Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

97 results about "Clinical phenotype" patented technology

In this context, a phenotype would be any observable characteristic or trait of a disease, such as morphology, development, biochemical or physiological properties, or behavior, without any implication of a mechanism. A clinical phenotype would be the presentation of a disease in a given individual. Some organizations...

IBS micro-ecological transplantation intelligent prediction method and system based on multi-omics driving

The invention provides an IBS micro-ecological transplantation intelligent prediction method and system based on multi-omics driving, and relates to the technical field of biomedicine. The method comprises the following steps: establishing a multi-omics data fusion subsystem to collect metagenome, metabolome, host genome and clinical phenotype group data of a target patient; inputting the data into a flora-metabolite combined network analysis model to construct an interaction network and extracting features; generating an incidence matrix based on the features and the host genome data and calculating indexes; generating indexes through a dynamic response algorithm in combination with the clinical phenotypic data and the indexes; and outputting a curative effect prediction result by using a transfer learning framework combined with modeling. The system comprises a data acquisition module, a network analysis module, a correlation calculation module, a dynamic response module and a joint modeling module. According to the method, multiple omics data are integrated, the flora and host relation is accurately mined, intelligent prediction of the micro-ecological transplantation curative effect is achieved, powerful support is provided for IBS personalized treatment, and meanwhile data processing and safety guarantee measures are taken.
Owner:THE FIRST MEDICAL CENT CHINESE PLA GENERAL HOSPITAL

Aging clock construction method based on causal machine joint model

The invention belongs to the technical field of health assessment, and particularly relates to an aging clock construction method based on a causal machine joint model. The method comprises the steps of 1, obtaining a multi-modal data set of a target crowd based on multi-modal data fusion and standardization preprocessing; 2, performing two-stage screening on the multi-modal data set to obtain core features; 3, analyzing interaction among multiple groups of schools based on the extended proportion advantage logistic regression hybrid model, and then carrying out P value calibration based on a fused saddle point approximation method; 4, constructing an aging clock based on a mixed causal effect graph model, evaluating a multi-dimensional causal relationship, and calculating the biological age of the individual; according to the method, clinical phenotype data and multi-omics data are fused, a machine learning and causal inference combined method is adopted, the individual aging degree and health risk are accurately analyzed, a high-performance aging clock model is provided for primary medical institutions, and scientific basis and decision support are provided for health management and early disease intervention.
Owner:SICHUAN UNIV

Linking human genes to clinical phenotypes using graph neural networks

PCT designated stage expiredWO2024249973A2BiostatisticsProteomicsClinical phenotypeGraph neural networks
This disclosure describes methods, non-transitory computer readable media, and systems that can utilize one or more machine learning models to predict relationships between human genes and phenotypes. For example, the disclosed systems can generate for human genes in relation to various clinical phenotypes. As a basis for generating such predictions, the disclosed systems can train a gene embedding neural network to determine relationships between genes and phenotypes using a two-stage training process that includes a supervised training stage and an unsupervised fine-tuning stage. In addition, the disclosed systems can utilize the gene embedding neural network to generate gene-to-phenotype scores indicating relationships between genes and phenotypes based on similarities among genes (as represented by gene embeddings). Further, the disclosed systems can utilize a diagnostic variant model to determine whether genomic samples exhibit diagnostic variants based on gene-to-phenotype scores as well as other variant-level features of the genomic samples.
Owner:ILLUMINA INC

Power transmission line real-time monitoring method and platform

The invention relates to the technical field of power transmission line monitoring, and discloses a power transmission line real-time monitoring method and platform. The method comprises the following steps: establishing a multi-omics data fusion subsystem to collect metagenome, metabolome, host genome and clinical phenotype group data of a target patient; inputting the data into a flora-metabolite combined network analysis model to construct an interaction network and extracting features; generating an incidence matrix based on the features and the host genome data and calculating indexes; generating indexes through a dynamic response algorithm in combination with the clinical phenotypic data and the indexes; and outputting a curative effect prediction result by using a transfer learning framework combined with modeling. The system comprises a data acquisition module, a network analysis module, a correlation calculation module, a dynamic response module and a joint modeling module. According to the method, multiple omics data are integrated, the flora and host relation is accurately mined, intelligent prediction of the micro-ecological transplantation curative effect is achieved, powerful support is provided for IBS personalized treatment, and meanwhile data processing and safety guarantee measures are taken.
Owner:NANJING SHENDA ENG TECH CO LTD

Big model technology-based biological information analysis system

The invention relates to the technical field of bioinformatics, in particular to a biological information analysis system based on a large model technology, which comprises a data analysis calibration module, a problem disassembly module, an analysis task arrangement module, a result mapping module and a feedback iteration module. According to the method, genome comparison and clinical phenotype timestamps are dynamically calibrated, time sequence dislocation deviation is eliminated, base complementary pairing is combined with protein network anomaly screening, low-abundance collaborative variation capture is enhanced, genotype-phenotype discrete distribution quantifies and unifies multi-modal data benchmark, and the problem of multi-source heterogeneous standardization deficiency is solved; the method comprises the following steps: classifying and integrating pathogenic gene semantic weights by structural variation, balancing a statistical threshold and a biological function, dynamically optimizing an analysis sequence, synchronously covering a key mutation region, improving function annotation of a non-coding region, integrating gene expression clustering and protein network topology in a three-dimensional distribution manner, breaking through two-dimensional space limitation, performing closed-loop feedback to correct a threshold iteration elimination rule, and finally obtaining a high-quality gene expression cluster. And the genetic heterogeneity false positive rate is reduced.
Owner:GUANXUN (HANGZHOU) ARTIFICIAL INTELLIGENCE TECHNOLOGY CO LTD

Pathogenic gene identification method and system based on multi-agent debate and medium

The invention relates to a pathogenic gene identification method and system based on multi-agent debate and a medium. The method comprises the following steps: acquiring gene detection data and clinical phenotype data; the data agent processes the acquired data, and calls a gene variation pathogenicity analysis operator and a molecular genetic large model to obtain first pathogenic gene information; the knowledge agent calls a molecular genetic large model to obtain second pathogenic gene information based on the first pathogenic gene information; the knowledge and data agents sequentially speak and debate pathogenicity of candidate pathogenic genes in the first or second pathogenic gene information on the basis of sorting results in the pathogenic gene information output by the knowledge and data agents; after each round of debate is finished, the debate agent judges whether the sorting results of the data and the knowledge agent on the candidate pathogenic genes are consistent or not, if the sorting results are consistent or the number of debate rounds reaches a threshold value, debate is finished, the debate agent conducts reasoning and outputs a result, and if not, the next round of debate is started. Compared with the prior art, the method has the advantages of no dependence on large-scale training data, high interpretability and the like.
Owner:SHANGHAI JIAOTONG UNIV

Systems and methods for extracting clinical phenotypes for alzheimer disease dementia from unstructured clinical records using natural language processing

An analytics computing device is provided. The analytics computing device includes a processor in communication with a database. The database configured to store electronic health record (EHR) data including structured EHR data and unstructured EHR data for a patient. The processor is configured to retrieve the EHR data from the database. The processor is further configured to parse, using a natural language processing model, the unstructured EHR data to retrieve one or more indicator phrases, the one or more indicator phrases correlated to an Alzheimer's disease (AD) diagnosis. The processor is further configured to identify, using a predictive model, the patient as being at risk for AD based on the retrieved indicator phrases and on the structured EHR data.
Owner:WASHINGTON UNIV IN SAINT LOUIS

Intelligent diagnosis and typing method for pneumonia-related ARDS

The invention discloses an intelligent diagnosis and typing method for pneumonia-related ARDS, and relates to the technical field of intelligent diagnosis and typing methods for ARDS, and the method comprises the steps: employing a data preprocessing method to carry out cleaning and standardization processing on pneumonia patient clinical data from MIMIC-IV and eICU databases, and obtaining a standardized data set; a correlation weight algorithm is adopted to screen 52 candidate variables in the standardized data set, and 18 key prediction factors are obtained; carrying out model training on the screened key predictive factors by adopting a machine learning stacking method to obtain a pneumonia-related ARDS diagnosis model; performing clustering analysis on the clinical data of the pneumonia-related ARDS patients by adopting a k-means clustering method, and dividing the patients into three clinical phenotypes based on nine input factors to obtain a subtype classification result; verifying a subtype classification result by adopting a random forest method to obtain a clinical subtype prediction model with high accuracy; and integrating and deploying the diagnosis model and the subtype classification model by adopting a webpage application program.
Owner:BEIJING ANZHEN HOSPITAL AFFILIATED TO CAPITAL MEDICAL UNIV

Rare disease information input and gene mutation analysis method and system based on phenotype matching and storage medium

The invention discloses a method and a system for assisting in inputting clinical information of rare diseases and analyzing gene mutation based on phenotypes. The method comprises the following steps: firstly, acquiring clinical information in voice, text and image forms of a patient through a multi-source data acquisition module, converting the clinical information into characters, and performing entity recognition and standardization processing to generate structured medical record data; secondly, extracting clinical phenotypes from the structured data; furthermore, a candidate gene list is obtained according to the gene-disease relationship, comprehensive scoring and sorting are carried out, and a concerned gene list is output. According to the method, efficient structured input and standardization of clinical information are realized, the accuracy and automation level of phenotype-gene matching are remarkably improved, the gene variation interpretation period is effectively shortened, and intelligent support is provided for precise diagnosis of genetic diseases.
Owner:WUHAN XINO MEDICAL LABORATORY CO LTD

Screening method of respiratory tract infection related biomarkers based on metatranscriptomics

The invention belongs to the technical field of biological detection, and discloses a screening method of respiratory tract infection related biomarkers based on metatranscriptomics. Respiratory tract infection samples with different clinical phenotypes are subjected to metatranscriptome sequencing, data quality control, comparison and transcript quantification, pathogen and host information is reserved, then genes which are stably expressed or remarkably changed in different groups are identified by combining differential expression analysis and co-expression analysis, and potential biomarkers are obtained. And taking an intersection gene of three machine learning algorithms including an LASSO algorithm, a random forest model and an SVM model to obtain the biomarker. The invention provides a biomarker screening method for rapid and accurate identification of respiratory tract infection.
Owner:中国人民解放军总医院第八医学中心

Construction and application of Primrose syndrome non-human animal model

The invention discloses construction and application of a Primrose syndrome non-human animal model, and belongs to the technical field of animal models and disease research. According to the invention, through a CRISPR / Cas9 technology, a codon CAC for coding 596th histidine in a No.14 exon of a mouse Zbtb20 gene is subjected to site-directed mutagenesis into CGC for coding arginine, and a hybrid mouse model for simulating pathogenic point mutation (p.H596R) of human Primrose syndrome is constructed. The model can stably reproduce key clinical phenotypes of the Primrose syndrome, including overgrowth after adult, serum IGF-1 rise, memory dysfunction and anxiety behaviors, and shows abnormal hippocampal neuronal development and synaptic transfer related pathways and the like. The invention provides an important experimental tool for deeply revealing the pathological mechanism of Primrose syndrome, developing drug screening and treatment intervention research and the like.
Owner:THE NAVAL MEDICAL UNIV OF PLA

A method and system for predicting immune response after respiratory viral infection using traditional Chinese medicine

This invention relates to the field of immune prediction technology and discloses a method and system for predicting immune responses after respiratory virus infection using traditional Chinese medicine. The method includes: acquiring an infection dataset; constructing patient markers based on the infection dataset, constructing infection markers based on the number of respiratory virus infections, determining data relationships based on patient markers, infection markers, and a disease course sliding window, and mapping fields in the infection dataset; extracting clinical phenotypic features based on status, infection, and immunity fields, matching detection item identifiers, determining multi-omics features, determining immune repertoire features based on genes and gene sequences, and determining features based on the four diagnostic methods of traditional Chinese medicine; and determining the predicted immune response after respiratory virus infection based on an intelligent immune response prediction model. This invention ensures the accuracy of predicting immune responses after respiratory virus infection using traditional Chinese medicine.
Owner:TIANJIN UNIV OF TRADITIONAL CHINESE MEDICINE

Method for screening of biomarkers associated with respiratory tract infections based on macro-transcriptomics

The application belongs to the technical field of biological detection, and discloses a screening method of respiratory tract infection related biomarkers based on macro-transcriptomics. The application performs macro-transcriptome sequencing on respiratory tract infection samples with different clinical phenotypes, performs data quality control, alignment, transcript quantification, retains pathogen and host information, and then identifies genes stably expressed or significantly changed in different groups by combining differential expression analysis and co-expression analysis, obtains potential biomarkers, and obtains the biomarkers by taking the intersection genes of three machine learning algorithms of LASSO algorithm, random forest model and SVM model. The application provides a screening method of biomarkers for rapid and accurate identification of respiratory tract infection.
Owner:中国人民解放军总医院第八医学中心

Multi-gene molecular diagnosis model as well as construction method and application thereof

The invention relates to the technical field of bioinformatics and medical data processing, and discloses a polygene molecular diagnosis model and a construction method and application thereof.The construction method comprises the steps that a data acquisition module constructs a genome, clinical phenotype and environmental exposure data matrix, a preprocessing module executes regression filling and standardizes continuous variables, and a data processing module performs data processing; the feature screening module executes double-layer screening by using LASSO and a random forest model to output a core feature subset, the model building module builds a logic regression architecture to calculate a baseline logarithm probability, and the dynamic updating module outputs a real-time risk probability in combination with follow-up visit environment data, a time adjustment coefficient and the baseline logarithm probability. And the interactive output module outputs a risk layering label and a feature contribution degree. According to the method, redundancy is eliminated through double-layer screening, the time dimension is introduced to adjust the real-time correction probability, visual attribution is realized in combination with the SHAP algorithm, and the dynamic monitoring capability and interpretability are improved.
Owner:HANGZHOU TRADITIONAL CHINESE MEDICINE HOSPITAL (HANGZHOU TRADITIONAL CHINESE MEDICINE HOSPITAL AFFILIATED TO ZHEJIANG UNIV OF TRADITIONAL CHINESE MEDICINE)

Mouse polycystic ovarian syndrome model induced by dehydroepiandrosterone under low-dose exposure of bisphenol A

The invention belongs to the technical field of medical animal disease model modeling, and particularly discloses a dehydroepiandrosterone-induced mouse polycystic ovarian syndrome model under bisphenol A low-dose exposure, specifically, a preparation method of the model comprises the following steps: continuously injecting a mouse for 21 days according to the injection amount of dehydroepiandrosterone of 6mg / 100g; the method comprises the following steps: carrying out intragastric administration on a mouse by using 10 mg / kg of bisphenol A on the 15th day of injection of dehydroepiandrosterone, and continuously carrying out intragastric administration on the mouse for 7 days to obtain the polycystic ovarian syndrome model of the mouse at the childbearing age. According to the mouse model obtained by DHEA modeling at the early stage of adolescence and BPA exposure modeling at the late stage of adolescence, the disordered mood cycle, obesity and high T level are obviously changed; and the human PCOS disease environment and clinical phenotype can be truly simulated.
Owner:KUNMING MEDICAL UNIVERSITY

Hepatolenticular degeneration clinical phenotype screening and determining method and system based on EHR

The invention discloses an EHR-based hepatolenticular degeneration clinical phenotype screening and determining method and system, relates to the technical field of medical data processing, and is used for judging which magnetic resonance imaging technology is adopted to detect a patient by using a selection rule based on clinical data of the patient. A patient is detected based on the adopted magnetic resonance imaging technology, imaging data are obtained, and the imaging data and clinical data are combined to generate a craniocerebral MR phenotype report of the patient. The system automatically judges and can dynamically adjust the image technology according to real-time data (such as disease courses, symptoms, laboratory examination results and the like) of the patient, a more suitable diagnosis tool is provided, an image mode is recommended in a personalized manner based on the condition of the patient, and the diagnosis accuracy is improved.
Owner:FIRST AFFILIATED HOSPITAL OF ANHUI UNIV OF CHINESE MEDICINE

Shank3 gene knockout mouse model as well as construction method and application thereof

The invention provides a Shank3 gene knockout mouse model as well as a construction method and application thereof, and belongs to the technical field of biomedicine. According to the CRISPR / Cas9 gene editing system provided by the invention, complete knockout of the whole Shank3 gene can be realized, and the CRISPR / Cas9 gene editing system can be used for constructing a Shank3 gene complete knockout model. In a mouse model provided by the invention, due to the complete knockout of the whole Shank3 gene, the homozygote has no Shank3 protein expression, and the heterozygote expression quantity is also reduced compared with that of a WT type, so that the Shank3 gene has important significance in functional development of the Shank3 gene or research of related diseases. The mouse model provided by the invention is applied to research on autism spectrum disorder, has higher similarity with the SHANK3 gene defect degree of a human autism spectrum disorder (ASD) patient, can be more properly used for simulating possible clinical phenotypes of human diseases, and has a wider application prospect.
Owner:CHILDRENS HOSPITAL OF FUDAN UNIV

Application of HGF receptor inhibitor in preparation of medicine for treating / preventing myasthenia gravis

The invention relates to the technical field of biomedicine, discloses application of an HGF receptor inhibitor in preparation of a medicine for treating / preventing myasthenia gravis, provides a novel treatment medicine for the myasthenia gravis, and innovatively discovers that the HGF receptor inhibitor can be used for treating / preventing the myasthenia gravis by regulating body inflammation and relieving the progress, clinical phenotype and pathological phenotype of MG diseases. The myasthenia gravis disease is treated.
Owner:THE FIRST AFFILIATED HOSPITAL OF CHONGQING MEDICAL UNIVERSITY

Cell analysis method and device integrating single cell transcriptome, block transcriptome and clinical phenotype information

The invention discloses a cell analysis method and device for integrating single cell transcriptome, block transcriptome and clinical phenotype information, and relates to the field of cell analysis. The method comprises the following steps: reconstructing single cell transcriptome data based on components associated with difference characteristics of different clinical phenotypes, extracting dynamic components associated with clinical phenotype changes in single cell data by using a machine learning model, and completing single cell data reconstruction by using orthogonal projection transformation and inverse transformation in the machine learning model. Mathematical derivation proves that the used machine learning model (partial least squares classification analysis) can extract features associated with clinical phenotype changes from single cell or block transcriptome data on the basis of keeping a data topological structure to the maximum, and the method can judge clinical phenotype related cell subgroups with higher reliability. And irrelevant noise is effectively reduced.
Owner:SHANGHAI GUAI BIOTECHNOLOGY CO LTD +1

Gene mutation point screening method and device based on clinical phenotype, terminal and medium

The present invention provides a method, apparatus, terminal, and medium for screening gene mutation points based on clinical phenotypes. The method includes: identifying candidate genes based on gene detection results, clinical text to be analyzed, and a multi-source database; calculating the basic weights of a first pathway; extracting candidate mutation sites within the genomic regions of the candidate genes and obtaining external evidence corresponding to the candidate mutation sites; performing phenotypic extraction on the clinical text to be analyzed to obtain a structured phenotype; inputting the structured phenotype, contextual information of the candidate mutation sites, and external evidence into a trained mutation site screening model to obtain intermediate semantic analysis results; determining the basic weights of a second pathway based on the intermediate semantic analysis results; obtaining a comprehensive weight for each candidate mutation site based on the basic weights of the first and second pathways; and screening the candidate mutation sites based on the comprehensive weights to obtain screening results. This application can perform site-level screening, improving the accuracy of gene mutation point screening.
Owner:PENG CHENG LAB

Systems and methods for discovery and analysis of markers

A business method for use in classifying patient samples. The method includes steps of collecting case samples representing a clinical phenotypic state and control samples representing patients without said clinical phenotypic state. Preferably the system uses a mass spectrometry platform system to identify patterns of polypeptides in said case samples and in the control samples without regard to the specific identity of at least some of said polypeptides. Based on identified representative patterns of the state, the business method provides for the marketing of diagnostic products using representative patterns. The present invention relates to systems and methods for identifying new markers, diagnosing patients with a biological state of interest, and marketing / commercializing such diagnostics. The present invention relates to systems and methods of greater sensitivity, specificity, and / or cost effectiveness.
Owner:SEER INC

Cross-domain disease prediction method based on graph self-supervised transfer learning

The invention discloses a cross-domain disease prediction method based on graph self-supervised transfer learning. The method comprises the following steps: processing functional magnetic resonance imaging data and clinical phenotype data; modeling by functional magnetic resonance imaging data of a subject to form a brain feature structure topological graph; nodes of the brain feature structure topological graph are sampled to obtain sub-graphs, and # imgabs0 # sub-graphs with the highest intimacy score are selected; mapping the node features of the target sub-graph to a low-dimensional vector space to obtain a node embedding matrix; the node embedding matrix is converted into a reconstruction matrix, and the Euclidean distance between an original feature vector and a reconstruction feature vector is calculated to obtain a generation learning score; establishing a comparison relationship between the target node and the adjacent sub-graph, and calculating a comparison learning score; generating a learning score and comparing the weighted sum of the learning score to obtain a prediction probability value of the disease category; and inputting to-be-migrated data into the prediction model to obtain a prediction result of the corresponding disease category. The cross-domain disease prediction accuracy and efficiency are improved.
Owner:FUJIAN NORMAL UNIV

Parkinson's disease freezing gait prediction method and device based on eye movement characteristics, equipment and medium

The invention provides a Parkinson's disease freezing gait prediction method and device based on eye movement characteristics, equipment and a medium. The method comprises the following steps: acquiring target information corresponding to a target object; the target information comprises target demographic data, target clinical features and target eyeball motion parameters collected at a certain time point, and / or target demographic data, target clinical features and target eyeball motion parameters continuously collected according to a preset frequency within a preset time; and inputting the target information into the target frozen gait prediction model, so that the frozen gait prediction model analyzes and processes the target information to obtain a static frozen gait risk assessment result and / or a dynamic frozen gait risk assessment result corresponding to the target object. According to the scheme, through multi-dimensional integration and collaborative verification of traditional clinical phenotypes and objective indexes of eye movement, non-invasive efficient evaluation of frozen gait risks is achieved, and objective basis and key technical support can be provided for early diagnosis and early treatment of disease subtypes.
Owner:SHANGHAI NINTH PEOPLES HOSPITAL SHANGHAI JIAO TONG UNIV SCHOOL OF MEDICINE

Base editing approaches for the treatment of beta-thalassemia

IVS1-110 (G>A) is one of the most common β-thalassemic mutations in the Middle East and Mediterranean area, representing >75% and >40% of β-thalassemic mutations in Cyprus and Greece, respectively. This point mutation is classified as a severe β+ mutation, and homozygous patients or compound heterozygotes harboring this mutation in combination with a β0 mutation have a clinical phenotype similar to β0 / β0 patients. Here, the inventors exploited adenine base-editors (ABEs) to correct the IVS1-110 (G>A) mutation in HSPCs from β-thalassemia patients and demonstrated the potential of this strategy to correct the pathological phenotype C observed during erythroid differentiation. In particular the inventors demonstrated that reverting the IVS1-110 (G>A) mutation using base editing corrected the β-thalassemic cell phenotype in vitro and in vivo. The present invention thus relates to base editing approaches for the treatment of β-thalassemia including sickle β-thalassemia.
Owner:INST NAT DE LA SANTE & DE LA RECHERCHE MEDICALE (INSERM) +3

Construction method and application of animal model of true microphthalmia

The present invention discloses a method for constructing an animal model of true microphthalmia and its application, which comprises: mutating the MFRP gene of a target animal by genetic engineering technology to obtain an animal model of MFRP gene p.P164S point mutation. The present invention constructs a mouse model of true microphthalmia by the above method, and the acquisition of the model can effectively simulate the clinical phenotype of true microphthalmia in humans, which is helpful to explore the specific regulatory mechanism of MFRP gene point mutation on mammalian eye development and high hyperopia, and can provide an animal model closer to the patient phenotype for subsequent drug screening and clinical research.
Owner:PEKING UNION MEDICAL COLLEGE HOSPITAL

Method for establishing an outer retinal tubular structure mouse model

This invention discloses a method for establishing a mouse model of outer retinal tubular structures, which is obtained by specifically knocking out the Lss gene in the mouse retina. This invention utilizes CRISPR / Cas9 gene editing technology to construct a mouse model of outer retinal tubular structures by specifically knocking out the Lss gene in the retina. The mouse model of outer retinal tubular structures constructed by this method is similar to the clinical phenotype of this type of retinal disease, providing a relatively ideal experimental animal model for studying the developmental regulation of the mammalian retina and the pathogenesis of retinal degeneration.
Owner:ZHONGSHAN OPHTHALMIC CENT SUN YAT SEN UNIV

Diabetes diagnostic kit for GCKR gene mutation and its application

The present invention discloses a diabetes diagnostic kit for GCKR gene mutation and its application. Two new gene mutation sites that lead to the phenotype of type 2 diabetes were identified: GCKR gene c.718C>T and c.1551G>T mutations. The present invention further expands the GCKR gene mutation diabetes diagnostic sites based on the Chinese hereditary endocrine and metabolic disease cohort and reported GCKR mutation case information, and further extracts the phenotypic characteristics of the new type of diabetes caused by GCKR gene mutation, constructs a diagnostic scoring model for diagnosing the new type of diabetes caused by GCKR gene mutation - GCKR score, and performs receiver operating curve verification to obtain an effective GCKR score diagnostic model. The present invention further constructs a precise diabetes typing diagnostic system. After obtaining the mutation information, the patient is scored and re-typed in combination with the patient's clinical phenotype for accurate diagnosis of diabetes. According to the precise diabetes typing, patients are treated, complications are monitored and prevented, and eugenics and prenatal care are provided with graded guidance.
Owner:THE SECOND XIANGYA HOSPITAL OF CENT SOUTH UNIV

Pre-pregnancy carrier screening genetic counseling system based on large language model

The invention provides a pre-pregnancy carrier screening genetic counseling system based on a large language model, which is applied to the technical field of gene sequencing analysis, and comprises a variation acquisition module used for screening to-be-sequenced gene data of a user to obtain pathogenic abnormality site information, converting pathogenic abnormality site information, disease clinical phenotypes, family history and individual past history into high-dimensional vectors; the variation retrieval module is used for dynamically retrieving the high-dimensional vector and recalling Top-K medical data in the semantic vector index database based on the semantic vector index database; the inference analysis module is used for evaluating the fertility genetic variation risk according to the Top-K related medical data and the high-dimensional vector to obtain an evaluation result; and the multi-round dialogue module enables the user to obtain an evaluation result through multi-round dialogues. The method has the advantages that the content such as fertility risks and intervention suggestions can be automatically generated, dialogue interaction with the patient can be carried out, and therefore the clinical genetic consultation burden is relieved.
Owner:RENJI HOSPITAL AFFILIATED TO SHANGHAI JIAO TONG UNIV SCHOOL OF MEDICINE

Artificial intelligence-based prediction method for serum-free medium components

ActiveCN122337352BCell phenotypeData set
The application relates to the technical field of culture medium prediction, and discloses a serum-free culture medium component prediction method based on artificial intelligence. The method comprises the following steps: constructing a phenotype condition vector according to a cell type identifier and a cell phenotype specification parameter, constructing a phenotype-formulation pairing data set according to historical culture batch data, training a conditional variational autoencoder with the phenotype condition vector as a conditional constraint, sampling a latent variable from a standard normal distribution, decoding the latent variable through a decoder to obtain a candidate culture medium formulation set, screening a candidate formulation with the minimum Euclidean distance through a forward verifier, and obtaining a recommended culture medium formulation. The application solves the problem that an existing serum-free culture medium component prediction method based on artificial intelligence cannot generate a culture medium formulation in reverse according to a clinical phenotype quality specification because the number of cells is taken as an optimization target.
Owner:BEIJING JIANQIANG WEIYE TECH CO LTD

Clinical feature-molecular indicator-based integrated data correlation analysis method and system

PendingCN122337659AData setMedicine
This invention provides a method and system for integrated data correlation analysis based on clinical features and molecular indicators, belonging to the field of medical data processing and intelligent prediction technology. The method includes: preprocessing collected clinical feature data and molecular indicator data to obtain a standardized structured dataset; extracting key clinical feature subsets and key molecular indicator subsets from the standardized structured dataset, and fusing them to generate a unified multidimensional fusion feature vector; dynamically calibrating at least three clinical phenotypic benchmarks in the unified multidimensional fusion feature vector using a clinical feature data spectrum, whereby the clinical phenotypic benchmarks are defined based on age feature spectrum nodes, infertility course trajectory critical scaling, and endometrial thickness quantification cutoff values. This invention can effectively complete the integrated correlation analysis of clinical features and molecular indicators and predict pregnancy outcomes, meeting the needs of precision clinical diagnosis and treatment.
Owner:REPRODUCTIVE HOSPITAL OF GUANGXI ZHUANG AUTONOMOUS REGION (REPRODUCTIVE HEALTH RES CENT OF GUANGXI ZHUANG AUTONOMOUS REGION)