67 results about "Area under the curve" patented technology

The invention discloses a construction method of a model for predicting an esophageal squamous cell carcinoma intervention effect. The construction method comprises the following steps: acquiring detection data of a predictive factor in a sample; the predictive factors at least comprise the content or the expression level of a depletion marker of a functional CD8 T cell in a sample and the content or the expression level of a C1QC + macrophage immune checkpoint molecule; and predicting the intervention effect of the esophageal squamous cell carcinoma according to the detection data of the predictive factor. Establishing a space proteomics map of a complex space tissue of a tumor microenvironment (TME) during treatment; key spatial features which are related to specific cell behaviors and influence treatment results are determined and layered; a powerful prediction model of drug response is developed by utilizing a machine learning technology, and the area under curve (AUC) can reach 97%.

The invention discloses application of a reagent for detecting a predictive factor in preparation of a product for predicting an intervention effect of a patient with esophageal squamous cell carcinoma. The reagent for detecting the predictive factor comprises a reagent for detecting the content or expression level of a depletion marker of functional CD8 T cells in a sample and a reagent for detecting the content or expression level of immune checkpoint molecules of C1QC + macrophages in the sample. According to the method, key spatial features which are related to specific cell behaviors and influence treatment results are determined and layered; a powerful prediction model of drug response is developed by utilizing a machine learning technology, and the area under curve (AUC) can reach 97%.

The invention discloses an application of Hsa-miR-24-3p in construction of a pancreatic ductal adenocarcinoma postoperative total lifetime prediction model. According to the invention, the expression of Hsa-miR-24-3p in preoperative serum of a PDAC patient is analyzed, and the total lifetime of a patient with increased level of Hsa-miR-24-3p (miR-24) is obviously reduced (Plt; 0.0001) of the method for manufacturing the same; multi-factor analysis shows that miR-24 is a prognosis factor independent of the age, gender and clinical pathological characteristics of a patient, and the prediction efficiency of miR-24 is remarkable; the area under the ROC curve reaches 0.82, which is superior to the area under the CA19-9 (0.61), the area under the CA125 (0.59), the area under the CA50 (0.51) and the area under the CEA (0.56); when the miR-24 and the TNM are staging, and the CA19-9 and the CA125 are integrated into the column diagram model, the prognosis prediction accuracy is further improved.

The invention discloses an arteriosclerosis risk prediction method, device and system and a storage medium, and the method comprises the steps: obtaining a genetic risk score, a blood glucose index and basic features of a crowd arteriosclerosis index, thereby constructing an arteriosclerosis risk prediction model; and drawing a working characteristic ROC curve of the testee and calculating an area AUC under the ROC curve to evaluate the discrimination degree of the model for predicting the arteriosclerosis risk of the testee. By adopting the technical scheme of the invention, arteriosclerosis high-risk groups of the middle-aged and elderly people can be accurately screened out, and overhigh disease burden of arteriosclerosis of the middle-aged and elderly people can be prevented and controlled. Genetic and non-genetic factors are simultaneously included to judge the possibility of suffering from arteriosclerosis of middle-aged and elderly people, so that the method has certain practical guiding significance for preventing and controlling arteriosclerosis in people with abnormal blood glucose index levels.

The invention relates to the technical field of medical diagnosis, in particular to a papillary thyroid carcinoma diagnosis method based on hsacirc0076710 and a kit. The invention provides a papillary thyroid carcinoma detection kit based on hsacirc0076710, the expression condition of circular RNA hsacirc0076710 in a living body can be accurately and rapidly detected, a new gene detection means can be provided for early diagnosis and prognosis of papillary thyroid carcinoma, meanwhile, the invention provides a papillary thyroid carcinoma diagnosis method based on hsacirc0076710, and the papillary thyroid carcinoma detection kit can be applied to diagnosis of papillary thyroid carcinoma. According to the method, diagnosis is carried out by detecting the expression level of hsacirc0076710 in a sample, the areas (AUC) under an ROC curve in tissue, a fine needle biopsy eluent and a serum sample are 0.851, 0.838 and 0.769 respectively, and the sensitivity reaches 83.7%-95.1%. Further analysis shows that the hsacirc0076710 has high expression and high expression of lymph node metastasis (OR = 3.21, plt; 0.001) and advanced TNM (stage III / IV), and can be used for early diagnosis and prognosis risk assessment of papillary thyroid carcinoma.

The application discloses a biomarker for diagnosing diabetic nephropathy and application thereof, and relates to the technical field of biological medicine. The biomarker for diagnosing diabetic nephropathy comprises urine MBP-1 or urine MBP-1 / urine creatinine. The urine MBP-1 or urine MBP-1 / urine creatinine biomarker has high identification efficiency: when the urine MBP-1 or urine MBP-1 / urine creatinine ratio is used for identifying DKD and NDRD, the area under the ROC curve (AUC) reaches 0.899, the sensitivity and the specificity are both higher than 0.85, and the two diseases can be efficiently distinguished. The method is non-invasive and convenient: only urine samples need to be collected, the risk of complications such as bleeding and infection caused by invasive operations such as kidney biopsy is avoided, the patient has high acceptance, repeated detection can be performed to dynamically track the disease condition, and special equipment is not needed, so that the method is convenient for clinical popularization and application. Through kidney tissue immunofluorescence verification, MBP-1 is deposited in a large amount in the glomerulus of DKD and is not deposited in NDRD, and thus the kidney local pathological change can be directly reflected.

The invention discloses a sepsis blood coagulation related prognosis marker gene and application thereof in preparation of sepsis prognosis prediction and diagnosis products, and belongs to the technical field of biology. The sepsis blood coagulation related prognostic marker genes are composed of WFDC1, FGFBP2, CX3CR1, GIMAP4, ELANE and DEFA4, and a prognostic scoring system (a sepsis prognostic risk prediction model) is further established based on the six sepsis blood coagulation related prognostic marker genes. A time-dependent ROC curve and multivariable Cox regression analysis show that the discrimination capability of six gene prognosis scoring systems developed by the invention on the total survival rate (OS) is superior to that of other clinical factors (age and gender), and the area under a three-week curve is not inferior to the area within one or two weeks; therefore, the prediction scoring system has lasting and relatively independent discrimination capability on the prognosis of the sepsis patient.

Provided are a detection reagent for acute graft-versus-host disease (aGVHD) and the use of the percentage of CD38+HLA−DR+CD8+ T cell as a biomarker for aGVHD. The present application has unexpectedly found that a proportion of the CD38+HLA−DR+CD8+ T cell in peripheral blood of a patient with aGVHD is significantly greater than that in peripheral blood of a healthy donor and a patient without aGVHD after transplantation. The receiver operating characteristic (ROC) curve analysis shows that the CD38+HLA−DR+CD8+ T cell has an area under the ROC curve (AUC) of 0.84, with a sensitivity of 80.8%, and a specificity of 75.0% when used in early diagnosis of aGVHD. Results indicate that the CD38+HLA−DR+CD8+ T cell is a marker for early diagnosis of aGVHD with a prominent diagnostic effect. The marker can guide the clinical medication.

The invention belongs to the technical field of biological detection, and particularly discloses a pair of echinococcosis detection markers based on serum circulating miRNA and application of the echinococcosis detection markers, the detection markers are a combination of miR-192-5p and miR-122-5p, the abundance of the miR-192-5p and the miR-122-5p in the serum of an echinococcosis patient is remarkably reduced, the miR-192-5p and the miR-122-5p are in negative correlation with echinococcosis infection, and the threshold values are 0.35 and 0.04 respectively. During detection, the relative expression level (taking caenorhabditis elegans miR-39-3p as an external reference) of caenorhabditis elegans miR-39-3p in serum is determined through qPCR, and the positive and negative properties are judged according to a threshold value; the area under the ROC curve of the marker combination reaches 0.97, and a double-blind test shows that the positive rate and the negative rate of human and mouse serum detection are 100%. The method solves the problems of missed diagnosis and misdiagnosis in existing echinococcosis detection, can be used for preparing a detection kit, realizes accurate detection, curative effect evaluation and prognosis management of echinococcosis, and has extremely high clinical application value.

The invention relates to a 177Lu-DOTATATE peptide receptor radionuclide curative effect prediction model and application thereof, the model is used for performing multicolor immunofluorescent staining on tissue slices of a neuroendocrine tumor (NET) patient, and the model at least comprises specific staining antibodies of cytokeratin (CK +) cells, CD8 cells and TIM-3 molecules; then carrying out image acquisition and analysis, and identifying two positive cells, namely CK < + > and CD8 < + > TIM-3 < + >; calculating an under-curve area difference AUC (CK) (CD8 + TIM-3 +) between an observation curve of a nearest neighbor distance accumulation function (G function) between CK + and CD8 + TIM-3 + and a Poisson distribution curve according to an R language software package, determining a response scoring formula and threshold division based on single-factor logistic regression of PRRT response degree of case data, and substituting the difference into the response scoring formula, and the response score can be used for curative effect prediction.

The invention relates to the technical field of biological information, and discloses a gastric cancer survival analysis method based on a deep learning multi-modal fusion model, and the method comprises the steps: collecting histopathologic images, gene expression data and clinical information data of a plurality of patients, carrying out the preprocessing of the histopathologic image data, and then generating a data set, dividing the data set into a training data set and a test data set according to 7: 3; inputting the training data set into a MulitDeepsurv model for training, and evaluating performance by adopting a consistency index and an area under an ROC curve to obtain a trained model; inputting the test data set into the trained model for testing to obtain a risk score; and analyzing the risk score by adopting a Kaplan-Meier curve to obtain a distribution diagram of high-risk and low-risk patients. The problem that it is difficult to extract effective prediction features from multi-modal data can be solved, and the accuracy of disease diagnosis and prognosis evaluation is improved.

The invention belongs to the technical field of bioinformatics and medical detection, and particularly relates to a marker combination for neuroblastoma (NB) noninvasive risk level grading, a prediction model, a prediction method and application thereof. The marker combination is used for determining the sex, determining whether the month age is greater than 18 months, determining whether plasma MYCN is amplified, determining whether tumors are metastatic, and determining the content of neuron-specific enolase and lactic dehydrogenase; a machine learning algorithm is used for constructing an NB noninvasive risk degree grading prediction model, the comprehensive performance of the random forest model is optimal, the area value under a subject working characteristic curve reaches 0.956, the sensitivity is 92.9%, the specificity is 82.1%, the accuracy rate is 87.5%, the Kappa value is 0.75, the F1 score is 0.881, and NB middle and low risk patients and NB high risk patients can be effectively distinguished; the NB non-invasive risk level grading prediction model constructed by the invention can quickly, accurately and non-invasively perform NB risk level grading, and has a relatively good clinical application value.

The application discloses a lung nodule diagnosis marker and application, and belongs to the technical field of biotechnology detection. The application provides the use of one or more of PLA2G6, PLA2G7, AKR1C1, AKR1C3, LTA4H and PTGER4 genes as biomarker molecules for diagnosing pulmonary sarcoidosis. The use of the biomarkers can assist biopsy and help diagnose related lung diseases. The genes for identifying sarcoidosis provided by the application have an accuracy rate (area under the ROC curve) of 96.5%, 90.9%, 89.1%, 87.5%, 87.2% and 85.8% for distinguishing healthy people, lung adenocarcinoma patients and pulmonary tuberculosis patients in sequence, and the comprehensive accuracy rate is 90.9%. The application collects a certain amount of clinical samples for research and verification, and the research results are in line with clinical practice, and have a good clinical application prospect.

The invention belongs to the field of neurological disease diagnosis, and provides a plasma lipid marker for diagnosing Alzheimer's disease and application thereof, and the plasma lipid marker is selected from one or more of PA 16: 016: 0, PE O-18: 022: 4, PE P-16: 022: 4, TG 46: 4-FA18: 2, LPC 22: 4, ChE 22: 4, ChE 22: 0, ChE 20: 2, ChE 18: 0, ChE 16: 1 and ChE 20: 1. According to the present invention, the area under the curve (ROC) of the Alzheimer's disease subject diagnosed by the 11 plasma lipid markers is up to 1, and the Alzheimer's disease patient and the healthy subject can be accurately distinguished; detection can be completed through a venous blood collection method, a traditional cerebrospinal fluid collection method with higher trauma is replaced, and low-trauma and low-cost large-range crowd screening of the Alzheimer's disease is facilitated.

The invention belongs to the technical field of biological medicines, and particularly relates to a group of markers for predicting serious adverse reactions of wide-period small cell lung cancer immune combined chemotherapy and application thereof. The biomarker combination is easy and convenient to sample, and biopsy tissue does not need to be provided. The total T cell percentage is CD3 + / CD45 +, the T cell toxic cell percentage is CD3 + / CD8 + / CD45 +, and the combined combination of the two can predict the occurrence of treatment-related adverse reactions greater than or equal to level 3 of a wide-period small cell lung cancer patient treated by ICI combined chemotherapy, and the combined prediction efficiency is superior to that of a single index. In the training set, the area under the AUC curve of the combined prediction model is 0.852, the optimal Cut-off value is 0.39, the sensitivity is 87.5%, and the specificity is 83.3%. In the constructed prediction model by applying independent external verification, the AUC of the combined prediction model is 0.847, the sensitivity of the model is 85.2%, and the specificity is 73.9%. The method has practicability, and provides precise treatment guidance for clinical medicine.

A protein marker panel for screening clinical futile recanalization (FR) in patients with large vessel occlusion-induced acute ischemic stroke (LVO-AIS) and use thereof are provided. The protein marker panel includes GUCA2A, CCL14, STAB1, and VSIG4. A combined diagnostic value of the protein marker panel is high, and receiver operating characteristic (ROC) curve analysis demonstrates an efficacy in distinguishing and screening FR patients, with an area under the curve (AUC) of 0.959, indicating desirable sensitivity and specificity. Such a protein marker panel shows promise as a significant indicator for clinical decision-making in FR evaluation.

The application discloses an intestinal microbial marker combination for cirrhosis diagnosis and application thereof, which is composed of 8 specific intestinal bacterial species. The application accurately identifies the core combination from 181 differential characteristics by performing metagenomic sequencing on fecal samples of cirrhosis patients and healthy controls, and combining random forest, LASSO regression and recursive feature elimination algorithms. The random forest diagnosis model based on the 8 markers realizes an excellent performance of area under curve (AUC) 0.841, sensitivity 84.3% and specificity 83.7% on a completely independent test set, and the performance does not decrease compared with the full feature model in the case of reducing the number of characteristics by 86.9%. The marker combination provided by the application is highly simplified and has strong discrimination, and provides a clear and efficient microbiological basis and technical scheme for developing a cirrhosis non-invasive diagnosis kit, a gene chip and other products based on intestinal flora.

The invention discloses a heart failure risk grading early warning method and system based on heterogeneous data fusion. The method comprises the following steps: synchronously collecting three types of heterogeneous data of high-frequency physiology, low-frequency subjective reports and event-driven behaviors of a patient; a dynamic weighted fusion architecture of a long short-term memory network LSTM and a gradient boosting decision tree GBDT is adopted for processing, and dynamic fusion is carried out through an attention mechanism; clinical key events such as unplanned re-admission and the like are used as feedback signals, and closed-loop optimization is performed on the model through a specific event-triggered local online incremental learning mechanism. In a multi-center prospective clinical research involving 1258 patients, the sensitivity of unplanned re-admission risk prediction within 30 days is improved to 0.92 + / -0.04 from 0.75 of a conventional optimization method, the AUC (area under a working characteristic curve) of a subject reaches 0.95, and an innovative technical scheme is provided for realizing accurate and dynamic extra-hospital heart failure risk management.

The invention provides a heart transplantation nutrition prognosis analysis system for a patient with dilated cardiomyopathy, three factors including prealbumin (PA), total bile acid (TBA) and NRS2002 score are incorporated into the analysis system, a corresponding algorithm is provided, and based on the algorithm, the optimal cutoff value of an undesirable outcome is predicted to be 0.121, the sensitivity is 72.9%, the specificity is 92.9%, and the area under a ROC curve (AUC) is 0.885 (95% CI: 0.802-0.967); when the absolute error of a calibration curve is 0.049, the HL goodness of fit test is equal to 6.134 (P is equal to 0.632 gt, 0.05), the net income threshold probability of DCA is 0.04-0.94, and the threshold probability of CIC is greater than 0.50, the prediction is highly consistent with the actual outcome. Meanwhile, the AUC value of the algorithm is obviously larger than that of other existing prediction methods, the algorithm can serve as a reliable tool for evaluating the postoperative adverse outcome risk of the patient in clinical practice, an important reference basis is provided for optimizing the individualized treatment strategy of the patient to be transplanted and perfecting the organ distribution scheme, and the accuracy and rationality of heart transplantation diagnosis and treatment can be improved.

This invention discloses a molecular diagnostic biomarker for amyotrophic lateral sclerosis (ALS) and its application. The ALS molecular diagnostic biomarker includes Ng and / or GP1bβ. This invention demonstrates that Ng and / or GP1bβ proteins are specifically and significantly upregulated in plasma. The area under the curve (AUC) for Ng alone in diagnosing ALS reaches 80.6%, the AUC for GP1bβ alone reaches 71%, and the AUC for the combined diagnosis of ALS by Ng and GP1bβ reaches 94%, with a specificity of 85%. Furthermore, Ng expression is significantly correlated with the progression of ALS, with a PCC of 0.57 (P-value = 3.4 × 10⁻⁶). ‑6 In particular, Ng expression was significantly correlated with the early progression rate of ALS (PCC = 0.45 (8.8 × 10⁻⁶)). ‑3 This indicates that Ng can also serve as a molecular diagnostic marker for the rate of ALS progression, used to predict patient survival.

The present application relates to a kind of biomarkers, which is selected from one or more of the following: UBR2, NPY4R, KLRF2, HABP2, GLP1R, DR1, RUNX2, ARHGAP5, LINC02135, DDHD1, MIR4523, TC2N.The biomarker is especially used for diagnosing stroke and differential diagnosis of cerebral hemorrhage.The present application screens 12 characteristic biomarkers to construct model, adopts receiver operating characteristic (ROC) analysis to evaluate the performance of model, uses sklearn to calculate area under curve (AUC), the sensitivity and specificity of model reach 0.898, 0.818 respectively, AUC value is 0.913;While differential diagnosis of cerebral hemorrhage, sensitivity and specificity reach 0.864, 0-854 respectively, AUC value is 0.909.The present application combines 5hmC modification spectrum of plasma evDNA and machine learning algorithm for the first time, the characteristic biomarker and / or model screened has the advantages of strong specificity and high sensitivity, overcome the problem of low efficiency and poor accuracy in the process of identifying stroke and cerebral hemorrhage in prior art.

The application belongs to the field of neurological disease diagnosis, and provides a plasma lipid marker for diagnosing Alzheimer's disease and an application thereof. The plasma lipid marker is selected from one or more of PA 16:0_16:0, PE O-18:0_22:4, PE P-16:0_22:4, TG 46:4-FA18:2, LPC 22:4, ChE 22:4, ChE 22:0, ChE 20:2, ChE 18:0, ChE 16:1, ChE 20:1. The area under the curve (ROC) of 11 plasma lipid markers for diagnosing Alzheimer's disease is as high as 1, which can accurately distinguish Alzheimer's disease patients from healthy subjects; the detection can be completed by a method of collecting venous blood, instead of a traditional method of collecting cerebrospinal fluid with higher trauma, and is helpful to realize low-trauma, low-cost mass screening of Alzheimer's disease.

The invention discloses a method for constructing a model for accurately predicting meningeal metastasis risk of non-small cell lung cancer based on plasma protein and application, and relates to the technical field of biological medicine. Aiming at the problems of late discovery and difficult diagnosis of NSCLC-LM, the inventor tries to adopt an Olink proteomics technology for the first time to know whether an LM risk exists or not in advance by detecting specific plasma protein of a patient in a relatively non-invasive manner, so that the patient is helped to find and treat early. Therefore, the inventor firstly collects blood samples of LM and nLM patients, then constructs a risk prediction model by using a training set, and finally judges the efficiency of the model through a verification set. A result shows that five specific proteins, namely FGF2, CD4, IL15, CXCL12 and PDCD1LG2, participate in model construction, the area under a queue curve is 0.8 or above, and the sensitivity and the specificity both reach relatively high levels. The invention has great significance in the fields of early diagnosis and screening of NSCLC-LM and the like.

The invention discloses a diabetes risk prediction method based on high-dimensional disease embedding and health data fusion. Comprising the steps of data acquisition and preprocessing, construction of a high-dimensional disease embedding space, calculation of an individual health condition vector, deduction of a health score vector based on physical examination data, a hybrid prediction model for risk assessment, and model training and deployment. According to the method, a hybrid machine learning architecture is adopted, firstly, a health condition vector, a health score vector and original physical examination data are effectively integrated through a special fusion module, and then fused features are input into an integrated prediction model to generate a highly accurate diabetes risk score; according to the method, the prediction performance is remarkably improved, and the area (AUC) under the working characteristic curve of a subject reaches 0.84.

The invention relates to a biomarker for diagnosis, disease course analysis and prognosis of paraquat poisoning and application of the biomarker. The biomarker is a urine metabolite Pseudouridine. Urine non-target metabonomics analysis shows that the relative amount of Pseudouridine is relatively low in urine of early-stage poisoning patients, is gradually reduced along with aggravation of illness, is increased in follow-up visit of five years, and is recovered to the level of a healthy control group; according to the invention, the prediction efficiency is judged through the area under the line (AUC) of a subject's working characteristic (ROC) curve, the Pseudouridine has good efficiency (AUC = 0.732) in the aspect of diagnosing whether paraquat is poisoned or not, has good efficiency (AUC = 0.855) in the aspect of judging the progression of paraquat poisoning, has good efficiency (AUC = 0.807) in the aspect of judging long-term prognosis in the early stage of poisoning (1-4 days), and has excellent efficiency (AUC = 0.979) in the aspect of judging long-term prognosis in the progression stage of poisoning (7-14 days). And the prediction efficiency of the Pseudouridine is better than the blood routine examination index reported in the literature. In conclusion, the Pseudouridine, as a biomarker for paraquat poisoning diagnosis, disease course analysis and prognosis, shows a good clinical application prospect.

The invention relates to a biomarker. The biomarker is selected from one or more of the following components: UBR2, NPY4R, KLRF2, HABP2, GLP1R, DR1, RUNX2, ARHGAP5, LINC02135, DDHD1, MIR4523 and TC2N. The biomarker is especially used for diagnosing cerebral apoplexy and identifying and diagnosing cerebral hemorrhage. According to the invention, 12 characteristic biomarkers are screened for model construction, the performance of the model is analyzed and evaluated by using the working characteristic (ROC) of a subject, the area under a curve (AUC) is calculated by using sklearn, the sensitivity and specificity of the model respectively reach 0.898 and 0.818, and the AUC value is 0.913; meanwhile, cerebral hemorrhage is identified and diagnosed, the sensitivity and the specificity respectively reach 0.864 and 0-854, and the AUC value is 0.909. According to the invention, the 5hmC modification spectrum of plasma evDNA is combined with a machine learning algorithm for the first time, the screened characteristic biomarker and / or model have the advantages of strong specificity and high sensitivity, and the problems of low efficiency and poor accuracy in the cerebral apoplexy and cerebral hemorrhage identification process in the prior art are solved.

The invention belongs to the technical field of medical treatment, and provides a method for predicting long-term relapse of early ventricular ablation based on intracardiac potential spectrums.The method comprises the steps that intracardiac bipolar potentials before and after ablation are collected at a successful ablation target; performing fast Fourier transform on the potential signal to obtain a power frequency spectrum of the potential signal; in the 0-200Hz analysis frequency band, calculating the area under the curve of the 50-200Hz high-frequency component as the integral of the high-frequency component, and calculating the ratio of the integral of the high-frequency component to the total integral of the frequency spectrum to obtain the integral ratio of the high-frequency component; the ratio before ablation and after ablation is calculated respectively, the change value of the ratio is calculated and determined through ROC curve analysis, and the change value exceeding a threshold value is used as a critical value for predicting the low recurrence risk after ablation, time-domain signal analysis is innovated into frequency-domain quantitative analysis, an objective and accurate new index is provided for evaluating the ablation injury quality and predicting prognosis, and the risk of low recurrence after ablation is predicted. The device is especially suitable for ventricular arrhythmia of aorta root origin.

The present invention relates to the technical field of prediction of growth trend of pulmonary subsolid nodules, and discloses a prediction model and prediction method for growth trend of pulmonary subsolid nodules, including a data acquisition module and a prediction analysis module. The prediction model and prediction method for growth trend of pulmonary subsolid nodules retain clinical data and lung CT image data that meet the screening criteria, substitute them into the VAE-Deepsurv algorithm model for training, obtain multiple versions of algorithm models through training, calculate the area under the ROC curve of multiple versions of algorithm models, retain the algorithm model with the largest area under the ROC curve as the final model, strictly control the feature quantity of the prediction model, classify the clinical data set and the image data set into the data collection module, calculate and generate the nodule growth data group, the individual risk index and the predicted growth data group by the prediction analysis module, judge the growth probability of pulmonary subsolid nodules, and generate corresponding reports, focusing on individual differences and high prediction accuracy.

This invention proposes a clinical prediction model and design method for the probability of developing anal fistula in Crohn's disease patients, belonging to the field of clinical medical technology. The risk prediction model includes: an input module receiving patient parameters consisting of age at diagnosis, biological agent mode switching, and Montreal manifestation classification at initial diagnosis; a processing module connected to the input module, calculating the assessment and prediction probability of anal fistula in Crohn's disease patients based on the age at diagnosis, biological agent mode switching, and Montreal manifestation classification data at initial diagnosis, according to the following formula; and an output module connected to the processing module, outputting the risk probability of anal fistula in Crohn's disease patients obtained from the risk prediction model. The prediction model is validated on the training and validation sets using the area under the receiver operating characteristic (ROC) curve and a calibration curve to determine its discriminative power and calibration. It can accurately predict the risk of anal fistula in Crohn's disease patients before treatment.

The invention discloses application of saliva copper ion content detection in hepatolenticular degeneration diagnosis, and relates to the technical field of hepatolenticular degeneration disease diagnosis. Saliva specimens of hepatolenticular degeneration patients and saliva specimens of healthy control groups are collected. And comparing the difference of the copper ion levels in saliva of the hepatolenticular degeneration group and the healthy control group by using two independent sample t tests. And analyzing and evaluating the diagnosis performance of the saliva copper ion content by using an ROC curve, and determining a critical value of diagnosis. The result shows that the average saliva copper ion content level of a hepatolenticular degeneration group is 27.0518 [mu] g / L, and the average saliva copper ion content level of a control group is 18.4097 [mu] g / L. The saliva copper ion content of a hepatolenticular degeneration patient is obviously higher than that of a control group (plt; 0.0001) of the method. The area under the curve of the content of the saliva copper ions is 0.8170, which indicates that the content of the saliva copper ions is a good substitute diagnostic marker for distinguishing hepatolenticular degeneration patients.