36 results about "Prognostic prediction" patented technology

This invention belongs to the field of biomedical technology, specifically relating to the discovery and application of biomarkers for predicting the efficacy of immunotherapy in nasopharyngeal carcinoma. This invention provides a reliable combination of 10-gene TLS biomarkers that can effectively predict the pathological TLS status in nasopharyngeal carcinoma tissue. This 10-gene TLS biomarker combination exhibits stable and significant prognostic predictive value: regardless of standard treatment or immunotherapy, a high TLS score can effectively identify patients with better survival outcomes (such as FFS, OS, and DMFS), providing important evidence for individualized risk assessment and treatment strategy selection.

The present invention relates to an artificial intelligence model and an implementation method therefor, which are capable of selecting and extracting, from CT images of patients with IgA nephropathy, image features significant for prognostic prediction and applying same to a machine learning model to thereby predict, with high accuracy, the likelihood of the patients with IgA nephropathy progressing to end-stage renal failure within five years. The present invention provides a prognostic prediction model that rapidly predicts the prognosis of a patient without an invasive kidney biopsy, overcomes the limitations of conventional pathology diagnosis relying on invasive methods, and enables periodic prognostic evaluation with significantly improved reliability. In addition, the present invention is capable of precisely reflecting characteristics of each item and accurately predicting a clinical course of a patient, by combining various feature selection methods and binary classifiers for each item of mesangial hypercellularity (M), endothelial hypercellularity (E), segmental glomerulosclerosis (S), and tubular atrophy / interstitial fibrosis (T), which constitute a MEST score.

The invention belongs to the technical field of tumor prognosis prediction, and relates to a colorectal cancer allotropic liver metastasis prediction method and system.The method comprises the steps that colorectal adenocarcinoma cases are collected, the volume of an intra-tumor region-of-interest is delineated and automatically expanded to generate the volume of a peritumor region-of-interest, image omics characteristics are extracted through a pyradiomics packet, core omics characteristics are screened out, and the colorectal cancer allotropic liver metastasis prediction result is obtained. The method comprises the following steps: respectively constructing an intratumoral model and a peritumoral model, analyzing and integrating intratumoral and peritumoral core omics characteristics through logistic regression to form a combined radiomics model, integrating the combined radiomics model and clinical risk factors, establishing a column diagram for predicting the non-hepatic metastasis lifetime, and dividing patients into a low-risk group and a high-risk group according to a column diagram score threshold value; according to the method, LMFS prediction results of 1-5 years can be quickly output, and 0.6911 is set as a standardized risk stratification cut-off value so as to support risk stratification and personalized treatment decision of a patient.

The invention discloses a biliary duct cancer PD-1 monoclonal antibody treatment prognosis prediction system based on blood magnesium level, and relates to the technical field of biliary duct cancer immunotherapy prognosis, the biliary duct cancer PD-1 monoclonal antibody treatment prognosis prediction system comprises four core modules, a blood magnesium detection module uses a full-automatic biochemical analyzer to detect serum magnesium, the serum magnesium is divided into a low magnesium group and a normal blood magnesium group, and synchronous quality control is performed; the clinical data acquisition module acquires multi-dimensional information, and two persons check and complement data; the prognosis analysis module integrates data, and evaluates prognosis through statistical test, survival analysis and subgroup verification; and the result output module generates an encrypted report, visually presents and synchronizes the encrypted report to the electronic medical record system. The serum magnesium is used as a prediction index, the cost is low, the serum magnesium is easy to obtain, the serum magnesium is adaptive to hospital equipment at all levels, the independent prediction value and subgroup consistency are confirmed through rigorous analysis, prognosis can be dynamically updated, individualized suggestions are generated, prediction accuracy and clinical practicability are improved, and biliary duct cancer immunotherapy precision is promoted.

The present disclosure relates to a method of determining a prognostic outlook for patients having metastatic breast cancer. The method includes receiving imaging data from an image of a patient that is receiving or that is to receive cycline dependent kinase 4 and 6 (CDK 4 / 6) inhibitor therapy for hormone receptor-positive (HR+) metastatic breast cancer. Radiomic heterogeneity features are extracted from imaging data associated with a metastasis within the imaging. A prognostic marker is determined from the radiomic heterogeneity features. The prognostic marker is indicative of a response of the patient to CDK 4 / 6 inhibitor therapy for HR+ metastatic breast cancer.

System and methods for computer modeling in medicine. A sort of period table of medical models is described for personalized diagnostics, prognostics and therapeutics, including at least 80 major categories of medical models. Generative artificial intelligence and geometric deep learning techniques, and algorithms including 2D and 3D graph machine learning and GenAI algorithms, are described, tailored and applied to diagnostic disease description, prognostic prediction and therapeutic development and management, including generation of novel synthetic drugs. The AI and machine learning techniques and algorithms are applied to understand each individual's genetic, RNA and protein anomalies that represent the source of many unique patient diseases. AI-enabled software agents assist physicians and researchers in building patient medical models. Several personalized medicine applications of individualized medical modeling include cardiovascular

A Computer Aided Diagnosis, CADx, system and method for predicting an outcome score for a patient is described. The system comprising: an input circuit configured to receive input data comprising at least one input medical image for a patient; an outcome prediction circuit operably coupled to the input circuit configured to receive input data from the input circuit for outcome prediction analysis; wherein the outcome prediction circuit is further configured to receive details of a suggested future intervention for the patient; and the input data to the outcome prediction circuit is analysed to generate the outcome score for the patient accounting for the details of the future intervention.

This invention relates to a multi-task learning-based integrated nutritional decision-making method and system for examination, diagnosis, treatment, and evaluation, belonging to the interdisciplinary field of clinical medicine and artificial intelligence. This method aims to address the problems of isolated tasks, limited data utilization, and lack of quantitative recommendation and prognostic prediction capabilities in existing nutritional decision-making technologies. The technical solution involves constructing a serial multi-task learning neural network model, sequentially including a feature extraction module, a nutritional diagnosis module, a nutritional treatment recommendation module, and a prognostic and efficacy evaluation module. A joint loss function that dynamically balances the weights of each task and reuses prognostic labels is designed for training. This invention achieves integrated decision-making throughout the entire process of examination, diagnosis, treatment, and prognosis. It can integrate multimodal data to achieve accurate feature extraction, provide personalized quantitative nutritional recommendations, and prospectively predict efficacy to guide clinical intervention, significantly improving the efficiency and accuracy of nutritional decision-making.

This invention relates to the application, kits, and methods of using TFF3 in the diagnosis and / or prognostic assessment of heart failure, specifically to the application of reagents for detecting biomarkers, where the biomarker is TFF3. Through proteomics screening and multicenter clinical cohort validation, this invention has demonstrated that TFF3 is significantly elevated in the plasma of patients with heart failure. The AUC value of TFF3 for diagnosing heart failure was higher than 0.9 in all cohorts, and its expression level was significantly associated with all-cause mortality risk, serving as an independent prognostic predictor. This invention also provides a kit for detecting the biomarker TFF3 in the diagnosis and / or prognostic assessment of heart failure, along with its method of use. This kit exhibits high sensitivity and specificity, demonstrating significant clinical application value.

This invention discloses a prognostic method and system for maintenance hemodialysis patients based on time-series analysis. The method includes: predicting patient data using a prediction model to obtain a prognostic plan; a feature embedding layer of the prediction model encoding input features into a unified embedding representation; a Transformer encoder capturing temporal features and long-term trends from the unified embedding representation to obtain a second feature; a variational autoencoder module for compressing and denoising the second feature to obtain a latent representation; and a prediction head for making predictions based on the latent representation to obtain a prognostic plan. Based on an improved network structure using time-series analysis, a prediction model is trained to predict the prognosis of maintenance hemodialysis patients. Multiple prediction heads can predict prognostic risks, indicator types, or indicator regression values; accurate prediction of multiple indicators can meet the multi-dimensional decision-making needs of clinical practice, providing effective data support for physicians' diagnostic / intervention plans.

This invention relates to the field of clinical medical technology, specifically to a cross-modal inference system for colorectal cancer transcriptome features based on HE-stained slides. The system includes a human-computer interaction module for users to upload clinical data, pathological images, and transcriptome data, and select model parameters; a backend core program module for processing the uploaded clinical data, pathological images, and transcriptome data and extracting data features; a multimodal large model module for receiving the data features extracted by the backend core program module, integrating and clustering them, and generating prognostic indicators based on the integrated features and clustering results; and an output report generation module for receiving prediction results and outputting a standardized report, including patient information, prediction results, and clinical recommendations. This invention can efficiently integrate multi-source data, enhance model transparency, and improve the multimodal prognostic assessment of clinical colorectal cancer, thereby providing more accurate prognostic predictions for colorectal cancer patients and assisting clinicians in developing personalized treatment plans.

The present invention relates to a biomarker PAX5 for sepsis-related diseases and a use thereof. The present invention provides a use of PAX5 or an active fragment or functional fragment thereof in the preparation of a product for early diagnosis, risk assessment, immune status evaluation, prognostic prediction and / or treatment plan selection of a sepsis-related disease in a subject.

The invention relates to a prognosis prediction model construction method and device, electronic equipment and a storage medium. The prognosis prediction model construction method comprises the following steps: determining key distinguishing features capable of distinguishing a normal region from a focus region based on a brain medical image; determining a hidden damaged tissue boundary around the focus area according to the key distinguishing features; wherein the brain tissue between the focus area and the damaged tissue boundary is a hidden abnormal blood flow tissue area which is difficult to directly detect based on a brain medical image; and constructing the prognosis prediction model based on the brain tissue characteristics in the damaged boundary. The embodiment of the invention can improve the prediction level.

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 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.

This invention relates to a method and medium for quantifying biomechanical heterogeneity and predicting prognosis in hepatocellular carcinoma (HCC) based on a multi-scale mechanical interaction network. The method includes: retrieving the shear modulus and loss angle parameter maps of the tumor based on multi-frequency magnetic resonance elastography data; dividing the tumor into multiple biomechanical regions using mechanical gradient-driven adaptive clustering; constructing an intratumoral mechanical interaction network and extracting its topological features; constructing a multi-organ mechanical coupling model of the tumor, liver, and spleen, and calculating the cross-organ stress transfer efficiency as a coupling feature; fusing intratumoral network features and cross-organ coupling features to form a multi-scale biomechanical phenotypic vector, and inputting it into a machine learning model in conjunction with clinical features to achieve individualized and accurate prediction of postoperative recurrence risk in HCC patients. Compared with existing technologies, this invention provides a novel systemic biomechanical perspective for prognostic assessment by quantifying the intratumoral mechanical heterogeneity and its mechanical interaction with host organs.

This invention relates to the field of medical artificial intelligence software, and discloses an AI-assisted diagnosis and treatment system for refractive errors based on an internet hospital. The system comprises five modules: a patient information management module, an intelligent diagnostic assistance module, a remote monitoring module, a disease progression risk warning and prognosis prediction module, and an online consultation and eye health education module. The image segmentation model uses wavelet transform operators to decompose and extract multi-scale frequency domain features from the original 3D-OCT volumetric data of the eye. These multi-scale frequency domain features are then merged and concatenated with the original 3D-OCT volumetric data of the eye in the channel dimension to generate a multi-channel feature cube. This multi-channel feature cube is input into the Unet algorithm network unit, and after encoder, decoder, and hierarchical skip connection operations, a multi-channel probability map is generated. Finally, the multi-channel probability map is converted into a binary lesion segmentation mask for output. The intelligent image analysis module of this invention can improve the accuracy and efficiency of image screening for early identification of pathological myopia.

The invention belongs to the technical field of medical artificial intelligence, and particularly relates to a non-small cell lung cancer (NSCLC) prognosis prediction model integrating patient characteristics, clinical data and molecular markers, in particular to a prognosis prediction system for non-small cell lung cancer, which can be used for predicting prognosis conditions of patients and providing treatment suggestions. Firstly, the potential prognosis value of a serum biomarker clinically applied at present in pan cancer is systematically analyzed, clinical important characteristics such as age and gender are integrated, and a prognosis and curative effect prediction system for patients with lung cancer is established. According to the system, the survival risk of the NSCLC patient and the sensitivity of the patient to treatment can be accurately predicted, and making of a more accurate and efficient clinical decision is facilitated. The product has the advantages of low price, simple system operation, accurate prediction and the like, and has a very wide market prospect.

The invention relates to the technical field of image analysis, in particular to a multi-modal fusion glioma intelligent prognosis prediction method and system, and the method comprises the steps: collecting multi-modal data, respectively extracting omics features, constructing a multi-modal fusion depth model, obtaining high and low risk groups, and respectively carrying out difference analysis from multiple omics dimensions, screening out a gene set which is remarkably and highly expressed in the high-risk group, obtaining an intersection of each group of study difference analysis results, preliminarily screening out candidate genes, carrying out inter-study correlation analysis, and screening out intersection genes; introducing the intersection genes into a public database, and screening out genes which are remarkably and highly expressed in GBM to obtain candidate genes; and respectively introducing the candidate genes into a plurality of public databases, and finally identifying potential treatment targets related to the high-risk group. According to the method, the accuracy, the interpretability and the clinical transformation potential of GBM patient layering are comprehensively improved by constructing the multi-modal fusion depth model and combining heterogeneity mechanism analysis and target screening verification.

The invention belongs to the technical field of prognosis prediction, and discloses a prognosis prediction model for lung cancer immunotherapy based on a blood lipid metabolism marker and application. The prognosis prediction model is constructed on the basis of the following blood lipid metabolism markers: H4A2, LDPL, H4A1, H4PL and H4FC. According to the method, the blood lipid metabolites in the peripheral blood sample of the lung cancer patient before immunotherapy are screened to obtain the key blood lipid metabolite marker and establish the prognosis prediction model, and the model is used for quantitatively evaluating the immunotherapy response condition of the patient, so that the accurate prediction of the curative effect can be realized.

A method includes accessing a digital pathology image that depicts tumor cells sampled from a subject. A plurality of patches may be selected from the digital pathology image, wherein each of the patches depicts tumor cells. A mutation prediction may be generated for each of the patches, wherein the mutation prediction represents a prediction of a likelihood that an actionable mutation appears in the patch. Based on the plurality of mutation predictions, a prognostic prediction related to one or more treatment regimens for the subject may be generated. The prognostic prediction may be based on determining one or more mutational contexts of the digital pathology image as an unknown driver or a tumor suppressor, an oncogene driver mutation, or a gene fusion.

This invention proposes a method and system for prognostic analysis of hematological stem cell transplantation based on OCR and NLP technologies. The method includes receiving and recognizing medical reports uploaded by users, recognizing them as raw text through an OCR service, and then converting them into medical text through post-processing. Subsequently, an NLP service is invoked to extract structured patient features, which are then optimized and input into a prognostic prediction model to obtain prediction results for various prognostic indicators. Finally, the outputs of multiple models are merged to generate a visualized prediction report. This invention achieves seamless data linkage and automated flow between modules without human intervention by constructing a fully automated collaborative architecture that integrates medical data uploading, OCR recognition, structured data extraction, AI prognostic prediction, and result output. This eliminates data breakpoints and human errors, solving the technical problems of isolated functional modules and data flow breakpoints in existing technologies. Furthermore, it improves adaptability to medical scenarios.

The invention provides a marker related to prognosis grading of lung infiltrating mucus adenocarcinoma and application of the marker. The marker related to the prognosis grading of the lung infiltrating mucinous adenocarcinoma comprises the proportion of low circularity tumor cell nucleuses in lung infiltrating mucinous adenocarcinoma tissues, the variable coefficient of the tumor cell nucleus area and the median of the solid degree of the tumor cell nucleuses. A specific statistical feature combination extracted from a tumor cell nucleus population form has an independent prognosis prediction value for the disease subtype, quantitative nucleus features and traditional structure grading are further subjected to algorithm fusion, a more comprehensive evaluation system is constructed, prognosis distinguishing ability (such as an HR value) is improved in magnitude, and the prognosis effect of the disease subtype is improved. And the classification result and the expression profile of the potential treatment target are systematically subjected to integrated correlation analysis, and treatment suggestions are established on the basis of specific and quantifiable statistical correlation between the morphological characteristics of the cell nucleus and the expression of the target, so that clinical decisions have more pathological basis, and are more accurate, transparent and reliable.

The invention discloses a hemodynamics-based preoperative prognosis evaluation method, device and equipment for a blood flow guiding dense net stent, and a storage medium, and the method comprises the steps: constructing a three-dimensional blood vessel geometric model based on medical image data of a patient, carrying out hemodynamics simulation, obtaining a jet path in a tumor cavity, and obtaining a flow path of the tumor cavity; performing virtual implantation on the blood flow guiding dense net stent in the three-dimensional blood vessel geometric model to obtain a stent center line of the stent in a tumor cavity, and calculating a jet flow compliance index for prognosis evaluation based on a jet flow path in the tumor cavity and the stent center line, a jet compliance comprehensive index is constructed based on the first jet compliance index, the second jet compliance index and the third jet compliance index, and prognosis evaluation is performed on the preoperative curative effect of the blood flow guiding dense net stent according to the comprehensive index, so that the reliability of prognosis prediction is improved.

The invention provides a non-small cell lung cancer prognosis prediction method based on a multi-time-point enhanced CT (Computed Tomography) image, which solves the problems of pathology complete remission prediction and the like, and comprises the following steps: S1, data preprocessing; s2, feature extraction; s3, feature selection; s4, constructing a model; and S5, evaluating the performance of the model. The method has the advantages of good prediction effect, high practicability and the like.

This invention relates to an auxiliary diagnostic method, system, device, and medium based on oral pathology images. The method includes: processing multiple oral pathology images of a patient to generate a structured data pool containing all lesion features and spatial information; quantifying the morphological distance between lesions based on a feature matrix and inferring their clonal evolutionary relationships to construct a phylogenetic tree; fusing the phylogenetic tree, spatial location, and morphological distance for correlation analysis to generate an interpretation report; extracting multidimensional risk factors and fusing them into a risk factor set; calculating a comprehensive recurrence risk index through a risk prediction model, and combining the aforementioned analysis results to generate a structured diagnostic report for assessing tumor biological behavior and assisting in the development of follow-up plans. This method overcomes the limitations of existing technologies that can only analyze multicentric lesions in isolation and cannot automatically correlate and interpret or integrate prognostic predictions, achieving a systematic, quantitative correlation analysis of multiple oral cancer lesions and a comprehensive assessment of recurrence risk.

The invention belongs to the technical field of image processing and model prediction, particularly relates to a liver cancer prognosis prediction system based on multi-phase CT image fusion, and solves the problems that in the prior art, liver cancer prognosis prediction depends on static data, multi-phase information fusion is insufficient, and model training adaptability is poor. According to the method, multi-phase CT images of an arterial phase, a portal vein phase, a delay phase and a scanning phase of a liver cancer patient are obtained, after preprocessing, correlation weights of phase features of all phases are accurately captured by combining a cross attention mechanism through a branch of'front-end coding network local convolution + rear-end encoder global 'of a multi-phase auto-encoder, fusion features are generated, and the fusion features are obtained. The multi-phase self-encoder and the prognostic prediction network are combined to achieve efficient extraction of multi-phase features, the features are fused to pass through the prognostic prediction network, a prognostic risk index is finally output, the total survival time is predicted, and the multi-phase self-encoder and the prognostic prediction network are jointly trained through a user-defined loss function and a PSADam optimization algorithm. The liver cancer prognosis prediction precision can be improved.

The invention relates to a protein marker for identifying right ventricular dysfunction in idiopathic dilated cardiomyopathy and application of the protein marker. RARRES1, MVB12B and GSK3A proteins are found to be remarkably related to right ventricular dysfunction in urine of a patient with idiopathic dilated cardiomyopathy, the three proteins have good diagnosis or prognosis prediction performance in diagnosis and prognosis evaluation, and an economic, non-invasive and accurate right ventricular dysfunction diagnosis and prognosis tool is provided.

This invention provides the application of IDH1 Kcr in the diagnosis and treatment of non-alcoholic fatty liver disease (NAFLD). The study shows that IDH1 Kcr levels are downregulated in NAFLD, indicating that IDH1 Kcr can serve as a biomarker for the diagnosis and / or prognostic analysis of NAFLD. By monitoring IDH1 Kcr levels, the diagnosis, early prevention, and prognostic prediction of NAFLD can be achieved, providing an important reference for clinical diagnosis and treatment plans.