909 results about "Disease progression" patented technology

The AI-enhanced cellular modeling and simulation platform is a computational system designed to enhance biomedical research and development and personalized medicine and wellness. This platform integrates simulation modeling, machine learning and artificial intelligence, multi-omics data, and sophisticated data fusion and decision-support techniques to create comprehensive models of cellular systems and processes across multiple scales. It enables researchers and clinicians to simulate complex biological interactions, predict disease progression, and design or optimize treatment strategies or medical devices with improved accuracy and efficacy. The system's architecture allows for integration of various components, including real-time data processing, federated learning, and quantum computing enhancements. From personalized drug discovery and cancer therapies to synthetic biology and epidemiological analysis, this platform offers powerful tools for understanding and manipulating cellular systems and bioengineered systems. By bridging the gap between molecular-level interactions between cells and materials and organism-wide effects, it enables significant advancements in healthcare and biological sciences.

The invention discloses a brain disease classification method and system. Precise diagnosis is realized through multi-modal data fusion and dynamic modeling. The method comprises the following steps: collecting multi-modal brain image information and cognitive behavior information of a user; performing dynamic function connection analysis on the resting state functional magnetic resonance time sequence signal to obtain a time-varying brain network feature matrix, and performing white matter fiber bundle topology reconstruction on a structure connection matrix; constructing a four-dimensional correlation tensor by using the time-varying network features, the structural connection weights and the anatomical features through a neurodynamic model; performing multi-task learning on the four-dimensional correlation tensor based on a time-varying graph neural network model, and outputting a quantitative diagnosis result; and finally generating a clinical classification report integrating the individualized brain network remodeling target, the disease progress risk layering and the treatment response prediction. By dynamically fusing the structure and functional features, comprehensive characterization of the pathological mechanism of the brain disease is realized, and decision support with both accuracy and interpretation is provided for clinical diagnosis.

The invention discloses a nerve disease detection and analysis method and system, and the method comprises the steps: obtaining a bracelet collection signal, a sphygmomanometer collection signal, a movement behavior image and behavior test data, and extracting tremor intensity features, gait symmetry features and autonomic nerve rhythm features through multi-band decomposition of the bracelet collection signal; analyzing the motion behavior image and the standardized motion test to obtain a motion function score; carrying out heart rate variability analysis to identify a neural function abnormality mode; constructing a neural function state map and calculating a feature weight; predicting a disease progress trend in combination with historical monitoring data; and dynamically adjusting a prediction result through subsequent feedback correction information. Through a mode of combining short-time intensive monitoring and long-term intermittent acquisition, long-term trend prediction and dynamic correction based on initial data are realized, and the reliability and practicability of nerve disease risk assessment in a home scene are remarkably improved.

Systems and methods are disclosed for evaluating a patient with vascular disease. One method includes receiving patient-specific data regarding a geometry of the patient's vasculature; creating an anatomic model representing at least a portion of a location of disease in the patient's vasculature based on the received patient-specific data; identifying one or more changes in geometry of the anatomic model based on a modeled progression or regression of disease at the location; calculating one or more values of a blood flow characteristic within the patient's vasculature using a computational model based on the identified one or more changes in geometry of the anatomic model; and generating an electronic graphical display of a relationship between the one or more values of the calculated blood flow characteristic and the identified one or more changes in geometry of the anatomic model.

The invention provides a medical decision support method and system based on big data. The method comprises the following steps: integrating and fusing patient information from different medical institutions, personal health monitoring equipment and a public health database to obtain a dynamic update library; a graph neural network algorithm is applied to analyze the relation between the patients and the relation between the patients and the environmental factors in the dynamic update library so as to predict the individualized disease development trend, and dynamic risk early warning signals are generated; based on the dynamic risk early warning signal, through feature importance analysis and a local interpretable model, revealing key factors and an interaction mechanism influencing disease progression, and applying a health economics evaluation method to generate a medical suggestion report; and in combination with the medical suggestion report, establishing a dynamic learning and feedback mechanism, optimizing personalized suggestions in the medical suggestion report, and constructing a medical decision support system. According to the technical scheme provided by the invention, the credibility of medical decision making is remarkably improved.

The present application provides methods and systems for detecting and quantifying chromosomal instability from histology images with machine-learning. Also described herein are methods for selecting treatments for a medical disease, by determining a chromosomal instability metric from histology images. The disclosed methods and systems may also be used to investigate disease progression and prognosis.

The invention discloses a glioma T cell prediction and prognosis evaluation method based on pathological images, particularly relates to the field of patient prognosis health evaluation, and aims to solve the problems that existing pathological evaluation is difficult to combine with tumor structure heterogeneity and immune infiltration distribution, and the future progress risk of a patient cannot be predicted based on follow-up visit pathological data. A spatial heterogeneity map of a tumor core area and an invasion edge is constructed in a digital pathological section, density gradients of T cells in different areas are calculated to generate a distribution heterogeneity coefficient, interaction processing is performed on the two types of characteristics in combination with historical follow-up visit records, and a time sequence neural network constructed based on a gating structure is combined to obtain a high-efficiency characteristic of the tumor. And outputting disease progress probabilities of a plurality of follow-up visit time points in the future to form a prognosis trajectory prediction curve, calculating a quantitative recurrence risk score according to curve slope change and an immune fluctuation mode, and finally generating an individualized management scheme, thereby realizing quantitative prediction evaluation and risk management of the prognosis trend of the glioma patient.

The invention discloses a senile weakness and Parkinson's disease multi-dimensional evaluation system based on an intelligent single-chip microcomputer, and belongs to the technical field of disease evaluation. The senile weakness and Parkinson's disease multi-dimensional evaluation system comprises a data acquisition module used for acquiring patient multi-dimensional real-time data based on artificial intelligence; the data transmission module is used for uploading the multi-dimensional real-time data of the patient based on artificial intelligence to the multi-dimensional evaluation terminal; and the multi-dimensional evaluation terminal is used for processing, analyzing and evaluating the multi-dimensional real-time data of the patient based on artificial intelligence, and determining a multi-dimensional evaluation result of senile weakness and Parkinson's disease based on the intelligent single-chip microcomputer. The problems that real-time monitoring and multi-dimensional evaluation cannot be carried out on senile weakness and Parkinson's disease based on an intelligent single-chip microcomputer in the prior art, and disease deterioration cannot be effectively prevented are solved. Real-time monitoring and multi-dimensional evaluation can be performed on senile weakness and Parkinson's disease on the basis of the intelligent single chip microcomputer, the illness state of a patient can be mastered in time, the patient can be tracked and treated in time, disease progression is slowed down, and deterioration of the illness state can be effectively prevented.

The invention discloses a detection method of a systemic lupus erythematosus immune spectrum based on full spectrum flow cytometry, and relates to the technical field of cell detection, and the detection method comprises the following steps: providing a fluorescein coupling antibody of a detection index; carrying out antibody titration on the fluorescein coupling antibody to obtain a dyeing concentration; the method comprises the following steps: carrying out surface staining on peripheral blood mononuclear cells of an SLE patient by adopting a fluorescein coupled antibody, carrying out intracellular mitochondrial superoxide staining, and resuspending in a detection solution to obtain a test sample; carrying out sample loading test on the test sample and the prepared single staining reference sample and negative sample, and collecting and analyzing particle information; and performing enclosure and dimension reduction analysis on the analyzed data to obtain a systemic lupus erythematosus immune spectrum and a cell activation state analysis result. According to the application, dozens of immune cell subtypes and activation states thereof in SLE can be detected under the condition of a single-tube sample, an SLE patient immune map is constructed, and a reference is provided for evaluating disease progression and formulating a treatment scheme.

A two-stage multi-task learning based method is disclosed for automated lesion response assessment according to Response Evaluation Criteria in Solid Tumors (RECIST). Pre-processed venous phase CT scans are inputted into a convolutional neural network (CNN) and a transformer to obtain coarse lesion segmentation masks, which are then optimized by a multi-task learning framework that incorporates longitudinal CT correlation and clinical prior knowledge to generate difference maps, and adopts an ordinal regression strategy that encodes the ground truth of response outcome. Sum of the volume (SOV) -based response assessment and new lesion assessment results are combined to obtain the overall RECIST response, i. e., response, stable disease, and progressive disease.

The present invention relates to a method for diagnosing and predicting the course of Alzheimer's disease (AD)-related dementia after feature extraction of brain images by Variational Autoencoders (VAE) and using Artificial intelligence and Machine learning (AI / ML) algorithms, as compared with non-demented control cases (CN), mild cognitive impairment (MCI), and other non-Alzheimer's dementia (non-ADD) cases. Method 1 extracts the reduced dimensional latent feature vector from the sMRI scans / brain images using a VAE and does multiple sampling from the latent distribution to reduce the class imbalance followed by classification using different AI / ML models. Method 2, the extracted feature vectors from VAE are used as input to a mixture of class-Restricted Boltzmann Machines (cl-RBM) for AD, MCI, and CN classification. Method-1 diagnoses AD and distinguishes it from MCI, CN, and non-ADD using MRI scans with or without additional aids. Method-2 further extends to diagnosis and prediction of AD.

The invention discloses an AI-based child nebulization treatment management system and method, and relates to the field of treatment scheme management, and the system comprises a management and control module which is used for obtaining the medical general archive access and read-write authority of a target medical place, carrying out the editing and sending of a control instruction for each functional module, and sending the control instruction to the medical general archive access and read-write authority to the medical general archive access and read-write authority to the medical general archive access and read-write authority; summarizing and storing working results and analysis data of the functional modules; the data acquisition module is used for acquiring physique data, illness state data and treatment plans of the patient in the current period based on a medical general archive; the feature selection module is used for performing feature recognition on the data acquired by the data acquisition module by adopting a multi-modal feature coupling algorithm; by collecting and analyzing physical characteristics, disease progression, historical treatment response and feedback information of a patient in real time, a personalized treatment scheme is formulated according to specific conditions of each child, a general treatment mode is avoided, unnecessary side effects are reduced, and treatment effectiveness and safety are improved.

Provided in the present invention are a marker combination for predicting thyroid cancer metastasis and the use thereof. Specifically, provided in the present invention is the use of the gene, mRNA, cDNA or protein of the risk marker combination for evaluating thyroid cancer metastasis or a detection agent thereof in the preparation / establishment of a diagnosis agent or kit / device for evaluating the risk of thyroid cancer metastasis. Research shows that the risk marker combination of thyroid cancer metastasis can be used as a marker for the early evaluation of thyroid cancer metastasis in a patient with thyroid cancer, has a high sensitivity and specificity, can be used to rapidly diagnose thyroid cancer metastasis at a relatively early stage of disease progression, and provides strong assistance for early treatment intervention of diseases.

The invention belongs to the technical field of early warning of diseases, and discloses a knee joint disease early warning system based on biomechanical analysis, which comprises a data acquisition module, a data analysis module, a main control module and an early warning module, the knee joint disease early warning system based on biomechanical analysis has the expected effects that the knee joint disease early warning system based on biomechanical analysis is provided, and a patient is helped to discover and take intervention measures in the early stage of knee joint diseases through real-time monitoring and early warning, so that the disease progress is delayed, and the life quality of the patient is improved. Meanwhile, the system provides a powerful tool for clinicians and rehabilitators and is used for formulating personalized rehabilitation treatment schemes.

The invention discloses an analysis and prediction system based on disease data, which belongs to the technical field of disease data analysis and comprises a cross-modal distillation data fusion module, a time domain causal chain analysis module, a multi-level disease risk prediction module, a disease critical state real-time monitoring module, a self-adaptive intervention strategy generation module and a clinical collaboration and feedback optimization module. A time decay factor and a smoothing coefficient are introduced through the time domain causal chain analysis module, the causal strength between variables is updated in real time, nonlinear changes of disease progression are adapted, and individual risk scores are generated through the multi-level disease risk prediction module in combination with the dynamic weight and the time decay factor of the causal atlas. A spatial smoothing function is introduced to suppress the influence of an abnormal value, group risks are quantified through a modal mean value and a standard deviation, individual weights are dynamically adjusted through a feedback mechanism, the long-term stability of prediction is improved, causal strength and feature importance are used for joint modeling, and the problem that a traditional statistical model ignores a potential causal path is avoided.

The invention discloses a hypertensive heart disease early screening system fusing ultrasonic multiple parameters, which comprises the following steps: acquiring ultrasonic image data and physiological index monitoring parameters of a patient at different time points, performing difference comparison on heart structure parameters to generate time sequence change data, and establishing a multi-dimensional data fusion scheme based on the time sequence change data and physiological indexes; according to the fusion scheme, acute risk trigger factors are identified, blood flow abnormal parameters are generated, and emergency threshold comparison is carried out to generate acute risk early warning signals; extracting a myocardial strain degradation rate to determine a chronic degradation acceleration time point, carrying out disease progress stage association to generate a chronic risk layering curve, and establishing a clinical index comparison table; carrying out double-layer correlation on the acute risk early warning signal and the chronic risk layering curve, and carrying out calibration judgment to generate a comprehensive risk judgment sequence; the sequence is decomposed into an acute judgment layer and a chronic judgment layer, a risk threshold value is configured to generate an instant early warning signal, a layered screening report is formed, and technical support is provided for early discovery of the hypertensive heart disease.

A system for the treatment of chronic diseases, consisting of: a data acquisition unit configured to capture patient health information in real time from wearable or networked health monitoring devices, electronic health records, and patient-reported outcomes; a central processing unit configured to preprocess the captured data by normalizing, aggregating, and coding the data for further analysis; a feature extractor operationally connected to the central processing unit, the feature extractor being capable of extracting key features from preprocessed data, including demographic data, clinical history, biomarker levels, and lifestyle;a predictive modeling engine communicating with the feature extraction module, wherein the predictive modeling engine is configured to use machine learning techniques to generate recognition models from historical patient data, the models predicting disease progression, treatment outcomes, and potential complications; a visualization interface connected to the predictive modeling engine, wherein the visualization interface is configured to display the results of the predictive analytics to healthcare providers and patients to enable actionable insights for the management of chronic diseases; and a feedback mechanism integrated into the visualization interface, configured to allow users to input real-time feedback on the predicted outcomes, the feedback being used to refine the predictive models over time.

The invention relates to a mulberry leaf flavone microcapsule as well as a preparation method and application thereof, and belongs to the technical field of microcapsule drug loading. The preparation method of the mulberry leaf flavone microcapsule comprises the following steps: S1, adding mulberry leaf flavone into a chitosan solution, carrying out ultrasonic treatment, shearing by using a homogenizer, and heating and stirring to obtain a mixed solution; s2, slowly dropwise adding a sodium tripolyphosphate solution into the mixed solution, reacting and curing until the solution becomes milk white liquid from clear and no precipitate is generated, then centrifuging and washing, and collecting particles; and S3, freezing the particles, and performing freeze drying to obtain the mulberry leaf flavone microcapsules. The mulberry leaf flavone microcapsule provided by the invention can be used for developing a novel medicinal preparation in the field of medicines, and can relieve disease symptoms and delay disease progression through the antioxidant and anti-inflammatory characteristics of the mulberry leaf flavone microcapsule; in the field of food, the method can be applied to development of functional food, for example, the method can be added into beverages and health-care products to provide health benefits of antioxidation, blood fat reduction and the like for consumers.

The invention relates to the technical field of medical imaging, in particular to a nuclear medicine imaging method and system, and the method comprises the steps: patient preparation, tracer agent distribution detection, image enhancement, multi-target dynamic imaging, image quantitative analysis and data fusion, and result output and diagnosis suggestion. A preliminary image of tracer agent distribution in the body of a patient is obtained through a multi-modal imaging device, a high-resolution image is generated through a convolutional neural network noise suppression algorithm, a contrast ratio self-adaptive enhancement algorithm and a super-resolution reconstruction algorithm based on a generative adversarial network, and accurate dynamic analysis is carried out. In combination with a random forest algorithm and a time sequence analysis model, performing quantitative analysis on the radioactive intensity, the volume and the metabolic rate of the target spot, and generating personalized diagnosis suggestions; according to the invention, the precision and diagnosis effect of nuclear medicine imaging are greatly improved, and the method is suitable for early diagnosis, curative effect evaluation and disease progress monitoring of clinical diseases.

A wearable electronic medical device that stores initial baseline biometric data in memory and determines patient-specific thresholds for monitored biometric parameters. Biometric sensors detect changes in these parameters in response to therapeutic treatment or disease progression, and exceeded thresholds activate actions such as patient notifications, changes in treatment, and transmission of data. Trusted receivers receive suggested diagnoses and treatment options determined by an AI-powered web crawler. The treatment includes electrocuetical and pharmaceutical treatment, and the physiological change includes an indication of a change in the cardiovascular condition. The device determines patient-specific thresholds by applying statistical weighting to monitored biometric parameters and determining an acceptable data set.

A system for improved breast cancer prognosis using multimodal machine learning; the system includes: a central processing unit (CPU) configured to coordinate and execute data processing tasks; a multimodal data acquisition interface for communication with multiple diagnostic devices and hospital databases, wherein the multimodal data acquisition interface is configured to receive different datasets, including mammography images, histopathological images, genetic profiles and medical records, a feature extraction unit that is operationally connected to the central processing unit, wherein the feature extraction unit is configured to apply deep learning models to extract relevant features from the received datasets, including cell structures from histopathological images, masses or calcifications from mammographic images, and genetic mutations from genetic profiles; a machine learning engine integrated into the central processing unit and the feature extraction unit, wherein the machine learning engine is configured to analyze the extracted features using multimodal learning techniques, and wherein the machine learning engine is further configured to combine data from multiple modalities to generate a prognosis for breast cancer, the prognosis comprising an assessment of the disease course, the risk of relapse, and the likely treatment response; a forecast reporting unit in communication with the machine learning machine, wherein the forecast reporting unit is configured to generate a comprehensive forecast report in both visual and text formats, the report presenting multimodal analysis results in a format interpretable by medical professionals; and a power supply configured to continuously power the system, the power supply also including an uninterruptible power supply (UPS) to ensure uninterrupted operation of the system in the event of power outages or fluctuations.

The invention discloses a medical image analysis processing method based on AI, and relates to the technical field of image analysis, and the method comprises the steps: collecting multi-modal medical image data of a patient from an image device, and carrying out the preprocessing of the multi-modal medical image data; fusing the preprocessed multi-modal medical image data, extracting biological tissue features, constructing a biological tissue feature library, and marking abnormal biological tissue features in the biological tissue feature library; according to a medical image analysis task, combining with the marked biological tissue feature library to train an AI visual detection model so as to identify and classify different abnormal biological tissues; and automatically detecting an abnormal biological tissue area in the image by using an AI visual detection model. According to the method, high-precision analysis can be carried out on medical images through the AI technology, tiny abnormal changes can be detected, the severity of lesions can be evaluated and the development trend of diseases can be predicted through quantitative analysis on image features, and the risk of disease progression can be timely found and reduced when the lesions do not cause obvious symptoms.

The invention discloses an intelligent Parkinson's disease dysfunction assessment method and system, and belongs to the technical field of medical assistance, and the method specifically comprises the steps: deploying an intelligent interaction terminal in a daily living environment of a user, and continuously collecting unstructured user instruction data through the daily interaction behavior of the user and equipment; carrying out anonymization processing on the collected instruction data, and extracting a multi-dimensional feature set containing instruction logic continuity and intention rationality; a dynamic baseline model is established based on the instruction data of the user in the health state period, the baseline model automatically expands the storage capacity according to the time dimension, and a personalized reference database synchronously evolved with user interaction characteristics is formed; by analyzing the evolution matching degree between real-time instruction features and a baseline model, when it is detected that instruction logic continuity or / and intention rationality continuously declines and exceeds a self-adaptive threshold value, a visual early warning report containing a disease progress risk level is generated; the method can assist in finding early risks of diseases.

The invention belongs to the technical field of traditional Chinese medicine preparations, and particularly relates to a traditional Chinese medicine preparation for treating Parkinson's disease and a preparation method thereof. The traditional Chinese medicine preparation for treating Parkinson's disease comprises the following raw materials in parts by weight: 20-30 parts of bischofia polycarpa, 17-25 parts of eucommia ulmoides, 12-16 parts of artemisia sphaerocephala, 10-15 parts of lycopodium clavatum, 8-13 parts of elm leaves, 7-14 parts of pericarpium citri reticulatae, 5-10 parts of semen cuscutae and 2-7 parts of liquorice. In the formula, monarch, minister, assistant and guide are reasonably matched, the curative effect is exact, and the effects of regulating qi and blood, nourishing liver, warming kidney, activating blood and dissipating blood stasis are achieved. The compound can effectively improve core symptoms of Parkinson's disease and delay disease progression, is expected to be further developed into clinical drugs for treatment of Parkinson's disease, and provides an innovative scheme for traditional Chinese medicine treatment of neurodegenerative diseases.

The invention discloses homocysteine as a Graves eye disease biomarker and application thereof, the biomarker is homocysteine (Hcy), application of a reagent for detecting the biomarker in preparation of a product for diagnosing Graves eye diseases, and the reagent is used for detecting the level of Hcy in sample serum. By detecting the level of homocysteine (Hcy) in serum, an objective and quantitative biomarker is provided for diagnosis of Graves eye diseases (GO), the diagnosis accuracy is remarkably improved, and the defects that existing clinical activity scores are high in subjectivity and insensitive to latent patients are overcome; the Hcy level is in positive correlation with GO activity, and can be used for monitoring disease progression and treatment effect, optimizing disease management, reducing serious complications and improving life quality of patients.

A medical system useful in the determination of future disease progression in a subject. More specifically the present invention applies machine learning techniques to aid prediction of disease pathology and clinical outcomes in subjects presenting with symptoms of cognitive decline and to expedite clinical development of novel therapeutics.

The invention relates to the technical field of hepatic fibrosis treatment strategy optimization, in particular to a hepatic fibrosis treatment strategy optimization system and method based on deep reinforcement learning. The strategy generation module is in communication connection with the database module; the simulation module is in communication connection with the strategy generation module and is used for simulating the application effect of the treatment strategy through a simulation system; the evaluation module is in communication connection with the simulation module and is used for determining an effect value of treatment strategy application through the simulation module and transmitting the effect value to the strategy generation module; the scheme recommendation module is in communication connection with the strategy generation module and is used for recommending the treatment strategy to a doctor; the invention constructs a comprehensive, dynamic and intelligent hepatic fibrosis treatment decision support system. The system not only can process high-dimensional and non-linear medical data, but also can capture dynamic characteristics of disease progression, so that a major span from static decision to dynamic optimization is realized, and the overall efficiency and expandability of the system are greatly improved.

The invention discloses an active diagnosis and treatment cooperation system and method based on artificial intelligence full-process dominance, and belongs to the technical field of medical artificial intelligence, and the system comprises a pre-diagnosis management module which actively carries out the medical care team distribution of a registered patient and completes chronic disease signing, performing intelligent triage after judging the disease progress and the onset risk of the signed patient, generating a pre-diagnosis examination list for the triage patient, and completing the diagnosis and treatment process of the pre-diagnosis stage; the in-diagnosis management module judges the health state of the patient and actively pushes a standardized diagnosis and treatment path to form a chronic disease prescription to be provided for a doctor, and the chronic disease prescription is pushed to the patient after being signed by the system and the doctor; and the post-diagnosis management module is used for automatically generating a dynamic tracking plan, establishing a grading follow-up visit mechanism, generating a follow-up visit scheme and automatically returning prognosis data of the patient to guide system optimization training. The whole process of chronic disease prevention and treatment is dominated through AI, the chronic disease management quality can be improved, the chronic disease prevention and treatment homogenization level is improved, and whole-process high-quality public service supply is achieved.

The invention relates to a molecular model established based on proteomics detection serum specimens and used for assisting in evaluating the renal injury progress of diabetic nephropathy as well as a construction method and application of the molecular model, new disease diagnosis markers can be found, and an existing disease diagnosis system can be optimized; according to the technical scheme, a proteomics technology is combined with various medical diagnosis technologies such as experiments and images through research thinking logic of evidence-based medicine and clinical epidemiology so as to diagnose whether a patient suffers from diseases or not and identify different diseases, and the molecular model is formed by combining proteins P23396 + P0CG47 + Q9NYQ8 + P63241, according to the present invention, the protein composition in the sample is detected by using the high-throughput mass spectrometry means, the difference of the diabetic nephropathy disease group and the non-disease group on the proteomics level is compared, the biomarker for the disease progress auxiliary evaluation model construction is screened, and the new scheme is provided for the disease progress auxiliary evaluation of the diabetic nephropathy.

The invention discloses a data-driven early-diabetic future diabetes-related disease progress risk prediction model and a construction method thereof, and the method comprises the steps: collecting clinical index data, including age, gender, BMI, WHR, HOMA-IR, HDL-C, TG, SBP, DBP, SCR and ALT, of early-diabetic patients in a training and verification queue; using an unsupervised soft clustering method combining dimension reduction based on UMAP, graph clustering and a Gaussian mixture model to identify the phenotypic heterogeneity of the prediabetes mellitus; obtaining the probability of the individual phenotype characteristics, evaluating the association between the probability and the development risk of the future diabetes related diseases in the early stage of diabetes, and constructing a development risk prediction model of the future diabetes related diseases in the early stage of urine diseases; and performing model optimization and robustness verification in the verification queue. According to the method, the heterogeneity of the prediabetes mellitus can be effectively identified, and accurate risk stratification and personalized prevention are realized.