Intelligent monitoring device and method for inhaler based on audio signals

Abstract

The invention discloses an inhaler intelligent monitoring device and method based on an audio signal. The monitoring device comprises a shell, and the shell comprises a hollow screw cover and a base; the hollow screw cap is installed on the base, and a PCB is installed in the base. An electronic module and a USB (Universal Serial Bus) data interface are arranged on the PCB, the electronic module comprises an audio sensor system, and the shell is used for placing the inhaler and transmitting the audio signal change caused by the air inlet flow rate of the inhaler to the sensor system for measurement. Audio signal changes caused by the inlet air flow velocity of the inhaler are detected and transmitted to the sensor system to calculate the flow velocity of the air inlet, and an inspiration flow curve is drawn at the client, so that real-time flow data feedback is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of inhaler monitoring, and in particular to an intelligent inhaler monitoring device and method based on audio signals. Background Art

[0002] An inhaler is a medical device used to deliver medication directly to the lungs, typically for the treatment of respiratory conditions such as asthma and chronic obstructive pulmonary disease (COPD). Inhalers are designed so that medication can quickly reach the respiratory tract and lungs through inhalation, providing rapid symptom relief or therapeutic effects.

[0003] The correct use of inhalers directly affects whether patients can effectively inhale medication, thereby ensuring treatment effectiveness. However, in actual applications, improper patient operation, such as insufficient inhalation force, may prevent the drug from fully entering the respiratory tract, thereby affecting the treatment effect. In addition, some patients are unaware when inhalation fails, resulting in decreased long-term treatment compliance and even more serious health problems. Therefore, real-time monitoring of inhaler usage status, timely identification of ineffective operation, and providing patient feedback are of great significance for improving the effectiveness of inhalation therapy and improving patient health.

[0004] Existing inhaler usage monitoring technologies mainly use two detection methods: air pressure signals or sound signals. Among them, monitoring technology based on air pressure signals usually requires the addition of an air pressure transmission structure inside or outside the inhaler to detect negative pressure changes, but this solution has two significant limitations: first, the physical modification of the air flow channel will change the original flow field characteristics, which may affect the delivery stability of the drug aerosol; second, the integration of the air pressure sensor not only increases the complexity of the system design, but also significantly increases the hardware cost. In comparison, the detection method based on sound signals does not require the modification of the internal structure of the inhaler, but there are new technical challenges such as environmental noise interference.

[0005] In contrast, monitoring methods based on sound signals have attracted attention due to their non-invasive characteristics. During use, inhalers produce specific airflow sounds, the characteristics of which can be used to identify different inhalation states. However, interference from environmental noise, differences in individual patients' inhalation methods, and differences in inhaler structures can all affect the collection and analysis of sound signals. Therefore, in order to achieve high-precision inhalation monitoring, more advanced signal processing and noise suppression algorithms are needed to ensure the reliability of the monitoring system in complex environments. Summary of the Invention

[0006] The purpose of the present invention is to solve the above-mentioned technical problems and provide an intelligent monitoring device and method for inhalers based on audio signals. The device aims to improve the accuracy of inhalation status recognition through advanced audio signal processing technology while avoiding changes to the original structure of the inhaler, thereby achieving accurate monitoring and guidance of the patient's inhalation process and improving the effectiveness of drug inhalation.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] An intelligent inhaler monitoring device based on audio signals comprises a housing, the housing including a hollow rotary cover and a base; the hollow rotary cover is mounted on the base, a PCB is mounted within the base; the PCB is provided with an electronic module and a USB data interface, the electronic module including an audio sensor system; the housing is used to house the inhaler and transmit audio signal changes caused by the inhaler's air intake flow rate to the sensor system for measurement.

[0009] Furthermore, an electronic module compartment and a battery compartment are provided inside the base, and a PCB board is installed in the electronic module compartment; the PCB board is fixed in the electronic module compartment using an installation box; and the battery compartment is used to install a battery that provides power for the PCB board.

[0010] Furthermore, the hollow rotary cover and the base are used to fix the inhaler base on the housing, so that the housing and the inhaler base can form a whole and move together.

[0011] Furthermore, the electronic module also includes a communication module, a power supply system and a voice-controlled switch, and the communication module adopts a combination of one or more of a low-power Bluetooth module, a Wi-Fi module, a Zigbee module, a LoRa module, a Thread module, a 4G cellular network module or a 5G cellular network module.

[0012] Furthermore, the inhaler is a metered dose inhaler, a dry powder inhaler, a nebulizer inhaler or a soft mist inhaler.

[0013] In another aspect, the present invention provides an intelligent monitoring method for an inhaler based on audio signals, which uses the above-mentioned intelligent monitoring device for an inhaler based on audio signals, and follows the following steps:

[0014] The client obtains the audio signal data detected in the sensor system through the communication module;

[0015] Construct fitting models using sensor data fusion algorithms based on Kalman filtering, machine learning, and deep learning;

[0016] Select the optimal model and determine the relevant model parameters as the target algorithm;

[0017] calculating an intake air flow rate of the inhaler device using a target algorithm based on the obtained audio signal value;

[0018] Draw the suction flow curve on the client side according to the intake air flow rate.

[0019] Furthermore, the optimal model is selected and the relevant model parameters are determined as the target algorithm, and the determination coefficient (R 2 ), mean absolute error (MAE), mean square error (MSE) and root mean square error (RMSE) are normalized and determined.

[0020] In another aspect, the present invention provides a method for identifying incorrect inhaler usage based on audio signals, using the above-mentioned intelligent inhaler monitoring device based on audio signals, comprising the following steps:

[0021] The client obtains the audio signal data detected in the sensor system through the communication module;

[0022] Perform feature extraction on the acquired audio data;

[0023] Using the extracted features (and features formed by their permutations and combinations), a classification model is constructed based on machine learning and deep learning algorithms;

[0024] Select the optimal model and determine the relevant model parameters as the target algorithm;

[0025] identifying incorrect use of the inhaler using a target algorithm based on the obtained audio signal value;

[0026] If an incorrect usage is encountered, the user will be reminded on the client side to correct the operation.

[0027] Furthermore, the feature extraction methods include: spectrogram, cepstral graph, Mel-spectrogram, Mel-frequency cepstral coefficient (MFCC), energy spectrum, pitch feature graph, zero crossing rate, and audio bandwidth.

[0028] Furthermore, the selection of the optimal model and determination of relevant model parameters as the target algorithm are determined by comprehensively evaluating the accuracy, precision, recall, specificity, F1 value (F1Score) and area under the receiver operating characteristic curve (AUC-ROC) indicators.

[0029] The present invention provides an intelligent inhaler monitoring device and method based on audio signals, which have the following beneficial effects: by detecting the changes in audio signals caused by the inhaler's air flow rate, the audio signals are transmitted to a sensor system to calculate the flow rate at the air inlet, and an inhalation flow curve is plotted on the client, achieving real-time flow data feedback; in addition, the present invention can also detect inhaler misuse (such as reverse exhalation) and promptly remind the user to correct the operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The specific embodiments of the present invention are further described in detail below with reference to the accompanying drawings:

[0031] Figure 1 A schematic structural diagram of an intelligent inhaler monitoring device based on audio signals provided by the present invention;

[0032] Figure 2 A schematic diagram of the explosion structure of an intelligent inhaler monitoring device based on audio signals provided by the present invention;

[0033] Figure 3 A schematic diagram of the internal connection structure of an intelligent inhaler monitoring device based on audio signals provided by the present invention;

[0034] Figure 4 A flowchart of an intelligent monitoring method for an inhaler based on audio signals provided by the present invention;

[0035] Figure 5 The present invention provides a flowchart of a method for identifying incorrect use of an inhaler based on audio signals.

[0036] Explanation of the reference numerals in the figure: 10, housing; 20, hollow screw cap; 30, base; 31, mounting box; 32, battery compartment; 33, battery compartment cover; 34, electronic module compartment; 40, PCB board; 41, electronic module; 42, USB data interface; 50, inhaler; 51, inhaler base. DETAILED DESCRIPTION

[0037] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0038] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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.

[0039] It should be noted that all directional indications in the embodiments of the present invention (such as up-down-left-right-front-back...) are only used to explain the relative position relationship - movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly. The connection can be a direct connection or an indirect connection.

[0040] like Figure 1-Figure 3 As shown, an intelligent monitoring device for an inhaler based on audio signals includes a housing 10, wherein the housing 10 includes a hollow rotary cover 20 and a base 30; the hollow rotary cover 20 is mounted on the base 30, and a PCB board 40 is mounted in the base 30; the PCB board 40 is provided with an electronic module 41 and a USB data interface 42, and the electronic module 41 includes an audio sensor system. The housing 10 is used to place an inhaler 50 and transmit the audio signal changes caused by the air flow velocity of the inhaler 50 to the sensor system for measurement.

[0041] By adopting the above technical solution, the audio signal changes caused by the inhaler's air flow rate are detected and transmitted to the sensor system to calculate the flow rate at the air inlet, and the inhalation flow curve is drawn on the client to achieve real-time flow data feedback.

[0042] Specifically, an electronic module compartment 34 and a battery compartment 32 are provided inside the base 10, and a PCB board 40 is installed in the electronic module compartment 34; the PCB board 40 is fixed in the electronic module compartment 34 using an installation box 31; the battery compartment 32 is used to install a battery that provides power for the PCB board.

[0043] Specifically, the hollow rotary cover 20 and the base 30 are used to fix the inhaler base 51 on the housing 10, so that the housing 10 and the inhaler base 51 can form a whole and move together.

[0044] Specifically, the electronic module 41 also includes a communication module, a power supply system and a voice-controlled switch. The communication module adopts a combination of one or more of a low-power Bluetooth module, a Wi-Fi module, a Zigbee module, a LoRa module, a Thread module, a 4G cellular network module or a 5G cellular network module.

[0045] Specifically, the inhaler 50 is a metered dose inhaler, a dry powder inhaler, a nebulizer inhaler or a soft mist inhaler.

[0046] In another aspect, the present invention provides an intelligent monitoring method for an inhaler based on audio signals, which uses the above-mentioned intelligent monitoring device for an inhaler based on audio signals, and follows the following steps:

[0047] The client obtains the audio signal data detected in the sensor system through the communication module;

[0048] Construct fitting models using sensor data fusion algorithms based on Kalman filtering, machine learning, and deep learning;

[0049] Select the optimal model and determine the relevant model parameters as the target algorithm;

[0050] Calculating the intake air flow rate of the inhaler (50) device using a target algorithm based on the obtained audio signal value;

[0051] Draw the suction flow curve on the client side according to the intake air flow rate.

[0052] The optimal model is selected and the relevant model parameters are determined as the target algorithm, and the coefficient of determination (R 2 ), mean absolute error (MAE), mean square error (MSE) and root mean square error (RMSE) are normalized and determined.

[0053] In another aspect, the present invention provides a method for identifying incorrect inhaler usage based on audio signals, using the above-mentioned intelligent inhaler monitoring device based on audio signals, comprising the following steps:

[0054] The client obtains the audio signal data detected in the sensor system through the communication module;

[0055] Perform feature extraction on the acquired audio data;

[0056] Using the extracted features (and features formed by their permutations and combinations), a classification model is constructed based on machine learning and deep learning algorithms;

[0057] Select the optimal model and determine the relevant model parameters as the target algorithm;

[0058] identifying incorrect use of the inhaler using a target algorithm based on the obtained audio signal value;

[0059] If an incorrect use is encountered, the user is reminded on the client side to correct the operation. By detecting misuse of the inhaler (such as reverse exhalation), the user is promptly reminded to correct the operation.

[0060] Among them, the feature extraction methods include: spectrogram, cepstral graph, Mel-frequency cepstral coefficient (MFCC), energy spectrum, pitch feature graph, zero crossing rate, and audio bandwidth.

[0061] The optimal model was selected and the relevant model parameters were determined as the target algorithm, which was determined by comprehensively evaluating the accuracy, precision, recall, specificity, F1 value and area under the receiver operating characteristic curve (AUC-ROC) indicators.

[0062] The parts not involved in this technical solution can be implemented using existing technologies.

[0063] The basic principles, main features, and characteristics of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of the present invention includes the appended claims and their equivalents.

Claims

1. An intelligent inhaler monitoring device based on audio signals, characterized in that: The invention comprises a housing (10), wherein the housing (10) comprises a hollow rotary cover (20) and a base (30); the hollow rotary cover (20) is mounted on the base (30), and a PCB board (40) is mounted in the base (30); an electronic module (41) and a USB data interface (42) are provided on the PCB board (40), and the electronic module (41) comprises an audio sensor system; the housing (10) is used for placing an inhaler (50) and transmitting audio signal changes caused by the air intake flow rate of the inhaler (50) to the sensor system for measurement.

2. The intelligent inhaler monitoring device based on audio signals according to claim 1, characterized in that: An electronic module compartment (34) and a battery compartment (32) are provided inside the base (10); a PCB board (40) is installed in the electronic module compartment (34); the PCB board (40) is fixed in the electronic module compartment (34) using a mounting box (31); and the battery compartment (32) is used to install a battery that provides electrical energy for the PCB board to operate.

3. The intelligent inhaler monitoring device based on audio signals according to claim 2, characterized in that: The hollow rotary cover (20) and the base (30) are used to fix the inhaler base (51) on the housing (10), so that the housing (10) and the inhaler base (51) can form a whole and move together.

4. The intelligent inhaler monitoring device based on audio signals according to claim 3, characterized in that: The electronic module (41) further comprises a communication module, a power supply system and a voice-controlled switch, wherein the communication module adopts a combination of one or more of a low-power Bluetooth module, a Wi-Fi module, a Zigbee module, a LoRa module, a Thread module, a 4G cellular network module or a 5G cellular network module.

5. The intelligent inhaler monitoring device based on audio signals according to claim 1, characterized in that: The inhaler (50) is a metered dose aerosol inhaler, a dry powder inhaler, a nebulizer inhaler or a soft mist inhaler.

6. A method for intelligent monitoring of an inhaler based on audio signals, using the intelligent monitoring device for an inhaler based on audio signals according to claim 2, characterized in that: Follow these steps: The client obtains the audio signal data detected in the sensor system through the communication module; Construct fitting models using sensor data fusion algorithms based on Kalman filtering, machine learning, and deep learning; Select the optimal model and determine the relevant model parameters as the target algorithm; Calculating the intake air flow rate of the inhaler (50) device using a target algorithm based on the obtained audio signal value; Draw the suction flow curve on the client side according to the intake air flow rate.

7. The method for intelligently monitoring an inhaler based on audio signals according to claim 6, characterized in that: The optimal model is selected and the relevant model parameters are determined as the target algorithm, and the comprehensive evaluation coefficient (R 2 ), mean absolute error (MAE), mean square error (MSE) and root mean square error (RMSE) are normalized and determined.

8. A method for identifying incorrect inhaler usage based on audio signals, wherein the intelligent inhaler monitoring device based on audio signals according to claim 2 is characterized in that: The steps include: The client obtains the audio signal data detected in the sensor system through the communication module; Perform feature extraction on the acquired audio data; Using the extracted features, build classification models based on machine learning and deep learning algorithms; Select the optimal model and determine the relevant model parameters as the target algorithm; identifying incorrect use of the inhaler using a target algorithm based on the obtained audio signal value; If an incorrect usage is encountered, the user will be reminded on the client side to correct the operation.

9. The method for identifying incorrect use of an inhaler based on audio signals according to claim 8, characterized in that: The feature extraction methods include: spectrogram, cepstral graph, Mel-frequency cepstral coefficient (MFCC), energy spectrum, pitch feature graph, zero crossing rate, and audio bandwidth.

10. The method for identifying incorrect use of an inhaler based on audio signals according to claim 8, characterized in that: The optimal model was selected and the relevant model parameters were determined as the target algorithm, which was determined by comprehensively evaluating the accuracy, precision, recall, specificity, F1 score and area under the receiver operating characteristic curve (AUC-ROC) indicators.

Images