Respiration detection system based on thermal tidal effect

Abstract

The invention relates to the technical field of remote monitoring, and discloses a breathing detection method based on a thermal tidal effect, and the method comprises the steps: fixing a breathing tube at a junction of a nasal cavity of a corresponding patient of a target patient and external air, so as to collect a tube wall temperature change signal of the target patient through a thermal sensor corresponding to the breathing tube; converting the pipe wall temperature change signal into an electric signal, and denoising the electric signal to obtain a denoised electric signal; calculating the power spectrum density of the de-noised electric signal to dynamically filter the de-noised electric signal to obtain a filtered electric signal; generating intermediate information of the filtered electric signal, and calculating waveform continuity of the intermediate information to construct a breathing curve of the target patient; and analyzing the respiratory failure coefficient of the target patient, constructing multi-stage early warning parameters of the target patient, and executing respiratory detection early warning of the target patient based on the multi-stage early warning parameters. The accuracy and efficiency of respiration detection can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of remote monitoring, and in particular to a breathing detection system based on thermal tidal effect. Background Art

[0002] Respiratory detection based on the thermal tidal effect refers to a technology that uses a temperature sensor to monitor the temperature changes produced during human breathing, thereby inferring respiratory frequency and status. It can provide continuous respiratory data and improve the efficiency of patient detection.

[0003] Currently, a common method for respiratory monitoring uses a gas sensor to measure gas flow, reflecting respiratory rate and exhaled air flow. However, these sensors transmit the patient's exhaled air through a long external air tube. This method has a significant reaction lag due to the long distance the exhaled air flows to the sensor. Furthermore, the low exhaled air flow prevents the measurement of respiratory activity, and condensation of water vapor in the exhaled air can clog the air tube, resulting in poor accuracy and efficiency of respiratory monitoring. Summary of the Invention

[0004] The present invention provides a respiration detection system based on thermal tidal effect, the main purpose of which is to improve the accuracy and efficiency of respiration detection.

[0005] To achieve the above objectives, the present invention provides a breathing detection system based on thermal tidal effect, comprising: The temperature signal acquisition module is used to fix the breathing tube at the junction of the target patient's nasal cavity and the external air, so as to acquire the tube wall temperature change signal of the target patient through the thermal sensor corresponding to the breathing tube; The electrical signal denoising module is used to convert the pipe wall temperature change signal into an electrical signal and denoise the electrical signal to obtain a denoised electrical signal; The electrical signal filtering module is used to calculate the power spectrum density of the denoised electrical signal to dynamically filter the denoised electrical signal to obtain a filtered electrical signal; The respiratory curve construction module is used to generate intermediate information of the filtered electrical signal and calculate the waveform continuity of the intermediate information to construct the respiratory curve of the target patient; The respiratory detection and warning module is used to analyze the respiratory failure coefficient of the target patient according to the respiratory curve, construct multi-level warning parameters of the target patient based on the respiratory failure coefficient, and perform respiratory detection and warning of the target patient based on the multi-level warning parameters.

[0006] Optionally, collecting the tube wall temperature change signal of the target patient by a thermal sensor corresponding to the breathing tube includes: Capturing the effectiveness of the breathing tube for the target patient's inhaled and exhaled gases; Determining a temperature gradient significance value of the target patient according to the effectiveness coefficient; Optimizing the position of the thermal sensor on the breathing tube according to the temperature gradient significance value to collect an initial tube wall temperature change signal of the target patient; analyzing an abnormal state of the initial pipe wall temperature change signal; When the abnormal state meets the preset abnormal standard state, the initial tube wall temperature change signal is used as the tube wall temperature change signal of the target patient.

[0007] Optionally, determining the temperature gradient significance value of the target patient according to the effectiveness coefficient includes: When the effectiveness coefficient meets a preset effectiveness coefficient threshold, analyzing the maximum temperature and the minimum temperature of the cycle corresponding to the target patient of the thermal sensor; determining a maximum rate of change of a periodic temperature of the target patient; Based on the maximum temperature of the cycle, the minimum temperature of the cycle, and the maximum rate of change of the temperature of the cycle, the temperature gradient significance value of the target patient is calculated using the following formula:

[0008] in, Indicates the significant value of the temperature gradient of the target patient, Indicates the maximum temperature of the cycle, Indicates the lowest temperature of the cycle, represents the standard deviation of ambient temperature noise, Indicates the The instantaneous temperature change rate of each sampling point, Indicates the The instantaneous temperature of each sampling point, Indicates the maximum rate of change of cycle temperature, Indicates the number of sampling points corresponding to the respiratory cycle of the target patient, Indicates cyclic stability.

[0009] Optionally, calculating the power spectral density of the denoised electrical signal includes: Segmenting the denoised electrical signal to obtain segmented electrical signals; Performing windowing on the segmented electrical signal to obtain a windowed electrical signal; analyzing the complex spectrum of the windowed electrical signal; and calculating the unilateral power spectrum of the windowed electrical signal through the complex spectrum; Based on the unilateral power spectrum, the power spectral density of the windowed electrical signal is calculated

[0010] Optionally, dynamically filtering the denoised electrical signal to obtain a filtered electrical signal includes: Extracting power spectrum features corresponding to the power spectrum density of the denoised electrical signal; Based on the power spectrum characteristics, defining a main frequency band and a noise frequency band of the power spectrum density, wherein the noise frequency band includes a body temperature fluctuation frequency band and a circuit interference frequency band; According to the main frequency band and the noise frequency band, a preset dynamic bandwidth control algorithm is used to construct an adaptive filter for the denoising electrical signal; Based on the adaptive filter, the denoised electrical signal is dynamically filtered to obtain a filtered electrical signal.

[0011] Optionally, constructing the adaptive filter for denoising the electrical signal using a preset dynamic bandwidth control algorithm according to the main frequency band and the noise frequency band includes: Determining a signal-to-noise ratio and an analysis frequency of the denoised electrical signal according to the main frequency band and the noise frequency band; Based on the signal-to-noise ratio and the analysis frequency, the dynamic filtering bandwidth of the denoised electrical signal is constructed using the dynamic bandwidth control algorithm, wherein the dynamic bandwidth control algorithm:

[0012] in, Indicates the frequency of the denoised electrical signal The dynamic filter bandwidth at represents the reference bandwidth adjustment coefficient, Indicates the frequency of the denoised electrical signal The signal-to-noise ratio at represents the analysis frequency, represents the Nyquist frequency; An adaptive filter for removing noise from the electrical signal is constructed by using the dynamic filtering bandwidth.

[0013] Optionally, the generating of the intermediate information of the filtered electrical signal includes: converting the filtered electrical signal into a digital value; Mapping the digital value to a temperature value using a preset thermocouple graduation table; Performing cold-junction compensation on the temperature value to obtain a compensated temperature value to generate a time-temperature sequence of the filtered electrical signal; Based on the time-temperature sequence, intermediate information of the filtered electrical signal is extracted.

[0014] Optionally, calculating the waveform continuity of the intermediate information includes: Calculating the second-order difference of the intermediate information; Based on the second-order difference, marking discontinuity points of the intermediate information; Calculating the window ratio of the discontinuous point; The waveform continuity of the intermediate information is determined according to the window ratio.

[0015] Optionally, analyzing the respiratory failure coefficient of the target patient according to the respiratory curve includes: Analyzing the respiratory rate, tidal volume surrogate index, and respiratory rhythm variation coefficient of the target patient according to the respiratory curve; Based on the respiratory rate, tidal volume surrogate index and respiratory rhythm variation coefficient, the respiratory failure coefficient of the target patient is calculated using the following formula:

[0016] in, represents the respiratory failure coefficient of the target patient, Represents the respiratory rate, Indicates normal respiratory rate, represents the normalized span of respiratory rate, represents a surrogate index of tidal volume, Indicates the normal temperature difference reference value, represents the normalized span of temperature difference, represents the coefficient of variation of respiratory rhythm, represents the respiratory rate weight, represents the tidal volume weight, represents the rhythm variation weight.

[0017] A respiration detection method based on thermal tidal effect, characterized in that the method comprises: Fixing the breathing tube at the junction of the target patient's nasal cavity and the external air, so as to collect the tube wall temperature change signal of the target patient through the thermal sensor corresponding to the breathing tube; Converting the pipe wall temperature change signal into an electrical signal, and performing denoising on the electrical signal to obtain a denoised electrical signal; Calculating the power spectral density of the denoised electrical signal to dynamically filter the denoised electrical signal to obtain a filtered electrical signal; generating intermediate information of the filtered electrical signal and calculating waveform continuity of the intermediate information to construct a respiratory curve of the target patient; According to the respiratory curve, the respiratory failure coefficient of the target patient is analyzed, and based on the respiratory failure coefficient, multi-level warning parameters of the target patient are constructed, and the target patient's respiratory detection warning is performed based on the multi-level warning parameters.

[0018] First, the breathing tube is fixed at the junction of the patient's nasal cavity and the external air, and a thermal sensor is used to collect temperature change signals from the tube wall, enabling direct, non-invasive monitoring of the respiratory process. This greatly improves the patient's comfort and reduces the discomfort and psychological stress caused by monitoring. It is particularly suitable for patients who require long-term monitoring. Secondly, the system performs denoising on the collected signal, effectively eliminating body temperature fluctuation signals and circuit interference signals, ensuring signal purity and accuracy. This step lays a solid foundation for subsequent respiratory rate spectrum extraction and dynamic filtering, making the construction of the respiratory curve more accurate and reliable. Furthermore, by extracting the respiratory rate spectrum and performing dynamic filtering, the system can more clearly identify the patient's respiratory rate and pattern. Combined with the generated respiratory curve, it can intuitively understand the patient's respiratory status and promptly detect abnormalities. Finally, the system analyzes the respiratory failure coefficient based on the respiratory curve and constructs multi-level warning parameters, achieving real-time warning of the patient's respiratory status. This is crucial for promptly detecting and treating emergency situations such as respiratory failure, effectively reducing patient risks, and improving treatment efficacy. Therefore, the present invention can improve the accuracy and efficiency of respiratory detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A functional module diagram of a respiration detection system based on thermal tidal effect provided by one embodiment of the present invention; Figure 2 A schematic flow chart of a respiration detection method based on thermal tidal effect provided by one embodiment of the present invention; Figure 3 A structural diagram of a respiration detection system based on thermal tidal effect provided by one embodiment of the present invention; The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0021] In addition, the step sequence in the following method embodiments is only an example and not a strict limitation.

[0022] In fact, the server-side device deployed by the respiratory detection system based on the thermal tidal effect may be composed of one or more devices. The above-mentioned respiratory detection system based on the thermal tidal effect can be implemented as: a business instance, a virtual machine, and a hardware device. For example, the respiratory detection system based on the thermal tidal effect can be implemented as a business instance deployed on one or more devices in a cloud node. In simple terms, the respiratory detection system based on the thermal tidal effect can be understood as a software deployed on a cloud node, which is used to provide respiratory detection services based on the thermal tidal effect to each user terminal. Alternatively, the respiratory detection system based on the thermal tidal effect can also be implemented as a virtual machine deployed on one or more devices in a cloud node. Application software for managing each user terminal is installed in the virtual machine. Alternatively, the respiratory detection system based on the thermal tidal effect can also be implemented as a server consisting of many hardware devices of the same or different types, and one or more hardware devices are provided to provide respiratory detection services based on the thermal tidal effect to each user terminal.

[0023] In terms of implementation, the thermal tidal effect-based respiration detection system and the user end are mutually compatible. Specifically, if the thermal tidal effect-based respiration detection system is an application installed on a cloud service platform, the user end serves as a client that establishes a communication connection with the application. Alternatively, if the thermal tidal effect-based respiration detection system is implemented as a website, the user end serves as a webpage. Alternatively, if the thermal tidal effect-based respiration detection system is implemented as a cloud service platform, the user end serves as a mini-program within an instant messaging application.

[0024] Reference Figure 1 , which is a functional module diagram of a breathing detection system based on thermal tidal effect provided by an embodiment of the present invention.

[0025] The respiration detection system 100 based on the thermal tidal effect of the present invention can be arranged in a cloud server. In terms of implementation, it can be used as one or more service devices, or it can be installed as an application on the cloud (e.g., a server, server cluster, etc. for respiration detection based on the thermal tidal effect), or it can be developed as a website. According to the functions implemented, the respiration detection system 100 based on the thermal tidal effect includes a temperature signal acquisition module 101, an electrical signal denoising module 102, an electrical signal filtering module 103, a respiration curve construction module 104, and a respiration detection early warning module 105.

[0026] In an embodiment of the present invention, in the tracking of respiratory detection based on the thermal tidal effect, each of the above modules can be implemented independently and called with other modules. The call here can be understood as that a certain module can be connected to multiple modules of another type and provide corresponding services to the multiple modules connected to it. In the respiratory detection system based on the thermal tidal effect provided by the embodiment of the present invention, there is no need to modify the program code. The scope of application of the respiratory detection architecture based on the thermal tidal effect can be adjusted by adding modules and directly calling them, so as to achieve cluster-type horizontal expansion, so as to achieve the purpose of quickly and flexibly expanding the respiratory detection system based on the thermal tidal effect. In actual applications, the above modules can be arranged in the same device or different devices, or they can be arranged in a virtual device, such as a service instance in a cloud server.

[0027] The following describes various components and specific workflows of a respiration detection system based on thermal tidal effects in conjunction with specific embodiments.

[0028] The temperature signal acquisition module 101 is used to fix the breathing tube at the junction of the target patient's nasal cavity and the external air, so as to acquire the tube wall temperature change signal of the target patient through the thermal sensor corresponding to the breathing tube.

[0029] The present invention fixes a breathing tube at the junction of the target patient's nasal cavity and the external air, and collects the tube wall temperature change signal of the target patient through a thermal sensor corresponding to the breathing tube to realize direct and non-invasive monitoring of the breathing process.

[0030] In detail, the collecting of the tube wall temperature change signal of the target patient by the thermal sensor corresponding to the breathing tube includes: Capturing the effectiveness of the breathing tube for the target patient's inhaled and exhaled gases; Determining a temperature gradient significance value of the target patient according to the effectiveness coefficient; Optimizing the position of the thermal sensor on the breathing tube according to the temperature gradient significance value to collect an initial tube wall temperature change signal of the target patient; analyzing an abnormal state of the initial pipe wall temperature change signal; When the abnormal state meets the preset abnormal standard state, the initial tube wall temperature change signal is used as the tube wall temperature change signal of the target patient.

[0031] The effectiveness coefficient measures the efficiency of the respiratory tube in capturing the target patient's inhaled and exhaled gases. It reflects the proportion of exhaled / inhaled gas that effectively flows through or contacts the thermal sensor, causing detectable temperature changes. The temperature gradient significance value refers to the severity or magnitude of the temperature change near the sensor caused by the flow of inhaled (usually cooler) and exhaled (usually warmer) gases within the respiratory tube. The initial tube wall temperature change signal refers to the raw data initially collected by the thermal sensor after optimizing the sensor position, without any processing (such as denoising or filtering), reflecting the temperature change of the respiratory tube wall (or more accurately, the gas or tube wall surface with which the sensor directly contacts) over the respiratory cycle. The abnormal state refers to a state in which the initial tube wall temperature change signal, after analysis, shows that it does not conform to a normal, regular breathing pattern. The abnormal standard state refers to a pre-set reference standard used to determine whether the initial tube wall temperature change signal is "abnormal." The tube wall temperature change signal refers to a screened tube wall temperature change signal that is deemed reliable and can be used for subsequent respiratory analysis.

[0032] Optionally, the effectiveness of capturing the breathing tube for the target patient's inhaled gas and exhaled gas is mainly achieved by analyzing the extent to which the inhaled gas and exhaled gas pass through the breathing tube.

[0033] Furthermore, determining the temperature gradient significance value of the target patient according to the effectiveness coefficient includes: When the effectiveness coefficient meets a preset effectiveness coefficient threshold, analyzing the maximum temperature and the minimum temperature of the cycle corresponding to the target patient of the thermal sensor; determining a maximum rate of change of a periodic temperature of the target patient; Based on the maximum temperature of the cycle, the minimum temperature of the cycle, and the maximum rate of change of the temperature of the cycle, the temperature gradient significance value of the target patient is calculated using the following formula:

[0034] in, Indicates the significant value of the temperature gradient of the target patient, Indicates the maximum temperature of the cycle, Indicates the lowest temperature of the cycle, represents the standard deviation of ambient temperature noise, Indicates the The instantaneous temperature change rate of each sampling point, Indicates the The instantaneous temperature of each sampling point, Indicates the maximum rate of change of cycle temperature, Indicates the number of sampling points corresponding to the respiratory cycle of the target patient, Indicates cyclic stability.

[0035] Among them, the effective coefficient threshold refers to the numerical limit used to determine whether the captured "effective coefficient" has reached an acceptable or sufficiently high level. The maximum temperature of the cycle refers to the highest value of the tube wall temperature detected by the thermal sensor in a complete respiratory cycle (one inhalation and one exhalation). The minimum temperature of the cycle refers to the lowest value of the tube wall temperature detected by the thermal sensor in a complete respiratory cycle. The maximum rate of change of the cycle temperature refers to the rate of change at the moment when the temperature changes the fastest in a respiratory cycle. The standard deviation of the ambient temperature noise refers to a measure of the degree of random fluctuation of the ambient temperature. The instantaneous temperature refers to the tube wall temperature value detected by the thermal sensor at a specific sampling moment. The instantaneous temperature change rate refers to the speed of temperature change at a certain moment or in a very short time interval. The cycle stability refers to the consistency of the target patient's respiratory cycle in time length and pattern.

[0036] The electrical signal denoising module 102 is configured to convert the pipe wall temperature change signal into an electrical signal and denoise the electrical signal to obtain a denoised electrical signal.

[0037] The present invention converts the pipe wall temperature change signal into an electrical signal, providing a basis for subsequent analysis. The electrical signal refers to an electronic representation of the pipe wall temperature change signal. Specifically, the conversion of the pipe wall temperature change signal into an electrical signal can be represented by a voltage value. A change in temperature causes a sensor (such as a thermistor, platinum resistance thermometer, thermocouple, or semiconductor temperature sensor) to produce a corresponding voltage change. The magnitude of this voltage reflects the temperature. For example, as temperature rises, the voltage may increase linearly or change nonlinearly. The de-noised electrical signal refers to a signal obtained by removing noise from the electrical signal. Specifically, low-pass filtering can be used to de-noise the electrical signal.

[0038] The electrical signal filtering module 103 is used to calculate the power spectrum density of the denoised electrical signal to dynamically filter the denoised electrical signal to obtain a filtered electrical signal.

[0039] The present invention calculates the power spectral density of the denoised electrical signal, which can effectively calculate the power spectral density of the denoised electrical signal and is used to analyze the frequency components and energy distribution of the signal.

[0040] In detail, the calculating the power spectral density of the denoised electrical signal includes: Segmenting the denoised electrical signal to obtain segmented electrical signals; Performing windowing on the segmented electrical signal to obtain a windowed electrical signal; analyzing the complex spectrum of the windowed electrical signal; and calculating the unilateral power spectrum of the windowed electrical signal through the complex spectrum; Based on the unilateral power spectrum, a power spectrum density of the windowed electrical signal is calculated.

[0041] Among them, the segmented electrical signal refers to dividing the original, longer denoised electrical signal into multiple shorter, non-overlapping or partially overlapping subsequences; the windowed electrical signal refers to the new signal obtained by multiplying the segmented electrical signal (segmented electrical signal) by a specific mathematical window function; the complex spectrum refers to the result obtained by applying the fast Fourier transform (FFT) or other discrete Fourier transform (DFT) algorithm to the windowed electrical signal; the unilateral power spectrum refers to the power spectrum calculated from the complex spectrum; and the power spectral density refers to the power within a unit frequency.

[0042] Optionally, windowing the segmented electrical signal to obtain the windowed electrical signal can be achieved by using a Hanning window, a Hamming window, a Blackman window, or the like.

[0043] The present invention dynamically filters the denoised electrical signal to obtain a filtered electrical signal, which can improve the quality of the signal and the accuracy of subsequent signal analysis.

[0044] In detail, the dynamically filtering the denoised electrical signal to obtain a filtered electrical signal includes: Extracting power spectrum features corresponding to the power spectrum density of the denoised electrical signal; Based on the power spectrum characteristics, defining a main frequency band and a noise frequency band of the power spectrum density, wherein the noise frequency band includes a body temperature fluctuation frequency band and a circuit interference frequency band; According to the main frequency band and the noise frequency band, a preset dynamic bandwidth control algorithm is used to construct an adaptive filter for the denoising electrical signal; Based on the adaptive filter, the denoised electrical signal is dynamically filtered to obtain a filtered electrical signal.

[0045] Among them, the power spectrum feature refers to the key parameters extracted from the calculated power spectral density (PSD) that can characterize the frequency domain characteristics of the signal, such as spectral peaks, spectral valleys, frequency band energy and other features; the main frequency band refers to the frequency range defined according to the extracted power spectrum feature and containing the main energy or information of the signal; the body temperature fluctuation frequency band refers to the frequency range related to the slow change of human body temperature; the circuit interference frequency band refers to the frequency range of the interference signal introduced by the measurement circuit itself or the external electromagnetic environment; the dynamic bandwidth control algorithm refers to an algorithm that can automatically adjust the filter parameters (such as passband, stopband, bandwidth, cutoff frequency, etc.) according to the characteristics of the input signal (here is the power spectrum feature) or external conditions; the adaptive filter refers to a filter whose parameters (such as coefficients, bandwidth, center frequency, etc.) can be automatically adjusted according to the input signal or preset rules; the filtered electrical signal refers to the output signal obtained after the original denoised electrical signal is processed by the adaptive filter constructed as described above.

[0046] Furthermore, the adaptive filter for denoising the electrical signal is constructed using a preset dynamic bandwidth control algorithm based on the main frequency band and the noise frequency band, including: Determining a signal-to-noise ratio and an analysis frequency of the denoised electrical signal according to the main frequency band and the noise frequency band; Based on the signal-to-noise ratio and the analysis frequency, the dynamic filtering bandwidth of the denoised electrical signal is constructed using the dynamic bandwidth control algorithm, wherein the dynamic bandwidth control algorithm:

[0047] in, Indicates the frequency of the denoised electrical signal The dynamic filter bandwidth at represents the reference bandwidth adjustment coefficient, Indicates the frequency of the denoised electrical signal The signal-to-noise ratio at represents the analysis frequency, represents the Nyquist frequency; An adaptive filter for removing noise from the electrical signal is constructed by using the dynamic filtering bandwidth.

[0048] The signal-to-noise ratio is an indicator of signal quality, which represents the ratio of signal power to noise power. The analysis frequency is the specific frequency value at which the filter parameters (such as bandwidth) are currently being calculated or adjusted. The dynamic filter bandwidth is the value of the dynamic filter bandwidth at the specific analysis frequency. f, the frequency range allowed to pass by the adaptive filter, the reference bandwidth adjustment coefficient refers to the coefficient used to adjust the basic size of the dynamic filter bandwidth, and the Nyquist frequency refers to half of the sampling rate of the denoised electrical signal.

[0049] The respiratory curve construction module 104 is configured to generate intermediate information of the filtered electrical signal and calculate waveform continuity of the intermediate information to construct a respiratory curve of the target patient.

[0050] The intermediate information of the filtered electrical signal generated by the present invention can accurately generate time-temperature intermediate data for respiratory analysis.

[0051] In detail, the intermediate information for generating the filtered electrical signal includes: converting the filtered electrical signal into a digital value; Mapping the digital value to a temperature value using a preset thermocouple graduation table; Performing cold-junction compensation on the temperature value to obtain a compensated temperature value to generate a time-temperature sequence of the filtered electrical signal; Based on the time-temperature sequence, intermediate information of the filtered electrical signal is extracted.

[0052] Among them, the digital value refers to the output result of the filtered electrical signal after analog-to-digital conversion (ADC), the thermocouple scale refers to a table that describes the specific nonlinear relationship between the generated electrical signal (voltage, i.e., the voltage represented by the digital value) and the measured temperature, the temperature value refers to the mapping (conversion) of the digital value (representing the voltage) to the corresponding temperature value, the compensated temperature value refers to the temperature value corrected to the original temperature value to eliminate the influence of the non-zero cold end temperature on the measurement result, the time-temperature sequence refers to the sequence that associates each compensated temperature value with its corresponding sampling time point, and the intermediate information refers to the specific characteristics, parameters or statistics extracted from the time-temperature sequence for further processing or analysis.

[0053] Optionally, the temperature value is subjected to cold-end compensation to obtain a compensated temperature value, wherein the compensated temperature value = the original temperature value + (the thermoelectric potential at 0 degrees Celsius - the thermoelectric potential at the actual cold-end temperature).

[0054] The waveform continuity of the intermediate information calculated by the present invention can be used to further analyze the reliability of the intermediate information, thereby improving the accuracy of subsequent analysis of the target patient's status.

[0055] In detail, the calculating of the waveform continuity of the intermediate information includes: Calculating the second-order difference of the intermediate information; Based on the second-order difference, marking discontinuity points of the intermediate information; Calculating the window ratio of the discontinuous point; The waveform continuity of the intermediate information is determined according to the window ratio.

[0056] Among them, the second-order difference refers to the result obtained by performing two differential operations on the intermediate information, the discontinuity point refers to the point in the calculated second-order difference sequence where the value jumps significantly or deviates from the normal range, the window ratio refers to an indicator that measures the relative density of discontinuity points within a specific time window, and the waveform continuity refers to a quantitative assessment of the overall or local smoothness and continuity of the intermediate information (time-temperature series).

[0057] Optionally, marking discontinuities in the intermediate information based on the second-order difference is typically achieved by setting a threshold. When the absolute value of the second-order difference exceeds the threshold, the corresponding point in the intermediate information sequence is marked as a discontinuity. This threshold can be set based on statistical characteristics of the signal (e.g., standard deviation).

[0058] The present invention constructs a respiratory curve for the target patient, which can more clearly identify the patient's respiratory rate and pattern. The respiratory curve shows the target patient's breathing pattern over time. In detail, the respiratory curve uses matplotlib to plot a continuous temperature change curve with time as the horizontal axis and temperature as the vertical axis.

[0059] The respiratory detection and warning module 105 is used to analyze the respiratory failure coefficient of the target patient according to the respiratory curve, construct multi-level warning parameters of the target patient based on the respiratory failure coefficient, and perform respiratory detection and warning of the target patient based on the multi-level warning parameters.

[0060] The present invention analyzes the respiratory failure coefficient of the target patient according to the respiratory curve, so as to intuitively understand the patient's respiratory condition and discover abnormal conditions in time.

[0061] In detail, analyzing the respiratory failure coefficient of the target patient according to the respiratory curve includes: Analyzing the respiratory rate, tidal volume surrogate index, and respiratory rhythm variation coefficient of the target patient according to the respiratory curve; Based on the respiratory rate, tidal volume surrogate index and respiratory rhythm variation coefficient, the respiratory failure coefficient of the target patient is calculated using the following formula:

[0062] in, represents the respiratory failure coefficient of the target patient, Represents the respiratory rate, Indicates normal respiratory rate, represents the normalized span of respiratory rate, represents a surrogate index of tidal volume, Indicates the normal temperature difference reference value, represents the normalized span of temperature difference, represents the coefficient of variation of respiratory rhythm, represents the respiratory rate weight, represents the tidal volume weight, represents the rhythm variation weight.

[0063] Among them, the respiratory rate refers to the number of times the patient breathes per unit time (usually per minute), the tidal volume surrogate index refers to the amplitude of temperature change in each respiratory cycle in the respiratory curve, the respiratory rhythm variation coefficient refers to an index for measuring the stability of the patient's respiratory rhythm, the respiratory failure coefficient refers to a quantitative assessment of the risk of respiratory failure in the target patient, the respiratory frequency normalization span refers to a parameter used to normalize the normal respiratory frequency, the temperature difference normalization span refers to a parameter used to normalize the normal temperature difference reference value, the respiratory frequency weight refers to the weight coefficient assigned to the normalized respiratory frequency deviation item, the tidal volume weight refers to the weight coefficient assigned to the normalized tidal volume surrogate index deviation item, and the rhythm variation weight refers to the weight coefficient assigned to the respiratory rhythm variation coefficient item.

[0064] Based on the respiratory failure index, the present invention constructs multi-level warning parameters for the target patient, enabling real-time early warning of the patient's respiratory status and effectively reducing patient risk. The multi-level warning parameters include risk levels and warning actions. For example, each risk level is assigned a corresponding respiratory failure index (RFI) threshold range, such as Level 1 (Normal): RFI < 0.2; Level 2 (Concern): 0.2 ≤ RFI < 0.5; Level 3 (Warning): 0.5 ≤ RFI < 0.8; and Level 4 (Critical): RFI ≥ 0.8. Associated warning actions define corresponding warning actions or recommended measures for each risk level. For example: Level 1: No special action required, continue routine monitoring. Level 2: A prompt pops up on the nurse's workstation, increasing monitoring frequency and recording abnormalities. Level 3: An audible / visual alarm sounds, notifying the on-duty nurse and preparing any necessary medications or equipment. Level 4: The highest level of alert, notifying the doctor and emergency team for immediate intervention.

[0065] Finally, the present invention performs the target patient's breathing detection warning based on the multi-level warning parameters to achieve efficient monitoring of the target patient's breathing.

[0066] First, the breathing tube is fixed at the junction of the patient's nasal cavity and the external air, and a thermal sensor is used to collect temperature change signals from the tube wall, enabling direct, non-invasive monitoring of the respiratory process. This greatly improves the patient's comfort and reduces the discomfort and psychological stress caused by monitoring. It is particularly suitable for patients who require long-term monitoring. Secondly, the system performs denoising on the collected signal, effectively eliminating body temperature fluctuation signals and circuit interference signals, ensuring signal purity and accuracy. This step lays a solid foundation for subsequent respiratory rate spectrum extraction and dynamic filtering, making the construction of the respiratory curve more accurate and reliable. Furthermore, by extracting the respiratory rate spectrum and performing dynamic filtering, the system can more clearly identify the patient's respiratory rate and pattern. Combined with the generated respiratory curve, it can intuitively understand the patient's respiratory status and promptly detect abnormalities. Finally, the system analyzes the respiratory failure coefficient based on the respiratory curve and constructs multi-level warning parameters, achieving real-time warning of the patient's respiratory status. This is crucial for promptly detecting and treating emergency situations such as respiratory failure, effectively reducing patient risks, and improving treatment efficacy. Therefore, the present invention can improve the accuracy and efficiency of respiratory detection.

[0067] like Figure 2 FIG. 1 is a flow chart of a respiration detection method based on the thermal tidal effect according to an embodiment of the present invention. In this embodiment, the respiration detection method based on the thermal tidal effect includes: Fixing the breathing tube at the junction of the target patient's nasal cavity and the external air, so as to collect the tube wall temperature change signal of the target patient through the thermal sensor corresponding to the breathing tube; Converting the pipe wall temperature change signal into an electrical signal, and performing denoising on the electrical signal to obtain a denoised electrical signal; Calculating the power spectral density of the denoised electrical signal to dynamically filter the denoised electrical signal to obtain a filtered electrical signal; generating intermediate information of the filtered electrical signal and calculating waveform continuity of the intermediate information to construct a respiratory curve of the target patient; According to the respiratory curve, the respiratory failure coefficient of the target patient is analyzed, and based on the respiratory failure coefficient, multi-level warning parameters of the target patient are constructed, and the target patient's respiratory detection warning is performed based on the multi-level warning parameters.

[0068] In the several embodiments provided by the present invention, it should be understood that the provided systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the module division is merely a logical function division, and actual implementation may employ other division methods.

[0069] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0070] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

[0071] Reference Figure 3 A structural diagram of a respiratory detection method based on the thermal tidal effect provided in one embodiment of the present invention includes a breathing tube 1, a thermal sensor 2, a data acquisition and preprocessing module 3, a data post-processing and feedback module 4, and a power module 5. The sensing portion of the thermal sensor 2 is connected to the breathing tube 1 and fixed at the junction of the patient's nasal cavity and the external air. The output end portion of the thermal sensor 2 is connected to the data acquisition and preprocessing module 3. The data acquisition and preprocessing module 3 implements signal denoising and filtering, and further processes the filtered electrical signal after denoising and filtering in the data post-processing and feedback module 4 to analyze the respiratory failure coefficient of the target patient and issue an early warning. The data acquisition and preprocessing module 3 and the data post-processing and feedback module 4 are powered by the power module 5.

Claims

1. A breathing detection system based on thermal tidal effect, characterized in that: The breathing detection system based on thermal tidal effect includes: The temperature signal acquisition module is used to fix the breathing tube at the junction of the target patient's nasal cavity and the external air, so as to acquire the tube wall temperature change signal of the target patient through the thermal sensor corresponding to the breathing tube; The electrical signal denoising module is used to convert the pipe wall temperature change signal into an electrical signal and denoise the electrical signal to obtain a denoised electrical signal; The electrical signal filtering module is used to calculate the power spectrum density of the denoised electrical signal to dynamically filter the denoised electrical signal to obtain a filtered electrical signal; The respiratory curve construction module is used to generate intermediate information of the filtered electrical signal and calculate the waveform continuity of the intermediate information to construct the respiratory curve of the target patient; The respiratory detection and warning module is used to analyze the respiratory failure coefficient of the target patient according to the respiratory curve, construct multi-level warning parameters of the target patient based on the respiratory failure coefficient, and perform respiratory detection and warning of the target patient based on the multi-level warning parameters.

2. The breathing detection system based on thermal tidal effect according to claim 1, characterized in that: The collecting of the tube wall temperature change signal of the target patient by the thermal sensor corresponding to the breathing tube includes: Capturing the effectiveness of the breathing tube for the target patient's inhaled and exhaled gases; Determining a temperature gradient significance value of the target patient according to the effectiveness coefficient; Optimizing the position of the thermal sensor on the breathing tube according to the temperature gradient significance value to collect an initial tube wall temperature change signal of the target patient; analyzing an abnormal state of the initial pipe wall temperature change signal; When the abnormal state meets the preset abnormal standard state, the initial tube wall temperature change signal is used as the tube wall temperature change signal of the target patient.

3. The respiration detection system based on thermal tidal effect according to claim 2, characterized in that: Determining the temperature gradient significance value of the target patient according to the effectiveness coefficient includes: When the effectiveness coefficient meets a preset effectiveness coefficient threshold, analyzing the maximum temperature and the minimum temperature of the cycle corresponding to the target patient of the thermal sensor; determining a maximum rate of change of a periodic temperature of the target patient; Based on the maximum temperature of the cycle, the minimum temperature of the cycle, and the maximum rate of change of the temperature of the cycle, the temperature gradient significance value of the target patient is calculated using the following formula: ； in, Indicates the significant value of the temperature gradient of the target patient, Indicates the maximum temperature of the cycle, Indicates the lowest temperature of the cycle, represents the standard deviation of ambient temperature noise, Indicates the The instantaneous temperature change rate of each sampling point, Indicates the The instantaneous temperature of each sampling point, Indicates the maximum rate of change of cycle temperature, Indicates the number of sampling points corresponding to the respiratory cycle of the target patient, Indicates cyclic stability.

4. The respiration detection system based on thermal tidal effect according to claim 3, wherein: The calculating the power spectral density of the denoised electrical signal comprises: Segmenting the denoised electrical signal to obtain segmented electrical signals; Performing windowing on the segmented electrical signal to obtain a windowed electrical signal; analyzing the complex spectrum of the windowed electrical signal; and calculating the unilateral power spectrum of the windowed electrical signal through the complex spectrum; Based on the unilateral power spectrum, a power spectrum density of the windowed electrical signal is calculated.

5. The breathing detection system based on thermal tidal effect according to claim 4, characterized in that: The dynamically filtering the denoised electrical signal to obtain a filtered electrical signal includes: Extracting power spectrum features corresponding to the power spectrum density of the denoised electrical signal; Based on the power spectrum characteristics, defining a main frequency band and a noise frequency band of the power spectrum density, wherein the noise frequency band includes a body temperature fluctuation frequency band and a circuit interference frequency band; According to the main frequency band and the noise frequency band, a preset dynamic bandwidth control algorithm is used to construct an adaptive filter for the denoising electrical signal; Based on the adaptive filter, the denoised electrical signal is dynamically filtered to obtain a filtered electrical signal.

6. The respiration detection system based on thermal tidal effect according to claim 5, characterized in that: The method of constructing the adaptive filter for denoising the electrical signal using a preset dynamic bandwidth control algorithm according to the main frequency band and the noise frequency band includes: Determining a signal-to-noise ratio and an analysis frequency of the denoised electrical signal according to the main frequency band and the noise frequency band; Based on the signal-to-noise ratio and the analysis frequency, the dynamic filtering bandwidth of the denoised electrical signal is constructed using the dynamic bandwidth control algorithm, wherein the dynamic bandwidth control algorithm: ； in, Indicates the frequency of the denoised electrical signal The dynamic filter bandwidth at represents the reference bandwidth adjustment coefficient, Indicates the frequency of the denoised electrical signal The signal-to-noise ratio at represents the analysis frequency, represents the Nyquist frequency; An adaptive filter for removing noise from the electrical signal is constructed by using the dynamic filtering bandwidth.

7. The respiration detection system based on thermal tidal effect according to claim 6, characterized in that: The intermediate information for generating the filtered electrical signal includes: converting the filtered electrical signal into a digital value; Mapping the digital value to a temperature value using a preset thermocouple graduation table; Performing cold-junction compensation on the temperature value to obtain a compensated temperature value to generate a time-temperature sequence of the filtered electrical signal; Based on the time-temperature sequence, intermediate information of the filtered electrical signal is extracted.

8. The respiration detection system based on thermal tidal effect according to claim 7, characterized in that: The calculating the waveform continuity of the intermediate information includes: Calculating the second-order difference of the intermediate information; Based on the second-order difference, marking discontinuity points of the intermediate information; Calculating the window ratio of the discontinuous point; The waveform continuity of the intermediate information is determined according to the window ratio.

9. The respiration detection system based on thermal tidal effect according to claim 8, characterized in that: Analyzing the respiratory failure coefficient of the target patient according to the respiratory curve includes: Analyzing the respiratory rate, tidal volume surrogate index, and respiratory rhythm variation coefficient of the target patient according to the respiratory curve; Based on the respiratory rate, tidal volume surrogate index and respiratory rhythm variation coefficient, the respiratory failure coefficient of the target patient is calculated using the following formula: ； in, represents the respiratory failure coefficient of the target patient, Represents the respiratory rate, Indicates normal respiratory rate, represents the normalized span of respiratory rate, represents a surrogate index of tidal volume, Indicates the normal temperature difference reference value, represents the normalized span of temperature difference, represents the coefficient of variation of respiratory rhythm, represents the respiratory rate weight, represents the tidal volume weight, represents the rhythm variation weight.

10. A breathing detection method based on thermal tidal effect, characterized in that: The method comprises: Fixing the breathing tube at the junction of the target patient's nasal cavity and the external air, so as to collect the tube wall temperature change signal of the target patient through the thermal sensor corresponding to the breathing tube; Converting the pipe wall temperature change signal into an electrical signal, and performing denoising on the electrical signal to obtain a denoised electrical signal; Calculating the power spectral density of the denoised electrical signal to dynamically filter the denoised electrical signal to obtain a filtered electrical signal; generating intermediate information of the filtered electrical signal and calculating waveform continuity of the intermediate information to construct a respiratory curve of the target patient; According to the respiratory curve, the respiratory failure coefficient of the target patient is analyzed, and based on the respiratory failure coefficient, multi-level warning parameters of the target patient are constructed, and the target patient's respiratory detection warning is performed based on the multi-level warning parameters.

Images