177 results about "Differential diagnosis" patented technology

The invention discloses an acute abdominal pain cause differential diagnosis system based on deep learning, and relates to the technical field of medical artificial intelligence, comprising: a data acquisition module acquires initial self-described text data of a patient; the standardization processing module generates a standardized symptom set through standardization processing; the cause reasoning module performs reasoning according to the standardized symptom set and the medical knowledge graph to obtain a suspected disease set; the contradiction detection module is used for detecting the contradiction between the symptom set and the self-contained text and calculating the contradiction intensity and disease cause relevancy; the priority calculation module ranks contradiction priorities according to contradiction intensity and disease cause relevancy; the contradiction processing module judges the contradiction significance score, if the contradiction significance score is lower than a threshold value, a standardized symptom set is output, and otherwise, an optimal clarification action is generated to solve the contradiction; an iteration updating module updates a symptom set according to clarification action feedback, and causes are inferred again until a termination condition is met; the method can ensure that the pathogenesis reasoning process gradually approaches the real pathogenesis, and improves the diagnosis reliability.

The invention belongs to the technical field of artificial intelligence, and particularly relates to an artificial intelligence medical diagnosis system based on multi-dimensional information fusion. Comprising the steps that a self-adaptive diagnosis path planning module judges whether a user request belongs to a preset non-diagnosis and treatment category or not, if yes, a quick response path is activated, and a standardized answer is retrieved and returned to a user; the preliminary diagnosis module generates a candidate disease hypothesis list, verifies the candidate disease hypothesis list and outputs a verified disease hypothesis list; the dynamic knowledge enhancement module generates missing knowledge according to the disease knowledge graph and the query verification disease hypothesis list and supplements the missing knowledge into the medical knowledge graph; a composite confidence evaluation module performs confidence evaluation on each hypothesis disease in the verification disease hypothesis list, and outputs a final disease confidence; the result integration module sorts the final disease confidence in a descending order and integrates the multi-dimensional information of each hypothetical disease to generate a structured differential diagnosis report; the system and the method can assist doctors in realizing high-accuracy, high-reliability and explainable intelligent medical diagnosis.

The invention relates to a pathological section intelligent auxiliary differential diagnosis system based on multi-modal fusion, in particular to the field of clinical pathology, semantic unification of multi-modal data is achieved through meta-task construction and a cross-modal alignment technology, and transferable diagnostic knowledge is extracted by utilizing a meta-learning framework; the method combines a generative model and knowledge constraints to generate high-quality synthetic data, and finally fuses real and synthetic samples through a self-adaptive diagnosis mechanism, thereby remarkably improving the differential diagnosis capability of rare lesions, effectively solving the problem of model generalization in a training data scarcity scene, and improving the accuracy of model identification. And efficient and reliable intelligent auxiliary decision support is provided for clinical pathological diagnosis.

An AI-based system and method for supporting differential diagnosis and standard of care in healthcare. The method involves receiving patient information from various sources, including patient-reported symptoms, physician notes, and sensor data from medical devices. The patient information is preprocessed and analyzed using deep learning models to generate a ranked list of potential diagnoses, each associated with likelihood scores and key contributing factors. The potential diagnoses are provided to physicians via an interactive interface, and physician feedback is collected to fine-tune the AI models using reinforcement learning. The method aims to enhance physician decision-making, improve diagnostic efficiency, and ensure adherence to the standard of care by leveraging AI's ability to analyze vast amounts of data more effectively than human physicians.

The invention discloses an AD diagnosis method fusing electroencephalogram frequency spectrum standardization deviation and a brain network. The AD diagnosis method comprises the steps that S1, band-pass filtering and fragment segmentation are conducted on multi-channel EEG signals of five brain regions; s2, for each segment, calculating brain region-frequency band characteristics of five different brain regions; s3, performing standardized modeling by adopting a GAMLSS model, identifying individual deviation information of a disease group about a specific brain region rPSD, training a LightGBM classifier by utilizing the individual deviation information, and extracting a structured feature vector by utilizing an internal structure of the classifier; s4, dividing each segment into a plurality of non-overlapping frequency boxes according to frequency resolution, calculating an FCN graph in a matrix form of each frequency box, constructing a three-dimensional image according to the FCN graph, and extracting a visual feature vector by using a Swin transformer network; and S5, constructing a connection vector, and inputting the connection vector into a classifier for classification. The method provides a new technical approach for accurate diagnosis and differential diagnosis of neurodegenerative diseases.

The application discloses a kind of sheep mycoplasma Mo, Mccp, Mmc triple PCR detection method establishment and application, by using high-throughput Mauve genome collinearity analysis the specific difference section between three kinds of sheep mycoplasma genomes each other, design and screen out the specific primer capable of differential diagnosis three kinds of sheep mycoplasma, by primer sequence amplification, sequencing, identify three new sheep mycoplasma differential diagnosis target molecule, respectively Mo differential diagnosis target molecule DprA, Mccp differential diagnosis target molecule MCCPF38_00240, Mmc differential diagnosis target molecule restriction endonuclease subunit S.Utilize new target specific section, establish the triple PCR method capable of simultaneous differential diagnosis three kinds of sheep mycoplasma (Mo, Mccp, Mmc).The PCR method of the application has the characteristics of clinical convenient, rapid diagnosis, can be widely used in the clinical diagnosis of sheep mycoplasma, with good market prospect and economic value.

The invention relates to 4 serum peptide patterns for diagnostics of intracranial hemorrhagic stroke (ICH) in humans and differential diagnosis from acute ischemic stroke that are defined using a list of the 34 quantitative peptides that in sera of patients with ICH are increased 2 folds or more as compared with individuals without stroke and patients with acute ischemic stroke and a list of 16 qualitative peptides detectable in sera of the patients with ICH but not detectable in the sera of individuals without stroke and in sera of patients with acute ischemic stroke.

The invention discloses an emergency intelligent triage method and system based on sensing equipment, and belongs to the technical field of medical triage, and the method specifically comprises the steps: collecting vital sign data through a physiological sensing device, and constructing an initial symptom vector; retrieving disease hypotheses based on the medical knowledge graph and constructing a time sequence path tree for each hypothesis; calculating a priority score of the detection node according to the resource occupancy state and the disease association quantity; selecting an optimal first-step detection point to execute detection, and correcting the assumed confidence of each disease by adopting a confidence inversion principle based on a detection result; the process is executed through iteration, a diagnosis path is dynamically adjusted, triage is completed when the confidence coefficient of the disease hypothesis reaches a definite diagnosis threshold value, and a differential diagnosis list is output and manual triage is started when the maximum number of iterations is reached. According to the method, through resource-aware detection node optimization and confidence inversion closed-loop optimization, dynamic path planning and intelligent decision making in the emergency triage process are realized, and the triage efficiency and accuracy are effectively improved.

The present invention relates to a method for the differential diagnosis of bipolar versus unipolar disorder in a human patient during a depressive phase from a biological sample of the patient, comprising determining the relative proportions of RNA editing variants of at least the A-to-I-edited RNA ZNF267 gene. The present invention also relates to a method for monitoring the treatment of a depressed patient exhibiting bipolar or unipolar disorder. Finally, the present invention provides a kit for the differential diagnosis of bipolar versus unipolar disorder in a patient during a depressive phase.

The embodiment of the invention provides a multi-role adaptive interaction method and system based on a stomatology knowledge base, and the method comprises the steps: recognizing a query role when a query signal is received, and obtaining the query content; calling a preset query engine matched with the query role, accessing a pre-constructed knowledge base according to the currently called query engine and the query content, and obtaining a differential diagnosis set containing a plurality of diseases with a sorting relationship; and performing multi-dimensional differential diagnosis reasoning on the diseases in the differential diagnosis set one by one according to the sorting relationship, correspondingly evaluating the comprehensive confidence coefficient of the reasoning result, and when the comprehensive confidence coefficient is not less than a preset threshold value, taking the corresponding disease as a diagnosis disease, and outputting a query report matched with the query role. According to the invention, doctors can be assisted to make professional clinical decisions, and convenient oral common sense popularization services can be provided for patients.

This disclosure belongs to the field of medical testing technology, and specifically relates to a classification, diagnostic, and prediction method, system, and electronic device for congenital neurodevelopmental disorders. Addressing the clinical diagnostic challenges of congenital neurodevelopmental disorders, this disclosure establishes for the first time a classification, diagnostic, and prediction method for congenital neurodevelopmental disorders based on whole-genome methylation signatures and customized SVM machine learning. This method achieves one-stop differential diagnosis across multiple mechanisms and diseases, filling a gap in existing technologies and providing a novel and efficient solution for the accurate diagnosis of congenital neurodevelopmental disorders.

The present application relates to the field of medical diagnosis, and in particular to screening biomarkers for differential diagnosis of gestational diabetes mellitus by using metabolomics, and establishing a model for diagnosing whether a pregnant individual is diabetic based on the biomarkers. The present application provides biomarkers and a diagnostic model for differential diagnosis of gestational diabetes mellitus, which can be applied to early diagnosis or prediction of gestational diabetes mellitus, and is of great significance for prevention or treatment of gestational diabetes mellitus.

The invention relates to the field of medical informatics, and provides a biomarker-based thyroid nodule benign and malignant identification method and system. The method comprises the following steps: collecting a serum sample; performing quantitative detection on the multiple markers in the serum sample to obtain concentration data of the multiple markers; inputting the multi-marker concentration data into a pre-constructed probability calculation model to obtain a prediction probability value; and according to a preset diagnosis threshold value and the prediction probability value, judging whether the thyroid nodule is benign or malignant to obtain a thyroid nodule benign or malignant identification result. By integrating multi-marker information, the biological difference between benign and malignant nodules is effectively captured, and the overall efficiency of differential diagnosis is improved.

The invention discloses a primer probe composition for detecting measles, parotitis, rubella and varicella virus nucleic acid and application, and belongs to the technical field of virus nucleic acid detection. The invention protects the real-time fluorescent PCR detection primer and probe composition for simultaneously or respectively detecting measles, parotitis, rubella and varicella viruses and different subtype strains, and plays a positive role in respectively or simultaneously performing clinical detection and prevention and diagnosis on different strains of several viruses. The detection method disclosed by the invention is simple, time-saving and labor-saving, wide in application range and convenient to use, and measles, rubella, parotitis and varicella viruses and different strains can be rapidly detected at the same time by amplifying a PCR reaction once. The primer probe composition provided by the invention is high in detection sensitivity, strong in specificity and good in repeatability, can realize rapid differential diagnosis on clinical samples, enables different patients to obtain timely targeted prevention and treatment, and has important significance for development of quadruple vaccines.

The application discloses an index combination for identifying diffuse large B-cell lymphoma and application thereof. The index combination is composed of gender, age and eight oligosaccharide chains, namely NGA2F, NG2FB, NG1A2F-1, NG1A2F-2, NA2F, NA2FB, NA3Fb and NA4Fb. The application also provides a prediction model, a prediction system, a computer readable storage medium and a kit constructed based on the index combination. Experimental results show that the prediction model has a sensitivity of 88.06%, a specificity of 92.98% and an AUC of 0.949 in identifying diffuse large B-cell lymphoma in a verification set. The application realizes, for the first time, non-invasive, rapid and high-accuracy identification of diffuse large B-cell lymphoma based on blood oligosaccharide chains combined with clinical indexes, and provides a brand-new tool for auxiliary differential diagnosis of patients with lymph node enlargement.

The invention relates to a spinal infection and tuberculosis intelligent diagnosis method based on an image large model, the core idea of the method is pre-training of a base and hierarchical fine tuning, that is, firstly, a general spinal image visual large model is trained based on a DINOv2 algorithm by using mass unmarked spinal MRI data, so that the spinal image visual large model masters the anatomical structure and basic pathological characteristics of the spinal column; and then a two-stage cascaded diagnosis network is designed on the base, so that the problems of whether infection exists or not and the infection type are solved respectively. The problems that in spinal infection differential diagnosis, labeling data is deficient and the feature extraction capacity is insufficient are solved, a DINOv2 self-supervised pre-training technology is utilized to construct a visual feature base model, automatic screening of spinal infectious diseases and accurate differential diagnosis of infection subtypes are achieved through a hierarchical two-stage reasoning architecture, and the accuracy of the spinal infection differential diagnosis is improved. Dependence on annotation data is greatly reduced, and identification accuracy of difficult cases is remarkably improved.

The application discloses a farm veterinarian question and answer and auxiliary diagnosis method and system based on a large language model, which comprises the following steps: standardizing a colloquial query to obtain structured query information; based on the information, mixed retrieval is carried out from a hierarchical veterinarian knowledge base to obtain a candidate disease list and a multi-source evidence set; a preliminary diagnosis answer is generated according to the multi-source evidence set, semantic and evidence alignment evaluation is carried out, and evidence sufficiency scores are generated; the differential diagnosis attributes of each disease in the candidate disease list are compared to identify key differences, and information missing items are identified by comparison with standard symptom profiles; based on the scores, key differences and information missing items, a multi-round diagnosis enhanced retrieval framework and user interaction are adopted, the candidate disease list and the multi-source evidence set are updated, and a diagnosis report is generated in combination with veterinary drug compliance rules. The application integrates hierarchical knowledge graphs, multi-evidence alignment and multi-round diagnosis logic, improves the accuracy of veterinarian question and answer, reduces knowledge illusion, and ensures drug compliance.

The application provides a gender stratified lung nodule disease identification and diagnosis model and system. Specifically, based on a machine learning method, six male characteristic indexes and six female characteristic indexes are used to construct a gender stratified identification and diagnosis system. The results show that the model based on support vector machine has an AUC greater than 0.8 in the training set and the validation set, has good identification ability, and can accurately identify and judge whether the patient with normal serum angiotensin converting enzyme level is a lung nodule disease patient. The system effectively solves the short board of the existing diagnosis method of lung nodule disease, and realizes the identification and diagnosis by using a small amount of characteristic indexes, greatly shortens the diagnosis time, and has a wide clinical application prospect.

The present application relates to the technical field of natural language processing, and discloses a large language model clinical diagnosis capability fine-grained evaluation method and system. The method comprises: obtaining a patient medical record data set; synchronously performing the following tasks: scoring a question-standard answer-model answer triple based on a predetermined scoring dimension, calculating the medical knowledge score of the evaluated model; the evaluated model performs a recall task and a differential task, confirms or excludes a differential diagnosis list, and obtains a final main diagnosis; linking the differential diagnosis list and the final main diagnosis output by the evaluated model in the patient medical record; and analyzing factors affecting the clinical diagnosis capability of the evaluated model based on the linking result. The present application aims to deeply and synchronously evaluate the medical knowledge and reasoning capability of a large language model based on the same clinical diagnosis situation.

The invention provides a biomarker for diagnosing primary biliary cholangitis and application of the biomarker, and belongs to the technical field of biomarkers. The biomarker disclosed by the invention comprises serum protein and / or N-glycopeptide. According to the method, the improvement of PBC diagnosis is taken as a starting point, the serum protein and the N-glycopeptide are taken as screening templates, a more accurate non-invasive prediction means for differential diagnosis of PBC is provided, and a theoretical basis is provided for rapid and accurate diagnosis of PBC.

This invention discloses a methylation marker for the differential diagnosis of malignant and benign breast tumors. The invention provides the application of the methylated SH3PXD2B gene as a marker in product preparation; the product is used for at least one of the following purposes: (1) distinguishing between benign and malignant breast tumors; (2) distinguishing between benign breast tumors and different subtypes or stages of malignant breast tumors; (3) distinguishing between different subtypes or stages of malignant breast tumors. This invention has significant scientific and clinical application value for differentiating between benign and malignant breast tumors, different subtypes or stages of malignant breast tumors, and guiding the development of reasonable clinical treatment plans.

The invention relates to a method for detecting misfolded alpha-synuclein protein in a biological sample to determine the presence of synucleinopathies in an individual. The method provided by the present invention can also be used for differential diagnosis of Lewy fold synucleinopathies from MSA synucleinopathies as well as for monitoring of the disease progression in individuals. Moreover, a kit for detecting misfolded αSyn protein in biological samples is provided.

The invention discloses a plasma protein marker for identifying or assisting in identifying parathyroid cancer and parathyroid adenoma and application of the plasma protein marker. The method comprises the following steps: firstly, collecting plasma specimens of a parathyroid carcinoma patient and a parathyroid adenoma patient before an operation, and screening through an unmarked quantitative proteomics technology to obtain 24 differential expression proteins; on the basis of the other part of plasma specimens of the parathyroid carcinoma patient and the parathyroid adenoma patient collected before the operation, the 24 differential expression proteins are verified through a parallel reaction monitoring technology; finally, three plasma protein markers (myoglobin, coronin-1A and a polyimmunoglobulin receptor) which can be used for identifying the parathyroid carcinoma and the parathyroid adenoma are obtained. Experiments prove that the plasma protein marker or the combination thereof can be used for auxiliary differential diagnosis of parathyroid carcinoma and parathyroid adenoma, and has important significance for improving the accuracy of preoperative diagnosis of parathyroid carcinoma.

The invention discloses a method for verifying LCBM tissue pathology types based on image parameter differences of DCE-MRI combined with DWI. By analyzing ADC values and DCE-MRI parameter differences of different pathological types of LCBMs and application values of DCE-MRI and DWI parameters in differential diagnosis of different histopathological LCBMs, contribution of ADC values and DCE-MRI parameters to different histopathological LCBMs is quantified by logistic regression, influences of DCE-MRI parameters on ADC values of different histopathological LCBMs are tested by multiple linear regression, the DCE-MRI parameters are tested by multiple linear regression, and the LCBMs of different histopathological LCBMs of different histopathological LCBMs of different pathological types are tested by multiple linear regression. The influence of ADC values on BBB leakage of the LCBM in different tissue pathologies not only verifies the characterization capability of multi-modal functional imaging parameters on the LCBM microenvironment, but also provides a new theoretical support and technical path for basic research and precise diagnosis and treatment of the LCBM through multi-modal integration, parameter weight quantification, interaction mechanism analysis and clinical application framework construction.

This invention provides a microfluidic chip for the multiplex differentiation and diagnosis of different avian influenza virus subtypes and its application. Specifically, it is a microfluidic chip based on TaqMan probes that can simultaneously and rapidly differentiate and diagnose 25 avian influenza subtypes, enabling high-throughput simultaneous detection of multiple gene targets. This invention utilizes high-throughput microfluidic chip technology to simplify the differential diagnosis procedure for avian influenza virus subtypes, resulting in more accurate and time-saving results. It is more suitable for rapid clinical diagnosis of avian influenza, providing technical support for rapid clinical detection, diagnosis, and prevention of avian influenza, and is of great significance for epidemic prevention and control and safeguarding public health security.

The application belongs to the technical field of kidney disease differential diagnosis, and particularly relates to a microbial gene marker for differentiating diabetic nephropathy and membranous nephropathy and application thereof. The application provides sufficient evidence for the differentiation and treatment of clinical diagnosis of diabetic nephropathy and pathological diagnosis of membranous nephropathy based on four microbial markers of Blautia, Akkermansia, Sphingomonas and Granulicatella.

The invention relates to the field of ophthalmic disease image recognition, and discloses an ophthalmic disease image recognition method based on a neural network model, and the method comprises the steps: collecting a fundus photographic image and an OCT image, and carrying out the size standardization processing; outputting a high signal-to-noise ratio preprocessed image through a convolution attention module and a multi-scale noise suppression neural network; constructing a double-attention fusion framework; features are dynamically fused through a cross attention mechanism, and small sample rare disease recognition performance is optimized in combination with a meta-learning training strategy; a classification threshold value is dynamically adjusted through Bayesian neural network probability modeling, and a preliminary recognition result is output; semantic mapping is completed based on an ophthalmic clinical diagnosis term library, and a structured report containing focus coordinates, lesion grading and differential diagnosis bases is generated; the problems that in the prior art, the requirement for large-scale crowd screening is difficult to meet, feature extraction accuracy is not high, feature expression is not comprehensive, the recognition accuracy is low, and a structured report cannot be output are solved.

The invention discloses an acute necrotizing pancreatitis severe prediction model construction method based on a machine learning method. The acute necrotizing pancreatitis severe prediction model construction method comprises the following steps: S1, collecting patient data based on an inclusion standard and an exclusion standard; s2, data preprocessing and feature selection; s3, obtaining an optimal differential diagnosis prediction model in combination with radiomics characteristics and a plurality of machine learning algorithms; s4, obtaining an evaluation index through prediction performance comparison; and S5, constructing a pancreas model, a pancreas surrounding model and a combination model, and producing an ROC curve interpretation result. The present invention develops and verifies a machine learning model for distinguishing between severe and moderate ANPs (i.e., ANSP and ANMSP). These models will be based on radiomics features extracted from pancreatic parenchyma portal vein phase CECT images, peripancreatic necrotic lesions, and combinations thereof. By evaluating the diagnostic performance of the models, early recognition of disease severity is realized, and support is provided for clinical decisions related to treatment.

The invention belongs to the technical field of medical diagnosis, and particularly relates to a visual column diagram construction method for identifying and diagnosing suppurative and tuberculous lumbar major muscle abscesses and interactive application. According to the invention, it is found that six indexes including serum uric acid (UA), thrombin time (TT), neutrophil absolute value (NEUT #), age (Age), fever (Fever) and erythrocyte sedimentation rate (ESR) are related to the type of the lumbar major muscle abscess, and a visual column diagram construction method for identifying and diagnosing suppurative and tuberculous lumbar major muscle abscess and interactive application are invented. And a first visual and quantifiable column diagram (Nomogram) prediction model for differential diagnosis of lumbar major muscle abscess is provided for the field. The technical problem that an abstract mathematical prediction model is converted into a visual graphic diagnosis tool which is intuitive in form and convenient to operate is solved, so that the visual graphic diagnosis tool can be separated from dependence on specific computing equipment, and clinical medical staff can quickly and accurately apply the visual graphic diagnosis tool on a diagnosis and treatment site conveniently.