24 results about "Disease taxonomy" patented technology

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 application relates to the technical field of natural language processing, and particularly discloses a disease classification method and device and a medium, the method comprising the following steps: performing data preprocessing and data enhancement on a medical text data set to obtain medical text data; analyzing the medical text data to construct a heterogeneous graph comprising patient nodes, symptom nodes and disease nodes; performing hierarchical attention training on the heterogeneous graph in combination with the relationships among the patient nodes, the symptom nodes and the disease nodes to obtain a disease classification model; inputting patient node data in the heterogeneous graph into the disease classification model to output disease probability and complete disease classification. The method prevents data sparseness through data enhancement, realizes relationship modeling by constructing a heterogeneous graph of medical text, thereby preventing data fragmentation, and finally adopts hierarchical attention training to dynamically screen weights, ensures effective information transmission, and ensures the robustness and interpretability of the medical text classification result.

The application discloses an anterior segment disease identification method, system, device and storage medium. The anterior segment disease identification method comprises the following steps: acquiring an image to be identified; inputting the image to be identified into a trained semi-supervised segmentation model to obtain a first image segmentation result output by the trained semi-supervised segmentation model; extracting a feature vector of the first image segmentation result; inputting the feature vector into a trained support vector machine model to obtain a disease classification result output by the trained support vector machine model; selecting a corresponding high-precision disease diagnosis model from a high-precision disease diagnosis model set based on the disease classification result, and taking the high-precision disease diagnosis model as a high-precision disease diagnosis model to be used; determining a second image segmentation result from the first image segmentation result based on the disease classification result; inputting the second image segmentation result and the image to be identified into the high-precision disease diagnosis model to be used to obtain an anterior segment disease identification result of the image to be identified, and the efficiency and accuracy of diagnosis are improved.

The application discloses a kind of multi-disease prediction systems based on binocular fundus image, including fundus feature extraction module, similarity-difference feature fusion module, clinical feature extraction module, multi-modal feature fusion module and multi-disease classification prediction module.System uses unified backbone network to extract left and right fundus image features, by similarity-difference feature fusion module, the features of two-way are added to each element to obtain preliminary fusion features, and the absolute value is obtained by subtracting each element to obtain different features, after normalization and 1 complement operation generates dissimilarity weight and similarity weight, separate out dissimilarity information and similarity information after weighting fusion according to hyperparameter α Fusion fundus feature is obtained;Multi-dimensional clinical variable features are extracted by two fully connected layers, after fundus features and clinical features are spliced, input multi-disease classification prediction module, and output disease prevalence probability.The application makes full use of the correlation and complementarity of binocular fundus image, and realizes high-precision, low-cost multi-disease screening combined with clinical indicators.

The present invention relates to the technical field of medical informatization, and in particular to a neurosurgical disease diagnosis and prognosis prediction system and method based on machine learning. The system includes six modules: a data collection module, a data processing module, a disease diagnosis module, a prognosis prediction module, a model evaluation module, and a result output module. The system integrates clinical data, image data and survival data. After preprocessing, screening and feature extraction, support vector machine and random forest algorithms are used to perform disease classification and prognosis prediction. By comparing the results of the algorithms, a diagnosis and a prognosis prediction are obtained. The model evaluation module dynamically adjusts the weights of the algorithms to optimize the prediction accuracy. Finally, the system integrates diagnosis, prediction and evaluation results to generate a visual diagnostic report. This innovative design enables multi-source data fusion, multi-model collaboration and dynamic optimization, significantly improves the diagnostic accuracy and prediction reliability, provides strong support for clinical decision-making, and is expected to play an important role in improving the level of diagnosis and treatment, improving patient prognosis, and optimizing the allocation of medical resources.

A grade of a specific microbial disease in a biological sample of a subject is determined. In one example, masked microbial reference genomes are used to determine the amount of free DNA molecules corresponding to a particular microbial species associated with a particular microbial disease. The masking may remove an area shared with another. In another example technique, end motifs are used for free DNA fragments from a subject and from a particular microbial species. A correlation between a subject and an amount of a set of terminal sequence motifs of a particular microbial species may be determined. The two groups of quantities of positive subjects are substantially more correlated than negative subjects.

The invention provides a distance perception Transform-based disease classification method and system, and relates to the technical field of image processing, and the method comprises the steps: obtaining a data set which comprises a plurality of case images and corresponding real disease classification labels; pre-processing the case image, and inputting the pre-processed case image into a constructed distance perception-based Transform disease classification model to obtain a corresponding predicted disease classification label; constructing a total loss function according to the real disease classification label and the predicted disease classification label, and training the distance perception Transform-based disease classification model; and inputting a to-be-classified case image into the trained distance perception-based Transform disease classification model to obtain a corresponding disease classification result. According to the method, distance perception fusion of case images is realized by constructing and training a distance perception-based Transform disease classification model, and the spatial continuity of a human body structure is emphasized in the fusion process, so that accurate classification of diseases is realized.

The invention discloses a disease classification prediction method and device based on prototype transfer learning, and a readable medium, and relates to the field of data processing, and the method comprises the steps: obtaining H-NMR metabolic spectrum data of serum samples of a person suffering from a first disease and a person suffering from a second disease, and carrying out the preprocessing, corresponding metabolome features are obtained, and a source domain data set and a target domain data set are constructed; constructing a disease classification prediction model, wherein the disease classification prediction model comprises a feature encoder and a classifier; performing prototype transfer learning-based training on the disease classification prediction model by using the source domain data set and the target domain data set to obtain a trained disease classification prediction model; and acquiring H-NMR metabolic spectrum data of a serum sample of a to-be-predicted person suffering from the second disease, performing preprocessing to obtain corresponding metabolome characteristics, and inputting the metabolome characteristics into the trained disease classification prediction model to obtain a disease classification result of the to-be-predicted person. According to the method, the classification accuracy and the model generalization performance can be effectively improved.

This invention provides a semantically guided hybrid expert-based multi-disease classification method and system, relating to the fields of artificial intelligence and medical information technology. The method includes: forming robust disease classification and expert assignment strategies by performing semantic embedding and clustering analysis on data samples; constructing a multi-disease classification network model based on disease categories and the number of experts; the multi-disease classification network model uses a hybrid gating mechanism to generate weight vectors that fuse the classification probabilities output by multiple experts, and is jointly trained using a dynamic classification loss including dynamic grouping to full classification and a gating loss including assignment conflict penalties. This method effectively decomposes complex classification tasks into manageable sub-tasks, handles different disease types or feature patterns through specialized mechanisms, simplifies the learning of complex decision boundaries, and improves the accuracy and robustness of multi-category disease classification.

A few-shot learning method for ICD disease classification, using an automatic ICD coding method based on deep learning, learning the standard name of each code in the international disease classification using a gating mechanism and regularization method, the standard name of each code in the international disease classification as an additional knowledge, and through a gating mechanism and regularization method, the standard name of the ICD code is integrated into the model, which can enrich the features learned by the model, so that the model can learn a small amount of samples to achieve high classification performance.

The invention discloses a disease classification method fusing multi-modal brain function connection space-time and causal features, which comprises the following steps: acquiring brain image data of a subject to construct a data set for training; constructing a deep learning network model which comprises a time sequence coding module, a cross attention fusion module, a modal fusion module and a graph convolution prediction module; and training the deep learning network model by using the data set to obtain a prediction model for disease classification. The invention also provides a disease classification system. According to the method provided by the invention, the time sequence features, the relevance features and the causality features are efficiently fused, and finally accurate disease classification is realized.

Provided herein are multi-modal methods and systems of diagnosing one or more disease, as described elsewhere herein.

The present disclosure provides systems and methods for machine learning classification and assessment of disease based on gene expression data. In an aspect, a method for determining a disease state of a subject may comprise: (a) assaying a biological sample obtained or derived from the subject to produce a data set comprising gene expression measurements of the biological sample at each of a plurality of disease-associated genomic loci; (b) computer processing the data set to determine the disease state of the subject; and (c) electronically outputting a report indicative of the disease state of the subject. In some embodiments, the plurality of disease-associated genomic loci comprises single nucleotide polymorphisms (SNPs). In some embodiments, the disease comprises a lupus condition. In some embodiments, the disease comprises cardiovascular disease (CVD).

The application discloses a common animal disease early warning method and system based on breeding environment detection data, and relates to the technical field of animal disease early warning. The method comprises the following steps: interacting with a target breeding environment, obtaining breeding environment detection data and neighborhood environment data; determining breeding object information of the target breeding environment, calling a pre-constructed disease classifier for qualitative classification analysis, and outputting a result as a potential disease set; determining a risk accumulation rate set of M environment indexes in the breeding environment detection data for the potential disease set according to historical disease data; generating predicted environment sequence data of the target breeding environment according to the neighborhood environment data and the breeding environment detection data, performing risk accumulation calculation on the potential disease set, and obtaining an accumulated disease risk of each potential disease; generating an animal disease early warning report based on the multiple accumulated disease risks, and performing early warning response. The application solves the technical problem of inaccurate animal disease early warning in the prior art.

The present disclosure provides systems and methods for machine learning classification and assessment of disease based on gene expression data. In an aspect, a method for determining a disease state of a subject may comprise: (a) assaying a biological sample obtained or derived from the subject to produce a data set comprising gene expression measurements of the biological sample at each of a plurality of disease-associated genomic loci; (b) computer processing the data set to determine the disease state of the subject; and (c) electronically outputting a report indicative of the disease state of the subject. In some embodiments, the plurality of disease-associated genomic loci comprises single nucleotide polymorphisms (SNPs). In some embodiments, the disease comprises a lupus condition. In some embodiments, the disease comprises cardiovascular disease (CVD).

The application discloses a disease classification model training method and device and a disease classification system, and applies to the technical field of data processing. The method comprises the following steps: obtaining target disease gene data and a transcriptome data set associated with a target disease; performing classification processing on the transcriptome data set to obtain a discovery set, a training set and a test set; obtaining a plurality of target gene pair features associated with the target disease according to the discovery set and the target disease gene data; processing the training set and the test set according to the plurality of target gene pair features to obtain a processed training set and a processed test set; and performing model training and testing by using a machine learning method according to the processed training set and the processed test set to obtain a disease classification model. In the classification system, the transcriptome data of a to-be-tested sample associated with the target disease is classified according to the disease classification model, and the category of the to-be-tested sample is obtained. The application improves the training precision and the training efficiency of the disease classification model.

The invention provides an intelligent disease identification and classification method and system based on multi-modal data fusion, and the method comprises the steps: S1, collecting multi-modal data of a medical image, a physiological signal and genome data, and carrying out the preprocessing of the multi-modal data; s2, extracting multi-scale features from the medical image through a convolutional neural network, extracting time sequence features from the physiological signal by using a bidirectional LSTM network, and extracting gene association features from the genome data based on a graph neural network; s3, fusing the three modal features by using a self-attention mechanism, dynamically adjusting the weight, and generating a global feature; and S4, inputting the global features into a classification network, and completing disease classification based on a cross entropy loss function. The system comprises a data preprocessing module, a multi-modal feature extraction module, a fusion module and a classification module, multi-modal deep fusion, self-attention weight distribution and modular design are provided, and the accuracy, robustness and clinical adaptability of disease classification can be improved.

The invention discloses a diagnosis report generation method based on a chest medical image, and the method comprises the steps: S1, building a model: introducing a multi-view feature learning module, a disease classification guiding module, a dual-order cooperative coding module and mixed feature fusion, and fusing a convolutional visual extractor and a Transform network architecture, constructing a multi-modal report generation model architecture by adopting an encoder and decoder framework; s2, training a model: pre-training to obtain a disease classifier; and S3, generating a report: inputting to-be-tested medical image data, and generating a diagnosis report by using the diagnosis report generation model. According to the method, a multi-view learning strategy is adopted, and complementary information under different views is effectively utilized; and meanwhile, deep fusion of organ features and global features is realized by means of a double-order collaborative coding module, and a comprehensive and accurate diagnosis report is generated.

The application discloses a disease classification model training method, a disease classification method and a system. The disease classification model training method comprises the following steps: acquiring a spectrum image set; converting the spectrum image set into a training image set based on a group of optical parameters of a super surface light guide element; training a disease classification model by using the training image set to obtain a loss value; updating at least one of the M groups of optical parameters of the super surface light guide element or both the at least one of the M groups of optical parameters of the super surface light guide element and the model parameters of the disease classification model based on the loss value to obtain a trained disease classification model and an optimal group of optical parameters of the super surface light guide element. The application converts a spectrum image into an optical image based on a group of optical parameters of a super surface light guide element, and through model training, the combination of the super surface light guide element and the model can realize disease classification prediction.

The invention discloses a medical report automatic generation method and system based on category guidance. The method comprises the following steps: acquiring a medical image; the medical image is analyzed through a pre-trained disease classification model, diagnosis category information corresponding to at least one disease entity is generated, and the diagnosis category information is used for representing the existence state of the disease entity in the image; based on the diagnosis category information, guiding prompt information is derived; and controlling a report generation model to convert the medical image into a structured diagnosis report text by utilizing the guide prompt information. Diagnosis category information is introduced to serve as a guiding mechanism, the model can more accurately pay attention to image features related to diseases, and the possibility of missed diagnosis or misdiagnosis is reduced; in the knowledge enhancement step, the latest medical evidence is fused into the generation process by retrieving and fusing structured clinical knowledge; according to the method, the professional, dynamic and interpretable report generation is realized through a multi-level guidance and fusion mechanism.

A computer-implemented, machine learning method for explaining and verifying correctness of an output of a large language model (LLM) includes splitting two sets of documents into a plurality of text spans by inputting the two sets of documents into a coarse chunking algorithm. Attribution links are generated using the text spans as input to a specialized LLM that has been trained to output a likelihood that one of the text spans in the first portion relates to one of the text spans in the second portion. Hallucination candidate text spans are identified in the text spans based on the attribution links. The hallucination candidate text spans and the attribution links are presented via a user interface. The method has applications including, but not limited to, use cases in computational biology and medical Al and healthcare for disease classification or supporting decision making in diagnosis and treatment of patients.

A document creation support apparatus includes at least one processor. The processor generates text describing a classification of a disease for at least one feature portion included in an image, and includes, in the text, a description regarding a relevant portion related to the classification of the disease described in the text.

The invention discloses a disease classification method and device based on metabonomics and a channel attention residual network, and the method comprises the steps: obtaining 1H-NMR metabolic spectrum data of human serum samples in different disease states, carrying out the sample expansion through employing an SMOTE algorithm, and obtaining the expanded 1H-NMR metabolic spectrum data; performing feature selection on the expanded 1H-NMR metabolic spectrum data by using an XGBoost model, screening out key features, and constructing training data in combination with corresponding disease categories; constructing a disease classification model based on the channel attention residual network, and training the disease classification model by adopting the training data to obtain a trained disease classification model; and acquiring 1H-NMR metabolic spectrum data of serum samples of to-be-classified persons, selecting corresponding key features, inputting the selected key features into the trained disease classification model, and predicting to obtain a corresponding disease category result. According to the method, the overfitting problem under the small sample and high dimension conditions can be effectively relieved, and the classification accuracy can be improved.

The application provides a disease classification model construction method and device, electronic equipment and storage medium. The method comprises the following steps: performing wave band screening on a plasma ATR-FTIR spectrum; dividing the spectrum into an original training set and a test set by using a KS algorithm; performing image processing by using a Markov transition field method; converting a two-dimensional matrix into a one-dimensional feature vector; performing dimension reduction processing on the one-dimensional feature vector by using principal component analysis; performing sample augmentation on minority class samples in the dimension reduction training set by using a synthetic minority over-sampling technique; combining the dimension reduction training set and virtual samples to obtain an augmented training set; and constructing a classification model by using a joint sparse boundary Fisher regularization classification algorithm. The application amplifies the weak spectral difference between majority class samples and minority class samples, and can balance the number of majority class samples and minority class samples in the training set, significantly improves the recognition sensitivity of target class patients, and is used for classifying mental diseases or neurodegenerative diseases.