315 results about "Clinical information" patented technology

The invention discloses an intestinal cancer immune response graph neural network prediction method, a medium and equipment, and the method comprises the steps: collecting pathological image information, immunodetection information and basic clinical information, extracting a tissue space distribution characteristic spectrum through a deep convolutional network, and constructing a graph neural network model in combination with an immunomarker expression characteristic matrix; spatial interaction characteristics of a tumor microenvironment are modeled by adopting a graph attention mechanism, finally a treatment response probability, an optimal treatment opportunity and an adverse reaction risk are predicted through a multi-task learning framework, and a clinical decision report containing a prediction response curve, a risk early warning threshold and a treatment time window suggestion is output. According to the method, through multi-modal data fusion and spatial interaction modeling, accurate prediction of intestinal cancer immunotherapy response is realized, and a more comprehensive reference basis is provided for clinical decision making.

The invention provides a traditional Chinese medicine electronic medical record natural language processing and knowledge graph construction method and system. The method belongs to the technical field of the crossing field of traditional Chinese medicine informatization, artificial intelligence natural language processing and knowledge engineering, and comprises the following steps: performing multi-granularity semantic unit division on the traditional Chinese medicine electronic medical record to generate traditional Chinese medicine text semantic unit data; constructing a multi-granularity semantic decoupling engine according to the traditional Chinese medicine text semantic unit data so as to construct a traditional Chinese medicine text semantic analysis framework; performing traditional Chinese medicine unstructured text deep analysis according to the traditional Chinese medicine text semantic analysis framework, and performing multi-dimensional semantic feature extraction to obtain traditional Chinese medicine text semantic feature data and medical record time sequence data; through multi-granularity semantic unit division and deep analysis, the unstructured text in the traditional Chinese medicine electronic medical record can be effectively converted into structured semantic data, and the ability to understand and process traditional Chinese medicine clinical information is further improved.

The invention is applicable to the technical field of clinical medicine, provides a clinical multi-modal cancer drug response prediction method based on feature reconstruction, constructs a clinical multi-modal model for drug response prediction of diffuse large B-cell lymphoma, and aims to predict the drug response of diffuse large B-cell lymphoma by integrating gene sequencing and clinical multi-modal data. And accurate drug reaction prediction is realized. The model adopts an end-to-end multi-stage processing flow: firstly, extracting gene features through TransP-Net, and processing multi-modal clinical data by using a clinical information encoder; then, pseudo-gene features are generated through a clinical-genome filling module to deal with the data missing problem; and finally, multi-modal deep fusion is realized through a clinical information decoder, and a prediction result is output. According to the method, data characteristics and working processes in a real clinical environment are fully considered, two conditions of complete gene data and missing gene data can be processed at the same time, and the method has a good clinical transformation prospect and application value.

The invention discloses a breast cancer lymph node metastasis prediction system based on a gene spectrum, and relates to the technical field of breast cancer prediction systems. Comprising a data acquisition module which collects gene spectrum data of a breast cancer patient and collects detailed clinical information of the patient; the preprocessing module is used for carrying out data cleaning and data normalization processing on the collected data; and the feature extraction module is used for extracting principal component features by applying principal component analysis on the basis of the gene expression data. According to the method, gene expression data are considered, various gene spectrum data such as gene mutation and copy number variation and detailed clinical information are integrated, the biological characteristics of the breast cancer can be reflected more comprehensively, and the prediction accuracy is improved.

The invention discloses a device for awareness level evaluation and a storage medium. The apparatus comprises: a processor; the device realizes the following operations: collecting clinical information of a person to be assessed and a task state electroencephalogram signal under a target stimulation normal form; extracting frequency domain characteristics of a specific frequency band and spatial-temporal characteristics of a target event related potential based on the task state electroencephalogram signal, and combining the frequency domain characteristics and the spatial-temporal characteristics into a corresponding electroencephalogram topographic map; inputting the corresponding electroencephalogram topographic map into a multi-modal large language model, and performing image feature extraction by using an image encoder to obtain electroencephalogram features; inputting clinical information into the multi-modal large language model, and performing text feature extraction by using a text encoder to obtain text features; and performing cross-modal attention calculation fusion on the electroencephalogram features and the text features by using a cross-modal fusion module to realize consciousness evaluation so as to output a consciousness evaluation result. By means of the scheme, the consciousness level of the patient can be automatically and accurately evaluated.

The invention discloses a post-stroke depression risk prediction system based on cerebral small vascular diseases and inflammatory markers, and relates to the technical field of computer-aided engineering, the post-stroke depression risk prediction system comprises: a data acquisition module acquires CSVD image data, serum inflammatory markers and clinical baseline information; the data preprocessing module processes image denoising registration, fills up marker missing values and encodes clinical information; the CSVD feature extraction module extracts image omics features and quantifies severity; the inflammation marker module calculates statistical characteristics and inflammation intensity; the multi-dimensional fusion module integrates features and eliminates redundancy; the risk prediction module is trained by using an improved attention CNN-LSTM model; the result output module visualizes risk and intervention suggestions; the model dynamic optimization module updates parameters by incremental learning. According to the method, multi-source key data are integrated, the prediction accuracy and generalization ability are improved, clinical interpretation and dynamic adaptability are achieved, early recognition of post-stroke depression is assisted, and patient prognosis is improved.

The invention discloses a traditional Chinese medicine intelligent diagnosis and treatment system and method. The diagnosis and treatment system comprises a medical thinking layer used for clinical information reasoning decision; the expert mixed framework layer is used for refined data processing, analysis and reasoning; the clinical tool layer is used for collecting and analyzing clinical information; the interaction layer is used for providing digital human, voice, image-text and other interaction modes for patients and doctors, and the medical thinking layer and the expert mixed framework layer are in communication interaction with the interaction layer and the clinical tool layer. The diagnosis and treatment system has the advantages that expert models in different fields are combined through the expert mixed framework layer to achieve refined and intelligent support and optimization of the traditional Chinese medicine diagnosis and treatment process, the traditional Chinese medicine clinical real diagnosis and treatment process is simulated, the medical thinking layer is applied to conduct clinical information reasoning and decision making, and the diagnosis and treatment efficiency is improved. And the reliability and interpretability of the traditional Chinese medicine intelligent diagnosis and treatment paradigm are improved, so that a grassroots traditional Chinese medicine doctor can be assisted to improve the differentiation accuracy, and the popularity of traditional Chinese medicine diagnosis and treatment services is promoted.

The invention provides a rare disease risk screening model training system and method, a screening system and a medium, and belongs to the technical field of medical information. According to the invention, an innovative three-stage architecture design is adopted, unified identification of all rare disease types is realized, and the blank in the prior art is filled. When only basic clinical information exists, a rare disease high-risk patient can be accurately identified, the diagnosis time is remarkably shortened, and a treatment precedent is won for the patient. The system adopts a small parameter quantity model integration strategy, reduces hardware requirements and maintenance cost, can be widely deployed in basic medical institutions, and promotes balanced distribution of medical resources. Through the technical measures of nested cross validation, algorithm comparison, threshold optimization and the like, the system has high accuracy and reliability, and the credibility of doctors to the system is enhanced.

The invention discloses a clinical intelligent decision-making method based on proxy workflow and a storage medium. Comprising the following steps: acquiring and preprocessing clinical information of a patient, and constructing a candidate disease set; and constructing a proxy directed workflow. In the retrieval stage, the diagnosis criteria corresponding to the candidate diseases are retrieved and aggregated from the diagnosis criteria library rechecked by the experts to form working memory. The preliminary diagnosis stage model node generates a preliminary candidate diagnosis set in combination with work memory and patient medical history and physical examination. And the final diagnosis stage generates a final diagnosis result based on the preliminary candidate diagnosis and the complete clinical information. And when the global confidence is lower than a threshold value, the model node pointedly checks an information source and updates reasoning and confidence. A successful reasoning track forms a demonstration set after manual auditing, the demonstration set is used for supervising a fine tuning model to obtain an initial strategy, multiple structured outputs are generated through grouping sampling, relative strategy updating is carried out in combination with reward signals and reference strategy regularization constraints, and optimization and stable improvement of the model diagnosis capability are achieved.

The invention specifically relates to a clinical deterioration risk prediction and early warning system and method based on machine learning, and relates to the technical field of medical artificial intelligence and clinical informatics, and the method comprises the steps: obtaining multi-dimensional time series data in real time; constructing a dynamic feature engineering vector; machine learning risk prediction; judging a risk threshold value and triggering early warning; and interpretation and suggestion generation driven by the large language model. According to the method, multi-dimensional time sequence data is continuously acquired in real time, multi-sliding window statistical features and standardized clinical deterioration scores are extracted in combination with dynamic feature engineering, and accurate quantitative risk prediction of multiple disease deterioration types such as sepsis and respiratory failure is realized by means of machine learning models which are specifically trained by XGBoost, LSTM and the like. The problem that traditional early warning depends on manual judgment and is high in hysteresis is effectively solved; medical staff can be helped to quickly grasp the core inducement of disease deterioration, and a standardized and landing action scheme is provided.

The invention discloses a structured information extraction system for a mental disorder electronic medical record based on a knowledge graph and a natural language, and belongs to the technical field of medical information processing. According to the system, firstly, core concepts such as diseases, symptoms and drugs are extracted from an authoritative guide to construct a mental disorder knowledge graph, and a standardized clinical knowledge base is established; then pre-training and fine-tuning the deep learning model on a large number of biomedical texts and desensitized medical records to enable the deep learning model to have a medical language understanding ability; performing preprocessing, named entity recognition and entity linking on the electronic medical record text, and mapping spoken expressions to standard medical terms; inference is carried out by utilizing a relation extraction model and combining with a knowledge graph to complement implicit clinical information; and finally, structured data output meeting the standards of FHIR and the like is generated. According to the method, through deep fusion of knowledge driving and data driving, the problems of insufficient semantic understanding and weak generalization ability of a traditional method are effectively solved, and the accuracy and clinical value of electronic medical record structured information extraction are remarkably improved.

The invention belongs to the technical field of medical image processing, and discloses a medical image diagnosis system based on image and text feature fusion, and the system comprises an image processing module which is responsible for carrying out the enhancement, segmentation and feature extraction of a medical image; the text analysis module is responsible for extracting key clinical information from the electronic medical record; the semantic alignment and feature fusion module is used for embedding image features and text features into a unified vector space to realize fusion of multi-modal data; the model training and optimizing module is responsible for training and optimizing a medical diagnosis system model; and the clinical application module is responsible for applying the trained medical diagnosis system model to an actual medical environment to assist doctors in disease diagnosis. According to the medical image diagnosis system based on image and text feature fusion, by combining image enhancement, morphological processing, NLP analysis and multi-modal feature fusion, the illness state of a patient can be understood more comprehensively, the diagnosis accuracy is improved, and a more reliable auxiliary decision making basis is provided for doctors.

The invention belongs to the technical field of medical image intelligent diagnosis, and provides a breast cancer focus benign and malignant discrimination method based on a gated multi-expert mechanism. The method comprises the following steps: firstly, carrying out standardization and semantic preprocessing on a mammary gland X-ray image, a BI-RADS imaging report and structured clinical data, embedding age, mammary gland density and focus position information into a text template in a natural language form, and realizing unified expression of multi-modal input; secondly, extracting image features by utilizing a ResNet network and a simplified CLIP model, obtaining a text semantic vector by adopting a Bio-ClinicalBERT model, and establishing two sub-paths of a lump expert and a calcification expert in a Transform structure; further, an expert weight is dynamically generated through a gating routing mechanism, and soft routing fusion is executed; and finally, outputting benign and malignant results of the breast cancer focus by the binary classification module. According to the method, deep fusion and dynamic collaboration of the mammary gland X-ray image, the BI-RADS text and the clinical information are realized, and the accuracy and interpretability of breast cancer discrimination can be remarkably improved.

The invention relates to the field of otological disease prediction, in particular to an otological disease prediction method based on multi-modal data fusion and confidence evaluation. According to the technical scheme, the method comprises the following steps: acquiring an otoendoscope digital image, broadband tympanic image measurement data and structured or unstructured clinical information; carrying out integrity verification and quality verification on the collected data, and checking whether the resolution of the digital image of the otoendoscope meets the minimum pixel requirement or not and whether the information is complete or not; preprocessing the otology data and extracting multi-modal features, and extracting an ear endoscope digital image feature vector, a feature vector representing broadband tympanic chamber image data and a clinical information feature vector; fusion is carried out after feature extraction, and confidence evaluation and recurrence risk prediction are carried out after fusion. According to the method, the three-mode data of the image, the physiological signal and the clinical text are deeply fused through the attention mechanism, so that the prediction accuracy of the otological diseases is remarkably improved. The method is suitable for otological disease prediction.

The invention provides a glycolipid metabolism related gene-based endometrial cancer prognosis prediction model construction method, which comprises the following steps of 1, acquiring data containing gene expression and clinical information, and preprocessing the data; 2, differential expression and prognosis gene screening; 3, constructing a prognosis model; 4, analyzing model gene enrichment; 5, evaluating the immunocompetence of the two GLRG related dangerous groups; and step 6, statistical analysis. According to the technical scheme, more accurate and reliable prognosis evaluation is provided for endometrial cancer by comprehensively analyzing multi-dimensional information such as gene expression, immune characteristics, mutation characteristics and drug sensitivity.

The invention relates to the technical field of data synchronization, in particular to a digestive system department clinical information acquisition and synchronization system, which comprises a multi-source heterogeneous acquisition module for generating a standardized diagnosis and treatment sequence, a characteristic spectrum construction module for mapping a text and an image into vector nodes and constructing a dynamic diagnosis and treatment characteristic spectrum, the state fingerprint verification module calculates a map fingerprint Hamming distance to position a difference feature node, and the incremental collaborative synchronization module constructs an incremental data packet and sends the incremental data packet to the central server. According to the method, the multi-dimensional characteristic spectrum based on the diagnosis and treatment time sequence is constructed, discrete images and texts are converted into topological association units, heterogeneous data semantic level alignment and integrity verification are achieved, version conflicts and information faults are eliminated, meanwhile, a dynamic hash fingerprint difference comparison strategy is adopted, accurate recognition is achieved, and only substantial change nodes are transmitted; and the network load is reduced, and high real-time consistency and zero-loss circulation of whole-flow information are ensured.

The present invention provides a multi-modal model construction method and system for predicting the efficacy of sorafenib in hepatocellular carcinoma. The method comprises: step 1, collecting clinical information of a target patient, and generating a whole slide image; step 2, preprocessing clinical data, and retaining clinical features as input for a multi-modal deep learning model; step 3, preprocessing the whole slide image; step 4, constructing an image model, acquiring patch-level scores of the pathological image on the basis of the preprocessed image and by using different aggregation algorithms, and predicting the score of the whole pathological image to obtain best model features; step 5, constructing a multi-modal model, performing modal fusion on the best model features and the clinical features, and outputting an image-level or patient-level prediction result; and step 6, testing and evaluating the model. The present invention achieves bimodal input of a pathological image and clinical information, fully utilizes the complementarity of the two types of modal data, and thus improves prediction accuracy.

The present invention relates to an AI-based system and method for generating enhanced radiology reports. The system comprises a database for storing multimodal patient data, a natural language processing (NLP) module for extracting clinical information, and a machine learning module for correlating the clinical information with radiology images to identify diagnostic insights. An AI-based report generation module analyzes the images and clinical information to generate a preliminary report, which is refined based on radiologist input. The generated report is then integrated into the patient's electronic health record. The system employs techniques such as multimodal deep learning, active learning, explainable AI, and federated learning to enhance diagnostic accuracy, capture expert feedback, provide transparency, and enable multi-institutional collaboration. The invention aims to improve the accuracy, efficiency, and value of radiology reporting in patient care.

The invention discloses a cerebral apoplexy patient postoperative neural function real-time monitoring method. The method comprises the steps that brain MRI image data and clinical information of a to-be-monitored patient and post-operation electroencephalogram data collected in real time are collected and preprocessed; respectively extracting neurophysiological features and radiomics features of the patient to be monitored based on the preprocessed data; performing significant feature screening on the clinical information, the neurophysiological features and the radiomics features, performing preprocessing on the screened data, and combining minimum absolute contraction and selection operator regression analysis to obtain quantitative electroencephalogram data feature indexes and radiomics scores; inputting the screened clinical information, the quantitative electroencephalogram data characteristic index and the radiomics score of the to-be-monitored patient into a trained prediction model, and predicting a risk index of early neurological deterioration of the to-be-monitored patient; the problem that the evaluation result is inaccurate due to the fact that a single clinical feature is adopted to evaluate the neural function in a traditional method is solved.

The invention, which relates to the technical field of cloud data diagnosis, discloses a cloud data sharing and diagnosis platform for microbial inspection, comprising a data preprocessing module, a federal modeling module, a multi-modal fusion module, a diagnosis scoring module, a block chain evidence storage module, a trusted sharing module and a dynamic optimization module. The data preprocessing module is used for performing format unification and feature extraction on original microbiological inspection data from a plurality of medical institutions by adopting a standardized coding method, the original microbiological inspection data comprises microscopic images, mass spectrum peak maps, drug sensitivity results and clinical information, and a structured inspection feature set is output; and the federated modeling module is used for carrying out cooperative training on locally deployed initial diagnosis models of all mechanisms by adopting a federated learning method based on differential privacy protection, locally calculating gradient information by utilizing the structured test feature set, and uploading gradient parameters subjected to noise disturbance to the central server for aggregation updating.

The invention belongs to the technical field of radiooncology, artificial intelligence and medical image fusion, and particularly relates to a model construction method and system for predicting the radiation pneumonitis risk of a patient receiving immune combined radiotherapy. According to the method, for a non-small cell lung cancer patient receiving immune checkpoint inhibitor (ICIs) combined radiotherapy, clinical information and radiotherapy dose parameters of the patient are collected, a positioning CT image and dynamic immune factor data are simulated, multi-source features including radiomics features, an immune change curve and dose volume indexes are extracted, and a multi-modal fusion prediction model is constructed. The system integrates automatic data input, feature extraction, model training and risk output modules, can output individual radiation pneumonitis risk scores, provides risk grading and dose intervention suggestions, and has high prediction accuracy and clinical interpretability. The method can be widely applied to individualized risk management and precise treatment of non-small cell lung cancer immune combined radiotherapy patients.

The invention discloses a medical document processing method and system based on a double-pipeline architecture, and relates to the technical field of document processing. According to the medical document processing method based on the double-assembly-line architecture, through a closed-loop process of document classification, preprocessing, double-assembly-line directional parallel processing and hierarchical vectorization storage, precise adaptation and efficient processing of multi-format and multi-type medical documents are achieved, the information loss rate and the key information truncation rate are greatly reduced, and the medical document processing efficiency is improved. According to the method, the document processing efficiency and the data standardization degree are improved, the warehousing success rate and the data traceability of the vector library are ensured, high-quality and structured data source support is provided for subsequent medical intelligent retrieval, clinical question and answer and retrieval enhancement generation system application, the knowledge base construction and maintenance cost is remarkably reduced, and the method is suitable for popularization and application. The problems that in existing medical document processing, medical semantics are not taken into consideration, so that key clinical information is easy to cut off, and a single processing flow cannot adapt to a structured guide and an unstructured case are solved.

The invention belongs to the technical field of tumor molecular diagnosis and biological information analysis, and relates to a high-throughput sequencing method and system for monitoring acute lymphocytic leukemia (MRD). Through targeted sequencing with a unique molecular identifier and / or a double-chain tag, error modeling based on a background noise spectrum and statistics / machine learning pseudo variation filtering, ultra-deep accurate detection of IG / TCR cloning and related gene low-frequency variation is realized. And an artificial intelligence recurrence risk prediction model is established by combining a time sequence MRD index, cloning diversity and clinical information, and a structured clinical report is output and docked with LIS / HIS. According to the method, the sensitivity and the specificity of ALL minimal residual disease detection can be remarkably improved, dynamic evaluation on leukemia cloning evolution and recurrence risks is realized, and a reliable basis is provided for individualized treatment decision and long-term follow-up visit.

The invention discloses a cerebral infarction swallowing dysfunction risk prediction method based on machine learning, and belongs to the technical field of risk prediction, and the method comprises the following steps: S1, retrieving and collecting a plurality of data sets related to cerebral infarction from an MIMIC IV database; s2, original data in the data set are preprocessed, clinical information is strictly verified, and data which does not conform to research standards are removed; s3, predicting the processed data through a plurality of models, and finding out the model with the best performance; and S4, continuously training the optimal model, constructing a swallowing function risk prediction model of the optimal model, deploying the optimal model to a webpage based on a Streamline framework, predicting the swallowing disorder risk of the patient, and generating a personalized SHAP force field graph. According to the method, a plurality of machine learning models are constructed, the model with the optimal performance is selected, and the cerebral infarction dysphagia risk is accurately predicted in combination with clinical data.

The invention provides a doctor influence comprehensive evaluation method based on multi-modal data fusion, and the method comprises the steps: collecting media reports, clinical information, social platforms and other multi-source heterogeneous data, introducing timestamp marks, and achieving the time sequence semantic vector representation of a doctor entity through a medical field pre-training model and sine function embedding; in combination with BiLSTM-CRF and an attention mechanism, doctor attributes and key events are identified, and an LSTM and a dynamic clustering algorithm are adopted to extract and divide doctor attribute evolution trajectories in stages; an influence score is calculated through an exponential decay function, stage knowledge graph nodes are generated, and incremental updating and node merging and splitting are supported; a graph convolutional network and a graph attention mechanism are adopted, a doctor influence evolution chain is constructed, information dynamic association and trend prediction are achieved, and the time sequence precision and data comprehensiveness of doctor influence evaluation and the dynamic evolution ability of a knowledge graph are improved.

The invention discloses a method and a system for constructing an intelligent typing diagnosis model of psoriasis. The method comprises the following steps: S1, collecting pairing multi-modal data of a psoriasis patient whose fingernails are not tired, wherein the pairing multi-modal data comprises clinical information, scanning electron microscope images of fingernail surface morphology and infrared spectrum data of fingernail protein; s2, constructing a clinical feature encoder; s3, constructing a spectral feature encoder; s4, constructing an image feature encoder; s5, constructing a hierarchical fusion module; and S6, three loss function components are constructed, multi-objective optimization of the model is realized, and a total loss function is adopted to carry out model training. According to the method, the clinical information, the scanning electron microscope image of the nail surface morphology and the infrared spectrum data of the nail protein are integrated, and the multi-mode deep learning technology is combined, so that early recognition and prediction of psoriatic arthritis in a psoriasis patient are realized.

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.

The invention provides an auxiliary detection system for diagnosing Alzheimer's disease, which relates to the technical field of classification diagnosis of Alzheimer's disease, and comprises a data acquisition module, a data processing module, a feature extraction module, a diagnosis model module and a report generation module, according to the method, four types of core data including clinical information, scale scores, MRI images and blood biomarkers are integrated, the core dimension of Alzheimer's disease diagnosis is covered, so that the pathological evolution of AD from molecular abnormality to structural damage can be more comprehensively captured by utilizing collaborative analysis of multi-modal features, and the diagnosis accuracy of the Alzheimer's disease is improved. The problem of missed diagnosis or misdiagnosis caused by single modal data is avoided, and the diagnosis accuracy is improved. And secondly, aiming at the heterogeneity problem of image data and blood marker data, a standardized processing technology is adopted, so that the consistency of data of different sources and different batches is ensured, the influence of equipment difference and experimental error is eliminated, and a reliable guarantee is provided for model input.

The invention relates to a kidney lump benign and malignant analysis method and device based on a laparoscopic ultrasound image, and belongs to the technical field of medical image processing.The method comprises the steps that radiomics characteristics of the laparoscopic ultrasound image are obtained, and radiomics scores of lump malignant risks are calculated according to the radiomics characteristics; determining an independent risk factor corresponding to the patient clinical variable, and constructing a clinical prediction model according to a mapping relationship between the patient clinical variable and the independent risk factor; and according to the radiomics score and the clinical prediction model, constructing a kidney lump benign and malignant analysis model. The technical problem that in the prior art, massive quantitative image features cannot be efficiently and accurately mined from medical images, and the most valuable iconography features cannot be screened out for analyzing clinical information is solved.

The invention discloses a medical diagnosis prediction method and system based on medical retrieval enhancement generation. According to the invention, the coverage range of clinical information is expanded by using external knowledge retrieved from different sources; in combination with a graph-based clinical text index normal form and a double-layer retrieval framework, multi-source information is synthesized into coherent and context-rich responses, and the problem that only fragmentary and lengthy responses can be returned due to the fact that complex interdependence relationships among medical entities cannot be captured when plane data is processed by a retrieval enhancement generation method is solved; and enhanced treatment embedding is obtained by using a patient treatment information expansion mechanism, so that the performance of the medical diagnosis prediction model is improved. Experiments show that the method improves the prediction accuracy on MIMIC-III data, and can provide most relevant and most logic-conforming enhanced information for medical codes to assist in clinical decision making.