37 results about "Pain level" patented technology

The invention provides a pain assessment system and method based on multi-modal physiological signals. The system comprises a multi-modal signal acquisition module, a signal preprocessing module, a multi-modal feature extraction module, a deep fusion analysis module, an individualized calibration module and a result output and early warning module. By synchronously collecting and analyzing multi-dimensional data such as facial expressions, sound features, physiological signs and behavior responses and combining deep learning and multi-modal information fusion technologies, objective quantitative evaluation and real-time monitoring of the pain degree are achieved, and accurate decision support is provided for clinical pain management.

The invention relates to the technical field of medical monitoring, and particularly discloses a pain degree assessment method and system based on multi-modal sensing and wearable equipment. The method comprises the following steps: acquiring physiological signals and limb movement data of a patient to form a multi-dimensional pain feature vector; a dynamic weight distribution algorithm is adopted, and physiological and limb action modal weight coefficients are adjusted in real time based on each modal data prediction confidence coefficient; a multi-modal classifier is utilized, features are fused through a cross-modal attention mechanism, and 0-10 levels of pain quantized values are output; and intelligent regulation and control of analgesia parameters are realized. The system comprises a multi-modal sensing module, a feature extraction module, a dynamic weight distribution module, a multi-modal classification module and an analgesia equipment control module. The wearable device integrates a sensor and a processing unit to realize data acquisition and analysis. According to the invention, the dynamic, precise and intelligent pain assessment is realized, the technical problems of strong subjectivity and poor real-time performance of the traditional assessment method are solved, and reliable technical support is provided for clinical analgesia management.

The invention relates to the field of medical auxiliary diagnosis, in particular to an intelligent child pain assessment system based on AI facial expression analysis, a facial detection module obtains a child facial image, and performs three-stage cascade detection by using a multi-task cascade convolutional neural network model to obtain facial key point pixel coordinate information; the key point positioning module carries out noise filtering processing on the coordinate information to obtain more accurate face key point coordinate information, the information is transmitted to the key point thermodynamic diagram representation module, and the key point thermodynamic diagram representation module generates a face key point thermodynamic diagram representing the degree of pains of children in combination with the face key point coordinate information and a thermodynamic diagram mechanism. The child pain intelligent evaluation module evaluates the degree of pain of the child based on the thermodynamic diagrams and obtains an evaluation result, and finally, the pain evaluation result visualization module visualizes the evaluation result, and the accuracy of pain characterization is improved through high-precision face detection and key point thermodynamic diagram technology, so that the accuracy of pain characterization is improved. And an effective method is provided for evaluating the pains of children.

The invention provides a pain discrimination method based on a time sequence and multiple modes. The pain discrimination method comprises the steps that conventional physiological indexes, behavior characteristic indexes and potential auxiliary indexes are collected; preprocessing the multi-modal data, including abnormal value processing, individual normalization and time alignment, and constructing a time sequence data block; establishing an individual baseline, dynamically calibrating a baseline threshold value every 7 days, and calibrating a blood glucose baseline once every 3 days for a diabetic patient; physiological features, behavior features and time sequence features of the time sequence data blocks are extracted through an AI model, multi-modal features are fused through an attention mechanism, and full-level pain is recognized through multi-modal index synchronous verification, multi-classification probability calculation and grading threshold judgment; and outputting a clinical intervention strategy corresponding to the pain level, and dynamically updating the model parameters and the baseline threshold based on clinical intervention feedback and new crowd data, so that various crowds can be covered, the hierarchical intervention strategy is output, the intervention delay is shortened, and the clinical practicability and accuracy of pain management are improved.

The invention relates to the technical field of medical informatics, in particular to a pain management-oriented physiological signal real-time monitoring and intervention system, which comprises a determination module for determining the abnormal tendency of a stimulation window updated in real time at each updating moment to obtain an abnormal tendency sequence; the determination module is also used for determining similar fluctuation segments in the abnormal tendency sequence; the determination module is also used for determining an abnormal process factor of the physiological sensing signal at the current moment based on the abnormal tendency difference value and the length of each similar fluctuation section; the determination module is also used for determining a trigger factor for evaluating the abnormal pain state at the current moment according to the abnormal process factors of each physiological sensing signal at the current moment and the previous moment, and performing normalization processing on the trigger factor to obtain a normalized trigger factor; and the intervention module is used for carrying out visualization and intervention on the pain degree of the target user based on the normalized trigger factor. According to the invention, the physiological signal abnormity identification accuracy and sensitivity are improved.

The application relates to a pain real-time discrimination and treatment effect evaluation system based on EEG microstate monitoring. The system comprises the following modules: a microstate extraction and analysis module which extracts GFP peak topography from EEG signal data, optimizes a template map, calculates the average duration of each microstate category and the like, and outputs a microstate feature parameter set; a pain real-time discrimination module which inputs the microstate feature parameter set into a deep learning model for detection to obtain a detection result containing a pain level; and a treatment effect evaluation module which obtains and compares the microstate feature parameter set before and after treatment, obtains a quantitative treatment effect index, and generates a report containing the index, analysis results and a microstate change trend chart. The system can monitor the pain state of a patient in real time through EEG signal microstate, and can provide objective evaluation indexes about the treatment effect for a clinician by quantifying the dynamic change of the EEG microstate of the patient before and after treatment, so that the scientificity and accuracy of treatment effect monitoring are improved.

A system and method for visualizing a position of a needle inside a patient's body for use in providing regional anesthesia and a system and method for providing electro anesthesia during surgery, post surgery and during rehabilitation. The method and system use EMG / AMG information regarding activity of a muscle associated with a target nerve to provide a visualization of a position of a needle or other device relative to the target nerve and to determine efficacy of the electro anesthesia. EMG / AMG information and feedback information such as EEG information may be used to provide automatic adjustment of a waveform provided for electro anesthesia to maintain a suitable pain level.

The application discloses a pain assessment model construction method and a non-contact continuous pain assessment method, and belongs to the field of image expression recognition. Through a non-contact mode, multi-modal time sequence data of a patient is collected, and after time-space synchronous processing to obtain a multi-modal frame package sequence, single-modal self-supervision pre-training is performed based on extracted single-modal time sequence data, and then a multi-modal projection layer is connected to obtain a front structure for cross-modal semantic alignment coding, so as to map output features of each mode to a large language model word vector dimension, and then a large language backbone model is connected to obtain an overall structure. The multi-modal time sequence data of the patient is input, fine-tuning training of the large language model is performed by indicating the overall structure to output a pain assessment result, a trained pain assessment model is obtained, and the trained pain assessment model is used for non-contact continuous pain assessment. The pain assessment result includes a pain level, a pain score, an interpretable heat map and the like. The application combines a large language model, so that the trained model can realize pain level division and interpretable continuous output.

This invention belongs to the field of rehabilitation training technology. It provides a method and system for analyzing upper limb rehabilitation training data, including the following steps: During the upper limb rehabilitation training process, static single-joint training parameter data and dynamic multi-joint collaborative training parameter data are collected in real time. The static single-joint training parameter data is then used to identify whether it meets the pain-free standard. This invention optimizes the problem of focusing only on single-joint data and ignoring multi-joint linkage and collaboration in upper limb rehabilitation training data analysis. It first identifies the static single-joint pain-free standard to eliminate basic interference, then filters and analyzes high-incidence combinations of multi-joint pain, and then reverse-engineers the final balance range where pain level meets the standard and range of motion is maximized, assessing the degree of achievement. Finally, it combines a safe expansion span to generate a stepped optimization range and predicts feasibility using a rehabilitation trend synergy index, achieving a shift from experience-driven to data-driven approaches.

The invention discloses a method for detecting the pain level in combination with neural activity and detection equipment, the detection equipment comprises a detection deck chair support, a buffer structure and a detection structure, the detection structure and the buffer structure are installed on the detection deck chair support, and the invention relates to the technical field of neuropathic pain detection. Through electroencephalogram spectrum analysis, electrocardio variability monitoring, pupil dynamic tracking and enphalin blood concentration detection, a pain related biomarker database is constructed, and compared with a traditional subjective scale, the objective index association degree is remarkably improved; the original arc-shaped guide rail buffer system and the rotary air bag fixing devices effectively absorb detection shaking, and are matched with the four pairs of rotary air bag fixing devices, so that the human engineering impact is attenuated under the low-frequency vibration working condition of below 10Hz.

The application discloses a pain pump administration control method and device, a pain pump and a storage medium. The method comprises the following steps: acquiring a corresponding relationship between a set index data range of a set associated part of a patient's operation site and a pain level, the set associated part being the brain or any body surface position within a set distance range of the operation site, and when the set associated part is the brain, the set index data is preset electroencephalogram index data of an electroencephalogram signal, and when the set associated part is any body surface position, the set index data is potential change amplitude data of an electromyogram signal; determining a current administration speed according to the detected set index data of the set associated part and the corresponding relationship between the set index data range and the pain level; and performing an infusion operation of the current patient according to the current administration speed. The application solves the problem that the existing pain level control pain pump administration is not objective enough, can determine the pain level based on the potential change, timely adjusts the administration, and can also issue an alarm when an abnormal situation occurs.

1. Name of this design product: Pain Assessment Scale (Naan Bread Pattern). 2. Purpose of this design: To assess the patient's pain level by using the pain rating values ​​on the card. 3. The key design features of this product are the combination of pattern and color. 4. The image or photograph that best illustrates the design's key features: the front view. 5. Other situations requiring explanation: Other explanation: Omitted views: Because this design product is a card-type product, the rear view, left view, right view, top view and bottom view do not have design features, so they are omitted.

The invention provides a method for obtaining a measure of user pain at home. The proposed concept is to measure the pain by utilizing sensor data obtained from force and / or motion sensors integrated in a personal care device, e.g. an oral care device, over the course of each of one or more personal care sessions of the user. Patterns in the sensor data, or changes in said patterns, can be used to infer pain information, such as an overall pain level, pain reaction events at certain points during the personal care session and / or at certain locations, or increased sensitivity at certain body areas. This provides a more objective and reliable estimation and monitoring of user oral pain that relying on patient (subjective) reporting of pain.

This application relates to the field of computer vision technology and discloses a method and system for detecting pain expressions. The method includes: acquiring a facial video stream, segmenting muscle regions and extracting texture features after facial key point localization and inter-frame alignment; calculating motion energy based on these features, extracting enhanced micro-expression temporal segments and multi-scale spatiotemporal features, constructing a muscle dynamics model and completing state estimation; generating an adaptive candidate spatiotemporal window set through spatiotemporal attention weighted fusion; performing temporal modeling for dynamic feature fusion, and selecting the optimal window by fusing micro-expression features; and outputting the final pain level after double consistency verification and loop closure optimization. This application overcomes the limitations of static images, accurately captures facial dynamics and temporal changes, strengthens feature correlation, and significantly improves detection accuracy.

The present application relates to the field of physical therapy equipment, especially to a kind of spinal step quantitative traction physiotherapy control system based on closed-loop force feedback, the system includes: data acquisition module, real-time traction force value, electromyographic signal data, displacement rate of change between traction bed movable bed plate and traction bed fixed bed body are collected;Traction bed drive module, according to the traction force control instruction output by self-learning fuzzy logic controller, execute traction action to traction bed body;Self-learning fuzzy logic controller, according to real-time traction force value, electromyographic signal data, displacement rate of change and the pain level signal feedback by the object to be traction, using step traction strategy, generates traction force control instruction, traction force control instruction is set to use the fuzzy parameter adjustment model pre-constructed based on neural network and fuzzy inference, dynamically generated by updating the shape parameter of membership function of first fuzzy logic rule.The present application effectively improves the self-adaptability and accuracy of traction force regulation.

The present application relates to the technical field of medical informatics, and in particular to a physiological signal real-time monitoring and intervention system for pain management, which comprises: a determination module configured to determine the abnormal tendency of a real-time updated stimulation window at each update time to obtain an abnormal tendency sequence; the determination module is further configured to determine similar fluctuation segments in the abnormal tendency sequence; the determination module is further configured to determine an abnormal progress factor of the physiological sensing signal at the current time based on the abnormal tendency difference and the length of each similar fluctuation segment; the determination module is further configured to determine a trigger factor for evaluating the abnormal pain state at the current time according to the abnormal progress factors of each physiological sensing signal at the current time and the last time, and to normalize the trigger factor to obtain a normalized trigger factor; and an intervention module configured to visualize and intervene in the pain degree of a target user based on the normalized trigger factor. The present application improves the accuracy and sensitivity of physiological signal anomaly recognition.

The invention discloses a multi-mode pain perception objective quantitative evaluation system and application, and relates to the technical field of pain perception, and the system comprises a data acquisition module which is used for obtaining visual data, voice data, text data, a photoelectric volume pulse wave PPG signal and an electrodermal response EDA signal corresponding to a target user; the data processing module is used for determining a pain index of the target user according to the visual data, the voice data and the text data; performing amplitude differential processing on the PPG signal to generate a PPG amplitude variation delta PPG; performing slope integration processing on the EDA signal to generate an EDA accumulated variation delta EDA; determining an energy competition index according to the ratio of the delta PPG to the delta EDA; determining the type of the pain index according to the size of the energy competition index; and the decision output module is used for outputting the pain index and the type of the target user. According to the present invention, the positive real pain is distinguished through the ratio of the [delta] PPG to the [delta] EDA so as to improve the accuracy of the pain level evaluation of the patient.

An apparatus includes a facial expression detection device and a computing device, the computing device being configured to receive facial pattern input from the facial expression detector, identify one or more micro-expressions in the facial pattern input, and predict one or more of pain intensity and pain source based on the identified one or more micro-expressions. Various aspects of the disclosed embodiments aim to identify pain sources non-contactly based on pain-induced micro-expressions using machine learning.

The invention discloses a deep learning-based facial micro-expression pain recognition and analysis method. The method comprises the following steps of S1, constructing an original data set; s2, preprocessing the obtained original data set; s3, based on the first-layer generative adversarial network and the preprocessed original data set, generating facial micro-expression images under different pain levels through a first-layer generator; s4, based on the second-layer generative adversarial network, extracting pain level features from the micro-expression image generated by the first-layer generative adversarial network and the real micro-expression data; s5, processing the extracted micro-expression features and pain grade scores through a fuzzy logic module; s6, based on a fuzzy logic reasoning result, performing defuzzification processing on the pain level; and S7, according to the real-time analysis result, continuously monitoring the pain state of the patient, and adjusting the sensitivity of the system to the micro-expression under different environmental conditions. According to the method, the facial micro-expression capture precision and the pain level identification accuracy in a complex environment are improved.

The application relates to a pain degree recognition method, device and system for a patient. The pain degree recognition method for a patient comprises the following steps: judging the data type of to-be-detected pain data; if the data type is a physiological signal type, adopting a multi-scale convolution mechanism, a compression-excitation residual network and a variable pressure encoder for feature extraction, and adopting a support vector machine to perform pain grading on the extracted signal features to obtain the pain degree of the patient; if the data type is an image type, adopting a double-branch feature extraction mechanism to perform multi-scale feature extraction on a facial expression image, alternately combining residual and attention mechanisms for feature fusion, and performing feature flattening and pain degree mapping on the fused feature map to obtain the pain degree of the patient. The pain degree recognition method for a patient has the advantages of high-precision pain grading based on physiological signals and high-accuracy pain grading based on images.

The invention relates to a pain real-time discrimination and treatment effect evaluation system based on EEG micro-state monitoring. The system comprises a micro-state extraction and analysis module which extracts a GFP peak topographic map from EEG signal data, optimizes the GFP peak topographic map to generate a template map, calculates parameters such as average duration of each micro-state category, and outputs a micro-state feature parameter set; the pain real-time judgment module inputs the micro-state characteristic parameter set into a deep learning model for detection, and a detection result containing a pain level is obtained; the treatment effect evaluation module obtains quantitative treatment effect indexes by obtaining and comparing micro-state characteristic parameter sets before and after treatment, and generates a report containing the indexes, analysis results and a micro-state change trend chart. According to the system, the pain state of a patient is monitored in real time through the EEG micro-state, objective evaluation indexes about the curative effect are provided for clinicians by quantifying the dynamic change of the EEG micro-state of the patient before and after treatment, and the scientificity and accuracy of treatment effect monitoring are improved.

This invention discloses a method and system for facial pain expression analysis based on spatiotemporal information. By sampling facial expression videos using a sliding window, several video segments are obtained, improving dataset utilization. Discrete cosine transform is applied to the video frames, followed by sawtooth scanning for enhancement, resulting in detailed feature enhancement maps that enhance detail information. Then, all video frames and their corresponding detailed feature enhancement maps from each sampled video segment are combined and input into a Transformer model. The Transformer model uses a concatenated cross-processing method to extract and fuse temporal and spatial features. Finally, the pain analysis result is obtained based on the pain level corresponding to each sampled video segment. This method effectively extracts feature information from facial expression videos, resulting in high accuracy in pain assessment.

A system for assessing back pain, comprising a wearable device designed to be worn on or around the torso of a user, equipped with one or more sensors positioned on the back portion of the wearable. The system includes one or more processors configured to measure movement characteristics of the user's back, issue prompts to a computing device requesting input on the user's psychological perception of pain levels, and receive corresponding user input data. The system analyzes the movement characteristics and psychological pain perception data to generate an assessment of the user's back pain. The assessment is then output to an associated output component. This system is particularly beneficial for monitoring and evaluating back pain in real-time, providing actionable insights for healthcare applications.

A pain-management system (300) configured to: receive a target-pain-score (314) that represents a level of pain that the user considers acceptable during a defined period of time; receive one or more target-input-parameters (304) which represent properties and / or activities of a user during the same defined period of time, wherein the one or more target-input-parameters (314) are a subset of a full list of input-parameters that are available; receive one or more settings (315) that represent one or more input-parameters that are to be increased or decreased; use a neural network that has been trained for the individual user to determine one or more calculated-user-parameters (316) based on the target-pain-score (314) and the target-input-parameters (304), wherein at least one of the calculated-user-parameters (316) is set based on the settings (315); and present the one or more calculated-user-parameters (316) using a user interface.

The present application belongs to the technical field of medical rehabilitation equipment, and discloses a kind of laryngeal postoperative intelligent monitoring rehabilitation auxiliary instrument and control method;Including obtaining the physiological data of the throat of patient throat;Four-channel tensor formed after processing physiological data of throat is input into physical information neural network model for analysis by constructing physical information neural network model, and the output of laryngeal entrance closure degree and pharyngeal wall tissue elastic modulus, determine the pain level of patient based on laryngeal entrance closure degree and pharyngeal wall tissue elastic modulus;Based on the analysis of mucous membrane dynamic displacement sequence data and pressure data, determine the swallowing mode characteristics of patient, and combine laryngeal entrance closure degree, pharyngeal wall tissue elastic modulus and pain level to carry out rehabilitation decision analysis, generate rehabilitation intervention instruction;Based on rehabilitation intervention instruction, execute dosing operation, and obtain the execution feedback record after completing dosing operation, adjust rehabilitation intervention instruction based on execution feedback record, significantly enhance the timeliness and effectiveness of treatment decision.

The application provides a facial-expression-based pain recognition method, device, equipment and storage medium, and the facial-expression-based pain recognition method comprises the following steps: acquiring a to-be-recognized face video, and extracting an AU image from the to-be-recognized face video; and inputting the AU image into a pre-trained pain recognition model to obtain a pain level of the to-be-recognized face image. The AU image related to pain is input into the pre-trained pain recognition model, so that other regions of the face unrelated to pain are avoided from being input into the pre-trained pain recognition model, and the accuracy of pain recognition is improved.

The embodiment of the application provides a method and device for determining a pain index caused by endometriosis, and relates to the field of medical devices and digital health technology. The method comprises: acquiring an RR interval sequence in real time through a photoplethysmogram sensor, acquiring a skin conductance signal sequence in real time through a skin galvanic activity sensor, and acquiring a pressure dynamic signal sequence in real time through a wearable pressure sensing unit; processing the RR interval sequence to obtain an HRV feature set, processing the skin conductance signal sequence to obtain an EDA feature set, and processing the pressure dynamic signal sequence to obtain a pressure dynamic feature set; time-synchronizing the HRV feature set, the EDA feature set and the pressure dynamic feature set, and then performing fusion processing to obtain a feature vector; and inputting the feature vector into a pre-trained pain index determination model to obtain a pain index reflecting the pain caused by endometriosis. The method can reflect the pain degree of a user when the user is in pain caused by endometriosis.

The invention relates to the technical field of pain assessment equipment, in particular to a pain degree assessment electronic temperature sensing ball and a pain assessment algorithm. The electronic temperature sensing ball comprises an elastic ball body, a pressure sensor, a temperature sensor, a microcontroller, a wireless communication module, a power module, a charging interface and a multi-color lamp ring, and all the parts are electrically connected to achieve data collection, processing and feedback. According to the pain assessment algorithm, objective quantitative assessment of the pain degree is achieved by collecting user grip strength data and skin temperature data through preprocessing, feature extraction, pain index calculation and grade assessment, and data visualization is achieved through visual display of a lamp ring and terminal equipment. The problems that existing pain assessment depends on subjective self-description, accuracy is insufficient, and operation is complex are solved, and the method has the advantages of being objective in assessment, easy and convenient to operate, capable of achieving real-time feedback and high in portability and can be widely applied to scenes such as clinical medical treatment and rehabilitation nursing.

The application belongs to the technical field of medical equipment and artificial intelligence, and discloses a tonsil postoperative intelligent analgesia system based on multi-modal data, which comprises a multi-modal data acquisition interface for acquiring multi-modal data, wherein the multi-modal data comprises physiological signals, behavior signals and patient self-reported pain scores; a main control chip electrically connected with the multi-modal data acquisition interface, used for analyzing and processing the multi-modal data based on an embedded intelligent analgesia decision model, and outputting the current pain level of the patient, the future pain trend prediction and the targeted drug administration instruction, wherein the intelligent analgesia decision model realizes unified perception and dynamic modeling of the multi-modal data on multiple time scales by introducing hierarchical pulse coding; and an infusion execution device electrically connected with the main control chip, used for responding to the drug administration instruction output by the main control chip and executing corresponding infusion operation. The application can improve the pain assessment accuracy of patients after tonsillectomy and conduct early warning.

The invention discloses a pain assessment model construction method and a non-contact continuous pain assessment method, and belongs to the field of image expression recognition. The method comprises the following steps: acquiring multi-modal time sequence data of a patient in a non-contact manner, performing time-space synchronization processing to obtain a multi-modal frame packet sequence, performing single-modal self-supervision pre-training based on the extracted single-modal time sequence data, connecting a multi-modal projection layer to obtain a front structure, and performing cross-modal semantic alignment coding; all modal output features are mapped to word vector dimensions of the large language model, then a large language trunk model is connected to obtain an overall structure, multi-modal time sequence data of a patient are input, a pain assessment result is output by indicating the overall structure to carry out fine tuning training of the large language model, and a trained pain assessment model is obtained; the method is used for non-contact continuous pain assessment; the pain assessment result comprises a pain level, a pain score, an interpretable heat map and the like; in combination with a large language model, the trained model can realize pain grade division and interpretable continuous output.