1540 results about "Treatment regimen" patented technology

The invention relates to the technical field of cardiovascular disease treatment, and discloses a cardiovascular disease medical decision support method based on a large model, and the method comprises the steps: obtaining multi-modal cardiovascular disease medical data, constructing a multi-source heterogeneous data set, carrying out the preprocessing and feature fusion, and constructing a combined representation model based on the pre-training large model and the fusion of traditional and western medicine knowledge. And designing a hierarchical space-time diagram convolutional network to generate a dynamic physiological state code of the patient, and constructing a multi-target optimization decision tree to generate a treatment scheme containing western medicines, traditional Chinese medicine prescriptions and non-drug intervention. A federal learning framework is adopted to cooperatively train a local model, data security is guaranteed, a global model is optimized, and a curative effect attribution module is further arranged to correct decision deviation. According to the method, multi-modal data and traditional Chinese and western medicine knowledge are integrated, personalized treatment scheme generation is achieved, data safety is guaranteed, and the cardiovascular disease diagnosis and treatment level is improved.

The invention discloses a heart failure treatment aid decision generation system based on multi-modal data fusion, and the system comprises a data collection module which is used for collecting the multi-modal data of a patient, and the multi-modal data comprises structured data, unstructured data and medical image data; the data processing module is used for carrying out standardization, quantization and vectorization processing on the multi-modal data; the knowledge graph construction module is used for constructing a knowledge graph of heart failure treatment, and the knowledge graph comprises a disease entity, a pathological feature, a treatment scheme and an association relationship thereof; the reasoning module is used for generating a personalized treatment decision based on the knowledge graph and the patient data; and the treatment scheme generation module is used for dynamically adjusting and outputting a personalized treatment scheme in combination with the real-time state data of the patient. The problems that multi-modal data are difficult to fuse and real-time disease change is difficult to dynamically adjust in heart failure diagnosis and treatment are solved, accurate diagnosis and personalized treatment are realized through knowledge graph reasoning and a dynamic correction mechanism, and the diagnosis and treatment efficiency and accuracy are remarkably improved.

The invention discloses a digital intelligent tumor prevention and treatment management platform and management method, and relates to the technical field of intelligent medical treatment, and the method comprises the steps: collecting the multi-modal data of a patient in real time, carrying out the standardized cleaning and space-time alignment processing, and generating a space-time tagging data set; inputting the multi-modal joint feature representation into an anti-fact inference engine, simulating potential effects under intervention of different treatment schemes, calculating individual processing effects, and generating an anti-fact rehabilitation suggestion set; according to the anti-fact rehabilitation suggestion set, a dynamic causal enhancement decision model is constructed, real-time physiological data feedback of the patient is continuously received through a near-end strategy optimization algorithm, and a treatment scheme is dynamically adjusted. According to the method, through multi-modal data space-time alignment and feature fusion, in combination with a tumor biological mechanism and a machine learning algorithm, the accuracy and clinical credibility of individualized tumor treatment scheme recommendation are remarkably improved.

The invention relates to a chronic heart failure dynamic course evolution prediction model construction method. Comprising the following steps: uniformly mapping continuous variables including LVEF and heart rate and event variables into a time trajectory frame through an event alignment and time domain nesting strategy; using a local change rate algorithm to identify inflection points including states before acute deterioration and intervention reactions in the course of disease of each patient; constructing a state fragment set for supporting hierarchical modeling in an evolution stage; a bidirectional fusion method of trajectory clustering and medical knowledge embedding is used to construct a state space with clinical interpretability including a compensation period, edge decompensation and an acute deterioration period; taking the trajectory vector as a main input, taking a state space as a prediction target, and introducing a dual-channel structure; predicting a future path based on the current state; the disease course track change of early medication / non-hospitalization / treatment scheme change is simulated; a doctor is supported to deduce a result; the change of the output state is analyzed through perturbation of the current trajectory, and key variables are found out.

The invention aims to provide an acne precise treatment and drug delivery system based on multi-modal data and feedback control. The system comprises an image acquisition and identification module, which carries out acne focus identification on an obtained skin image based on a deep learning algorithm, and extracts focus feature data; the sensor acquisition module is used for acquiring skin physiological parameters and environmental parameters related to acnes; the multi-modal fusion module carries out fusion processing on the focus characteristic data, the skin physiological parameters and the environmental parameters to generate current acne state parameters; the digital twinborn prediction module constructs a digital twinborn model of the patient according to the current acne state parameters and predicts the development trend of acnes; the individualized treatment decision module formulates an individualized treatment scheme and a corresponding administration dosage according to a prediction result of the digital twinning prediction module; and a set of system capable of realizing multi-source data acquisition, automatic evaluation, prediction analysis and personalized treatment scheme recommendation of the acne of the patient is constructed.

The invention relates to an auxiliary diagnosis and treatment method, device and equipment and a storage medium, and the method comprises the steps: verifying the quality of medical data through an intelligent matching mechanism, and generating a supplementary signal containing standardized guidance for unqualified image data in real time; a cross-modal fusion technology is adopted to integrate the tongue image, the pulse image, the image and the inspection data, and a comprehensive feature vector of a unified dimension is constructed; outputting correlation mapping of the traditional Chinese medicine syndromes and the western medicine diseases based on the pathological reasoning model, and generating a drug treatment scheme and a non-drug treatment scheme through a treatment scheme reasoning model; and finally, dynamically optimizing the dialectical logic parameters and the treatment weight parameters according to user feedback. The method solves the problems of difficulty in multi-source medical data fusion, one-sided diagnosis basis and lack of curative effect feedback closed loop, significantly improves the accuracy and adaptability of personalized diagnosis and treatment, and provides standardized intelligent support for traditional Chinese and western medicine combined diagnosis and treatment.

The invention discloses a tumor disease assessment method based on big data, and particularly relates to the technical field of tumor disease assessment. Medical data and living habit data of a patient are collected through multiple data interfaces, integration is carried out through preprocessing and a multi-modal data fusion technology, tumor microenvironment features and drug metabolism features are extracted, a comprehensive feature vector is generated, the effectiveness of a chemotherapy regimen is predicted by using a machine learning model, and when the effectiveness of the chemotherapy regimen is low, the chemotherapy regimen is identified. Newest clinical tests and drug data are introduced regularly, model parameters are dynamically optimized in combination with the chemotherapy regimen improvement effect, it is ensured that the model reflects the newest clinical progress in real time, the problems of model updating lag and drug innovation mismatching are effectively solved, the accuracy and effectiveness of a treatment regimen are improved, and the treatment cost is reduced. And meanwhile, side effects caused by blind attempts are reduced, and powerful support is provided for personalized precise medical treatment.

The invention discloses a CNN-Transform method based on multi-scale feature interaction, and mainly relates to the technical field of medical image analysis. Comprising the following steps: S1, acquiring sufficient amount of pancreas and tumor CT data, labeling the data, defining an ROI (Region of Interest), and distributing corresponding labels; s2, dividing the data set obtained in the step S1 into a training set and a test set, and preprocessing the training set and the test set by a data enhancement method including random rotation, scaling and mirroring; and S3, a CNN-Transform pancreas and tumor segmentation model PanUNet based on multi-scale feature interaction is constructed. Visual and accurate image information can be provided for doctors through accurate pancreas and tumor segmentation, personalized treatment schemes can be formulated in time, and the survival rate of patients is increased.

The invention belongs to the field of bioinformatics, and relates to an anti-cancer drug response prediction method based on an attention mechanism. The method comprises the following steps: firstly, capturing uniform-dimension drug and cancer cell line characteristics through a multi-layer perceptron; secondly, fusing drug characteristics by adopting a Transform encoder, and constructing a cell encoder for cancer cell line characteristic polymerization; then, designing a cross-modal cross fusion module to promote information interaction between the two; and finally, predicting a semi-suppressed concentration value subjected to logarithmic transformation between the two through a multi-layer perceptron. Experimental results show that compared with an existing optimal method, the method has the advantage that the RMSE is reduced by 2.9%. According to the method, accurate prediction of the anti-cancer drug response is achieved by integrating drug and cancer cell line data, screening of potential anti-cancer drugs can be accelerated, personalized treatment schemes can be optimized, the cure rate of cancer patients is further increased, and the method has great significance in cancer treatment.

The invention relates to the technical field of health risk assessment, in particular to an intelligent early warning system for postoperative infection risk of orthopedic trauma. The system comprises a data acquisition module for acquiring physiological feature data and biomarker data; the key monitoring and screening module screens key monitoring patients according to the continuous abnormal representation growth degree of the initial physiological signs; the infection risk assessment module obtains a marker level index by using the initial deviation level and the growth amplitude of the biomarker, and obtains a wound infection risk coefficient in combination with the prediction condition of historical biomarker data; and the early warning report generation module is used for dividing patient early warning levels according to the physiological parameter abnormality and the wound infection risk coefficient to generate a risk report. According to the method, the evaluation accuracy of postoperative infection is improved through the physiological sign abnormity continuity and the biomarker sudden increase and prediction trend, the subsequent early warning level and risk report generation are more reliable, and a more personalized and accurate treatment scheme can be provided for a patient.

An interactive pain management system is provided comprising a laser treatment device and an application executing on the device that receives entry of identification information for a first patient and receives entry of a body region to receive treatment. The system also receives entry of a present pain level experienced in the body region, accesses stored information describing previously reported conditions of the first patient and based on the received entries and the accessed store information, determines a treatment regimen for the first patient. The laser treatment device executes the treatment regimen by manual administration by the first patient or a qualified technician. The system requests entry of the first patient's present condition, the condition comprising one of feeling worse, feeling better, and experiencing no change since an immediately previous treatment. Changes in the condition of the first patient are incorporated into the determination of the treatment regimen.

The invention relates to the technical field of clinical treatment scheme recommendation. The invention relates to a clinical treatment scheme recommendation method based on brain diseases. The method comprises the following steps: S1, collecting brain examination data of a patient and other collectable body data, and then extracting disease features and other features of the brain; s2, collecting a historical clinical treatment scheme set and corresponding historical patient data, and combining the historical clinical treatment scheme set with the historical patient data to score the effect of the treatment scheme; according to the scheme adjusting model, the system can carry out personalized adjustment on the treatment scheme according to individual differences of patients, the unique characteristics of each patient are considered, the most suitable treatment scheme is customized for the patient, and meanwhile, the treatment effect of the treatment scheme is predicted by applying a simulation analysis technology; a doctor and a patient can roughly know effects possibly brought by different schemes before treatment, so that the doctor can select a scheme with a better curative effect expectation, and blind attempts are avoided.

The invention discloses an intelligent medical system suitable for an internet hospital, and relates to the technical field of intelligent medical treatment, and the system comprises the following steps: building an electronic health record, and obtaining the information of a patient; performing remote diagnosis and treatment according to the patient information to obtain a diagnosis and treatment result; performing medicine management according to the diagnosis and treatment result to obtain medicine management information; performing patient health monitoring according to the medicine management information to obtain patient health data; personalized health suggestions are made according to the health data of the patient, and health suggestions are obtained; performing patient health tracking and feedback according to the health suggestions to obtain health feedback; making and adjusting a rehabilitation plan according to the health feedback to obtain the rehabilitation plan; and performing health assessment and diagnosis and treatment feedback according to the rehabilitation plan. The accuracy of drug recommendation is improved, the safety and effectiveness of a treatment scheme are ensured, the scientificity and individual adaptability of health suggestions are improved, and the effectiveness and sustainability of a health management scheme are enhanced.

A neurostimulation system that has a programmer which has a power supply and processors with processing circuitry and a neurostimulation device which has power supply, processors and communication circuitry for providing communication with a neurostimulation device as well as communication circuitry for communication with the programmer. The neurostimulation system is configured to deliver treatment to a patient in accordance with a clinician prescribed protocol of a regimen. The neurostimulation system compares a delivered therapy treatment which has a treatment protocol to a defined treatment protocol of a prescribed treatment and adjusts the prescribed treatment stimulation parameters to compensate for a difference between the delivered neurostimulation therapy treatment and the prescribed treatment protocol for closely approximating the prescribed treatment protocol.

The invention provides a dynamic adjustment method based on a depression mind-correcting treatment scheme, and relates to the technical field of medical care information, and the method comprises the steps: collecting multi-dimensional information of a patient, and collecting life behavior risk data, psychological scale data and cognitive function evaluation data; comprehensively evaluating the depression level of the patient; determining the priority of a treatment therapy module according to the multi-dimensional information of the patient; generating an initial treatment scheme; calculating a daily task comprehensive weight value, and dynamically adjusting the training content of the next day; and evaluating the state of the patient in stages, recalculating the priority of each therapy module, and optimizing the therapeutic scheme. Through multi-dimensional data fusion evaluation and intelligent algorithm dynamic adjustment, a complete closed-loop feedback optimization system is constructed, precision and individuation of a depression treatment scheme are achieved, the treatment effect and patient compliance are effectively improved, the recurrence risk is reduced, and a more scientific and effective treatment scheme is provided for depression patients.

The invention provides a drug screening and curative effect evaluation method and system based on a glioma organ-like model, and relates to the technical field of biological material analys.The method includes the steps that a three-dimensional fluorescence image of the glioma organ-like model is collected, signal intensity analysis and compensation processing are carried out, a growth feature mapping model is constructed, and the three-dimensional fluorescence image of the glioma organ-like model is obtained; and phenotypic characteristics for representing the glioma organoid heterogeneity are obtained. Inputting the phenotypic characteristics into a drug response evaluation network, and calculating a drug sensitivity score; the drug molecular feature library and the drug collaborative analysis model are combined, the synergistic interaction index of different drug combinations is calculated, the optimal drug combination is screened, the drug administration dosage and the drug administration time sequence are determined in combination with phenotypic features, and finally an individualized treatment scheme is generated. According to the invention, the curative effect of the drug on the glioma organs can be effectively evaluated, and the optimal drug combination and administration scheme can be screened out, so that the accuracy and effectiveness of glioma treatment are improved.

The present invention relates to bispecific antibodies (bsAbs) and the use of such antibodies in the treatment of disease in subjects. Moreover, advantageous treatment regimens are provided for the treatment of B-cell Non-Hodgkin Lymphoma (B-NHL).

The invention discloses a traditional Chinese medicine diagnosis and treatment aided decision-making method and system, and relates to the technical field of traditional Chinese medicine intelligent diagnosis and treatment aided decision-making, and the method comprises the steps: carrying out the wavelet transformation analysis of pulse condition waveform time series data, extracting a pulse condition dynamic change feature sequence, inputting a tongue image color change rate and a pulse condition feature change rate into a space-time convolution network, and obtaining a time-space convolution network; generating a tongue pulse dynamic association index and outputting a preliminary syndrome classification; fourier transform analysis is carried out on the spleen channel acupoint impedance spectrum, false-true state judgment is carried out in combination with tongue pulse dynamic correlation indexes, preliminary syndrome classification is corrected, and a false-true state quantification result and corrected syndrome classification are output; and matching the corrected syndrome classification with the traditional Chinese medicine knowledge map, adjusting the dosage according to a virtual-real state quantification result, reversely verifying the drug-syndrome specificity through a curative effect database, screening an optimal treatment scheme, and outputting a personalized diagnosis and treatment scheme. According to the method, the syndrome classification precision is improved, and an objective basis is provided for personalized dose adjustment.

The invention belongs to the technical field of probiotics, and particularly relates to lactobacillus reuteri ShuiMian with a sleep aiding effect and application of the lactobacillus reuteri ShuiMian. A new ShuiMian strain is separated from feces of a healthy infant in Guangzhou city, Guangdong province, PTZ is adopted to construct a zebra fish insomnia model, and research finds that the strain can inhibit eye movement frequency, inhibit brain discharge, reduce dopamine secretion, promote GABA secretion and promote Gabra gene expression, and the zebra fish insomnia model can be used for treating insomnia. The effect of promoting sleep is achieved. Therefore, the strain has a unique sleep-promoting mechanism, can assist in developing novel sleep-promoting medicines in the field of medicines, and provides a safer and more effective treatment scheme for insomnia patients. In the health care industry, a nutritional supplement can be prepared, the mass sleep quality is improved, and the development of sleep health related industries is promoted.

The invention discloses a differentiated thyroid cancer lung metastasis risk prediction model construction method and system. 4D Label-free quantitative proteomics analysis and PRM and IHC dual verification are carried out on primary focus paraffin embedded tissue samples of lung metastatic DTC patients and non-lung metastatic DTC patients, and it is found that multiple key differential expression proteins DEPs may become potential biomarkers for predicting the DTC lung metastasis risk. In addition, the sample size is enlarged, three single and combined DTC lung metastasis risk prediction models are respectively constructed based on clinical features and key DEPs expression, then internal verification is performed on the efficiency of the three fitted models, and the optimal model is taken to construct Nomogram. According to the method, help is provided for risk stratification of lung metastasis of DTC patients, and an important basis is provided for formulating clinical individualized treatment schemes and follow-up visit strategies for high-risk patients.

The invention discloses a method, a system and equipment for evaluating the treatment effect of CGRP on epilepsy or brain injury caused by epilepsy. It is found for the first time that CGRP inhibits expression of P2RX7 by inhibiting a JAK-STAT1 pathway so as to play a role in treating epilepsy or brain injury caused by epilepsy. On the basis, the invention provides a method, a system and equipment for evaluating the treatment effect of the CGRP on the epilepsy or the brain injury caused by the epilepsy for the field, so that a doctor is assisted in evaluating the treatment effect of a patient suffering from the epilepsy or the brain injury caused by the epilepsy, and a clinician is guided to formulate an individualized treatment scheme for the patient.

System and methods for alerting a healthcare provider to prescribed treatments having reduced or no effectiveness due to genetic composition is provided. A database containing treatments known to have reduced or no efficacy in persons having particular genetic markers is queried to determine whether any treatments prescribed by, or likely to be prescribed by, a healthcare provider to the patient are known to have reduced or no efficacy in persons having the same certain genetic markers as the patient. An alert indicating such information is displayed at a healthcare provider system.

The invention discloses an AI syndrome differentiation and treatment model system suitable for a multi-dimensional difference environment, which comprises a data integration layer and a three-cause characteristic processing and dynamic dialectical model, and is characterized in that the data integration layer comprises outpatient service data, hospitalization data, follow-up visit data, physical characteristics, pathogenesis solar terms / five-transportation six-qi and regional medicinal material relationships; the three-factor feature processing comprises human-factor feature processing, time-factor feature processing and place-factor feature processing; the dynamic dialectical model comprises multi-modal data fusion, three-factor weight dynamic allocation and curative effect correction syndrome reasoning. The syndrome differentiation accuracy of chronic epigastric pain patients reaches 89.2%, the clinical curative effect and acceptability of a treatment scheme are improved, the average iteration period of the model is shortened to 72 h through a feedback closed-loop system, the method deeply conforms to Chinese geographical population characteristics, and the method has the advantages of being high in adaptability and good in application prospect through an environment perception-physique evaluation-dynamic syndrome differentiation three-level linkage mechanism. Precise diagnosis and treatment of one person with one prescription at once is achieved, and core technical support is provided for modernization of traditional Chinese medicine.

The invention belongs to the technical field of biotechnology and animal models, and discloses a double-person-derived mouse model for simulating a tumor immune microenvironment and a construction method and application thereof. The method comprises the following steps: firstly, pretreating NSG immunodeficient mice by adopting low-dose whole-body irradiation in combination with double-antibody targeted bone marrow depletion, and transplanting CD34 + hematopoietic stem cells from the same human donor to complete human immune system reconstruction; separating tumor primary cells, tumor-related fibroblasts and tumor vascular endothelial cells of the same donor, performing three-dimensional co-culture to obtain homologous human tumor organs, and performing in-situ inoculation to immune reconstruction mice to obtain a target model. The core defects of MHC mismatching, low immune reconstruction efficiency, poor tumor immune microenvironment simulation degree, low clinical consistency and the like of an existing model are overcome, and the method can be used for tumor immune treatment drug screening, microenvironment mechanism research and personalized tumor treatment scheme verification.

The invention belongs to the technical field of medical instruments, and particularly relates to a cryoablation catheter and an ablation system.The cryoablation catheter comprises an inner catheter body and an outer catheter body, the outer catheter body is coaxially arranged on the outer side of the inner catheter body in a sleeving mode, and the inner catheter body is configured to be of a multi-cavity structure; the multiple plugging assemblies are arranged on the outer side of the inner catheter; wherein in the initial state, the multiple plugging assemblies and the inner catheter are located in the outer catheter, and in the working state, the multiple plugging assemblies and the inner wall of the intestinal tract jointly form an ablation closed space. The cryoablation catheter is guided to a target position through the guide wire, the closed ablation space is formed through cooperation of the plugging assembly and the inner wall of the cavity, a freezing medium is input into the closed ablation space to conduct cryoablation on the inner wall of the cavity, an available treatment scheme is provided for patients suffering from type 2 diabetes, obesity or other cavity lesions, and meanwhile the treatment effect is improved. The device has the advantages of small trauma, less pain of patients, low surgical risk and the like.

The invention discloses a drug-resistant marker for treating prostatic cancer olaparib and application of the drug-resistant marker, and relates to the technical field of medicine, and the marker is a PCAR1 gene. Research finds that the PCAR1 gene is remarkably and highly expressed in prostate cancer Olaparil drug-resistant cells and clinical drug-resistant samples, and can be used as a key marker for judging the drug resistance of prostate cancer patients to Olaparil. By detecting the expression level of the PCAR1 gene, the treatment reaction of a patient to the olaparil can be effectively predicted, and a basis is provided for clinically and accurately selecting a treatment scheme. Meanwhile, the specific siRNA designed aiming at the PCAR1 gene can obviously inhibit the expression of the PCAR1 gene, and can effectively reduce the drug resistance of cancer cells to olaparione, promote the apoptosis of the cancer cells and inhibit the proliferation of the cancer cells when being combined with the olaparione for use. Based on the siRNA, the invention prepares a pharmaceutical composition containing the siRNA and olaparil, and provides a new drug combination scheme for the treatment of prostatic cancer.

The invention provides an application of a T lymphatic activation related cytokine as a biomarker in prediction of children immune globulin non-reactive Kawasaki disease. The team finds that in patients of an IVIG sensitive group and an IVIG non-response group, differences of expression levels of IL-6 and IL-17 before and after treatment have statistical significance; meanwhile, ROC curve analysis shows that IL-6 and IL-17 serve as early warning signals, and the prediction efficiency of the IVIG-unreacted Kawasaki disease is remarkably superior to that of existing prediction factors. Particularly, the levels of IL-6 and IL-17 are re-evaluated after initial treatment, so that the early prediction accuracy of the IVIG unresponsive Kawasaki disease can be further improved. By introducing IL-6 and IL-17 as novel biomarkers, early accurate prediction of the IVIG unresponsive Kawasaki disease is realized. Compared with the prior art, the method can provide a quicker and more accurate risk assessment basis for clinicians, so that early recognition of high-risk patients, optimization of subsequent treatment schemes and reduction of serious complications are facilitated, and a new thought and direction are provided for clinical diagnosis and treatment.

The present disclosure relates to a once weekly dosing regimen of a dual GLP-1R and GCGR agonist, formulations, and methods of using the same to induce weight loss in humans suffering from fatty liver disease, where the humans may or may not suffer from other complications, such as type 2 diabetes and / or cardiovascular disease / disorder. The dual agonist of the GLP-1R and the GCGR comprises a peptide product of SEQ ID NO. 1 (pemvidude), and a preparation method of the GLP-1R and GCGR dual agonist.

The invention belongs to the technical field of medical auxiliary diagnosis, and discloses an ulcerative colitis virtual biopsy method and system based on a multi-modal image, and the method comprises the steps: building an ulcerative colitis medical image database; constructing a prediction data set according to the extracted quantitative features and the pathological grades of the ulcerative colitis patients; based on the prediction data set, constructing and training an ulcerative colitis virtual biopsy model; and acquiring new clinical data of a patient with ulcerative colitis in real time, inputting the acquired new clinical data into the trained ulcerative colitis virtual biopsy model, and outputting a pathological grading result of ulcerative colitis through extraction and prediction of pathological features. According to the method, automatic analysis of image and endoscopic image features of the lesion area can be realized, the pathological activity state of the ulcerative colitis patient can be accurately judged, and association with long-term prognosis of the patient is established, so that help is provided for clinicians to formulate an individualized UC treatment scheme.

The invention relates to the technical field of biological medicines, in particular to an iRGD targeted and anti-fibrosis small molecule dual-modified exosome as well as a construction method and application thereof. The exosome utilizes the specific binding penetration enhancement effect of iRGD (the amino acid sequence is CRGDKGPDC) and a fibroblast high-expression integrin receptor, so that the enrichment efficiency of the exosome at a focus part is improved; the anti-fibrosis micromolecule Let-7a-5p can inhibit a TGF-beta signal channel by blocking Smad2 / 3 phosphorylation, and the anti-fibrosis micromolecule Let-7a-5p and the anti-fibrosis microRNA carried by the exosome generate a synergistic anti-fibrosis effect; the exosome phospholipid bilayer can also protect Let-7a-5p from enzymolysis and prolong the half-life period, and iRGD modification can reduce the non-targeted uptake rate. An animal model verifies that the double-modified exosome has a good skin fibrosis resisting effect, and side effects such as liver and kidney function damage are not found. The invention provides an effective and safe treatment scheme for resisting skin fibrosis.