121 results about "Precision medicine" patented technology

The invention provides a cross-omics sparse feature selection system and method based on hierarchical causal modeling, and the system comprises a data input and preprocessing module which is used for receiving multi-omics original data of a multivariate sample; the hierarchical causal structure learning module is connected with the data input and adaptive preprocessing module and is used for constructing a cross-omics hierarchical causal topology; the causal-oriented sparse feature selection module is connected with the hierarchical causal structure learning module; and the model retraining and integration module is used for constructing a three-layer weighted integration discrimination model based on the screened markers, optimizing the fusion weight of each layer through a gradient descent algorithm, and outputting a final prediction result. According to the method, the protein-metabolism biological hierarchy relationship and serum-urine complementary information are fully utilized, and the method has good generalization ability and can be widely applied to marker mining and prediction modeling of cancers, metabolic diseases and the like, so that the accuracy and reliability of precise medical treatment are improved.

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 discloses a multi-omics data integration and classification method, system and device based on hierarchical attention, and is applied to the field of precise medical big data analysis. The method comprises the following steps: firstly, generating feature embedding and feature importance scores through a plurality of parallel feature-level attention modules; then, embedding and inputting all the characteristics of the omics into a unified omics-level attention module, and generating omics embedding and omics importance scores; and finally, a classification prediction task is executed based on omics embedding, and a classification result is output for disease classification. The invention completely abandons a traditional dependency graph convolutional network and an integration normal form of variants of the dependency graph convolutional network, and provides a universal hierarchical attention integration architecture. The framework supports classification tasks of any complex diseases, is not limited by omics data types and combination modes, not only is remarkably superior to a traditional integration normal form in classification performance, but also shows a unique negative generalization distance, and proves that the framework has excellent generalization ability. Meanwhile, features and omics importance scores automatically output by the model provide a powerful analysis tool for biomarker discovery and precise diagnosis and treatment of complex diseases.

The invention relates to the technical field of medical information, and discloses a CRRT treatment intelligent safety early warning system based on multi-modal fusion, and the system comprises a data collection and fusion module which is used for collecting multi-modal data from a plurality of heterogeneous data sources in real time, carrying out the standardization and fusion processing of the multi-modal data, and generating fusion data with a unified time sequence; the knowledge model library is used for storing medical knowledge, clinical guidelines and historical data related to CRRT treatment and trained early warning and decision models; according to the system, through multi-modal data fusion and machine learning, the crossing from passive alarm to active early warning is realized, and the safety of a patient is remarkably improved. The intelligent decision support can output an individualized treatment scheme, promote precise medical treatment and optimize resource utilization, the system integration and grading alarm mechanism effectively reduces the cognitive load of medical care, and the self-learning ability of the system ensures that an early warning model can be continuously evolved and promotes the continuous improvement of clinical treatment quality.

This invention belongs to the field of biomedical technology, specifically relating to the application of DNA damage response gene-related SNPs in the treatment and prognosis of acute myeloid leukemia (AML). This invention is the first to discover that single nucleotide polymorphisms (SNPs) in the DNA damage response pathway (focusing on three major functional modules: damage sensing, signal transduction, and DNA repair) are closely related to the clinical characteristics, treatment response, and survival prognosis of AML. This lays the foundation for constructing a multi-gene risk model based on the DNA damage response pathway and provides theoretical support for integrating germline SNP maps into precision medicine strategies for AML.

The application discloses an adaptive clustering federated learning modeling method for precision medicine, and relates to the technical field of precision medicine, and comprises the following steps: data collection and preprocessing and model construction and training; the application accurately determines the optimal number of the global model through adaptive clustering, and divides clustering groups according to the similarity of the client model parameters, realizes independent training of the groups, effectively improves the adaptability of the model to different client data characteristics, samples and label distribution differences, avoids the problem that a single model has poor performance in some clients, and significantly enhances the ability of the model to capture complex medical patterns; the model generalization is optimized through grouped training, so that the model can better cope with new data distribution, under the premise of ensuring the privacy and security of medical data, the accuracy and reliability of the model in precision medical scenes such as disease diagnosis and prognosis prediction are greatly improved.

A method for practicing precision medicine comprising providing, to a blockchain platform, each of clinical data and genetic data, providing the blockchain platform, the blockchain platform having a first data structure comprising clinical data and a second data structure comprising genetic data, harmonizing the first and second data structures, creating at least one cohort based on the harmonized first and second data structures, and identifying at least one relationship between the clinical data and the genetic data in each of the at least one cohort.

The invention discloses a drug collaborative screening system based on artificial intelligence prediction and metabonomics verification, and belongs to the technical field of artificial intelligence and bioinformatics crossing. Comprising a multi-source data acquisition and feature fusion module, an artificial intelligence prediction module, a drug screening and visualization module, a metabonomics verification module and a feedback optimization and self-learning module. According to the invention, through multi-modal data integration and feature coding, unified modeling of a drug-disease-molecule network is realized; drug combination synergistic effect prediction is realized through an artificial intelligence algorithm; a prediction result is verified by using non-targeted metabonomics data, and the mechanism interpretability of the model is enhanced; a technical system capable of realizing closed-loop optimization is constructed, and an algorithm and experiment dual-verification platform is provided for drug discovery and precision medicine.

The invention discloses an amino acid L / D type enantiomer separation and quantitative detection method based on LC-MS, and belongs to the technical field of biological analysis. Aiming at the problems of difficulty in separation of amino acid L / D type enantiomers in human serum, low detection sensitivity, complex analysis process and the like, the method disclosed by the invention is simple in pretreatment, short in instrument collection time, high in chiral enantiomer separation degree, small in matrix effect, high in sensitivity, low in cost and convenient for large-scale clinical sample detection in a laboratory; the method not only can make up the limitation that only the L type is detected at present, but also can provide a key analysis method for early warning of diseases, drug effect and toxicokinetics research and precise medical evaluation.

This invention relates to a method and system for constructing a medical knowledge graph based on cross-dimensional alignment using artificial intelligence, belonging to the field of medical knowledge graphs. This method integrates authoritative databases from multiple medical domains by constructing a unified medical semantic space across scales and modalities; and combines deep representation learning and manifold alignment techniques to design a joint embedding and dynamic alignment framework for multi-source heterogeneous knowledge, achieving semantic unification and structure-fidelity mapping of different standard systems in a low-dimensional dense space. This invention not only effectively alleviates the semantic fragmentation problem between ontology but also significantly improves the system's semantic understanding and cross-database retrieval capabilities for complex clinical texts, providing a computable and reasonable knowledge foundation for clinical decision support, disease prediction, and precision medicine.

The invention belongs to the technical field of biological medicine and molecular biology, and provides a hypertrophic cardiomyopathy virulence gene MYH7c.794Cgt; the invention relates to T (p.Thr265Ile) and an application thereof. The MYH7 gene mutation is located on the ninth exon, the 794th base is mutated from C to T, namely ACC is mutated to ATC, and the 265th amino acid in the coded amino acid sequence is mutated from threonine to isoleucine. The mutation induces cardiac hypertrophy by disrupting energy metabolism-this defect occurs prior to the occurrence of systolic dysfunction. Along with increasingly prominent status of precision medicine in cardiovascular treatment, a treatment strategy aiming at an upstream pathological process (such as energy homeostasis and mitochondrial dysfunction) provides a way with a wide prospect for preventing and treating MYH7-related hypertrophic cardiomyopathy. MYH7 gene screening has important values in the aspects of promoting early diagnosis, guiding timely treatment intervention and realizing risk-based prevention and management.

The application discloses a wearable system for evaluating postoperative pulmonary complication risk, comprising: a data acquisition module, including a vest, a pulse oximeter and a signal recording box, for collecting physiological signals of an evaluated person during submaximal exercise test; a data processing module connected with the data acquisition module, for processing the physiological signals to obtain characteristic data based on the peak and slope of the physiological signals; a model calculation module connected with the data processing module, for inputting the characteristic data into a model trained by using a stochastic gradient algorithm and including preoperative clinical physiological characteristic data, to calculate a postoperative pulmonary complication incidence rate; and a model evaluation module connected with the model calculation module, for determining whether the evaluated person has postoperative pulmonary complications according to a Melbourne Group Score Scale. The system can accurately predict the probability of pulmonary complications by the cooperation of the modules, and provide precise medical intervention guidance for clinical treatment.

A single-cell level spatial omics multi-modal fusion method, comprising: extracting differential expression genes and nuclear spatial morphological features from spatial transcriptome data, single-cell sequencing data and histological images, and realizing field adaptation between different platforms by using conditional variational autoencoder. Based on a probability inference model, spatial transcriptome expression, single-cell omics and morphological features are fused to jointly infer the type and gene expression level of each cell. A spatial cell network is constructed by a graph attention mechanism to realize the spatial diffusion and recognition of cell types in the whole slice range. Combined with a multi-omics enhancement module, the unmeasured gene and protein expression are completed based on expression similarity, and the prediction consistency is improved through spatial correction. The method realizes high-resolution reconstruction of single-cell multi-omics information in three-dimensional space, improves the information coverage and spatial resolution of spatial omics data, and provides an efficient and low-cost solution for spatial biology and precision medicine research.

This invention relates to the field of gastric cancer organoid microarray technology, and more particularly to a gastric cancer organoid microarray culture medium and its applications. The invention provides a novel culture medium adapted for gastric cancer organoid microarray culture. The medium components include basal medium, penicillin / streptomycin dual antibiotics, antibacterial agents, hydroxyethylpiperazine ethanesulfonic acid, B-27 additive, Glutamax culture medium additive, R-vertebral protein 1, scutellarin B, and tetramethylpyrazine, among other components. This invention solves key problems in existing technologies such as slow growth, morphological instability, poor heterogeneity adaptation, and low long-term culture activity of gastric cancer organoids, providing an ideal experimental model for high-throughput screening and precision medicine applications on microarrays.

This application discloses a thermosensitive adhesive, its preparation method, and its application, belonging to the technical field of thermosensitive adhesives. The thermosensitive adhesive of this application is prepared by photoinitiated polymerization of a raw material mixture at a temperature of 25-120°C. The raw material mixture comprises 25-49 moles of thioctic acid, 1-25 moles of N-alkane-1,0-dimethyl thioctinamide, and 0.5-2 moles of tris(2-carbonylethyl)phosphohydrochloride, citric acid, or guanidine hydrochloride. The thermosensitive adhesive of this application exhibits adjustable adhesion properties and maintains good optical transparency and interfacial compatibility near human body temperatures of 25-40°C. It also maintains good adhesion stability in the human body fluid environment and under repeated loading or temperature cycling conditions, potentially expanding its application potential in the field of precision medicine.

This invention discloses a STEP universal encoding method and system for all things in the universe based on four fundamental cosmic quantities: space (S), time (T), energy (E), and the full spectrum (P). It relates to the fields of universal encoding technology, cross-domain information transmission, matter feature identification, precision detection, and medical diagnosis. This method collects spatial structure, temporal characteristics, energy distribution, and full-spectrum response data of target objects from multiple dimensions. After normalization and scaling, it generates unique codes. The core is characterized by the basic ratios of S / T, S / E, and T / E, as well as the comprehensive ratio range of S / T / E / P, possessing inherent uniqueness and cross-civilization interpretability. The system comprises six modules: multi-dimensional acquisition, data processing and scaling, STEP encoding generation, encoding storage and transmission, decoding and feature restoration, and application output interfaces. It is adaptable to scenarios such as deep space communication, precision medicine, traditional Chinese medicine quantification, object identification, chip instruction set compatibility, and AI large-scale model inference acceleration. This invention solves the technical problems of existing encoding systems' limitations in scenarios, limited information carrying capacity, and lack of universal interpretation standards, achieving unique identification, complete description, and secure transmission of all things in the universe.

A new generation of precision medicine with interfaces processing the predictive feedback over the course of hyperthermia treatment sessions is provided. Implementation of MR-thermometry measurements and real-time spatial imaging can resolve many of the limiting factors currently associated with hyperthermia treatment. More significantly, implementation of artificial intelligence (machine learning) mediated image analysis and database construction can provide the international community with standards for monitoring, and thermal dose calibration.

The application provides a kind of image positioning sticker marking method based on iodine-gallium complex chelate, through chelation reaction to prepare excellent stability iodine-gallium complex developer, non-woven fabric substrate is modified by chitosan coating, combined with screen printing process to prepare high-precision positioning sticker, and establish standardized clinical marking process. The method uses iodine-gallium double element synergistic development mechanism, so that the CT value of the marking area is 350-400HU, the contrast of the surrounding tissue is improved by 40%, the development clarity retention rate is more than 92% after 48 hours of sticking, the positioning error is stable within 0.3mm, solves the pain points of traditional marking easy diffusion and poor adhesion. The application has excellent biocompatibility, the skin allergy rate is only 0.8%, the single patient positioning operation time is shortened to 5-10 minutes, the production cost is reduced by 40%, can be widely used in precise medical positioning scenes such as tumor radiotherapy and interventional surgery, has significant clinical popularization value.

The present disclosure relates to Sigma-1 receptor agonists, and their target engagement and capacity to correct multiple EEG biomarkers of cortical dysfunction. The present disclosure further provides Precision Medicine or personalized therapy of using a Sigma-1 receptor agonist in treating neurodevelopmental and / or neurodegenerative disorder through engaging with EEG biological pathways. Also provided are kits for practicing the methods.

The invention relates to the technical field of molecular biology and precision medical treatment, and relates to a molecular marker for predicting FOLFOX chemosensitivity and application thereof. A patient-derived colorectal cancer organoid biological sample library is constructed, the heterogeneity of in-vitro drug reaction is analyzed and evaluated through transcriptome, clinical groups sensitive to FOLFOX chemotherapy can be accurately recognized, a molecular marker prediction system containing 11 genes is obtained through further screening, and the molecular marker prediction system is used for predicting the FOLFOX chemotherapy. The method effectively overcomes the technical defect of lack of accurate prediction of colorectal cancer chemosensitivity at present, and has important value in the aspects of revealing disease mechanisms and guiding personalized treatment.

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 invention relates to the field of tumor molecular diagnosis and precision medicine, in particular to a model for predicting early chemotherapy failure of a DLBCL patient and application of the model. By detecting the ctDNA concentration level of the patient base line and the early treatment period and / or combining clinical characteristic parameters, a multivariable risk assessment algorithm is established, the high-risk patient can be identified in the early treatment period, a reliable basis is provided for individualized treatment, and remarkable clinical and social values are achieved.

The present application relates to the technical field of remote photoplethysmography, and in particular to a rPPG physiological index estimation method and system based on a multi-scale time sequence Mamba architecture; a parallel signal processing architecture is first constructed, a confidence degree guided optical flow motion compensation module is used to improve ROI time sequence consistency and relieve motion artifacts, a differential denoising module is combined to weaken light disturbance, and two enhanced spatial features are obtained; then a gating weighting module is used to map the spatial features to the channel dimension for adaptive fusion, information conflicts in spatial fusion are avoided, and effective inputs are provided for time sequence modeling; finally, a bidirectional time sequence collaborative module that integrates time sequence separable convolution and state space model is constructed, local short-term dynamics and long-term periodic rules are collaboratively captured, and the robustness of time sequence feature representation is improved while maintaining computational efficiency. The present application can efficiently and accurately extract physiological indexes such as heart rate in complex scenes, has strong robustness, and is suitable for digital health scenes such as precision medicine and telemedicine.

The utility model relates to medicine weighing technical field discloses a kind of discharging mechanism of medicine weighing device, including base, the base lower surface is fixedly connected with connecting plate, the base upper surface is fixedly connected with shell, the discharging assembly includes hydraulic rod, blanking pipe and blanking cover, the blanking pipe is fixedly connected in shell inner wall, the blanking cover outer wall is rotatably connected in blanking pipe lower surface, the blanking cover outer wall is fixedly connected with connecting rod, the connecting rod one end is fixedly connected with connecting block, the blanking cover is arranged in shell interior, the blanking cover output end is fixedly connected in connecting block lower surface. In the utility model, discharging assembly is driven connecting block by hydraulic rod, drives connecting rod to rotate blanking cover, realizes the opening and closing of blanking pipe, accurately adjusts medicine falling rate, avoids excess or deficiency, the design simplifies discharging process, improves weighing accuracy and operation reliability, applicable to high-precision medicine subpackaging environment.

The invention discloses a pig jejunum crypt separation and organoid model construction method, and belongs to the technical field of animal tissue separation and culture. The method specifically comprises the following steps: intestinal tract collection, cleaning solution preparation, intestinal tract treatment, tissue trimming, tissue cleaning, digestive juice preparation, tissue digestion, cell mass separation, crypt separation, crypt counting, crypt collection, crypt inoculation and organoid culture. The porcine jejunum organ obtained by the method has a typical three-dimensional cystic structure, has complete epithelial polar and functional cell types, including microvillus, goblet cells, panning cells and endocrine cells, and shows good barrier function and drug metabolic activity. A reliable in-vitro model platform is provided for pig intestinal development, nutrient absorption, pathogen infection mechanism research and precision medical treatment, meanwhile, a technical foundation is laid for large-scale application of organoids, and the method has important scientific significance and clinical value.

The invention relates to a detection strategy of a programmable TMSD-CRISPR system for DNA / RNA (deoxyribonucleic acid / ribonucleic acid) single base mutation. Based on split crRNA and dynamic and thermodynamic regulation and control mechanisms of a dynamic nanotechnology, the purpose of identifying DNA / RNA single-base mutation at different sites is achieved by utilizing different kinetic rates of toehold-mediated strand displacement on strand displacement with a single-base mismatched target strand. According to the present invention, the identification factors for the ssDNA / dsDNA / RNA mutation are significantly enhanced (the ssDNA mutation is 169.4, the dsDNA mutation is 243.8, and the RNA mutation is 156.2), such that the DNA mutation detection with the abundance as low as 0.025% is achieved, and the single base mutation detection is allowed to be performed in the miR-21; in the research of a queue containing 75 clinical samples, the method successfully detects and accurately identifies all KRAS G12V variants at the accuracy rate of 100%, and shows the huge potential of the KRAS G12V variants in clinical molecular diagnosis. The programmable split TMSD-CRISPR has excellent specificity and adjustability, and can be used as a multifunctional platform for biomedical research, molecular diagnosis and precision medicine.

The invention provides a living single cell multi-modal in-situ detection analysis method and a treatment scheme evaluation optimization method, and relates to the technical field of precision medical treatment, and the method comprises the following steps: obtaining multi-modal data of a living single cell to be detected in situ; the multi-modal data comprises at least two of the following data: electrical impedance data of a living single cell to be detected under a plurality of frequencies, Raman spectrum data of the living single cell to be detected, and image data of the living single cell to be detected; the frequency is the frequency of an alternating current signal applied to the cell through the electrode; extracting multi-modal dynamic characteristics of the living single cell to be detected from the multi-modal data by adopting a combined modal data analysis method; wherein the combined modal data analysis method comprises a cell electrophysiological analysis method, a cell multi-molecular spectroscopy analysis method and a cell image analysis method. Therefore, the multi-modal dynamic measurement method is utilized to obtain multiple groups of dynamic characteristic information of the cells, and accurate treatment effect evaluation and process optimization can be realized.

The application provides a non-target detection device and system based on a nanopore and a detection method thereof, the non-target detection device and system based on a nanopore are used for non-target detection of a complex matrix through a nanopore, feature extraction is performed on a nanopore detection graph, and sample classification is realized through model construction, the detection method does not make a prior definition on a to-be-detected target, and various molecular information existing in serum is acquired in a net catching manner, non-target capture and overall state analysis of various molecules in serum are realized, and a new way of rapid and portable disease screening is provided.The application breaks through the limitation of traditional single marker detection by combining the nanopore technology and machine learning, and is expected to promote the development of precision medicine in a more efficient and comprehensive direction.

The present application belongs to the tumor precision medicine and artificial intelligence medical technology field, and particularly relates to a non-small cell lung cancer neoadjuvant immunotherapy efficacy prediction method based on transfer learning. The method first pretreats the non-small cell lung cancer immunotherapy cohort and the neoadjuvant immunotherapy cohort, selects immunotherapy and neoadjuvant immunotherapy characteristic genes, and based thereon, carries out deep learning training on the immunotherapy cohort to obtain a basic model, finally, the basic model is fine-tuned to the neoadjuvant immunotherapy training data set through transfer learning, and finally used to the neoadjuvant immunotherapy cohort to predict the neoadjuvant immunotherapy effect. The present application improves the stability and generalization ability of the model in the small sample neoadjuvant treatment scene through gene selection and transfer fine-tuning, and can be used for clinical auxiliary decision and population stratification.

The invention provides a biomarker for predicting the treatment response of an ovarian cancer patient to a VEGFR (vascular endothelial growth factor receptor) inhibitor and application of the biomarker, and finds that the fat volume of the ovarian cancer patient can be used as the biomarker for predicting the curative effect of the VEGFR inhibitor to tumors. Based on two markers of visceral fat volume and subcutaneous fat volume, an SAS trajectory analysis model is constructed, and clinical benefit people of an ovarian cancer VEGFR inhibitor treatment scheme are screened out; further in-vitro co-culture and in-vivo animal experiments prove that the existence of fat cells can specifically enhance the anti-tumor effect of the VEGFR inhibitor, and clinical correlation is explained from a biological mechanism; the invention provides a new tool and theoretical basis for realizing individualized precise medication of ovarian cancer targeted therapy.