47 results about "Prognostic model" patented technology

The invention provides a lung adenocarcinoma prognostic marker and a model, constructs a lung adenocarcinoma prognostic model based on mRNA and lncRNA related to programmed cell death (PCD), and synthesizes bioinformatics analysis and experiments to explore the biological effect of the lncRNA model in lung adenocarcinoma. The prognosis model covers all PCD pathways and various molecules, has stable prognosis prediction accuracy, and can provide a potential molecular target for personalized treatment. According to the method disclosed by the invention, the PCD-related mRNA and lncRNA are integrated to construct a lung adenocarcinoma diagnosis model suitable for Chinese population, so that the identification capability of tumor patient classification is enhanced from multiple aspects, the accuracy and reliability of prognosis prediction are improved, powerful support can be provided for promoting personalized treatment strategies of lung adenocarcinoma patients, and the method is suitable for popularization and application.

A hybrid liver cancer prognosis model, prognosis system and medium, the model takes independent influence factors as input and outputs hybrid liver cancer postoperative risk scores, the hybrid liver cancer postoperative risk scores are used for dividing risk levels, and the risk levels are used for hybrid liver cancer prognosis evaluation. And / or is used for postoperative adjuvant chemotherapy decision-making of mixed liver cancer. The hybrid liver cancer prognosis model is jointly constructed by combining the traditional clinical pathological characteristics and immune microenvironment indexes, the key effect of the tumor immune microenvironment in CHC prognosis is indicated, and the constructed hybrid liver cancer prognosis model has good CHC prognosis prediction performance; in addition, decisions of postoperative adjuvant chemotherapy can be provided for patients with different risk levels, precise treatment of the CHC patients is achieved, and long-term survival prognosis of the CHC patients is improved.

The invention relates to the technical field of biomedicine, in particular to a liver cancer molecular subtype typing and prognosis model construction method based on glycometabolism and lactic acid metabolism related genes and application thereof. According to the invention, the typing and prognosis model of liver cancer subtypes is constructed for the first time on the basis of a coordinated regulation network of a glycometabolism gene and a lactic acid metabolism gene, the constructed liver cancer subtype subtypes comprise Cluster1 and Cluster2, and the total survival rates of different subtypes have significant difference; the clinical characteristics T.stage and TNM.stage of different subtypes are obviously different from each other; 12 kinds of immune cells have significant differences among different subtypes; iPS immune scores of different subtypes are significantly different; the TIDE scores of different subtypes have significant score differences; the genes with the highest mutation frequency in different subtypes comprise TP53, CTNNB1 and TTN. CLM scores of the prognosis model constructed on the basis of the collaborative regulation network of the glycometabolism genes and the lactic acid metabolism genes have no significant difference in different patient states; the 17 immune cells have significant differences between high and low risk groups. And a new way is provided for individualized treatment strategy formulation and survival outcome improvement of HCC.

The invention discloses a prognosis evaluation method and system for diffuse large B-cell lymphoma. According to the method, firstly, a gene module closely related to lipid metabolism is screened from DLBCL transcriptome data through weighted gene co-expression network analysis (WGCNA), and then eight key prognosis genes including FNDC1, IL22RA2, C15orf48, OMD, MFAP2, BC017398, CXCL6 and TNFAIP6 are identified from the module by adopting multi-step regression analysis (single factor Cox, LASSO and multi-factor Cox). A risk scoring model is constructed based on the expression levels and regression coefficients of the genes, and DLBCL patients can be divided into a high-risk group and a low-risk group with significant survival differences. The risk score and the clinical pathological factors are further integrated to construct a column graph, and individualized survival probability prediction can be achieved. The invention further provides a corresponding prognosis evaluation system, electronic equipment and a storage medium. An independent data set verifies that the prognosis model has excellent prediction performance and clinical practical value.

The invention discloses a colorectal cancer metabolism-related prognosis model construction method based on multiple omics. By integrating multiple omics data, the defect is overcome, a new view angle and method are provided, the accuracy and practicability of the prognosis model are effectively improved, and the blank in the prior art is filled. Meanwhile, the method provided by the invention is not only suitable for prognosis prediction of colorectal cancer patients, but also can be popularized and applied to other types of cancers. As the metabolism-related gene plays an important role in various cancers, the technical scheme provided by the invention has relatively high universality and popularization value, and can provide reference for prognosis prediction and personalized treatment of other cancers. Finally, the prognosis model provided by the invention can be used as a clinical decision support tool to help doctors to make more scientific and accurate decisions in diagnosis and treatment processes. Through early recognition of high-risk patients and implementation of targeted intervention measures, prognosis of the patients can be significantly improved, and the risk of relapse and metastasis can be reduced.

This invention discloses a method for constructing a prognostic model for acute myeloid leukemia (AML) based on ferroptosis-related genes. The method involves acquiring gene expression data from AML patients and healthy samples to screen for differentially expressed ferroptosis-related genes (DEGs) associated with AML. Using univariate Cox proportional hazards regression analysis, LASSO regression analysis, and multivariate Cox proportional hazards regression analysis, key genes ACSF2, SLC7A11, DNAJB6, and SOCS1 are selected from these DEGs. A prognostic risk model is constructed based on the expression levels of these key genes and their corresponding multivariate Cox regression coefficients. The risk score formula is: Risk Score = 0.534 × ACSF2 expression value - 0.453 × DNAJB6 expression value + 0.194 × SLC7A11 expression value + 0.308 × SOCS1 expression value. The prognostic model constructed in this invention has high predictive accuracy and reliability, effectively stratifying the risk and assessing the prognosis of AML patients, providing an important reference for the clinical treatment of AML.

The invention relates to the technical field of biology, in particular to 5-hydroxymethylcytosine and application of a prognosis model of 5-hydroxymethylcytosine in nasopharynx cancer prognosis evaluation. According to the method, the prognosis scoring model capable of layering the outcome of the patient is constructed, and the model shows strong distinguishing performance in a training set and a verification set. When it is integrated into a prognostic model together with tumor staging and EBV status, the 5hmC score results in higher calibration accuracy and net clinical benefit in decision curve analysis. According to the findings, a 5hmC prognosis model is determined as a noninvasive marker rich in biological information, can be used for prognosis risk layering of NPC patients, and has potential significance for individualized management and improvement of outcome prediction.

The invention discloses a hepatocellular carcinoma patient prognosis combined prediction model and a construction method and application thereof. The construction method comprises the following steps: acquiring baseline clinical indexes and serum N-carbohydrate chain characteristic data of a patient; key clinical indexes and key glycomics markers are screened out through feature engineering; and fusing the screened features into a joint feature vector, training by using a Cox regression model, and constructing a joint prediction model capable of outputting a risk score and a corresponding risk hierarchical threshold. The invention further relates to an evaluation system based on the model, a storage medium and a kit applying the model. According to the method, the functional serum glycomics characteristics are introduced into prognosis prediction of the specific treatment scene for the first time, the defects that an existing prediction method is single in index and limited in precision are overcome through multi-dimensional information integration, more accurate individualized risk layering can be achieved, a reliable tool is provided for clinical treatment decision making, and the method has important clinical application value.

The invention discloses an acute myelogenous leukemia disulfide death gene related prognosis risk model construction method, which comprises the following steps: constructing a disulfide death gene related prognosis feature preliminary model: taking a TCGA-LAML data set as a training set, taking GSE12417 and GSE71014 queues as a verification set, combining a plurality of known disulfide death genes, and constructing the disulfide death gene related prognosis feature preliminary model; and determining a new disulfide death gene data set. And based on a stacking strategy, fitting the preliminary model of the prognosis characteristics related to the disulfide death with a plurality of gene models to obtain an expanded stacking model, and taking the expanded stacking model as a final prognosis model related to the disulfide death of the acute myelogenous leukemia patient. And in combination with a process strategy of data input-feature screening-machine learning training-risk output, the constructed double-sulfur death gene related prognosis features are expanded, and the prediction efficiency of the model is improved.

This invention discloses a method for constructing a gene methylation prognostic assessment model for differentiated thyroid cancer, characterized by the following steps: S1, obtaining a test sample; S2, extracting and storing DNA from the test sample; S3, performing methylation analysis; S4, constructing a prognostic classification model based on DNA methylation, calculating the risk value of the prognostic model as Risk Score = 0.15411928*cg03190661 - 0.10405129*cg15676916 + 0.06108015; S5, cross-validating to evaluate performance and obtain the gene methylation prognostic assessment model. This model uses the Risk Score to assess the prognosis of differentiated thyroid cancer: low-risk group, normal follow-up is recommended; medium-risk group, follow-up time can be reduced to half; high-risk group, close follow-up is required.

This invention discloses a prognostic model and construction method for cervical squamous cell carcinoma, belonging to the fields of bioinformatics and oncology. The construction method is based on a set of genes related to programmed cell death, integrating multi-omics data of cervical squamous cell carcinoma patients from The Cancer Genome Atlas (TCGA), Gene Expression Omnibus (GEO), and the Cancer Genome Characterization Project (CGCI). After standardized preprocessing, differential expression analysis, bootstrap resampling combined with univariate Cox regression for initial screening, consensus screening using multiple machine learning algorithms, and finally, multivariate Cox proportional hazards regression analysis to identify three core independent prognostic genes and construct a risk scoring model. This model has undergone multi-dimensional validation and optimization, demonstrating robust predictive performance. The method of this invention is standardized and highly reproducible, and the constructed model has high accuracy and strong generalization ability, providing a reliable tool for individualized prognostic assessment and clinical decision-making for cervical squamous cell carcinoma patients.

This invention relates to the field of medical imaging assessment technology, specifically a prognostic assessment system for liver cancer portal vein tumor thrombosis radiotherapy that integrates multiple MRI parameters. The system includes modules for MRI multi-parameter acquisition, data preprocessing, feature extraction, fusion assessment, dynamic updating, result output, and data storage. The system acquires MRI structural, functional, and temporal parameters. After preprocessing such as adaptive noise reduction, it extracts core features using an attention mechanism combined with CNN. An attention fusion algorithm integrates MRI features, radiotherapy dose, and clinical parameters. An improved algorithm is used to construct a prognostic model, which is dynamically optimized through transfer learning. The system outputs visualized prognostic results, treatment recommendations, and abnormal warnings, and the data is stored with encryption. This system addresses the problems of low assessment accuracy, lack of dynamic adjustment, and poor practicality in existing technologies, improving assessment accuracy and timeliness, providing reliable support for individualized radiotherapy decisions, and balancing data security with clinical research needs.

The application discloses a kind of adolescent depressive patient curative effect evaluation system based on electroencephalogram microstate, specifically relates to electroencephalogram microstate analysis technical field, including data acquisition module, data preprocessing module, data processing module, microstate analysis module, prognosis model construction module, emotion recognition module, curative effect evaluation module and man-machine interaction module;Through prognosis model construction module, emotion recognition module, based on correlation prognosis model, microstate is mapped to emotional state;Through curative effect evaluation module, calculate curative effect evaluation index, obtain the curative effect evaluation result of the adolescent depressive disorder of the to-be-measured adolescent with attempted suicide behavior;Through man-machine interaction module, user can understand the real-time emotional state of adolescent, curative effect evaluation index and curative effect evaluation effect, to comprehensively, accurately and conveniently evaluate the brain stability and adaptability of treatment maintenance period adolescent depressive disorder patient.

The invention discloses a method for analyzing an action mechanism of a plasticizer acetyl tri-n-butyl citrate (ATBC) for inducing breast cancer based on network toxicology. The method comprises the following steps: firstly, integrating multiple databases to obtain and standardize ATBC targets, and identifying disease-related genes in combination with differential expression of TCGA data and weighted gene co-expression network analysis (WGCNA); overlapping target spots are obtained through intersection of the three, a protein interaction network is constructed, and function enrichment analysis is carried out. TCGA is used as a training set, GEO is used as a verification set, random forest and Lasso regression are combined to screen out core targets MAOA and ADRA2A, and a prognosis model is constructed. And finally verifying that the ATBC can be stably combined with the two target spots through molecular docking (the combination energy is 1t;-5.0 kcal / mol). According to the invention, a full-process scheme from target prediction, function analysis, machine learning screening to molecular docking verification is established, and a standardized normal form is provided for the study of the carcinogenic mechanism of environmental chemicals.

The invention discloses a colorectal cancer multi-target prognosis risk assessment model construction method based on palmitoylation related lncRNA, and relates to the technical field of colorectal cancer prognosis model construction. The method comprises the following steps: step 1, data acquisition; step 2, identifying lncRNA (long non-coding ribonucleic acid) related to S-palmitoylation; step 3, determining a key lncRNA (long non-coding RNA) for constructing a prognosis model; 4, establishing a risk scoring model; and 5, testing the prognosis model. Based on a TCGA database, palmitoylation related genes and CRC transcriptome data are integrated, lncRNA significantly related to the palmitoylation related genes and the CRC transcriptome data is screened through co-expression analysis, and a multi-target prognosis risk assessment model based on the palmitoylation related lncRNA is constructed. And further model testing and mechanism exploration, immune infiltration and mutation load evaluation, drug sensitivity prediction and the like are carried out, so that a more accurate prognosis evaluation tool is expected to be provided for CRC patients, the development of mechanism-driven individualized treatment strategies is promoted, and the method has important significance in improving treatment of the patients and increasing the survival rate.

This invention discloses the application of Tiaoqi Jiedu Tongyou granules in the preparation of anti-esophageal cancer drugs targeting the IL1B / AHR / PSMD3 axis, belonging to the field of biomedical technology. Experiments have demonstrated that Tiaoqi Jiedu Tongyou granules can significantly downregulate the expression of IL1B, AHR, and PSMD3 proteins in cisplatin-induced esophageal cancer cells, inhibit cisplatin-induced treatment-related aging and aging-related secretory phenotypes, reduce the secretion of IL-6, IL-8, CXCL2, and TNF-α, and inhibit cell proliferation, migration, and invasion in a concentration-dependent manner. It can intervene in high-risk esophageal cancer patients identified by the IL1B / AHR / PSMD3 trigene prognostic model. This invention also discloses an anti-esophageal cancer drug containing the active ingredients of the granules and pharmaceutically acceptable excipients, which can intervene in high-risk esophageal cancer patients identified by the IL1B / AHR / PSMD3 trigene prognostic model. This invention provides a new drug intervention pathway for aging-related inflammation and recurrence after esophageal cancer chemotherapy, and has significant clinical application value.

The present invention provides a method for diagnosing or predicting the prognosis of hepatocellular carcinoma in a mammal or human subject by detecting ALAS1 or a combination of ALAS1 and TXNRD1. The invention also provides kits and instruments for diagnosing or predicting the prognosis of hepatocellular carcinoma in mammals or human individuals by detecting said proteins. The invention provides a novel double-gene hepatocellular carcinoma prognosis model containing the ALAS1 and the TXNRD1. The double-gene hepatocellular carcinoma prognosis model comprises the ALAS1 and the TXNRD1.

The application provides a lung adenocarcinoma prognosis marker and model, a lung adenocarcinoma prognosis model based on programmed cell death (PCD) related mRNA and lncRNA is constructed, and the biological function of the lncRNA model in lung adenocarcinoma is explored through bioinformatics analysis and experiments. The prognosis model covers all PCD pathways and various molecules, has a robust prognosis prediction accuracy, and can provide potential molecular targets for personalized treatment. The method of the application comprehensively constructs a lung adenocarcinoma diagnosis model suitable for Chinese population by using PCD related mRNA and lncRNA, enhances the recognition ability of tumor patient classification from multiple aspects, improves the accuracy and reliability of prognosis prediction, can provide strong support for promoting the personalized treatment strategy of lung adenocarcinoma patients, and is suitable for popularization and application.

The invention relates to a construction method of a triple negative breast cancer prognosis model based on a macrophage gene, which sequentially comprises the steps of data acquisition and pretreatment, macrophage characteristic gene capture, consensus clustering and gene pool construction, model construction and performance evaluation, variable importance sequencing, external verification and clinical value and the like. Through integration of transcriptome data, clinical information and macrophage related gene expression characteristics of a patient, a high-precision, nonlinear and interpretable survival prediction model is constructed, and scientific screening of treatment response crowds is realized. In addition, the invention also relates to application of the prognosis model constructed by the method in preparation of products for predicting prognosis risk, immunotherapy or chemotherapy sensitivity of triple negative breast cancer patients.

The invention discloses a lung adenocarcinoma prognosis prediction method based on machine learning. RNA transcription data and clinical information of a lung adenocarcinoma patient are collected from a database, and a data set is constructed; performing gene expression data preprocessing and difference analysis to obtain differential expression genes; sequencing the risk coefficients of the differential genes by using single-factor COX analysis; carrying out survival related feature recognition on the screened genes by virtue of eight machine learning algorithms related to survival analysis to obtain related genes with prognosis values; a machine learning combinatorial algorithm is utilized to train multiple prognosis models, C-index average values of the prognosis models are calculated and compared, and an optimal StepCox-RSF algorithm is selected to carry out patient layering and prognosis prediction model construction according to feature genes; according to the risk score of the patient, predicting the total survival rate and the risk grouping condition of the patient; according to the method, the reflecting capacity of the model to the immune microenvironment is remarkably improved, the prediction precision is optimized, and a scientific basis is provided for personalized treatment of lung adenocarcinoma patients.

This invention discloses a risk stratification assessment model, device, and construction method for RUNX1::RUNX1T1-positive children with acute myeloid leukemia. The construction method includes: acquiring sample clinical data; assessing the correlation between clinical predictors and overall survival (OS) and event-free survival (ORS); for continuous variables, determining the optimal risk cutoff value for predicting poor prognosis; converting the continuous variables into binary variables; performing univariate Cox proportional hazards regression analysis to screen for factors significantly associated with OS and ORS; and incorporating these factors into a multivariate Cox proportional hazards regression model to confirm independent prognostic factors. This invention systematically integrates the clinical variable MRD1 and the percentage of peripheral blood blasts at diagnosis as core predictors, constructing a model capable of accurately assessing ORS. + A prognostic model for pAML risk was developed and rigorously validated. This model demonstrated superior predictive performance, effectively and accurately identifying patients with a high actual risk of relapse and death from the traditionally low-risk patient population.

This disclosure relates to the field of computer-aided healthcare, providing a deep learning-based prognostic method, device, and electronic device for AECOPD comorbid with depression. The method includes: acquiring inpatient and post-discharge data of sample patients with AECOPD and depression; inpatient data including examination data upon admission and upon discharge, including peripheral blood serum neuroactive substance data and peripheral blood inflammatory marker data; and post-discharge data including the interval between the first occurrence of CID-C after discharge, the number of CID-C occurrences within 6 months after discharge, and the probability of CID-C occurring within 90 days after discharge; generating training samples based on the inpatient and post-discharge data, and storing the training samples in a training dataset; training a prognostic model using the training dataset; and performing prognostic analysis on target patients with AECOPD and depression using the trained prognostic model. The prognostic method provided by this disclosure can provide rapid and accurate prognosis for AECOPD comorbid with depression.

This invention provides a prognostic gene for EGFR-mutant lung adenocarcinoma and a prognostic model constructed from it. Specifically, this invention provides a method for analyzing and identifying prognostic-related genes in EGFR-mutant lung adenocarcinoma, thereby identifying a group of genes strongly associated with the prognosis of EGFR-mutant lung adenocarcinoma, and using these prognostic genes to construct a scientifically validated and reliable prognostic model, providing a reliable clinical basis for precision medicine in cancer.

The application relates to the technical field of medical information processing, and discloses a tumor prognosis model training method and system based on transdifferentiation related genes, which comprises the following steps: step 1, acquiring gene expression, clinical characteristics and survival follow-up data, and extracting transdifferentiation gene expression data; step 2, determining transdifferentiation gene normalization relative order values; step 3, determining a starting plasticity end index, a blood vessel acquisition end index and a transdifferentiation direction index; step 4, determining a microenvironment consequence index, coupling strength and a synergistic enhancement item; step 5, performing consistency screening to obtain a stable transdifferentiation characteristic gene set; step 6, performing constraint training to obtain a prognosis model weight parameter and a trained tumor prognosis model; and step 7, calculating a final prognosis risk score, determining an optimal risk classification threshold, and obtaining a risk stratification result. The application realizes the generation of a tumor patient prognosis risk score and a risk stratification result.

The disclosure belongs to the field of genetic testing and biomedicine, relating to a method for constructing a prognostic model of hepatoma and an application thereof, comprising 1) obtaining and identifying fibroblasts with high FAP expression; 2) obtaining and identifying TAMs; 3) analyzing co-localization between fibroblasts with high FAP expression obtained and the TAMs obtained previously; 4) communicating and analyzing the fibroblasts with high FAP expression after the localization in the Step 3) with TAMs to obtain CCC ligand-receptor genes; 5) screening the CCC ligand-receptor genes obtained previously based on machine learning to obtain key CCC ligand-receptor genes; and 6) constructing a prognostic model of hepatoma according to the key CCC ligand-receptor genes obtained in the Step 5). The present disclosure provides a method for constructing a prognostic model of hepatoma that can be applied to auxiliary judgment of the prognosis of hepatoma patients and an application thereof.

This invention provides a method and system for establishing a prognostic model for traumatic brain injury (TBI) based on multimodal data fusion and AI, belonging to the field of medical artificial intelligence technology. The method includes collecting patient clinical text and CT image data, performing preprocessing, extracting clinical text features and image data features, and constructing three major models: a TBI prognostic prediction model, a clinical model of the predictive efficacy of edema expansion on TBI prognosis, and a TBI cerebral edema expansion prediction model. The final output of the prognostic model prediction results includes patient risk stratification results, neurological function prognostic prediction results, and cerebral edema expansion prediction results. The system includes a data acquisition module, a data preprocessing module, a feature extraction module, a multimodal model construction module, and a result output module. This invention can accurately achieve risk stratification and prognostic prediction for TBI, effectively improving the accuracy and efficiency of diagnosis and treatment, reducing the risk of misdiagnosis and missed diagnosis, and providing strong support for improving patient prognosis.

The invention discloses a prognosis model for predicting cervical cancer based on autophagy-related genes and a construction method of the prognosis model, and belongs to the technical field of biomedicine. The model contains four characteristic genes related to prognosis of cervical cancer: BCL2, SPNS1, TM9SF1 and TP73, and the characteristic genes can become biological markers related to cervical cancer; the calculation formula of the prognosis model is as follows: risk score = (-0.411 * BCL2 gene expression quantity) + (0.753 * SPNS1 gene expression quantity) + (0.669 * TM9SF1 gene expression quantity) + (-0.398 * TP73 gene expression quantity). The prognosis model provided by the invention can evaluate the prognosis of the cervical cancer patient, improve the prognosis prediction capability of the cervical cancer patient, effectively identify the high-risk patient, assist in predicting the curative effect of immunotherapy, detect and intervene the high-risk patient earlier in clinic, improve the survival rate and life quality of the patient, and improve the clinical application prospect. A reference is provided for individualized diagnosis and treatment of cervical cancer; and tests and external verification prove that the model is stable and effective.

The application comprises a RAS gene cluster-based pediatric AML prognosis model construction method, which relates to the cross field of bioinformatics and medical technology. It comprises: S1: data acquisition and integration, standardization and integration processing of expression data; S2: sample typing, obtaining at least two subtypes with different prognoses; S3: prognosis model construction; S4: clinical correlation verification, constructing a visual prognosis evaluation system integrating risk stratification and clinical characteristics; S5: immune infiltration correlation verification, establishing the correlation between risk stratification and immune infiltration characteristics; S6: drug sensitivity correlation verification, determining the correlation between risk stratification and drug sensitivity; S7: key gene verification. The application realizes the precise risk stratification of pediatric AML patients by integrating RAS signal pathway gene characteristics and clinical data, and the prognosis model is verified by training set and verification set, which provides a standardized scientific research model framework and reliable data support, and provides an efficient auxiliary tool for pediatric AML related scientific research.

The invention provides a laryngeal cancer / hypopharyngeal cancer prognosis prediction method based on a machine learning model, and belongs to the technical field of biomedicine and machine learning. The method comprises the following steps: S100, acquiring a reference laryngeal cancer / hypopharyngeal cancer prognosis prediction model; s200, acquiring a second number of case samples of the second type of laryngeal cancer / hypopharyngeal cancer patients; s300, based on the similarity, endowing a plurality of case samples of the first-class laryngeal cancer / hypopharyngeal cancer patients with different weights; s400, performing secondary training on the reference laryngeal cancer / hypopharyngeal cancer prognosis prediction model based on a second number of second-class laryngeal cancer / hypopharyngeal cancer patient case samples and the first-class laryngeal cancer / hypopharyngeal cancer patient case samples endowed with different weights or different weights to obtain a retraining model; s500, performing laryngeal cancer / hypopharyngeal cancer prognosis prediction based on the retraining model; accurate training and application of the laryngeal cancer / hypopharyngeal cancer prognosis model can be achieved through machine learning and migration training under the condition that the number of target type patient samples is insufficient.