86 results about "Tuberculosis" patented technology

The invention discloses a diagnosis method for predicting tuberculosis risk by using blood routine indexes, which comprises the following steps: (1) collecting open-source blood routine data, preprocessing, and dividing into a training set, a test set and a verification set; (2) screening blood routine examination and 25 indexes derived from the blood routine examination, and obtaining a preliminary screening result through LASSO regression analysis; (3) inputting the preliminary screening result into seven machine learning models, including a logistic regression model, a random forest model, a naive Bayes model, a K proximity model, a support vector machine model, an XGBoost model and a GBM model, for analysis to obtain a final variable combination and an optimal model; (4) inputting the verification set into the optimal model to obtain a DCA decision curve and a calibration curve; early discovery and precise diagnosis and treatment of tuberculosis are promoted, and meanwhile the pressure of medical resources is effectively relieved.

The invention provides a tuberculosis early screening method based on deep learning, and belongs to the technical field of tuberculosis screening. The method comprises the following steps: collecting multi-modal medical image data, RNA sequencing data, electronic medical record text data and clinical examination data of a tuberculosis patient, preprocessing the data, and extracting characteristics of each modal data; and by using an IRENE model, the extracted features are fused through a bidirectional multi-modal attention mechanism, and overall characterization is learned. And based on the fusion features, adopting a federal learning technology to train an ensemble learning classification model, and outputting a screening result. A decision support model based on reinforcement learning is further constructed, a decision strategy is optimized in combination with a screening result, electronic medical record text data, clinical examination data and historical diagnosis and treatment information, and finally a binary classification result for judging whether the patient suffers from tuberculosis or not is given. According to the method, multi-modal data are integrated, the advantages of deep learning in the aspects of feature extraction and fusion are fully played, and early screening of tuberculosis is realized.

The invention belongs to the technical field of medical equipment, and particularly relates to a portable tuberculosis drug aerosol inhalation device. The device comprises a medicine storage chamber, an outflow channel and a controller, the top of the medicine storage chamber is provided with a medicine tank groove with a conical pricking pipe, and one-step medicine filling through placing and pressing can be achieved; the respiratory rhythm of a user is identified through lip contact and a respiratory airflow sensor, and the atomizer is synchronously controlled to start and stop; the system has the functions of liquid medicine identity recognition, heating temperature control and self-adaptive power adjustment based on liquid medicine storage, efficient, safe and comfortable tuberculosis medicine inhalation treatment is achieved, and the medication compliance and the treatment effect are remarkably improved.

The invention relates to a method for detecting six second-line antituberculous drugs by high performance liquid chromatography. The method comprises the following steps: providing an internal standard stock solution and a standard stock solution of six second-line antituberculosis drugs; preparing an internal standard working solution and a standard curve working solution by utilizing the diluent; preparing a solution of a product to be detected by using the Tianlongitudinal sample extraction liquid TZ-002; a liquid chromatograph is used for detection, and the conditions are as follows: a mobile phase A is a Tianlongitudinal sample releasing agent TZ-D004; a mobile phase B is acetonitrile; a mobile phase C is water; and gradient elution. According to the method, the plasma concentration of the second-line antituberculous drug taken by a tuberculosis patient is measured by applying the reversed-phase high-performance liquid chromatography, the cost is relatively low, the analysis time is short, the sensitivity is high, and the accuracy is high. The kit can be used for simultaneously detecting the blood concentration of six second-line antituberculosis drugs such as isopropylthioamide, levofloxacin, linezolid, moxifloxacin, deramanib and bedaquiline in human serum, and is expected to provide a more reliable basis for clinicians to adjust the dosage of the antituberculosis drugs.

The invention belongs to the technical field of biology, and particularly relates to a group of markers for diagnosing active tuberculosis and application. The biomarker is easy and convenient to sample, only peripheral blood needs to be taken for detection, and the result reporting speed is high. The biomarker disclosed by the invention is high in accuracy: when a subject's working characteristic curve (ROC) analysis shows that when GCH1, GK, MTHFD2 and SLC7A6 are combined, it can be known through database screening that the ROC for diagnosing active tuberculosis patients in TB patients, HC control and LTBI patients is 0.906, the specificity is 93.9, and the sensitivity is 85.7; clinical tests prove that the ROC of active tuberculosis patients in TB patients, HC control and LTBI patients is 0.942, the specificity is 90.9, and the sensitivity is 85.7.

The invention relates to the technical field of medical artificial intelligence and public health data management crossing, in particular to an intelligent tuberculosis screening and data analysis management system which comprises a data acquisition module, an intelligent screening module, a data analysis management module, a clinical interaction module and a system management module. The multi-source data fusion and the dynamic threshold reasoning enable the early-stage tiny focus detection rate to be larger than or equal to 85%, the screening time is shortened to 5 minutes per case (80% higher than that of manual film reading), cross-mechanism and cross-dimension data integrated acquisition and sharing are achieved, 'hospital-disease control-grassroots' data intercommunication is achieved, and the screening efficiency is improved. Complete data support is provided for epidemiological analysis, longitudinal individual tracking and transverse group analysis are combined, the early warning period of regional outbreak is larger than or equal to 2 weeks, and a public health prevention and control gateway is assisted to move forwards.

The present invention provides a kit for detecting tuberculosis antibodies. The kit includes a sample diluent, an enzyme conjugate reagent, a chromogenic substrate reagent, a concentrated washing solution reagent, and a detection cassette. The detection cassette includes a sampler and a reaction part. A reaction chamber is provided in the reaction part, a test strip is provided in the reaction chamber, and a quality control area and a detection area are provided on the test strip. A liquid inlet is provided on one side of the reaction chamber, and a liquid outlet is provided on the side of the reaction chamber away from the liquid inlet; a second liquid inlet is provided at the top of the sampler, and a second liquid outlet is provided on the side wall at the bottom of the sampler. The second liquid outlet matches the size of the liquid inlet. The sampler and the reaction part are connected by plugging to make the second liquid outlet communicate with the liquid inlet. By setting the detection cassette as a sampler and a reaction part, the sampling and the reaction are spatially isolated. The sampling is simple and easy to operate. Whether it is the sampling or the reaction stage, the solution is in a closed space, which can effectively prevent the phenomenon that the solution is contaminated by the outside world and causes inaccurate detection.

The invention provides a tuberculosis prediction method and system based on multi-disease association dynamic fusion, and relates to the technical field of data processing, and the method comprises the steps: obtaining multi-source disease data which comprises tuberculosis data and associated disease data; preprocessing the multi-source disease data to obtain a data set; dividing the data set into a training set and a verification set; using the training set to train a plurality of prediction models; calculating performance indexes of the plurality of prediction models by using the verification set; calculating dynamic weights of the plurality of prediction models based on the performance indexes; and performing weighted fusion on the prediction results of the plurality of prediction models by using the dynamic weight to obtain a fused prediction result. According to the invention, by fusing the associated disease data, a multi-model dynamic fusion prediction system is constructed, the tuberculosis prediction precision is significantly improved, the method has strong robustness, multi-scene adaptability and visual decision support capability, and accurate prevention and control of public health are effectively assisted.

In some aspects, a system is disclosed for detecting genetic targets for diagnosing tuberculosis and associated antibiotic resistance. The system includes a mechanical instrument and a cartridge assembly. The cartridge assembly comprises one or more reservoirs, with at least one reservoir containing a wet reagent. The cartridge also includes a chip with a fluidic channel holding a liquid slug. The chip has an optical detection region positioned between a heating region and a cool region. The mechanical instrument controls the back and forth motion of the liquid slug between the heating and cool regions. Additionally, the cartridge assembly includes one or more puncture elements configured to pierce the reservoirs and provide the wet reagent to the chip. The system further includes an optical detection unit with an optical light-emitting element, an optical detector, and a processing unit for analyzing the optical detection region of the chip.

The invention relates to the technical field of medical instruments, in particular to a tuberculosis ward atomization respirator with a negative pressure collection function, comprising: a mask assembly, the mask assembly comprises a breathing mask and a sealing strip, and the breathing mask is internally provided with an air pressure sensor for identifying air pressure change; the atomization assembly is connected with the mask assembly and used for intermittently conveying atomized medicine into the breathing mask. During expiration, the airflow adjusting assembly does not hinder the gas flow rate of the gas feeding pipe, the gas flow rate is increased, and a low-pressure area is formed at the position of the pressure-adjustable one-way valve assembly, so that the pressure-adjustable one-way valve assembly does not hinder communication of the exhaust pipe and the negative-pressure pipe; the exhaust gas in the breathing mask is exhausted outwards through the exhaust pipe and the negative pressure pipe, the airflow adjusting assembly reduces the gas flow rate of the gas feeding pipe at the end of expiration, negative pressure collection is not conducted on the gas in the breathing mask at the end of expiration any more, namely positive pressure is provided at the end of expiration, and early closure of pulmonary alveoli is avoided.

The invention discloses a tuberculosis patient treatment effect dynamic monitoring system and evaluation method, the system comprises a data acquisition module, a data transmission module, a data storage module, a data preprocessing module, a dynamic monitoring analysis module and a user interaction module, can acquire multi-dimensional data such as physiological indexes, images, symptoms, medication compliance and the like, and carries out encryption transmission, structured storage and preprocessing on the multi-dimensional data; and analyzing and generating a dynamic change curve and early warning information through a machine learning model. The evaluation method comprises the steps of collecting multi-stage data, encrypting, transmitting and storing, preprocessing the data, calculating dynamic scores and trends by a model, generating an evaluation report, and regularly optimizing the model. According to the scheme, the problems of traditional monitoring data fragmentation, evaluation experience and the like are solved, the treatment effect and medication compliance can be improved, medical resource allocation is optimized, data support is provided for scientific research, and the method is suitable for whole-cycle treatment monitoring and evaluation of tuberculosis patients.

The invention discloses a five-wing flat-top nine-tooth anti-tuberculosis drill bit, comprising a drill bit base, a base connecting part, a drill bit body connecting part and drill bit teeth, wherein the drill bit teeth are divided into an external cutting group and an internal cutting group; the drill bit teeth of the external cutting group are symmetrically arranged into five, namely a first cutting head, a second cutting head, a third cutting head, a fourth cutting head and a fifth cutting head, and a drill bit body connecting part is arranged between the drill bit teeth and the base connecting part; the drill bit teeth of the internal cutting group are embedded in the drill bit base, and the drill bit teeth of the internal cutting group include four drill bit teeth, namely a sixth cutting head, a seventh cutting head, an eighth cutting head and a ninth cutting head; the problem that when mining a high-gas mine, the rock hardness is high, the drill bit is severely worn and it is difficult to drill during the drilling process is solved.

The present invention discloses the use of an inhibitor targeting T-cell TIGIT in the preparation of an anti-tuberculosis drug. The inhibitor includes ociperlimab, AGEN1777, tiragolumab, etc. The present invention blocks TIGIT on the surface of T cells, promoting the ability of T cells to clear intracellular bacteria in macrophages by upregulating MPEG1, thereby achieving control of tuberculosis proliferation and providing evidence for the development of anti-tuberculosis drugs.

The invention belongs to the technical field of medicine application, discloses application of paeoniflorin in preparation of medicine for treating nodular sclerosis, and particularly discloses application of paeoniflorin or pharmaceutically acceptable salt thereof in preparation of medicine for treating and / or preventing hereditary intelligence and cognitive dysfunction diseases. The new medicinal value of the known compound paeoniflorin is explored, the paeoniflorin is used for treating the hereditary intellectual and cognitive impairment diseases (such as nodular sclerosis) and can be prepared into the medicine for treating the hereditary intellectual and cognitive impairment diseases, and a new application field is developed for application of radix paeoniae alba and radix paeoniae rubra medicinal materials.

Provided are: a biomarker whereby useful information about the presence / absence of infection can be provided in a short time using urine, which is easily collected, as a specimen sample; a method for screening a tuberculosis infection sample using said marker; and a probe kit that can be used in said screening. In the present invention, miRNA included in urine collected from an active tuberculosis patient and a healthy person is comprehensively detected and analyzed, and on the basis of the result of searching for miRNA that is specifically over- / under-expressed depending on the presence or absence of tuberculosis infection, miRNA expressed at a high frequency relative to that of a healthy person (SEQ ID NO: 1-25 and 45-55) and miRNA expressed at a low frequency relative to that of a healthy person (SEQ ID NO: 26-45 and 56-75) are specified as biomarkers. Nucleotides that can hybridize with these biomarkers are used as probes.

The invention discloses a tuberculosis data management control system based on an AI disease simulation model, and relates to the technical field of medical data management and control. The system comprises the following components: a data acquisition module, a multi-omics data integration and analysis module, a diagnostic reagent research, development and optimization module, a clinical test simulation module, a personalized path generation module and a data management center. Multi-omics data of genomics, proteomics, metabonomics and the like are deeply integrated through an AI algorithm, target molecules closely related to tuberculosis specificity are accurately recognized, a core basis is provided for research and development of diagnostic reagents, personalized optimization is performed according to individual data of patients, and the diagnosis accuracy is improved. In addition, through the clinical test simulation module, the detection difference of the reagent in different people can be predicted, and factors possibly influencing the test result are informed in advance, so that a more feasible clinical test scheme is generated.

The present application relates to the technical field of chromatographic analysis detection, in particular to a gynecological tuberculosis endocrine disorder typing system based on chromatography-mass spectrometry. The system comprises a memory and a processor, and the processor executes a computer program stored in the memory to realize the following steps: evaluating the compound identification accuracy according to the number of compounds in different reference samples in each specimen source, determining the sample weight of each specimen source in combination with the ideal effect of the specimen source and the proportion of the number of reference samples; evaluating the mixed similarity in combination with the retention time and response intensity of the compounds in the chromatographic data segment in each compound set; obtaining the correction weight by comprehensively considering the number of compounds, the mixed similarity and the sample weight of each compound set in each reference sample, and further determining the gynecological tuberculosis endocrine disorder typing. The present application overcomes the identification deviation problem caused by insufficient reference samples and similar compound structures, and improves the accuracy of gynecological tuberculosis endocrine disorder typing.

The invention discloses a composite milk adjuvant, a preparation method and application of the composite milk adjuvant in vaccines, and belongs to the technical field of medicines. The technical problems to be solved are relatively weak cell immunocompetence, relatively poor immunogenicity and relatively weak immunoregulation capability. According to the technical scheme, squalene, polyoxyethylated castor oil 35 and poloxamer 407 are used as raw materials to prepare a basic formula of the milk adjuvant, an immunologic stimulant is added on the basis to prepare the composite milk adjuvant, and the physicochemical properties and safety of the composite milk adjuvant are represented. The synergistic effect of the milk adjuvant on humoral immunity and cellular immunity is further evaluated by being matched with a recombinant tuberculosis antigen Ag85B to immunize mice, and data support is provided for application of the milk adjuvant in development of novel vaccines such as tuberculosis vaccines and the like. The composite milk adjuvant prepared by the invention not only keeps good humoral immunity and induces generation of high-level IgG1 and IgG2a, but also remarkably improves the response level of cellular immunity.

The invention relates to the technical field of tuberculosis vaccines, in particular to a tuberculosis VLP nanoparticle vaccine and preparation and application thereof. According to the tuberculosis VLP nanoparticle vaccine, through up-regulation of Th1 type, Th2 type and TH17 type cellular immune response and down-regulation of Treg cellular immune response, the H37Rv growth inhibition ability of splenic lymphocytes and lung cells in vitro is enhanced, and the cellular immune response induced by EPPE + mi3 / AS01E and the H37Rv growth inhibition ability of the cells in vitro are higher than those of BCG and a corresponding subunit vaccine EPPE / AS01E; in addition, the EPPE + mi3 / AS01E can be used as a BCG booster vaccine, and the cell immune response after BCG immunization and the H37Rv growth inhibition capacity of cells in vitro are improved.

This invention belongs to the field of vaccine technology, specifically relating to a method for effectively activating the body's immune system against tuberculosis infection by identifying candidate antigen epitopes for mRNA vaccines. The method comprises the following steps: screening for population-specific tuberculosis protective antigens based on reverse prediction from a TCR immune repertoire; constructing an mRNA vaccine containing these population-specific tuberculosis protective antigens and identifying the optimal antigen; and evaluating the in vivo immunogenicity, immunogenicity, and immunoprotective effects of the mRNA vaccine. This technical solution combines population-specific common HLA allele profiles with existing tuberculosis-specific TCR databases to target and predict broad-spectrum protective antigens recognized by TCRs shared under the major HLA backgrounds in the population. LNP-mRNA vaccine technology has been established as an ideal platform for delivering these newly discovered advantageous antigens.

The invention discloses a tuberculosis medication intelligent management medicine box which comprises a medicine box body, a front end body, a side expansion body and a rear end body, the front end body is provided with a medicine inlet, a bagged medicine decapsulation assembly and a medicine outlet hole, and the bagged medicine decapsulation assembly comprises a first pressure part, a second pressure part and a driving part; the side expansion body is provided with a first taking and placing opening, a medicament bottle uncovering assembly, a second taking and placing opening and a storage cavity. The rear end body is provided with a medicine taking connector, a medicine taking assembly and a guiding assembly. The device has the following advantages and effects that the four functions of bagged medicine decapsulation, medicine bottle uncapping, plate medicine storage and medicine particle bottle automatic medicine feeding are achieved, and the bagged medicine, the medicine bottle, the plate medicine and the medicine particle bottle which are common in the actual use process are effectively covered, so that integrated management of various medicine forms can be achieved; and the purpose of key operation automation can be achieved.

The invention belongs to the field of traditional Chinese medicine, and particularly relates to a traditional Chinese medicine composition and application thereof. Aiming at the pathogenesis that the spleen and stomach are damaged by antituberculous drugs, so that the spleen is disabled in transportation, damp turbidity is stopped, stomach is disharmonized and reduced, and cold and heat are mixed, the invention provides a traditional Chinese medicine composition consisting of nine medicines such as fresh ginger, ginger processed pinellia, roasted rhizoma atractylodis macrocephalae, rhizoma atractylodis, dried tangerine or orange peel and poria cocos. The traditional Chinese medicine composition disclosed by the invention has the advantages of few medicines, quick response, high safety and good curative effect, can be used for remarkably improving gastrointestinal reaction of a tuberculosis patient after chemotherapy by being combined with conventional treatment, has a clear synergistic effect and has a remarkable application advantage.

The invention relates to a thienopyridone compound, application thereof and an antituberculosis drug. The thienopyridone compound disclosed by the invention has a structure as shown in a formula (I), wherein-Ar1-(R1) n is a C6-C10 aromatic ring substituted by n R1 or a 4-10-membered heteroaromatic ring, n is selected from 0, 1, 2, 3 or 4, and n R1 is selected from C1-C6 alkyl, C1-C5 alkoxy, C3-C10 cycloalkyl, halogen, C1-C8 acyl, C1-C6 alkyl substituted by hydroxyl, C1-C6 alkyl substituted by halogen, nitro or cyano; -Ar2-(R2) n is a C6-C10 arylene ring substituted by n R2 or a 4-10-membered heteroaromatic ring, n is selected from 0, 1, 2, 3 or 4, and n R2 is respectively selected from C1-C6 alkyl, C1-C5 alkoxy, C3-C10 cycloalkyl, halogen or nitryl; and R3 is selected from the following groups: H or C1-C8 acyl groups. The thienopyridone compound has a novel mother nucleus structure and excellent anti-tubercle bacillus activity, and has a very strong inhibition effect on the growth of tubercle bacillus.

This invention belongs to the field of traditional Chinese medicine oral decoction preparation technology. Specifically, it relates to a method for preparing a stable and safe decoction of traditional Chinese medicine composition for hepatitis, jaundice virus, cirrhosis, and ascites. The decoction is prepared by decocting the following eleven traditional Chinese medicine components: 30g of raw Lysimachia christinae, 30g of Plantago asiatica, 30g of Poria cocos peel, 30g of Dioscorea opposita, 26g of Areca catechu peel, 16g of Salvia miltiorrhiza, 16g of Bupleurum chinense, 16g of Alisma plantago-aquatica, 16g of Astragalus membranaceus, 13g of Lycopus lucidus, and 10g of processed pangolin scales. When decocting, pour the mixture into a sterilized and cleaned porcelain medicine pot, add cold water and soak for 30 minutes. Bring to a boil over high heat, then simmer over low heat for 20 minutes. Turn off the heat and let it cool slightly before drinking. This is the medicine product. By combining classical traditional methods with modern decoction technology, the decoction of these eleven traditional Chinese medicines yields a traditional Chinese medicine preparation with significant effects and convenient administration. This formula features comprehensive regulation and enhancement. It selects herbs such as Lysimachia christinae, Plantago asiatica, Poria cocos, and Salvia miltiorrhiza, which have antibacterial, drainage, dampness-removing, anti-inflammatory, and blood-stasis-removing components for liver ascites. The combination of eleven Chinese herbs has anti-inflammatory, detoxifying, and dampness-removing effects, which are beneficial for treating liver ascites lesions, removing hepatitis, jaundice, tuberculosis, damp-heat accumulation, inflammation-induced ascites, enhancing immunity, and healing effects.

The present invention relates to the technical field of pollutant disinfection and treatment, and in particular to a device and system for treating pollutants in biomedical tuberculosis wards. The device comprises: a breathing mask, a system for treating pollutants in biomedical tuberculosis wards, an exhaled gas transmission pipeline, an ultraviolet disinfection chamber, a gas transmission pipeline, an atomization pipeline, a drug storage tank, a metering pump, an ultrasonic atomizer, a first plate-shaped gas guide plate, a plasma disinfection chamber, a second plate-shaped gas guide plate, a third plate-shaped gas guide plate, an exhaust port, a wavy gas guide plate, a wavy gas guide plate, a robotic arm, a drug delivery pipeline, a discharge electrode and an insulating medium, and a heating wire. The present invention improves the disinfection and treatment effects of tuberculosis and reduces the risk of infection.

The invention relates to an antigen construct for rapid immune detection, in particular to an antigen molecule for realizing dimerization or trimerization through foldon or a variant thereof. The antigen construct can enhance the conformation stability and improve the antibody binding efficiency, so that the sensitivity and shelf life stability in colloidal gold, fluorescent microspheres, ELISA (enzyme-linked immuno sorbent assay) and other in-vitro diagnosis methods in immunochromatography are remarkably improved. The construct is suitable for antibody detection of rabies, influenza, coronavirus, Brucella, tuberculosis and the like in zoonosis and HIV, HBV, HCV, syphilis and the like in human infectious diseases, and can be widely applied to clinical screening, animal quarantine, family self-test and public health emergency monitoring.

The application discloses a kind of composite water-soluble vaccine adjuvant and preparation method thereof, belong to biological medicine technical field.The adjuvant is based on the composite technology of water-soluble component and targeted delivery carrier, through the dual targeting effect of mannose modified beta-glucan, the uptake efficiency of dendritic cells to antigen is significantly improved, and the regulation of immune response is realized by synergistic levamisole.The adjuvant has the characteristics of uniform particle size, excellent water solubility, good storage stability, etc., and the immune enhancement effect is significantly better than traditional adjuvant, and can be widely used in the research and development of influenza, tuberculosis and tumor vaccines, has important clinical value and industrialization potential.

The invention relates to a critical tuberculosis intelligent auxiliary decision-making system and method based on multi-modal data, and the system comprises a data collection and preprocessing module which collects the multi-modal data of a patient, and carries out the standardization processing of the data; the multi-modal corpus construction module is used for converting the omics data into natural language description, constructing a corpus and realizing embedding alignment of omics and languages by adopting a comparative learning method; the multi-modal time sequence large model training module is used for carrying out model training by utilizing a Transform architecture and combining images, texts and omics data, introducing a time attention mechanism and carrying out dynamic modeling on multi-time-point data; the AI auxiliary decision-making system module is used for constructing a cross-modal attention mechanism and realizing data fusion; and the verification and optimization module is used for carrying out prospective verification, evaluating systematicness and optimizing model parameters and system functions in the multi-center hospital. According to the invention, by integrating clinical data, image data, omics data and the like, early warning, precise typing and individualized treatment recommendation of severe tuberculosis are realized.

The invention discloses a serology-based rapid diagnosis method for juvenile tuberculosis. The invention provides an economical and efficient method for diagnosing tuberculosis of teenagers. Based on serum proteomics of clinically active teenager tuberculosis patients, a rapid tuberculosis diagnosis method based on serology is found. According to the present invention, through a variety of machine learning algorithms, the combination of the three proteins such as the apolipoprotein A1 (Apolipoprotein A-I, APOA1), the hemoglobin subunit alpha (Hemoglobin subunit alpha-1, HBA1) and the hemoglobin subunit beta (Hemoglobin subunit beta, HBB) has the highest accuracy and the highest sensitivity in the teenager tuberculosis diagnosis process, such that the combination can be adopted as the serological diagnosis marker of the teenager tuberculosis; the invention provides a new method for rapid diagnosis of juvenile tuberculosis.

The invention discloses an application of plasma exosome miRNA (micro Ribonucleic Acid) in preparation of a product for screening and / or diagnosing tuberculosis. The miRNA is miR-19b-3p, miR-98-5p and / or miR-181b-5p. The detection reagent developed on the basis of the plasma miRNAs can specifically detect the expression levels of miR-19b-3p, miR-98-5p and / or miR-181b-5p in the plasma exosome of a subject, so that tuberculosis patients can be quickly and reliably recognized, the sensitivity and accuracy are high, and the detection reagent has high clinical application value and wide application prospects.