371 results about "Risk factor" patented technology

The invention relates to the technical field of health monitoring, in particular to a cardiovascular disease data fusion and multi-dimensional health assessment method, which comprises the following steps of: acquiring multi-source data of a patient through a sensor and wearable equipment, preprocessing the acquired data, ensuring data integrity, extracting physiological features by adopting a convolutional neural network, and evaluating the health of the patient. The method comprises the steps of extracting non-physiological data features through principal component analysis, constructing a multi-dimensional feature set, identifying cardiovascular disease related risk factors through a random forest algorithm, distributing weights through a logistic regression algorithm to generate individualized risk scores, analyzing time sequence trends of the risk factors based on a long and short-term memory network model, and generating dynamic risk scores in real time. When the score exceeds a preset threshold value, an early warning mechanism is automatically triggered, and a patient and medical staff are notified through an application program; according to the method, accurate assessment and personalized intervention of cardiovascular health are realized through multi-source data fusion and dynamic analysis, and the method has high efficiency and timeliness.

The invention relates to the technical field of medical data processing, in particular to a risk assessment system for chronic diseases. The system is used for performing physiological index analysis according to a medical physiological monitoring signal to generate physiological index data; performing individual physiological index weight empowerment on the physiological index data based on genomics data to obtain individual physiological index data; performing quantitative analysis on pathological influence factors of chronic disease types according to the electronic health record data and the individual physiological index data, and generating individual chronic disease influence factor quantitative data; performing composite interaction risk factor analysis on the individual chronic disease influence factors based on the quantitative data of the individual chronic disease influence factors to generate individual chronic disease composite interaction risk factor data; and performing individual chronic disease risk assessment based on the individual chronic disease composite interaction risk factor data to generate individual chronic disease risk assessment data. According to the invention, chronic disease health management and accurate evaluation are realized through collaborative evaluation work of chronic disease risks.

The invention relates to the technical field of engineering waste treatment, and particularly discloses a waste slag site selection method, device and equipment. According to the method, a low-lying area and a stable slope suitable for the waste slag field are identified by utilizing a GIS technology, and basic data are provided for preliminary site selection; through weighted analysis of multi-dimensional risk factors, the association degree of each risk factor can be displayed to the greatest extent, the overall risk level is reflected through comprehensive scores, all factors can be comprehensively considered, a more comprehensive and accurate site selection basis is provided, the scientificity and accuracy of the site selection process are ensured, and the site selection efficiency is improved. The decision-making efficiency and accuracy are improved; meanwhile, each risk factor is evaluated and predicted based on a time sequence, environment prediction and long-term risk evaluation can be dynamically carried out on the to-be-selected site of the waste slag field, the impact possibly faced by the waste slag field in the future can be effectively predicted, and the long-term safety and sustainability of the waste slag field can be ensured.

The embodiment of the invention provides a blood glucose monitoring and early warning method, device and equipment and a storage medium. The method comprises the following steps: acquiring historical blood glucose data and body index data of a user; determining a mean value and a standard deviation of the historical blood glucose data, and determining a blood glucose threshold value of the user based on the mean value and the standard deviation; key risk factors in the body index data and the weight corresponding to each key risk factor are determined, and the blood glucose risk score of the user is determined according to the key risk factors and the corresponding weights; and determining a blood glucose threshold value of the user and a target early warning level corresponding to the blood glucose risk score from a plurality of preset early warning levels, and executing a corresponding target early warning strategy in response to the condition that the target early warning level is greater than the preset early warning threshold value. The embodiment of the invention aims to improve the accuracy and flexibility of blood glucose monitoring and early warning.

The invention relates to a food safety risk analysis method and system based on big data. The method comprises the steps of collecting food full-life-cycle key data through Internet of Things equipment and a data platform, and completing data format standardization to form a structured data set; key risk factors are extracted through the structured data set, a risk factor weight matrix is constructed, and a primary risk value of the food sample is calculated; establishing a time sequence prediction model by using the primary risk value and historical time sequence data, calculating a risk change trend, and predicting a future risk fluctuation condition; calculating a food risk grade according to the primary risk value and the risk change trend, and generating a corresponding risk classification label; performing comparative analysis on the risk classification label and an actual supervision result, calculating a model deviation, and optimizing a risk calculation and trend prediction model based on a deviation result; the optimized analysis results are integrated, the risk level and the change trend are displayed through a graphical interface, and intelligent early warning prompts and intervention decision suggestions are provided.

The invention provides an intelligent management system for chronic diseases and common diseases of old people. The intelligent management system comprises an old people comprehensive evaluation module, a multidisciplinary collaborative diagnosis and treatment module, a multi-medication risk prediction management module, an intelligent chronic disease follow-up diagnosis management module and a health science popularization knowledge base module, the senile comprehensive assessment module inputs the personal chronic disease map of the patient into a risk factor prediction model for prediction, and outputs a comprehensive assessment result; the multidisciplinary cooperative diagnosis and treatment module is used for the first diagnosis / receiving diagnosis doctor to coordinate multidisciplinary doctors to perform cooperative diagnosis and treatment; the multi-medication risk prediction management module is used for giving comprehensive diagnosis, multi-medication management and risk prediction to the patient through collaborative diagnosis and treatment; the chronic disease intelligent follow-up diagnosis management module carries out follow-up visit tracking, health risk prediction and review prompting on the patient; and the health science knowledge base module matches and pushes corresponding health education knowledge. The accuracy and timeliness of senile chronic disease co-disease risk assessment prediction and management are improved, and a good auxiliary effect is achieved on improvement of the life quality of patients.

The invention discloses a personal obesity risk prediction system and method based on AI of big data, and belongs to the field of medical health, and the system comprises a data collection module, a multi-dimensional feature construction module, a risk label dynamic generation module, a model training and risk prediction module, a credibility evaluation and calibration module and the like. The system collects multi-source heterogeneous data through wearable equipment, a biochemical interface and a health platform API (Application Program Interface), uniformly encodes the multi-source heterogeneous data into a standard time sequence and then constructs behavior-metabolism-environment coupling characteristics. And performing joint modeling on the dynamic features and the labels by adopting a graph neural network in combination with causal factorization, and outputting an individual obesity risk prediction result. The result credibility is improved through Monte Carlo Dropout and a confidence interval calibration mechanism, and calibration information is fed back to a feature construction link to optimize a modeling strategy. Finally, the key risk factors are presented in the form of a visual thermodynamic diagram and a causal path diagram, and an individualized intervention suggestion vector is generated. The method has the beneficial effects of improving prediction accuracy and enhancing individual intervention pertinence.

The invention relates to the technical field of information platform construction, in particular to a construction method and system of a sports information intelligent service platform. The method comprises the following steps: collecting user motion image data and user health basic data; key body node position information in the movement process of the user is extracted; generating a user motion track curve based on the key node position information, and calculating a deviation angle and a deviation distance with a standard track template to obtain motion correctness data; constructing a user fitness risk assessment model according to the action correctness data and the user health basic data, analyzing the difference degree with a preset safety threshold, and generating layered health guidance data; and decomposing the layered health guidance data into quantifiable progress units, and generating progress tracking data. According to the method, the user motion image data and the health basic data are combined, the evaluation model capable of identifying individualized risk factors is constructed, and more accurate safety guidance is realized.

The invention relates to the technical field of risk management, in particular to a water conservancy project risk early warning analysis method and system based on multi-source information, and the method comprises the following steps: dividing a dam body, a flood discharge gate and a spillway region according to spatial dimensions, extracting leakage monitoring records of a flood season, a dry season and an emergency weather event period, and storing the leakage monitoring records; and calculating a trigger factor frequency to generate a trigger factor feature sequence. According to the method, through hierarchical division of space and time dimensions, extraction of trigger factor frequency and analysis of support degree and confidence degree are combined, so that extraction of risk factor features is more comprehensive and accurate. In the construction of the dynamic propagation path, the spatial trajectory and the time evolution rule of the risk factor are deeply analyzed, so that the propagation path of the risk factor is clearly displayed, the accurate prediction of the risk diffusion region is realized, and a basis is provided for the division of the risk level in the subsequent region.

Methods for training and using a machine learning model for predicting a likelihood of an event occurring in a patient having a malignant tumour are provided. The method of using the machine learning model includes inputting a pathology image of a portion of a malignant tumour of a patient and one or more categorical risk factors associated with the malignant tumour or the patient. The method also includes extracting, from the pathology image, one or more features relating to one or more properties of the malignant tumour. The method further comprises determining a predicted likelihood of an event occurring in the patient based on the extracted features and the one or more categorical risk factors. The method additionally includes outputting the predicted likelihood.

The invention provides a knowledge graph-based public security multi-source risk factor association identification analysis method, which relates to the technical field of risk identification, and comprises the steps of obtaining multi-source risk factor data, extracting information from unstructured data, constructing an initial association network, performing feature analysis and calculating a similarity matrix; and the close association subgroups are identified through community discovery, a multi-level association network is constructed, a conduction path is analyzed, a weight is calculated, and finally risk early warning information is generated. According to the invention, the complex association between public security risk factors can be effectively identified, and the risk prediction accuracy is improved.

The invention relates to the technical field of elderly endocrine medical information management, in particular to an elderly endocrine disease risk assessment method based on big data. According to the method, all the highest similarity vectors of the target medical vectors are screened out; obtaining a basic risk factor according to the detection moment distribution and the similarity between the two; obtaining self risk factors in combination with detection moments of all medical vectors; obtaining a data change risk factor according to the number of the similar sick patients and the data difference and the detection moment difference between the medical vector and the first medical vector; and obtaining endocrine system stable factors by using the similarity between the medical vectors, combining the endocrine system stable factors to obtain dynamic risk factors, and performing senile endocrine disease risk assessment on the to-be-assessed person. According to the method, the timeliness of physiological changes and risk factors of the old people is considered, so that the risk assessment of the endocrine diseases of the old people is more accurate.

The invention relates to the field of diabetic feet, and discloses a diabetic foot risk assessment method and system based on a knowledge graph, and the method comprises the steps: collecting patient data of diabetic feet, recognizing patient group features, risk factors and risk features of the diabetic feet, constructing a risk prediction model of the diabetic feet, extracting keywords from risk prediction data of the risk prediction model so as to query domain knowledge of the diabetic foot, constructing a diabetic foot ontology structure, identifying an entity object of the ontology structure, performing disambiguation processing, extracting entity data of the entity object from the domain knowledge, and obtaining a disambiguation result of the entity object according to the disambiguation result and the entity data. The storage knowledge of the diabetic foot is fused, the reasoning conclusion of the diabetic foot is obtained by combining the reasoning rule and the reasoning type, the risk factor and the risk level of the patient data are recognized, and a risk assessment report of the diabetic foot is generated. The accuracy of diabetic foot risk assessment can be improved.

The invention discloses a constipation prediction system based on an artificial intelligence large model, and relates to the technical field of medical health information. In order to solve the problems that complex risk factors of constipation are difficult to comprehensively capture, so that the feature coverage range of a prediction model is limited, group classification and risk level dynamic evaluation are not performed on users, so that an intervention scheme is high in universality, but accurate management requirements of different groups are difficult to meet. Multi-source data such as electronic medical records and physiological parameters are integrated through the multi-modal data processing module, refined classification of user groups is achieved, feature causal relationships are analyzed in combination with a knowledge graph technology, constipation prediction accuracy is improved, the intelligent prediction module dynamically adapts to a model according to group risk levels, and constipation prediction accuracy is improved. The probability distribution is output, a visual causal path report is generated, and the dynamic decision-making module adjusts an intervention scheme through doctor-patient cooperation based on a knowledge graph matching strategy set and optimizes a strategy in real time by using an effect feedback mechanism, so that personalized health management is realized.

The invention relates to a perioperative delirium risk prediction method and device and a storage medium, and belongs to the technical field of big data processing. The method comprises the steps of obtaining to-be-predicted multi-modal data; encoding the multi-modal data, and extracting global state features; fusing information of different modes through a multi-mode cross attention mechanism to generate fusion features; the fusion features are combined with coding information to be input into a recursive reasoning module, and global state features at future time points are gradually reasoned; inputting the global state features at the future time point into a perioperative period delirium risk prediction model, and generating a perioperative period delirium risk probability at the future time point; and generating a perioperative period delirium risk probability sequence in a time sequence form through recursive reasoning. According to the method, multi-dimensional perioperative delirium risk factors are covered; the capturing capability of feature interaction and association between modals is improved; the change trend of the perioperative period risk can be dynamically predicted, and the interpretability and practicability of the model are enhanced.

The invention relates to a heart failure home patient-oriented multivariable trend anomaly detection method, which comprises the following steps of: constructing an initial contour of a multivariable health trend for a patient, and introducing a trend inertia vector: updating trend inertia to form an individual trend trajectory relationship; detecting an inertia breaking point in the trend trajectory diagram; analyzing whether the variables within 12-36 hours before and after the focusing breaking point analysis generate collaborative disturbance or not; performing reprocessing through a disturbance amplification operator to form a potential early warning factor; constructing a multivariable intervention graph by using the disturbance cooperation matrix; monitoring the offset direction and strength of the causal propagation chain on each path; if the plurality of paths are subjected to direction deviation in the same period at the same time, judging that the deviation is pathological trend deviation; converting the causal offset path into a single trend risk factor, spreading a plurality of weak signals in a variable graph, evaluating systematic influence, forming a fuzzy risk scoring curved surface relationship, and outputting an individual trend risk level; the sensitivity and continuity of trend identification are improved, individual differences are adapted, and the false alarm rate is reduced.

The invention relates to the technical field of model construction, in particular to a construction method of a disease feature recognition and evaluation model based on the Internet of Things. The method comprises the following steps that multi-modal physiological data of a patient are collected in real time through Internet of Things medical equipment, data preprocessing is conducted on the multi-modal physiological data of the patient, standard patient physiological data are generated, and the standard patient physiological data are stored in a distributed database; extracting gene sequencing data based on the biological sample library; performing global health risk factor perception on the standard patient physiological data to generate user level health risk perception data; and carrying out feature fusion on the user level health hazard perception data and the gene sequencing data to construct a disease feature matrix containing a space-time dimension. Through multi-modal data fusion, spatio-temporal evolution modeling, deep learning architecture and personalized risk assessment, the precision and timeliness of disease feature recognition assessment model construction are improved.

The invention relates to the technical field of health data processing, in particular to a cross-device health data fusion method, which comprises the following steps of monitoring a device connection state, identifying data missing and resending, calibrating multi-device time and performing data difference, calculating a device stability score to adjust confidence fusion data, extracting periodic health parameters and analyzing a change trend. And detecting the factor activation state and combining the sensitivity to obtain a risk score, and outputting a health processing result. According to the method, through combination of equipment connection state identification and data caching progress calculation, the precision of breakpoint data recovery is enhanced, a timestamp alignment and interpolation correction mechanism is adopted, continuous compensation of multi-source data is realized, the data weight is adjusted by using a stability score, the credibility of fused data is improved, and the reliability of the fused data is improved. In combination with behavior characteristic trend extraction and risk factor sensitivity determination, the accuracy and individualized distinguishing ability of chronic disease risk identification are optimized, and the individualized health management and disease prevention ability is enhanced.

According to the physical examination item recommendation method, device and equipment based on the large language model and the computer readable storage medium, interactive physical examination questions and answers are performed with the target user according to the initial risk factors and the related question list corresponding to the candidate disease information list, the collection efficiency of the dynamic health information of the target user is improved, and the user experience is improved. And mining dynamic health information. In combination with dynamic health information, symptom information and health risk factors are further mined, and a disease information list of the target user is enriched, so that personalized physical examination item recommendation of the target user is realized. And the basic health information of the target user is combined with the dynamic health information, and the potential disease information of the target user is determined comprehensively, so that the physical examination item information more adaptive to the target user is obtained according to the comprehensive target disease information list, and the recommendation efficiency and recommendation accuracy of the physical examination item information are improved.

The invention relates to a causal feature selection method for type II diabetes mellitus. The execution process of the method is described as follows: (1) preprocessing and standardizing original data; (2) introducing a type II diabetes risk factor reinforcement learning causal discovery method, and constructing a type II diabetes characteristic causal structure; (3) executing a forward selection stage, taking causal information gain as a selection strategy, and taking a feature set with high score of a strategy function as an output data set; and (4) executing a backward deletion stage, and deleting repeated redundant features by taking a correlation coefficient as a deletion strategy to obtain a final feature set. Existing feature selection methods are mostly based on correlation among variables and have the defect that causal relationships among the variables are difficult to reflect. The invention designs a new type II diabetes feature selection method based on the combination of causal information gain and correlation coefficients, and the method can effectively reduce the model training time, improve the model robustness, and provide a new thought for diagnosis and prevention research of type II diabetes.

The invention discloses an IDI full-project cycle risk digital assessment method and system, which have the beneficial effects that potential risk factors are identified from project data by adopting a text mining technology, risk factor importance assessment is carried out by utilizing a mode of weighting word frequency through information entropy, risk influence factors can be comprehensively identified, and the risk assessment accuracy is improved. Exploring the internal influence of project quality and risk factors; a multi-level and multi-dimensional risk evaluation system is constructed by adopting an analytic hierarchy process, so that the quality risk state of a project can be comprehensively reflected, and a quantitative standard of an evaluation index system is given; according to the method, a project risk evaluation model is constructed, a project risk scoring model is constructed from four dimensions of a hierarchical weight matrix, a severity matrix, a conditional probability matrix and an index occurrence probability matrix of risk indexes, various risk factors are considered, and the mutual relation and occurrence possibility between risks can be known more comprehensively; a Monte Carlo simulation method is adopted to grade and divide project risks, and the risk can be quickly traced, monitored and managed according to a result.

The invention discloses a children obesity early warning method and system based on obesity risk factor analysis, and the method comprises the steps: carrying out the feature screening of collected children multi-dimensional health related data containing parental information, birth history and lifestyle, and recognizing the important risk factors and weights of children obesity; important risk factors are supplemented through literature review; the method comprises the following steps: formulating scale questions including parental information, birth history and lifestyle based on important risk factors and weights in combination with clinical expert opinions, assigning scores to the scale questions, dividing according to a scale score result to form children obesity risk prediction levels, and providing personalized health management schemes for subjects with different risk levels. The method is low in cost, easy to implement, high in compliance and based on non-invasive characteristics, and is particularly suitable for early obesity screening and early warning of 3-6-year-old children.

The invention relates to the technical field of information management, in particular to an underground pipeline gallery risk monitoring method and device. According to the method, a heterogeneous sensing terminal network is used for sensing a target underground pipeline gallery according to a fast and slow time sequence, and a pipeline gallery monitoring anchor point set is determined; performing cross-modal interaction on a heterogeneous sensing terminal network based on the pipeline and pipe gallery monitoring anchor point set to obtain a pipeline and pipe gallery monitoring anchor point multi-modal fusion feature set; performing anchor point risk assessment according to the pipeline and pipe gallery monitoring anchor point multi-modal fusion feature set, and obtaining a pipeline and pipe gallery monitoring anchor point risk factor set according to an assessment result; and when the pipeline and pipe gallery monitoring anchor point risk factor set is greater than or equal to a preset anchor point risk factor threshold value, triggering a risk early warning instruction. According to the method, accurate identification and dynamic early warning of the key risk points of the underground pipeline gallery are achieved through fast and slow time sequence sensing and cross-modal feature fusion processing based on the monitoring anchor points.

The invention discloses a food safety event intelligent early warning system based on multi-source data analysis, and relates to the technical field of food safety early warning, the system can enhance the adaptability and flexibility of a model through continuous self-optimization and adjustment, the system can become more accurate and efficient along with the increase of the data volume, and the early warning efficiency is improved. And problems caused by long-term dependence on fixed rules and outdated models are avoided. By fusing the data of a plurality of sensors, the system can timely discover various potential pollution sources and identify the risk of cross contamination, and risk factors possibly neglected by a traditional method are avoided. The intelligent decision support function of the system greatly reduces the burden of manual intervention, improves the timeliness and accuracy of the reaction, and avoids the delay or error caused by manual judgment. The early warning can significantly improve the response speed, reduce the occurrence probability of food safety problems, reduce the potential safety hazards in food production, and guarantee the health and safety of consumers.

The invention relates to the technical field of diabetes prediction, in particular to a method for predicting early diabetes based on health data, and the method comprises the steps: carrying out the data collection and preprocessing of an individual health system, and obtaining diabetes risk related data; performing off-line calculation on the data by using a feature correlation analysis technology, and extracting a diabetes prediction feature set; performing risk assessment on the feature set through a preset diabetes prediction model to generate a diabetes risk prediction result; key risk factors are extracted, a risk factor classification model based on a random forest is constructed, risk attribution analysis is carried out, and main risk factors are identified; then, comprehensive assessment is carried out on the main risk factors in combination with confidence propagation analysis and risk path analysis technologies, and a core risk source is positioned; the individual diabetes risk portrait is constructed according to the core risk source, the relationship among the risk factors is analyzed, a personalized early intervention scheme is formulated, and the comprehensiveness, precision and interpretability of early diabetes prediction are remarkably improved.

The invention relates to a cardiovascular disease risk assessment system and method. On the basis of fully considering the influence of dimension index information of kidney-related risk factors on the occurrence risk of cardiovascular diseases, heart and kidney metabolic indexes are integrated. And a mathematical model Fine-Gray is used for screening predictive factors by a step-by-step method. On the premise that traditional cardiovascular disease risk factors are reserved, in order to give consideration to the accuracy and easy generalization of risk assessment, prediction factors are simplified through strict calculation and derivation; the method is constructed based on a small amount of clinically ubiquitous detection index information such as age, sex, smoking or not, systolic pressure (SBP), fasting blood glucose (FBG), non-high density lipoprotein cholesterol (non-HDL-C) and estimated glomerular filtration rate (eGFR) as predictive factors. The method has the advantages of simplicity and convenience in operation, less required information and low professional requirement. Meanwhile, the risk of the outcome of various clinical cardiovascular diseases (including CVD, ASCVD and HF) can be evaluated at the same time, and the method can be suitable for various scenes such as primary medical care and clinical diagnosis and treatment.

The invention discloses a hospital pharmacy inventory intelligent management system and method, and belongs to the technical field of data management. Medicine basic information and multiple batches of inventory records are acquired; an application risk grade R is extracted based on the medicine application label; combining the remaining validity period, the stability parameter and the risk factor to construct a batch ex-warehouse priority scoring model P; generating a sorting ex-warehouse list and executing allocation and ex-warehouse operation; when it is monitored that the medicine is in time or the inventory is abnormal, dynamically adjusting the score and updating the sorting result; according to the invention, fine control of the drug delivery sequence can be realized, clinical availability of high-risk-purpose drugs is guaranteed preferentially, and inventory use efficiency and medication safety are improved at the same time.

The present invention provides a method for establishing a hyperuricemia prediction model using a machine learning algorithm, which belongs to the field of health assessment technology. The embodiment of the present invention uses a UKBB cohort based on a large population as training, and uses an internal test set and a dataset of healthy physical examinees from Southern Hospital as an external test set to establish and verify a reliable and practical stacked multimodal machine learning model trained based on genetic and clinical data, which is used to timely identify HUA phenotypes and early predict gout and metabolic-related outcome risks. The model has excellent performance, exceeding each single machine learning model, and shows satisfactory efficacy. The ISHUA marker can quantify gout risk and metabolic-related results at an early stage, can provide active guidance for daily health examinations and the management of risk factors, and provide valuable information support for clinicians to appropriately manage HUA risk factors after routine health screening.

The invention relates to the technical field of food safety data processing and intelligent early warning, and particularly discloses a safety early warning method and system based on food safety inspection data. The method comprises the following steps: acquiring multi-source food safety inspection data, performing structured preprocessing, and constructing a unified feature vector space; extracting space-time correlation characteristics to generate a dynamic risk factor sequence; inputting the sequence into an interpretable fusion model for score calculation, and generating a risk score matrix; fusing the product information to generate an attribute labeling vector, constructing a food safety knowledge graph and carrying out causal reasoning; and generating early warning information and a risk tracing path based on a reasoning result, and carrying out reverse correction and model updating on the risk factors. According to the method, multi-source data modeling, causal relationship reasoning and a model self-learning mechanism are fused, dynamic identification and closed-loop early warning of food risks are realized, and the method has high adaptability and interpretability.

The invention, which relates to the technical field of the emergency internal medicine department, discloses an intelligent assessment and early warning system for the illness state of the emergency internal medicine department, and the system carries out quantitative assessment based on pathological characteristics of multiple dimensions through a comprehensive assessment and early warning module and a blood sugar fluctuation and fundus disease analysis module. The integration of the data can form a comprehensive fundus lesion risk factor Rrisk, and the fundus lesion risk of a diabetic patient is subjected to all-around quantitative evaluation. According to the system, fundus lesion risks of patients are divided through set risk levels, and intervention suggestions of different levels are provided in combination with a comprehensive fundus lesion risk factor Rrisk. When the patient is at a high risk level, the system can trigger related early warning in time to remind medical staff to take targeted treatment or further examination, and serious consequences such as disease development to blindness and the like are avoided. The multi-dimensional comprehensive evaluation not only improves the diagnosis accuracy of the fundus lesion of the patient, but also provides powerful decision support for clinical treatment.