210 results about "Blood test" patented technology

The present invention relates to a blood testing machine comprising a loading device, a retrieving device, a batching device, a transfer device, and a testing device. After a blood sample is collected, a blood collection tube and other materials are placed in the loading device. After the loading device loads the sample, the retrieving device clamps the blood collection tube and other materials on the loading device and moves them to a set position in the batching device. The blood in the blood collection tube is sampled by the batching device and the reagents required for the test are added to form a test specimen. The transfer device transfers the test specimen to the testing device for blood testing. Compared with the prior art, the present invention substantially automates the steps of blood testing, including sample transportation, sample reception and processing, on-board testing, and sample storage, greatly improving the accuracy and speed of testing.

The invention provides a blood transfusion treatment scheme recommendation system and method based on historical information, and relates to the field of medical information.The blood transfusion treatment scheme recommendation method comprises the steps that firstly, basic information and diagnosis information of a patient, real-time blood test information and historical blood transfusion medical record information are extracted from HIS, LIS, EMR and TMIS systems; performing joint semantic analysis on the basic information, the diagnosis information and the real-time blood test information, and converting the historical blood transfusion medical record information into a dynamic vector sequence; then, the current blood index and the historical blood transfusion time sequence are dynamically matched in a frequency domain space through nonlinear spectrum analysis, and a personalized recommendation scheme is generated in combination with the implicit reasoning ability of a pre-trained medical large model, so that the limitation of a traditional system in the aspects of static parameter setting, individual adaptability and semantic mining is broken through; and the accuracy and timeliness of blood transfusion treatment decision making are remarkably improved.

The invention discloses a phosphatidylcholine gold nano CT (Computed Tomography) probe as well as a preparation method and application thereof, and belongs to the technical field of medical materials. The preparation method comprises the following steps: step S1, preparing a phosphatidylcholine ligand NH2-MPC; step S2, synthesis of a gold nanocluster GS-Au25 is carried out; and S3, the GS-Au25 is modified with a PC ligand, and the PC-Au25 is prepared. The ultra-small gold nano CT probe PC-Au25 with an Au25 gold nano cluster as a core and phosphatidylcholine PC as a surface ligand is obtained by optimizing and screening the core size and the surface ligand property of ultra-small gold nano particles. Wherein the 2-methacryloyloxyethyl phosphorylcholine is used as a PC ligand for the first time to modify the surfaces of the ultra-small gold nanoparticles, so that the surface modification of the ultra-small gold nanoparticles is realized, and the ultra-small gold nanoparticles can be efficiently and freely filtered through the kidney. The CT probe can be applied to the determination of the glomerular filtration rate through a CT imaging or blood test method.

The invention provides a myocardial amyloidosis classification prediction method and system based on cardiac magnetic resonance multi-sequence radiomics, and is applied to the technical field of data processing. The method comprises the following steps: preprocessing cardiac magnetic resonance multi-sequence image information to generate a standardized multi-sequence image data set; processing the standardized multi-sequence image data set to generate a target image omics feature vector; processing the gene detection information to generate pathogenic gene characteristics and mutation type characteristics; processing the target radiomics feature vectors and the cardiac magnetic resonance parameters based on medical knowledge graph data to generate an AL type myocardial feature associated feature set and an ATTR type myocardial feature associated feature set; processing the blood detection index information and the intestinal microflora parameter information to generate myocardial amyloidosis influence factors; and processing the data based on the target myocardial amyloidosis classification prediction model to generate a myocardial amyloidosis classification prediction result.

The invention discloses an application method of a serum Raman spectrum as a biomarker in cognitive impairment diagnosis, a cognitive impairment diagnosis system is used for diagnosis, the cognitive impairment diagnosis system comprises a Raman spectrum detection and preprocessing module, a database module and a cognitive diagnosis module, and the application method comprises the following steps: step 1, collecting a sample; step 2, pre-treating a sample; 3, collecting and preprocessing a serum sample by using a Raman spectrum detection and preprocessing module; 4, performing model construction and optimization by utilizing a database module; step 5, performing efficiency evaluation; and 6, performing cognitive grading diagnosis on the new sample by using a cognitive diagnosis module. The method has remarkable technical progress, no cognitive impairment diagnosis blood test method suitable for the whole crowd exists clinically at present, cognitive impairment can be diagnosed through the Raman spectrum of serum, detailed cognitive function grading can be carried out, and the cost of a single sample is less than 100 yuan.

A method of determining the risk of developing a known disease or condition or of identifying the presence of the known disease or condition in a subject includes obtaining subject data that includes results of blood tests. The blood tests include a basic metabolic panel (BMP) and a complete blood count (CBC) panel. The method further includes classifying the subject data with respect to the risk of the subject having or developing the known disease or condition by using the subject data in a machine learning classification system. The classification system includes a machine learning model previously trained on BMP and CBC data from a positive group of training subjects who received a diagnosis of the disease or condition and from a negative group of training subjects who were not diagnosed to have the disease or condition.

A microfluidic device (12) for applying blood samples to a sensor element (26) for protein defect diagnosis and / or for conditioning a sensor element (26) for protein defect diagnosis is proposed, as is a protein defect diagnosis device (10) with the microfluidic device (12). A method for applying blood samples to a sensor element (26) for protein defect diagnosis and / or for conditioning a sensor element (26) for protein defect diagnosis and a method for analyzing protein defects in a blood sample (212) are also disclosed.

A system for early diagnosis and prognosis prediction of sepsis, according to an embodiment of the present invention, includes: a memory for storing general blood test data of a patient; and a processor, wherein the processor may be configured to pre-process the general blood test data of the patient stored in the memory as data to be input to an artificial intelligence model, input the pre-processed data to the artificial intelligence model trained for early diagnosis and prognosis prediction of sepsis, and obtain a sepsis prediction result from the artificial intelligence model.

The invention provides a metabolism-related fatty liver disease prediction method based on a self-attention mechanism, and the method comprises the steps: obtaining blood test and four diagnosis instrument data of a patient, and constructing a fatty liver disease data set; according to the same index data of the same patient in different periods, adding time sequence information codes to form an optimized fatty liver disease data set with sequence features; constructing and training a fatty liver detection model, wherein the fatty liver detection model comprises a convolutional neural network, a layered attention module and a feedforward neural network layer; and inputting patient data into the trained fatty liver detection model to obtain the metabolism-related fatty liver disease prediction grade of the patient. According to the invention, the method achieves the refined reasoning of the time sequence indexes of the patient through multi-scale convolution and hierarchical attention, and improves the prediction precision of the model.

The invention discloses a personalized rehabilitation scheme recommendation system for movement cognitive impairment of old people. The system comprises a data acquisition module which is used for collecting case data about a patient; the blood test data processing module is used for performing embedded representation on the blood test data of the patient; the chief complaint text processing module is used for performing embedded representation on the patient chief complaint text; the rehabilitation scheme acquisition module is used for characterizing a single rehabilitation measure, completing characterization of a composite rehabilitation scheme, predicting the rehabilitation measure to perform event classification based on patient personalization, simulating interaction of multiple rehabilitation measures and obtaining characterization of the rehabilitation scheme; and the rehabilitation scheme recommendation module is used for recommending a personalized rehabilitation scheme for the motor cognitive impairment of the old people by utilizing the trained rehabilitation measure scoring model. According to the method, the problems of slow convergence process and even over-fitting caused by lack of an embedding process for users and articles in a current recommendation algorithm are solved; and patient personalization is not considered in single rehabilitation measure recommendation.

A biological test system has receptacles for a variety of removable electro-mechanical biological blood test-based elements having multiple features such as lancets or strips. Testing is through an analysis biological test processor that provides results to a user test output with all designed to be contained in a pocket-transportable user biological test form factor that houses all elements. Biological test elements can be interchanged for multiple sensing modalities with automatic activation based on cartridge insertion of a glucose test element, an A1C test element, a ketone test element, or the like. Designs can include a user sampler configuration selector for a user sampling selection that may be analyzed so a user-personalizable, biological sampler control processor can automatically disable operation for test safety if a user sampling selection is determined to be unacceptable. The system can also provide a user cartridge action prompt, a user reselection prompt, or other action to clear the disable.

The invention discloses a bone defect repair material suitability prediction method based on deep learning, and the method comprises the steps: carrying out the overlapping and uniform partitioning of a bone defect region and a host bone region in three-dimensional CT image data, carrying out the position coding and feature extraction of a plurality of sub-blocks through a three-dimensional visual Transform model of multi-scale position coding, and obtaining the anatomical and functional features; calculating a bone metabolism activity score and a systemic inflammation score based on blood detection data, and then constructing pathophysiological features; performing multi-round interaction on the anatomical and functional features, the pathophysiological features, the parameter data and the multidirectional multi-head cross attention layer, in each round, selecting one modal feature as a query vector, and selecting any modal feature in the rest modal features as a key vector and a value vector; and fusing the interaction features of each round, and determining the suitability score and the risk level of the bone repair material by combining the attention weight and the bone metabolism activity score in the multidirectional multi-head cross attention layer.

The invention relates to a sepsis detection system which evaluates the sepsis risk of a patient in real time by integrating clinical signs, various physiological parameters, laboratory detection data and biomarkers and utilizing an intelligent algorithm. The system comprises a data acquisition module, a data transmission module, a data processing module, a user display module and an alarm module. The data acquisition module monitors physiological parameters such as consciousness, body temperature, heart rate, respiratory rate, finger pulse oxygen saturation, invasive blood pressure, urine volume and skin piebald in real time, and biomarker data such as leukocyte count, neutrophile granulocyte, neutrophile granulocyte number, C-reactive protein, procalcitonin and interleukin-6 are obtained through blood detection. And the data processing module performs sepsis risk assessment by integrating the biomarkers and the physiological parameters in combination with a machine learning model, and outputs a risk level. The user display module displays the evaluation result in real time and provides treatment suggestions, and the alarm module triggers an alarm under the high-risk condition to ensure timely intervention.

The utility model belongs to the technical field of blood detection sampling devices, and particularly relates to a blood detection sampling collector which comprises a main body and two first clamping grooves, a first connecting sleeve and a second connecting sleeve are inserted into the two first clamping grooves respectively, first clamping blocks are clamped with the interiors of the first clamping grooves, and second clamping blocks are clamped with the interiors of the second clamping grooves respectively. Limiting sleeves are clamped in the two limiting frames, rectangular grooves are formed in the bottoms of the two limiting frames, compression springs are fixedly connected to the inner tops of the limiting grooves, movable semi-rings are fixedly connected to the bottoms of the compression springs, fixing rings are fixedly connected to the inner side walls of the limiting sleeves, and diaphragms are fixedly connected to the interiors of the fixing rings. By arranging the limiting frame, the compression spring, the movable semi-ring, the limiting sleeve and the diaphragm, air isolation of a needle output hole is achieved, and pollution to blood in the main body caused by long-term exposure of the needle is avoided; and by arranging a first stop block and a second stop block, the two limiting frames can be conveniently limited by the limiting block.

This application provides a diabetes assessment device and a diabetes assessment method, relating to the field of image processing technology. The diabetes assessment device includes: an image determination module configured to determine a fundus image to be assessed, wherein the fundus image is used to characterize the physiological structures of the fundus; and a diabetes assessment module configured to determine a diabetes assessment result based on the fundus image to be assessed. By setting the image determination module, the fundus image to be assessed can be determined; by setting the diabetes assessment module, the diabetes assessment result can be determined based on the fundus image to be assessed. That is, invasive examinations such as blood tests are unnecessary; the diabetes assessment result can be determined solely based on the fundus image to be assessed, without causing harm to the patient's physical or mental health.

Provided are a resistive random-access memory (RRAM)-based blood test system and method. The system comprises: a computing chip, an RRAM chip, a power supply module, and a sensor module; the computing chip is connected to the RRAM chip; the RRAM chip is connected to the sensor module; and the power supply module is connected to the computing chip and the RRAM chip; the sensor module is configured to test a substance in blood and convert test result data into a plurality of pieces of first voltage data; the RRAM chip is configured to preprocess the received plurality of pieces of first voltage data and obtain second current data; and the computing chip is configured to, based on the second current data, perform a function computation on the second current data according to a preset function computation model, and obtain a blood-based classification result.

The utility model relates to the technical field of blood, and discloses a blood vibration mixing device which comprises an operation table, a vibration assembly is arranged above the operation table, the vibration assembly comprises a vibration table, a storage shell is arranged on the vibration table, and a plurality of storage grooves are formed in the storage shell; a plurality of reset springs are jointly and fixedly connected to the lower portion of the vibration table and the upper portion of the operation table, a rotating assembly is arranged in the operation table, and the rotating assembly comprises a rotating pipe, the vibration assembly is arranged, the storage shell rotates through the rotating pipe and a rotating rod, and therefore the storage shell can drive blood test tubes in the storage groove to rotate; meanwhile, under the action of reset springs on the vibration table, after the reset springs vibrate, the vibration table can drive the storage shell to vibrate, and therefore the blood test tubes in the storage groove can rotate and vibrate, and the blood can be fully mixed.

The invention relates to a medical data analysis method and device based on artificial intelligence, equipment and a medium. The method comprises the following steps: acquiring medical data of a user; the medical data comprises blood detection data, medical image index data and basic data, and the medical data is provided with a sampling time label; extracting a change trend of the medical data to obtain a comprehensive feature vector; the comprehensive feature vector at least comprises a blood detection change vector and a medical image index change vector; calculating weighted weights of the blood detection change vector and the medical image index change vector in the comprehensive feature vector, and adjusting the comprehensive feature vector based on the weighted weights to obtain a fused feature vector; and predicting a disease type and a disease risk probability of the user based on the fusion feature vector, and generating a medical report of the user based on the disease type and the risk probability. By adopting the method, the accuracy and timeliness of cardiovascular and cerebrovascular medical data analysis can be improved.

A point-of-care testing (POCT) system comprising an analyzer, a measurement cartridge, and a calibration cartridge for calibrating the measurement cartridge is described. The measurement cartridge comprises at least one electrochemical sensor for measuring the one or more properties of the blood sample, and the calibration cartridge comprises a similar at least one electrochemical sensor and at least one sealed blister containing calibration fluid for calibrating the measurement cartridge. Examples of properties of the blood sample may be pH, blood gases, electrolytes, and metabolites like glucose and creatinine. The measurement cartridge may also comprise an optical chamber for measuring for example, bilirubin and hemoglobin species, for which the analyzer comprises stored calibration algorithms. The optical chamber may be disposed in any location in the measurement cartridge, for receiving a portion of the blood sample.

A method of selecting a treatment for a subject having cancer is disclosed. The method comprises:(a) determining a level of catalytic activity of at least one DNA repair enzyme in a biological sample of the subject; and(b) selecting an immune checkpoint regulator as a treatment for a subject having a statistically significant different level of catalytic activity of the DNA repair enzyme as compared to the catalytic activity of the DNA repair enzyme in a biological sample of a healthy subject.

Eating only one meal a day can slow down the brain's awakening and onset of activity in the morning after sleep. [Solution] A transparent diet, in which the blood test data values ​​of the food consumed are known, is eaten in the morning or at noon, and a free meal is eaten in the evening. The contents of the free meal are then compared with the blood test data, and the diet is adjusted accordingly.

The present invention provides a computer-implemented method for creating an interpretable machine learning classification model, the method being implemented on one or more processors connected to a memory. According to an embodiment, the method includes the steps of defining the model by setting up a chained component classification (CBC) architecture (300) including several multiple chained component classification (CBC) blocks (310), training the model end-to-end with available input data (402) including forward propagating samples (401) of the input data (402) through the chained CBC architecture (300), and interpreting the output of each CBC block (310) of the chained CBC architecture (300) except for the last CBC block (310) as a likelihood vector of the concept detected in the respective CBC block (310). The present invention can be used for several anticipated medical / healthcare use cases, such as transparent disease classification by analyzing markers in blood tests and knowledge discovery for disease classification.

A tangent flow hemolysis blood testing assembly, device and method are described herein.

The present invention discloses an EBV-related gastric cancer diagnostic marker and its application, wherein the diagnostic marker is selected from at least one of LF2 protein and BFRF3 protein. The present invention is the first to screen and obtain two diagnostic markers for EBV-related gastric cancer (EBVaGC) based on proteome chips and phage display technology - LF2 protein and BFRF3 protein, which can efficiently and accurately diagnose EBVaGC. In particular, the AUC of the combined diagnosis of these two proteins can reach 0.911, which is significantly better than the AUC of the individual diagnoses. And when diagnosing EBVaGC based on these two proteins, no tissue sample is required, only a serum sample is required, and it can be detected during a routine blood test. Therefore, compared with existing diagnostic methods, the present invention has the characteristics of high accuracy, small limitations, and low cost, reduces the cost of medical treatment for patients, is conducive to the realization of universal screening of the population, simplifies the diagnosis process of EBVaGC, and significantly improves the treatment efficiency.

The blood test tube support convenient to place comprises a support body, the support body is fixedly connected with a base, a lifting block is arranged on the outer wall of the support body, a position adjusting mechanism is arranged between the lifting block and the support body, and lifting handles are rotationally connected to the outer walls of the two ends of the top of the support body. A plurality of protection pipes are arranged on the outer wall of the top of the lifting block, the inner walls of the protection pipes are hollow, movable plates are arranged on the inner walls of the protection pipes, and clamping limiting mechanisms are arranged between the movable plates and the protection pipes. According to the device, the test tubes can be sealed and stored through the multiple protection tubes arranged on the outer wall of the lifting block, the test tubes can enter the protection tubes through the clamping limiting mechanisms arranged in the protection tubes, limiting protection is conducted on the test tubes, and the purposes of sealing and position limiting protection are achieved; by arranging the position adjusting mechanism between the lifting block and the bracket, the test tube can be conveniently inserted into the inner wall of the protection tube, and the placement convenience is improved.

An exemplary embodiment includes obtaining, by a computing system, observed values of an individual's demographic values, an individual's vital sign values, and an individual's blood test values; applying, by the computing system, a machine learning model to the observed values; providing, by the computing system, a prediction as to whether the individual exhibits undiagnosed albuminuria or proteinuria based on the observed values; and the machine learning model is trained by a training dataset. The training dataset includes corresponding demographic values, vital sign values, blood test values, and observed values of either a urine albumin-to-creatinine ratio (UACR) value or a urine protein-to-creatinine ratio (UPR) value for a plurality of individuals. The machine learning model is configured to provide a prediction as to whether further observed values indicate undiagnosed albuminuria or proteinuria.

The present invention relates to a blood test method based on electrochemical impedance spectroscopy that can calculate clinical indicators in real time without separate clinical test equipment for calculating clinical indicators by changing the initial values ​​of blood parameters to fit the actual impedance and virtual impedance of the blood, and calculating clinical indicators using the blood parameters with changed initial values.

According to the technical scheme, the multi-tube blood test specimen mixer comprises a main body and a touch control box, a movable ball is installed at the bottom in the main body, an overturning base is installed at the top of the movable ball through a connecting rod, a supporting base is installed at the position, close to the outer surface, of the top of the overturning base, and a rotating disc is installed at the top of the supporting base through a steel ball A; rotating shafts are installed at the four corners in the rotating disc, a uniform mixing seat is installed at the tops of the rotating shafts, a supporting frame is installed in the middle of the top in the main body, and a high-speed camera is installed on the outer surface of the supporting frame. The multi-tube blood test sample mixer solves the problems that after an existing blood gas analysis sample is uniformly mixed, a corresponding blood gas sample needs to be manually searched in multiple tubes through naked eyes and taken out, the operation is tedious, and the use convenience is not high, the blood gas sample taking-out efficiency is improved, and the working efficiency is improved. Meanwhile, the detection efficiency of the blood-gas mixer is improved.

The embodiment of the invention relates to the technical field of artificial intelligence, and particularly discloses a pneumonia risk prompting method and system based on artificial intelligence. According to the embodiment of the invention, a pneumonia risk model is constructed; receiving a lung examination image uploaded by the target patient, performing image denoising processing, and receiving a blood examination report text uploaded by the target patient; performing dual-channel feature extraction to obtain dual-channel feature data; carrying out weight fusion on the dual-channel feature data; and importing the fusion feature data into a pneumonia risk model, outputting a pneumonia infection level, and carrying out environment monitoring and specific prompting. The method can construct a pneumonia risk model, perform image denoising processing on a received lung examination image, perform dual-channel feature extraction and weight fusion, import fusion feature data into the pneumonia risk model, output a pneumonia infection level, and perform specific prompt, so that artificial analysis and judgment by experienced medical personnel are not needed, and the accuracy of the pneumonia risk model is improved. And automatic judgment and risk prompt are directly carried out through artificial intelligence.

The utility model discloses a blood transfusion cross-matching inspection test tube rack, which particularly relates to the technical field of medical equipment and comprises a bottom plate, a fixing frame is fixedly arranged at the top of the bottom plate, a limiting groove is formed in the surface of the bottom plate, a limiting block is clamped in the limiting groove, and a movable frame is fixedly arranged at the top of the limiting block. Two shells are arranged between the fixed frame and the movable frame, clamping mechanisms are fixedly arranged in the two shells, each clamping mechanism comprises a sponge layer fixedly arranged in the corresponding shell, a plurality of placement grooves with different hole diameters are formed in the surface of each sponge layer, a plurality of test tube holes with different hole diameters are formed in the surface of each shell, and the test tube holes are communicated with the placement grooves. The test tube holes correspond to the placement grooves in position, and a partition plate is fixedly arranged at the top of the sponge layer. According to the test tube rack, test tubes with different sizes can be conveniently fixed, the test tubes can be conveniently taken and used, meanwhile, the heights and angles of the test tubes can be conveniently adjusted, and the reaction of solvents in the test tubes can be better observed.