CN118873111B

CN118873111B - Respiratory monitoring precision optimization method, device, computer equipment and storage medium

Info

Publication number: CN118873111B
Application number: CN202411283126.4A
Authority: CN
Inventors: 胡康; 王守东; 李网林
Original assignee: Hangzhou Shenluo Medical Technology Co ltd
Current assignee: Hangzhou Shenluo Medical Technology Co ltd
Priority date: 2024-09-13
Filing date: 2024-09-13
Publication date: 2025-02-11
Anticipated expiration: 2044-09-13
Also published as: CN118873111A

Abstract

The present application relates to a method, device, computer equipment and storage medium for optimizing respiratory monitoring accuracy. The method includes: obtaining first indicator values corresponding to at least two physiological indicators respectively; each first indicator value is estimated based on the first PPG signal obtained by sampling the PPG sensor controlled by the sampling controller; based on each first indicator value, the predicted value of each physiological indicator in the next respiratory cycle is predicted; based on each first indicator value and each predicted value, the target sampling parameter of the next respiratory cycle when the estimation accuracy is the highest is determined; based on the target sampling parameter, the sampling controller is adjusted for sampling parameters, and when sampling the next respiratory cycle, the third indicator value of each physiological indicator is obtained based on the adjusted sampling parameter, and the prediction function parameters are updated based on the third indicator value; the prediction function parameters include the calculation parameters corresponding to blood oxygen, heart rate and respiration. The use of this method can improve the estimation accuracy when estimating the indicator value.

Description

Respiratory monitoring precision optimization method, device, computer equipment and storage medium

Technical Field

The present application relates to the field of physiological index monitoring, and in particular, to a respiratory monitoring accuracy optimization method, apparatus, computer device, and storage medium.

Background

Along with the development of the physiological index monitoring technology, a sampling parameter optimization technology appears, and the sampling parameter optimization is mainly performed through index values of physiological indexes.

In the conventional technology, after an index value of a physiological index is estimated from a signal acquired by a sensor, sampling parameters are optimized according to characteristics of the index value.

However, at present, only the accuracy optimization of a physiological index (such as blood oxygen) with a single dimension can be performed, the optimization effect is poor, and the accuracy of an index value estimated after the subsequent sampling is low.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a respiratory monitoring accuracy optimization method, apparatus, computer device, and storage medium for multi-feature network control that can improve the accuracy of estimation when estimating an index value.

In a first aspect, the present application provides a respiratory monitoring accuracy optimization method, comprising:

acquiring first index values corresponding to at least two physiological indexes respectively, wherein each first index value is estimated based on a first PPG signal obtained by sampling a PPG sensor controlled by a sampling controller;

Predicting a predicted value of each physiological index in the next respiratory cycle based on each first index value;

Determining a target sampling parameter of the next respiratory cycle when the estimation precision is highest based on the first index values and the predicted values, wherein the estimation precision is the precision when each second index value of the next respiratory cycle is estimated and obtained based on a second PPG signal corresponding to the next respiratory cycle;

And carrying out sampling parameter adjustment on the sampling controller based on the target sampling parameter, obtaining a third index value of each physiological index based on the adjusted sampling parameter when sampling is carried out in the next respiratory cycle, and updating a prediction function parameter based on the third index value, wherein the prediction function parameter comprises calculation parameters corresponding to blood oxygen, heart rate and respiration.

In one embodiment, each of the first index values includes a first heart rate value, a first blood oxygen content, and a first respiration feature value, the first respiration feature value includes a first time interval when the respiration motion is relatively static, the target sampling parameter further includes a plurality of sampling moments, and determining, based on each of the first index values and each of the predicted values, the target sampling parameter of the next respiration cycle when the estimation accuracy is highest includes:

Taking an error estimation lower bound as an optimization target, and determining each sampling time based on the ending time of the first time interval, a sampling value of the ending time and the first blood oxygen content;

and respectively determining the sampling frequency of the next respiratory cycle corresponding to each sampling moment when the estimation precision is highest and the emission intensity of the emission unit of the PPG sensor based on each first index value and each predicted value.

In one embodiment, each of the predicted values includes at least a second time interval when the respiratory motion is relatively static in the next respiratory cycle, and each of the sampling moments includes at least a first moment corresponding to the maximum signal strength of the next respiratory cycle and at least one second moment in the second time interval.

In one embodiment, each of the first index values includes a first heart rate value, a first blood oxygen content, and a first respiration feature value, the first respiration feature value includes a first respiration signal feature value and a first time interval when respiration motion is relatively static, and predicting, based on each of the first index values, a predicted value of each of the physiological indexes at a next respiration cycle includes:

Predicting a second respiratory signal characteristic value of a next respiratory cycle based on the first heart rate value, the first blood oxygen content and the first respiratory signal characteristic value;

predicting a second blood oxygen content of a next respiratory cycle based on the first blood oxygen content and the second respiratory signal characteristic value;

A second time interval when respiratory motion of a next respiratory cycle is relatively static is predicted based on the first time interval and the first heart rate value.

In one embodiment, the method further comprises:

acquiring a second PPG signal obtained by sampling a PPG sensor in the next respiratory cycle and a second time interval when the respiratory motion obtained by prediction is relatively static;

determining a third time interval in the next breath cycle other than the second time interval;

filtering the second PPG signal in the second time interval and the third time interval based on the prior parameters corresponding to the physiological indexes;

and estimating and obtaining a second index value of each physiological index based on the filtered second PPG signal.

In one embodiment, the filtering the second PPG signal in the second time interval and the third time interval based on the a priori parameters corresponding to the physiological indexes includes:

if two target physiological indexes simultaneously corresponding to the second time interval exist in the at least two physiological indexes, determining the correlation degree between each sampling data corresponding to the second time interval in the second PPG signal and each target physiological index respectively;

And respectively carrying out filtering processing on each sampled data based on the prior parameters corresponding to the target physiological indexes with highest correlation degree.

In one embodiment, each of the second index values includes a second heart rate value, a second blood oxygen content, and a second respiration feature value, and estimating the second index value of each of the physiological indexes based on the filtered second PPG signal includes:

Respectively extracting a respiration characteristic PPG signal corresponding to respiration, a blood oxygen characteristic PPG signal corresponding to blood oxygen and a heart rate characteristic PPG signal corresponding to heart rate from the filtered second PPG signal;

Determining the second respiratory feature value based on the respiratory feature PPG signal, the second respiratory feature value comprising a second respiratory signal feature value and a fourth time interval when respiratory motion is relatively static;

Determining the second blood oxygen content based on the fourth time interval and the blood oxygen characteristic PPG signal;

The second heart rate value is determined based on the fourth time interval and the heart rate characteristic PPG signal.

In a second aspect, the present application also provides a respiratory monitoring accuracy optimization device, including:

The acquisition module is used for acquiring first index values corresponding to at least two physiological indexes respectively, wherein each first index value is obtained by estimating a first PPG signal obtained by controlling a PPG sensor to sample based on a sampling controller;

the prediction module is used for predicting and obtaining a predicted value of each physiological index in the next respiratory cycle based on each first index value;

The optimization module is used for determining a target sampling parameter of the next breathing cycle when the estimation precision is highest based on each first index value and each predicted value, wherein the estimation precision is the precision when each second index value of the next breathing cycle is estimated and obtained based on a second PPG signal corresponding to the next breathing cycle;

The updating module is used for adjusting the sampling parameters of the sampling controller based on the target sampling parameters, obtaining third index values of the physiological indexes based on the adjusted sampling parameters when sampling is performed in the next respiratory cycle, and updating the prediction function parameters based on the third index values, wherein the prediction function parameters comprise calculation parameters corresponding to blood oxygen, heart rate and respiration.

In a third aspect, the present application also provides a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:

In a fourth aspect, the present application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:

According to the respiratory monitoring precision optimizing method, the respiratory monitoring precision optimizing device, the computer equipment and the storage medium, the predicted value of each physiological index in the next respiratory cycle is obtained through index value prediction, then the target sampling parameter of the next respiratory cycle when the estimated precision is highest is determined based on each first index value and each predicted value, the sampling controller is adjusted based on the target sampling parameter, the sampling parameter of each physiological index is updated, the third index value of each physiological index is obtained based on the updated sampling parameter after the sampling of the next respiratory cycle, the predicted function parameter is updated based on the third index value, and the predicted function parameter comprises blood oxygen, heart rate and calculation parameters corresponding to respiration. Thus, before the sensor signal is sampled in the next respiratory cycle, a predicted value of each physiological index of the next respiratory cycle is predicted, and a target sampling parameter is determined at least based on the predicted value. That is, the sampling parameters used in the subsequent sampling are not determined only by the index value obtained by current estimation, but also combined with the predicted value, so that the target sampling parameters are more suitable for being used in the sampling of the next respiratory cycle, and the optimization effect is improved. On the basis, the prediction function parameters are updated according to the obtained third index value after the sampling of the next respiratory cycle, so that multi-feature network control is realized, and the estimation accuracy when the index value is obtained by estimation is improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are needed in the description of the embodiments of the present application or the related technologies will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other related drawings may be obtained according to these drawings without inventive effort to those of ordinary skill in the art.

FIG. 1 is a flow chart of a method of optimizing respiratory monitoring accuracy in one embodiment;

fig. 2 is a graph of respiratory motion and PPG reflected signal strength versus time relating to one embodiment;

FIG. 3 is a schematic diagram of a predicted distribution of sampling instants in one embodiment;

FIG. 4 is a graph of respiratory motion waveforms in one embodiment;

FIG. 5 is a waveform diagram of an embodiment after the second time interval is fused with the characteristic signal;

FIG. 6 is a flow chart of a joint optimization method for respiratory monitoring in another embodiment;

FIG. 7 is a block diagram of a respiratory monitoring accuracy optimization device in one embodiment;

Fig. 8 is an internal structural diagram of a computer device in one embodiment.

Detailed Description

The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.

In an exemplary embodiment, as shown in fig. 1, a respiration monitoring accuracy optimization method is provided, and the method is applied to a computer device for illustration, and includes the following steps 102 to 108. The computer device may be a medical respiration monitoring device, which may be a respiration monitor, a tongue muscle stimulator or a hypoglossal nerve stimulator.

It should be noted that the respiration monitoring device may determine the sleep respiration quality according to the index values of the physiological indexes, and thereby determine whether to stimulate the lingual muscle or the hypoglossal nerve, so as to achieve the purpose of respiration during sleep intervention. If it is determined that the sleep quality of breathing is low, the lingual muscle or hypoglossal nerve is stimulated to cause movement of the tongue, thereby alleviating upper airway obstruction and improving the quality of breathing. Wherein:

step 102, obtaining first index values corresponding to at least two physiological indexes respectively, wherein each first index value is obtained by estimating a first PPG signal obtained by controlling a PPG sensor to sample based on a sampling controller.

Among these physiological indicators include, but are not limited to, respiration, heart rate, and blood oxygen.

Wherein, the PPG sensor is attached to the chest of the monitored subject. The PPG sensor is a sensor for measuring blood volume changes by using optical technology, and can collect PPG signals for detecting the intensity changes of reflected light of blood, so as to obtain heart rate values, blood oxygen content and respiration characteristic values corresponding to heart rate, blood oxygen and respiration respectively.

Optionally, the first PPG signal is a correspondence between time and received reflected light, where the intensity of the received reflected light is positively related to the amount of blood oxygen cells in the blood.

Optionally, when the first PPG signal is obtained by controlling the PPG sensor to sample by the sampling controller, the sampling parameter is controlled by the sampling controller, specifically, the sampling frequency and the emission intensity of the PPG sensor are controlled by the sampling controller to sample at the sampling time. Among them, sampling parameters include, but are not limited to, sampling time, sampling frequency, and emission intensity.

Step 104, predicting and obtaining the predicted value of each physiological index in the next respiratory cycle based on each first index value.

The next breathing cycle is obtained by dividing the time series data of the first PPG signal by the breathing cycle. The time series data refers to a data sequence arranged in a time series, which is a sampling time series.

Further, each first index value comprises a first heart rate value, a first blood oxygen content and a first respiration characteristic value, wherein the first respiration characteristic value comprises a first respiration signal characteristic value and a first time interval when the respiration motion is relatively static.

The first time interval refers to a sub-time interval in a time interval corresponding to the current respiratory cycle. For the respiratory cycle, as shown in fig. 2, during sleep breathing, the reciprocating motion of the thoracic cavity changes the reflection surface of the PPG signal in the detection node attached to the thoracic cavity surface of the monitored subject, resulting in the correlation of the reflected signal intensity and respiratory motion as shown in fig. 2.

Specifically, when the monitored object performs an expiratory motion and an inspiratory motion, that is, a respiratory motion, the PPG reflected signal intensity changes periodically, that is, changes from an expiratory saturated region to an inspiratory saturated region, or changes from the inspiratory saturated region to the expiratory saturated region, which is one respiratory cycle.

It can be understood that the current respiratory cycle is the respiratory cycle in which the current monitored subject performs the ongoing respiratory motion, and is reflected in the PPG signal, that is, the respiratory cycle in which the latest measured PPG reflected signal intensity is located. Correspondingly, the next breathing cycle is the breathing cycle in which the monitored object does not perform breathing motion yet.

And predicting and obtaining a predicted value of each physiological index in the next respiratory cycle based on each first index value, wherein the predicted value comprises a second respiratory signal characteristic value, a second blood oxygen content and a second time interval. The following respectively describes a second respiratory signal characteristic value, a second blood oxygen content and a second time interval of the next respiratory cycle obtained by prediction:

The second respiratory signal characteristic value comprises a second period, a second amplitude and a second phase, wherein the second amplitude The prediction can be obtained by the following formula one:

(one)

Wherein, For a first amplitude in the first respiratory signal characteristic value,AndIn the form of an empirical formula,For the sequence number of the current respiratory cycle,For a plurality of heart rate values for the current respiratory cycle,For a plurality of blood oxygen levels of the current respiratory cycle.

Accordingly, the second period and the second phase may be determined by a formula similar to formula one, and will not be described again.

Second blood oxygen contentThe prediction can be obtained by the following formula II:

(II)

Wherein, A sequence number for the current respiratory cycle; At the second amplitude of the signal, For the second period of time,Is a second phase; Is composed of 、AndA vector of the components; Is a vector composed of a plurality of first blood oxygen contents.

The second time interval may be defined by a second starting timeAnd a second end timeDetermining, wherein the second start timeThe result can be obtained through the prediction of the formula III:

(III)

Wherein, A first starting time of a first time interval; In the form of an empirical formula, Is a plurality of heart rate values for the current respiratory cycle.

Second end timeThe result can be predicted by the formula four:

(IV)

Wherein, A first end time of the first time interval; In the form of an empirical formula, Is a plurality of heart rate values for the current respiratory cycle.

And 106, determining a target sampling parameter of the next respiratory cycle when the estimation precision is highest based on each first index value and each predicted value, wherein the estimation precision is the precision when each second index value of the next respiratory cycle is estimated and obtained based on a second PPG signal corresponding to the next respiratory cycle, and the target sampling parameter comprises the sampling frequency and the emission intensity of an emission unit of the PPG sensor.

The PPG sensor comprises a transmitting unit and a receiving unit, wherein the transmitting unit is used for transmitting light, and the receiving unit is used for receiving reflected light corresponding to the transmitted light.

Further, when determining the target sampling parameter of the next respiratory cycle with the highest estimation accuracy based on each first index value and each predicted value, the target sampling parameter further includes determining each sampling time based on the end time of the first time interval, the sampling value of the end time and the first blood oxygen content, and then determining the sampling frequency of the next respiratory cycle with the highest estimation accuracy and the emission intensity of the emission unit of the PPG sensor corresponding to each sampling time based on each first index value and each predicted value.

The lower error estimation bound refers to the minimum value that the difference between the calculated result and the true value can reach. In this embodiment, the calculation result refers to each sampling time.

Each predicted value at least comprises a second time interval when the respiratory motion is relatively static in the next respiratory cycle, and each sampling time at least comprises a first time corresponding to the maximum signal intensity of the next respiratory cycle and at least one second time in the second time interval. That is, each sampling time at least includes a time in a second time interval corresponding to a heart rate or blood oxygen in a next respiration cycle and a time in a time interval corresponding to respiration in the next respiration cycle, so that signal characteristics of the PPG signal in different characteristic time intervals are considered, and determination accuracy of each sampling time is improved.

It should be noted that the target sampling parameter is determined at the end of the current respiratory cycle, i.e. at the end of the first time interval.

For example, determining the sampling instant, i.e. predicting the timing signal of the next breathing cycle, may be performed by the following formula five when determining the sampling instant:

(V)

Wherein, For the sequence number of the breathing cycle,In order to predict the probability of a probability,For the probability calculation formula,For the moment of sampling,To be the average of the PPG signal strength of the prediction interval,Is the signal distribution of the timing signal.

Correspondingly, the first sampling instant after the end instant of the predicted first time intervalWhen it is, it can pass the formulaAnd (5) calculating to obtain the product. The distribution parameters in the formula includeAndIs affected by the oxygen content of blood, thus at the predicted sampling instantPreviously, the distribution parameters need to be updated by the following equation six and equation seven:

(six)

(Seven)

Wherein, Is the average of the end time of the first time interval, i.e. the sampling timeThe mean value of the last sampling moment; a signal profile of the timing signal being an end time of the first time interval; And Is a normal distribution of blood oxygen content.

As shown in the figure 3 of the drawings,For the end time of the first time interval, each sampling time may include-The solid line in the prediction interval is drawn by the mean value corresponding to each sampling time.

In determining the sampling frequency and the emission intensity corresponding to each sampling instant, the determination may be performed by the following equation eight:

(eight)

Wherein, For the maximum estimation accuracy to be achieved,In order to calculate the function for the accuracy of the estimation,For the moment of sampling,For the sampling frequency to be the same,Is the emission intensity. The first index values and the predicted values are known amounts, and are not shown in the formula eight.

For example, the target sampling parameter corresponding to each sampling time may be predicted in such a manner that prediction and sampling are alternately performed. As predictedAfter the corresponding target sampling parameters, the sampling controller controls the PPG sensor to sample according to the target sampling parameters, and after the sampling, the range of the prediction interval is updated according to the sampling values, so that the estimation accuracy is higher.

And step 108, adjusting sampling parameters of the sampling controller based on the target sampling parameters, obtaining third index values of the physiological indexes based on the adjusted sampling parameters when sampling in the next respiratory cycle, and updating prediction function parameters based on the third index values, wherein the prediction function parameters comprise calculation parameters corresponding to blood oxygen, heart rate and respiration.

The calculation parameters are parameters in the prediction functions (i.e., formulas one to seven) used in the prediction process.

Optionally, the parameter updating and adjusting are performed on the original sampling parameter in the sampling controller through the target sampling parameter, then the sensor is controlled to sample through the adjusted sampling parameter to obtain a PPG signal, and then a third index value of each physiological index is obtained through the PPG signal, and the prediction function parameter is updated accordingly. The prediction function parameters are updated by multi-feature network control based on the index values corresponding to the sampled values in real time, so that the accuracy of the index values obtained later is improved.

According to the method, the predicted value of each physiological index in the next respiratory cycle is obtained through index value prediction, then the target sampling parameter of the next respiratory cycle when the estimation accuracy is highest is determined based on each first index value and each predicted value, the sampling controller is adjusted based on the target sampling parameter, the sampling parameter of each physiological index is updated, a third index value of each physiological index is obtained based on the updated sampling parameter after sampling in the next respiratory cycle, the prediction function parameter is updated based on the third index value, and the prediction function parameter comprises blood oxygen, heart rate and calculation parameters corresponding to respiration. Thus, before the sensor signal is sampled in the next respiratory cycle, a predicted value of each physiological index of the next respiratory cycle is predicted, and a target sampling parameter is determined at least based on the predicted value. That is, the sampling parameters used in the subsequent sampling are not determined only by the index value obtained by current estimation, but also combined with the predicted value, so that the target sampling parameters are more suitable for being used in the sampling of the next respiratory cycle, and the optimization effect is improved. On the basis, the prediction function parameters are updated according to the obtained third index value after the sampling of the next respiratory cycle, so that multi-feature network control is realized, and the estimation accuracy when the index value is obtained by estimation is improved.

In an exemplary embodiment, the above method further comprises steps 202-208. Wherein:

Step 202, obtaining a second PPG signal obtained by sampling the PPG sensor in the next respiratory cycle, and a second time interval when the respiratory motion obtained by prediction is relatively static.

Step 204, determining a third time interval in the next breath cycle, excluding the second time interval.

Step 206, filtering the second PPG signal in the second time interval and the third time interval respectively based on the prior parameters corresponding to the physiological indexes.

Step 208, estimating a second index value of each physiological index based on the filtered second PPG signal.

Wherein each physiological index has a different characteristic signal, i.e. a different characteristic on the PPG signal, which corresponds to the a priori parameters of the characteristic signal.

For example, to avoid loss of information, the signal segments corresponding to the second time interval and the third time interval respectively are filtered by a priori parameters corresponding to the corresponding physiological indexes, instead of filtering the complete second PPG signal multiple times by a priori parameters corresponding to all physiological indexes.

For example, when the second PPG signal is filtered, the second PPG signal is filtered in a second time interval corresponding to respiration by a priori parameter corresponding to respiration, and the second PPG signal is filtered in a third time interval corresponding to blood oxygen by a priori parameter corresponding to blood oxygen. If there are time interval 1 and time interval 2 on the second PPG signal, where time interval 1 corresponds to respiration, time interval 2 corresponds to blood oxygen, the prior parameter corresponding to respiration is used to perform filtering processing on the signal segment of the second PPG signal corresponding to time interval 1, and the prior parameter corresponding to blood oxygen is used to perform filtering processing on the signal segment of the second PPG signal corresponding to time interval 2.

It should be noted that, after the second PPG signal is filtered, a characteristic PPG signal corresponding to each physiological index may be extracted therefrom.

When calculating the index value corresponding to the heart rate and the blood oxygen, the calculation is generally performed using a signal segment corresponding to a time period when the respiratory motion in the second PPG signal is relatively stationary. The index value calculated by the signal segment has higher accuracy.

Because of this, the third time interval for the heart rate and blood oxygen may be the same, which is a time interval in one breathing cycle other than the second time interval for the breath. As shown in fig. 4, fig. 4 is a waveform of a characteristic PPG signal corresponding to respiration, wherein a first time interval corresponding to respiration includes t _{o_start}-t_{o_stop} and t _{i_start}-t_{i_stop}, and a first time interval corresponding to heart rate and blood oxygen is t _{o_stop}-t_{i_start}.

In an embodiment, if the same portion exists in the time intervals corresponding to the at least two physiological indexes, the time intervals of the same portion may be divided into intervals according to a certain proportion, so that the corresponding physiological indexes respectively correspond to different division obtaining intervals. For example, if the same partial time zone 3 exists between the time zone 1 corresponding to breath and the time zone 2 corresponding to blood oxygen, the time zone 3 is divided into two parts in an equal division manner, and the two parts correspond to breath and blood oxygen respectively.

In another embodiment, for the prior parameter corresponding to each physiological index, filtering the second PPG signal in the second time interval and the third time interval respectively, which specifically includes:

if two target physiological indexes simultaneously corresponding to a second time interval exist in the at least two physiological indexes, determining the correlation degree between each sampling data corresponding to the second time interval in the second PPG signal and each target physiological index respectively, and filtering each sampling data based on the prior parameter corresponding to the target physiological index with the highest correlation degree.

The second PPG signal is actually formed by a plurality of sampling data, and the waveform thereof is formed by connecting points corresponding to sampling values corresponding to the sampling data.

The correlation degree refers to the matching degree between the sampled data and the prior parameters corresponding to each physiological index.

In an exemplary embodiment, each sampled data has different correlation degrees with different physiological indexes, and when each sampled data is subjected to filtering processing through a priori parameter corresponding to the physiological index with the highest correlation degree, information of the sampled data can be more reserved, so that accuracy of obtaining the first index value through subsequent estimation is improved.

In the embodiment, when the index value is determined through the PPG signal, considering that the features corresponding to different physiological indexes are associated with each other, the overall PPG signal is not subjected to various filtering respectively, and segmented filtering is realized through the corresponding time interval. That is, only one kind of filtering corresponding to the physiological index is performed on the PPG signal corresponding to each time interval, but not all kinds of filtering corresponding to the physiological index are performed, so that information loss in the PPG signal is avoided, and accuracy of each index value is improved.

On the basis of the above embodiments, each second index value includes a second heart rate value, a second blood oxygen content and a second respiration feature value, and the estimating the second index value of each physiological index based on the filtered second PPG signal includes the following steps 302 to 308. Wherein:

Step 302, extracting a respiration characteristic PPG signal corresponding to respiration, a blood oxygen characteristic PPG signal corresponding to blood oxygen and a heart rate characteristic PPG signal corresponding to heart rate from the filtered second PPG signal respectively.

The characteristic PPG signals are obtained by performing correlation computation estimation on the filtered second PPG signals and the corresponding characteristic signals, namely, the respiratory characteristic PPG signals can be estimated by the characteristic signals corresponding to respiration, the blood oxygen characteristic PPG signals can be estimated by the characteristic signals corresponding to blood oxygen, and the heart rate characteristic PPG signals can be estimated by the characteristic signals corresponding to heart rate.

A second respiration feature value is determined based on the respiration feature PPG signal, the second respiration feature value comprising a fourth time interval when the second respiration signal feature value and the respiration motion are relatively static, step 304.

Wherein the second respiratory signal characteristic value comprises a second period, a second amplitude, and a second phase.

Alternatively, the second respiration feature value may be directly identified from a waveform corresponding to the respiration feature PPG signal.

As shown in fig. 4, fig. 4 is a waveform diagram corresponding to the respiration feature PPG signal. For the period T _i, the exhalation interval T _{o_start}-t_{o_stop}, the inhalation interval T _{i_start}-t_{i_stop}, and T _{o_stop}-t_{i_start} are the fourth time interval when relatively static can be identified from the respiratory feature PPG signal.

Step 306, determining a second blood oxygen content based on the fourth time interval and the blood oxygen characteristic PPG signal.

As shown in fig. 5, the signal segment of the blood oxygen characteristic PPG signal corresponding to the fourth time interval, that is, the signal segment corresponding to t _{o_stop}-t_{i_start}, can be determined in the blood oxygen characteristic PPG signal by fusing the fourth time interval with the blood oxygen characteristic PPG signal. And then determining a second blood oxygen content from the signal segment.

Further, when the second blood oxygen content is determined by the signal segment, sampling data is obtained from the signal segment, and then the second blood oxygen content is calculated by the sampling data.

The calculation process comprises the steps of determining a first alternating current component and a first direct current component of a red light signal in sampling data, and a second alternating current component and a second direct current component of an infrared signal, and obtaining second blood oxygen content based on the first alternating current component, the first direct current component, the second alternating current component and the second direct current component.

Referring to the following formula nine, the second blood oxygen content Spo2 may be specifically calculated by the formula nine:

(nine)

Wherein, Is the first alternating component of the red light signal,Is the first direct current component of the red light signal,As the second alternating component of the infrared signal,Is the second direct current component of the infrared signal.

Step 308, determining a second heart rate value based on the fourth time interval and the heart rate characteristic PPG signal.

Similarly, as shown in fig. 5, the fourth time interval is fused with the heart rate characteristic PPG signal, so that a signal segment of the heart rate characteristic PPG signal corresponding to the fourth time interval, that is, a signal segment corresponding to t _{o_stop}-t_{i_start}, can be determined in the heart rate characteristic PPG signal. A second heart rate value is then determined from the signal segment.

In an exemplary embodiment, as shown in FIG. 6, the overall flow of the method may include steps 1-16. Wherein:

And step 1, controlling a PPG sensor (comprising a PPG transmitting unit and a PPG receiving unit) to sample based on a sampling controller according to sampling time, sampling frequency and transmitting intensity to obtain a PPG signal, and inputting the PPG signal into a PPG feature extractor. The PPG sensor is used as a respiration monitoring node, and can be attached to the chest of a monitored subject or placed in the chest of the monitored subject.

And 2, carrying out priori processing, filtering and the like on the PPG signal.

And 3, extracting to obtain the respiratory feature PPG.

And 4, extracting to obtain blood oxygen characteristic PPG.

And 5, extracting to obtain heart rate characteristics PPG.

And 6, detecting respiratory motion based on the respiratory feature PPG, and obtaining a first respiratory signal feature value and a first time interval when respiratory motion is relatively static.

And 7, calculating the blood oxygen content based on the blood oxygen characteristic PPG and the first time interval obtained in the subsequent step 9.

And 8, calculating a heart rate value based on the heart rate characteristic PPG and the first time interval obtained in the subsequent step 9.

And 9, inputting the first time interval into a blood oxygen content calculation module and a heart rate calculation module, calculating to obtain a first blood oxygen content by the blood oxygen content calculation module, and calculating to obtain a first heart rate value by the heart rate calculation module.

And 10, inputting a first time interval into a breath prediction module, carrying out breath prediction by the breath prediction module based on the first time interval and the first heart rate value obtained in the subsequent step 12 to obtain a second time interval when the breath motion of the next breath period is relatively static, and predicting by the breath prediction module based on the first blood oxygen content obtained in the step 11, the first heart rate value obtained in the subsequent step 12 and the first time interval to obtain a second breath signal characteristic value of the next breath period.

And 11, inputting the first blood oxygen content into a blood oxygen prediction module, and predicting the second blood oxygen content of the next respiratory cycle by the blood oxygen prediction module based on the first blood oxygen content and the second respiratory signal characteristic value obtained in the subsequent step 13.

Step 12, inputting a first heart rate value into a breath prediction module.

And 13, the respiratory prediction module inputs a second respiratory signal characteristic value to the blood oxygen prediction module.

And 14, inputting the second respiratory signal characteristic value and the second time interval which are predicted by the respiratory prediction module into an estimation accuracy optimizer. And the estimation precision optimizer is used for carrying out estimation precision optimization based on each index value and the predicted value to obtain the target sampling parameter. The estimation accuracy optimizer also obtains predicted values of other physiological indexes of the next respiratory cycle.

And 15, inputting a predicted value obtained in the prediction process, such as a second time interval, to the PPG feature extractor.

And step 16, inputting target sampling parameters to the sampling controller for the sampling controller to adjust the sampling parameters, obtaining third index values of the physiological indexes based on the adjusted sampling parameters when sampling is performed in the next respiratory cycle, and updating the prediction function parameters based on the third index values, wherein the prediction function parameters comprise calculation parameters corresponding to blood oxygen, heart rate and respiration.

It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides a respiratory monitoring precision optimizing device for realizing the respiratory monitoring precision optimizing method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the respiratory monitoring accuracy optimization device or devices provided below may be referred to the limitation of the respiratory monitoring accuracy optimization method hereinabove, and will not be repeated herein.

In one exemplary embodiment, as shown in FIG. 7, a respiratory monitoring accuracy optimization apparatus is provided, comprising an acquisition module 702, a prediction module 704, an optimization module 706, and an update module 708, wherein:

The acquisition module 702 is configured to acquire first index values corresponding to at least two physiological indexes respectively, where each first index value is estimated based on a first PPG signal obtained by sampling the PPG sensor controlled by the sampling controller;

a prediction module 704, configured to predict, based on each of the first index values, a predicted value of each of the physiological indexes in a next respiratory cycle;

An optimizing module 706, configured to determine, based on each of the first index values and each of the predicted values, a target sampling parameter of a next respiratory cycle when an estimation accuracy is highest, where the estimation accuracy is an accuracy when each second index value of the next respiratory cycle is estimated based on a second PPG signal corresponding to the next respiratory cycle;

the updating module 708 is configured to adjust a sampling parameter of the sampling controller based on the target sampling parameter, and obtain a third index value of each of the physiological indexes based on the adjusted sampling parameter when sampling in the next respiratory cycle, and update a prediction function parameter based on the third index value, where the prediction function parameter includes calculation parameters corresponding to blood oxygen, heart rate and respiration.

In one embodiment, the optimization module 706 includes:

A first determining unit, configured to determine each sampling time based on an end time of the first time interval, a sampling value of the end time, and the first blood oxygen content, with an error estimation lower bound as an optimization target;

And a second determining unit, configured to determine, based on each of the first index values and each of the predicted values, a sampling frequency of a next respiratory cycle corresponding to each of the sampling moments when an estimation accuracy is highest, and an emission intensity of an emission unit of the PPG sensor, respectively.

In one embodiment, the prediction module 704 includes:

A first prediction unit, configured to predict a second respiratory signal feature value of a next respiratory cycle based on the first heart rate value, the first blood oxygen content, and the first respiratory signal feature value;

The second prediction unit is used for predicting and obtaining second blood oxygen content of the next respiratory cycle based on the first blood oxygen content and the second respiratory signal characteristic value;

And the third prediction unit is used for predicting a second time interval when the respiratory motion of the next respiratory cycle is relatively static based on the first time interval and the first heart rate value.

In one embodiment, the respiratory monitoring accuracy optimizing device further includes:

The acquisition module is used for acquiring a second PPG signal obtained by sampling the PPG sensor in the next respiratory cycle and a second time interval when the respiratory motion obtained by prediction is relatively static;

A determining module for determining a third time interval in the next breath cycle, other than the second time interval;

The filtering module is used for filtering the second PPG signal in the second time interval and the third time interval respectively based on prior parameters corresponding to the physiological indexes;

And the estimation module is used for estimating and obtaining a second index value of each physiological index based on the filtered second PPG signal.

In one embodiment, the filtering module includes:

A third determining unit, configured to determine, if two target physiological indexes simultaneously corresponding to the second time interval exist in the at least two physiological indexes, a correlation degree between each sampling data corresponding to the second time interval in the second PPG signal and each target physiological index;

And the filtering unit is used for respectively carrying out filtering processing on each sampled data based on the prior parameter corresponding to the target physiological index with the highest correlation degree.

In one embodiment, the estimation module includes:

The extraction unit is used for respectively extracting a respiration characteristic PPG signal corresponding to respiration, a blood oxygen characteristic PPG signal corresponding to blood oxygen and a heart rate characteristic PPG signal corresponding to heart rate from the filtered second PPG signal;

A fourth determination unit for determining the second respiration feature value based on the respiration feature PPG signal, the second respiration feature value comprising a second respiration signal feature value and a fourth time interval when respiration motion is relatively static;

a fifth determining unit for determining the second blood oxygen content based on the fourth time interval and the blood oxygen characteristic PPG signal;

a sixth determining unit for determining the second heart rate value based on the fourth time interval and the heart rate characteristic PPG signal.

The modules in the respiratory monitoring accuracy optimization device can be realized in whole or in part by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one exemplary embodiment, a computer device is provided, which may be a respiratory monitoring device, the internal structure of which may be as shown in fig. 8. The computer device includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input means. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The Communication interface of the computer device is used for conducting wired or wireless Communication with an external terminal, and the wireless Communication can be realized through bluetooth, WIFI, a mobile cellular network, near field Communication (NEAR FIELD Communication, NFC) or other technologies. The computer program when executed by a processor implements a respiration monitoring accuracy optimization method.

It will be appreciated by those skilled in the art that the structure shown in FIG. 8 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.

In one exemplary embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:

In one embodiment, the processor when executing the computer program further performs the steps of:

In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:

In one embodiment, the computer program when executed by a processor performs the steps of:

It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are both information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data are required to meet the related regulations.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile memory and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (RESISTIVE RANDOM ACCESS MEMORY, reRAM), magneto-resistive Memory (MagnetoresistiveRandom Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (PHASE CHANGE Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in various forms such as static Random access memory (Static Random Access Memory, SRAM) or Dynamic Random access memory (Dynamic Random AccessMemory, DRAM), and the like. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computation, an artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) processor, or the like, but is not limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the present application.

The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.

Claims

1. A method for optimizing respiratory monitoring accuracy, the method comprising:

Predicting a predicted value of each physiological index in a next respiratory cycle by using a prediction function based on each first index value, wherein each predicted value at least comprises a second time interval when respiratory motion is relatively static in the next respiratory cycle;

the sampling controller is used for carrying out sampling parameter adjustment based on the target sampling parameter, and when the next respiratory cycle is sampled, a third index value of each physiological index is obtained based on the adjusted sampling parameter, and a prediction function parameter is updated based on the third index value, wherein the prediction function parameter comprises calculation parameters corresponding to blood oxygen, heart rate and respiration;

2. The method of claim 1, wherein each of the first index values comprises a first heart rate value, a first blood oxygen content, and a first respiration feature value, the first respiration feature value comprising a first time interval when respiratory motion is relatively static, the target sampling parameter further comprising a plurality of sampling instants, the determining, based on each of the first index values and each of the predicted values, the target sampling parameter for the next respiration cycle at which the estimation accuracy is highest comprising:

3. The method of claim 2, wherein each of the sampling instants comprises at least a first instant corresponding to a maximum signal strength of a next respiratory cycle and at least one second instant within the second time interval.

4. The method of claim 1, wherein each of the first index values comprises a first heart rate value, a first blood oxygen content, and a first respiration characteristic value comprising a first respiration signal characteristic value and a first time interval when respiration motion is relatively static, wherein predicting a predicted value for each of the physiological indices at a next respiration cycle based on each of the first index values comprises:

5. The method of claim 1, wherein filtering the second PPG signal during the second time interval and the third time interval, respectively, based on the a priori parameters corresponding to each of the physiological indicators comprises:

6. The method of claim 5, wherein each of the second index values comprises a second heart rate value, a second blood oxygen content, and a second respiration feature value, wherein estimating a second index value for each of the physiological indexes based on the filtered second PPG signal comprises:

7. A respiratory monitoring accuracy optimization device, the device comprising:

the prediction module is used for predicting and obtaining predicted values of the physiological indexes in the next respiratory cycle by using a prediction function based on the first index values, wherein each predicted value at least comprises a second time interval when respiratory motion is relatively static in the next respiratory cycle;

the updating module is used for adjusting sampling parameters of the sampling controller based on the target sampling parameters, obtaining third index values of the physiological indexes based on the adjusted sampling parameters when sampling is performed in the next respiratory cycle, and updating prediction function parameters based on the third index values, wherein the prediction function parameters comprise calculation parameters corresponding to blood oxygen, heart rate and respiration;

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 6 when the computer program is executed.

9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any one of claims 1 to 6.