Electrical stimulation device, method of controlling an electrical stimulation device

Abstract

The present disclosure provides an electric stimulation device and a control method thereof. The electric stimulation device comprises: an electrode, which is in contact with a target object in a use state and is used to electrically stimulate a target tissue of the target object; a sensor, which is used to collect breathing data of the target object; and a controller, which is electrically connected with the sensor and the electrode and is used to: determine a current breathing state of the target object according to the breathing data; determine a predicted breathing state of the target object in a next breathing cycle according to the current breathing state of the target object; determine a target stimulation parameter according to the predicted breathing state; and control the electrode to output a stimulation signal based on the target stimulation parameter. The stimulation signal is dynamically adjusted according to the breathing state of the user, so that the stimulation signal can accurately stimulate the muscle or nerve of the user and keep the airway of the user unobstructed.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of nerve stimulation, and in particular to an electrical stimulation device and a control method of the electrical stimulation device. BACKGROUND

[0002] Patients with sleep breathing disorders will cause the pharyngeal and lingual muscles to relax physiologically during sleep, resulting in the tongue blocking the pharyngeal cavity passage at the back during sleep, and thus causing respiratory pause and hypopnea during sleep. Therefore, the muscle tissue or nerve tissue of the patient with sleep breathing disorders needs to be stimulated to enhance and maintain the openness of the upper respiratory tract of the patient, so as to reduce or eliminate the airway obstruction caused by the backward falling of the root of the tongue.

[0003] In related technologies, the stimulation treatment mode for patients with sleep breathing disorders is an open-loop stimulation mode or a stimulation mode based on oral cavity state feedback. This will cause the electrical stimulation device to continuously output a stimulation signal in a specific mode, so as to keep the relevant muscles of the patient in a contraction state, and thus keep the respiratory tract unobstructed. However, if the patient's muscles or nerves are continuously stimulated for a long time, the patient's muscles or nerves are prone to fatigue, which affects the treatment effect. SUMMARY

[0004] Therefore, the present disclosure provides an electrical stimulation device and a control method of the electrical stimulation device.

[0005] According to a first aspect of an embodiment of the present disclosure, an electrical stimulation device is provided, and the electrical stimulation device comprises:

[0006] an electrode, which is in contact with a target object in a use state, and is used to perform electrical stimulation on a target tissue of the body of the target object;

[0007] a sensor, which is used to collect breathing data of the target object, the breathing data comprising at least one of the following: motion data, exhalation temperature data, thoracic pressure data, electrical impedance data, blood oxygen data, and posture data;

[0008] a controller, which is electrically connected with the sensor and the electrode, and is used to:

[0009] determine a current breathing state of the target object according to the breathing data;

[0010] determine a predicted breathing state of the target object in a next breathing cycle according to the current breathing state of the target object;

[0011] determine a target stimulation parameter according to the predicted breathing state;

[0012] control the electrode to output a stimulation signal based on the target stimulation parameter, so as to stimulate the target tissue.

[0013] In some embodiments, the current respiratory state comprises a current respiratory frequency, a current respiratory amplitude, a current respiratory phase, a current respiratory deceleration frequency, a current respiratory deceleration phase, a current blood oxygen content, and a current motion state;

[0014] The determining, according to the respiratory data, of the current respiratory state of the target object comprises:

[0015] The current respiratory frequency, the current respiratory amplitude, and the current respiratory phase of the target object are determined according to the thoracic pressure data, the electrical impedance data, and the exhalation temperature data in the respiratory data;

[0016] The current respiratory deceleration frequency and the current respiratory deceleration phase of the target object are determined according to the thoracic pressure data, the electrical impedance data, the blood oxygen data, and the exhalation temperature data in the respiratory data;

[0017] The current blood oxygen content of the target object is determined according to the blood oxygen data in the respiratory data;

[0018] The current motion state of the target object is determined according to the motion data and the posture data in the respiratory data.

[0019] In some embodiments, the determining, according to the respiratory data, of the current respiratory state of the target object comprises:

[0020] In response to determining that there is an interference signal in the respiratory signal of the target object, a sampling window is determined according to a preset respiratory frequency range and a preset respiratory motion feature, wherein the respiratory signal is determined according to the motion data in the respiratory data;

[0021] The respiratory signal in the sampling window is feature extracted according to the preset respiratory motion feature, to determine a feature weight;

[0022] An analog respiratory signal is determined according to a reference respiratory frequency and a reference respiratory phase;

[0023] The reference respiratory frequency and the reference respiratory phase are adjusted according to the feature weight, to minimize the residual error between the respiratory signal and the analog respiratory signal, and to determine the current respiratory frequency and the current respiratory phase in the current respiratory state.

[0024] In some embodiments, the determining, according to the current respiratory state of the target object, of the predicted respiratory state of the target object in the next respiratory cycle comprises:

[0025] The current respiratory state is feature extracted to obtain a feature vector;

[0026] predict a predicted respiration state of the target object in a next respiration cycle based on the state vector corresponding to the current respiration state and the feature vector, by using a pre-constructed respiration state space model.

[0027] In some embodiments, the determining the target stimulation parameter according to the predicted respiration state comprises:

[0028] determining an initial stimulation parameter of the next respiration cycle according to the predicted respiration state;

[0029] determining posture change data of the target object according to the respiration data collected by the sensor, wherein the posture change data comprises at least one of the following: sleep position data, sleep action data, and oral-nasal respiration mode data;

[0030] adjusting the initial stimulation parameter based on the posture change data to determine the target stimulation parameter.

[0031] In some embodiments, the target stimulation parameter comprises a stimulation output time, a stimulation duration, and a stimulation signal intensity.

[0032] The determining the initial stimulation parameter of the next respiration cycle according to the predicted respiration state comprises:

[0033] determining the stimulation output time based on a preset time offset and a respiration start time in the predicted respiration state;

[0034] determining the stimulation duration based on a dynamic time bandwidth of the respiration signal and a length of the predicted respiration state;

[0035] determining the stimulation signal intensity based on a respiration amplitude and a blood oxygen content in the predicted respiration state.

[0036] In some embodiments, the adjusting the initial stimulation parameter based on the posture change data to determine the target stimulation parameter comprises:

[0037] determining a confidence degree of the initial stimulation parameter at each time in the next respiration cycle based on the posture change data;

[0038] determining a weight of the initial stimulation parameter according to the confidence degree;

[0039] adjusting the initial stimulation parameter according to the weight of the initial stimulation parameter to determine the target stimulation parameter.

[0040] In some embodiments, the determining the confidence degree of the initial stimulation parameter at each time in the next respiration cycle based on the posture change data comprises:

[0041] acquire prior feature of the posture change data information;

[0042] extract features of the posture change data information and the posture change data information;

[0043] According to the feature extraction result of the prior feature and the feature extraction result of the posture change data, the confidence evaluation model is used to evaluate the predicted respiratory state, and the confidence of the initial stimulation parameter at each time in the next respiratory cycle is determined.

[0044] In some embodiments, the controller is further configured to:

[0045] update the respiratory state space model based on the difference between the actual respiratory state and the predicted respiratory state of the target object in the next respiratory cycle;

[0046] adjust the acquisition parameters of the sensor based on the predicted respiratory state, wherein the acquisition parameters of the sensor include at least one of the following: acquisition frequency, resolution, and power.

[0047] According to a second aspect of the embodiments of the present disclosure, a control method of an electrical stimulation device is provided, and the method comprises:

[0048] acquire respiratory data of a target object based on a sensor, wherein the respiratory data includes at least one of the following: motion data, exhalation temperature data, chest pressure data, electrical impedance data, blood oxygen data, and posture data;

[0049] determine a current respiratory state of the target object according to the respiratory data;

[0050] determine a predicted respiratory state of the target object in the next respiratory cycle according to the current respiratory state of the target object;

[0051] determine a target stimulation parameter through a controller according to the predicted respiratory state;

[0052] control an electrode to output a stimulation signal to stimulate a target tissue of the target object based on the target stimulation parameter through the controller.

[0053] In some embodiments, the current respiratory state includes respiratory frequency, current respiratory amplitude, current respiratory phase, current respiratory weakening frequency, current respiratory weakening phase, current blood oxygen content, and current motion state.

[0054] The determination of the current respiratory state of the target object according to the respiratory data comprises:

[0055] Based on the intrathoracic pressure data, electrical impedance data, and expiratory temperature data in the respiratory data, determine the target's current respiratory rate, current respiratory amplitude, and current respiratory phase.

[0056] Based on the intrathoracic pressure data, electrical impedance data, blood oxygen data, and expiratory temperature data in the respiratory data, the current respiratory attenuation frequency and current respiratory attenuation phase of the target object are determined;

[0057] Based on the blood oxygen data in the respiratory data, determine the current blood oxygen content of the target object;

[0058] Based on the motion and posture data in the breathing data, the current motion state of the target object is determined.

[0059] In some embodiments, determining the current respiratory state of the target object based on the respiratory data includes:

[0060] In response to the determination that there is an interference signal in the respiratory signal of the target object, a sampling window is determined according to a preset respiratory frequency range and preset respiratory motion characteristics, wherein the respiratory signal is determined based on the motion data in the respiratory data;

[0061] Based on the preset respiratory motion characteristics, feature extraction is performed on the respiratory signal within the sampling window, and feature weights are determined.

[0062] The simulated respiratory signal is determined based on the reference respiratory rate and reference respiratory phase;

[0063] The reference respiratory rate and reference respiratory phase are adjusted according to the feature weights to minimize the residual between the respiratory signal and the simulated respiratory signal, and to determine the current respiratory rate and current respiratory phase in the current respiratory state.

[0064] In some embodiments, determining the predicted respiratory state of the target object in the next respiratory cycle based on the target object's current respiratory state includes:

[0065] Based on a pre-built respiratory state space model;

[0066] Feature vectors are obtained by extracting features from the current breathing state.

[0067] Based on the state vector corresponding to the current breathing state and the feature vector, the predicted breathing state of the target object in the next breathing cycle is predicted through the breathing state space model.

[0068] In some embodiments, determining the target stimulus parameters based on the predicted respiratory state includes:

[0069] determine an initial stimulation parameter of a next breathing cycle according to the predicted breathing state;

[0070] determine posture change data of the target object according to the breathing data collected by the sensor, wherein the posture change data comprises at least one of the following: sleep position data, sleep action data, and oral-nasal breathing mode data;

[0071] adjust the initial stimulation parameter based on the posture change data to determine the target stimulation parameter.

[0072] In some embodiments, the target stimulation parameter comprises a stimulation output time, a stimulation duration, and a stimulation signal intensity.

[0073] The determining of the initial stimulation parameter of the next breathing cycle according to the predicted breathing state comprises:

[0074] determining the stimulation output time based on a preset time bias and a breathing start time in the predicted breathing state;

[0075] determining the stimulation duration based on a dynamic time bandwidth of the breathing signal and a length of the predicted breathing state;

[0076] determining the stimulation signal intensity based on a breathing amplitude and a blood oxygen content in the predicted breathing state.

[0077] In some embodiments, the adjusting of the initial stimulation parameter based on the posture change data to determine the target stimulation parameter comprises:

[0078] determining a confidence degree of the initial stimulation parameter at each time in the next breathing cycle based on the posture change data;

[0079] determining a weight of the initial stimulation parameter according to the confidence degree;

[0080] adjusting the initial stimulation parameter according to the weight of the initial stimulation parameter to determine the target stimulation parameter.

[0081] In some embodiments, the determining of the confidence degree of the initial stimulation parameter at each time in the next breathing cycle based on the posture change data comprises:

[0082] obtaining prior features of the posture change data information;

[0083] performing feature extraction on the prior features of the posture change data information and the posture change data information;

[0084] According to the feature extraction result of the prior feature and the feature extraction result of the posture change data, the predicted respiratory state is evaluated through a confidence evaluation model, and the confidence of the initial stimulation parameter at each time in the next respiratory cycle is determined.

[0085] In some embodiments, the method further comprises:

[0086] Based on the difference between the actual respiratory state and the predicted respiratory state of the target object in the next respiratory cycle, the respiratory state space model is updated;

[0087] Based on the predicted respiratory state, the acquisition parameters of the sensor are adjusted, wherein the acquisition parameters of the sensor include at least one of the following: acquisition frequency, resolution and power.

[0088] The technical solution provided by the embodiments of the present disclosure can include the following beneficial effects:

[0089] By collecting the respiratory data of the user in the sleep state through the sensor, the respiratory state of the user in the next respiratory cycle is predicted, and the stimulation signal is dynamically adjusted according to the respiratory state of the user, so as to ensure that the stimulation signal can accurately stimulate the target tissue of the user and keep the respiratory tract of the user unobstructed, while avoiding the problem of fatigue of the target tissue of the user caused by long-time stimulation of the fixed stimulation signal, thereby improving the use experience of the user and the treatment effect on the sleep respiratory disorder of the user.

[0090] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0091] The accompanying drawings, which are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure and, together with the specification, serve to explain the principles of the present disclosure.

[0092] Figure 1 is a structure diagram of an electrical stimulation device according to an exemplary embodiment of the present disclosure;

[0093] Figure 2 is a schematic diagram of a respiratory signal containing an interference signal according to an exemplary embodiment of the present disclosure;

[0094] Figure 3 is a flowchart for determining respiratory frequency and phase according to an exemplary embodiment of the present disclosure;

[0095] Figure 4 is a flowchart of a method for determining a predicted respiratory state according to an exemplary embodiment of the present disclosure;

[0096] Figure 5is a flowchart of a method of determining a target stimulation signal according to an example embodiment of the present disclosure;

[0097] Figure 6 is a flowchart of a method of adjusting initial stimulation parameters according to an example embodiment of the present disclosure;

[0098] Figure 7 is a flowchart of a control method of an electrical stimulation device according to an example embodiment of the present disclosure;

[0099] Figure 8 is a flowchart of a control method of an electrical stimulation device according to an example embodiment of the present disclosure. DETAILED DESCRIPTION

[0100] The example embodiments will be described in detail with reference to the accompanying drawings. In the following description, the same numbers are used to denote the same elements, unless otherwise indicated. The embodiments described in the following example embodiments are not representative of all embodiments consistent with the present disclosure. Rather, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0101] The terminology used in the present disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the present disclosure. As used in the present disclosure and the appended claims, the singular forms "a," "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0102] It will be understood that, although the terms first, second, third, etc. can be used herein to describe various information, these terms are not intended to denote a temporal or chronological order. Rather, these terms are used merely as labels to identify particular information. For example, a first information can be termed a second information, and similarly, a second information can be termed a first information, without departing from the scope of the present disclosure. Depending on the context, the word "if' as used herein can be interpreted to mean "when" or "in response to determining" or "in response to a determination".

[0103] A sleep-disordered breathing patient is prone to have the respiratory tract blocked by surrounding tissues after the body muscles relax after entering sleep, and the respiratory tract is not smooth, thereby causing sleep-disordered breathing. When the obstructive respiratory disorder occurs, due to the negative pressure of the respiratory tract structure at the time of inhalation, it is difficult for air to enter the lungs to supplement oxygen, and thus the oxygen content in the patient's body is reduced due to the inability to be supplemented, and the carbon dioxide content in the body is increased, thereby affecting the sleep quality of the patient, and in severe cases, causing serious problems such as brain tissue damage.

[0104] In the related art, an electrical stimulation device can be used to output a stimulation signal to the nerve tissue or muscle tissue of the tongue of a user when the user is sleeping, so as to make the muscle related to the respiratory tract of the user contract, thereby keeping the respiratory tract smooth. However, the current stimulation method for sleep breathing disorders is an open-loop stimulation method or a stimulation method based on oral state feedback. In the currently applied method, the electrical stimulation device continuously outputs a stimulation signal in the corresponding mode to stimulate the tongue muscle of the user to keep contracting during sleep. However, long-time continuous stimulation during sleep of the user can easily cause muscle or nerve fatigue of the user, affect the effect of muscle stimulation, and also cause certain interference to the sleep of the user, thereby affecting the sleep quality of the user. At the same time, long-time continuous output of the stimulation signal can also cause high power consumption of the electrical stimulation device, thereby affecting the endurance of the electrical stimulation device.

[0105] Based on this, the present disclosure provides an electrical stimulation device, which can be a placement type electrical stimulation device, specifically, a tongue muscle stimulator, which electrically stimulates the muscle tissue of the tongue of a user by being placed in the oral cavity of the user. In addition, it can also be an implantable electrical stimulation device, specifically, a hypoglossal nerve stimulator, which electrically stimulates the hypoglossal nerve of a user by being implanted in the human body of the user. The electrical stimulation device can output a stimulation signal to the muscle of the tongue or the hypoglossal nerve of a user when the user is sleeping, so as to keep the respiratory tract of the user smooth in the sleep state. The electrical stimulation device comprises:

[0106] An electrode, which is in contact with a target object in a use state, and is used to electrically stimulate a target tissue of the target object.

[0107] A sensor, which is used to collect breathing data of the target object, the breathing data comprising at least one of the following: motion data, exhalation temperature data, thoracic pressure data, electrical impedance data, blood oxygen data, and posture data.

[0108] A controller, which is electrically connected with the sensor and the electrode, and is used to:

[0109] determine a current breathing state of the target object according to the breathing data;

[0110] determine a predicted breathing state of the target object in a next breathing cycle according to the current breathing state of the target object;

[0111] determine a target stimulation parameter according to the predicted breathing state;

[0112] control the electrode to output a stimulation signal based on the target stimulation parameter, so as to stimulate the target tissue.

[0113] In some embodiments, the structure diagram in the electric stimulation device can be as shown in Figure 1 The controller is in an electrical connection relationship with the electrodes and the sensor, respectively. The sensor collects the breathing data of the target object during the sleep process and transmits the breathing data to the controller. The controller determines the current breathing state of the target object according to the breathing data collected by the sensor, and then predicts the predicted breathing state of the target object in the next breathing cycle according to the current breathing state. According to the predicted breathing state of the target object, the target stimulation parameter for muscle stimulation or nerve stimulation of the target object is determined. Finally, the electrodes output the stimulation signal with the target stimulation parameter to stimulate the muscle or nerve of the target object, so that the tongue muscle of the target object contracts and the respiratory tract is smooth, avoiding respiratory disorders caused by respiratory tract obstruction of the target object.

[0114] The target tissue can be a tongue muscle tissue of the target subject, such as the genioglossus muscle, the geniohyoid muscle, the palatoglossus muscle, and the like, or can be the hypoglossal nerve of the target subject. When the electrical stimulation device is an implanted electrical stimulation device, the electrode is attached to the tongue muscle of the target subject, so that the stimulation signal output by the electrical stimulation device can stimulate the tongue muscle tissue of the target subject. When the electrical stimulation device is an implanted electrical stimulation device, the electrode is built-in to the hypoglossal position of the target subject, so that the electrical stimulation device can stimulate the hypoglossal nerve of the target subject. The sensor can include a motion sensor, a temperature sensor, a pressure sensor, an impedance sensor, an oxygen sensor, and a posture sensor. The motion sensor can collect motion data of the target subject during sleep, such as turning over, kicking legs, and the like. The motion sensor can also collect respiratory movements of the target subject during exercise, such as chest displacement data. The temperature sensor can be disposed at the nasal cavity of the target subject or at the nostril of the target subject, for collecting the temperature of the exhaled gas when the target subject exhales. The pressure sensor can be externally disposed outside the chest cavity of the target subject or implanted in the chest of the target subject, for collecting the chest cavity pressure data of the target subject to determine the lung pressure of the target subject, to determine the breathing amplitude and breathing rhythm of the target subject. The impedance sensor can be disposed at the chest and abdomen of the target subject, for collecting the electrical impedance change information of the chest and abdomen of the target subject, to determine the breathing rhythm of the target subject. The oxygen sensor is used to collect the oxygen concentration in the body of the target subject, and if the oxygen saturation in the body of the target subject is lower than a threshold value, it indicates that the target subject is breathing is blocked, and the external oxygen has not entered the lungs in time to supply the body of the target subject. The posture sensor can detect a continuous and significant change in the body of the target subject, such as a change in the sleeping posture, such as a change from supine to lateral recumbency. It should be noted that the breathing data at least includes all time series of the target subject in the current one breathing cycle, or includes breathing data of multiple breathing cycles in a historical time period, such as breathing data in the past ten minutes. The breathing cycle can be determined according to the breathing phase, from 0-180° phase of inspiration period, to 180-360° phase of expiration period, which can be regarded as a complete breathing cycle.

[0115] After the sensor collects the respiratory data of the target object, the respiratory data can be transmitted to the controller through a data transmission channel. After receiving the respiratory signal, the controller can predict the predicted respiratory state of the target object in the next breathing cycle according to the respiratory state space model. The predicted respiratory state can include the motion state, respiratory frequency, phase, amplitude, blood oxygen content, and respiratory weakening frequency and phase of the target object. According to the predicted respiratory state of the target object, the risk of respiratory tract obstruction of the target object, the inspiratory duration, expiratory duration, and blood oxygen saturation change of the next breathing cycle can be determined, and then the target stimulation parameters such as the stimulation output time, stimulation signal intensity, and stimulation signal duration can be determined. At the beginning of the next breathing cycle, the electrode controlled according to the target stimulation parameters outputs the stimulation signal to stimulate the muscle contraction of the target object, so that the respiratory tract of the target object in the next breathing cycle remains smooth. The electrode can be placed in the oral cavity of the target object when the electrical stimulation device is used, so that the stimulation signal output by the electrode can stimulate the target tissue of the target object. The stimulation signal can be a biphasic square wave with a frequency of 30-40 Hz and an amplitude of 0.5-3.0 mA.

[0116] In some embodiments, when the controller determines the predicted respiratory state of the target object in the next breathing cycle according to the respiratory data collected by the sensor, the current respiratory state of the target object can be determined according to the respiratory data, and then the predicted respiratory state of the target object in the next breathing cycle is determined according to the current respiratory state of the target object.

[0117] First, the respiratory state vector of the target object in the current breathing cycle can be constructed according to the respiratory data collected by the sensor, and then the respiratory state vector in the current breathing cycle is input into the preset respiratory state space model, and the predicted respiratory state is predicted based on the preset respiratory state space model, so as to obtain the predicted respiratory state in the next breathing cycle. The respiratory state vector includes motion state, respiratory frequency, phase, amplitude, blood oxygen content, respiratory weakening frequency, and respiratory weakening phase. Among them, the state transition matrix in the respiratory state space model can be determined according to the respiratory state data sequence in the historical time period to estimate the optimal matrix. For example, it can be determined by maximum likelihood estimation, expectation maximization algorithm or least squares method.

[0118] In some embodiments, the current respiratory state includes respiratory frequency, current respiratory amplitude, current respiratory phase, current respiratory weakening frequency, current respiratory weakening phase, current blood oxygen content, and current motion state. Determining the respiratory state of the target object in the current breathing cycle can first determine a plurality of respiratory indicators of the target object, which can specifically include:

[0119] According to the thoracic pressure data, electrical impedance data and exhalation temperature data in the respiratory data, a current respiratory frequency, a current respiratory amplitude and a current respiratory phase of the target object are determined; according to the thoracic pressure data, electrical impedance data, blood oxygen data and exhalation temperature data in the respiratory data, a current respiratory weakening frequency and a current respiratory weakening phase of the target object are determined; according to the blood oxygen data in the respiratory data, a current blood oxygen content of the target object is determined; and according to the motion data and posture data in the respiratory data, a current motion state of the target object is determined.

[0120] After the respiratory data collected by the sensors is acquired, the respiratory data can be preprocessed first, for example, the respiratory data can be synchronously sampled to ensure that all sensor data time stamps are aligned (using hardware synchronization or software interpolation), the respiratory data can also be processed, and different sensor signals can also be normalized to eliminate the influence of dimensions.

[0121] During different stages of the respiratory process, the thoracic pressure, thoracic electrical impedance and exhalation temperature all change with the respiratory process. For example, the thoracic pressure increases in negative pressure during inhalation and recovers during exhalation; the thoracic electrical impedance increases during inhalation (air entering reduces conductivity) and decreases during exhalation; the temperature during exhalation is significantly higher than that during inhalation (exhaled gas ≈ body temperature, inhaled gas ≈ room temperature). Therefore, based on the thoracic pressure data, electrical impedance data and exhalation temperature data in the respiratory data, the current respiratory frequency, current respiratory amplitude and current respiratory phase of the target object can be determined. For example, according to the electrical impedance data during the respiratory process, the characteristics of the electrical impedance data are extracted by spectral analysis method, so as to determine the current respiratory frequency, or the peak value test method can also be used to analyze the minimum values in the pressure data and exhalation temperature, and according to the interval between adjacent minimum values, the current respiratory period is determined, and then the current respiratory frequency is determined, and further, multi-sensor cross verification can also be used to compare the frequencies calculated by the three signals, and the abnormal value is proposed, so as to determine the current respiratory frequency.

[0122] It should be noted that in the sleep state, the target object may cause the respiratory signal collected by the motion sensor to be weak due to body position change, and at the same time cause the environmental noise in the respiratory signal to seriously interfere, for example Figure 2 As shown in the schematic diagram, the respiratory signal includes obvious noise interference, causing the respiratory cycle boundary in the respiratory signal to be blurred. In this case, it will further cause the estimation accuracy of the respiratory frequency and the respiratory phase to be low, and if the estimation accuracy of the respiratory frequency and the respiratory phase is low, it will cause the accuracy of the target stimulation parameter to be low when the target stimulation parameter is determined according to the current respiratory state, and further cause the stimulation accuracy of the hypoglossal nerve or the tongue muscle tissue of the target object to be low, and the hypoglossal nerve or the tongue muscle tissue of the target object cannot be accurately stimulated.

[0123] Based on this, in some embodiments, feature extraction can be performed on the respiratory signal carrying the interference signal to improve the accuracy of determining the respiratory frequency and the respiratory phase. For details, please refer to the flowchart shown in FIG. 1, which includes the following steps: Figure 3

[0124] S301, in response to determining that the respiratory signal of the target object contains an interference signal, determining a sampling window according to a preset respiratory frequency range and a preset respiratory motion feature.

[0125] S302, performing feature extraction on the respiratory signal in the sampling window according to the preset respiratory motion feature to determine a feature weight.

[0126] S303, determining an analog respiratory signal according to a reference respiratory frequency and a reference respiratory phase.

[0127] S304, adjusting the reference respiratory frequency and the reference respiratory phase according to the feature weight to minimize the residual error between the respiratory signal and the analog respiratory signal, and determining the current respiratory frequency and the current respiratory phase in the current respiratory state.

[0128] The preset respiratory frequency range can be determined according to the historical respiratory data of the target object, and the preset respiratory motion feature can be determined by performing feature extraction on the historical respiratory data of the target object. The respiratory signal can be determined according to the motion data in the respiratory data, for example, the respiratory signal can be determined according to the chest displacement data of the target object. According to the respiratory feature in the respiratory signal, it can be determined whether there is an interference signal in the respiratory signal. For example, when there are data points in the respiratory signal that exceed the preset amplitude range, it can be determined that there is an interference signal in the respiratory signal. Or, if the change rate (slope) between adjacent sampling points in the respiratory signal exceeds the preset threshold, it can be determined that there is an interference signal in the respiratory signal.

[0129] In the case where it is determined that the respiratory signal of the target object contains an interference signal, the length of the sampling window can be determined according to the preset respiratory frequency range and the preset respiratory motion feature, so that the sampling window contains a certain number of respiratory cycles. For example, if the preset respiratory frequency range is 3-6 times per minute, the length of the sampling window can be determined as 100s, so that the sampling window contains at least 5 respiratory cycles. For another example, according to the preset respiratory motion feature, the sampling window in the respiratory signal contains a selected smooth, periodic and sinusoidal motion. By selecting the sampling window, the calculation resources can be saved in the invalid frequency band, the interference signal in the sampling window can be preliminarily reduced, and the subsequent calculation efficiency can be improved.

[0130] ​After the sampling window is determined, the respiratory signal in the sampling window can be feature extracted according to the preset respiratory motion feature to determine a feature weight. Specifically, a filter can be designed according to the preset respiratory motion feature, and the respiratory signal in the sampling window can be convoluted by the filter to enhance the signal component (i.e., the respiratory signal) similar to the preset respiratory motion feature in the sampling window and weaken the dissimilar component (i.e., the noise), thereby improving the signal-to-noise ratio of the respiratory signal in the sampling window. After the respiratory signal in the sampling window is convoluted, a weight feature vector of the respiratory signal in the sampling window can be obtained, and the feature weight represents the weight of different respiratory frequencies.

[0131] The reference respiratory frequency can be determined according to the preset respiratory frequency range, for example, by selecting a respiratory frequency in the preset respiratory frequency range. The reference respiratory frequency can also be determined according to the feature weight, for example, by determining the respiratory frequency corresponding to the maximum weight value in the feature weight as the reference respiratory frequency. After the respiratory frequency is determined, a corresponding reference respiratory phase can be selected according to the respiratory frequency, and the reference respiratory phase can also be determined according to the preset respiratory motion feature. After the reference respiratory frequency and the reference respiratory phase are determined, a respiratory model can be constructed according to the reference respiratory frequency and the reference respiratory phase, and a simulated respiratory signal can be obtained according to the respiratory model. The respiratory model can be a sine wave function, and the simulated respiratory signal can be obtained by substituting the reference respiratory frequency and the reference respiratory phase into the sine wave function.

[0132] The reference respiratory frequency and the reference respiratory phase are adjusted according to the feature weight to minimize the residual error between the respiratory signal and the simulated respiratory signal, and the current respiratory frequency and the current respiratory phase in the current respiratory state are determined.

[0133] Then, the residual error between the respiratory signal and the simulated respiratory signal is calculated, and a cost function is constructed according to the feature weight and the residual error between the respiratory signal and the simulated respiratory signal. The values of the reference respiratory frequency and the reference respiratory phase are iteratively adjusted by minimizing the cost function until the cost function converges, and the reference respiratory frequency at this time is determined as the current respiratory frequency in the current respiratory state, and the reference respiratory phase at this time is determined as the current respiratory phase in the current respiratory state. In some embodiments, the residual error between the respiratory signal and the simulated respiratory signal can be minimized by algorithms such as Gradient Descent, Gauss-Newton, or Levenberg-Marquardt to obtain the current respiratory frequency and the current respiratory phase.

[0134] In determining the respiratory amplitude, the respiratory amplitude can be determined according to the weighted calculation of the peak value in the electrical impedance data and the peak value in the thoracic pressure data, and the exhaled air volume can be determined according to the integral area of the respiratory temperature data, so as to determine the respiratory amplitude. In determining the respiratory phase, the respiratory cycle can be segmented based on a pre-constructed respiratory cycle template, for example, the rising edge (exhalation start) of the respiratory temperature data is used as the cycle starting point, and then the key point detection is performed, for example, the end of inspiration point is determined according to the peak value time of the thoracic pressure data and / or the electrical impedance data, and the end of exhalation point is determined according to the time when the exhalation temperature data falls back to the baseline, so as to determine the respiratory phase.

[0135] According to the thoracic pressure data, the electrical impedance data, the blood oxygen data and the exhalation temperature data in the respiratory data, the respiratory weakening frequency and the respiratory weakening phase of the target object are determined. The respiratory weakening frequency refers to the frequency of abnormal breathing patterns of the target object caused by repeated collapse of the upper airway during sleep, including the apnea frequency and / or the hypopnea frequency. The apnea frequency refers to the time when the respiratory airflow is completely stopped and exceeds a threshold, but the thoraco-abdominal breathing movement still exists (caused by obstruction). The apnea frequency can be determined according to the number of apneas per hour of sleep, for example, if the target object has 30 apneas per hour, the apnea frequency is 30 times per hour. The specific respiratory data collected by the sensor is that the exhalation temperature data disappears (indicating that there is no airflow in the nasal cavity), but the thoracic pressure data and / or the electrical impedance data indicate that the target object is in a breathing state, such as a reduced thoracic pressure fluctuation amplitude (reduced inspiration effort) / reduced electrical impedance change amplitude (insufficient chest expansion). At the same time, the blood oxygen data indicates that the blood oxygen saturation in the target object decreases. The hypopnea frequency refers to the partial reduction of respiratory airflow and lasts more than a threshold, accompanied by a decrease in blood oxygen saturation or micro-awakening. The hypopnea frequency can be determined according to the number of hypopneas per hour of sleep, for example, if there are 20 hypopneas per hour, the hypopnea frequency is 20 times per hour. The specific respiratory data collected by the sensor is that the exhalation temperature peak value is reduced or the plateau period is shortened (airflow is reduced), but the thoracic pressure fluctuation amplitude is reduced (inspiration effort is reduced) / electrical impedance change amplitude is reduced (chest expansion is insufficient), and at the same time, the blood oxygen data indicates that the blood oxygen saturation in the target object decreases.

[0136] The respiratory weakening phase refers to a specific stage of reduced ventilation efficiency in a single respiratory cycle due to partial or complete collapse of the upper airway, mainly including inspiratory obstruction, i.e., the upper airway collapses during inspiration, airflow is limited but respiratory effort exists, and expiratory limitation, i.e., airflow is prolonged due to airway narrowing or dynamic collapse during expiration. The detection method of the inspiratory weakening phase needs to perform cycle segmentation and feature extraction steps. First, the temperature rise of the exhalation is used to mark the beginning of the exhalation (cycle start point), and the temperature falls from the lowest point to the peak value of the electrical impedance / pressure as the inspiratory phase. Then, according to the chest pressure data features, electrical impedance data features, and blood oxygen data features, the inspiratory weakening data is determined, wherein the chest pressure data features include enhanced negative pressure fluctuations (sawtooth waveforms reflecting efforts to resist obstruction), the electrical impedance data features include a slow impedance rise speed (due to limited airflow, limited chest expansion), and the blood oxygen data features include a decrease in blood oxygen saturation. The expiratory weakening phase needs to first locate the expiratory phase according to the time of the peak value of the chest pressure data, the time of the peak value of the electrical impedance data, or the time of the exhalation temperature data falling to the baseline, and then determine the expiratory weakening phase according to the exhalation temperature data plateau, the chest pressure exhalation not returning to the baseline, and other data features.

[0137] And the current blood oxygen content of the target object can be determined according to the blood oxygen data in the respiratory data. And the motion state of the target object can be determined according to the motion data and the posture data in the respiratory data. The motion state represents the body movement or posture of the target object during sleep. The number of times of turning over, the acceleration standard deviation (reflecting the amplitude of movement) can be determined according to the time domain features in the motion data. The frequency domain features can be extracted according to the Fourier transform to determine the movement of the target object, such as the typical frequency of 0.1-0.3 Hz of the turning over movement. The continuity of the movement can also be determined according to the periodicity features. The spatial relationship of the body movement of the target object can also be extracted according to the posture data, and then the sleep posture of the target object can be determined, for example, the prone position can be identified according to the included angle between the midpoint of the shoulder and the key point of the nose (the included angle is less than a critical value).

[0138] After obtaining the current respiratory state of the target object, the controller can predict the predicted respiratory state of the target object in the next respiratory cycle based on the current respiratory state of the target object. The method for determining the predicted respiratory state is shown in the flowchart of Figure 4 The flowchart includes:

[0139] S401, feature extraction is performed on the current respiratory state to obtain a feature vector.

[0140] S402, based on the state vector corresponding to the current respiratory state and the feature vector, the predicted respiratory state of the target object in the next respiratory cycle is predicted through a pre-constructed respiratory state space model.

[0141] The state transition matrix in the respiratory state space model can be determined based on a respiratory state data sequence in a historical time period. The current respiratory state is extracted to obtain a feature vector corresponding to the current respiratory state. Then, the current respiratory state and the feature vector are input into a pre-constructed respiratory state space model to predict the respiratory state of the next respiratory cycle. In an embodiment, the calculation method of the predicted respiratory state can refer to formula (1):

[0142]

[0143] (1)

[0144] wherein, represents the predicted respiratory state, represents the current respiratory state, represents the state transition matrix, represents the feature vector, and G is a weight matrix.

[0145] The weight matrix is used to map the feature vector to the state space, and the elements thereof reflect the contribution strength of different features to the next cycle state. The weight matrix can explicitly quantify the influence of the features on the state, and can include prior information related to the respiratory cycle, amplitude, blood oxygen content, etc., such as that a prolonged respiratory cycle corresponds to a reduced frequency, a decreased respiratory amplitude corresponds to a reduced blood oxygen saturation, a rapid decrease in blood oxygen saturation corresponds to a reduced respiratory frequency, a current reduced respiratory frequency corresponds to a continuously weakened next respiratory cycle, and the like.

[0146] After determining the predicted respiratory state of the target object in the next respiratory cycle, the target stimulation parameter can be determined according to the predicted respiratory state. However, during sleep, the user will change the body movement and body position, which will cause a certain displacement of the sensor or even a failure of the sensor, thereby causing the respiratory signal to be disturbed by a certain noise, and further affecting the detection accuracy of the respiratory state of the patient, and finally affecting the output accuracy of the stimulation signal.

[0147] Based on this, the embodiments of the present disclosure further provide a method for determining a target stimulation signal, which can refer to Figure 5 which includes:

[0148] S501, determining an initial stimulation parameter of the next respiratory cycle according to the predicted respiratory state;

[0149] S502, determining posture change data of the target object according to the respiratory data collected by the sensor, wherein the posture change data comprises at least one of the following: sleep position data, sleep action data, and oral-nasal breathing mode data;

[0150] S503, adjusting the initial stimulation parameter based on the posture change data to determine the target stimulation parameter.

[0151] The initial stimulation parameter comprises a stimulation output time, a stimulation duration, and a stimulation signal intensity. The output time is used to determine a time for outputting a stimulation signal in a next breathing cycle, the stimulation duration is used to determine a duration of the stimulation signal output by the electrical stimulation device in the next breathing cycle, and the stimulation signal intensity is used to determine an amplitude value of the stimulation signal output by the electrical stimulation device in the next breathing cycle.

[0152] In some embodiments, the process of determining the initial stimulation parameter comprises:

[0153] determining the stimulation output time based on a preset time bias and a breathing start time in the predicted breathing state.

[0154] determining the stimulation duration based on a dynamic time bandwidth of the respiratory signal and a length of the predicted breathing state.

[0155] determining the stimulation signal intensity based on a breathing amplitude and a blood oxygen content in the predicted breathing state.

[0156] The initial stimulation parameter comprises a stimulation output time, a stimulation duration, and a stimulation signal intensity. The output time is used to determine a time for outputting a stimulation signal in a next breathing cycle, the stimulation duration is used to determine a duration of the stimulation signal output by the electrical stimulation device in the next breathing cycle, and the stimulation signal intensity is used to determine an amplitude value of the stimulation signal output by the electrical stimulation device in the next breathing cycle.

[0157] After obtaining the predicted breathing state, the next breathing state cycle can be determined according to the predicted breathing state. For details, refer to formula (2):

[0158] (2)

[0159] wherein, is the breathing state cycle, which is calculated by a weighted average of each dimension in the state The weight of the kth dimension is represented by , and the next breathing state cycle can be obtained.

[0160] ​In an embodiment, the stimulation output time point can be determined based on a preset time offset and a breathing start time point in the predicted breathing state. It should be noted that the stimulation signal can be sent in advance before the start of the next breathing cycle, and the preset time offset can be determined according to a neural conduction delay and a muscle mechanical response delay, and can generally take a value of 200 ms to 500 ms, and can be calibrated according to different target objects. According to the breathing state cycle determined in the predicted breathing state, the start time point of the next breathing cycle can be determined. Then, before the start time point of the next breathing cycle, the stimulation output time point is determined based on the preset time offset.

[0161] The dynamic time bandwidth refers to a time domain window corresponding to a frequency range of effective physiological changes of the breathing signal (such as 0.1-2 Hz corresponding to 0.5-10 seconds), and the main frequency bandwidth can be determined by the power spectral density (PSD) of the breathing signal. The length of the predicted breathing state is the breathing state cycle of the next time. After determining the next breathing state cycle, the stimulation duration can be determined according to the method shown in formula (3) as follows:

[0162] (3)

[0163] wherein h is the stimulation duration, is the dynamic time bandwidth.

[0164] In determining the stimulation signal intensity, the breathing amplitude and the blood oxygen content can be fitted by a polynomial to obtain the stimulation signal intensity, and details can be referred to formula (4):

[0165] (4)

[0166] wherein wherein , is a polynomial coefficient, and n is the degree of the polynomial, is the breathing amplitude, is the blood oxygen content.

[0167] In order to further improve the accuracy of the stimulation signal output by the electrical stimulation device, the interference signal in the breathing data collected by the sensor can be estimated to improve the accuracy of the predicted breathing state. Therefore, the posture change data of the target object can be determined according to the breathing data collected by the sensor, and the initial stimulation parameters are corrected according to the posture change data of the target object. The posture change data includes at least one of the following: sleep position data, sleep action data, and oral-nasal breathing mode data of the target object.

[0168] In some embodiments, sleep posture data of the target object can be determined according to posture data and electrical impedance data in the respiratory data. The sleep posture data of the target object refers to the transition of the body posture of the target object during sleep (e.g., supine, lateral, prone, etc.). In determining the sleep posture change of the target object, the posture data detected by the accelerometer can be used to extract the values of the body of the target object in the X, Y, and Z axes, the change information of the electrical impedance data, and the predetermined determination condition of the posture change to determine the sleep posture change of the target object. For example, the sleep posture of the target object can be determined according to the static gravity component in the posture data, in which supine corresponds to Z axis ≈ 1g and X / Y ≈ 0g; left lateral corresponds to X axis ≈ -1g and Y / Z ≈ 0g; and prone corresponds to Z axis ≈ -1g. Alternatively, the posture change of the target object can be determined by dynamic rollover detection, for example, the peak value of the Y-axis angular velocity of the gyroscope (typical rollover angular velocity > 50° / s). The decrease of the abdominal impedance in the electrical impedance data (due to the compression of the abdomen, the electrode contact is improved) can represent that the target object has a transition from supine to lateral.

[0169] In some embodiments, sleep movement data of the target object can be determined according to movement data and thoracic pressure data in the respiratory data. The sleep movement change refers to the body movement caused by limb movement, turning over, or short-term micro-awakening of the target object during sleep. The time when the target object starts to move and the time when the movement ends can be determined according to the movement data, and the respiratory state of the target object can be further determined according to the thoracic pressure data, for example, if the pressure value reaches a peak after the movement data represents that the target object starts to move, it represents that the limb of the target object is moving. For another example, if the thoracic pressure data changes but the movement data represents that the target object does not have limb movement, it can be determined that the target object may only cough or the movement sensor has displacement.

[0170] In some embodiments, oral-nasal breathing mode data of the target object can be determined according to exhalation temperature data in the respiratory data and a predetermined temperature change rule. The oral-nasal breathing mode refers to the dynamic behavior of the target object in which the nasal cavity and the oral cavity are alternately used as the main ventilation channel during breathing. The temperature change rule represents the change rule of the exhalation temperature of the target object in different breathing states. For example, in the nasal breathing state, the peak value of the exhalation temperature is high (≈34-36°C, nasal cavity warming), and the temperature rising / falling slope is gentle (nasal airflow resistance is large). In the oral breathing state, the peak value of the exhalation temperature is low (≈30-32°C, oral cavity is not sufficiently warmed), and the temperature rises and falls sharply (airflow speed is fast). Therefore, the oral-nasal breathing mode change of the target object can be determined according to the exhalation temperature data of the target object.

[0171] After the posture change data of the target object is determined, the initial stimulation parameter can be adjusted according to the posture change data of the target object. For details, please refer to Figure 6 the flowchart shown in the figure:

[0172] S601, based on the posture change data, determining the confidence of the initial stimulation parameter at each time in the next breathing cycle.

[0173] S602, according to the confidence, determining the weight of the initial stimulation parameter.

[0174] S603, according to the weight of the initial stimulation parameter, adjusting the initial stimulation parameter to determine the target stimulation parameter.

[0175] In some embodiments, the confidence of the posture change data can be evaluated according to a breathing state confidence evaluation model to obtain the confidence of the initial stimulation parameter at each time in the next breathing cycle, and then the confidence is determined as the weight of the initial stimulation parameter. Finally, the weight of the initial stimulation parameter is multiplied by the initial stimulation parameter to determine the target stimulation parameter based on the initial stimulation parameter.

[0176] In an embodiment, when determining the confidence of the initial stimulation parameter at each time in the next breathing cycle, the prior feature of the posture change data information can be obtained first; then the prior feature of the posture change data information and the posture change data information are extracted; finally, according to the feature extraction result of the prior feature and the feature extraction result of the posture change data, the predicted breathing state is evaluated by the confidence evaluation model to determine the confidence of the initial stimulation parameter at each time in the next breathing cycle.

[0177] The prior feature of the posture change data information can be obtained based on historical data or population statistics, which represents the data distribution corresponding to the posture change data under different breathing states. When the prior feature of the posture change data and the posture change data are extracted, the feature extraction can be performed by a convolutional neural network to obtain the feature extraction result of the prior feature of the posture change data and the feature extraction result of the posture change data. Finally, the predicted breathing state can be evaluated by the confidence evaluation model to determine the confidence of the initial stimulation parameter at each time in the next breathing cycle. For example, the confidence of the initial stimulation parameter at each time in the next breathing cycle can be determined according to formula (5) as follows:

[0178] (5)

[0179] wherein, is the confidence is the predicted breathing state, is the sleep posture data, sleep posture data, mouth-nose breathing mode data, a breathing state confidence evaluation model, a preset prior feature sequence for each dimension. cov represents feature extraction of data by a convolutional neural network.

[0180] Through the breathing state confidence evaluation model, the prior feature correlation of the predicted breathing state can be estimated in combination with the prior distribution features of the sleep posture data and the sleep posture data of the target object at the current moment, to obtain the confidence of the initial stimulation parameter at each moment in the next breathing cycle.

[0181] After obtaining the confidence, the initial stimulation parameter can be adjusted according to formula (6) to obtain the target stimulation parameter, as follows:

[0182] (6)

[0183] wherein, the target stimulation parameter, the initial stimulation parameter.

[0184] It should be noted that the initial stimulation parameter includes parameters such as stimulation output time, stimulation duration, and stimulation signal intensity, and the target stimulation parameter obtained after adjustment according to the confidence also includes parameters such as stimulation output time, stimulation duration, and stimulation signal intensity.

[0185] After obtaining the target stimulation parameter, the controller can control the electrode to output a stimulation signal according to the target stimulation parameter, so as to electrically stimulate the hypoglossal nerve or the tongue muscle tissue of the target object, thereby ensuring that the stimulation signal can accurately stimulate the muscle of the user and keep the airway of the user unobstructed, and improving the sleep experience of the user.

[0186] In some embodiments, the controller can also correct the breathing state space model and correct the collection parameters of the plurality of sensors. For example, based on the difference between the actual breathing state and the predicted breathing state of the target object in the next breathing cycle, the breathing state space model is updated. When predicting the breathing state of the next cycle, the Kalman filter can be used to observe the breathing state of the target object, so that at the end of the next breathing cycle k, the actual breathing state can be obtained through the breathing data collected by the sensor. The Kalman filter combines the predicted breathing state and the actual breathing state (weighted according to the uncertainty of prediction and observation) to produce a better breathing state space model that integrates information. This updated breathing state space model can be used as the basis for predicting the breathing state at time k+1. This process is repeated continuously to achieve continuous prediction and updating of the breathing state space model.

[0187] By continuously predicting and updating the respiratory state space model, the respiratory state space model can effectively fuse the current respiratory state information and the system dynamic model, improve the prediction accuracy of the next period respiratory state, and further improve the accuracy of the output stimulation signal.

[0188] In order to reduce the power consumption of the electrical stimulation device and improve the endurance of the electrical stimulation device, after the next breathing period ends, the acquisition parameters of the sensor can also be adjusted based on the predicted respiratory state. The acquisition parameters of the sensor include at least one of the following: acquisition frequency, resolution, and power. The update of the acquisition frequency can refer to formula (5):

[0189] (5)

[0190] wherein, indicates the acquisition frequency, and q indicates the effective sampling frequency coefficient.

[0191] The update method of the resolution can refer to formula (6):

[0192] (6)

[0193] wherein, indicates the resolution, and is a resolution adjustment coefficient.

[0194] The update method of the power can refer to formula (7):

[0195] (7)

[0196] wherein, M is a state reference value in a normal respiratory state, which can be adaptively adjusted according to different populations, is a weight coefficient, which is used to convert the norm difference into an actual power value.

[0197] The embodiments of the present disclosure predict the respiratory state of the user in the next breathing period by collecting the respiratory data of the user in the sleep state through the sensor, and dynamically adjust the stimulation signal according to the respiratory state of the user, so as to ensure that the stimulation signal can accurately stimulate the hypoglossal nerve or the tongue muscle tissue of the user, keep the respiratory tract of the user unobstructed, and avoid the problem of muscle fatigue of the user caused by long-time stimulation of the fixed stimulation signal, thereby improving the use experience of the user and the treatment effect on sleep apnea of the user.

[0198] The embodiments of the present disclosure also provide a control method of an electrical stimulation device, which is applied to the electrical stimulation device. The method steps are described in Figure 7 , which include:

[0199] S701, obtaining breathing data of a target object based on a sensor.

[0200] S702, determining a current breathing state of the target object according to the breathing data.

[0201] S703, determining a predicted breathing state of the target object in a next breathing cycle according to the current breathing state of the target object.

[0202] S704, determining a target stimulation parameter by a controller according to the predicted breathing state.

[0203] S705, controlling an electrode to output a stimulation signal based on the target stimulation parameter by the controller.

[0204] The breathing data includes at least one of motion data, exhalation temperature data, thoracic pressure data, electrical impedance data, blood oxygen data, and posture data. The electrical stimulation device can obtain the breathing data of the target object wearing or implanted with the electrical stimulation device based on the sensor to obtain the breathing data including the motion data, the exhalation temperature data, the thoracic pressure data, the electrical impedance data, the blood oxygen data, and the posture data. Then, based on the breathing data, the current breathing state of the target object is determined by a breathing state space model in the controller, and the breathing state of the target object in the next breathing cycle is predicted to obtain the predicted breathing state. Further, according to the predicted breathing state, the target stimulation parameter in the next breathing cycle is calculated and determined, and the electrode is controlled to output the stimulation signal according to the target stimulation parameter, so that the hypoglossal nerve or the tongue muscle tissue of the target object is stimulated by the stimulation signal, the tongue muscle is contracted when stimulated, and the user's airway is kept unobstructed. At the same time, the problem of muscle fatigue caused by long-term stimulation of the fixed stimulation signal is avoided, the use experience of the user is improved, and the treatment effect on the sleep breathing disorder of the user is improved.

[0205] In some embodiments, the current breathing state includes a breathing frequency, a current breathing amplitude, a current breathing phase, a current breathing weakening frequency, a current breathing weakening phase, a current blood oxygen content, and a current motion state.

[0206] The determining the current breathing state of the target object according to the breathing data includes:

[0207] According to the thoracic pressure data, the electrical impedance data, and the exhalation temperature data in the breathing data, the current breathing frequency, the current breathing amplitude, and the current breathing phase of the target object are determined.

[0208] According to the thoracic pressure data, the electrical impedance data, the blood oxygen data, and the exhalation temperature data in the breathing data, the current breathing weakening frequency and the current breathing weakening phase of the target object are determined.

[0209] determine a current blood oxygen content of the target object according to blood oxygen data in the respiration data;

[0210] determine a current motion state of the target object according to motion data and posture data in the respiration data.

[0211] In some embodiments, the determining the current respiration state of the target object according to the respiration data comprises:

[0212] in response to determining that there is an interference signal in the respiration signal of the target object, determining a sampling window according to a preset respiration frequency range and a preset respiration motion feature, wherein the respiration signal is determined according to motion data in the respiration data;

[0213] extracting a feature weight of the respiration signal in the sampling window according to the preset respiration motion feature;

[0214] determining a simulated respiration signal according to a reference respiration frequency and a reference respiration phase;

[0215] adjusting the reference respiration frequency and the reference respiration phase according to the feature weight to minimize a residual error between the respiration signal and the simulated respiration signal, and determining a current respiration frequency and a current respiration phase in the current respiration state.

[0216] In some embodiments, the determining the predicted respiration state of the target object in the next respiration cycle according to the current respiration state of the target object comprises:

[0217] based on a pre-constructed respiration state space model;

[0218] extracting a feature vector from the current respiration state;

[0219] predicting the predicted respiration state of the target object in the next respiration cycle through the respiration state space model based on a state vector corresponding to the current respiration state and the feature vector.

[0220] In some embodiments, the determining the target stimulation parameter according to the predicted respiration state comprises:

[0221] determining an initial stimulation parameter of the next respiration cycle according to the predicted respiration state;

[0222] determining posture change data of the target object according to the respiration data collected by the sensor, wherein the posture change data comprises at least one of the following: sleep body position data, sleep action data, and oral-nasal breathing mode data;

[0223] adjust the initial stimulation parameter based on the posture change data to determine the target stimulation parameter.

[0224] In some embodiments, the target stimulation parameter comprises a stimulation output time, a stimulation duration, and a stimulation signal intensity.

[0225] The determining of the initial stimulation parameter of the next breathing cycle according to the predicted breathing state comprises:

[0226] determining the stimulation output time based on a preset time offset and a breathing start time in the predicted breathing state;

[0227] determining the stimulation duration based on a dynamic time bandwidth of the breathing signal and a duration of the predicted breathing state;

[0228] determining the stimulation signal intensity based on a breathing amplitude and a blood oxygen content in the predicted breathing state.

[0229] In some embodiments, the adjusting of the initial stimulation parameter based on the posture change data to determine the target stimulation parameter comprises:

[0230] determining a confidence degree of the initial stimulation parameter at each time in the next breathing cycle based on the posture change data;

[0231] determining a weight of the initial stimulation parameter according to the confidence degree;

[0232] adjusting the initial stimulation parameter according to the weight of the initial stimulation parameter to determine the target stimulation parameter.

[0233] In some embodiments, the determining of the confidence degree of the initial stimulation parameter at each time in the next breathing cycle based on the posture change data comprises:

[0234] obtaining a prior feature of the posture change data information;

[0235] extracting features of the prior feature of the posture change data information and the posture change data information;

[0236] evaluating the predicted breathing state by a confidence degree evaluation model according to a feature extraction result of the prior feature and a feature extraction result of the posture change data to determine the confidence degree of the initial stimulation parameter at each time in the next breathing cycle.

[0237] In some embodiments, the method further comprises:

[0238] updating the breathing state space model based on a difference between an actual breathing state in the next breathing cycle of the target object and the predicted breathing state.

[0239] adjusting, based on the predicted respiratory state, a collection parameter of the sensor, wherein the collection parameter of the sensor comprises at least one of a collection frequency, a resolution, and a power.

[0240] In an embodiment, the method of controlling the electrical stimulation signal by the electrical stimulation device can refer to the flowchart shown in FIG. 6. Figure 8

[0241] In step 1, the sensor collects the respiratory data of the target object wearing the electrical stimulation device, wherein the respiratory data comprises at least one of the following: motion data, exhalation temperature data, thoracic pressure data, electrical impedance data, blood oxygen data, and posture data.

[0242] In step 2, the sensor transmits the respiratory data to the controller, and the controller calls the respiratory state space model to predict the respiratory state of the target object in the next respiratory cycle according to the respiratory data collected by the sensor, to obtain a predicted respiratory state.

[0243] In step 3, the initial stimulation parameter is determined according to the predicted respiratory state.

[0244] In step 4, the posture change data of the target object during sleep is determined according to the respiratory data, and then the confidence of the initial stimulation parameter at each time in the next respiratory cycle is determined based on the posture change data.

[0245] In step 5, the initial stimulation parameter is adjusted according to the confidence to determine the target stimulation parameter.

[0246] In step 6, the electrode outputs the stimulation signal according to the target stimulation parameter.

[0247] In step 7, the controller optimizes the collection parameter of the sensor according to the predicted respiratory state, which can include the collection frequency, the resolution, the power, and the like.

[0248] In step 8, after the electrode outputs the stimulation signal in the new respiratory cycle, the sensor continues to collect the respiratory data of the target object in the new respiratory cycle according to the updated collection parameter. The controller determines the actual respiratory state of the new respiratory cycle according to the respiratory data in the new respiratory cycle, and updates the parameters in the respiratory state space model according to the actual respiratory state of the new respiratory cycle and the predicted respiratory state of the new respiratory cycle in the previous respiratory cycle, so that the respiratory state space model can accurately predict the respiratory state of the next respiratory cycle.

[0249] ​After the parameter updating in the respiratory state space model is completed, the next cycle of respiratory state can be predicted according to the new respiratory state space model, and the target stimulation parameter of the next cycle is determined, and the electrode outputs the stimulation current according to the target stimulation parameter.

[0250] The respiratory data of the user in the sleep state is collected through the sensor, the respiratory state of the user in the next respiratory cycle is predicted, and the stimulation signal is dynamically adjusted according to the respiratory state of the user, so as to ensure that the stimulation signal can accurately stimulate the tongue muscle tissue or hypoglossal nerve of the user, keep the respiratory tract of the user unobstructed, and avoid the problem that the tongue muscle tissue or hypoglossal nerve of the user is tired due to long-time stimulation of the fixed stimulation signal, thereby improving the use experience of the user and the treatment effect on sleep apnea of the user. At the same time, the respiratory space state model and the sensor collection parameter are updated according to the predicted respiratory state and the actual respiratory state, which can improve the accuracy of predicting the respiratory state of the next cycle, and further improve the output accuracy of the stimulation signal.

[0251] For each of the method embodiments described above, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the disclosure is not limited by the order of the described actions, because according to the disclosure, certain steps can be performed in other order or simultaneously.

[0252] Secondly, those skilled in the art should know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the disclosure.

[0253] The above describes specific embodiments of the disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than the order described in the embodiments and still achieve desirable results. In addition, the processes depicted in the figures do not necessarily require the particular order shown or sequential order to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous or possible.

[0254] Those skilled in the art will readily appreciate other implementation of the disclosure upon considering the specification and practicing the application claimed herein. The disclosure is intended to cover any variations, uses, or adaptations of the disclosure following the general principles thereof and including its general principles and including those not expressly set forth in the specification or claims. The specification and examples are to be regarded as exemplary only, and the true scope and spirit of the disclosure are indicated by the following claims.

[0255] It is to be understood that the present disclosure is not limited to the precise construction herein described and as shown in the drawings, and that various modifications and changes can be made by those skilled in the art without departing from the scope thereof. The scope of the present disclosure is limited only by the claims appended hereto.

[0256] The above description is merely the preferred embodiment of this disclosure, and is not used to limit this disclosure. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this disclosure should be included in the scope of this disclosure.

Claims

1. An electrical stimulation device, characterized by The electric stimulation device comprises: an electrode, which is in contact with a target object in a use state, for electrically stimulating a target tissue of the body of the target object; a sensor for collecting breathing data of the target object, the breathing data comprising at least one of motion data, exhalation temperature data, thoracic pressure data, electrical impedance data, blood oxygen data, and posture data; a controller, which is electrically connected to the sensor and the electrode, for: determining a current breathing state of the target object according to the breathing data; determining a predicted breathing state of the target object in a next breathing cycle according to the current breathing state of the target object; determining a target stimulation parameter according to the predicted breathing state; controlling the electrode to output a stimulation signal based on the target stimulation parameter to stimulate the target tissue; the determination of the predicted breathing state of the target object in the next breathing cycle according to the current breathing state of the target object comprises: feature extraction on the current breathing state to obtain a feature vector; prediction of the predicted breathing state of the target object in the next breathing cycle based on a state vector corresponding to the current breathing state and the feature vector through a pre-constructed breathing state space model; the determination of the target stimulation parameter according to the predicted breathing state comprises: determination of an initial stimulation parameter of the next breathing cycle according to the predicted breathing state; determination of posture change data of the target object according to the breathing data collected by the sensor, wherein the posture change data comprises at least one of sleep body position data, sleep action data, and oral-nasal breathing mode data; adjustment of the initial stimulation parameter based on the posture change data to determine the target stimulation parameter.

2. The electrical stimulation device of claim 1, wherein, The current breathing state comprises a breathing frequency, a current breathing amplitude, a current breathing phase, a current breathing weakening frequency, a current breathing weakening phase, a current blood oxygen content, and a current motion state. The determination of the current breathing state of the target object according to the breathing data comprises: determination of a current breathing frequency, a current breathing amplitude, and a current breathing phase of the target object according to thoracic pressure data, electrical impedance data, and exhalation temperature data in the breathing data; determination of a current breathing weakening frequency and a current breathing weakening phase of the target object according to thoracic pressure data, electrical impedance data, blood oxygen data, and exhalation temperature data in the breathing data; determination of a current blood oxygen content of the target object according to blood oxygen data in the breathing data; determination of a current motion state of the target object according to motion data and posture data in the breathing data.

3. The electrical stimulation device of claim 2, wherein, The determination of the current breathing state of the target object according to the breathing data comprises: in response to a determination that there is an interference signal in a breathing signal of the target object, determination of a sampling window according to a preset breathing frequency range and a preset breathing motion feature, wherein the breathing signal is determined according to motion data in the breathing data; feature extraction on the breathing signal in the sampling window according to the preset breathing motion feature to determine a feature weight; determine an analog respiration signal according to the reference respiration frequency and the reference respiration phase; adjust the reference respiration frequency and the reference respiration phase according to the feature weight to minimize a residual error between the respiration signal and the analog respiration signal, and determine a current respiration frequency and a current respiration phase in a current respiration state.

4. The electrical stimulation device of claim 1, wherein, The initial stimulation parameter includes a stimulation output time, a stimulation duration and a stimulation signal intensity. The determining of the initial stimulation parameter of the next respiration cycle according to the predicted respiration state includes: determining the stimulation output time based on a preset time offset and a respiration start time in the predicted respiration state; determining the stimulation duration based on a dynamic time bandwidth of the respiration signal and a time length of the predicted respiration state; determining the stimulation signal intensity based on a respiration amplitude and a blood oxygen content in the predicted respiration state.

5. The electrical stimulation device of claim 1, wherein, The adjusting of the initial stimulation parameter based on the posture change data to determine the target stimulation parameter includes: determining a confidence degree of the initial stimulation parameter at each time in the next respiration cycle based on the posture change data; determining a weight of the initial stimulation parameter according to the confidence degree; adjusting the initial stimulation parameter according to the weight of the initial stimulation parameter to determine the target stimulation parameter.

6. The electrical stimulation device of claim 5, wherein, The determining of the confidence degree of the initial stimulation parameter at each time in the next respiration cycle based on the posture change data includes: obtaining prior features of the posture change data information; performing feature extraction on the prior features of the posture change data information and the posture change data information; determining the confidence degree of the initial stimulation parameter at each time in the next respiration cycle by evaluating the predicted respiration state through a confidence degree evaluation model according to a feature extraction result of the prior features and a feature extraction result of the posture change data.

7. The electrical stimulation device of claim 1, wherein, The controller is further configured to: update the respiration state space model based on a difference between an actual respiration state in the next respiration cycle of the target object and the predicted respiration state; adjust a collection parameter of the sensor based on the predicted respiration state, wherein the collection parameter of the sensor includes at least one of a collection frequency, a resolution and a power.

Images