47 results about "Reference range" patented technology

The invention discloses an action state evaluation method and system based on a time-varying muscle synergistic effect. According to the method, a muscle synergistic effect matrix of standard walking actions, a standard reference range of a scaling coefficient and a time delay parameter and a classifier for action state recognition are constructed, then real-time surface electromyogram signals of a target individual are collected in a real-time stage, and the muscle synergistic effect matrix is extracted; calculating a second similarity index with a muscle synergistic effect matrix of a standard walking action; and inputting the second similarity index into the classifier, if the second similarity index is identified as a'moving 'state, performing an action state evaluation process, otherwise, re-collecting the real-time surface electromyogram signal of the next window. According to the method, the time-varying muscle synergistic effect model is adopted, and the time dimension is introduced, so that the dynamic change in the whole muscle activation process can be more accurately captured; meanwhile, the muscle activation process is modeled from the source, whether the action is completed or not is reflected, and more attention is paid to physiological rationality and control strategies.

The invention relates to the technical field of industrial internet-of-things monitoring, and discloses an internet-of-things-based remote monitoring method and system for asphalt mixture stirring equipment. The method comprises the following steps: acquiring key component operation parameters and external environment variables, and performing time domain statistical filtering to obtain an initial operation sequence; performing adaptive window length smoothing and frequency domain noise suppression to obtain a clean operation sequence; performing environment equivalent correction on the clean operation sequence by using the external environment variable to obtain a calibration feature vector; performing multi-dimensional feature correlation analysis according to the calibration feature vector, and determining a working condition switching label; determining a dynamic reference range according to the working condition switching label; calculating a preliminary abnormal probability according to the calibration feature vector and the dynamic reference range; and performing historical trend weighting and abnormal integration to obtain a final health assessment result. According to the method, through environment correction and dynamic reference following, environment interference and working condition misjudgment are eliminated, and accurate evaluation of the equipment health state is achieved.

The invention provides a medical index standardization matching method and device, and the method specifically comprises the steps: obtaining medical text data, carrying out the preprocessing of the medical text data, and forming the preprocessed medical text data; constructing a medical synonym dictionary, and dynamically expanding the medical synonym dictionary to form a dynamically expanded medical synonym dictionary; matching the preprocessed medical text data through three matching strategies to form three matching results; fusing the first matching result, the second matching result and the third matching result to form a fused matching result; performing consistency check on the fused matching result, extracting numerical values and unit information by using a regular expression, and detecting unit conflicts and reference range deviations to form unit and range verification results; and according to the synonym dictionary, the fused matching result and the unit and range verification result, a standardized index matching result is formed, and the user experience is improved.

The invention discloses a highly anatomical real multi-organ ultrasonic CT (Computed Tomography) image data set construction method. According to an original image of an organ, an artificial intelligence segmentation model is used for segmenting the organ into multiple types of tissues, proper medium parameter values are allocated, and a small-scale and anatomically real ultrasonic CT phantom data set is generated; performing fine adjustment on the basic generative artificial intelligence model by adopting an ultrasonic CT phantom data set to generate large-scale new data, filtering out unreasonable image results, and re-adjusting medium parameter values exceeding a reference range, so as to generate a large amount of diversified and physically real phantom data; simulating to obtain an output scattered wave field after the interaction of the sound wave and the phantom, completing the construction of a large-scale medium parameter-wave field data pair, and obtaining a multi-organ ultrasonic CT image data set; the ultrasonic CT data set constructed by the method has the characteristics of large scale, diversification and high anatomy authenticity, and is used for realizing a high-resolution ultrasonic CT image reconstruction task.

The invention provides a fault diagnosis method and device for a turbine generator and a readable storage medium. The electromechanical operation parameters of the turbine generator are collected in real time, comprehensive and multi-dimensional perception of the operation state of the turbine generator is achieved by fusing multi-dimensional electrical and mechanical parameters, and a data foundation is laid for fusion diagnosis. And dynamically determining an expected reference range of the to-be-diagnosed parameter corresponding to the current working condition based on the current value of the working condition definition parameter, comparing the actual measurement value of the to-be-diagnosed parameter with the expected reference range, and generating one or more abnormal indication signals based on the comparison result, therefore, the diagnosis process can adapt to the real-time operation condition of the equipment, and the problem of poor adaptability of a fixed threshold value in a variable working condition environment is solved. Afterwards, the fault diagnosis result of the turbine generator is comprehensively output through fusion and correlation analysis of multi-source information, and compared with a traditional single parameter analysis method, the fault recognition precision is remarkably improved.

The invention discloses a child overweight and obesity detection method and system based on multi-index cooperative determination, and the method comprises the steps: firstly deploying and initializing a special multi-mode detection tool, and inputting the basic information of a child; and then guiding the integrated device and the portable module for children to acquire physique indexes according to prompts, calling intelligent wearing behavior data, verifying the intelligent wearing behavior data, and storing the intelligent wearing behavior data into a local database of the terminal. Extracting multi-modal data, importing the multi-modal data into a built-in model, matching a WHO standard and a metabolic reference range according to age and gender, assigning differential weights according to growth stages, and correcting and outputting an obesity trend probability basic value in combination with a growth rate. The behavior data is quantified, a risk matrix is established, a cause is positioned, then a report result containing obesity probability, influence factors and early warning levels is generated through integration, and suggestions are given to abnormal children on site. And effective intervention of overweight and obesity of children is facilitated.

The present application relates to the technical field of industrial internet of things monitoring, and discloses a remote monitoring method and system for asphalt mixture mixing equipment based on the internet of things.The method comprises the following steps: collecting key component operating parameters and external environmental variables, performing time domain statistical filtering to obtain an initial operating sequence; performing adaptive window length smoothing and frequency domain noise suppression to obtain a clean operating sequence; using the external environmental variables to perform environmental equivalent correction on the clean operating sequence to obtain a calibration characteristic vector; performing multi-dimensional feature correlation analysis according to the calibration characteristic vector to determine a working condition switching label; determining a dynamic reference range according to the working condition switching label; calculating a preliminary abnormality probability according to the calibration characteristic vector and the dynamic reference range; performing historical trend weighting and abnormality integration to obtain a final health assessment result.This method eliminates environmental interference and working condition misjudgment through environmental correction and dynamic reference following, and realizes accurate assessment of the health state of the equipment.

The application discloses a kind of medical inspection report multi-stage cascade processing method and system, wherein the method comprises: obtaining inspection report, and the original table data in the inspection report is cascade pretreated, and standardization table data is generated;Based on the standardization table data, structured index extraction is carried out, and structured index data is obtained, and the result value in the structured index data and reference range determine index state information;Based on the structured index data, generate basic information data and health advice text, wherein the health advice text is generated based on the index state information.The application effectively solves the problem that the expression of inspection report of different hospitals / equipment is quite different and cannot be aligned stably.

The invention provides a wrist closed-loop peripheral nerve electrical stimulation method and system, and relates to the technical field of nerve regulation and wearable medical instruments.The method comprises the steps that physiological signals and wearing state information of the radial styloid process, the ulna styloid process and the wrist transverse grain midpoint of the wrist are obtained, and the reference range and the dynamic calibration boundary of stimulation parameters are obtained; based on the reference range and the dynamic calibration boundary, determining a structural relationship according to the position data of the radial styloid process, the ulna styloid process and the wrist cross grain midpoint of the wrist, and performing regional characteristic analysis on the structural relationship to obtain an analysis result; and calculating geometric characteristics in the regional characteristic analysis result to obtain a geometric moment quantification result of the region. According to the invention, an individual parameter setting, closed-loop online updating and long-term maintainable engineering system is realized.

A measurement device is disclosed, which may include or wirelessly connected to sensors or sensing devices for sensing an electrical property. The measurement device can receive user input, e.g., from physical UI components, to set a reference range of values and measures the electrical property of a device under test. Under a limit gauge operation mode, if the measured value is outside the reference range, the measurement device can produce an alert to notify its users.

A method (10) for determining the scalp (21) type of a user (20), the method (10) comprising: obtaining a value of a humidity level (111) indicating a region of the scalp (21) of the user (20) and a value of a sebum level (112) indicating the region of the scalp (21) of the user (20); comparing a group including the two values ​​with a reference range of scalp humidity level (111) and sebum level (112), the reference range forming at least five scalp groups (131-135), each scalp group (131-135) being associated with a range of humidity level (111) and a range of sebum level (112), and also associated with a skin and / or hair care composition and / or skin and / or hair care treatment compatible with the same range of humidity level (111) and sebum level (112) of the corresponding category; identifying the scalp (21) type of the user (20) based on the comparison; and outputting the identified scalp (21) type.

In at least one embodiment, a hemoglobin measuring device may include a plurality of sensors, a display configured to present information, and a computing device in communication with the sensors and display and having a processor and a memory storing instructions executable by the processor. The instructions may include instructions to receive, from the sensors, measurements of one or more forms of glycated hemoglobin in a blood samples, determine a total fetal hemoglobin value in the blood sample by performing a peak area summation of all forms of fetal hemoglobin, subtract the total fetal hemoglobin value from 100 to derive a total adult hemoglobin value, determine a glycated fetal hemoglobin value, compare the glycated fetal hemoglobin value to a reference range to obtain a comparison, determine a baseline glucose control value based on the comparison, and output the baseline glucose control value and the comparison to a display for medical evaluation.

The invention relates to the technical field of medical treatment, in particular to a medical record extraction method based on a large language model. The method comprises the following steps: performing fine-grained classification and context verification on candidate terms through a BERT-Md model, and outputting a fact support; guiding the first call of the large language model through the first composite prompt, and synthesizing a context example specific to a case; and guiding the second calling of the large language model through the second composite prompt to generate a target clinical abstract. The invention provides a large language model-based medical record extraction method, which comprises the following steps of: extracting and classifying key clinical elements from an original medical record through a BERT-Md model, and inputting the extracted key words into a large language model to generate a context example conforming to clinical logic; and ensuring that the generated abstract contains eight necessary modules through a constraint decoding technology, automatically marking an abnormal test value reference range, and outputting a clinical abstract with a standard format and standard information density.

This application relates to a method and system for generating AMH test reports using multi-dimensional data fusion. The method includes extracting AMH samples from women of a specific age group and establishing a regression standard curve between age and the mean AMH value based on statistical distribution. The theoretical AMH value is obtained from the standard curve based on the patient's age, and combined with the actual test value to calculate the AMH standard offset reflecting the degree of deviation. Based on the statistical distribution of the sample set, a preset interval threshold reference range for the offset is set and simultaneously presented in the report as an evaluation benchmark. When the offset exceeds a preset risk threshold, multi-dimensional clinical data from the patient's historical diagnosis, hormone levels, and ultrasound are automatically collected and entered into the analysis process. The offset index, reference range, and multi-dimensional data mining results are fused to obtain structured and personalized report suggestions to assist in precise clinical decision-making.

The invention discloses a heart rate variability evaluation method based on temperature change, and relates to the technical field of physiological signal processing and health monitoring. The method comprises the following steps: firstly, synchronously acquiring electrocardiosignals and environment temperature data of a measured object under different temperature conditions; then processing the electrocardiosignal to extract an RR interval sequence, and calculating a group of heart rate variability characteristic indexes; secondly, performing function fitting by taking the environment temperature as an independent variable and the heart rate variability characteristic index as a dependent variable, and constructing a personalized response model reflecting the change of the individual HRV along with the temperature; and finally, based on the model, determining an HRV theoretical reference value at a standard temperature or extracting a temperature sensitivity quantitative characteristic, and comparing the HRV theoretical reference value with a healthy population reference range, thereby realizing accurate evaluation of the autonomic nerve function state or the temperature adaptability. According to the method, by quantifying the influence of the temperature on the heart rate variability, the defect that in the prior art, evaluation is inaccurate in a variable-temperature environment is effectively overcome, and the reliability and applicability of an evaluation result are remarkably improved.

Described herein are various embodiments of techniques for determining reference values / ranges for diagnostic markers for patients during treatment and recovery during and / or after illness or injury. Some methods may include obtaining a patient's medical information (including any diagnosed medical conditions) and calculating, based on the medical condition and an elapsed time since onset or start of treatment, expected reference ranges for one or more diagnostic markers. These methods may also include outputting an indication of whether the measurements for the diagnostic marker or markers fall outside the reference range(s). In some embodiments, the reference values can be adjusted depending on additional pathologies indicated in the patient's medical information. Some such patient- and / or pathology-specific reference values / ranges can also be displayed to medical professionals to aid in patient care and / or leveraged in automated patient monitoring systems to alert doctors that a patient is not recovering according to the expected trajectory.

This invention discloses a method, system, medium, and equipment for diagnosing the causes of lightning damage and optimizing lightning protection measures. The method includes: determining multiple parameters affecting the lightning trip rate and defining reference ranges for each parameter; normalizing each parameter based on its reference range; calculating the gradient value of each parameter based on the normalized parameters, wherein a larger gradient value indicates that the corresponding parameter is diagnosed as a major factor in the cause of lightning damage; taking corresponding counter-attack measures or bypass measures for each parameter according to its gradient value, and calculating the lightning trip rate after taking optimized measures; determining whether the lightning trip rate after taking optimized measures reaches a preset standard, and if it reaches the preset standard, determining the optimized measures taken for each parameter as the optimal comprehensive measures. This invention can efficiently and accurately diagnose the causes of lightning damage and efficiently and accurately propose optimal lightning protection measures.

This invention relates to a method of identifying a Blood Brain Barrier peptide shuttle (BBBpS) comprising determining a set of physicochemical properties of a test peptide. The set of physicochemical properties may comprise Molecular weight, Extinction coefficient, Hydrophobic nature, Isoelectric point, Net charge at pH 7, Charge, Average hydrophobicity, Hydrophobicity at pH 7, and Hydrophilic residues ratio. If each of these physicochemical properties falls within a reference range then the test peptide is identified as a BBB peptide shuttle. Methods of identifying producing and using BBB peptide shuttles are provided.

The invention discloses a variance verification-based station monitoring index fluctuation detection method and terminal, and the method comprises the steps: obtaining a historical monitoring index data sequence of a station, and dividing the historical monitoring index data sequence into a plurality of index data subsequences according to a time sequence; calculating an average value of trend values, a variance of residual values and a variance acceleration of the residual values of each index data sub-sequence, and further determining a trend value average value reference range, a residual value variance reference range and a residual value variance acceleration reference range; and acquiring the latest monitoring index data sequence of the station, and determining whether the latest monitoring index data sequence fluctuates or not by judging whether the average value of the trend values of the latest monitoring index data sequence, the variance of the residual values or the variance acceleration of the residual values exceed the corresponding reference range or not. According to the invention, whether the monitoring index data of the station fluctuates or not can be accurately judged from multiple angles, so that operation and maintenance personnel can carry out early warning processing in time, and reliable protection is provided for the safety of the station.

According to the liquid level measurement system of the low-temperature container and the liquid level measurement calibration method adopting the liquid level measurement system, strain gauges are arranged on a plurality of hangers between an inner container and an outer container of the low-temperature container respectively, and a plurality of liquid level values of low-temperature liquid in the inner container are obtained through strain data of the strain gauges; meanwhile, the position range of a gas phase and liquid phase interface is obtained through a plurality of temperature sensors which are evenly arranged in the inner container in the vertical direction, so that the reference range of liquid level values is obtained, and the multiple liquid level values, obtained through strain data of the multiple strain gauges, of the low-temperature liquid are screened one by one through the reference range; the liquid level values outside the reference range are removed, the remaining liquid level values are averaged, and finally the accurate liquid level value is obtained. Therefore, on the premise that the liquid level of the low-temperature liquid in the low-temperature container is accurately measured, extra heat leakage is not increased, and the storage safety of the low-temperature container is improved.

The invention discloses a three-dimensional ankle data processing system and method, and relates to the technical field of computer software, in the system, a data calculation and analysis module comprises an index numerical value module, an index big data reference range module and an index personal development follow-up visit module, the index big data reference range module is used for calculating data of length, width, height, angle, area, volume and cross section girth of the three-dimensional foot model and outputting basic indexes and characteristic indexes, and the index big data reference range module is used for statistically analyzing a percentile reference range of each index according to age and gender based on the three-dimensional foot model data and is used for objective comparison and evaluation of individual detection results. The index personal development follow-up visit module generates a follow-up visit curve of each index changing along with time based on the unique identity identification code of the user, long-term dynamic monitoring and intervention effect evaluation are achieved, and the problem that individual evaluation lacks objective quantitative standards is solved.

The embodiment of the invention provides a blood leukocyte precise separation method combining immune density and a centrifugation technology. The blood leukocyte precise separation method comprises the following steps: performing multicolor immunofluorescence labeling on leukocyte subgroups in a blood sample; performing flow cytometry analysis on the marked sample, and establishing an initial multicolor fluorescence compensation matrix for the current sample individual; dynamically adjusting and generating a corrected compensation matrix of the individual specificity based on the deviation degree of the initial compensation matrix in a sample group reference range; carrying out association mapping on a specific physical sorting interval which is determined after the signal recalculation and the enclosure and is rich in the target leukocyte subgroup and a density gradient centrifugal separation condition; and directly carrying out density gradient centrifugation operation on the blood sample subjected to immunolabeling by utilizing the association mapping. According to the scheme of the embodiment of the invention, the high-purity specific leukocyte subgroup can be efficiently separated from a complex blood sample on the premise of keeping high cell activity and flux.

The invention is suitable for the field of medical information processing, and provides a diagnosis result checking method and system based on an aggregate database, and the method comprises the following steps: constructing the aggregate database through collecting the physiological data of a long-term healthy individual, and training and generating an individualized health reference model based on the database; receiving all-item physiological index detection data of a target individual, and synchronously starting a first checking process and a second checking process; obtaining a dominant abnormal index set under the general standard through a first checking process, and obtaining deviation indexes of all physiological indexes relative to the individualized health standard through a second checking process; and synthesizing the dominant abnormal index set and the deviation index to generate a diagnosis check report. According to the method, the problem of misjudgment caused by neglect of individual differences due to dependence on a population statistics reference range in the prior art is effectively solved, and false positive abnormal items caused by normal variation of individuals can be accurately identified.

The present application provides a patient diagnosis and treatment information system and an information processing method. The patient diagnosis and treatment information system comprises a processor, a communication module, and a display screen. The communication module is configured to obtain monitoring values of a plurality of monitoring parameters of a patient collected or generated by a plurality of medical devices, and transmit the obtained monitoring values to the processor. The processor is configured to: determine monitoring baseline data respectively corresponding to the plurality of monitoring parameters of the patient, the monitoring baseline data being used for defining reference ranges for the monitoring parameters corresponding to the monitoring baseline data; control the display screen to simultaneously display, on a display interface of the display screen, diagnosis and treatment task information, monitoring values of at least one monitoring parameter at a plurality of time points, and the monitoring baseline data corresponding to the at least one monitoring parameter, wherein the diagnosis and treatment task information is used for prompting medical staff to carry out a corresponding diagnosis and treatment task; and for the at least one monitoring parameter, perform statistical analysis on the monitoring values of the at least one monitoring parameter obtained within a preset time period, and control the display screen to output a statistical analysis result on the display interface of the display screen.

The application discloses a kind of highly anatomically real multi-organ ultrasound CT image dataset construction methods.The present application is according to the original image of organ, using artificial intelligence segmentation model to divide organ into multiple class tissues, and divide appropriate medium parameter value, produce a small scale but anatomically real ultrasound CT phantom dataset;Using ultrasound CT phantom dataset to fine-tune the basic generative artificial intelligence model, generate large-scale new data, filter out unreasonable image results and adjust the medium parameter value beyond the reference range again, to generate a large number of diversified and physically real phantom;Simulated to obtain the output scattered wave field after the interaction of sound wave and phantom, complete large-scale medium parameter-wave field data pair construction, obtain multi-organ ultrasound CT image dataset;The ultrasound CT dataset constructed by the present application has the characteristics of large scale, diversification and high anatomical reality, for realizing high-resolution ultrasound CT image reconstruction task.

The invention provides a medication recommendation method and device, electronic equipment, a storage medium and a program product, and relates to the technical field of computers. According to the method, the diagnosis information of the patient is acquired from the hospital information system, the corresponding medical insurance disease group can be accurately matched, the medical insurance payment standard can be determined, close combination of a medication decision and a medical insurance policy is ensured, and medical insurance payment deviation caused by information asymmetry is avoided. Secondly, the cost interval is determined based on the medical insurance payment standard, the medicine cost of the patient and the preset medicine proportion upper limit, a clear cost reference range is provided for a doctor, the medical cost can be reasonably controlled, and unnecessary medical resource waste is reduced. Moreover, the target drug combination is determined by combining the diagnosis information, the cost interval and the hospital medication scheme database, the normalization and effectiveness of medication are considered, the rationality of the cost is also considered, and the optimal drug combination can be recommended for the patient. And finally, the target drug combination is pushed to a doctor end, so that intelligent decision support is provided for doctors, the standardization and consistency of doctor advices are improved, drug use deviation and medical dispute risks caused by manual selection are reduced, and the overall quality and efficiency of medical services are improved.

The invention provides a distance measurement method and device, and the method comprises the steps: transmitting first distance measurement information which comprises a reference distance measurement value; and receiving second distance measurement information, the second distance measurement information being used for indicating whether a first distance measurement value is reliable, the first distance measurement value being obtained by distance measurement of the first device, and the second distance measurement information being obtained by the first device based on the reference distance measurement value and the first distance measurement value. The reliability of distance measurement can be improved under the condition that the data processing complexity of the server is reduced.

The present invention provides methods for detecting multiple biomarkers indicative for lysosomal storage diseases from a dried blood spot. In particular, the present invention provides a method that is suited for detecting multiple biomarkers, each indicative for the presence of a distinct lysosomal storage disease in a subject, based on a single sample preparation procedure. In particular, the method allows simultaneous extraction of different biomarkers such as Lyso-Gb1 (GlcSph). Lyso-Gb3, and others from a dried blood spot sample. The invention further provides a kit of parts comprising means for conducting the methods subject of the invention. Finally, the invention provides a set of reference ranges for Lyso-Gb1 (GlcSph) and Lyso-Gb3 in healthy subjects starting from dried blot spot samples.

The application discloses a blood loss risk assessment method and system based on image data analysis, and relates to the technical field of image processing, which comprises the following steps: identifying and positioning the pixel coordinates and corresponding world coordinates of all the inside corner points of the checkerboard in the calibration plate image, solving a homography matrix, defining a color correction function, and constituting a reference range interval of healthy skin; judging the scalar field of each pixel position in the image based on the healthy skin reference range, generating an initial wound area binary mask, and calculating a normalized chroma state field; and performing risk assessment on the bleeding state of a patient. Through the combination of homography matrix correction and color correction function, the application effectively solves the problems of image geometric distortion and color error, improves the accuracy of wound image analysis, and enhances the accuracy and stability of the evaluation results through the combination of local entropy production rate and diffusion flux vector field.