29 results about "Blood parameters" patented technology

The method is mainly applied to the technical field of deep learning. The invention discloses an intelligent diagnosis method, device and equipment for snake venom poisoning and a medium, and the method comprises the steps: obtaining multi-modal data which comprises a wound image, a symptom text and a blood parameter; performing feature extraction processing on the wound image, the symptom text and the blood parameters to obtain image features corresponding to the wound image, semantic features corresponding to the symptom text and high-dimensional features corresponding to the blood parameters; performing alignment and fusion processing on the image features, the semantic features and the high-dimensional features through a cross-modal attention mechanism to generate fusion features; after the fusion features are input into a preset multi-task classification model, classification is carried out in a snake species label space and a toxicity category space according to the fusion features, a poisoning grade score is determined, and a diagnosis report is generated based on the poisoning grade score. According to the invention, high-precision, rapid and intelligent diagnosis of snake venom poisoning can be realized.

The invention discloses an intelligent disturbance and analysis method and system for hemodialysis data, and relates to the field of hemodialysis data analys.The intelligent disturbance and analysis method comprises the steps that in the hemodialysis process, disturbance signals are superposed through a blood input pump, so that blood parameters input into a dialyzer generate preset configuration changes, and therefore input disturbance signals are formed; in the disturbance applying period, blood parameters of the blood output end of the dialyzer are collected in real time, and corresponding output response signals are formed; performing cross-correlation analysis on the input disturbance signal and the output response signal, and calculating a time delay parameter between the input disturbance signal and the output response signal; periodically and repeatedly detecting, carrying out regression analysis on the time delay parameter, and when the time delay parameter is continuously increased along with time, judging that the dialyzer has a blockage trend and outputting early warning information. According to the method, early detection on the dialyzer blockage is realized through the dynamic time-lag characteristics under the condition of not increasing a sensor, and the safety of a hemodialysis system is improved.

Embodiments pertain to a method of assessing the cardiometabolic health of a subject by (1) receiving a plurality of parameters of the subject, where the plurality of parameters includes a T2 relaxation time constant of a subject's blood (T2 value) and one or more additional parameters; and (2) feeding the plurality of parameters into an algorithm, where the algorithm correlates the plurality of parameters to the subject's cardiometabolic health. The methods may also include a step of communicating cardiometabolic health risk. The methods may also include a step of implementing a treatment decision. Further embodiments pertain to system for assessing the cardiometabolic health of a subject in accordance with such methods.

State of art techniques for measurement of blood viscosity, RBC concentration and the like are in vitro methods. Embodiments of the present disclosure provide a method and system for in vivo non-invasive measurement of blood parameters using Laser Enabled Swept Frequency Acoustic Interferometry (LE-SFAI) principle. A Continuous Wave Laser diode based Photo Acoustic (CWPA) signal in frequency domain generated from laser excitation incident on a biological tissue of a subject carrying blood vessel is acquired by the ultrasound sensor and converted to a windowed time domain CWPA signal limited to two peaks. The signal characteristics such as risetime, amplitude, and time difference between first peak and the second peak are obtained to derive blood viscosity, Red Blood Corpuscles (RBC) concentration, and blood vessel diameter.

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.

The invention relates to the technical field of poultry health assessment, in particular to a method for predicting and identifying the high fat deposition risk of the liver of a laying hen based on blood amino acid parameters. The method comprises the following steps: collecting a blood sample when the laying hen is in a metabolic state after absorption, detecting the total amino acid content and the alanine content in blood, and substituting blood parameters into a pre-established liver triglyceride prediction model to obtain the predicted liver triglyceride content, and comparing the prediction results to judge the high fat deposition risk of the liver of the laying hen. According to the method, the laying hens do not need to be slaughtered and sampled, the fat deposition state of the livers of the living laying hens can be rapidly evaluated, and the method is suitable for early screening and risk early warning of high fat deposition of the livers of the laying hens under the large-scale breeding condition.

The invention discloses an image processing method and device for judging suspension red blood cell hemolysis. The method comprises the following steps: acquiring a blood image set; the blood image set comprises a plurality of blood images and corresponding label information; acquiring a blood parameter information set; the blood parameter information set comprises a plurality of blood parameters and corresponding label information; the blood parameters comprise hemoglobin concentration, reticulocyte concentration, indirect bilirubin concentration, lactic dehydrogenase concentration and globin concentration; utilizing the blood image set and the blood parameter information set to construct a blood hemolysis composite detection model; based on the blood hemolysis composite detection model, processing the collected blood image and blood parameters to obtain hemolysis detection result information; the hemolysis detection result information is used for representing erythrocyte hemolysis information of the blood corresponding to the collected blood image and blood parameters.

The invention relates to a computer system (1) for assisting a user in preparing or performing a blood treatment procedure for a patient by means of a blood treatment device (100). The computer system (1) comprises a computing device (5), an input interface (501) and an output interface (503); wherein the input interface (501) is configured for inputting input values entered by a user, the input values comprising values proposed or set by the user for setting device parameters on the blood treatment device (100) for extracorporeal blood treatment of a patient; furthermore, the computing device (5) is programmed to predict a result value of at least one blood parameter or at least one test parameter of the patient at a point in time during the treatment, or a profile of the patient over a period of time during the treatment, based on the input value of the input; the calculation device (5) can transmit the predicted value or the change curve to an output interface (503) in a signal transmission mode, and the predicted value or the change curve is transmitted from the interface to an output device (505) and other devices for user confirmation.

The present disclosure relates to a control device or closed-loop control device programmed to control or regulate a blood treatment apparatus during an administered treatment of a patient's blood using an extracorporeal blood tubing set and the blood treatment apparatus based on set adjustable values of treatment parameters set by using the blood treatment apparatus or using another device optionally connected to the extracorporeal blood tubing set, wherein the control device or closed-loop control device is further programmed, after reading, to compare at least one measurement value collected during the administered treatment, as the actual value of a blood parameter with a stored target value of the blood parameter. Based on this comparison and observation of a set adjustable value of one of the treatment parameters, either a correction value or correction factor to change the set adjustable value or a new adjustable value is determined in each case.

A medical device includes a holder that may be applied to the skin of a patient, a biofuel cell, a pump configured for supplying blood to the biofuel cell, a sensor configured to emit a signal representative of a blood parameter, a control unit connected to the pump and the sensor, and a rechargeable battery electrically connected to the biofuel cell. The control unit is configured to perform a recharging procedure including the following steps: processing the signal emitted by the sensor, estimating a value of the blood parameter of the patient, comparing said estimated value with a threshold value, and, based on the comparison, commanding the activation of the pump for delivering a predetermined amount of blood to the biofuel cell for generation electricity and recharging the battery.

Device for ventilation, comprising: a breathing gas source for providing breathing gas for the ventilation of a patient; at least one sensor connected to an interface (8) of the device, which can be positioned on the patient's skin and is designed to non-invasively measure at least one component of the patient's blood as at least one ventilator-dependent blood parameter; a control device designed to evaluate at least one blood parameter and autonomously change at least one operating parameter of the device depending on the at least one blood parameter, wherein maximum corridors are specified for the at least one operating parameter to prevent implausible automatic ventilation settings, and operator inputs are evaluated to take external control specifications into account; a device housing (1) with a control panel (2) and a display (3), wherein an oxygen supply valve is adaptable to the device in the area of ​​the device housing (1) and a respiratory gas pump is arranged in an interior of the device, wherein a humidifier is also adaptable to the device, wherein the display (3) is designed as a display so that a physician can select a disease pattern directly on the display; a modem or other interface for transmitting recorded data to the physician, as well as abnormalities, operating hours, or other data to a maintenance or customer service department to ensure proper functioning of the device; wherein the control device is designed to change the at least one operating parameter within a control loop, to which data of the at least one blood parameter are supplied as setpoint and actual values, and to assign strategies for carrying out the control to specific disease patterns, wherein each strategy includes a priority list of 1 to N different settings that are to be processed within the respective bandwidths when applying the strategy, wherein the strategies with their respective settings and bandwidths can be stored and made available as fixed predefined strategies for specific disease patterns; wherein the control device is further configured to take into account characteristic settings and their ranges for the disease pattern chosen by the physician and to apply the settings taken into account; wherein at least one blood parameter includes a carbon dioxide partial pressure and the control device is further designed to compare an actual value of the carbon dioxide partial pressure with a setpoint when performing the control and, if a current strategy has been fully executed and the setpoint has not been reached, to automatically apply a new strategy suitable for further improving the patient's condition.

The invention relates to a device and a method for measuring a plurality of blood parameters by artificial intelligence. The invention provides for: exciting blood with electromagnetic radiation of a plurality of determined wavelengths; receiving analog information about a plurality of electromagnetic and / or optical responses of the blood, the plurality of electromagnetic and / or optical responses comprising electromagnetic radiation backscattered or diffused by the blood; converting the analog electromagnetic and / or optical response information into digital electromagnetic and / or optical response data; processing the digital electromagnetic and / or optical response data and an actual temperature value of the blood by means of a neural network; determining a value of each parameter as a result of the processing; determining a plurality of ratios of optical counts; providing the plurality of ratios and the temperature value as input to the neural network; processing the plurality of ratios by the neural network taking into account a plurality of data in previous measurements of blood parameters made during a previous training; providing the value of each parameter as output of the neural network. The device can be coupled to a test tube or directly to a tube of an extracorporeal blood circuit.

An embodiment relates to a method for testing blood based on electrochemical impedance spectroscopy, the method being able to calculate clinical indicators in real time without separate clinical test equipment for calculating clinical indicators by changing initial values of blood parameters to fit an actual impedance and a virtual impedance of blood, and calculating clinical indicators using the blood parameters of which the initial values are changed.

A wearable non-invasive blood viscosity monitor and methods of using the same are described. The blood viscosity monitor includes first and second sensors configured to sense blood parameters non-invasively from a subject and a processor circuit configured to generate an indication of blood viscosity using the sensed blood parameters from at least one of the first and second sensors and to generate a medical diagnostic using the indication of blood viscosity. An output circuit presents the medical diagnostic to alert a clinician about an elevated viscosity. The first and second sensors may be on the same or different fixation devices and adapted to provide measurements that are mixed and matched by the processor circuit to provide validation of measurements, averaging of measurements, or to select the most reliable data for each modality and measurement context.

The application discloses a blood detector, which comprises a sampling and distributing device, a routine blood test device, a first specific protein test device, a second specific protein test device and a control device. The first specific protein test device comprises at least two first reaction test components, so that the blood detector can realize the detection of routine blood parameters, first specific protein parameters and second specific protein parameters by collecting less blood samples, thereby reducing the pain of patients and simplifying the detection process. The control device controls the sampling and distributing device to start collecting and distributing the next blood sample before the routine blood test device completes the detection of at least one routine blood parameter of the current blood sample, so that the two first reaction test components have time overlap in the detection process, the detection of multiple blood samples can be realized at the same time, and the efficiency of blood detection is improved.

A modular patient monitor provides a multipurpose, scalable solution for various patient monitoring applications. In an embodiment, a modular patient monitor utilizes multiple wavelength optical sensor and / or acoustic sensor technologies to provide blood constituent monitoring and acoustic respiration monitoring (ARM) at its core, including pulse oximetry parameters and additional blood parameter measurements such as carboxyhemoglobin (HbCO) and methemoglobin (HbMet). Expansion modules provide blood pressure BP, blood glucose, ECG, CO2, depth of sedation and cerebral oximetry to name a few.Aspects of the present disclosure also include a transport dock for providing enhanced portability and functionally to handheld monitors. In an embodiment, the transport dock provides one or more docking interfaces for placing monitoring components in communication with other monitoring components. In an embodiment, the transport dock attaches to the modular patient monitor.

The invention relates to a fatty liver risk prediction method and system based on multi-model integration and a storage medium, and belongs to the technical field of artificial intelligence and medical information. The method comprises the following steps: acquiring blood biochemical parameters of a target object, and performing feature selection on the blood biochemical parameters based on clinical priori knowledge to obtain a key parameter set; the key parameter set is arranged into a two-dimensional parameter matrix with glycosylated hemoglobin as the center, the two-dimensional parameter matrix is input into a pre-trained integrated prediction model, and the model comprises various heterogeneous sub-models such as a special convolutional neural network, an artificial neural network, a support vector machine, XGBoost and LightGBM; and finally determining the risk level of the target object suffering from the progressive non-alcoholic steatohepatitis through a hard voting integration strategy of a preset threshold value K based on the output of each sub-model. According to the method, high-precision risk prediction can be realized only by using conventional blood parameters, dependence on expensive or invasive examination is avoided, and the method has important application value in primary medical institutions.

The application discloses an image processing method and device for judging hemolysis of suspended red blood cells, and the method comprises the following steps: acquiring a blood image set; the blood image set comprises a plurality of blood images and corresponding label information; acquiring a blood parameter information set; the blood parameter information set comprises a plurality of blood parameters and corresponding label information; the blood parameters comprise hemoglobin concentration, reticulocyte concentration, indirect bilirubin concentration, lactate dehydrogenase concentration and globin concentration; a blood hemolysis composite detection model is constructed by using the blood image set and the blood parameter information set; the collected blood image and blood parameter are processed based on the blood hemolysis composite detection model, and hemolysis detection result information is obtained; the hemolysis detection result information is used for representing the red blood cell hemolysis information of the corresponding blood of the collected blood image and blood parameter.

The present invention relates to a method for determining distinguishing parameters of a neuro-inflammatory disease, said method comprising (a) obtaining parameters from a group of samples, wherein said group of samples comprises at least (i) a first subgroup of samples, and (ii) a second subgroup of samples, and (b) determining distinguishing parameters of the obtained parameters in step (a) at least between said first subgroup of samples and said second subgroup of samples by conducting analytical determination. Further, the present invention relates to a set of distinguishing parameters as well as distinct uses of such sets. Additionally, the present invention relates to a method for determining a subtype of a neuro-inflammatory autoimmune disease in a subject.

The invention provides a multi-pipe-diameter self-adaptive blood parameter continuous monitoring probe, a probe assembly and a monitoring system, and relates to the field of blood parameter monitoring equipment. The multi-pipe-diameter self-adaptive blood parameter continuous monitoring probe comprises an accommodating shell, a detection unit and a movable fastener, the containing shell comprises an upper cover and a lower cover which are detachably connected, and the upper cover and / or the lower cover are / is provided with a containing groove so that a containing channel used for allowing a pipeline to penetrate through can be formed between the upper cover and the lower cover. The detection unit comprises at least one probe group, the probe group comprises a light source and a light signal receiving probe, the light source and the light signal receiving probe are mounted in the lower cover, and the light signal receiving probe protrudes out of the inner wall of the accommodating channel; and the fastener is moved to drive the optical signal receiving probe to move towards the center of the accommodating channel. The multi-pipe-diameter self-adaptive blood parameter continuous monitoring probe provided by the invention solves the technical problems of high cost and inconvenience in use of blood parameter continuous monitoring equipment in the prior art.

An apparatus for extracorporeal treatment of blood (1) comprising a treatment unit (2), a blood withdrawal line (6), a blood return line (7), a preparation line (19) and a spent dialysate line (13); a non- invasive blood volume sensor (50) for determining an additional property of blood is active on a tube segment (61) of the blood withdrawal line or of the blood return line; the sensor includes one source (53) for directing a signal towards the blood, a plurality of detectors (57) for receiving the signal, and a controller (65) receiving the output signals from the detectors (57) and determining a blood volume variation and a value of sodium concentration in the blood (Napl) both based on the output signals. A process of determining at least one parameter and on property of blood circulating an extracorporeal blood circuit is also disclosed.

The invention relates to a measuring cuvette (100) for receiving a blood sample (105), comprising: - a sample holder (110) configured to receive the blood sample and to guide it by passive hydrodynamic forces to a plurality of measuring areas (122, 122') of the measuring cuvette; - a plurality of measuring channels (120, 120'), wherein each measuring channel comprises exactly one measuring area from the plurality of measuring areas; - an overflow reservoir (130) which is hydrodynamically connected to the plurality of measuring channels and configured to receive a portion of the blood sample that overflows via the measuring channels, wherein at least one measuring area from the plurality of measuring areas is configured to be optically transparent in an irradiation direction of the measuring cuvette, and wherein at least one measuring area from the plurality of measuring areas is not optically transparent.

The invention relates to a computer-implemented method for determining in vivo and in vitro states by analyzing blood parameters, said method comprising: a) acquiring blood parameters of a blood sample by means of a blood analyzer, said blood parameters comprising quantitative and qualitative measured variables, said measured variables comprising attributes of individual cells, and a step b) for determining the in vivo and in vitro states of the individual cells; the single cells comprise blood cells; b) creating at least one scattering pattern having at least two axes, wherein each axis of the scattering pattern comprises a different measurement variable; c) determining at least one in vivo and / or in vitro and / or post-death state by means of at least one deep learning model and / or at least one machine learning model, the input variables for the at least one deep learning model comprising at least one scattering map; wherein input variables for the at least one machine learning model comprise at least one one-dimensional vector, and creation of the one-dimensional vector is achieved through vectorization of the at least one scattering graph; and d) automatically generating a report comprising at least one result regarding the determination of the at least one state.

Embodiments pertain to a method of assessing the cardiometabolic health of a subject by (1) receiving a plurality of parameters of the subject, where the plurality of parameters includes a T2 relaxation time constant of a subject's blood (T2 value) and one or more additional parameters; and (2) feeding the plurality of parameters into an algorithm, where the algorithm correlates the plurality of parameters to the subject's cardiometabolic health. The methods may also include a step of communicating cardiometabolic health risk. The methods may also include a step of implementing a treatment decision. Further embodiments pertain to system for assessing the cardiometabolic health of a subject in accordance with such methods.

The invention discloses a blood parameter optical detection and calibration method based on RKHS-PLS, and belongs to the field of blood physiological parameter detection.The blood parameter optical detection and calibration method comprises the following steps that S1, incident light intensity and transmitted light intensity of each wavelength are recorded; s2, calculating preliminary predicted values of hematocrit and oxyhemoglobin saturation of each wavelength; s3, training a partial least square regression method calibration model; s4, evaluating the trained partial least square regression method calibration model; and S5, inputting the newly collected incident light intensity and transmission light intensity under each wavelength into the partial least square regression method calibration model output in the step S4, and generating final prediction values of hematocrit and oxyhemoglobin saturation. By adopting the blood parameter optical detection and calibration method based on RKHS-PLS, through integration of physical modeling and data analysis, the theoretical deviation of the traditional Lambert-Beer law is made up, the physical interpretability is reserved, the detection precision is remarkably improved, and the calibration frequency is greatly reduced.