92 results about "Patient stratification" patented technology

The invention provides a prostate cancer biochemical recurrence prediction system based on a deep learning image and clinical information multi-mode model. The prostate cancer biochemical recurrence prediction system comprises an input module, a preprocessing module, a feature selection module, a fusion module, a prediction module, a data management and storage module and a result output and decision support module. According to the method, bpMRI image data and clinical information of a patient are fully utilized, multi-mode information is fully fused through a deep learning technology, and accurate prediction of biochemical recurrence is achieved. And the robustness of the model is further enhanced by adopting 5-fold cross validation and a diversified data enhancement strategy. Experimental results show that the method can assist in making more accurate patient layering and personalized follow-up visit schemes, and potentially reduces the over-treatment and missed diagnosis risks. The invention provides an efficient and reliable AI solution for prostatic cancer prognosis evaluation, and provides powerful support for promoting precise medical treatment and making personalized treatment strategies.

Among other things, the present disclosure pertains to methods and compositions related to phasing of allelic variants of genetic loci. Phasing of allelic variants of genetic loci on an individual patient's chromosomes is highly valuable for many purposes, including patient stratification for allele-specific therapeutics.

The present disclosure relates generally to biomarker discovery and patient stratification, and more specifically to machine learning techniques for discovering relevant biomarkers using data collected as part of the standard-of-care (SoC), which can be used to identify a relevant patient population for a therapeutic with a known mechanism of action (MoA). An exemplary method for predicting activity of a molecular analyte of a patient comprises: training a first module of a machine learning model based on a plurality of medical images of a first cohort; training a second module of the machine learning model based on one or more molecular analyte data sets obtained from a second cohort; receiving a medical image from the patient; and predicting, using the trained first and second modules of the machine learning model, the activity of the molecular analyte from the medical image of the patient.

The invention discloses a multi-omics cancer subtype recognition method, system and device based on density sensing cluster structure guide contrast learning and a medium, and belongs to the technical field of bioinformatics and artificial intelligence crossing. The method comprises the following steps: acquiring and preprocessing multi-omics data; constructing an omics specific auto-encoder and learning potential representation; constructing a density sensing cluster block in the potential space; constructing a cross-omics positive and negative sample pair based on cluster block sample overlapping; difficult negative sample mining; constructing a cluster block level cross-omics contrast learning target, and training and updating; a self-supervised soft refinement mechanism is introduced to dynamically enhance a cluster structure; and carrying out multi-loss joint optimization and model iteration training. According to the method, the robustness and the stability of a cancer subtype recognition result can be improved, high-dimensional, multi-source and multi-noise multi-omics data can be efficiently modeled and analyzed, good generalization ability and application potential are achieved, and reliable technical support can be provided for cancer subtype research, patient stratified analysis and precise medical aid decision making.

The invention belongs to the technical field of breast cancer treatment, and particularly relates to a patient layering method based on a breast cancer single cell space proteome multicellular enrichment mode, which comprises the following steps: S1, breast cancer single cell space proteome image data cell segmentation and cell type identification; s2, constructing a cell network diagram, and simulating a tumor microenvironment; s3, detecting closely connected cell communities, and extracting cell community characteristics; s4, carrying out cell community feature clustering, and representing a tumor microenvironment distribution mode of the patient; and S5, calculating the similarity of the tumor microenvironment distribution modes of the patients, and layering the patients. By means of the method, the patients can be layered, and prognosis of the patient groups has significant difference.

The present disclosure relates generally to biomarker discovery and patient stratification, and more specifically to machine learning techniques for discovering relevant biomarkers using data collected as part of the standard-of-care (SoC), which can be used to identify a relevant patient population for a therapeutic with a known mechanism of action (MoA). An exemplary method for predicting activity of a molecular analyte of a patient comprises: training a first module of a machine learning model based on a plurality of medical images of a first cohort; training a second module of the machine learning model based on one or more molecular analyte data sets obtained from a second cohort; receiving a medical image from the patient; and predicting, using the trained first and second modules of the machine learning model, the activity of the molecular analyte from the medical image of the patient.

The invention provides a big data resource service-based patient hierarchical intervention method and system, which are applied to the technical field of medical information, and are used for acquiring full-cycle health data of a patient, generating and updating a patient disease course trajectory sequence, analyzing health index change and trend under short, medium and long time scales, and calculating health scores and steady-state coefficients, so as to realize hierarchical intervention of the patient. A layered intervention scheme is generated, detection and personalized intervention of the health state of the patient are achieved, the timeliness and pertinence of medical intervention can be improved, and the disease management effect is optimized.

The disclosed method and system pertain to stratifying a patient population for precision medicine in Inflammatory Bowel Disease (IBD) treatment. The method involves accessing a multi-omic dataset comprising genomic, transcriptomic, and proteomic profiles of patient data. Machine learning algorithms are employed to analyze the dataset and identify biomarkers associated with a response to a drug for treating IBD. The patient population is stratified into phenotypic groups based on the identified biomarkers using unsupervised clustering. A patient population predicted to respond to the drug is defined based on the stratification and further analysis of patient metadata. The system includes a data storage unit and a processor configured to perform the method. The method and system can be used to optimize therapeutic interventions in IBD management.

The present disclosure relates generally to biomarker discovery and patient stratification, and more specifically to machine learning techniques for discovering relevant biomarkers using data collected as part of the standard-of-care (SoC), which can be used to identify a relevant patient population for a therapeutic with a known mechanism of action (MoA). An exemplary method for predicting activity of a molecular analyte of a patient comprises: training a first module of a machine learning model based on a plurality of medical images of a first cohort; training a second module of the machine learning model based on one or more molecular analyte data sets obtained from a second cohort; receiving a medical image from the patient; and predicting, using the trained first and second modules of the machine learning model, the activity of the molecular analyte from the medical image of the patient.

The invention relates to a biomarker of a glioblastoma invasion leading edge region and application of the biomarker, and belongs to the technical field of biological detection. In order to solve the technical problems of unknown tumor invasion mechanism, scarcity of treatment targets and inaccurate prognosis evaluation caused by lack of a GBM invasion leading edge region specific marker in the prior art, 12 GBM invasion leading edge region specific high-expression genes, namely CREG2, KIF5A, CELF4, TMEM132D, KHDRBS2, SNAP25, SYT1, ASIC2, PAK3, RBFOX1, STMN2 and CNTNAP2, are analyzed and screened through space transcriptomics. A COX multi-factor regression risk assessment system is developed and constructed based on the markers. According to the invention, a molecular basis is provided for accurate recognition of a GBM invasion range, patient layering and prognosis prediction, targeted therapy development and curative effect monitoring.

Methods of assigning a COVID pathological type for a subject suffering from COVID-19 are provided. Aspects of the methods include assigning a COVID pathological type for the subject based on a determined quantitative, multiplex cytokine / chemokine panel in a test sample from the subject. Also provided are methods of treating a subject (e.g., a long hauler subject) for chronic COVID-19. Aspects of such methods include administering to the long hauler subject a CCR5 / CCL5 interaction inhibitor to treat the long hauler subject. Also provided are compositions for use in practicing the methods. The methods and compositions find use in a variety of applications, including patient stratification, treatment and therapy determination and therapy response assessment.

The invention relates to the technical field of intelligent medical treatment, in particular to an AI-based brain disease test data management intelligent question-answering system, which comprises a multi-modal data acquisition module, an intelligent data processing module, an AI core model module, an interaction service module and a treatment guidance module, data aggregation is realized through a hospital interface, an equipment protocol and the like, and cleaning, standardization and multi-modal fusion are performed on multi-source data; precise question answering is achieved through the intelligent question answering unit, brain disease classification and stage division are completed through the patient layering unit, and a personalized scheme is generated by means of the treatment scheme generation unit; the interaction mode can be dynamically adjusted according to the cognitive level of a patient, emotion is recognized, guidance is provided, a doctor is supported to correct a scheme, and an iterative model is learned through feedback. The problems that in the prior art, the disease type is single, the data dimension is limited, and interaction adaptation is insufficient are solved, multi-disease-type whole-course precise management of brain diseases is achieved, and scheme scientificity and doctor-patient interaction experience are improved.

Methods for the diagnosis, prognosis, patient stratification and prediction of pharmacological response in patients afflicted by psychiatric disorders based on electroretinography (ERG) parameters are described.

The present invention relates to combination therapies and patient stratification with bispecific anti-EGFR / c-Met antibodies.

The present invention provides novel polypeptide derivatives that bind to human epidermal growth factor receptor 2 (HER2) and conjugates thereof, and their use as diagnostic agents, in particular for the early detection, patient stratification and treatment monitoring of cancer forms characterized by overexpression of HER2.

Methods and systems for patient stratification include learning (404) interdependent biomarkers as integrated time-series machine learning models. A disease stage is identified (424) for a patient based on collected biomarker data. A treatment for the patient is performed (430) based on the identified disease stage and a predicted future response of the patient.

Disclosed are methods and agents for predicting response to therapy, immune status and / or disease progression. More particularly, disclosed are methods, agents and kits for analyzing cellular distribution of PD-L2, including its nuclear localization, for stratifying a patient as a likely responder or non-responder to a therapy, for managing treatment of a patient with a therapy, for monitoring a disease in a patient following treatment with a therapy, for determining the status of a disease and / or for determining the immune status of a patient.

The present invention relates to combination therapies and patient stratification with bispecific anti-EGFR / c-Met antibodies.

The invention discloses a disease community discovery and patient layering method based on gene information guidance, and belongs to the technical field of biological information.According to the method, an initial disease set is created through full phenotype correlation research, and the diseases are expressed in a high-dimensional embedding space of electronic health record data; vector representation of diseases is optimized and extracted by learning individual features of the diseases and a topological structure of a co-disease network of the diseases through a graph auto-encoder, the diseases are divided into different communities with consistent interiors by embedding vectors into the optimized diseases and applying a clustering algorithm, and the method is provided based on the individual health history, and is suitable for the individual health history and the co-disease network. According to the method for classifying new patients into a certain community, accurate patient layering is achieved, a complex multi-disease network is disclosed, a brand-new systematic perspective is provided for disease understanding, a traceable and data-driven bridge from genes to patient subgroups is established, and a novel framework is provided for medical conversion.

This invention discloses a multi-terminal interconnected nursing system and method based on the Internet of Things (IoT). The multi-terminal interconnected nursing method includes: collecting patients' physiological and behavioral data through IoT devices deployed at home; generating exclusive early warning thresholds and analysis models by a personalized data module, with rules pushed to the hospital, community nursing, home monitoring, and family members via a multi-terminal synchronization protocol; automatically generating nursing tasks based on the patient's data anomaly level and the urgency of nursing needs; allowing nursing staff to access complete patient information integrated across multiple terminals with a single click through an integrated operation portal; periodically iterating and optimizing the personalized model library based on multi-terminal feedback data; and achieving dynamic synchronization of multi-terminal thresholds and analysis models by constructing a patient-stratified personalized data model library, creating a multi-terminal integrated collaborative platform, integrating multi-source data, and reconstructing the information display and operation logic at the nursing staff's end, thereby improving the accuracy of nursing decisions and the efficiency of nursing service execution.

A respiration monitoring device comprises an electronic controller configured to: receive an audio signal that is acoustically coupled with an airway of a patient receiving mechanical ventilation therapy from a mechanical ventilator; map the audio signal to one or more lung disease or injury condition categories; and at least one of: display the mapped one or more lung disease or injury condition categories on a display device; and determine a recommended adjustment to one or more parameters of the mechanical ventilation therapy delivered to the patient based at least on the mapped lung disease or injury condition categories and displaying the recommended adjustment on the display device.

Identifying and refining clinically significant patient stratification is a critical step toward realizing the promise of precision medicine in a number of medical conditions such as asthma. In this context, we describe the construction unbiased patient stratification scores based on DNA methylation (DNAm) patterns and gene expression patterns and their utilization to refine the efficacy of hallmark biomarkers for predicting drug response in asthma patients, as well as patients having diseases / conditions caused by excessive Type 2 inflammation, such as atopic dermatitis.

The present disclosure relates generally to biomarker discovery and patient stratification, and more specifically to machine learning techniques for discovering relevant biomarkers using data collected as part of the standard-of-care (SoC), which can be used to identify a relevant patient population for a therapeutic with a known mechanism of action (MoA). An exemplary method for predicting activity of a molecular analyte of a patient comprises: training a first module of a machine learning model based on a plurality of medical images of a first cohort; training a second module of the machine learning model based on one or more molecular analyte data sets obtained from a second cohort; receiving a medical image from the patient; and predicting, using the trained first and second modules of the machine learning model, the activity of the molecular analyte from the medical image of the patient.

Provided herein are compositions and methods related to the production and detection of a histone H1.0 protein dimethylated at lysine residue 180 (K180) (H1.0K180me2 protein) or a histone H1.0 peptide dimethylated at a lysine residue corresponding to K180 (H1.0K180me2 peptides). The H1.0K180me2 protein and H1.0K180me2 peptides are useful for applications including, but not limited to, molecular diagnostics of DNA damage, genotoxic stress, radiation exposure, and Alzheimer's disease, therapeutics, monitoring of therapeutic regimens, patient stratification, and drug screening. Also provided herein are antibodies specific for the H1.0K180me2 protein and H1.0K180me2 peptides.

The invention belongs to the technical field of medical informatization and artificial intelligence, and particularly relates to a lupus erythematosus patient layering and personalized treatment scheme recommendation system which comprises a data access module, a data preprocessing module, a graph neural network modeling module, a layering label updating module, a subtype division module and a treatment scheme recommendation module. Accessing multi-source data through a data interface, constructing a data association graph by adopting a graph neural network, and analyzing a potential association relationship among data of different dimensions; a deep learning algorithm is combined to dynamically update layering labels of patients, the patients are subdivided into hormone sensitive subtypes, immunosuppressor dependent subtypes, refractory subtypes and other subtypes, and personalized treatment schemes are matched. According to the method, the layering accuracy of the patient and the scientificity of a treatment scheme can be improved, the dependence on artificial experience is reduced, and technical support is provided for precise medical treatment of the lupus erythematosus patient.

The present disclosure relates generally to biomarker discovery and patient stratification, and more particularly to machine learning techniques for discovering related biomarkers using data collected as part of standard care (SoC), which may be used to identify related patient populations with therapeutic agents of known mechanisms of action (MoA). An exemplary method for predicting patient molecular analyte activity includes: training a first module of a machine learning model based on a plurality of medical images of a first queue; a second module to train the machine learning model based on one or more molecular analyte data sets obtained from a second queue; receiving a medical image from the patient; and predicting the activity of the molecular analyte from the medical image of the patient using the trained first and second modules of the machine learning model.

Objective discrimination of a disease label of a depressive symptom with respect to an active state of a brain is achieved. One means for solving the problems of the present invention is to provide a discriminating device for assisting in determination of whether a subject has a depressive symptom. The discriminating device includes a storage device for storing information for identifying a classifier generated by classifier generation processing based on a signal obtained by using a brain activity detecting apparatus to measure, in advance and time-sequentially, a signal indicating a brain activity of a plurality of predetermined regions of each brain of a plurality of participants in a resting state, the plurality of participants including healthy individuals and patients with depression. The classifier is generated so as to discriminate a disease label of a depressive symptom based on a weighted sum of a plurality of functional connectivities selected by feature selection as being relevant to the disease label of the depressive symptom through machine learning from among functional connectivities of the plurality of predetermined regions. The discriminating device further includes a processor configured to execute discriminating processing of generating a classification result for the depressive symptom of the subject by using the classifier.

The present invention firstly discloses a gene methylation biomarker combination and a screening model for the screening of high-grade cervical lesions. By comparing differentially methylated positions (DMPs) in normal tissues and high-grade lesion tissues, and using the corresponding CpG islands as diagnostic biomarkers for research, the present invention screens out 12 optimal CpG islands with consistent characteristics through a random forest classifier, and establishes a screening model based on the CpG island level of cervical exfoliated cells. This model can perform risk assessment on patients with positive HPV and negative cytology, distinguish high-risk groups from low-risk groups, and recommend different follow-up or intervention measures clinically to achieve patient stratification and effectively improve the accuracy of cervical cancer screening; the screening model has the advantages of high sensitivity and specificity, and objective risk assessment results.