it will take effect on the client. The user can select the corresponding answer option or give an answer according to the configured question on the client, and obtain the final classification result returned to the client according to the logical branch path. In this way, users can be guided to provide more clinical information, thereby helping to judge the clinical significance of possible pathogens to the current case.

[0071] In a feasible implementation, since different microorganisms have different characteristic manifestations, the classification rules of the branch nodes of the logic tree include but are not limited to test report information, clinical examination information, infection sources and clinical manifestations, which are conducive to accurate distinction and related medical information that is beneficial to microbial classification. Different questions to be asked can be determined by combining the logic tree and different microorganisms. The questions to be asked will have different focuses according to different microorganisms, wherein the test report information includes specific sequence number, relative abundance and coverage, the clinical examination information includes one or more examination information of clinical physical examination items, instrument physical examination items or laboratory physical examination items, such as imaging examination, blood test and other clinical examination information, the infection source includes hospital infection or community infection, etc., and the clinical manifestation includes a series of abnormal changes in the patient's body. For example, various symptoms including cough, fever, headache, weakness and hemoptysis can be called clinical manifestations. Exemplarily, the questions to be asked in the logic tree can be matched according to the characteristics of each microorganism corresponding to the possible pathogenic bacteria to determine the questions to be asked corresponding to each target microorganism, and to inquire in a targeted manner. Further, for microorganisms with the same focus, the same question can be shared to achieve the effect of asking and answering them together. For example, when the microbial characteristics of bacteria A and B include a specific sequence number that is higher than a certain threshold, a unique conclusion can be drawn. Therefore, the question to be asked can be "What are the specific sequence numbers of bacteria A and B?", and the user's answer can be "Bacteria A is 100 and bacteria B is 100", and then the specific sequence numbers of bacteria A and B in the answer are extracted as 100 respectively. In the logic tree, it can be obtained that "when bacteria A is 100, it is a definite pathogen, and when bacteria B is 100, it is a possible pathogen".

[0072] Exemplarily, when the above-mentioned question to be asked includes at least the test report information, it means that for the target microorganism, the test report information has a greater impact on its classification result and has a higher emphasis. Then, the target microorganism is classified according to the answer and the logical classification tree to determine the target classification information of the target microorganism, which may include steps A1-A2:

[0073] A1. Perform semantic analysis on the answer to extract target inspection report information corresponding to the target microorganism in the answer, wherein the target detection information includes one or more of the number of specific sequences, relative abundance and coverage;

[0074] A2. Classify the target microorganism according to the target inspection report information and the logical classification tree to determine the target classification information of the target microorganism.

[0075] It should be noted that when the question to be asked is about the test report information of the microorganism, the target test report information corresponding to the target microorganism in the answer can be extracted by semantic analysis of the answer. The target detection information includes one or more of the specific sequence number, relative abundance and coverage. Then, the classification rules corresponding to the extracted target test report information of the target microorganism are determined in the logical classification tree to obtain the target classification information of the target microorganism. For example, after analyzing the test report information, the target microorganism changes from a possible pathogen to a pathogen, from a possible pathogen to a background bacteria, or is still a possible pathogen.

[0076] Exemplarily, when the question to be asked at least includes clinical examination information, classifying the target microorganism according to the answer and the logical classification tree to determine the target classification information of the target microorganism may include steps B1-B2:

[0077] B1. Performing semantic analysis on the answer to extract target clinical examination information from the answer, wherein the target clinical examination information includes at least one or more examination information of clinical physical examination items, instrument physical examination items or laboratory physical examination items;

[0078] B2. Classify the target microorganism according to the target clinical examination information and the logical classification tree to determine target classification information of the target microorganism.

[0079] It should be noted that by asking the test items corresponding to the target microorganism, the target clinical examination information corresponding to the clinical examination items is extracted from the answers, and then the classification rules corresponding to the extracted target clinical examination information of the target microorganism are determined in the logical classification tree to obtain the target classification information of the target microorganism. For example, after analyzing the clinical examination information, the target microorganism changes from a possible pathogen to a pathogen, from a possible pathogen to a background bacteria, or remains a possible pathogen.

[0080] Exemplarily, when the question to be asked at least includes the source of infection, the step of classifying the target microorganism according to the answer and the logical classification tree to determine the target classification information of the target microorganism may include steps C1-C2:

[0081] C1. Performing semantic analysis on the answer to extract the target infection source corresponding to the target microorganism in the answer, wherein the target infection source includes at least nosocomial infection or community infection;

[0082] C2. Classify the target microorganism according to the target infection source and the logical classification tree to determine target classification information of the target microorganism.

[0083] It should be noted that the classification of some microorganisms also takes into account the source of infection. When the source of infection is included in the question to be asked, the answer can be semantically analyzed to extract the target source of infection corresponding to the target microorganism in the answer, which at least includes hospital infection or community infection. Then, the classification rules corresponding to the target source of infection of the target microorganism are determined in the logical classification tree to classify the microorganism and determine the target classification information of the target microorganism. For example, after analyzing the source of infection, the target microorganism changes from a possible pathogen to a pathogen, from a possible pathogen to a background bacteria, or it remains a possible pathogen.

[0084] Exemplarily, when the question to be asked at least includes clinical manifestations, the step of classifying the target microorganism according to the answer and the logical classification tree to determine the target classification information of the target microorganism may include steps D1-D2:

[0085] D1. performing semantic analysis on the answer to extract target clinical manifestations in the answer, where the target clinical manifestations include one or more abnormal changes occurring in the body;

[0086] D2. Classify the target microorganism according to the target clinical manifestation and the logical classification tree to determine target classification information of the target microorganism.

[0087] It should be noted that the classification of some microorganisms will focus on clinical manifestations. When the questions to be asked include clinical manifestations, the answers can be semantically analyzed to extract the target clinical manifestations corresponding to the target microorganisms in the answers, such as coughing, exertion, etc. Then, the classification rules corresponding to the target clinical manifestations of the target microorganisms are determined in the logical classification tree to classify the microorganisms and determine the target classification information of the target microorganisms. For example, after analyzing the clinical manifestations, the target microorganism changes from a possible pathogen to a pathogen, from a possible pathogen to a background bacteria, or it remains a possible pathogen.

[0088] 305. Determine a microbial classification result corresponding to each microorganism in the microbial information according to the microbial classification information and the target classification information, and return the microbial classification result to the client;

[0089] It should be noted that step 305 and Figure 1 The contents of step 105 are similar and will not be described here to avoid repetition. For details, please refer to the aforementioned contents of step 105.

[0090] 306. If the microbial classification result of the microorganism includes a microbial category of pathogenic bacteria, determining a first diagnosis and treatment recommendation for the microorganism corresponding to the pathogenic bacteria according to the microorganism corresponding to the pathogenic bacteria, the microbial classification result, and clinical information input by the user;

[0091] 307. If the microbial classification result of the microorganism includes a microbial category of possible pathogenic bacteria, then based on the microorganism corresponding to the possible pathogenic bacteria, the microbial classification result and the clinical information input by the user, determine the second diagnosis and treatment recommendation for the microorganism corresponding to the possible pathogenic bacteria, and the second diagnosis and treatment recommendation at least includes the pathogenicity probability of the microorganism corresponding to the possible pathogenic bacteria.

[0092] It should be noted that, in this embodiment, different from the monotonous explanation of terms on the conventional mNGS report, this embodiment will provide the classification results of all detected microorganisms and auxiliary diagnosis suggestions to the customers who submit the test, and also provide corresponding diagnosis and treatment suggestions. For various types of pathogenic microorganisms, the corresponding diagnosis and treatment suggestions are also configured in the form of a decision tree in the background after the auxiliary diagnosis suggestions, that is, they are set in the branch nodes of the logic tree. When the user obtains a certain input microorganism with a high probability of causing disease, the corresponding diagnosis and treatment suggestions for the microorganism will be returned to help clinicians prescribe the right medicine and symptomatic treatment. Among them, a first diagnosis and treatment suggestion will be given for the final confirmed pathogenic bacteria, and the first diagnosis and treatment suggestion is used to indicate how to treat or recommend a treatment plan for the caused disease. A second diagnosis and treatment suggestion will be given for the final possible pathogenic bacteria, and the second diagnosis and treatment suggestion is used to indicate how to treat or recommend a treatment plan for the possible disease, as well as the pathogenicity probability of the possible disease caused by the microorganism corresponding to the possible pathogenic bacteria. Please refer to Figure 4, which is a schematic diagram of a diagnosis and treatment suggestion in an embodiment of the present invention, wherein, Figure 4a is a schematic diagram of a first diagnosis and treatment suggestion in an embodiment of the present invention, Figure 4b Schematic diagram of a second diagnosis and treatment suggestion in an embodiment of the present invention, such as Figure 4a The first diagnosis and treatment recommendation shown is the diagnosis and treatment recommendation for the "definite pathogen" Streptococcus pneumoniae, and the auxiliary diagnosis recommendation is "Streptococcus pneumoniae is likely to be the pathogen, and community-acquired pneumonia is considered"; the diagnosis and treatment recommendations are "1. β-lactam antibiotics for Streptococcus pneumoniae infection give priority to penicillins or enzyme inhibitors such as amoxicillin / clavulanic acid, ceftriaxone, respiratory quinolones: moxifloxacin, levofloxacin; carbapenems may be weaker than the aforementioned drugs in improving the symptoms of Streptococcus pneumoniae infection. 2. Anti-pseudomonas β-lactams are not effective and should be avoided. 3. After the initial targeted treatment, if the efficacy has not improved, the first choice is to re-evaluate the complications of the pathogen (abscess, endocarditis), and then re-submit the specimens for examination to evaluate the possibility of other pathogens." For example Figure 4bThe second diagnosis and treatment recommendations shown are for the "possible pathogens" cytomegalovirus and Acinetobacter baumannii. Among them, the diagnosis and treatment recommendations for the "possible pathogens" cytomegalovirus include auxiliary diagnosis recommendations "The probability that cytomegalovirus is the pathogen is 90%. CMV is considered to be the main pathogen of infection, and other opportunistic pathogens may also be present."; Diagnosis and treatment recommendations "1. CMV disease is a common pathogen in patients with low immunity, especially after organ transplantation. When sufficient sequences (>100) are found in the blood test, more proviral treatment should be given. 2. CMV infection may affect multiple organs, and liver and colon lesions are easily overlooked.".

[0093] In a feasible implementation, the method may further include steps I, II, III and VI:

[0094] I. receiving feedback information of the user returned by the client, wherein the feedback information includes correct interpretation feedback or incorrect interpretation feedback;

[0095] It should be noted that users can provide feedback on the classification results obtained on the client. For example, if a doctor believes that the classification of a certain microorganism is incorrect, he can provide feedback. Therefore, the feedback information includes correct interpretation feedback or incorrect interpretation feedback.

[0096] II. Counting the correct interpretation feedback and the incorrect interpretation feedback to determine the interpretation accuracy rate;

[0097] Furthermore, the accuracy of the interpretation is obtained through user feedback. Specifically, the accuracy of the interpretation is determined by statistically analyzing the correct interpretation feedback and the incorrect interpretation feedback. Furthermore, data statistics can be performed for different microorganisms to calculate the accuracy of the interpretation of each microorganism one by one.

[0098] III. If the interpretation accuracy is less than a preset accuracy threshold, a correction prompt is output to the administrator backend, wherein the correction prompt is used to prompt the administrator to determine whether to update the classification rules of the logical classification tree according to the user's feedback information and the interpretation accuracy;

[0099] VI. If the interpretation accuracy is greater than or equal to a preset accuracy threshold, determine not to update the logical classification tree.

[0100] Exemplarily, the interpretation accuracy can be used to determine whether to update the classification rules of the logical classification tree. Specifically, if the interpretation accuracy is less than the preset accuracy threshold, a correction prompt is output to the administrator background. The correction prompt is used to prompt the administrator to determine whether to update the classification rules of the logical classification tree based on the user's feedback information and the interpretation accuracy; if the interpretation accuracy is greater than or equal to the preset accuracy threshold, it is determined not to update the logical classification tree. Furthermore, the correction prompt includes the microbial information to be updated corresponding to the interpretation error feedback, and the corresponding classification rules are updated through the microbial information to be updated. Before updating, the administrator can make a judgment on the user's feedback based on professional knowledge, and will only update if the feedback content is true and correct. Otherwise, it will not be updated.

[0101] Through two-way feedback between users and results (scoring and providing feedback on diagnostic and treatment recommendations), the interaction between clinical doctors and sequencing companies is strengthened, which is conducive to the precision of clinical diagnosis and treatment and helps to calibrate and optimize project results. That is, the system records all user usage records, including each input and system output of auxiliary diagnostic results, as well as their satisfaction and feedback on each result, so that administrators can monitor the use of the system, continuously improve the system's knowledge logic library, and enrich the knowledge of microorganisms and pathogenic types covered by the system. Please refer to Figure 5 , Figure 5 is a schematic diagram of a user feedback interface in an embodiment of the present invention, Figure 5 The user feedback shown includes feedback on the rating of the classification results, additional feedback for adding detected microorganisms, and other feedback.

[0102] Through evidence-based medicine, we organically combine expert experience, effective patient clinical information, and big data models, and continuously revise expert experience and model indicators through a large number of actual case results, so that the classification interpretation system can achieve higher accuracy. We combine the logical experience of clinical experts in interpreting countless macrogene reports in combination with microbial characteristics and clinical data to realize an intelligent microbial diagnosis model - logical classification tree (rule configuration and diagnosis matching). The interpretation is fast and accurate, and it only takes a few minutes to get a preliminary conclusion or diagnosis and treatment recommendation.

[0103] It should be noted that, from the technical principle of mNGS, the data filtering of bioinformatics technology and the construction of various databases cannot solve the problem of simultaneous detection of multiple pathogens in most cases, that is, it is impossible to distinguish the real pathogens in the report; furthermore, whether it is the technical optimization of wet experiments or dry experiments, it is impossible to provide clinical customers with diagnosis and treatment suggestions. At present, the accuracy of the interpretation of mNGS reports still depends more on the doctor's experience and takes a long time: the reasons why clinicians have difficulty interpreting mNGS reports and cannot judge the "real pathogens" are as follows: ① mNGS detection has high sensitivity and large amount of information; ② There is no unified standard for the interpretation of each parameter in the test report; ③ I do not understand the characteristics of microorganisms colonizing in various parts of the human body; ④ It is difficult to obtain the necessary clinical information required for the interpretation of the macrogene report; ⑤ Clinicians, especially grassroots doctors, are not able to comprehensively interpret the macrogene test report and necessary clinical information. Through the solution of this embodiment, the above problems can be solved one by one.

[0104] The embodiment of the present invention discloses a method for interpreting microbial information, through which: (1) the first intelligent analysis method established for the interpretation of mNGS reports in the country is realized, and a more accurate analysis of the report results after filtering based on bioinformatics analysis is realized, which assists in improving the report interpretation ability of grassroots doctors, maximizes the clinical value of macro-gene detection, and helps patients with accurate diagnosis and effective treatment. (2) This method is based on the judgment experience of clinical experts, microbial characteristics and effective patient clinical information, and has developed an efficient pathogen classification model (logical classification tree), and can analyze and judge multiple microorganisms at the same time, assisting doctors to quickly identify possible pathogens, which is convenient and fast. Compared with the common filtering of background bacteria only, this method also screens certain pathogenic microorganisms in certain specimen types based on the experience of clinical authoritative experts, and the rest are classified as possible pathogens, and combined with more clinical information to further confirm the diagnosis. The classification rules of pathogens in the present invention are simpler and clearer: the classification of positive pathogens is based on the years of experience and specialist consensus of clinical experts; the classification of background bacteria, in addition to reference materials such as professional guide literature manuals, also combines the background bacteria library screened out by statistical analysis of the actual results of metagenomic testing accumulated by the testing agency itself for many years; and when classifying, it fully considers that the pathogenicity of the same pathogen detected in different specimen types is different, and accurate classification will be performed in combination with the specimen type. (3) Compared with other similar intelligent interpretation methods, the present invention has a more flexible custom configuration judgment logic function, and the custom configuration framework is customized based on the diagnosis and treatment path of pathogenic microorganism metagenomic detection. It has both a decision logic support system based on microbial species, specimen types and other specialty fields, and can flexibly configure the structure and content of the decision tree, so that the judgment logic path of auxiliary interpretation can be updated, modified or added at any time without repeated development. If there are microorganisms that are not covered by the method logic tree, the user's search records in the system can be monitored in real time, and then the judgment rule decision tree corresponding to the microorganism can be added in the background; for example, if the user is not satisfied with the suggestions of a certain auxiliary interpretation or the actual diagnosis result does not match the suggestion, the administrator can also modify the logic decision tree in the background through feedback. This flexible custom configuration framework can help the auxiliary decision system to continuously grow and update its interpretation knowledge base, cover the most clinical scenarios at the lowest cost, and continuously improve the clinical compliance of the interpretation, which is something that many interpretation systems with fixed logic cannot do. (4) Based on the flexibility of the system background logic that can be customized and configured as mentioned in (3), the invention is not only suitable for interpreting mNGS project reports, but can also be used in similar high-throughput projects related to pathogenic microorganisms, such as targeted sequencing of multiple pathogens, third-generation sequencing of microorganisms, etc. The same logic can be reused, and different logic can be added, which can cover the auxiliary clinical interpretation sequencing results of multiple scenarios.In addition, the judgment logic decision tree of each microorganism can also be connected to other systems through an interface, such as the system of the testing agency, which can connect the information registered by the user when submitting the test and the test result information, and directly give the final auxiliary diagnosis and treatment suggestions through the system logic judgment without repeated input, which is more convenient. (5) The present invention also has the system operation function of the management background, which can not only count the total number of existing microorganisms (microorganism library), clinical interaction problems (problem library), and rule decision trees (rule library) in the background and the distribution of related types, but also monitor and record the activity of front-end users and the most frequently queried microorganism types. It is convenient for the back-end administrator to update and improve the system's knowledge logic library at any time according to the actual use of the system, continuously cover more and more complex clinical scenarios and cases, and truly help doctors to treat diseases. In addition, the system is also equipped with complete back-end permissions, logs, dictionary management and other functions, which can provide a complete set of system solutions for pathogenic microorganism metagenome auxiliary decision-making, including system operation and maintenance, so as to continuously output rich and high-quality intelligent interpretation opinions, unlike most auxiliary interpretation systems that remain unchanged or require frequent releases for updating.

[0105] See also Figure 6 , Figure 6 FIG. 1 is a structural block diagram of a device for interpreting microbial information in an embodiment of the present invention. Figure 6 The device shown comprises:

[0106] Information acquisition module 601: used to acquire microbial information and specimen information input by the user on the client;

[0107] The first classification module 602 is used to determine the microbial classification information in the microbial information by using a preset logical classification tree, the microbial information and the specimen information, wherein the microbial classification information includes the corresponding relationship between each microorganism in the microbial information and the microbial category, the microbial category includes pathogenic bacteria, possible pathogenic bacteria or background bacteria, and the logical classification tree includes a number of classification rules constructed based on expert knowledge and clinical experience;

[0108] Question consultation module 603: for determining the question to be asked corresponding to the target microorganism in the logic classification tree according to the target microorganism corresponding to the possible pathogenic bacteria if the microorganism classification information includes possible pathogenic bacteria, and returning the question to be asked to the client;

[0109] The second classification module 604 is used to receive the answer given by the user based on the question to be asked and returned by the client, and classify the target microorganism according to the answer and the logical classification tree to determine the target classification information of the target microorganism;

[0110] The classification determination module 605 is used to determine the microorganism classification result corresponding to each microorganism in the microorganism information according to the microorganism classification information and the target classification information, and return the microorganism classification result to the client.

[0111] It should be noted that Figure 6 The functions of each module in the device shown are Figure 1 The steps in the method shown are similar in content, and are not described here in detail to avoid repetition. Figure 1 The content of each step in the method shown.

[0112] The present invention provides a device for interpreting microbial information, which includes: an information acquisition module: used to acquire microbial information and specimen information input by a user on a client; a first classification module: used to determine microbial classification information in the microbial information by using a preset logical classification tree, microbial information and specimen information, wherein the microbial classification information includes a corresponding relationship between each microorganism in the microbial information and a microbial category, wherein the microbial category includes pathogenic bacteria, possible pathogenic bacteria or background bacteria, and the logical classification tree includes a number of classification rules constructed based on expert knowledge and clinical experience; a question consultation module: used to determine a question to be asked corresponding to the target microorganism in the logical classification tree according to the target microorganism corresponding to the possible pathogenic bacteria if the microbial classification information includes possible pathogenic bacteria, and return the question to be asked to the client; a second classification module: used to receive an answer made by the user based on the question to be asked returned by the client, and classify the target microorganism according to the answer and the logical classification tree to determine the target classification information of the target microorganism; a classification determination module: used to determine the microbial classification result corresponding to each microorganism in the microbial information according to the microbial classification information and the target classification information, and return the microbial classification result to the client. Through the above-mentioned device, after the preliminary classification of microorganisms using specimens, further classification of questions to be asked obtained from classification rules constructed based on clinical experience for possible pathogens can be achieved, thereby improving the accuracy of classification of microorganisms corresponding to possible pathogens. This can assist in improving the report interpretation ability of primary care doctors, maximize the clinical value of high-throughput projects for pathogenic microorganisms, and assist in accurate diagnosis and effective treatment of patients.

[0113] Figure 7 FIG. 1 shows an internal structure diagram of a computer device in an embodiment. The computer device may be a client or a server. Figure 7As shown, the computer device includes a processor, a memory and a network interface connected via a system bus. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor can implement the above method. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor can implement the above method. Those skilled in the art can understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0114] In one embodiment, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following steps: Figure 1 or Figure 3 The steps of the method are shown.

[0115] In one embodiment, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the processor performs the following steps: Figure 1 or Figure 3 The steps of the method are shown.

[0116] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0117] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0118] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for interpreting microbial information, characterized in that: The method comprises: Obtain the microbial information and specimen information entered by the user on the client; Using a preset logical classification tree, the microorganism information and the specimen information, determining microorganism classification information in the microorganism information, wherein the microorganism classification information includes a correspondence between each microorganism in the microorganism information and a microorganism category, wherein the microorganism category includes pathogenic bacteria, possible pathogenic bacteria or background bacteria, and the logical classification tree includes a number of classification rules constructed based on expert knowledge and clinical experience; If the microorganism classification information includes possible pathogenic bacteria, determining the question to be asked corresponding to the target microorganism in the logical classification tree according to the target microorganism corresponding to the possible pathogenic bacteria, and returning the question to be asked to the client; receiving the answer given by the user based on the question to be asked and returned by the client, and classifying the target microorganism according to the answer and the logical classification tree to determine the target classification information of the target microorganism; Determine, according to the microbial classification information and the target classification information, a microbial classification result corresponding to each microorganism in the microbial information, and return the microbial classification result to the client; Wherein, the method further comprises: If the microbial classification result of the microorganism includes a microbial category of pathogenic bacteria, determining a first diagnosis and treatment recommendation for the microorganism corresponding to the pathogenic bacteria according to the microorganism corresponding to the pathogenic bacteria, the microbial classification result, and clinical information input by the user; If the microbial classification result of the microorganism includes a microbial category of possible pathogenic bacteria, then according to the microorganism corresponding to the possible pathogenic bacteria, the microbial classification result and the clinical information input by the user, a second diagnosis and treatment suggestion for the microorganism corresponding to the possible pathogenic bacteria is determined, and the second diagnosis and treatment suggestion at least includes the pathogenicity probability of the microorganism corresponding to the possible pathogenic bacteria; Wherein, the method further comprises: Receiving feedback information of the user returned by the client, wherein the feedback information includes correct interpretation feedback or incorrect interpretation feedback; Performing data statistics on the correct interpretation feedback and the incorrect interpretation feedback to determine the interpretation accuracy rate; If the interpretation accuracy is less than a preset accuracy threshold, a correction prompt is output to the administrator backend, wherein the correction prompt is used to prompt the administrator to determine whether to update the classification rules of the logical classification tree according to the user's feedback information and the interpretation accuracy; If the interpretation accuracy is greater than or equal to a preset accuracy threshold, it is determined not to update the logical classification tree.

2. The method according to claim 1, characterized in that: The question to be asked at least includes test report information, and the target microorganism is classified according to the answer and the logical classification tree to determine the target classification information of the target microorganism, including: Performing semantic analysis on the answer, extracting target inspection report information corresponding to the target microorganism in the answer, wherein the target detection information includes one or more of the number of specific sequences, relative abundance and coverage; The target microorganism is classified according to the target inspection report information and the logical classification tree to determine the target classification information of the target microorganism.

3. The method according to claim 1, characterized in that: The question to be asked at least includes clinical examination information, and the step of classifying the target microorganism according to the answer and the logical classification tree to determine the target classification information of the target microorganism includes: Performing semantic analysis on the answer to extract target clinical examination information in the answer, wherein the target clinical examination information at least includes examination information of one or more of clinical physical examination items, instrument physical examination items or laboratory physical examination items; The target microorganism is classified according to the target clinical examination information and the logical classification tree to determine target classification information of the target microorganism.

4. The method according to claim 1, characterized in that: The question to be asked at least includes the source of infection, and the target microorganism is classified according to the answer and the logical classification tree to determine the target classification information of the target microorganism, including: Performing semantic analysis on the answer to extract the target infection source corresponding to the target microorganism in the answer, wherein the target infection source includes at least nosocomial infection or community infection; The target microorganism is classified according to the target infection source and the logical classification tree to determine target classification information of the target microorganism.

5. The method according to claim 1, characterized in that: The question to be asked at least includes clinical manifestations, and the target microorganism is classified according to the answer and the logical classification tree to determine the target classification information of the target microorganism, including: Performing semantic analysis on the answer to extract target clinical manifestations in the answer, wherein the target clinical manifestations include one or more abnormal changes occurring in the body; The target microorganism is classified according to the target clinical manifestation and the logical classification tree to determine target classification information of the target microorganism.

6. A device for interpreting microbial information, characterized in that: The device comprises: Information acquisition module: used to obtain the microbial information and specimen information entered by the user on the client; The first classification module is used to determine the microbial classification information in the microbial information by using a preset logical classification tree, the microbial information and the specimen information, wherein the microbial classification information includes the corresponding relationship between each microorganism in the microbial information and the microbial category, the microbial category includes pathogenic bacteria, possible pathogenic bacteria or background bacteria, and the logical classification tree includes a number of classification rules constructed based on expert knowledge and clinical experience; Question consultation module: for determining the question to be asked corresponding to the target microorganism in the logic classification tree according to the target microorganism corresponding to the possible pathogenic bacteria if the microorganism classification information includes possible pathogenic bacteria, and returning the question to be asked to the client; A second classification module is used for receiving the answer given by the user based on the question to be asked and returned by the client, and classifying the target microorganism according to the answer and the logical classification tree to determine the target classification information of the target microorganism; Classification determination module: used to determine the microbial classification result corresponding to each microorganism in the microbial information according to the microbial classification information and the target classification information, and return the microbial classification result to the client; Wherein, the device is also used for: If the microbial classification result of the microorganism includes a microbial category of pathogenic bacteria, a first diagnosis and treatment suggestion for the microorganism corresponding to the pathogenic bacteria is determined according to the microorganism corresponding to the pathogenic bacteria, the microbial classification result, and the clinical information input by the user; if the microbial classification result of the microorganism includes a microbial category of possible pathogenic bacteria, a second diagnosis and treatment suggestion for the microorganism corresponding to the possible pathogenic bacteria is determined according to the microorganism corresponding to the possible pathogenic bacteria, the microbial classification result, and the clinical information input by the user, and the second diagnosis and treatment suggestion at least includes the pathogenicity probability of the microorganism corresponding to the possible pathogenic bacteria; Wherein, the device is also used for: Receive feedback information of the user returned by the client, the feedback information including correct interpretation feedback or incorrect interpretation feedback; perform data statistics on the correct interpretation feedback and the incorrect interpretation feedback to determine the interpretation accuracy; if the interpretation accuracy is less than a preset accuracy threshold, output a correction prompt to the administrator background, the correction prompt is used to prompt the administrator to determine whether to update the classification rules of the logical classification tree according to the user's feedback information and the interpretation accuracy; if the interpretation accuracy is greater than or equal to the preset accuracy threshold, determine not to update the logical classification tree.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 5.

8. A computer device comprising a memory and a processor, characterized in that: The memory stores a computer program, and when the computer program is executed by the processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 5.

Images