32 results about "Predictive factor" patented technology

The invention provides a construction method and a construction system of a chronic lymphocytic leukemia prediction model based on machine learning, electronic equipment and a storage medium, and relates to the field of chronic lymphocytic leukemia prognosis research. The construction method comprises the steps of obtaining original sample data, and performing preliminary screening; performing data cleaning on the screened sample data; determining a prediction factor from the plurality of features of the cleaned sample data; dividing the cleaned sample data corresponding to the prediction factor and the target variable into a training set and a test set; inputting the training set after unbalance processing into a LightGBM model for training to obtain a prediction model; inputting the test set into a prediction model, performing hyper-parameter optimization on the prediction model, and evaluating the performance of the prediction model; calibrating the prediction model to obtain a calibrated prediction model; the method has the beneficial effects that the method can be realized only by depending on conventionally available predictive factors, and the patient screening can be realized before the CLL clinical symptoms appear.

The present invention relates to a system and a method for monitoring mental health and generating personalized reports. According to one embodiment of the present invention, the method for monitoring mental health and generating personalized reports comprises: receiving a user's response data to a self-report questionnaire, wherein the self-report questionnaire comprises questionnaires corresponding to the respective mental health scales; and generating a report on the user's mental state based on the response data to the self-report questionnaire. The mental state report includes a personalized mental health graph that visualizes daily scores for each mental health scale in the form of a bar chart.The bar charts included in the personalized mental health graphic can be displayed in colors that are predetermined according to criteria for the respective mental health scale. According to the present invention, it is possible to capture psychological, biological, and social digital phenotypes of groups with non-suicidal self-harm via the self-report questionnaire and thereby investigate predictive factors related to these phenotypes.

The invention provides an extreme weather power load prediction method and system, and the method comprises the steps: obtaining historical data, and determining a basic load in extreme weather according to the historical data; constructing a total load decomposition model, stripping initial estimation of a basic load and a random load in the total load according to the total load decomposition model, and obtaining a meteorological load mid-value through multiple regression fitting; according to the meteorological load median, screening core meteorological factors through improved grey correlation analysis, and combining stepwise regression screening and extreme value adaptation correction to obtain an accurate meteorological load; constructing a comprehensive predictive factor set according to the precise meteorological load; and inputting each prediction factor of the comprehensive prediction factor set into the trained improved BP neural network model, and outputting a power load prediction value in extreme weather, thereby effectively improving meteorological load separation precision and extreme weather load prediction precision.

The invention relates to the technical field of data prediction, and discloses a colorectal progression stage adenoma data prediction method and system based on machine learning, a terminal and a storage medium, and the method comprises the steps: screening out a corresponding candidate prediction factor according to the colorectal progression stage adenoma data of each target sample; and dividing the candidate prediction factors into a training set and a verification set, constructing a target machine learning model by using the training set, inputting the verification set into a plurality of decision trees of the target machine learning model, outputting an original prediction probability, and converting the original prediction probability into a classification probability to obtain a prediction result. According to the method, an efficient, explainable and visual machine learning early warning model is utilized, a visual decision path is generated, conventional non-invasive indexes can be effectively integrated, and individualized prediction of colorectal progression stage adenoma data is achieved.

This invention relates to the field of intrinsic ability prediction technology and discloses a method for predicting the intrinsic ability characteristics of the elderly based on machine learning. First, intrinsic ability score data of the elderly in five dimensions, including cognition and psychology, are acquired, and heterogeneity classification is performed using latent profile analysis. Using the classification results as labels, random forest and LASSO regression are used in parallel to screen key predictive factors to form a feature subset. A classification prediction model is built based on XGBoost, and hyperparameters are optimized through cross-validation and grid search. The SHAP and LIME algorithms are integrated to achieve both global and local interpretability. Finally, the model is deployed on an online interactive platform, where inputting individual characteristics outputs the IC propensity classification, probability, and feature contribution explanation. This invention achieves accurate classification and interpretable prediction of the intrinsic abilities of the elderly, reduces the dependence of assessment on professionals and the environment, and is suitable for large-scale application in grassroots elderly care scenarios.

This invention discloses a machine learning model integrating oral microbiome and clinical features and its application in predicting sarcopenia at high altitudes. The method targets high-altitude populations residing at altitudes >3500 meters, collecting oral microbiome 16S rRNA sequencing data, clinical features, and lifestyle data. Core predictive factors are selected through adaptive preprocessing and elastic network regularized regression, and a classification model is constructed using logistic regression. To address the sample imbalance problem in high-altitude areas, this scheme introduces a synthetic balanced sampling strategy based on target distribution doubling; simultaneously, Platt Scaling is used for two-layer probability calibration, combined with a dynamic threshold optimization mechanism based on F1-Score to improve discrimination accuracy. This invention is the first to integrate oral microbiome shaped by the high-altitude environment (such as…)… Selenomonas , Veillonella (etc.) are incorporated into the predictive model. Experiments show that the model achieves an AUC of 0.868 on the independent test set and has advantages such as being completely non-invasive, low-cost, and highly interpretable. This invention provides an efficient early screening program for sarcopenia in resource-scarce high-altitude areas.

The invention relates to the technical field of medical artificial intelligence, and particularly discloses a method for establishing a disease prediction model of GCK-MODY in gestational diabetes population based on machine learning. The model takes five clinical characteristics as input variables: a body mass index before pregnancy, fasting blood glucose and glycosylated hemoglobin levels during GDM diagnosis, continuous multi-generation diabetes family history and a newly discovered predictive factor, namely GDM diagnosis week of pregnancy. A classification model is constructed through a support vector machine algorithm, and a SHapley additive interpretation method is adopted to provide global and local interpretation of a prediction result, so that model transparency is enhanced. The area of the model under a curve in a test is obviously superior to that of an existing screening standard. The invention also provides an electronic device, a storage medium and a prediction system comprising the model, which can assist clinicians in early recognition of GCK-MODY high-risk patients, provide decision support for targeted gene detection, avoid unnecessary enhanced hypoglycemic treatment of pregnant women, reduce the risk of maternal and infant complications, and promote precise medical development of gestational diabetes mellitus.

The invention discloses a pregnancy individualized medication dosage prediction factor screening method, a prediction model construction method and a prediction system, and relates to the technical field of medicine. Factors which are obviously related to blood concentration and have no obvious multicollinearity among variables are screened out from factors influencing pregnancy drug dosage to serve as drug dosage prediction factors, and a corresponding prediction model and system are constructed. According to the screening method, the prediction model construction method and the prediction system provided by the invention, auxiliary decision making can be provided for individualized drug dosage during pregnancy.

This invention discloses a method and related equipment for predicting and intervening in the risk of stillbirth related to umbilical cord torsion. The method acquires multimodal clinical data, including the pregnant woman's complaints and prenatal ultrasound examination information, and standardizes the data to extract core predictive factors such as changes in fetal movement, signs of umbilical cord root torsion, and fetal growth restriction, as well as auxiliary predictive factors such as abnormal amniotic fluid volume and abnormal placental-umbilical cord insertion, constructing a feature vector that the model can process. Based on a pre-trained risk prediction model, the risk of stillbirth related to umbilical cord torsion is quantitatively assessed, a comprehensive risk score is output, and risk levels are classified. Based on the risk level, a pre-set clinical intervention strategy is automatically matched to form standardized treatment recommendations, which are then output to the clinical terminal. This method overcomes the limitations of traditional methods that rely on low sensitivity of single ultrasound diagnosis, achieving early risk identification and tiered management.

This invention discloses a method for predicting the glycemic index (GI) of oat products in vitro, belonging to the field of food testing technology. This invention systematically integrates multi-dimensional data on the nutritional components, structural characteristics, and in vitro digestion kinetics of oat products. Using machine learning algorithms such as Bayesian ridge regression, it screens out five key predictive factors: β-glucan content, damaged starch content, median particle size, aleurone layer thickness, and 180-minute hydrolysis index. Combined with in vivo GI measurements, a high-precision prediction model is constructed through nonlinear regression fitting. This invention transforms the complex GI formation mechanism into a clear and measurable quantitative relationship, providing an efficient and low-cost technical solution for the rapid development, process optimization, and quality control of low-GI oat products, and has clear industrial application value.

The invention provides a 30-day death rate prediction device and method for cerebral hemorrhage patients, equipment, a medium and a program product, relates to the technical field of medical biology, and analyzes data in MIMIC and eICU-CRD databases. And performing feature selection by using Lasso regularization, mutual information and recursive feature elimination (RFE). And training to obtain a prediction model, and performing internal verification and external verification by applying comprehensive performance indexes. The feature importance is interpreted using an SHAP value. Determining key predictors includes acute physiological score III (APSIII), age, leukocyte (WBC), and albumin level. Compared with traditional scoring systems such as GCS and APSIII, the model shows higher prediction accuracy in the aspect of predicting the death rate in 30 days, and has more balanced sensitivity and specificity. The machine learning method provided by the embodiment of the invention shows a promising prognosis value in the aspect of predicting the 30-day death risk of ICH patients received by ICU. It needs to be noted that the models can only serve as supplementary judgments and cannot replace clinical judgments.

The present invention relates to a method for providing information for predicting therapeutic responsiveness or prognosis to transarterial chemoembolization. The gut microbiota of the present invention serves as a biomarker for predicting therapeutic responsiveness or prognosis to transarterial chemoembolization in patients with liver cancer. The gut microbiota of the present invention can be utilized as a potential predictive factor for clinical outcomes of transarterial chemoembolization, can also be used as an adjunct therapeutic target for treatment of liver cancer patients, and enables prediction of survival rates of liver cancer patients who have undergone transarterial chemoembolization. Accordingly, the biomarker of the present invention is expected to be usefully applied as a marker for predicting therapeutic responsiveness or prognosis to transarterial chemoembolization in patients with liver cancer.

This invention relates to the field of medical prediction technology, specifically to a method and system for constructing a prediction model for the occurrence of TMA (tumor homicide) in pediatric HSCT patients. The method involves acquiring sample data from each pediatric patient and grouping them; encoding variables according to coding rules; comparing the differences in variables between the TMA group and the non-TMA group to obtain the inter-group difference test results for each variable, thereby screening candidate variables; using the LASSO algorithm with an L1 regression model penalty term to screen the candidate variables and obtain key predictive factors; combining a logistic regression model and multiple machine learning algorithms into an initial occurrence prediction model and training it to obtain the final occurrence prediction model. The model constructed by this technical solution can predict based on the variables corresponding to the key predictive factors, and since the model is trained using pediatric sample data, it fully considers the special characteristics of pediatric patients, resulting in high accuracy in risk assessment.

The invention provides application of 73rd histidine methylation of serum actin as a marker in preparation of a reagent for assisting early prognosis evaluation of sepsis, and belongs to the technical field of biomarkers. Tests show that the 73rd site histidine of serum actin is subjected to methylation modification, and the differences among a Control group, a Survivor group and a Non Survivor group are remarkable; the secondary spectrum of the target peptide fragment shows that the peptide spectrum matching effect of the modified peptide fragment is good, and the modification identification is credible; and the area under the ROC curve and the 95% confidence interval are 73.56% (60.17%-82.68%). Under the optimal cutoff value of 30.29, the sensitivity is 0.792, the specificity is 0.639, the positive predicted value is 0.656, the negative predicted value is 0.780, the positive likelihood ratio is 2.198, and the negative likelihood ratio is 0.325. Therefore, the 73 histidine methylation of serum actin is an independent predictive factor of sepsis prognosis, can be used as a reliable and potential biomarker for early prognosis evaluation of sepsis, and has important clinical application value.

The invention relates to the technical field of elevator dispatching optimization, in particular to an elevator group control energy-saving dispatching method and system based on load prediction.The method comprises the steps that the actual passenger flow with the same time property as the current moment in elevator historical operation data is analyzed, and a first predictive factor is constructed; the method comprises the following steps: acquiring a pedestrian flow load, taking the pedestrian flow load as a reference prediction value, analyzing the similarity between the reference prediction value and all historical operation data, distributing contribution degree weight to the historical operation data of each day, constructing a second prediction factor, obtaining a pedestrian flow prediction value, and finally correcting the pedestrian flow prediction value in real time according to the difference between the pedestrian flow prediction value and the actual pedestrian flow load of the current day; and constructing an adaptive inertia weight of a particle swarm algorithm based on the human traffic prediction correction value, and searching an optimal solution to perform response scheduling. The invention aims to improve the dispatching efficiency of the whole elevator group.

This invention discloses a predictive model for early fever and infection after CAR-T therapy. The equation for this predictive model is: P = 1 / (1 + e^(-3.23 + 0.017 × CRP + 0.003 × IL - 6 - 0.023 × platelet count - 8.048 × lymphocyte count - 1.241 × FCV + 1.6146 × neutropenia grade)); where P is the probability of infection. P < 0.20 is defined as low risk, classified as CRS; 0.2 ≤ P ≤ 0.6 is defined as medium risk, requiring further testing to determine whether it is infection or CRS; P > 0.6 is defined as high risk, classified as infection. This predictive model is used to predict the likelihood of infection in the first fever event after CAR-T therapy. By analyzing various clinical laboratory indicators and combining logistic regression analysis, the model screens out key predictive factors related to infection risk, ultimately establishing an efficient and easy-to-use predictive tool. This model can effectively predict the occurrence of infection, provide clinicians with guidance for early intervention, reduce unnecessary clinical testing, and optimize patients' treatment plans.

The present application relates to a kind of vertebral body fracture postoperative secondary fracture risk prediction model, construction method and prediction system, including the multidimensional data of collection research object;The multidimensional data of the research object meeting the requirements is standardized pre-processing;Fractured vertebral body positioning sub-network is constructed, and the output ROI of injured vertebra is input into image parameter measurement sub-network, and the output result is converted to obtain standardized image parameter set;Standardized image parameter set and clinical data are merged, and independent predictive factor is screened;Based on independent predictive factor, the risk prediction model of vertebral body fracture postoperative secondary fracture based on nomogram is constructed.The present application realizes the automatic, standardized extraction of multimodal image parameters by cascading CNN network, integrates multi-center patient baseline data, surgery-related data and postoperative nursing data, and can be used for accurately predicting the risk of secondary OVCF within 2 years after operation by feature screening and model construction;Solve the problems of poor generalization, strong subjectivity and insufficient patient compliance in the prior art.

This invention discloses a method for constructing a predictive model for heart failure and all-cause mortality risk in patients with chronic kidney disease (CKD). It relates to the field of model construction technology, and its key technical points are as follows: This invention uses G3a-G5 stage CKD patients with preserved ejection fraction as the research subjects, establishes a prospective cohort, collects clinical indicators, biomarkers, and quality of life scores, and uses new-onset heart failure combined with all-cause mortality as the composite endpoint. After standardized follow-up and data preprocessing, univariate Cox regression, Lasso, random forest, XGBoost combined with Venn diagrams are used to screen predictive factors. Age, lipoprotein(a), ferritin, GDF15, and EQ-5D quality of life score are identified as independent predictors. A time-dependent nomogram model is constructed, and multi-dimensional efficacy validation is performed. This model is adapted to the specific pathophysiological state of CKD, with accurate predictions and good calibration. With accompanying online interactive tools, it can achieve individualized risk assessment and stratified intervention for 24-36 months, solving the problems of poor applicability and inaccurate prediction in existing models, and has strong clinical applicability.

This invention discloses an artificial intelligence deep learning model for predicting the sensitivity of neoadjuvant chemotherapy in colorectal cancer, belonging to the field of colorectal cancer treatment prediction technology. Its key technical points include the following steps: S1, data collection; S2, patient grouping; S3, screening predictive factors; S4, artificial neural network modeling; and S5, model validation. This invention successfully screens common clinical indicators for predicting the sensitivity of neoadjuvant chemotherapy in colorectal cancer and constructs an artificial neural network risk prediction model. This model can be applied to clinical practice, providing predictions for the sensitivity of neoadjuvant chemotherapy in colorectal cancer, thereby assisting clinicians in achieving more accurate predictions of chemotherapy efficacy. This invention helps optimize clinical treatment strategies, promotes the development of individualized neoadjuvant therapy regimens for colorectal cancer, and provides new ideas and methods for precision medicine.

This application relates to the biomedical field and discloses a predictive model and validation method for ART virological failure in HIV / AIDS patients. The model construction method includes the following steps: S1, collecting clinical data from HIV or AIDS patients; S2, performing multiple imputation processing on the clinical data to generate multiple datasets; S3, using a stepwise regression method to screen predictive factors in each dataset; S4, synthesizing the datasets to determine the final predictive factors; S5, establishing a virological failure prediction model based on the final predictive factors. The predictive model constructed by this invention can serve as an effective tool for predicting the risk of ART virological failure in HIV or AIDS patients in clinical practice. The application of this model helps improve treatment effectiveness, optimize resource allocation, and ultimately improve patient treatment outcomes. Furthermore, by continuously collecting new patient data and re-evaluating model performance, the accuracy and practicality of the model can be further improved.

The invention relates to the technical field of molecular markers, in particular to application of ADAMTS-5 as a biomarker of calcified aortic valve diseases. Through comparison of ADAMTS-5 levels in serum of a control group (a patient without CAVD) and serum of a patient in a CAVD group, the ADAMTS-5 level in serum of a CAVD patient is found to be remarkably reduced, and the ADAMTS-5 level in serum of a severe CAVD group is particularly remarkably reduced, so that a biomarker for CAVD diagnosis is developed on the basis, and then ADAMTS-5 is confirmed to be an independent predictive factor of CAVD through verification and is not influenced by levels of blood fat, renal function and the like. In addition, a working characteristic curve of a subject confirms that the under-curve area (AUC) of the ADAMTS-5 in CAVD diagnosis is remarkably improved to 0.799 (95% confidence interval: 0.750-0.848, Plt, 0.001), and the ADAMTS-5 has good sensitivity and specificity.

The invention discloses a half-year drought event prediction method and system based on a sea-land gas physical quantity driving deep learning model. The method comprises the following steps: acquiring global reanalysis weft wind U, warp wind V, vertical wind speed OMEGA, surface pressure SP, sea temperature SST, temperature T, potential height GPH, outward long-wave radiation OLR, second-layer soil humidity SWVL and sea ice coverage SICOC data; the reanalysis data are integrated into day-by-day data, an atmosphere apparent heat source Q1 is calculated, and all variables are processed into standard distance flatness; extracting SST, SWVL, Q1, OLR, 200hPa RV and 100hPa GPH combination as predictive factors day by day in the past 180 days to hitherto; inputting the integrated prediction factors into a trained SimVP model, and predicting a global grid scale drought index in the next 180 days; inputting the drought index of the next 180 days into the three-dimensional DBSCAN model to generate a three-dimensional drought event drought body; and extracting regional drought events, and generating a drought frequency diagram. According to the invention, real-time prediction of the drought event can be realized more quickly and more accurately.

The invention relates to the field of medical prediction, and discloses a method for constructing a risk prediction model for children live liver transplantation recipients to return to ICU (Intensive Care Unit), which comprises the following steps of: incorporating factors possibly related to children liver transplantation recipients to return to ICU through literature research and expert consultation; general information of a child liver transplantation recipient, ICU hospitalization information and operation related information are obtained, and ICU intraday blood examination information and immunosuppressor drug concentration are transferred out; and screening variables related to the return ICU by adopting single-factor Cox regression. Carrying out regression on the single factor Cox to obtain plt; and introducing a variable of 0.05 into multi-factor Cox regression analysis, screening a model based on an AIC criterion, determining independent prediction factors influencing the outcome, and drawing a column graph. According to the method, a time-dependent ROC curve, a calibration curve, a consistency index and a clinical decision curve are adopted to evaluate the line graph, a bootstrap method is adopted for internal verification, and the process is repeated for 1000 times.

A method, model, and system for screening predictive factors of perioperative hypoglycemia during gastrointestinal endoscopy, relating to the field of medical technology, is disclosed. This method employs univariate analysis and multivariate logistic regression to screen seven statistically significant factors from various factors influencing perioperative hypoglycemia during gastrointestinal endoscopy, defining these as hypoglycemia predictive factors. These seven factors are: blood urea nitrogen, preoperative blood glucose, glycated hemoglobin, nutritional status, laxative use, diagnostic category, and diastolic blood pressure. The outcome event of the predictive model is set as whether the patient experiences perioperative hypoglycemia, and the input factors are the seven screened hypoglycemia predictive factors. The predictive system includes a data input module and a hypoglycemia prediction module, with the hypoglycemia prediction module containing a built-in hypoglycemia risk prediction model. The model and system provided by this invention can provide hypoglycemia risk assessment for perioperative patients, assisting clinicians in decision-making.

The invention provides a primary lung cancer death risk prediction method based on multi-source data, and relates to the field of data processing, and the method comprises the steps: obtaining and associating multi-source heterogeneous data such as hospital treatment, laboratory inspection, image examination and disease control center death registration, and building a training database after cleaning and structuring; screening key predictive factors by adopting LASSO survival regression, constructing a multivariable survival regression model, and generating a score table; converting the baseline features of the patient into an initial death risk score based on a score table; carrying out distribution self-adaptive correction, feature coupling adjustment and risk self-feedback regulation and control in sequence so as to dynamically optimize the score; and finally outputting the adjusted death risk score and providing the adjusted death risk score for clinical use. According to the method, effective fusion of multi-source data and objective screening of key factors are realized, the accuracy, adaptability and interpretability of prediction are improved through a dynamic regulation and control mechanism, and visual and quantitative death risk assessment support can be provided for clinicians.

This disclosure relates to a method, apparatus, device, and medium for constructing a predictive model for adverse maternal and infant outcomes in pregnant women who are positive for anti-SSA / Ro and / or SSB / La antibodies. The method includes: acquiring a training set and multiple predictive factors related to adverse maternal and infant outcomes; performing regression analysis on each predictive factor based on the training set using a multivariate logistic regression analysis model to determine the regression coefficients of each predictive factor and construct a predictive model; plotting an ROC curve based on a pre-defined validation set and evaluating the predictive value of the predictive model based on the area under the ROC curve; and plotting a nomogram based on the predictive model if the predictive value reaches a pre-defined value. The nomogram includes: a score axis, a total score axis, and a risk probability axis for each predictive factor. This disclosure enables the construction of a predictive model that comprehensively considers the influence of multiple factors, improving the operability of the predictive model in clinical practice.

The present application relates to the technical field of disease risk prediction, in particular to a risk prediction method for adverse reactions and complications of resectable NSCLC neoadjuvant immunotherapy during the perioperative period based on nomogram and application. The method comprises the following steps: screening relevant variables by single factor Logistic regression; introducing the screened variables into multi-factor Logistic regression to determine independent prediction factors, and constructing a prediction model and a nomogram according to the independent prediction factors; and evaluating the model discrimination degree by using a ROC curve, and evaluating the model calibration ability by using a Hosmer-Lemeshow test and a calibration ROC curve. The neoadjuvant immunotherapy combined with chemotherapy has a significant treatment effect (MPR rate 51.43%, PCR rate 31.43%), the incidence of treatment-related adverse reactions is 58.57%, and the incidence of postoperative complications is 44.28%. Through multi-factor analysis, it is determined that erythrocyte sedimentation rate (> 20 mm / h), intraoperative blood loss (> 200 ml) and postoperative hospitalization time (> 1 week) are independent risk factors for perioperative complications, and the risk prediction model constructed according to the independent risk factors has good prediction performance.

The invention provides a living body prediction model for identifying the brain injury degree of a neonatal hypoxic ischemic brain injury (nHIBD) model mouse and a construction method of the living body prediction model, and belongs to the field of brain injury. According to the method, related data such as weight values and multi-dimensional behavioristics of the model mouse before and after nHIBD are acquired as predictive factors, and according to the result of the actual brain injury degree of the nHIBD model mouse, the function relationship between the brain injury degree of the model mouse and the predictive factors is innovatively established; through a prediction system combining an ordered multi-classification Logistic regression model and a statistical test system, the problem that after an nHIBD model is constructed, living model animals with the unified brain injury degree cannot be obtained, and then basic research results such as mechanism analysis and drug screening are affected is solved. According to the method, the limitation of single-factor analysis is broken through, the prediction accuracy is improved, a quantification tool with biological logic and statistical support is provided for early-stage in-vivo identification of different degrees of nHIBD brain injuries in basic research, and then support is provided for subsequent research.

The invention relates to a method for establishing an isolated pulmonary nodule malignancy probability prediction model, which comprises the following steps of: acquiring basic information of a patient and tissues of suspicious pulmonary nodules, dividing the patient into a modeling group and a verification group in combination with a CT (Computed Tomography) imaging report, setting clinical variables, applying Logistic regression to significant factors of the modeling group to obtain independent prediction factors of a solid SPN (Specific Patient Nodule), and establishing a model for predicting the malignancy probability of the solid SPN. Establishing an SPN malignant probability prediction model, namely an XJTUFAH model; the invention further provides a method for comparing the malignant probability prediction rate of the isolated pulmonary nodules by using the XJTUFAH model with the Mayo model, the VA model and the PKUPH model, case data of a verification group are respectively input into the established XJTUFAH model, the Mayo model, the VA model and the PKUPH model, an ROC curve is drawn, the area AUC under the curve, the sensitivity and the specificity of a quantitative system are estimated, and then SPSS20.0 software (IBM, Armonk, Erk) is used for calculating the malignant probability prediction rate of the isolated pulmonary nodules. NewYork) is subjected to statistical analysis, and prediction rates corresponding to the four sets of models are calculated. The method is high in comparison data accuracy of the prediction rate, and is simple and easy to implement.

This invention relates to the field of medical data processing technology, specifically to a method and system for constructing a cervical metastasis prediction model for T1 stage oral squamous cell carcinoma. Addressing the problems of existing technologies, such as the difficulty in accurately assessing the risk of occult lymph node metastasis in T1 stage patients preoperatively, the decreased discrimination and calibration of existing models due to mixed staging, and the lack of intuitive and usable tools, this application constructs a cervical metastasis prediction model for T1 stage oral squamous cell carcinoma. The specific construction method is as follows: Obtaining the subject's characteristic data; using the occurrence of cervical lymph node metastasis as the dependent variable, performing univariate logistic regression analysis on the independent variables of the characteristic data to determine candidate risk factors; performing multivariate logistic regression analysis on the obtained candidate risk factors to screen independent predictive factors; constructing a nomogram based on the independent predictive factors, and predicting the risk of cervical lymph node metastasis in T1 stage oral squamous cell carcinoma patients based on the nomogram.