87 results about "Clinical prognosis" patented technology

The invention belongs to the technical field of data processing, and particularly discloses a method and system for predicting the lifetime of a non-small cell lung cancer patient after radiotherapy, and the method comprises the steps: collecting multi-time-point imaging and hematology follow-up visit data of the patient after radiotherapy, building a longitudinal follow-up visit sequence, and mapping the longitudinal follow-up visit sequence to a unified time axis; determining a bimodal first-time significant improvement point through preset rule judgment, and constructing and standardizing an asynchronous index according to the bimodal first-time significant improvement point; then inputting a feature vector at a follow-up time point, encoding a bimodal sequence through a Transform time sequence encoder, and generating joint representation through cross-modal interaction; and finally, inputting the standardized asynchronous index, the joint representation and the clinical and radiotherapy characteristics into a DeepHit model, and outputting a patient survival distribution prediction result. According to the method, bimodal indexes can be accurately captured, time dislocation is improved, prediction accuracy and individualization degree are improved, and a reliable basis is provided for clinical prognosis evaluation.

The invention relates to the technical field of medical data analysis, in particular to a urinary system tumor big data analysis system which comprises a target kernel generation module, a kernel matrix calculation module, a parameter optimization module and a risk division module. According to the method, a target kernel matrix reflecting clinical prognosis differences is constructed and serves as an optimization reference, a radiomics and genomics feature kernel matrix is generated through hardware acceleration parallel computing, kernel function width parameters are dynamically iteratively updated based on an alignment degree numerical value so as to ensure that multi-modal feature distribution is highly matched with a prognosis label, and the accuracy of the multi-modal feature distribution is improved. A multi-dimensional feature space containing rich pathological information is constructed by combining a weighted fusion mechanism after centralization processing, so that a support vector machine is trained to determine a high-robustness decision boundary, and precise division of tumor risk levels is realized while high-dimensional data calculation delay is greatly reduced; and the reliability and timeliness of auxiliary diagnosis and treatment results in a complex pathological environment are effectively improved.

The invention relates to an anti-NMDAR encephalitis clinical prognosis evaluation method based on artificial intelligence, and belongs to the technical field of artificial intelligence and data processing. The method comprises the following steps: acquiring multi-modal nerve image data of a patient; performing fusion preprocessing on the multi-modal neural image data by adopting a tensor decomposition fusion strategy, and reserving cross-modal spatial correlation through low-rank constraint to obtain a fused output tensor; carrying out focus perception anisotropic diffusion filtering on the fused output tensor to obtain an output image after diffusion filtering; an anti-NMDAR encephalitis clinical prognosis evaluation model is constructed, the output image after diffusion filtering is input into the model for training, an Adam adaptive optimizer is adopted to optimize the training process, and finally a trained model is obtained; and inputting a to-be-evaluated output image after diffusion filtering into the trained model to obtain an evaluation classification result. The identification and classification capability of the model on the focus can be enhanced.

The invention relates to a molecular typing model construction and identification method of BRCA mutation breast cancer. The method comprises the following steps: performing unsupervised clustering analysis on a gene with most significant change in a common transcriptome expression profile of BRCA1 / 2 mutant breast cancer to obtain an optimal clustering number, and dividing the optimal clustering number into subtypes with different clinical prognosis and molecular characteristics of the optimal clustering number; based on the clustering result, a random forest algorithm is utilized to construct a molecular typing model, the model comprises a plurality of key classification genes, and the molecular typing model is verified through a verification set and an external data set so as to ensure the accuracy, the stability and the clinical applicability of the molecular typing model. Molecular typing can be rapidly and accurately carried out according to common transcriptome sequencing data of a BRCA1 / 2 mutant breast cancer patient tumor sample, and a scientific basis is provided for selection of an individualized treatment scheme.

The invention relates to the technical field of medical image processing, and particularly discloses a lesion image generation method for ultrasonic diagnosis, which comprises the following steps of: 1, acquiring initial state data of a lesion; 2, obtaining intervention factor data; 3, performing feature coding on the initial state data and the intervention factor data to obtain an initial feature vector and an intervention feature vector; and 4, inputting the initial feature vector and the intervention feature vector into a pre-trained time sequence generation model, and generating a continuous image sequence of the focus changing along with time. By constructing the time sequence generation model fusing the multi-modal feature coding and the space-time attention mechanism, the continuous image sequence of the focus changing along with time can be accurately generated, the disease progress or treatment response process can be accurately simulated, and a powerful reference basis is provided for clinical prognosis evaluation.

The invention relates to the technical field of pathological section image recognition, in particular to a method for accurately predicting clinical prognosis of a colorectal cancer patient, which comprises the steps of full-view digital section acquisition, full-view digital section preprocessing, Transformer-dynamic agency attention-Mama network and interpretability analysis. According to the method, firstly, a tissue slice segmentation unit and a preliminary feature extraction unit are integrated, full-view digital slice feature extraction is achieved, then a Transformer-dynamic agency attention coupling architecture is adopted, time sequence dependence modeling is achieved through a multi-layer Mama module, finally, a feature aggregation unit is used for outputting patient risk scores, and the patient risk scores are obtained. And realizing visual explanation of the model decision by adopting a thermodynamic diagram. According to the method, through fusion of long sequence data processing, a dynamic agency attention mechanism and a state space modeling technology, the technical bottlenecks of insufficient feature characterization capability, difficulty in long-range dependence modeling and the like in traditional pathological image analysis are solved.

The invention discloses an image processing and simulation analysis method for a carotid artery image, which comprises the following steps: firstly, acquiring a CTA image, observing and selecting, then importing the CTA image, adjusting the image contrast, generating a three-dimensional blood vessel model, extracting a carotid artery focus, and carrying out overall and local surface optimization processing on the model. The method comprises the steps that firstly, a model is built, then local surface cutting naming and grid division are conducted on the model, finally parameters are set, CFD hemodynamic simulation is conducted, a simulation result is subjected to visualization processing, and preoperative and postoperative data are compared and analyzed. According to the method, multi-modal imaging data of brain CT perfusion imaging, brain CT angiography and the like of a patient suffering from carotid artery stenosis can be collected to be used for reconstructing a three-dimensional model of the carotid artery stenosis, the carotid artery hemodynamic characteristics of the patient and the individual characteristics of the patient are analyzed in an auxiliary mode based on computational fluid mechanics, operation mode selection is optimized, and the three-dimensional model of the carotid artery stenosis is reconstructed. Cerebral ischemia reperfusion injury is avoided, clinical prognosis of a patient is improved, and life quality of the patient is improved.

The invention discloses a tumor radiotherapy patient symptom management and prognosis evaluation method and system, and relates to the field of tumor radiotherapy, and the method comprises the steps: obtaining the age data, biological data, clinical data and symptom data of a tumor radiotherapy patient; calculating a comprehensive symptom score through the dynamic symptom evaluation model and the symptom data; when the symptom comprehensive score exceeds a preset threshold value, automatically matching a targeting scheme according to the symptom dominant factor; performing correction calculation on the biological data and the clinical data based on the age data to obtain a biological prognosis index and a clinical prognosis index; performing difference significance judgment on the biological prognosis index and the clinical prognosis index, and calculating a comprehensive prognosis index; dynamically adjusting the radiotherapy plan according to the biological prognosis index, the clinical prognosis index and the comprehensive prognosis index; the weight coefficient is updated after the radiotherapy plan is adjusted each time; according to the invention, dynamic symptom evaluation, multi-dimensional prognosis evaluation and adaptive radiotherapy plan adjustment can be realized.

The invention discloses a cancer profiling classification and prognosis prediction method based on generic cancer multi-omics data, and relates to a cancer profiling classification and prognosis prediction method. The invention aims to solve the problems of cancer subtype classification and prognosis prediction in generic cancer multi-omics. The method comprises the following steps: step 1, acquiring a multi-omics generic cancer data set, wherein the multi-omics generic cancer data set comprises a data set consisting of mRNA (messenger ribonucleic acid), DNA (deoxyribonucleic acid) methylation, miRNA (micro Ribonucleic Acid) and clinical prognosis data; 2, preprocessing the multi-omics cancer data set in the step 1; step 3, constructing a deep neural network model; 4, training the deep neural network model constructed in the step 3 based on the multi-omics generic cancer data set preprocessed in the step 2; and 5, carrying out cancer subtype classification and prognosis prediction on to-be-detected data based on the deep neural network model trained in the step 4. The invention belongs to the technical field of bioinformatics.

The invention belongs to the field of biological medicine, and relates to a detection reagent based on a nasopharyngeal carcinoma related TCR sequence and application of the detection reagent. The invention provides a storage assembly for storing data, the storage assembly stores instructions for diagnosing an individual suspected to suffer from nasopharynx cancer, receives input individual data, and the individual data comprises obtained sequences of TCR libraries in biological samples of the individual and obtained TCR library sequence information of the individual; analyzing TCR library sequence information of the individual and reference CDR3 beta amino acid sequence comparison information to obtain a TCR clone number completely matched with the reference CDR3 beta amino acid sequence, and obtaining a TCR score according to the obtained TCR clone number completely matched with the reference CDR3 beta amino acid sequence; and on the basis of the TCR score, outputting diagnosis information about whether the individual suffers from nasopharynx cancer or not. The storage assembly for storing data can be used to obtain a diagnostic system for diagnosing an individual suspected of having nasopharynx cancer. The diagnosis system disclosed by the invention can be applied to screening of high-risk groups with nasopharyngeal carcinoma, early diagnosis and treatment of nasopharyngeal carcinoma, evaluation of clinical prognosis and development of a new immunotherapy strategy.

The application provides a model construction and verification method and nomogram for predicting the clinical prognosis of SFTS patients complicated with AP. By collecting the clinical data of SFTS patients, the independent risk factors related to adverse prognosis are screened out by using LASSO regression analysis, a multi-factor Logistic regression model is constructed, and the model is visualized by nomogram for predicting the adverse prognosis of SFTS patients complicated with AP. The model has high discrimination and calibration, and can provide an effective prediction tool for clinicians to optimize clinical decision-making.

The application belongs to the technical field of biotechnology, and particularly relates to a marker for prognosis evaluation of acute myeloid leukemia and application thereof, wherein the marker is HCK-positive mono-like cells, the HCK-positive mono-like cells are determined by co-positivity of antigens CD163, antigen CD68, antigen FCN1 and antigen HCK, and the application provides a marker with high sensitivity, strong specificity and good universality, which is used for detecting adult acute myeloid leukemia bone marrow or peripheral blood samples, so as to assist in judging the clinical prognosis of patients with acute myeloid leukemia.

The invention discloses a combination of a glutathione synthesis inhibitor and a glucose uptake inhibitor, a nanoparticle delivery system and application thereof, and belongs to the field of medicines. The invention proves that the SLC7A11 is remarkably overexpressed in lung adenocarcinoma and is related to poor clinical prognosis; experiments find that the combination of the glutathione synthesis inhibitor and the glucose uptake inhibitor shows an effect of enhancing lung adenocarcinoma treatment in medium and high SLC7A11 expression cells, and can also achieve an effect equivalent to glucose deprivation under the condition of SLC7A11 overexpression in low expression cells. In order to optimize a delivery mode and minimize systemic toxicity, the invention also prepares a dual-cell membrane coated dual-drug nanoparticle delivery system, the system shows the ability to enhance tumor targeting and drug controllable release, effectively solves the problem of expression difference (heterogeneity) of SLC7A11 in tumors, and shows a significant anti-tumor effect in a preclinical model, and the system has good application prospects. And a promising treatment method is provided for treating lung adenocarcinoma.

The invention discloses a detection kit for detecting JAK2V617F mutation, which is characterized by comprising: a JAK2V617F detection reagent, which comprises an inner primer pair, an outer primer pair and a specific probe for specifically amplifying a JAK2V617F mutant gene; the internal reference detection reagent comprises a primer pair and a probe of an internal reference gene; the PCR reaction buffer solution comprises a reaction mixed solution and a HotstartTaq enzyme; the kit comprises a positive control, a known proportion of V617F mutant DNA, a negative control, a JAK2V617F wild type DNA, a positive control and a known proportion of V617F mutant DNA. Compared with the prior art, the invention has the advantage of providing the detection kit for detecting JAK2V617F mutation, which can be used for diagnosis, identification and clinical prognosis of PV.

The invention discloses a blood coagulation index detection system and method based on ultrasonic guided waves, and the method comprises the steps: calculating a blood coagulation index corresponding to a sample according to an obtained viscoelasticity change curve; comprising the following steps: the clot starting time is defined as the time interval from the time when a blood sample is placed in a blood clot index detection system to the time when initial fibrin starts to form, and the R time of a TEG detection result of a gold standard method is marked; the clot stabilization time is defined as the clot formation time of the blood sample and the K time of the TEG detection result of the gold standard method; the theta angle is used for measuring the generation and cross-linking speed of fibrin and the alpha angle of a TEG detection result of a gold standard method; the maximum clot strength is the MA value of the TEG detection result of the gold standard method. Compared with a TEG method, the method has the advantages that the detection time of blood coagulation indexes is remarkably shortened, time guarantee is provided for emergency blood coagulation function evaluation and reasonable application of blood products in an operation, and improvement of clinical prognosis is facilitated.

The present invention discloses a prognostic marker for gastric adenocarcinoma, which consists of 8 genes: F5, SLC5A1, PHYHD1, FNDC1, NFE2L3, SCUBE2, CBS, and CTHRC1. The risk assessment model constructed based on these 8 genes helps to better predict the prognosis of gastric adenocarcinoma patients, effectively evaluate the prognostic risks of different patients, intervene early, bring great help to guiding the clinical treatment of this disease, and thus improve the 5-year survival rate of gastric adenocarcinoma patients. The risk assessment model of the present invention has high prediction accuracy, is universal, and is significantly superior to other gastric adenocarcinoma prognosis methods in the prior art and is also significantly superior to other models constructed during the research process.

The present application relates to pathological section image recognition technical field, specifically to a kind of accurate prediction colorectal cancer patient clinical prognosis method, including full field digital slide acquisition, full field digital slide preprocessing, Transformer-dynamic proxy attention-Mamba network and explainability analysis.The method first integrates tissue section segmentation unit and preliminary feature extraction unit, realize full field digital slide feature extraction, then adopt Transformer-dynamic proxy attention coupling architecture, and realize time series dependence modeling by multilayer Mamba module, finally use feature aggregation unit to output patient risk score, and use heat map to realize the visualization explanation of model decision.The present application solves the technical bottlenecks such as insufficient feature representation ability and long-range dependence modeling difficulty in traditional pathological image analysis by fusing long sequence data processing, dynamic proxy attention mechanism and state space modeling technology.

The application provides a prognosis prediction method and system for chronic Doc patients, relates to the technical field of clinical prognosis evaluation, and collects multi-modal data such as neuroimaging, neuroelectrophysiological data, biochemical indexes and clinical data, carries out standardized processing and feature extraction, and fuses spatial features, time sequence features and key features.Combining a trained consciousness state grading evaluation model and a prognosis prediction model, a feature level data set is generated, and the consciousness state grading and prognosis development trend of the patient are accurately predicted.The application effectively integrates the complementary information of multi-modal data, improves the accuracy and reliability of prognosis prediction, and provides scientific support for clinical decision-making, individualized treatment and medical resource optimization.

The invention discloses a prognosis molecular marker for multiple myeloma (MM), a prognosis layering model and application of the prognosis molecular marker and the prognosis layering model. Specifically, six core genes significantly related to poor clinical prognosis are screened out, and an MM prognosis layering model is constructed through early clinical data based on the six core genes. Meanwhile, on the basis of the prognosis layering model, a set of Droplet digital PCR (ddPCR) detection method which is completely matched with the prognosis layering model and is efficient is constructed; and a group of brand-new clinical samples are used as a verification set to verify the prognosis layering model and the corresponding ddPCR detection method. In conclusion, the invention proves that the six-gene prognosis layering model and the ddPCR detection method thereof can effectively distinguish prognosis high-risk group patients from prognosis low-risk group patients. The method not only provides a new tool for accurate layering of multiple myeloma, but also can assist in clinical formulation of individualized treatment strategies for high-risk patients, improves the scientificity of clinical diagnosis and treatment decisions, and has important application value.

The embodiment of the application provides a two-stage clustering diagnosis and automatic machine learning prediction method and model, the method comprises the following steps: feature weighting is performed on 3D space coordinates and SUV in tumor PET images to realize first-stage clustering; voxel-level clustering analysis is performed on tumor regions in the tumor PET images to realize second-stage clustering, and tumor sub-regions with different metabolic characteristics are outlined; based on the tumor sub-regions outlined in the two-stage clustering, features of the whole tumor and different sub-regions are extracted; based on the extracted features, an automatic machine learning prediction algorithm is constructed to predict labels in a classification task and numerical values in a regression task; based on the Kernel SHAP method, the feature importance of the prediction result is analyzed for interpretability. The method and model provided by the application can accurately identify and predict tumor high-risk and low-risk sub-regions, thereby improving the accuracy of individualized radiotherapy plans and improving the clinical prognosis of patients.

The application belongs to the field of tumor molecular diagnosis and targeted therapy, and specifically finds lncRNA RP11-499F3.2 which is significantly highly expressed in head and neck cancer through bioinformatics analysis of TCGA data; it is verified through clinical samples that the expression level of RP11-499F3.2 in head and neck squamous cell carcinoma is significantly higher than that in paracancerous tissues, and is closely related to the clinical prognosis of patients with head and neck squamous cell carcinoma; it is found through functional experiments that high expression of RP11-499F3.2 can promote the in-vitro proliferation, migration and invasion of head and neck squamous cell carcinoma cells; meanwhile, it is also found that RP11-499F3.2 can promote the drug resistance of head and neck squamous cell carcinoma cells to cetuximab; the disclosed lncRNA RP11-499F3.2 helps to reveal the new pathogenesis of head and neck cancer, provides a new tumor marker for the prognosis monitoring of head and neck cancer, and provides a new idea for the clinical treatment of head and neck cancer.

The utility model discloses a multifunctional guider for olecranal fracture and osteotomy, and belongs to the technical field of surgical auxiliary instruments. Comprising a guide fixing plate and a guide assembly, the guide fixing plate is provided with a positioning hole, a fixing hole and olecranon hooks, the guide fixing plate is an arc-shaped plate capable of being attached to the olecranon end of the ulna, the positioning hole and the fixing hole transversely and longitudinally penetrate through the guide fixing plate respectively, the two olecranon hooks are symmetrically arranged on the guide fixing plate, and the olecranon hooks are arranged on the guide assembly. A guide assembly is arranged on the guide fixing plate between the two olecranon hooks, the guide assembly comprises two sighting device sleeves, and a V-shaped osteotomy guide opening is further formed in the guide fixing plate; the olecranon fracture reduction and fixation device can assist in olecranon fracture reduction and fixation, accurate screw placement and needle insertion, meanwhile, accurate osteotomy can be achieved during olecranon osteotomy, follow-up reduction and fixation are completed, and good clinical prognosis is achieved.

The application belongs to the field of gene drugs, and particularly relates to CTRTS, an analog thereof and application thereof. The CTRTS has a nucleotide sequence as shown in SEQ ID NO. 1. The CTRTS analog is CTRTS Agomir, and has a nucleotide sequence as shown in SEQ ID NO. 2. The present application finds that the expression level of CTRTS is reduced when doxorubicin induces cardiotoxicity; overexpression of CTRTS can significantly inhibit doxorubicin-induced cardiotoxicity, and plays an important role in the regulation of myocardial cell death. The existing drug has limited therapeutic effect, therefore, CTRTS plays an important role in the regulation of myocardial cell death, can regulate the doxorubicin-induced cardiotoxicity treatment by participating in the regulation of the myocardial cell death process, so as to improve the clinical prognosis effect.

High levels of nuclear NMT1 are associated with longer relapse free survival in ERα positive breast cancer patients. Both low levels of cytosolic and nuclear NMT1 correlated to very poor clinical outcomes. NMT2 also plays an important function in breast cancer signalling, regulated through phosphorylation. For example, NMT2 phosphorylation status is a key element in the progression of ER+ breast cancer cells. Specifically, nuclear localization of NMT2 is associated with poor outcomes in breast cancer patients.

The invention discloses a human SLC7A11AR gene. The nucleotide sequence of the human SLC7A11AR gene is as shown in SEQ ID NO: 1; the reagent for detecting the expression quantity of the human SLC7A11AR gene is applied to preparation of the lung adenocarcinoma clinical diagnosis reagent, the expression level of the human SLC7A11AR gene is in negative correlation with clinical prognosis of the lung adenocarcinoma, and experimental results show that the expression of the human SLC7A11AR gene in a lung adenocarcinoma cell line is higher than that of normal lung epithelial cells; after the SLC7A11AR gene is knocked down, the proliferation of the lung adenocarcinoma cell line is obviously inhibited; the ASO sequence for inhibiting the expression of the human SLC7A11AR gene is combined with a ferroptosis inducer, so that the growth of lung adenocarcinoma in vivo can be obviously inhibited; the invention reveals that the SLC7A11AR gene is a potential risk gene of lung adenocarcinoma, and SLC7A11AR expression inhibition is combined with a ferroptosis inducer IKE to enhance the treatment effect of lung adenocarcinoma.

The invention discloses an application of a serum protein biomarker in preparation of an auxiliary evaluation reagent related to feline calicivirus infection. The biomarker is long-chain acyl coenzyme A synthetase 4 (ACSL4) or calcium binding protein S100A2. When the expression level of the ACSL4 protein in the serum of the to-be-detected cat is obviously increased relative to the expression level in the control serum of a healthy cat, the FCV infection induced lung injury is indicated; when the expression level of the S100A2 protein in the serum of the to-be-detected cat is obviously reduced relative to the expression level in the control serum of the healthy cat, the FCV infection related oral lesion prognosis is poor. The serum ACSL4 and S100A2 can be used as specific biomarkers of FCV infection, so that the problem of high detection false negative rate caused by high virus variation is solved, the diagnosis accuracy is remarkably improved, and quantitative evaluation on clinical prognosis of FCV infection is realized.

The present invention is applicable to the field of biomedical technology and provides a diagnostic kit for unstable carotid atherosclerotic plaques. The present invention aims to collect urine samples from patients with carotid atherosclerotic plaques, perform proteomic mass spectrometry sequencing, and conduct comprehensive analysis in combination with transcriptomic and proteomic data of tissue samples. In this process, we successfully discovered two reliable diagnostic biomarkers: ADAMDEC1 and IQGAP2. These two biomarkers can not only be used to prepare diagnostic kits to achieve accurate diagnosis of unstable carotid atherosclerotic plaques, but also provide strong support for the judgment of disease prognosis. In addition, the discovery of the present invention has also opened up a new method for the diagnosis of carotid plaque stability and provided a more reliable basis for clinical prognosis evaluation and the identification of new therapeutic targets.

The invention discloses application of MISP as a breast cancer diagnosis / prognosis marker and a treatment target. The in-depth study on the expression of MISP in breast cancer cells and the influence on malignant biological behaviors such as breast cancer proliferation shows that compared with normal breast epithelial cells, the MISP is highly expressed in the breast cancer cells, the expression of the MISP is highly related to poor clinical prognosis of breast cancer patients, and the proliferation of the breast cancer cells can be inhibited by reducing the expression of the MISP. A new biomarker is provided for diagnosis and prognosis of the breast cancer, a new target spot is provided for treatment of the breast cancer, and important scientific significance is achieved in the aspects of subsequent drug research and development, clinical treatment and the like.

The invention discloses a dynamic prognosis management method, device and equipment based on k-mer evolution and a storage medium, and relates to the technical field of bioinformatics and clinical prognosis management.The method comprises the steps that k-mer analysis is conducted on high-throughput sequencing data of a patient at different time points, a time sequence k-mer frequency spectrum is constructed, and based on the time sequence k-mer frequency spectrum, the time sequence k-mer frequency spectrum is constructed; a multi-scale Shannon entropy sequential sequence reflecting tumor clone diversity is calculated, the change trend of the Shannon entropy sequential sequence is analyzed, evolution dynamic characteristics of tumor clone are quantified, and individualized prognosis risk rating and treatment scheme recommendation are generated according to the evolution dynamic characteristics and clinical indexes of patients. And based on a preset early warning threshold value and the prognosis risk rating, triggering dynamic early warning. By means of the mode, the problems that due to the fact that a current tumor prognosis management technology depends on static and single-time-point data, tumor cloning dynamic evolution cannot be accurately tracked in real time, treatment early warning lags behind, and the curative effect prediction error rate is high are solved.

The application provides an integrated learning model construction method based on a genetic algorithm and a comprehensive evaluation method, relates to the technical field of digital technology, and constructs an integrated learning model construction framework based on the genetic algorithm and the comprehensive evaluation method to improve the classification performance and prediction accuracy of the integrated model. By constructing a basic learning device, the R- CIEM score is used to hierarchically divide the basic learning device formed by the used machine learning method, the hierarchical results of the basic learning device are obtained, the basic learning device with the level of "excellent" is selected to combine and construct an integrated learning model, the integrated learning model is used, and the basic information and clinical test data of the same type of clinical patients in the test set are used to predict the clinical evaluation information and clinical prognosis information of the patients.