124 results about "Sleep apnea" patented technology

The invention discloses an electrocardiosignal-based sleep apnea detection method and system and a storage medium. The method comprises the following steps: acquiring a target electrocardiosignal to be analyzed, performing R peak identification on the target electrocardiosignal, calculating an RR interval between two adjacent R peaks, and acquiring a voltage amplitude of the electrocardiosignal at the R peak position as an R peak amplitude; on the basis of the RR interval, the RR interval is converted into an instantaneous heart rate sequence, resampling operation is carried out on the heart rate sequence, interpolation processing is carried out on non-uniform sampling points obtained after resampling so as to obtain a continuous and equally-spaced heart rate curve, and signals of a breathing-related frequency band are extracted through filtering to serve as electrocardio derived breathing signals; and splicing the RR interval, the R peak amplitude and the electrocardio-derived respiration signal to form a multi-channel feature, and inputting the multi-channel feature into a trained sleep respiration detection model to obtain sleep apnea state judgment information. Therefore, the apnea state can be detected more comprehensively, and the accuracy of sleep apnea detection is improved.

The invention provides a sleep apnea real-time early warning system based on heart rate variability analysis, belongs to the technical field of computer data processing, and provides a data processing method which is used for dynamically selecting a monitoring terminal, adaptively adjusting an analysis threshold value based on a sleep situation and carrying out time sequence correlation verification on a heart rate and a sound signal. And the sleep apnea event monitoring accuracy and the system operation efficiency are improved. The monitoring terminals are dynamically selected, the predictive switching strategy is adopted, continuity and high quality of heart rate data streams input into the data processing system are ensured, the data acquisition modes caused by body position changes of the user in the sleep period are switched, subsequent analysis errors are avoided, and the user experience is improved. By determining situation information such as sleeping postures of a user in real time and dynamically adjusting an analysis threshold value of heart rate variability, a data processing model can intelligently adjust the sensitivity of the data processing model according to the risk level, and deep time sequence correlation verification is carried out in combination with heart rate and sound signals, so that collaborative analysis of multi-modal information is realized.

The invention relates to the field of biosensors, and discloses a cardiovascular data monitoring method for the cardiovascular medicine department. According to the method, electrocardio, respiration and blood oxygen signals are synchronously collected through a non-invasive terminal, sleep apnea events are analyzed and recognized in a combined mode, the electrocardio signals are deeply analyzed to detect cardiovascular abnormalities, and time sequence characterization of the function state of the autonomic nervous system is generated based on heart rate variability; and further constructing a time sequence causal reasoning model, quantifying the triggering effect of the respiratory event on the cardiovascular event, generating a comprehensive night cardiovascular risk layering index, and triggering graded early warning. According to the invention, non-sensitive, long-time-history and high-precision night cardiovascular risk dynamic assessment and causal mechanism analysis are realized.

The invention discloses a system for predicting the occurrence risk of obstructive sleep apnea, and belongs to the technical field of digital medical treatment. The system for predicting the obstructive sleep apnea occurrence risk comprises a data acquisition module, a perioperative period risk assessment module, a risk prediction module and a result output module. The problem that in the prior art, it is difficult to accurately predict the OSA risk is solved, the risk can be comprehensively and accurately evaluated by comprehensively collecting basic physiological data, clinical symptom data and common disease information of the user and generating accurate feature data through processing, a reliable basis is provided for the user and medical staff, and by combining perioperative period risk evaluation, the risk prediction accuracy of the OSA risk is improved. According to the method, operation related risks can be identified, feature data and perioperative period risk data are fused through the constructed risk prediction model, the risk level of obstructive sleep apnea of the user can be evaluated, and a risk evaluation result and early warning can be output in time, so that intervention can be performed in advance, and the risk of a patient can be reduced.

Techniques for addressing sleep disorders are provided. A system includes a nerve stimulator that is configured to deliver stimulation energy to a nerve of a sleeping patient. A system includes a sensor for gather data from the sleeping patient and a controller for processing the data. The controller is configured to cause the stimulation energy that is provided to be adjusted based on the sensed data.

The invention provides a multi-modal fusion obstructive sleep apnea (OSA) identification method based on deep canonical correlation analysis (DCCA). For multi-modal characteristics, a whole process from data preprocessing, feature extraction and screening to feature fusion and classification is designed. Firstly, AHI indexes, voice data and craniofacial image data of a subject are collected and preprocessed, and DeepSpectrum voice features and geometric morphology image features based on MediaPipe are extracted. Then, feature screening is carried out by adopting a competitive group optimizer (CSO) and a ReliefF algorithm respectively; for a class imbalance problem, an oversampling (AMDO) method based on an adaptive mahalanobis distance is introduced to balance data. Non-linear mapping and deep fusion are carried out on high-dimensional features of the two modals through DCCA, low-dimensional high-correlation features are generated, and information complementarity between the modals is improved. And finally, inputting the fused features into a classifier and evaluating the performance by using five-fold cross validation. According to the invention, effective fusion between modals is realized by using DCCA, and a new method is provided for early screening and auxiliary diagnosis of OSA.

The invention discloses a sleep apnea monitoring system and method, and the method comprises the following steps: S1, collecting a multi-modal physiological signal, executing the preprocessing, and generating a standardized sequence; s2, recognizing a sleep stage label, and extracting breathing phase and thoracico-abdominal phase difference information; s3, detecting a suspected apnea event, calculating a consistency index and a confidence coefficient, and outputting a candidate event; s4, when a safety threshold is met, disturbance verification is carried out, responses before and after intervention are collected, and event types are judged; s5, constructing an upper airway digital twinborn model, simulating and predicting an intervention effect, and outputting an abnormal severity score and an early warning; and S6, fusing the event and the risk information, generating a self-evolution risk curve, and outputting a monitoring report. According to the method, through multi-modal physiological signal fusion and upper airway digital twin modeling, accurate recognition, typing judgment and individualized risk dynamic monitoring of sleep apnea are achieved.

1. The name of the design product: headband for sleep apnea electrical stimulation instrument. 2. The use of the design product: headband for sleep apnea electrical stimulation instrument, providing non-invasive treatment for patients with obstructive sleep apnea syndrome. 3. The design features of the design product: the shape of the design product. 4. The picture or photo that best indicates the design features: perspective view 1.

A method of establishing a model for detecting atrial fibrillation (AF) and sleep apnea (SA) is implemented by a computer system that stores training electrocardiograms, and includes steps of: dividing the training electrocardiograms into training segments, each of which contains a common length of time of recorded electrical activity of a heart; for each of the training segments, labeling the training segment with a symptom indicator that indicates whether the training segment is related to AF and whether the training segment is related to SA; for each of the training segments, performing feature extraction on the training segment to obtain an entry of feature data; and establishing the model by using a machine learning algorithm based on the entries of feature data and the symptom indicators.

The invention provides a radar non-inductive respiration monitoring system and method based on a passive wrinkled airbag, and the system comprises a sleep monitoring pillow and a respiration recognition and abnormity monitoring subsystem, the respiration recognition and abnormity monitoring subsystem comprises a signal monitoring and coupling module which processes original monitoring data, and transmits the processed data to the sleep monitoring pillow; a human body respiration direct measurement signal and an air bag coupling amplification signal are obtained; the state recognition and inversion module is used for carrying out in-place state recognition, sleeping posture recognition and airbag state inversion on the coupled double-domain fusion respiration candidate data to obtain state constraint data; the respiration reconstruction and feature extraction module is used for performing screening and feature extraction on the double-domain fusion respiration candidate data to obtain respiration feature data; and the abnormity identification and confirmation module is used for identifying the apnea candidate event and the abnormal event, obtaining an abnormity judgment result and carrying out graded alarm pushing. According to the invention, through the non-inductive pillow type structure and radar-air bag double-domain fusion perception, breathing abnormity intelligent monitoring with high robustness and low false alarm rate is realized.

A method and device for treating tinnitus and / or hearing impairment of a user at bedtime includes providing an audio stimulus to the user using a parametric array speaker. Some embodiments treat tinnitus by removing a frequency notch corresponding to the user's tinnitus frequencies from the audio signal. The audio signal may be ambient sound detected by a microphone, or may be a prerecorded file which may comprise noise or other audio such as audiobooks or music. Some embodiments combine treatment of tinnitus or hearing impairment with treatment for apnea, hypopnea or snoring.

The application provides a sleep apnea detection method and system, and relates to the technical field of deep learning and medical signal processing, wherein the method comprises the following steps: constructing a heterogeneous deep learning model comprising two parallel heterogeneous model branches and independently supervising training of the two heterogeneous model branches; putting the pre-trained heterogeneous deep learning model into a cooperative retraining module based on course learning for cooperative retraining; introducing an uncertainty estimation mechanism in the cooperative training process to dynamically evaluate and correct pseudo labels, and combining active correction, uncertainty-based screening and arbitration-driven dynamic reweighting to realize suppression of pseudo label noise and reasonable use of model divergence, so that high robustness and generalization performance can be maintained in a semi-supervised learning scene.

The invention relates to the technical field of medical identification, in particular to a sleep apnea real-time monitoring and early warning system, which comprises an acquisition module used for acquiring PSG data of a target user from a sleep moment to a current moment; the determination module is used for determining all OSA events from the sleep moment to the current moment according to a spectrogram of respiratory effort waves and a spectrogram of airflow of a window corresponding to each moment in the PSG data; the determining module is further used for determining the blood oxygen consumption time period of the current OSA event; the determination module is also used for determining a trusted OSA event; and the early warning module is used for constructing an early warning model of the target user by using the PSG data of the credible OSA event, and performing sleep apnea early warning on the target user by using the real-time PSG data of the target user acquired in real time and the early warning model. According to the invention, the accuracy of OSA diagnosis is improved.

Compositions including Δ-9-tetrahydrocannabinol (THC) and a carbonic andydrase inhibitor and methods of using these compositions for the treatment of obstructive sleep apnoea (OSA). The treatment method also includes administering dronabinol and acetazolaminde and combinations thereof to a subject in need thereof.

The present application belongs to the technical field of sleep respiratory disease detection, and is a sleep apnea identification method based on a hybrid neural network. The method uses a millimeter wave radar to perceive human sleep in a surrounding bed environment, adopts spatial two-dimensional analysis to locate the chest cavity position, and solves the interference problem in radar sign extraction of different targets at the same distance. Shannon entropy of the respiratory signal is constructed as an iteration index of the whale optimization algorithm, and the minimum index is used to realize iteration optimization of the variational mode extraction parameter, so that different breathing states are matched with different parameters to accurately extract the main frequency narrowband respiratory signal. The respiratory time-frequency energy graph obtained through data processing is used as input, and a CNN network and a bidirectional long short-term memory module are used to jointly construct a feature extraction module, so that the application can identify the frequency change trend over time, capture more comprehensive features, and accurately identify target sleep apnea. In addition, the hybrid network can accurately classify unmanned scenes, apnea, low ventilation and normal breathing.

The application discloses a sleep apnea detection method based on a millimeter wave radar, and relates to the technical fields of radar signal processing and vital sign detection.The method comprises the following steps: transmitting a detection signal to a target through a millimeter wave radar to obtain an intermediate frequency signal and a signal transformation matrix; calculating a dynamic energy change value based on the preprocessed signal transformation matrix, and determining a target distance bin of each frame according to a statistical result of the dynamic energy change value; determining whether the target is in a position stable state according to the discrete degree of the target distance bin of each frame in a preset time window; extracting a phase signal at the target distance bin of each frame in the window in the position stable state, obtaining a breathing signal waveform curve based on the phase signal, and detecting a sleep apnea event.The application can realize high-precision detection of the sleep apnea event under various complex conditions, and effectively solves the problems of unstable target locking, large noise interference and lack of distance adaptability in state determination.

The invention discloses a sleep monitoring and intelligent early warning system and method based on a multi-modal time sequence signal, and the system comprises a multi-modal sensor module which is used for collecting an original heterogeneous time sequence signal of a subject in a sleep period; the time sequence data preprocessing module is used for performing timestamp alignment, band-pass filtering noise reduction, baseline drift correction and sliding window segmentation on the original heterogeneous time sequence signals and extracting multi-modal feature vectors; the sleep feature recognition module is used for receiving the multi-modal feature vector, performing deep feature learning and outputting sleep staging probability distribution and a sleep apnea event detection mark; the large language model module is used for performing joint coding on an output result, a historical sleep file of the subject and a clinical diagnosis text to generate a structured sleep quality assessment report and health risk association analysis; and the multi-level intelligent early warning and decision support module is used for triggering early warning signals of different levels and generating personalized sleep intervention suggestions.

The present disclosure relates to a method and apparatus for predicting obstructive sleep apnea. The method for predicting obstructive sleep apnea according to one embodiment of the present disclosure includes generating analysis data from facial photograph information of an analysis subject, storing response data of an OSA screening questionnaire of the analysis subject in the memory, inputting the analysis data and the response data into a pre-trained machine learning model and inferring information about the degree of OSA, and transmitting the inference result to at least one terminal or outputting the inference result to a display.

1. The name of the design product: continuous positive airway pressure machine. 2. The use of the design product: used for relieving snoring, hypoventilation and sleep apnea of patients during sleep, thereby achieving the purpose of auxiliary treatment, usually used in home environment, medical institutions. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view 1. 5. Other circumstances that need to be explained: A is a liquid crystal display screen.

A dental appliance is disclosed. The appliance may include an arcuate base shaped to extend along at least a portion of an upper dental arch of a patient and match with a custom fit at least certain maxillary teeth of the patient. The appliance may further include a tongue-retention feature. The tongue-retention feature may connect to the arcuate base and comprise a palatal portion and a sublingual portion. The sublingual portion may cooperate with the palatal portion to form a cavity shaped to receive an anterior portion of a tongue of the patient therewithin. The palatal portion may have an exterior surface custom-formed to match at least a portion of a hard palate of the patient.

An air mattress and related air pressure control system, where the air mattress can change shapes to help reducing snoring and sleep apnea. The air mattress has individually inflatable and deflatable air compartments that can be inflated to different degrees to create a desired profile, such as a sloped profile, of the air mattress. When the air mattress is used for sleeping, a controller controls the inflation and deflation of the air compartments upon detecting a snoring sound. The air compartments are inflated by compressed air from a compressed air cylinder, rather than a pump, so as to reduce noise during operation. When the air mattress is not used for sleeping, the compressed air cylinder may be re-filled by a pump.

The application discloses a sleep apnea detection method and system based on transcutaneous carbon dioxide monitoring, and belongs to the technical field of sleep apnea detection. The application integrates a miniaturized transcutaneous carbon dioxide detection module composed of a flexible optical sensor and a multi-channel PPG, a bioimpedance sensor and an accelerometer; a heating module is controlled by a PID algorithm to realize constant temperature, so that non-invasive transcutaneous carbon dioxide detection is ensured; a multi-sensor data fusion system is built to realize synchronous acquisition of physiological parameters; a low-power embedded processing unit is adopted to realize real-time processing and monitoring of physiological multi-modal data. The application also cooperates with a machine learning model and combines TcCO2 fluctuation, SpO2 drop rate and respiratory interval variability to realize real-time identification and early warning of sleep apnea events. The application realizes highly integrated and long-lasting continuous monitoring of respiratory health, and effectively improves the home screening capability of sleep breathing disorders.

The invention provides an obstructive sleep apnea detection method, system and device and a storage medium, and relates to the technical field of signal processing, and the method comprises the steps: obtaining pressure signals detected by at least two bed-mounted pressure sensors in a human body sleep state, and the crowd type characteristics and the pre-sleep activity characteristics of a to-be-detected person; performing quality evaluation on each path of pressure signal, and determining a target pressure signal based on a quality evaluation result; preprocessing the target pressure signal, and performing time domain and frequency domain feature extraction on the preprocessed target pressure signal; and inputting the extracted multi-dimensional features, the crowd type features of the to-be-detected person and the pre-sleep activity features into a pre-trained machine learning model to obtain a classification result of whether the to-be-detected person suffers from obstructive sleep apnea. According to the method and the device, under the condition that PSG equipment is not used, accurate detection of the OSA is realized.

In general, the invention relates to pharmaceutical compositions comprising (R)-oxybutynin and a norepinephrine reuptake inhibitor (NRI) and methods of treating Sleep Apnea comprising administering (R)-oxybutynin and a norepinephrine reuptake inhibitor (NRI). In some embodiments, the NRI is atomoxetine.

The invention provides a multi-domain electrocardio intelligent analysis method of a mixed Fourier and wavelet convolutional neural network, belongs to the technical field of artificial intelligence and medical health crossing, and solves the technical problems that global spectrum features and local transient features are difficult to consider and task generalization is poor in traditional single-domain ECG analysis. According to the technical scheme, the method comprises the following steps: S1, preprocessing an ECG signal, filtering, segmenting, normalizing and enhancing data; s2, constructing a three-branch model; s3, fusing the attention mechanism with multi-domain features; s4, setting a task classification head; s5, using Adam optimization and an early stop strategy to prevent overfitting; and S6, inputting data, and outputting arrhythmia classification, biological recognition and sleep apnea detection results. According to the method, generalization and accuracy are improved through multi-domain fusion, multiple tasks are supported, and clinical and biological recognition scenes are adapted.

This invention belongs to the field of infant and toddler care technology and discloses an active intervention system and method for infant and toddler sleep apnea. Through a dedicated algorithm and adaptive acquisition components, it accurately collects sleep audio, physiological parameters, and environmental information, and performs semantic annotation and feature association on various types of data to establish dedicated semantic correspondence rules. Simultaneously, it ensures the temporal consistency of different types of data, transforming unstructured raw data into structured semantically related data. Based on the apnea risk level and specific triggers obtained from semantic parsing, it designs differentiated, graded intervention strategies to carry out targeted active intervention operations for different triggers, replacing the traditional single alarm mode. Simultaneously, it collects real-time feedback data on the effects of intervention and dynamically adjusts intervention parameters and strategies based on feedback, making apnea intervention more targeted, improving the timeliness and effectiveness of intervention, and reducing the potential risk of infant and toddler sleep apnea.

A heat exchanger is disclosed for causing cryolysis of adipose tissue of a human tongue. The heat exchanger includes a body having cooling channels for circulating fluids therein. The body forms a contact surface that contacts a portion of the dorsal surface of the tongue and a portion of the base of the tongue. The heat exchanger includes a pair of side walls extending from the body and forming a pair of side contact surfaces that are dimensioned so that they contact the dorsal and lateral surfaces of the tongue in a manner so as to constrict the tongue when the contact surface is in contact with the tongue. A method of treatment for apnea using the heat exchanger and / or administering a chemical adipolysis formulation / vasoconstriction agent is also disclosed.

In general, the invention relates to pharmaceutical compositions comprising a norepinephrine reuptake inhibitor (NRI), muscarinic receptor antagonist, and carbonic anhydrase inhibitor and methods of treating Sleep Apnea comprising the administration of these pharmaceutical compositions.

The present application is suitable for sleep apnea detection technical field, and provides a sleep apnea detection method based on wavelet transform.The present application adopts discrete wavelet decomposition technology, decomposes electrocardiogram signals into multi-scale information as model input, and fuses a supervised contrast learning concept, constructs an end-to-end deep learning network model, and realizes efficient and accurate classification of sleep apnea.Compared with the traditional detection method which depends on expert manual analysis method or needs complex preprocessing steps, the present application improves the detection efficiency and simplifies the complexity of signal processing.More importantly, the present application directly uses time series signals as input, avoiding the complex secondary feature extraction process, which makes the present application more easily converted into actual hardware equipment for implementation and application.In addition, using the public ApneaECG dataset for testing, the prediction accuracy of the present application exceeds the current electrocardiogram-based automatic sleep apnea detection model.

The invention provides a computer-implemented method for controlling a dose titration of a medicament to be provided to a subject for treating obstructive sleep apnea. The method includes obtaining a dose level of a previous dose of the medicament, the previous dose having been provided to the subject and obtaining a medicament efficacy measure based on a response of the subject to the previous dose. A dose titration for a future dose of the medicament is determined based on the medicament efficacy measure and the dose level of the previous dose.