Intelligent peak flow rate early warning method and related device

Abstract

The invention discloses an intelligent peak flow rate early warning method and a related device. The method comprises the following steps: measuring a peak expiration flow rate of a subject in an expiration process by using a peak flow rate measuring device; calculating the real-time flow of the pressure data by using a Bernoulli equation; the maximum value in the real-time flow is determined to serve as the peak expiration flow rate, and the time point corresponding to the peak expiration flow rate is recorded; inputting the peak expiratory flow velocity, the time point, the personal information of the subject and the medication record of the subject into a trained weighted support vector regression machine model, and predicting the predicted peak expiratory flow velocity of the subject in the future preset time; and generating an early warning signal when the minimum value or the decrease amplitude of the predicted peak expiratory flow rate exceeds a set threshold value. According to the method, the predicted peak expiratory flow rate of the subject in the future preset time is predicted according to the peak expiratory flow rate, the time point, the personal information of the subject and the medication record of the subject, the patient compliance is remarkably improved, and the early warning scheme has higher practical value.

Description

Technical Field

[0001] The present invention relates to the field of medical health assistance technology, and in particular to an intelligent peak flow velocity early warning method and device, and a computing device. Background Art

[0002] Respiratory diseases such as chronic obstructive pulmonary disease and asthma impose significant pain and financial burdens on patients. Traditional peak flow meters are portable, handheld devices that allow patients to directly read the peak flow rate (PEF) value by forcing an exhale. While simple and easy to use, these devices can directly affect the measurement results due to the patient's exhalation force and technique, making them prone to errors. Furthermore, patients must manually record measurement data, which is prone to omissions and errors, making long-term trend analysis difficult. Furthermore, the inability to provide intelligent early warnings based on historical data and individual differences makes it difficult to detect the risk of worsening conditions in advance.

[0003] To solve the above problems, the present invention proposes an intelligent peak flow rate warning method, which predicts the subject's predicted peak expiratory flow rate within a preset time in the future based on the peak expiratory flow rate, time point, subject personal information and subject medication record, so as to improve patient compliance and make the warning more practical. Summary of the Invention

[0004] In view of the above problems, the present invention provides an intelligent peak flow velocity early warning method and device, and a computing device.

[0005] According to one aspect of the present invention, an intelligent peak flow velocity early warning method is provided, comprising:

[0006] Measuring the peak expiratory flow rate during exhalation of the subject using a peak flow rate measurement device, wherein pressure data during exhalation of the subject is collected in real time by a pressure sensor; calculating the real-time flow rate of the pressure data using the Bernoulli equation; determining the maximum value of the real-time flow rate as the peak expiratory flow rate and recording the time point corresponding to the peak flow rate;

[0007] Inputting the peak expiratory flow rate, the time point, the subject's personal information, and the subject's medication record into a trained weighted support vector regression model to predict the subject's predicted peak expiratory flow rate within a preset time in the future;

[0008] When the lowest value or the decreasing amplitude of the predicted peak expiratory flow rate exceeds a set threshold, a warning signal is generated.

[0009] In an optional manner, the dynamic weight adjustment formula of the weighted support vector regression model is:

[0010]

[0011] Among them, w i (t) is the dynamic weight of the i-th feature at time t; wi0 is the initial weight; λ is the time decay coefficient; η is the pressure-flow correlation coefficient; ΔP k (t) and ΔV k (t) are the instantaneous changes of pressure and flow in the kth respiratory cycle; n is the length of the historical data window.

[0012] In an optional manner, the set threshold is dynamically adjusted by an adaptive threshold generation algorithm, and the dynamic adjustment formula is:

[0013]

[0014] Where μ(t) and σ(t) are the mean and standard deviation of the most recent m measurements, respectively; ΔP base,j is the jth baseline pressure change; ΔV peak,j is the jth peak flow velocity change.

[0015] In an optional manner, the predicted peak expiratory flow rate is corrected by a multimodal data fusion model, and the correction formula is:

[0016]

[0017] Among them, V SVR is the original prediction value of the support vector regression machine; θ c is the impact weight of the c-th environmental parameter; is the rate of change of environmental parameters; is the rate of change of flow rate after drug administration; ω(t) is the drug metabolic kinetic attenuation function; t is the duration of drug effect.

[0018] In an optional embodiment, the peak flow rate measurement device adopts a dual-modal sensor array, wherein the main sensor is a micro-electromechanical system piezoresistive pressure sensor with a measuring range of 0-10kPa and a response time of <1ms; the auxiliary sensor is an ultrasonic time-difference flow rate sensor with a measuring range of 0-20L / s and an accuracy of ±2%.

[0019] In an optional embodiment, before measuring the peak expiratory flow rate during exhalation of the subject using a peak flow rate measurement device, the method further includes:

[0020] The subjects were given an initial health assessment, which included pulmonary function tests, cardiopulmonary function assessments, and a history of respiratory diseases.

[0021] In an optional manner, the method further includes:

[0022] The peak flow velocity measurement device is connected to the patient's mobile terminal via a wireless network, and the measurement data is uploaded to the remote monitoring platform in real time;

[0023] The remote monitoring platform exchanges data with the EMR system and automatically updates the patient's peak expiratory flow rate, medication records and warning information so that doctors can view changes in the patient's condition through the EMR system; when a warning signal is generated, a notification is automatically sent to the patient's responsible doctor and designated caregiver.

[0024] In an optional manner, the method further includes:

[0025] Build a gamified health management platform that transforms daily tasks like peak flow rate self-tests and medication reminders into a virtual city-building game. Players earn virtual currency by completing health goals, which they can use to decorate their virtual hospital rooms or redeem for free lung function tests.

[0026] Analyze patients' historical behavior data to generate personalized motivational messages. When missed tests are detected for three consecutive days, a contextual reminder is triggered.

[0027] Match users with similar disease courses. When a new user triggers a red alert, it will automatically recommend 3 health mentors who have successfully controlled acute attacks and provide 24-hour online experience sharing.

[0028] According to another aspect of the present invention, there is provided an intelligent peak flow velocity warning device, comprising:

[0029] A peak flow rate measurement module is configured to measure the peak expiratory flow rate during exhalation of a subject using a peak flow rate measurement device, wherein the pressure data of the subject during exhalation is collected in real time by a pressure sensor; the real-time flow rate of the pressure data is calculated using the Bernoulli equation; the maximum value of the real-time flow rate is determined as the peak expiratory flow rate and the time point corresponding to the peak flow rate is recorded;

[0030] A peak prediction module, configured to input the peak expiratory flow rate, the time point, the subject's personal information, and the subject's medication record into a trained weighted support vector regression model to predict the subject's peak expiratory flow rate within a preset time in the future;

[0031] The early warning module is configured to generate an early warning signal when the lowest value or the decreasing amplitude of the predicted peak expiratory flow rate exceeds a set threshold.

[0032] According to another aspect of the present invention, there is provided a computing device, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus;

[0033] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute operations corresponding to the above-mentioned intelligent peak flow velocity warning method.

[0034] According to the solution provided by the present invention, a peak flow rate measuring device is used to measure the peak expiratory flow rate during the exhalation process of a subject, wherein the pressure data of the subject during exhalation is collected in real time by a pressure sensor; the real-time flow of the pressure data is calculated using the Bernoulli equation; the maximum value of the real-time flow is determined as the peak expiratory flow rate and the time point corresponding to the peak flow rate is recorded; the peak expiratory flow rate, the time point, the subject's personal information and the subject's medication record are input into a trained weighted support vector regression model to predict the subject's predicted peak expiratory flow rate within a preset time in the future; when the minimum value or the decrease in the predicted peak expiratory flow rate exceeds a set threshold, an early warning signal is generated. The present invention predicts the subject's predicted peak expiratory flow rate within a preset time in the future based on the peak expiratory flow rate, time point, the subject's personal information and the subject's medication record, significantly improving patient compliance and making the early warning solution more practical.

[0035] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0037] Figure 1 A schematic diagram showing a flow chart of an intelligent peak flow velocity warning method according to an embodiment of the present invention is shown;

[0038] Figure 2 A schematic diagram showing a framework of an intelligent peak flow velocity warning device according to an embodiment of the present invention is shown;

[0039] Figure 3 A schematic structural diagram of a computing device according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0040] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0041] Figure 1FIG. 1 is a flow chart showing an intelligent peak flow velocity warning method according to an embodiment of the present invention. Figure 1 As shown, the following steps are included:

[0042] Step S101, using a peak flow rate measuring device to measure the peak expiratory flow rate during the subject's exhalation process, wherein the pressure data of the subject during exhalation is collected in real time by a pressure sensor; the real-time flow of the pressure data is calculated using the Bernoulli equation; the maximum value of the real-time flow is determined as the peak expiratory flow rate and the time point corresponding to the peak flow rate is recorded.

[0043] In this embodiment, a pressure sensor is used to collect data in real time to capture instantaneous peak values ​​to reflect dynamic changes during exhalation, avoiding the risk of missing peak values ​​due to insufficient sampling frequency in traditional methods. Pressure data is converted into flow rate through the Bernoulli equation, avoiding the equipment complexity and cost brought by direct flow measurement. By converting pressure into flow rate and utilizing the high precision of the pressure sensor, the accuracy of peak flow rate measurement is indirectly improved. Compared with devices that directly measure flow rate, the method of using a pressure sensor in conjunction with the Bernoulli equation simplifies the device structure, reduces costs, and is convenient to carry and use.

[0044] Specifically, a peak flow rate measurement device (including a pressure sensor) is connected to the subject, the pressure sensor is activated, and the sampling frequency is set. The subject exhales according to the instructions of the medical staff or the device. The pressure sensor collects pressure data during exhalation in real time and transmits the data to the processor or computing unit. The pressure data is converted into real-time flow data using the Bernoulli equation. The commonly used formula of the Bernoulli equation is: Where ΔP is the pressure difference, and k is a correction factor (calibrated experimentally) related to the device geometry and fluid properties. The calculated flow data is monitored in real time, and the maximum value of the real-time flow, namely the peak expiratory flow rate (PEF), and the corresponding time point of the peak expiratory flow rate are recorded. The peak expiratory flow rate and the corresponding time point are stored in local memory and transmitted to a remote monitoring platform or mobile terminal via a wireless network.

[0045] For example, an asthma patient uses a smart peak flow measurement device for daily monitoring at home. The patient activates the device and follows the on-screen instructions to take a deep breath followed by a rapid, forced exhalation. A microelectromechanical system (MEMS) piezoresistive pressure sensor collects real-time pressure data during exhalation (100 pressure data points are collected within 0.5 seconds). Each pressure data point is converted to a corresponding flow rate using the Bernoulli equation. The maximum pressure difference is 2 kPa, which is calculated to correspond to a flow rate of 8 L / s. The maximum real-time flow rate is determined to be 8 L / s, which is recorded as the peak expiratory flow rate. The time point corresponding to this peak flow rate is also recorded as 0.25 seconds after the start of exhalation. The peak expiratory flow rate (8 L / s), time point (0.25 seconds), patient personal information (e.g., name, age), and medication history (e.g., 200 μg of salbutamol) are then uploaded to a remote monitoring platform via a wireless network. After receiving the data, the remote monitoring platform inputs the data into a trained weighted support vector regression model to predict the patient's peak expiratory flow rate within a preset timeframe. If the predicted peak expiratory flow rate falls below the set threshold, the platform will generate an early warning signal and notify the patient's responsible physician and designated caregiver.

[0046] In an optional embodiment, the peak flow rate measurement device adopts a dual-modal sensor array, wherein the main sensor is a micro-electromechanical system piezoresistive pressure sensor with a measuring range of 0-10kPa and a response time of <1ms; the auxiliary sensor is an ultrasonic time-difference flow rate sensor with a measuring range of 0-20L / s and an accuracy of ±2%.

[0047] In this embodiment, a dual-modal sensor array is used, with the main sensor and the auxiliary sensor working together. When the main sensor fails or the data is abnormal, the auxiliary sensor can continue to provide measurement data. For example, when the main sensor is impacted by the airflow and the data is distorted, the auxiliary sensor provides more accurate flow data, which can still be used after being corrected by the algorithm. The main sensor (pressure sensor) and the auxiliary sensor (flow rate sensor) have different measurement ranges, and their combined use can expand the overall measurement range. The pressure sensor may be more sensitive in the high-pressure area, while the ultrasonic flow rate sensor may be more stable in the low-flow area. The combined use covers a wider respiratory flow range and is suitable for subjects with different physiques and breathing habits.

[0048] In an optional embodiment, before measuring the peak expiratory flow rate during exhalation of the subject using a peak flow rate measurement device, the method further includes:

[0049] The subjects were given an initial health assessment, which included pulmonary function tests, cardiopulmonary function assessments, and a history of respiratory diseases.

[0050] In this embodiment, some potential health problems can be discovered through evaluation, for example, the patient complains of intermittent coughing and wheezing. The pulmonary function test FEV1 is 70% of the expected value, FEV1 / FVC is 0.65 (lower than normal), there is airflow limitation, and the electrocardiogram shows sinus rhythm. The patient has a 20-year smoking history and a history of chronic bronchitis. He lacks exercise and has high work pressure. Based on the pulmonary function test results and medical history, he was diagnosed with chronic obstructive pulmonary disease (COPD). The data such as pulmonary function test results, medical history, smoking history, etc. are included in the weighted support vector regression model for training. The patient is classified as a medium-risk level for COPD, and a lower peak flow rate warning threshold is set. When the predicted peak flow rate is lower than 20% of its baseline value, a warning is issued.

[0051] Step S102: input the peak expiratory flow rate, the time point, the subject's personal information, and the subject's medication record into a trained weighted support vector regression model to predict the subject's peak expiratory flow rate within a preset time in the future.

[0052] In this embodiment, multiple factors such as peak expiratory flow rate, time point, subject personal information and medication records are integrated into the weighted support vector regression model, which can achieve highly personalized peak flow rate prediction and better capture individual differences and influencing factors. The weighted support vector regression model adopts a dynamic weight adjustment method to adaptively adjust the weights of different features according to changes in the pressure-flow relationship, better adapting to changes in the subject's breathing pattern and disease progression. By predicting the peak flow rate within a preset time in the future to achieve early warning, doctors and patients can take timely intervention measures to prevent acute attacks or worsening of the disease.

[0053] For example, an asthma patient measures peak flow rate every morning and evening and records medication use. Peak expiratory flow rate data for the past week includes: 450 L / min, 430 L / min, 460 L / min, etc. Time of measurement: 8:00 AM and 8:00 PM daily. Subject's personal information: Gender: Male, Age: 50, Height: 175 cm, Weight: 70 kg. Medication history: Albuterol aerosol, 2 puffs, twice daily. A weighted support vector regression model is trained using the past month's historical data. The model's weights are dynamically adjusted based on the patient's breathing pattern and medication use. The model inputs the current peak expiratory flow rate (440 L / min), time of measurement (8:00 PM), subject information, and medication history. The model predicts peak expiratory flow rates for the next 24 hours, for example: 430 L / min, 420 L / min, 410 L / min, etc. The warning threshold is set at a peak expiratory flow rate below 400 L / min or a decrease of more than 15%. If the model predicts that the peak expiratory flow rate will fall below 400 L / min within the next 24 hours, an early warning signal is issued.

[0054] In an optional manner, the dynamic weight adjustment formula of the weighted support vector regression model is:

[0055]

[0056] Among them, w i (t) is the dynamic weight of the i-th feature at time t; w i0 is the initial weight; λ is the time decay coefficient; η is the pressure-flow correlation coefficient; ΔP k (t) and ΔV k (t) are the instantaneous changes of pressure and flow in the kth respiratory cycle; n is the length of the historical data window.

[0057] In this embodiment, traditional support vector regression (SVR) models typically use static weights. However, this application dynamically adjusts feature weights based on time and the relationship between pressure and flow, better adapting to changes in the patient's breathing pattern and the progression of the disease, thereby improving prediction accuracy. By combining the instantaneous changes in pressure and flow, the dynamic characteristics of the respiratory process are more accurately reflected.

[0058] Step S103 : generating a warning signal when the lowest value or the decreasing amplitude of the predicted peak expiratory flow rate exceeds a set threshold.

[0059] In this embodiment, peak expiratory flow rate prediction enables early detection of worsening patient conditions, providing early warnings and thus saving valuable treatment time and preventing acute exacerbations. The system considers not only the lowest peak expiratory flow rate but also its magnitude of decline. Even if the predicted value doesn't reach its absolute lowest point, an excessively rapid decline triggers an alert, enabling a more comprehensive assessment of signs of disease progression.

[0060] In an optional manner, the set threshold is dynamically adjusted by an adaptive threshold generation algorithm, and the dynamic adjustment formula is:

[0061]

[0062] Where μ(t) and σ(t) are the mean and standard deviation of the most recent m measurements, respectively; ΔP base,j is the jth baseline pressure change; ΔV peak,j is the jth peak flow velocity change.

[0063] In this embodiment, the adaptive threshold is adjusted based on changes in individual breathing patterns and disease status, thereby improving the sensitivity (capable of timely detecting abnormalities) and specificity (reducing unnecessary alerts) of the warning. Different patients have different physiological baselines and disease progression rates. Taking the mean and standard deviation of the most recent m measurements into account allows for more refined individual baseline threshold adjustments, allowing the warning signal to better reflect the individual's true health status.

[0064] In an optional manner, the predicted peak expiratory flow rate is corrected by a multimodal data fusion model, and the correction formula is:

[0065]

[0066] Among them, V SVR is the original prediction value of the support vector regression machine; θ c is the impact weight of the c-th environmental parameter; is the rate of change of environmental parameters; is the rate of change of flow rate after drug administration; ω(t) is the drug metabolic kinetic attenuation function; t is the duration of drug effect.

[0067] In this example, for example, an asthma patient is using salbutamol aerosol. Assume that the model predicts that the patient's peak flow rate at a certain time in the future will be 350 L / min. Consider two environmental parameters: the air pollution index (API) and temperature. In the past hour, the air pollution index has increased by 10 units. For every unit increase, the peak flow rate decreases by 2 L / min. The temperature has dropped by 2 degrees Celsius in the past hour. The patient received albuterol aerosol half an hour ago. Assume that the effect of albuterol is most pronounced in the first hour and then gradually decreases. The pharmacokinetic decay function ω(t) = e -0.693t , where t is in hours (half-life is 1 hour). At its peak, salbutamol increases the peak flow rate by 100 L / min, so the initial drug effect at t = 0 is 100 L / min / hour. Corrected prediction = 368 L / min. After correction by the multimodal data fusion model, the predicted peak flow rate changes from 350 L / min to 368 L / min because the model takes into account the beneficial effects of the drop in ambient temperature and the therapeutic effects of the drug. The corrected prediction results better reflect the patient's actual condition.

[0068] In an optional manner, the method further includes:

[0069] The peak flow velocity measurement device is connected to the patient's mobile terminal via a wireless network, and the measurement data is uploaded to the remote monitoring platform in real time;

[0070] The remote monitoring platform exchanges data with the EMR system and automatically updates the patient's peak expiratory flow rate, medication records and warning information so that doctors can view changes in the patient's condition through the EMR system; when a warning signal is generated, a notification is automatically sent to the patient's responsible doctor and designated caregiver.

[0071] In this embodiment, for example, patient A uses a peak flow rate measuring device to measure his peak expiratory flow rate every morning and evening and uploads the data to the remote monitoring platform. After receiving the peak expiratory flow rate data of patient A, the remote monitoring platform analyzes the data and associates the data with patient A's personal information, medication records and other information. The remote monitoring platform finds that patient A's peak expiratory flow rate continues to decline and is lower than the set threshold, and automatically generates an early warning signal. An early warning notification is sent to patient A's responsible doctor and designated caregiver via SMS and APP push. After receiving the early warning notification, patient A's responsible doctor checks the medical records and contacts patient A to adjust the medication plan to avoid acute asthma attacks.

[0072] In an optional manner, the method further includes:

[0073] Build a gamified health management platform that transforms daily tasks like peak flow rate self-tests and medication reminders into a virtual city-building game. Players earn virtual currency by completing health goals, which they can use to decorate their virtual hospital rooms or redeem for free lung function tests.

[0074] Analyze patients' historical behavior data to generate personalized motivational messages. When missed tests are detected for three consecutive days, a contextual reminder is triggered.

[0075] Match users with similar disease courses. When a new user triggers a red alert, it will automatically recommend 3 health mentors who have successfully controlled acute attacks and provide 24-hour online experience sharing.

[0076] According to the solution provided by the present invention, a peak flow rate measuring device is used to measure the peak expiratory flow rate during the exhalation process of a subject, wherein the pressure data of the subject during exhalation is collected in real time by a pressure sensor; the real-time flow of the pressure data is calculated using the Bernoulli equation; the maximum value of the real-time flow is determined as the peak expiratory flow rate and the time point corresponding to the peak flow rate is recorded; the peak expiratory flow rate, the time point, the subject's personal information and the subject's medication record are input into a trained weighted support vector regression model to predict the subject's predicted peak expiratory flow rate within a preset time in the future; when the minimum value or the decrease in the predicted peak expiratory flow rate exceeds a set threshold, an early warning signal is generated. The present invention predicts the subject's predicted peak expiratory flow rate within a preset time in the future based on the peak expiratory flow rate, time point, the subject's personal information and the subject's medication record, significantly improving patient compliance and making the early warning solution more practical.

[0077] Figure 2 The following is a schematic diagram showing the framework of an intelligent peak flow velocity warning device according to an embodiment of the present invention. The intelligent peak flow velocity warning device includes:

[0078] The peak flow rate measurement module 210 is configured to measure the peak expiratory flow rate during exhalation of a subject using a peak flow rate measurement device, wherein the pressure data of the subject during exhalation is collected in real time by a pressure sensor; the real-time flow rate of the pressure data is calculated using the Bernoulli equation; the maximum value of the real-time flow rate is determined as the peak expiratory flow rate and the time point corresponding to the peak flow rate is recorded;

[0079] The peak prediction module 220 is configured to input the peak expiratory flow rate, the time point, the subject's personal information, and the subject's medication record into a trained weighted support vector regression model to predict the subject's peak expiratory flow rate within a preset time period in the future;

[0080] The warning module 230 is configured to generate a warning signal when the lowest value or the decreasing amplitude of the predicted peak expiratory flow rate exceeds a set threshold.

[0081] Figure 3 The schematic diagram of the structure of the computing device embodiment of the present invention is shown. The specific embodiment of the present invention does not limit the specific implementation of the computing device.

[0082] like Figure 3As shown, the computing device may include: a processor 302 , a communications interface 304 , a memory 306 , and a communication bus 308 .

[0083] Processor 302, communication interface 304, and memory 306 communicate with each other via communication bus 308. Communication interface 304 is used to communicate with other devices, such as clients or other server network elements. Processor 302 is used to execute program 310, which may specifically perform the steps described in the aforementioned embodiment of the intelligent peak flow velocity warning method.

[0084] Specifically, the program 310 may include program codes, which include computer operation instructions.

[0085] Processor 302 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included in a computing device may be processors of the same type, such as one or more CPUs, or processors of different types, such as one or more CPUs and one or more ASICs.

[0086] The memory 306 is used to store the program 310. The memory 306 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0087] According to the solution provided by the present invention, a peak flow rate measuring device is used to measure the peak expiratory flow rate during the exhalation process of a subject, wherein the pressure data of the subject during exhalation is collected in real time by a pressure sensor; the real-time flow of the pressure data is calculated using the Bernoulli equation; the maximum value of the real-time flow is determined as the peak expiratory flow rate and the time point corresponding to the peak flow rate is recorded; the peak expiratory flow rate, the time point, the subject's personal information and the subject's medication record are input into a trained weighted support vector regression model to predict the subject's predicted peak expiratory flow rate within a preset time in the future; when the minimum value or the decrease in the predicted peak expiratory flow rate exceeds a set threshold, an early warning signal is generated. The present invention predicts the subject's predicted peak expiratory flow rate within a preset time in the future based on the peak expiratory flow rate, time point, the subject's personal information and the subject's medication record, significantly improving patient compliance and making the early warning solution more practical.

[0088] Those skilled in the art will appreciate that modules in the devices of the embodiments may be adaptively modified and deployed in one or more devices different from the embodiments. Modules, units, or components in the embodiments may be combined into a single module, unit, or component, and furthermore, they may be divided into multiple submodules, subunits, or subcomponents. All features disclosed in this specification (including the accompanying claims, abstract, and drawings), as well as all processes or units of any method or device disclosed therein, may be combined in any combination, except where at least some of such features and / or processes or units are mutually exclusive. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that provides the same, equivalent, or similar purpose. Furthermore, those skilled in the art will appreciate that although some embodiments herein include certain features included in other embodiments but not others, combinations of features from different embodiments are intended to be within the scope of the present invention and to form different embodiments. For example, in the claims below, any of the claimed embodiments may be used in any combination. The present invention may be implemented using hardware comprising a number of different elements and using a suitably programmed computer. In a unit claim that lists several means, several of these means may be embodied by the same hardware item. Unless otherwise specified, the steps in the above embodiments should not be understood as limiting the order of execution.

Claims

1. Use a peak flow rate measuring device to measure the peak expiratory flow rate during the subject's exhalation, where: collecting pressure data of the subject during exhalation in real time using a pressure sensor; calculating the real-time flow rate of the pressure data using the Bernoulli equation; determining the maximum value of the real-time flow rate as the peak exhalation flow rate and recording the time point corresponding to the peak flow rate; Inputting the peak expiratory flow rate, the time point, the subject's personal information, and the subject's medication record into a trained weighted support vector regression model to predict the subject's predicted peak expiratory flow rate within a preset time in the future; When the lowest value or the decreasing amplitude of the predicted peak expiratory flow rate exceeds a set threshold, a warning signal is generated.

2. The intelligent peak flow velocity warning method according to claim 1, characterized in that: The dynamic weight adjustment formula of the weighted support vector regression model is: Among them, w i (t) is the dynamic weight of the i-th feature at time t; w i0 is the initial weight; λ is the time decay coefficient; η is the pressure-flow correlation coefficient; ΔP k (t) and ΔV k (t) are the instantaneous changes of pressure and flow in the kth respiratory cycle; n is the length of the historical data window.

3. The intelligent peak flow velocity warning method according to claim 1, characterized in that: The set threshold is dynamically adjusted by an adaptive threshold generation algorithm, and the formula for dynamic adjustment is: Where μ(t) and σ(t) are the mean and standard deviation of the most recent m measurements, respectively; ΔP base,j is the jth baseline pressure change; ΔV peak,j is the jth peak flow velocity change.

4. The intelligent peak flow velocity warning method according to claim 1, characterized in that: The predicted peak expiratory flow rate is corrected by a multimodal data fusion model, and the correction formula is: Among them, V SVR is the original prediction value of the support vector regression machine; θ c is the impact weight of the c-th environmental parameter; is the rate of change of environmental parameters; is the rate of change of flow rate after drug administration; ω(t) is the drug metabolic kinetic attenuation function; t is the duration of drug effect.

5. The intelligent peak flow velocity warning method according to claim 1, characterized in that: The peak flow rate measurement device uses a dual-modal sensor array, in which the main sensor is a micro-electromechanical system piezoresistive pressure sensor with a range of 0-10kPa and a response time of <1ms; the auxiliary sensor is an ultrasonic time-of-flight flow rate sensor with a measurement range of 0-20L / s and an accuracy of ±2%.

6. The intelligent peak flow velocity warning method according to claim 1, characterized in that: Before measuring the peak expiratory flow rate during exhalation of the subject using the peak flow rate measurement device, the method further includes: The subjects were given an initial health assessment, which included pulmonary function tests, cardiopulmonary function assessments, and a history of respiratory diseases.

7. The intelligent peak flow velocity warning method according to claim 1, characterized in that: The method further comprises: The peak flow velocity measurement device is connected to the patient's mobile terminal via a wireless network, and the measurement data is uploaded to the remote monitoring platform in real time; The remote monitoring platform exchanges data with the EMR system and automatically updates the patient's peak expiratory flow rate, medication records and warning information so that doctors can view changes in the patient's condition through the EMR system; when a warning signal is generated, a notification is automatically sent to the patient's responsible doctor and designated caregiver.

8. The intelligent peak flow velocity warning method according to claim 1, characterized in that: The method further comprises: Build a gamified health management platform that transforms daily tasks like peak flow rate self-tests and medication reminders into a virtual city-building game. Players earn virtual currency by completing health goals, which they can use to decorate their virtual hospital rooms or redeem for free lung function tests. Analyze patients' historical behavior data to generate personalized motivational messages. When missed tests are detected for three consecutive days, a contextual reminder is triggered. Match users with similar disease courses. When a new user triggers a red alert, it will automatically recommend 3 health mentors who have successfully controlled acute attacks and provide 24-hour online experience sharing.

9. An intelligent peak flow velocity warning device, characterized in that: include: A peak flow rate measurement module is configured to measure the peak expiratory flow rate during exhalation of a subject using a peak flow rate measurement device, wherein the pressure data of the subject during exhalation is collected in real time by a pressure sensor; the real-time flow rate of the pressure data is calculated using the Bernoulli equation; the maximum value of the real-time flow rate is determined as the peak expiratory flow rate and the time point corresponding to the peak flow rate is recorded; A peak prediction module, configured to input the peak expiratory flow rate, the time point, the subject's personal information, and the subject's medication record into a trained weighted support vector regression model to predict the subject's peak expiratory flow rate within a preset time in the future; The early warning module is configured to generate an early warning signal when the lowest value or the decreasing amplitude of the predicted peak expiratory flow rate exceeds a set threshold.

10. A computing device comprising: A processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute operations corresponding to the above-mentioned intelligent peak flow velocity warning method.

Images