158 results about "Disease category" patented technology

Clinical trials are defined, managed and evaluated according to an overall end-to-end system. The central authority creates protocol meta-models and makes them available to clinical trial protocol designers. Each meta-model includes a short list of preliminary patient eligibility attributes which are appropriate for a particular disease category. The protocol designer chooses the appropriate meta-model, and encodes the clinical trial protocol, including eligibility and patient workflow, within the selected meta-model. The resulting protocol database is stored together with databases of other protocols in a library of protocol databases. Sponsors and individual clinical sites have controlled access to the protocols. Study sites make reference to the pertinent protocol databases to which they have access in the protocol database library in order to perform patient eligibility screening. Once a patient is enrolled into a study, the protocol database indicates to the clinician what tasks are to be performed at each patient visit. These tasks can include both patient management tasks and data management tasks. The workflow graph advantageously also instructs the proper time for the clinician to obtain a patient's informed consent. The system reports patient progress to study sponsors, who can then monitor the progress of the trial, and to a central authority which can then generate performance metrics. Advantageously, a common controlled medical terminology database is used by all components of the system.

The invention relates to a winter jujube disease identification method based on a deep convolutional neural network and a disease image. The method includes the following steps that: an original winter jujube diseased fruit RGB color image collected by an Internet of Things is converted into a YUV color model, and preprocessing is performed; the a rectangular region of interest of disease spots which contains a disease image is extracted, the rectangular region of interest is segmented through using a K-means clustering algorithm, so that a YUV color disease spot image can be obtained; and a three-channel layered convolutional neural network model is constructed and is trained by using training data, and a jujube disease image to be recognized is inputted into the trained model so as to be subjected to disease category identification. The method of the invention can be applied to an Internet of Things-based greenhouse winter jujube disease monitoring system and can obtain accurate disease identification results.

Evaluation of health care provider quality is described. Data is obtained, the data including claims data and member data of a member panel of a health care provider, the member panel including patients to which the provider provides health care services. Based on the obtained data, quality scores are determined for the provider across the member panel and across health care quality domains. A composite health provider quality score of the health provider is then determined, where the composite health provider quality score is a composite of the determined quality scores across the member panel and across the multiple health care quality domains. In some embodiments, risk-adjustment is performed for the quality scores, such as risk-adjustment against a peer reference base based on disease categories, patient age, and patient gender.

A system and method is provided for determining a probability that a member of a health plan has a disease or condition within one or more disease categories, by using data from the member's pharmacy claims. Logistic regression models are generated for each condition category using therapeutic drug categories, provider information, and / or other variables including member demographic information.

Mycobacterial proteins from culture filtrate or cytosol are disclosed as being useful B cell antigens for early diagnosis of mycobacterial disease, particularly in humans. These proteins include four that had not previously been recognized as B cell antigens (LppZ protein encoded by Mtb gene Rv3006; SodC protein encoded by Mtb gene Rv0432; BfrB protein encoded by Mtb gene Rv3841 and TrxC protein encoded byMtb gene Rv3914). Antigenic compositions include these proteins and / or peptide fragments thereof, in various combinations with each other or with one or more of a set of 10 additional Mtb proteins known to be antigens (in paricular early antigens. Methods and kits for using these antigenic composition for early diagnosis of mycobacterial infection and disease are also disclosed.

The invention discloses a medical image disease classification method based on naive Bayes. According to an equipment type and image finding, diagnosis and other text information in a diagnosis report form, the disease type which an image examination result belongs to is automatically judged. Considering the influence of the independence assumption of naive Bayes classification in actual application, the method carries out disease clustering analysis by utilizing a K-Means clustering algorithm, data with the high similarity level are classified into the same cluster, data with the low similarity level are classified into different clusters, and meanwhile the number of disease categories is determined. The characteristics of high efficiency and high speed of a naive Bayes algorithm are utilized, classification precision is guaranteed, and meanwhile classification speed of medical image search is improved to a large degree.

The invention relates to a medical expense information processing method. The method is characterized by comprising the steps of receiving medical information; judging whether the medical information conforms to a case classification standard or not, if so, querying a first expense information threshold range corresponding to a first case category to which the medical information conforms, judging whether the medical information conforms to rational drug use regulations or not, if so, extracting medical expense information from the medical information, judging whether the medical expense information is contained in the first expense information threshold range or not, if not, outputting abnormal result information; if the medical information does not conform to the rational drug use regulations, outputting abnormal result information; if the medical information does not conform to the case classification standard, bringing the medical information into a new second disease category, and setting a second expense information threshold range for the second disease category; and extracting medical expense information from the medical information, judging whether the medical expense information is contained in the second expense information threshold range or not, and if not, outputting abnormal result information.

The invention discloses a method for converting physical examination diagnostic data into a disease label. The method comprises the steps that 1, the physical examination diagnostic data is subjected to text word segmentation and new word finding processing, and a word sequence is obtained; 2, in the word sequence, needed disease vocabularies are extracted, and disease names are obtained; 3, synonyms in the disease names are merged, and merged disease names are obtained; 4, the disease names are clustered, and a disease category tree is set up; 5, disease marking is carried out according to the merged disease names and the disease category tree, and the disease label is obtained. According to the method, multiple natural language processing technologies are adopted for mining disease results in the physical examination diagnostic data, a disease classification structure is extracted, code digitization is carried out, the disease name label is provided for physical examination records, and therefore the physical examination result is more directly described, and other big data medical treatment can be served.

The invention relates to a traditional Chinese medicine clinical digital evaluation system.The system includes five first-grade indexes including a clinical treatment effect index, a preponderant disease index, a traditional Chinese medicine diagnosis and treatment method index, a work attitude index and a workload index.The ability of a doctor can be graded and analyzed through the big data analysis technology on the basis of the traditional Chinese medicine clinical digital evaluation system.Evaluation is conducted layer upon layer from sub-index evaluation to comprehensive evaluation, internal evaluation and external evaluation are organically combined, and clinical treatment effects, preponderant disease categories, traditional Chinese medicine diagnosis and treatment methods and work efficiency and work attitude of doctors are comprehensively analyzed.By means of the big data processing technology, the indexes are subjected to detailed weight calculation to obtain a data conclusion with bases, and accordingly work ability and level of traditional Chinese medicine doctors are scientifically evaluated.

The invention discloses a graded diagnosis and treatment evaluating method based on data mining. The method comprises the steps: extracting essential information and diagnosis and treatment information on patients from medical records, associating the essential information and the diagnosis and treatment information with disease category information and medical institution information, and firstly, carrying out data cleaning and missing value filling so as to divide the patients into patients of different flow directions; then, calculating graded diagnosis and treatment monitoring indexes by using the data; portraying visiting behaviors and features of different patients by a GainRatioAttributeEva feature selection algorithm and a RIPPER sorting algorithm. According to the method, through evaluating graded diagnosis and treatment by qualitative indexes and quantified indexes, the defects in the current graded diagnosis and treatment evaluating methods that only the quantified indexes exist, the indexes are required to be reported layer upon layer, mis-reporting and confused reporting occur during reporting, and the tracking of reasons behind the indexes is absent are overcome; by using a data mining technology, graded diagnosis and treatment evaluation is more timely and accurate.

The invention provides a road image intelligent acquisition and identification method based on deep learning. The road image intelligent acquisition and identification method comprises the following steps: shooting a road video image through road image acquisition hardware, extracting key frames in the video image through a program, detecting and identifying the key frames through an image intelligent identification algorithm, and determining a disease position, a disease category and a disease grade in the road image. According to the invention, positioning of the road disease area and classification tasks of types and grades can be completed, and manual intervention is not needed, and unmanned operation is completely realized, and the automation degree is high, and the fault tolerance ishigh, and the road maintenance patrol efficiency can be greatly improved, and the intelligent management level of the industry is improved.

The embodiment of the invention provides a road disease identification method and device based on a neural network. The method comprises the following steps of: obtaining a sample; obtaining a road disease image sent by vehicle-mounted collection equipment, inputting the road disease image into a preset convolutional neural network model, calculating to obtain a disease category value corresponding to the road disease image; the disease relative position and the disease instance are divided into regions; wherein the disease relative position is the position of the disease in the road disease image; determining a disease category corresponding to the road disease image according to the disease category value, determining a disease level corresponding to the road disease image according to the disease relative position or the disease instance segmentation area, The disease category and the disease grade can be automatically identified through the disease image, the identification efficiency is high, the identification accuracy can be improved through the preset convolutional neural network model, and the problems of low manual identification efficiency and potential safety hazards are avoided.

The invention discloses a medical data processing device and method for per-disease payment. The device comprises a health-care management data processing system and a hospital clinical business dataprocessing system. Basic data of various disease categories and policy data of health care for applying for reimbursement according to the disease categories are built separately by the systems on thebasis of internet or mobile internet cloud computing, clinical project list catalogs based on the policy framework are built, all medical institutions call the data in clinical businesses, and clinical business processing and expense settlement are achieved under the per-disease payment health-care policy framework. A patient can see a doctor smoothly in any local hospitals or hospitals in placesother than the patient's own hometown, and real time settlement is achieved through per-disease payment of the health care.

The invention discloses a pest and disease detection method based on a deep convolutional neural network. The method includes: classifying crop pests and diseases to be detected according to crop categories, pest and disease categories and severity degrees; shooting leaves of the diseased crops by using a camera instrument to make a data set related to plant diseases and insect pests; setting a stacked network module, the stacked network module comprising a convolutional layer, a normalization layer and an activation function layer in a convolutional neural network, the number of feature map layers of each layer being superposed and fused with each other; embedding the stacked network module into a pest and disease damage detection deep convolutional neural network; building a network model through a pest and disease damage detection deep convolutional neural network framework, training the network model on the basis of a data set, and finally sending crop leaves to be detected into the network model to obtain a detection result. The method is high in detection precision and wide in application range, and can be applied to the field of agricultural crop prevention and control, suchas paddy field disease and pest detection, fruit tree disease and pest detection and soybean disease and pest detection.

The invention relates to the medical diagnosis field, in particular to a clinical somatic symptom classification test and appraisal system. The clinical somatic symptom classification test and appraisal system comprises a somatic symptom detection module, an analysis module and a guide module, wherein the measurement emotionality somatic symptom data, the measurement biological somatic symptom data, the measurement cognitive somatic symptom data and the measurement imaginative somatic symptom data of a single object are obtained according to a clinical somatic symptom scale; then, confirming the symptom category of the single object, and calculating the physiological index score and the psychology index score of the single object; and providing a processing proposal for the single object. Since the clinical somatic symptom scale is set to be used, a patient does not need to judge disease categories through various time-consuming high-expenditure detections so as to lower detection cost and shorten detection time, and therefore, deficiencies in the prior art are eliminated.

Disclosed, in one general aspect, is a musculoskeletal imaging system that includes a source of feature data extracted from imaging data resulting from imaging acquisitions from joints of different individuals affected by different diseases, and this feature data includes disease characteristic categorization information for a plurality of disease categories. A comparison module is operative to compare patient imaging data resulting from an imaging acquisition from a joint of a patient with the feature data. The comparison module is also operative to provide at least one categorization indicator for the patient imaging data that indicates a correspondence between spatial information in the patient imaging data and the disease categories for which there is extracted categorization information in the feature data.

The invention discloses a disease predicting model construction method based on a gradient iterative tree. The disease predicting model construction method comprises the steps of preprocessing collected clinical data, adopting basic information and blood routine examination indexes to construct features; constructing a first predicting model based on a GBDT algorithm, labeling a data set of the first predicting model, adopting a training set to train the first predicting model, adopting grid search to adjust and optimize the parameters, and optimizing the first predicting model, wherein the first predicting model is used for predicting diseases and health conduction; constructing a second predicting model based on the GBDT algorithm, labeling a data set of the second predicting model, adopting the training set to train the second predicting model, adopting grid search to adjust and optimize the parameters, and optimizing the second predicting model, wherein the second predicting modelis used for predicting specific disease categories. By the adoption of the disease predicting model construction method, data can be rapidly labeled, the obtained disease predicting models have high predicting accuracy rate, and the predicting time is short.

The invention discloses a crop disease identification method based on a deep fusion convolutional neural network. An IR _ CNN model provided by the method is formed by cascading effective modules in Inception v1 and ResNet50, and can be used for respectively extracting crop disease image diversity and deep features and fusing the crop disease image diversity and the deep features. The IR _ CNN model module is composed of neural networks with different branches, so that the width of the overall network is increased; full connection or even general convolution is converted into sparse connection, so that the calculated amount of the network is reduced. According to the method of the invention, the feature extraction capabilities of different network models are combined, so that x diversity features and deep features in crop disease images can be better obtained, the features are fused subsequently; various disease categories of different crops, especially complex crop diseases, can be better identified through training learning. The method has high identification precision.

The invention provides a hospitalization service performance evaluation method of medical institutions. The 20th chapter in codes of international classification of diseases ICD-10 is used as main disease classification MDC, for the diseases in each MDC, grouping is conducted continuously according to the top three of the ICD codes of disease categories, standardized processing is conducted on all indexes through the disease category grouping DCGs method, the medical technology difficulty and the service capacity, efficiency and quality of hospitals are evaluated, and therefore the total hospitalization service performance is obtained. The method involves a hospitalization service capacity evaluation method, a hospitalization service efficiency evaluation method, a hospitalization service quality evaluation method and a total hospitalization service performance evaluation method. Through the methods, a hospital performance evaluation model based on hospitalization medical record home page information is established according to core contents of medical service performance, and the purpose of analyzing and studying hospital service performance is achieved.

The embodiment of the invention provides a disease diagnosis method and a terminal, wherein the method comprises the following steps: acquiring disease symptoms of a user; judging the disease category of the user according to the disease symptoms of the user and pre-stored disease sample data, acquiring a rehabilitation proposal corresponding to the disease category, wherein the disease sample data comprise disease names, disease symptoms and rehabilitation proposals for various diseases; outputting the disease category and the rehabilitation proposal to the user. The terminal is used to judge the disease category of the user according to the symptoms of the user, and provides the corresponding rehabilitation proposal for the user.

The invention provides a deconvolution-guided semi-supervised plant leaf disease identification and segmentation method, which uses a small amount of disease category labels and disease spot pixel-level labels to achieve disease category identification and disease spot region segmentation through deconvolution. According to the method, a category prediction label of an unmarked sample is generatedthrough a consistency regularization and entropy minimization method; image mixing is carried out on the marked sample and the unmarked sample, and semi-supervised disease classification is carried out by utilizing the newly generated image; and up-sampling is performed on the category information, and semi-supervised scab segmentation is performed by using a small number of pixel-level marks. Inthe process of model training, model parameters are updated by using exponential weighted average, so that the model is more robust in test data. The method is suitable for identifying and segmentingplant leaf diseases with insufficient label samples, integration of identification and segmentation is achieved, the model has high generalization capacity in leaf images with insufficient light andforeign matter shielding, and the identification and segmentation speed can meet the real-time requirement.

The invention discloses a quality monitoring method and device for insurance cooperative hospitals, a storage medium and a terminal, relates to the data processing technology field and mainly solves aproblem that different patients have different evaluations of medical service items and can not reasonably provide insurance companies with the accurate information about costs, services and the medical quality. The method comprises steps that claims data of different cooperative hospitals for the insured personnel and the pre-inputted evaluation information of the cooperative hospitals are acquired; according to disease categories, disease subtypes and treatment strategies, diagnosis disease-related group DRGs grouping of the claims data is carried out, and expected values of the medical expenses are determined; the cost consumption index and the time consumption index in the evaluation information are analyzed; predictive classification is carried out according to the expected values ofthe medical expenses of the different cooperative hospitals, the cost consumption index and the time consumption index, and the quality results of the cooperative hospitals are determined. The methodis advantaged in that the method is suitable for carrying out quality monitoring of the insurance cooperative hospitals.

A method of creating a classification system for rating the nature and severity of health care requirements, including obtaining a set of medical disease codes, categorizing the medical disease codes into major disease categories, and categorizing the medical disease codes in each major disease category into episode disease categories based on severity.

Embodiments of the invention include methods, systems, and computer program products for generating a medical problem list. A non-limiting example of the method includes receiving, by a processor, a plurality of disease categories. A disease category set that includes a plurality of top level disease categories is defined using the processor, wherein the disease category set is based at least in part upon the plurality of disease categories. The processor is used to extract a plurality of candidate training problems from an electronic patient record training set. The processor is used to assign each of the candidate training problems to the plurality of top level disease categories. The processor is used to generate a disease category model for each of the top level disease categories from the electronic patient record training set using a machine learning technique.

The embodiment of the invention relates to an automatic test method and device, a computer readable storage medium and electronic equipment. The method relates to the technical field of medical big data processing, and comprises the following steps: classifying historical medical data according to disease categories to obtain a plurality of classification results corresponding to the disease categories, and extracting a plurality of key fields corresponding to the disease categories in each classification result; structuring and normalizing the key fields to obtain a plurality of standard fields, and training an initial network model by utilizing the disease categories and the standard fields corresponding to the disease categories to obtain an automatic test model; and inputting to-be-tested medical data into the automatic test model to obtain a first test result corresponding to the to-be-tested medical data, and judging whether the to-be-tested medical data is successfully tested ornot according to the first test result. According to the embodiment of the invention, the accuracy of the first test result is improved.

Relating to the technical field of moxibustion in Chinese medicinal physiotherapy, the invention discloses a moxa stick with a Chinese medicinal prescription and a preparation method thereof. The moxa stick is composed of artemisia argyi, Tainding, herba siegesbeckiae, girardinia cuspidata, trachelospermum jasminoide, rosin, clove, costus root, frankincense, radix angelicae pubescentis, angelica dahurica, radix saposhnikoviae, herba schizonepetae, herba selaginellae, sapindus, sophora japonical, Baicaodan and barley koji. According to the invention, by adding various important ingredients into artemisia argyi, the moxa stick has wider curative effect, and because of the use of a food grade adhesive, the moxa stick does not deteriorate easily, at the same time by combining several groups of moxa sticks into a large diameter moxa stick, thus prolonging the burning time of the moxa stick, and ensuring the burning stability and continuity of the moxa stick. The preparation method of the moxa stick is simple, and can change the Chinese medicinal components in the moxa stick according to the treated disease category.

The invention provides a medical image recognition method, device and equipment and a storage medium, and relates to the field of artificial intelligence such as computer vision, deep learning and smart medical treatment. The medical image recognition method comprises the steps that a medical image is input into a disease grading network, a category activation graph output by the disease grading network and disease categories and disease confidence coefficients of the category activation graph are obtained, the category activation graph can represent related areas indicating the correspondingdisease categories in the medical image, and division of the disease categories is related to one or more lesions; the method further includes inputting the medical image into a pathological sign recognition network; obtaining one or more focus probability graphs output by the pathological sign recognition network, wherein each pixel of each lesion probability graph indicates the probability thata corresponding sub-region in the medical image comprises a lesion, and under the condition that the corresponding disease confidence coefficient is greater than the preset confidence coefficient, thesimilarity between the category activation graph and each focus probability graph in the one or more related focus probability graphs is greater than a set threshold value.

The invention discloses a knee joint disease ultrasonic diagnosis method based on deep learning multiple channels and a graph embedding method, and the method comprises the following steps: carrying out the preprocessing of an effusion region in a knee joint ultrasonic image through employing an snake algorithm, and then inputting the effusion region into a defined network model for semantic segmentation; on the basis of a Resnet network structure, training a knee joint ultrasonic image in a data set by utilizing a graph embedding method of secondary training, and finally performing verification by utilizing tests of a segmentation network and a classification network. According to the invention, the knee joint ultrasonic image is segmented and trained by using the thinking of multi-channel superposition and a graph embedding method; disease categories can be distinguished according to whether hydrops areas in different knee joint disease ultrasonic images are accompanied by the difference of synovial membrane thickening or not, the situation that knee joint ultrasonic image judgment completely depends on naked eyes and personal judgment of doctors is avoided, the problems of subjectivity and personal errors are eliminated, and the whole segmentation and classification recognition method is simple, efficient and accurate in diagnosis.

Mycobacterial proteins from culture filtrate or cytosol are disclosed as being useful B cell antigens for early diagnosis of mycobacterial disease, particularly in humans. These proteins include four that had not previously been recognized as B cell antigens (LppZ protein encoded by Mtb gene Rv3006; SodC protein encoded by Mtb gene Rv0432; BfrB protein encoded by Mtb gene Rv3841 and TrxC protein encoded by Mtb gene Rv3914). Antigenic compositions include these proteins and / or peptide fragments thereof, in various combinations with each other or with one or more of a set of 10 additional Mtb proteins known to be antigens (in particular early antigens. Methods and kits for using these antigenic composition for early diagnosis of mycobacterial infection and disease are also disclosed.

The invention provides a diagnosis result verification method and device and electronic equipment, and belongs to the technical field of artificial intelligence medical treatment and knowledge maps. The method comprises the steps of obtaining a to-be-verified diagnosis result sent by a first client and associated target medical record data; determining a first label set corresponding to the to-be-verified diagnosis result according to a preset mapping relationship between labels and diseases; processing the target medical record data by using a preset label classification model to determine asecond label set corresponding to the target medical record data; and determining the credibility of the to-be-verified diagnosis result according to the overlap ratio of the first label set and the second label set. According to the invention, through the verification method of the diagnosis result, misdiagnosis verification of the diagnosis result of a doctor is realized according to the overlapratio of the disease category to which the to-be-verified diagnosis result belongs and the disease category to which the target medical record data belongs, so that the diagnosis accuracy of a primary medical institution is improved, and the misdiagnosis rate is reduced.