WO2024104176A1 - 一种慢阻肺风险评估方法、装置、电子设备及存储介质 - Google Patents

一种慢阻肺风险评估方法、装置、电子设备及存储介质 Download PDF

Info

Publication number
WO2024104176A1
WO2024104176A1 PCT/CN2023/129131 CN2023129131W WO2024104176A1 WO 2024104176 A1 WO2024104176 A1 WO 2024104176A1 CN 2023129131 W CN2023129131 W CN 2023129131W WO 2024104176 A1 WO2024104176 A1 WO 2024104176A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
physiological parameter
copd
behavior
motion data
Prior art date
Application number
PCT/CN2023/129131
Other languages
English (en)
French (fr)
Inventor
夏凯伦
李靖
王伟
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2024104176A1 publication Critical patent/WO2024104176A1/zh

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/08—Measuring devices for evaluating the respiratory organs
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires

Definitions

  • the present application relates to the field of terminal device technology, and in particular to a method, device, electronic device and storage medium for assessing the risk of chronic obstructive pulmonary disease.
  • COPD chronic obstructive pulmonary disease
  • COPD chronic obstructive pulmonary disease
  • structural changes such as airway narrowing or emphysema caused by smoking and other reasons, resulting in obstruction of respiratory airflow, feeling labored or breathless, often accompanied by discomfort such as coughing and sputum.
  • COPD chronic obstructive pulmonary disease
  • the main cause of COPD is smoking.
  • a home full of kitchen fumes and smoke, working in places with a lot of smoke and dust for a long time, passive smoking, and frequent respiratory infections in childhood can also lead to the onset of COPD.
  • the obstruction of respiratory airflow in COPD will become more and more serious, not only affecting the respiratory system, but also affecting multiple organs in the body such as bones, muscles, and heart.
  • the present application provides a COPD risk assessment method that can provide timely warning of COPD in users, achieve early detection of COPD, enable early diagnosis and treatment of COPD, and effectively protect the user's health.
  • the first aspect of the present application provides a method for assessing the risk of chronic obstructive pulmonary disease, comprising: obtaining a user's first motion data and a first physiological parameter; determining a motion behavior corresponding to the first motion data, the motion behavior including at least one of walking, running, climbing stairs, and resting; determining an assessment result based on the motion behavior and the first physiological parameter.
  • this assessment method can provide timely warnings for COPD based on the user's daily exercise conditions even if the user has not undergone a pulmonary function test, thereby achieving early detection of COPD, enabling early diagnosis and treatment of COPD, and effectively protecting the user's health.
  • determining the evaluation result based on the movement behavior and the first physiological parameter includes: selecting a target model that matches the movement behavior from multiple preset models, the target model is trained based on first historical movement data, a historical first physiological parameter corresponding to the first historical movement data, and a first physiological parameter reference value, the first physiological parameter reference value is a physiological parameter value of a non-COPD patient corresponding to the first historical movement data; inputting the first physiological parameter into the target model to determine the evaluation result.
  • the obtaining of the user's first motion data and first physiological parameter includes: obtaining the first motion data and the first physiological parameter in real time within a first preset period; the determining of the motion behavior corresponding to the first motion data includes: determining the motion behavior corresponding to the first motion data after each acquisition of the first motion data; selecting a target model matching the motion behavior from a plurality of preset models, inputting the first physiological parameter into the target model, and determining the evaluation result includes: selecting a target model matching the motion behavior from a plurality of preset models after each determination of the motion behavior, and inputting the first physiological parameter corresponding to the motion behavior into the target model; when the evaluation result of the target model is that the first total number of times the user has COPD symptoms is greater than a first preset number, sending a first prompt message.
  • determining the evaluation result based on the movement behavior and the first physiological parameter includes: determining a standard value of a physiological parameter that matches the movement behavior, the standard value of the physiological parameter being a physiological parameter value corresponding to the movement behavior in a non-COPD patient; determining the evaluation result based on the first physiological parameter and the standard value of the physiological parameter.
  • the method also includes: obtaining second motion data and second physiological parameters of the user; inputting the second motion data and the second physiological parameters into a preset smoking detection model to obtain a detection result of whether the user is smoking, wherein the preset smoking detection model is trained based on the second historical motion data, the historical second physiological parameters corresponding to the second historical motion data, and the second physiological parameter reference value, and the second physiological parameter reference value is the physiological parameter value corresponding to the second motion data in the non-smoking state of the user; if within a second preset period, the detection result is that the second total number of times the user is smoking is greater than the second preset number, a second prompt message is sent.
  • determining the evaluation result based on the movement behavior and the first physiological parameter includes: determining the evaluation result based on the movement behavior, the first physiological parameter and the second total number of times that the detection result is that the user is smoking.
  • determining the evaluation result based on the movement behavior, the first physiological parameter and the detection result as the second total number of times the user is smoking includes: selecting a target comprehensive evaluation model from multiple comprehensive evaluation models based on the movement behavior and the second total number of times; and inputting the first physiological parameter and the second total number of times into the target comprehensive evaluation model to determine the evaluation result.
  • the first prompt message after sending the first prompt message, it also includes: acquiring the physiological sounds of the user; performing feature extraction on the physiological sounds, inputting the result of the feature extraction into a sound feature detection model, and obtaining a lung function assessment result of the user; when the lung function assessment result does not meet a second preset requirement, sending a third prompt message.
  • the method further includes: sending a questionnaire to the user for characterizing the possibility of developing COPD; obtaining the filled-in results of the questionnaire, and sending a fourth prompt message when the filled-in results do not meet the third preset requirement.
  • the first physiological parameter includes one of the following or any combination thereof: heart rate, blood oxygen saturation, respiratory rate, and heart rate variability.
  • the second aspect of the present application discloses a COPD risk assessment device, comprising: a motion data acquisition module, the motion data acquisition module is used to acquire a user's first motion data; a physiological parameter acquisition module, the physiological parameter acquisition module is used to acquire the user's first physiological parameter; a motion behavior determination module, the motion behavior determination module is used to determine the motion behavior corresponding to the first motion data, the motion behavior including at least one of walking, running, climbing stairs and resting; a COPD assessment module, the COPD assessment module is used to determine an assessment result based on the motion behavior and the first physiological parameter.
  • the third aspect of the present application discloses a computer-readable storage medium, including computer instructions.
  • the computer instructions When the computer instructions are executed on an electronic device, the electronic device executes the above-mentioned COPD risk assessment method.
  • the fourth aspect of the present application discloses an electronic device, which includes a processor and a memory, the memory is used to store instructions, and the processor is used to call the instructions in the memory so that the electronic device executes the above-mentioned COPD risk assessment method.
  • the COPD risk assessment device of the second aspect, the computer-readable storage medium of the third aspect, and the electronic device of the fourth aspect provided above all correspond to the method of the first aspect. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above and will not be repeated here.
  • FIG1 is a schematic diagram of a process of a method for assessing risk of chronic obstructive pulmonary disease provided in an embodiment of the present application
  • FIG2 is a diagram of a standard for evaluating dyspnea symptoms according to an embodiment of the present application.
  • FIG. 3 is a diagram showing changes in heart rate of a COPD patient while walking continuously, provided in one embodiment of the present application;
  • FIG. 3 is a graph showing HRV changes of COPD patients and normal people during continuous walking provided by an embodiment of the present application;
  • FIG. 4 is a diagram showing changes in respiratory rate of a COPD patient and a normal person when climbing stairs, provided in one embodiment of the present application;
  • FIG4 is a graph showing changes in blood oxygen saturation of a COPD patient and a normal person when climbing stairs, provided in an embodiment of the present application;
  • FIG5 is a block diagram of a COPD symptom capture algorithm provided in an embodiment of the present application.
  • FIG6 is a flow chart of a method for assessing risk of chronic obstructive pulmonary disease provided in one embodiment of the present application.
  • FIG7a is a diagram showing the effect of the first prompt information provided by an embodiment of the present application on a wearable device
  • FIG7b is a diagram showing the effect of the first prompt information provided by an embodiment of the present application on a terminal device
  • FIG8 is a flow chart of a method for assessing risk of chronic obstructive pulmonary disease provided in one embodiment of the present application.
  • FIG9 is a diagram showing changes in the ACC sensor when the wearable device is a headset provided by an embodiment of the present application when the user smokes;
  • FIG10 is a diagram showing changes in the ACC sensor when a user smokes when the wearable device provided by an embodiment of the present application is a watch or a bracelet;
  • FIG11 is a block diagram of a smoking motion capture algorithm provided in an embodiment of the present application.
  • FIG12 is a diagram showing the effect of the second prompt information provided by an embodiment of the present application on a wearable device
  • FIG13 is a flow chart of a method for assessing risk of chronic obstructive pulmonary disease provided in one embodiment of the present application.
  • FIG14 is a flow chart of a COPD non-sensing detection algorithm provided in an embodiment of the present application.
  • FIG15 is a schematic diagram of a flow chart of a method for assessing risk of chronic obstructive pulmonary disease provided in an embodiment of the present application
  • FIG. 16 is a diagram showing the difference in cough sounds between a healthy person and a COPD patient provided in an embodiment of the present application.
  • FIG17 is a block diagram of a lung function assessment algorithm provided in one embodiment of the present application.
  • FIG18a is a diagram showing the effect of the third prompt information provided by an embodiment of the present application on a wearable device
  • FIG18b is a diagram showing the effect of the third prompt information provided by an embodiment of the present application on a terminal device
  • FIG19 is a flow chart of a method for assessing risk of chronic obstructive pulmonary disease provided in one embodiment of the present application.
  • FIG20a is a diagram showing the effect of a questionnaire provided in an embodiment of the present application on a terminal device
  • FIG20b is a diagram showing the effect of a questionnaire provided in an embodiment of the present application on a terminal device
  • FIG21a is a diagram showing the effect of the fourth prompt information provided by an embodiment of the present application on a wearable device
  • FIG21 b is a diagram showing the effect of the fourth prompt information provided by an embodiment of the present application on a terminal device
  • FIG22 is a schematic diagram of functional modules of a COPD risk assessment device provided in one embodiment of the present application.
  • FIG. 23 is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application.
  • “at least one” means one or more, and “more than one” means two or more than two.
  • “And/or” describes the association relationship of associated objects, indicating that three relationships may exist.
  • a and/or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural.
  • the terms “first”, “second”, “third”, “fourth”, etc. (if any) in the specification, claims and drawings of this application are used to distinguish similar objects, rather than to describe a specific order or sequence.
  • words such as “exemplary” or “for example” are used to indicate examples, illustrations or descriptions. Any embodiment or design described as “exemplary” or “for example” in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as “exemplary” or “for example” is intended to present related concepts in a specific way.
  • Figure 1 is a flow chart of a COPD risk assessment method provided in an embodiment of the present application. This embodiment is applied to a wearable device worn by a user, as shown in Figure 1, and includes the following steps:
  • Step S101 Acquire the user's first motion data and first physiological parameter.
  • the first physiological parameter corresponds to the first motion data, that is, the wearable device synchronously obtains the first motion data and the first physiological parameter of the user.
  • the first physiological parameter includes one of the following or any combination thereof: heart rate, blood oxygen saturation, respiratory rate, and heart rate variability (Heart Rate Variability, HRV).
  • this is the current MRC (Medical Research Council) dyspnea symptom assessment level standard. If users often experience increased respiratory rate, decreased HRV, increased heart rate, and decreased blood oxygen saturation in their daily lives, such as brisk walking/climbing stairs on flat ground, continuous walking for several minutes on flat ground, and in daily quiet conditions, they may be at risk of COPD.
  • MRC Medical Research Council
  • COPD patients and non-COPD patients were asked to walk on flat ground for several minutes and climb stairs. Monitor changes in their heart rate, respiratory rate, HRV, blood oxygen and other physiological parameters. The results showed that there were significant differences between COPD patients and non-COPD patients in the first physiological parameter.
  • Figure 3 (a) is a graph showing the heart rate changes of COPD patients when they continue to walk.
  • the horizontal axis shown in Figure 3 (a) is the total walking time
  • the vertical axis is the heart rate value.
  • the heart rate value will continue to increase over time.
  • Figure 3 (b) is a graph showing the HRV changes of COPD patients and normal people when they walk continuously.
  • the horizontal axis shown in Figure 3 (b) is the total number of milliseconds of walking, and the vertical axis is the HRV value. It can be seen from Figure 3 (b) that when COPD patients walk continuously on flat ground for several minutes, the HRV value will continue to decrease over time, while the HRV value of normal people will first increase and then decrease.
  • Figure 4 (a) is a graph showing the respiratory rate changes of COPD patients and normal people when they climb stairs.
  • the horizontal axis shown in Figure 4 (a) is the total number of seconds for climbing stairs, and the vertical axis is the respiratory rate value. It can be seen from Figure 4 (a) that the respiratory rate of COPD patients rises more slowly when climbing stairs.
  • Figure 4 (b) is a graph showing changes in blood oxygen saturation of COPD patients and normal people when they climb stairs.
  • the horizontal axis shown in Figure 4 (b) is the total number of seconds for climbing stairs, and the vertical axis is the blood oxygen saturation. It can be seen from Figure 4 (b) that the blood oxygen saturation of COPD patients when climbing stairs is lower than that of normal people when climbing stairs.
  • the wearable device includes: a watch, a headset, a smart bracelet, and other wearable devices with a display function. This embodiment does not specifically limit the type of the wearable device.
  • the wearable device is provided with a plurality of sensors, such as an accelerometer (ACC), a gyroscope sensor, an altimeter, etc., which can monitor the user's first motion data, and an optical heart rate sensor can monitor the user's heart rate.
  • sensors such as an accelerometer (ACC), a gyroscope sensor, an altimeter, etc., which can monitor the user's first motion data, and an optical heart rate sensor can monitor the user's heart rate.
  • Step S102 Determine the movement behavior corresponding to the first movement data.
  • the first motion data corresponds to a certain motion behavior of the user, including walking, running, climbing stairs, and resting (quiet/sleeping) state, etc.
  • the wearable device can obtain the user's motion data, such as the user's height change, speed change, etc., based on sensors such as accelerometers, gyroscope sensors, and altimeters.
  • a window will pop up to ask the user to confirm whether the motion behavior is being performed. For example, a window "Are you climbing stairs?" may pop up on the display interface, and the user may click "Confirm", and the wearable device will confirm that the user is climbing stairs. If the user does not click "Confirm” for a long time, such as the user still does not click "Confirm” after the window pops up for one minute, the wearable device will assume that the user clicks "Confirm” to confirm that the user is climbing stairs.
  • the wearable device can also use voice prompts to allow the user to confirm whether a certain exercise behavior is being performed. It is understandable that this embodiment does not specifically limit the way in which the wearable device allows the user to confirm whether a certain exercise behavior is being performed.
  • Step S103 Determine an evaluation result according to the exercise behavior and the first physiological parameter.
  • the evaluation result can be determined in the following manner: a target model that matches the movement behavior is selected from multiple preset models, the target model is trained based on the first historical movement data, the historical first physiological parameter corresponding to the first historical movement data, and the first physiological parameter reference value, the first physiological parameter reference value is the physiological parameter value of non-COPD patients corresponding to the first historical movement data; the first physiological parameter is input into the target model to determine the evaluation result.
  • each movement behavior of the user corresponds to a preset model, such as “walking” corresponds to the first preset model, “running” corresponds to the second preset model, “climbing stairs” corresponds to the third preset model, and “resting state” corresponds to the fourth preset model.
  • FIG. 5 Please refer to Figure 5 for a block diagram of the COPD symptom capture algorithm.
  • Wearable devices are used to record changes in the user's ACC, heart rate, respiratory rate, and blood oxygen saturation over a period of time. Specifically, first determine the user's exercise state based on changes in ACC and time; then extract the corresponding original features of physiological parameters such as respiratory rate, HRV, heart rate, etc. within the time range, including but not limited to time-frequency domain, approximate entropy, fitting coefficient and other features; then extract aggregate features from the original feature library, including but not limited to median, variance, coefficient of variation, etc.; finally, input the aggregate feature set into the target model for machine/deep learning, and then the target model outputs whether the user has COPD symptoms. of the evaluation results.
  • the evaluation result can also be determined in the following manner: determining a physiological parameter standard value that matches the exercise behavior, the physiological parameter standard value is a physiological parameter value corresponding to the exercise behavior of a non-COPD patient; determining the evaluation result based on the first physiological parameter and the physiological parameter standard value. It is understandable that the physiological parameter standard value can be the same as the first physiological parameter reference value mentioned above.
  • the difference between the first physiological parameter and the standard value of the physiological parameter is within a preset range. If the difference is within the preset range, the evaluation result is that the user does not have symptoms of COPD; if the difference is outside the preset range, the evaluation result is that the user has symptoms of COPD.
  • the evaluation result of whether the user has symptoms of COPD can be presented to the user in the form of a first prompt message.
  • the first prompt message can be a voice prompt, a text prompt on a display interface, etc. This embodiment does not specifically limit the presentation form of the first prompt message.
  • the embodiments of the present application have at least the following advantages: since the user's motion data and physiological parameters under different motion behaviors are different, by obtaining the user's first motion data, the motion behavior corresponding to the first motion data can be determined, and then the assessment result of the user's COPD risk can be determined based on the motion behavior and the first physiological parameter, thereby improving the accuracy of the COPD risk assessment method.
  • this assessment method can provide timely warning of COPD based on the user's daily exercise conditions even if the user has not undergone a pulmonary function test, thereby achieving early detection of COPD, enabling early diagnosis and treatment of COPD, and effectively protecting the user's physical health.
  • FIG. 6 is a flow chart of a COPD risk assessment method provided in an embodiment of the present application.
  • This embodiment is a further improvement of the above-mentioned embodiment, and the main improvement is that in this embodiment, the first total number of times that the user is assessed to have COPD symptoms within a first preset period is obtained, and when the first total number is greater than the first preset number, a first prompt message is sent. In this way, the accuracy of assessing whether the user has COPD can be further improved, thereby improving the reliability of the COPD risk assessment method.
  • This embodiment is applied to a wearable device worn by a user, as shown in FIG6 , and includes the following steps:
  • Step S201 acquiring first motion data and first physiological parameters in real time within a first preset period.
  • the first preset period may be one week or one month. This embodiment does not specifically limit the value of the first preset period.
  • Step S202 after acquiring the first motion data each time, determining the motion behavior corresponding to the first motion data.
  • Step S203 After each movement behavior is determined, a target model matching the movement behavior is selected from multiple preset models, and a first physiological parameter corresponding to the movement behavior is input into the target model; when an evaluation result of the target model is that the first total number of times the user has COPD symptoms is greater than a first preset number, a first prompt message is sent.
  • the wearable device will evaluate whether the user has COPD symptoms for each exercise. For example, if the user has 20 exercise behaviors (such as walking and climbing stairs) in a week, the wearable device will evaluate whether the user has COPD symptoms 20 times in total.
  • the first prompt message is sent. Specifically, assuming that the first preset period is one week and the preset evaluation number is 15 times, when the wearable device evaluates that the user has COPD symptoms more than 15 times in one week, the first prompt message is sent.
  • a first prompt message is sent.
  • the wearable device obtains 60 times of exercise by the user in one month, and the number of times the user is assessed to have COPD symptoms is 30 times, then the ratio of the first total number of times to the number of times the user exercises is less than the preset ratio, and the first prompt message is not sent.
  • Figure 7a and Figure 7b are effect diagrams of the first prompt information on the wearable device and the terminal device.
  • FIG. 7a it is a diagram showing the effect of the first prompt information on the wearable device.
  • the first preset period is one month, and the preset evaluation times are 15 times.
  • the wearable device detects that the user's breathing rate and heart rate increase too fast during walking, that is, the wearable device evaluates that the user has COPD symptoms.
  • the wearable device will automatically detect the user's breathing rate and heart rate.
  • the display screen of the wearable device displays the interface content shown in FIG. 7 a .
  • FIG. 7b it is a diagram showing the effect of the first prompt information on the wearable device.
  • the wearable device is connected to the user's terminal device, and the terminal device includes but is not limited to a mobile phone, a computer, a tablet computer, etc.
  • the first prompt information is sent to the terminal device so that the display interface of the terminal device displays the first prompt information.
  • the terminal device shown in Figure 7b is a mobile phone, the first preset period is one month, and the preset number of evaluations is 20 times.
  • the wearable device detects that the user's breathing rate and heart rate increase too fast after walking on flat ground for 6 minutes, that is, the wearable device evaluates that the user has symptoms of COPD. After the first total number of evaluations of COPD symptoms is greater than 20 times, the display screen of the terminal device displays the interface content shown in Figure 7b.
  • “resting state” such as nighttime sleep corresponds to the fourth preset model, and the first physiological parameters of the user in each exercise state are obtained, and the first physiological parameters obtained are input into the corresponding preset model according to different exercise behaviors.
  • the first physiological parameters corresponding to the 40 walking behaviors are input into the first preset model
  • the second physiological parameters corresponding to the 3 climbing stairs behaviors are input into the second preset model
  • the third physiological parameters corresponding to the 17 running behaviors are input into the third preset model
  • the fourth physiological parameters corresponding to the 30 nighttime sleep behaviors are input into the fourth preset model
  • the COPD symptom risk scores are obtained for each exercise state respectively.
  • the 40 evaluation results of the first preset model, the 3 evaluation results of the second preset model, the 17 evaluation results of the third preset model, and the 30 evaluation results of the fourth preset model are input into the preset comprehensive evaluation model, and according to the score and frequency of each behavior, a more accurate result of whether the user has COPD symptoms is obtained comprehensively.
  • the embodiments of the present application have at least the following advantages: since the user's motion data under different motion behaviors are different, by obtaining the user's first motion data and selecting a target model that matches the first motion data from multiple preset models, different preset models can be used for different motion behaviors of the user, thereby improving the accuracy of the COPD risk assessment method. Since the target model is trained based on historical motion data, historical first physiological parameters, and reference values of the first physiological parameters, the accuracy of the model output results can be ensured, and by inputting the first physiological parameter into the target model to obtain an assessment result of whether the user has COPD symptoms, the accuracy of the COPD risk assessment method is further improved.
  • this assessment method can provide timely warning of COPD based on the user's daily exercise conditions even if the user has not undergone a pulmonary function test, thereby achieving early detection of COPD, enabling early diagnosis and treatment of COPD, and effectively protecting the user's health.
  • FIG 8 is a flow chart of a COPD risk assessment method provided in an embodiment of the present application.
  • This embodiment is a further improvement of the previous embodiment, and the main improvement is that in this embodiment, it is also detected whether the user is smoking, and a second prompt message is sent when it is detected that the user has smoked multiple times. Since the main cause of COPD is smoking, in this way, the user can be reminded after the user has smoked multiple times, so that the user can reduce the frequency of smoking after receiving the second prompt message, further ensuring the user's physical health.
  • This embodiment is applied to a wearable device worn by a user, as shown in FIG8 , and includes the following steps:
  • Step S301 Acquire the user's first motion data and first physiological parameter.
  • Step S302 Determine the movement behavior corresponding to the first movement data.
  • Step S303 Determine an evaluation result according to the exercise behavior and the first physiological parameter.
  • Steps S301 to S303 of this embodiment are similar to steps S101 to S103 of the aforementioned embodiment, and are not described again here to avoid repetition.
  • Step S304 Acquire the user's second motion data and second physiological parameter.
  • the second motion data may be an ACC value sensed by a device worn by the user.
  • the second physiological parameter includes one of the following or any combination thereof: heart rate, respiratory rate.
  • heart rate When the user inhales, the body will have the following characteristics: (1) Heart rate changes: the heart rate of the human body will increase significantly in a short period of time after coughing, and then slowly return to normal heart rate; (2) When smoking, there is a deep breathing action, and the respiratory rate changes for a short time.
  • the ACC value changes when the user smokes. Specifically, when the user smokes, the user will inhale/breathe, and may also lower or raise the head, which will cause the ACC sensor to Changes in the device and gyroscope sensors.
  • FIG. 10 it is a graph showing the change of ACC value when the wearable device is a watch or a bracelet. Specifically, when the hand wearing the watch or the bracelet smokes, it will be accompanied by the action of raising the hand, which will also cause the change of sensors such as ACC.
  • Step S305 input the second motion data and the second physiological parameter into a preset smoking detection model to obtain a detection result of whether the user is smoking.
  • FIG. 11 Please refer to Figure 11 for a block diagram of the smoking motion capture algorithm.
  • the user's ACC changes, heart rate changes, respiratory rate changes, and heart rate changes are recorded through wearable devices.
  • the second preset model in this embodiment and the first preset model in the above-mentioned embodiment may be the same model or different models, and this embodiment does not specifically limit this.
  • the second prompt information may be a voice prompt, a text prompt on a display interface, etc. This embodiment does not specifically limit the presentation form of the second prompt information.
  • FIG 12 it is a diagram showing the effect of the second prompt information on the wearable device. Assuming that the preset number of times is 7 times, and the second preset period is 12 hours. When the wearable device evaluates that the user is smoking more than 7 times within 12 hours, the second prompt information is sent.
  • the embodiments of the present application have at least the following advantages: since the user's motion data and physiological parameters under different motion behaviors are different, by obtaining the user's first motion data, the motion behavior corresponding to the first motion data can be determined, and then the assessment result of the user's COPD risk can be determined based on the motion behavior and the first physiological parameter, thereby improving the accuracy of the COPD risk assessment method.
  • this assessment method can provide timely warning of COPD based on the user's daily exercise conditions even if the user has not undergone a pulmonary function test, thereby achieving early detection of COPD, enabling early diagnosis and treatment of COPD, and effectively protecting the user's physical health.
  • Figure 13 is a flow chart of a COPD risk assessment method provided in an embodiment of the present application.
  • This embodiment is a further improvement on the aforementioned embodiment.
  • the main improvement is that in this embodiment, whether the user has COPD symptoms is also evaluated in combination with the user's smoking frequency, which can further improve the accuracy of evaluating whether the user has COPD, thereby improving the reliability of the COPD risk assessment method.
  • This embodiment is applied to a wearable device worn by a user, as shown in FIG13 , and includes the following steps:
  • Step S401 Acquire the user's second motion data and second physiological parameter.
  • Step S402 inputting the second motion data and the second physiological parameter into a preset smoking detection model to obtain a detection result of whether the user is smoking.
  • Step S403 If within the second preset period, the detection result is that the second total number of times the user is smoking is greater than the second preset number, a second prompt message is sent.
  • Step S404 Acquire the user's first motion data and first physiological parameter, and determine the motion behavior corresponding to the first motion data.
  • Step S405 Select a target comprehensive evaluation model from a plurality of comprehensive evaluation models according to the exercise behavior and the second total number of times.
  • Step S406 input the first physiological parameter and the second total number of times into the target comprehensive evaluation model to determine the evaluation result.
  • the wearable device records the changes in the user's heart rate, breathing rate, and blood oxygen saturation during exercise, and records the number of times the user smokes.
  • time changes determine what kind of exercise state the user is in; then extract the corresponding original features of physiological parameters such as respiratory rate, HRV, heart rate within the time range, including but not limited to time-frequency domain, approximate entropy, fitting coefficient and other features; then extract aggregated features from the original feature library, including but not limited to median, variance, coefficient of variation, etc.; finally, input the aggregated feature set and the recorded user smoking frequency into the target model for machine/deep learning, and then the target model outputs the evaluation result of whether the user has COPD symptoms.
  • physiological parameters such as respiratory rate, HRV, heart rate within the time range, including but not limited to time-frequency domain, approximate entropy, fitting coefficient and other features
  • aggregated features from the original feature library, including but not limited to median, variance, coefficient of variation, etc.
  • input the aggregated feature set and the recorded user smoking frequency into the target model for machine
  • the wearable device sends the second prompt information to the user.
  • the user exercises once on the second day. If the user's exercise behavior and the first physiological parameter are used, it is possible to evaluate that the user does not have symptoms of COPD. However, considering that the user smoked 8 times in the previous day, the user's exercise behavior, the first physiological parameter and the total number of times he smoked are used, and the user is evaluated to have symptoms of COPD.
  • the target comprehensive evaluation model in this embodiment and the target model in the previous embodiment may be the same model or different models, and this embodiment does not specifically limit this.
  • the embodiments of the present application have at least the following advantages: since the user's motion data under different motion behaviors are different, by obtaining the user's first motion data and selecting a target model that matches the first motion data from multiple preset models, different preset models can be used for different motion behaviors of the user, thereby improving the accuracy of the COPD risk assessment method. Since the target model is trained based on historical motion data, historical first physiological parameters, and reference values of the first physiological parameters, the accuracy of the model output results can be ensured, and by inputting the first physiological parameter into the target model to obtain an assessment result of whether the user has COPD symptoms, the accuracy of the COPD risk assessment method is further improved.
  • this assessment method can provide timely warning of COPD based on the user's daily exercise conditions even if the user has not undergone a pulmonary function test, thereby achieving early detection of COPD, enabling early diagnosis and treatment of COPD, and effectively protecting the user's health.
  • Figure 15 is a flow chart of a COPD risk assessment method provided in an embodiment of the present application.
  • This embodiment is a further improvement on the aforementioned embodiment.
  • the main improvement is that in this embodiment, after sending the first prompt message to the user, it is further confirmed whether the user has COPD based on the user's physiological sounds, thereby further improving the reliability of the COPD risk assessment method.
  • This embodiment is applied to a wearable device worn by a user, as shown in FIG15 , and includes the following steps:
  • Step S501 acquiring first motion data and first physiological parameters in real time within a first preset period.
  • Step S502 after acquiring the first motion data each time, determining the motion behavior corresponding to the first motion data.
  • Step S503 After each movement behavior is determined, a target model matching the movement behavior is selected from multiple preset models, and a first physiological parameter corresponding to the movement behavior is input into the target model; when an evaluation result of the target model is that the first total number of times the user has COPD symptoms is greater than a first preset number, a first prompt message is sent.
  • Steps S501 to S503 of this embodiment are similar to steps S201 to S203 of the aforementioned embodiment, and will not be described again to avoid repetition.
  • Step S504 Acquire the physiological sounds of the user.
  • the display interface of the first prompt information has a “start measurement” button. After the user clicks the “start measurement” button, the wearable device starts to obtain the user's physiological sounds.
  • COPD patients have difficulty breathing due to airway obstruction, and the user's lung function can be evaluated through physiological sounds such as coughing and blowing.
  • this is a difference diagram of coughing sounds between healthy people and COPD patients.
  • Coughing sound The patient's respiratory mucus hypersecretion and ciliary dysfunction trigger coughing; compared with normal people, the patient's cough is unevenly distributed in the time domain, and there is a short tail after each cough; in the frequency domain, the audio energy of COPD patients is concentrated in the low frequency band.
  • Blowing sound The patient's airway is narrow, and when blowing hard, the blowing sound lasts for a short time and the intensity decays quickly.
  • Step S505 extract features of physiological sounds, input the feature extraction results into a sound feature detection model, and obtain the user's lung function assessment results.
  • the physiological sound signal is preprocessed, including speech enhancement, filtering and pre-emphasis, to enhance the physiological sound signal and filter out background noise and invalid frequency bands;
  • the original features of the preprocessed physiological sounds are then extracted, including Mel-frequency cepstral coefficients and differences, spectral contrast, spectral entropy, linear prediction coefficients, spectral centroid, spectral bandwidth and other time and frequency domain features.
  • Aggregate features are then extracted from the original feature library, including but not limited to median, variance, coefficient of variation, etc.
  • the aggregate feature set is input into the sound feature detection model for machine/deep learning to obtain the user's lung function assessment results.
  • Step S506 When the lung function assessment result does not meet the second preset requirement, a third prompt message is sent.
  • the third prompt information may be a voice prompt, a text prompt on a display interface, etc. This embodiment does not specifically limit the presentation form of the third prompt information.
  • the third prompt information is shown on the wearable device and the terminal device.
  • Figure 18a is a diagram showing the effect of the third prompt information on the wearable device;
  • Figure 18b is a diagram showing the effect of the third prompt information on the terminal device.
  • the pulmonary function assessment result is presented in the form of a comprehensive pulmonary function score. When the comprehensive pulmonary function score is lower than the preset score, it indicates that the pulmonary function assessment result does not meet the second preset requirement, and the third prompt information shown in Figures 18a and 18b is sent.
  • the embodiments of the present application have at least the following advantages: since the user's motion data under different motion behaviors are different, by obtaining the user's first motion data and selecting a target model that matches the first motion data from multiple preset models, different preset models can be used for different motion behaviors of the user, thereby improving the accuracy of the COPD risk assessment method. Since the target model is trained based on historical motion data, historical first physiological parameters, and reference values of the first physiological parameters, the accuracy of the model output results can be ensured, and by inputting the first physiological parameter into the target model to obtain an assessment result of whether the user has COPD symptoms, the accuracy of the COPD risk assessment method is further improved.
  • this assessment method can provide timely warning of COPD based on the user's daily exercise conditions even if the user has not undergone a pulmonary function test, thereby achieving early detection of COPD, enabling early diagnosis and treatment of COPD, and effectively protecting the user's health.
  • FIG 19 is a flow chart of a COPD risk assessment method provided in an embodiment of the present application.
  • This embodiment is a further improvement of the aforementioned embodiment.
  • the main improvement is that in this embodiment, after sending the third prompt information, a questionnaire for characterizing the possibility of COPD will also be sent to the user.
  • the questionnaire is used to further confirm whether the user has COPD, thereby further improving the accuracy of assessing whether the user has COPD.
  • This embodiment is applied to a wearable device worn by a user, and the specific process is shown in FIG19 , including the following steps:
  • Step S601 Acquire the user's first motion data and first physiological parameter.
  • Step S602 after acquiring the first motion data each time, determining the motion behavior corresponding to the first motion data.
  • Step S603 After each movement behavior is determined, a target model matching the movement behavior is selected from multiple preset models, and a first physiological parameter corresponding to the movement behavior is input into the target model; when an evaluation result of the target model is that the first total number of times the user has COPD symptoms is greater than a first preset number, a first prompt message is sent.
  • Step S604 Acquire the physiological sounds of the user.
  • Step S605 extract features of physiological sounds, input the feature extraction results into a sound feature detection model, and obtain the user's lung function assessment results.
  • Step S606 When the lung function assessment result does not meet the second preset requirement, a third prompt message is sent.
  • Steps S601 to S606 of this embodiment are similar to steps S501 to S506 of the aforementioned embodiment, and will not be described again to avoid repetition.
  • Step S607 Sending a questionnaire to the user to characterize the possibility of developing COPD.
  • the display interface of the third prompt information has a "Start Screening" button. After the user clicks the "Start Screening" button, the wearable device sends a questionnaire to the user.
  • the questionnaire is displayed on the terminal device.
  • the wearable device is connected to the user's terminal device.
  • the wearable device needs to send a questionnaire, it sends the questionnaire to the terminal device so that the terminal device's display interface displays the questionnaire.
  • the terminal device shown in Figures 20a and 20b is a mobile phone.
  • the questionnaire involves issues such as smoking, chest tightness, asthma, mucus or phlegm, and sleep quality in daily life.
  • Step S608 Obtain the filling result of the questionnaire, and send a fourth prompt message when the filling result does not meet the third preset requirement.
  • the fourth prompt information may be a voice prompt, a text prompt on a display interface, etc. There is no specific limitation on the presentation form of the fourth prompt information.
  • the fourth prompt information is shown on the wearable device and the terminal device.
  • Figure 21a is the effect of the fourth prompt information on the wearable device;
  • Figure 21b is the effect of the fourth prompt information on the terminal device.
  • the fourth prompt information will display the user's dyspnea symptom assessment level with reference to the dyspnea symptom assessment level standard shown in Figure 2, so as to intuitively inform the user of the severity of COPD.
  • the embodiments of the present application have at least the following advantages: since the user's motion data under different motion behaviors are different, by obtaining the user's first motion data and selecting a target model that matches the first motion data from multiple preset models, different preset models can be used for different motion behaviors of the user, thereby improving the accuracy of the COPD risk assessment method. Since the target model is trained based on historical motion data, historical first physiological parameters, and reference values of the first physiological parameters, the accuracy of the model output results can be ensured, and by inputting the first physiological parameter into the target model to obtain an assessment result of whether the user has COPD symptoms, the accuracy of the COPD risk assessment method is further improved.
  • this assessment method can provide timely warning of COPD based on the user's daily exercise conditions even if the user has not undergone a pulmonary function test, thereby achieving early detection of COPD, enabling early diagnosis and treatment of COPD, and effectively protecting the user's health.
  • the COPD risk assessment device includes:
  • a motion data acquisition module 1 the motion data acquisition module 1 is used to acquire the user's first motion data; a physiological parameter acquisition module 2, the physiological parameter acquisition module 2 is used to acquire the user's first physiological parameter; a motion behavior determination module 3, the motion behavior determination module 3 is used to determine the motion behavior corresponding to the first motion data, the motion behavior including at least one of walking, running, climbing stairs and resting; a COPD assessment module 4, the COPD assessment module 4 is used to determine the assessment result based on the motion behavior and the first physiological parameter.
  • Figure 23 is a schematic diagram of the hardware structure of the electronic device 1000 provided in an embodiment of the present application.
  • the electronic device 1000 may include a processor 1001 and a memory 1002.
  • the memory 1002 is used to store one or more computer programs 1003.
  • the one or more computer programs 1003 are configured to be executed by the processor 1001.
  • the one or more computer programs 1003 include instructions, and the above instructions can be used to implement the above-mentioned COPD risk assessment method in the electronic device 1000.
  • the structure shown in this embodiment does not constitute a specific limitation on the electronic device 1000.
  • the electronic device 1000 may include more or fewer components than shown, or combine or separate some components, or arrange the components differently.
  • the processor 1001 may include one or more processing units, for example, the processor 1001 may include an application processor (AP), a modem, a graphics processor (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and/or a neural-network processing unit (NPU), etc.
  • AP application processor
  • GPU graphics processor
  • ISP image signal processor
  • DSP digital signal processor
  • NPU neural-network processing unit
  • Different processing units may be independent devices or integrated in one or more processors.
  • the processor 1001 may also be provided with a memory for storing instructions and data.
  • the memory in the processor 1001 is a cache memory.
  • the memory may store instructions or data that the processor 1001 has just used or cyclically used. If the processor 1001 needs to use the instruction or data again, it may be directly called from the memory. This avoids repeated access, reduces the waiting time of the processor 1001, and thus improves the efficiency of the system.
  • the processor 1001 may include one or more interfaces.
  • the interface may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver/transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input/output (GPIO) interface, a SIM interface, and/or a USB interface.
  • I2C inter-integrated circuit
  • I2S inter-integrated circuit sound
  • PCM pulse code modulation
  • UART universal asynchronous receiver/transmitter
  • MIPI mobile industry processor interface
  • GPIO general-purpose input/output
  • SIM interface SIM interface
  • USB interface USB interface
  • the memory 1002 may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), an Secure Digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.
  • a non-volatile memory such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), an Secure Digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.
  • This embodiment also provides a computer-readable storage medium, which stores computer instructions.
  • the electronic device executes the above-mentioned related method steps to implement the COPD risk assessment method in the above-mentioned embodiment.
  • the electronic device and computer storage medium provided in this embodiment are used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, and will not be repeated here.
  • the above functions can be distributed to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.
  • the disclosed devices and methods can be implemented in other ways.
  • the device embodiments described above are schematic.
  • the division of the modules or units is a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed.
  • Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
  • the unit described as a separate component may or may not be physically separated, and the component shown as a unit may be one physical unit or multiple physical units, that is, it may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
  • the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium.
  • the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute all or part of the steps of the method described in each embodiment of the present application.
  • the aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

Landscapes

  • Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Epidemiology (AREA)
  • Pathology (AREA)
  • Biomedical Technology (AREA)
  • Primary Health Care (AREA)
  • Molecular Biology (AREA)
  • Pulmonology (AREA)
  • Surgery (AREA)
  • Biophysics (AREA)
  • Physics & Mathematics (AREA)
  • Physiology (AREA)
  • Veterinary Medicine (AREA)
  • Animal Behavior & Ethology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

本申请提供一种慢阻肺风险评估方法、装置、电子设备及计算机可读存储介质，涉及终端设备技术领域，慢阻肺风险评估方法包括：获取用户的第一运动数据和第一生理参数（101）；确定与第一运动数据对应的运动行为（102），运动行为包括行走、跑步、爬楼梯以及静息中的至少一种；根据运动行为和第一生理参数，确定评估结果（103）。本申请可在用户没有进行肺功能检查的情况下，也能对慢阻肺进行及时预警，实现了对慢阻肺的早发现，使得慢阻肺能够早诊断、早治疗，有效地保障了用户的身体健康。

Description

一种慢阻肺风险评估方法、装置、电子设备及存储介质
本申请要求于2022年11月14日提交中国专利局，申请号为202211426393.3、申请名称为“一种慢阻肺风险评估方法、装置、电子设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及终端设备技术领域，尤其涉及一种慢阻肺风险评估方法、装置、电子设备及存储介质。
背景技术
慢性阻塞性肺疾病(简称慢阻肺)是一种常见的慢性呼吸疾病，主要是由于吸烟等原因引起气道狭窄或肺气肿等结构改变，导致呼吸气流受阻，感到呼吸费力或透不上气，常伴有咳嗽、咳痰等不适。目前，慢阻肺全国患病近1亿，超过90％的患者是吸烟引起的。慢阻肺的主要诱因是吸烟，此外，居家充满厨房油烟和烟雾、长时间在多烟雾和粉尘的地方工作、被动吸烟、儿时经常呼吸道感染也会导致慢阻肺病发。慢阻肺的呼吸气流受阻会越来越重，不仅让呼吸系统受累，还累及骨骼肌肉、心脏等全身多个脏器。
然而，由于慢阻肺早期病人没有明显不适，因此病人很少会去就医，待有症状就医时，已出现气道狭窄的现象，导致慢阻肺的治疗效果不佳。
发明内容
有鉴于此，本申请提供一种慢阻肺风险评估方法，可对用户出现的慢阻肺进行及时预警，实现了对慢阻肺的早发现，使得慢阻肺能够早诊断、早治疗，有效地保障了用户的身体健康。
本申请的第一方面提供一种慢阻肺风险评估方法，包括：获取用户的第一运动数据和第一生理参数；确定与所述第一运动数据对应的运动行为，所述运动行为包括行走、跑步、爬楼梯以及静息中的至少一种；根据所述运动行为和所述第一生理参数，确定评估结果。
本申请的实施例至少具有以下优点：
由于用户在不同运动行为下的运动数据和生理参数均不相同，通过获取用户的第一运动数据，从而能够确定与第一运动数据对应的运动行为，再根据运动行为和第一生理参数，确定用户慢阻肺风险的评估结果，提高了慢阻肺风险评估方法的准确性。此外，此种评估方式能够在用户没有进行肺功能检查的情况下，也能基于用户日常的运动情况对慢阻肺进行及时预警，实现了对慢阻肺的早发现，使得慢阻肺能够早诊断、早治疗，有效地保障了用户的身体健康。
在一些可能的实现方式中，所述根据所述运动行为和所述第一生理参数，确定评估结果，包括：在多个预设模型中选择与所述运动行为匹配的目标模型，所述目标模型是根据第一历史运动数据、与所述第一历史运动数据对应的历史第一生理参数和第一生理参数参考值训练得到，所述第一生理参数参考值为非慢阻肺患者与所述第一历史运动数据对应的生理参数值；将所述第一生理参数输入所述目标模型，确定所述评估结果。
通过采用该技术方案，能够对用户不同的运动行为选择不同的预设模型，确保目标 模型输出结果的准确率。
在一些可能的实现方式中，所述获取用户的第一运动数据和第一生理参数，包括：在第一预设周期内，实时获取所述第一运动数据和所述第一生理参数；所述确定与所述第一运动数据对应的运动行为，包括：在每次获取所述第一运动数据后，均确定与所述第一运动数据对应的运动行为；所述在多个预设模型中选择与所述运动行为匹配的目标模型，将所述第一生理参数输入所述目标模型，确定所述评估结果，包括：在每次确定所述运动行为后，均从多个所述预设模型中选择与所述运动行为匹配的目标模型，并将与所述运动行为对应的第一生理参数输入所述目标模型；在所述目标模型的所述评估结果为所述用户具有慢阻肺症状的第一总次数大于第一预设次数时，发送第一提示信息。
通过采用该技术方案，能够进一步提高评估用户是否具有慢阻肺的准确性，从而提高了慢阻肺风险评估方法的可靠性。
在一些可能的实现方式中，所述根据所述运动行为和所述第一生理参数，确定评估结果，包括：确定与所述运动行为匹配的生理参数标准值，所述生理参数标准值为非慢阻肺患者与所述运动行为对应的生理参数值；根据所述第一生理参数和所述生理参数标准值，确定所述评估结果。
通过采用该技术方案，能够快速获得用户是否具有慢阻肺的评估结果，提高了用户的使用体验。
在一些可能的实现方式中，所述方法还包括：获取所述用户的第二运动数据和第二生理参数；将所述第二运动数据和所述第二生理参数输入预设吸烟检测模型，得到所述用户是否正在吸烟的检测结果，其中，所述预设吸烟检测模型根据第二历史运动数据、与所述第二历史运动数据对应的历史第二生理参数和第二生理参数参考值训练得到，所述第二生理参数参考值为所述用户非吸烟状态下与所述第二运动数据对应的生理参数值；若在第二预设周期内，所述检测结果为用户正在吸烟的第二总次数大于第二预设次数，发送第二提示信息。
通过采用该技术方案，能够检测用户是否吸烟，并在用户多次吸烟时警告用户，使得用户在接收到第二提示信息后能够减少吸烟频率，进一步保障了用户的身体健康。
在一些可能的实现方式中，所述根据所述运动行为和所述第一生理参数，确定评估结果，包括：根据所述运动行为、所述第一生理参数和所述检测结果为所述用户正在吸烟的第二总次数，确定所述评估结果。
通过采用该技术方案，能够进一步提高评估用户是否具有慢阻肺的准确性，从而提高了慢阻肺风险评估方法的可靠性。
在一些可能的实现方式中，所述根据所述运动行为、所述第一生理参数和所述检测结果为所述用户正在吸烟的第二总次数，确定所述评估结果，包括：根据所述运动行为和所述第二总次数，在多个综合评估模型中选择目标综合评估模型；将所述第一生理参数和所述第二总次数输入所述目标综合评估模型，确定所述评估结果。
通过采用该技术方案，能够进一步提高评估用户是否具有慢阻肺的准确性，从而提高了慢阻肺风险评估方法的可靠性。
在一些可能的实现方式中，在所述发送第一提示信息之后，还包括：获取所述用户的生理音；对所述生理音进行特征提取，将所述特征提取的结果输入声音特征检测模型，得到所述用户的肺功能评估结果；在所述肺功能评估结果不满足第二预设要求时，发送第三提示信息。
通过采用该技术方案，能够在向用户发送第一提示信息后，根据用户的生理音进一步确认用户是否具有慢阻肺，提高了慢阻肺风险评估方法的可靠性。
在一些可能的实现方式中，在所述发送第三提示信息之后，还包括：向所述用户发送用于表征慢阻肺发病可能性的问卷调查表；获取所述问卷调查表的填写结果，在所述填写结果不满足第三预设要求时，发送第四提示信息。
通过采用该技术方案，能够通过问卷调查表进一步确认用户是否具有慢阻肺，从而 进一步提高了评估用户是否具有慢阻肺的准确性。
在一些可能的实现方式中，所述第一生理参数包括以下之一或其任意组合：心率、血氧饱和度、呼吸率以及心率变异性。
通过采用该技术方案，能够准确评估用户是否具有慢阻肺症状。
本申请第二方面公开了一种慢阻肺风险评估装置，包括：运动数据获取模块，所述运动数据获取模块用于获取用户的第一运动数据；生理参数获取模块，所述生理参数获取模块用于获取所述用户的第一生理参数；运动行为确定模块，所述运动行为确定模块用于确定与所述第一运动数据对应的运动行为，所述运动行为包括行走、跑步、爬楼梯以及静息中的至少一种；慢阻肺评估模块，所述慢阻肺评估模块用于根据所述运动行为和所述第一生理参数，确定评估结果。
本申请第三方面公开了一种计算机可读存储介质，包括计算机指令，当所述计算机指令在电子设备上运行时，使得所述电子设备执行上述的慢阻肺风险评估方法。
本申请第四方面公开了一种电子设备，所述电子设备包括处理器和存储器，所述存储器用于存储指令，所述处理器用于调用所述存储器中的指令，使得所述电子设备执行上述的慢阻肺风险评估方法。
可以理解地，上述提供的第二方面的慢阻肺风险评估装置，第三方面的计算机可读存储介质，第四方面的电子设备均与上述第一方面的方法对应，因此，其所能达到的有益效果可参考上文所提供的对应的方法中的有益效果，此处不再赘述。
附图说明
图1为本申请一实施例提供的慢阻肺风险评估方法的流程示意图；
图2为本申请一实施例提供的呼吸困难症状评估等级标准图；
图3中的(a)为本申请一实施例提供的慢阻肺患者持续行走时的心率变化图；
图3中的(b)为本申请一实施例提供的慢阻肺患者与正常人持续行走时的HRV变化图；
图4中的(a)为本申请一实施例提供的慢阻肺患者与正常人爬楼梯时的呼吸率变化图；
图4中的(b)为本申请一实施例提供的慢阻肺患者与正常人爬楼梯时的血氧饱和度变化图；
图5为本申请一实施例提供的慢阻肺症状捕捉算法框图；
图6为本申请一实施例提供的慢阻肺风险评估方法的流程示意图；
图7a为本申请一实施例提供的第一提示信息在穿戴设备上的效果图；
图7b为本申请一实施例提供的第一提示信息在终端设备上的效果图；
图8为本申请一实施例提供的慢阻肺风险评估方法的流程示意图；
图9为本申请一实施例提供的穿戴设备为耳机时的用户吸烟时的ACC传感器变化图；
图10为本申请一实施例提供的穿戴设备为手表或手环时的用户吸烟时的ACC传感器变化图；
图11为本申请一实施例提供的吸烟动作捕捉算法框图；
图12为本申请一实施例提供的第二提示信息在穿戴设备上的效果图；
图13为本申请一实施例提供的慢阻肺风险评估方法的流程示意图；
图14为本申请一实施例提供的慢阻肺无感检测算法流程图；
图15为本申请一实施例提供的慢阻肺风险评估方法的流程示意图；
图16为本申请一实施例提供的健康人和慢阻肺患者的咳嗽音差异图；
图17为本申请一实施例提供的肺功能评估算法框图；
图18a为本申请一实施例提供的第三提示信息在穿戴设备上的效果图；
图18b为本申请一实施例提供的第三提示信息在终端设备上的效果图；
图19为本申请一实施例提供的慢阻肺风险评估方法的流程示意图；
图20a为本申请一实施例提供的问卷调查表在终端设备上的效果图；
图20b为本申请一实施例提供的问卷调查表在终端设备上的效果图；
图21a为本申请一实施例提供的第四提示信息在穿戴设备上的效果图；
图21b为本申请一实施例提供的第四提示信息在终端设备上的效果图；
图22为本申请一实施例提供的慢阻肺风险评估装置的功能模块示意图；
图23为本申请一实施例提供的电子设备的硬件结构示意图。
具体实施方式
为了能够更清楚地理解本申请的上述目的、特征和优点，下面结合附图和具体实施方式对本申请进行详细描述。需要说明的是，在不冲突的情况下，本申请的实施方式及实施方式中的特征可以相互组合。
在下面的描述中阐述了很多具体细节以便于充分理解本申请，所描述的实施方式仅是本申请一部分实施方式，而不是全部的实施方式。
除非另有定义，本文所使用的所有的技术和科学术语与属于本申请的技术领域的技术人员通常理解的含义相同。本文中在本申请的说明书中所使用的术语只是为了描述具体的实施方式的目的，不是旨在于限制本申请。
进一步需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。
本申请中“至少一个”是指一个或者多个，“多个”是指两个或多于两个。“和/或”，描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B可以表示：单独存在A，同时存在A和B，单独存在B的情况，其中A，B可以是单数或者复数。本申请的说明书和权利要求书及附图中的术语“第一”、“第二”、“第三”、“第四”等(如果存在)是用于区别类似的对象，而不是用于描述特定的顺序或先后次序。
在本申请实施例中，“示例性的”或者“例如”等词用于表示作例子、例证或说明。本申请实施例中被描述为“示例性的”或者“例如”的任何实施例或设计方案不应被解释为比其它实施例或设计方案更优选或更具优势。确切而言，使用“示例性的”或者“例如”等词旨在以具体方式呈现相关概念。
请参考图1，为本申请实施例提供的慢阻肺风险评估方法的流程图。本实施例应用于用户佩戴的穿戴设备，如图1所示，包括以下步骤：
步骤S101：获取用户的第一运动数据和第一生理参数。
在一些实施例中，第一生理参数与第一运动数据对应，即穿戴设备同步获取用户的第一运动数据和第一生理参数。
在一些实施例中，第一生理参数包括以下之一或其任意组合：心率、血氧饱和度、呼吸率以及心率变异性(Heart Rate Variability，HRV)。
如图2所示，为当前MRC(Medical Research Council，英国医学研究委员会)呼吸困难症状评估等级标准。用户如果在日常生活中，例如平地快步行走/爬楼梯、平地持续行走数分钟、日常安静状态下，若经常出现呼吸率升高、HRV下降、心率升高以及血氧饱和度降低等状态时，可能存在慢阻肺风险。
如图3、图4所示，让慢阻肺患者和非慢阻肺患者在平地行走数分钟以及爬楼梯， 监测他们的心率、呼吸率、HRV、血氧等生理参数的变化。结果显示，慢阻肺患者和非慢阻肺患者在第一生理参数上存在明显差异。
请参见图3中的(a)，为慢阻肺患者持续行走时的心率变化图。具体的说，图3中的(a)所示的横坐标为行走的总时间，纵坐标为心率值。由图3中的(a)可知，慢阻肺患者在平地持续行走数分钟时，心率值会随着时间的推移不断升高。
请参见图3中的(b)，为慢阻肺患者与正常人持续行走时的HRV变化图。图3中的(b)所示的横坐标为行走的总毫秒数，纵坐标为HRV值，由图3中的(b)可知，慢阻肺患者在平地持续行走数分钟时，HRV值会随着时间的推移不断降低，而正常人的HRV值会先升高再降低。
请参见图4中的(a)，为慢阻肺患者与正常人爬楼梯时的呼吸率变化图。图4中的(a)所示的横坐标为爬楼梯的总秒数，纵坐标为呼吸率值，由图4中的(a)可知，慢阻肺患者在爬楼梯时，呼吸率上升的较为缓慢。
请参见图4中的(b)，为慢阻肺患者与正常人爬楼梯时的血氧饱和度变化图。图4中的(b)所示的横坐标为爬楼梯的总秒数，纵坐标为血氧饱和度，由图4中的(b)可知，慢阻肺患者在爬楼梯时的血氧饱和度比正常人在爬楼梯时的血氧饱和度低。
在一些实施例中，穿戴设备包括：手表、耳机、智能手环等具有显示功能的可穿戴设备，本实施例并不对穿戴设备的类型做具体限定。
具体的说，穿戴设备内设有多个传感器，如加速度(ACC，Acceleration)传感器、陀螺仪传感器、高度计等能够监测用户的第一运动数据，光学心率传感器能够监测用户的心率。
步骤S102：确定与第一运动数据对应的运动行为。
在一些实施例中，第一运动数据对应用户某一运动行为，运动行为包括行走、跑步、爬楼梯以及静息(安静/睡眠)状态等，穿戴设备可以根据加速度传感器、陀螺仪传感器、高度计等传感器获取用户的运动数据，如用户的高度变化、速度变化等。
在一些实施例中，穿戴设备通过第一运动数据匹配某一运动行为后，会弹出窗口让用户确认是否在进行该运动行为。例如，可以在显示界面弹出“您是否在爬楼梯”的窗口，用户可以点击“确认”，穿戴设备即确认用户在爬楼梯。如果用户长时间没有进行点击“确认”的操作，如弹出窗口一分钟后用户仍未点击“确认”，此时穿戴设备默认用户点击“确认”，确认用户在爬楼梯。
在一些实施例中，穿戴设备还可以通过语音提示的方式，使用户确认是否在进行某一运动行为。可以理解的是，本实施例并不对穿戴设备通过何种方式让用户确认是否在进行某一运动行为进行具体的限定。
步骤S103：根据运动行为和第一生理参数，确定评估结果。
在一些实施例中，可以通过以下方式确定评估结果：在多个预设模型中选择与运动行为匹配的目标模型，目标模型是根据第一历史运动数据、与第一历史运动数据对应的历史第一生理参数和第一生理参数参考值训练得到，第一生理参数参考值为非慢阻肺患者与第一历史运动数据对应的生理参数值；将第一生理参数输入目标模型，确定评估结果。
在一些实施例中，用户的每一个运动行为均与一个预设模型对应，如“行走”对应第一预设模型，“跑步”对应第二预设模型，“爬楼梯”对应第三预设模型，‘静息状态’对应第四预设模型。
请参见图5，为慢阻肺症状捕捉算法框图。通过穿戴设备记录用户一个时间段内的ACC变化、心率变化、呼吸率变化以及血氧饱和度变化。具体的说，首先根据ACC、时间变化，确定用户处于何种运动状态；之后对该时间范围内的呼吸率、HRV、心率等生理参数，提取相应的原始特征，包括但不限于时频域、近似熵、拟合系数等特征；然后对原始特征库提取聚合特征，包括但不限于中位数、方差、变异系数等；最后将聚合特征集输入目标模型中进行机器/深度学习，再由目标模型输出用户是否具有慢阻肺症状 的评估结果。
在一些实施例中，还可以通过以下方式确定评估结果：确定与运动行为匹配的生理参数标准值，生理参数标准值为非慢阻肺患者与运动行为对应的生理参数值；根据第一生理参数和生理参数标准值，确定评估结果。可以理解的是，生理参数标准值可以与前述提到的第一生理参数参考值相同。
在一些实施例中，在确定生理参数标准值后，检测第一生理参数与生理参数标准值的差值是否在预设范围内，若差值在预设范围内，则评估结果为用户没有慢阻肺症状；若差值在预设范围外，则评估结果为用户具有慢阻肺症状。
在一些实施例中，用户是否具有慢阻肺症状的评估结果可以通过第一提示信息的形式展现给用户，第一提示信息可以为语音提示、显示界面文字提示等，本实施例并不对第一提示信息的展现形式做具体限定。
针对第一提示信息的具体内容，后文中有详细描述，为了避免重复，此处不再赘述。
本申请的实施例至少具有以下优点：由于用户在不同运动行为下的运动数据和生理参数均不相同，通过获取用户的第一运动数据，从而能够确定与第一运动数据对应的运动行为，再根据运动行为和第一生理参数，确定用户慢阻肺风险的评估结果，提高了慢阻肺风险评估方法的准确性。此外，此种评估方式能够在用户没有进行肺功能检查的情况下，也能基于用户日常的运动情况对慢阻肺进行及时预警，实现了对慢阻肺的早发现，使得慢阻肺能够早诊断、早治疗，有效地保障了用户的身体健康。
请参考图6，为本申请一实施例提供的慢阻肺风险评估方法的流程图，本实施例是对前述实施例的进一步改进，主要改进之处在于：本实施例中，会获取用户在第一预设周期内被评估具有慢阻肺症状的第一总次数，在第一总次数大于第一预设次数时，发送第一提示信息。通过此种方式，能够进一步提高评估用户是否具有慢阻肺的准确性，从而提高了慢阻肺风险评估方法的可靠性。
本实施例应用于用户佩戴的穿戴设备，如图6所示，包括以下步骤：
步骤S201：在第一预设周期内，实时获取第一运动数据和第一生理参数。
在一些实施例中，第一预设周期可以为一个星期，也可以为一个月，本实施例并不对第一预设周期的数值进行具体限定。
步骤S202：在每次获取第一运动数据后，均确定与第一运动数据对应的运动行为。
步骤S203：在每次确定运动行为后，均从多个预设模型中选择与运动行为匹配的目标模型，并将与运动行为对应的第一生理参数输入目标模型，在目标模型的评估结果为用户具有慢阻肺症状的第一总次数大于第一预设次数时，发送第一提示信息。
具体的说，穿戴设备对用户每一次的运动，均会评估用户是否具有慢阻肺症状。如用户在一个星期内的运动行为(如行走、爬楼梯)有20次，则穿戴设备会总计评估20次用户是否具有慢阻肺症状。
在一些实施例中，在第一总次数超过预设评估次数时，发送第一提示信息。具体的说，假设第一预设周期为一个星期，预设评估次数为15次，则当穿戴设备在一个星期内评估用户具有慢阻肺症状的次数超过15次时，发送第一提示信息。
在一些实施例中，在第一总次数和用户运动次数的比值大于预设比值时，发送第一提示信息。具体的说，假设第一预设周期为一个月，预设比值为0.8，穿戴设备获取用户在一个月内的运动次数为60次，评估用户具有慢阻肺症状的次数为30次，则第一总次数和用户运动次数的比值小于预设比值，不发送第一提示信息。
为了便于理解，下面结合图7对本实施例如何发送第一提示信息进行具体的说明：
请参见图7a和图7b，为第一提示信息在穿戴设备及终端设备上的效果图。
如图7a所示，为第一提示信息在穿戴设备上的效果图。第一预设周期为一个月，预设评估次数为15次。穿戴设备检测到用户在行走过程中出现呼吸率和心率升高过快的状态，即穿戴设备评估用户具有慢阻肺症状，在评估具有慢阻肺症状的第一总次数大 于15次后，穿戴设备的显示屏显示如图7a所示的界面内容。
如图7b所示，为第一提示信息在穿戴设备上的效果图。穿戴设备与用户的终端设备连接，终端设备包括但不限于手机、电脑、平板电脑等，穿戴设备需要发送第一提示信息时，将第一提示信息发送至终端设备，以使终端设备的显示界面显示第一提示信息。图7b所示的终端设备为手机，第一预设周期为一个月，预设评估次数为20次。穿戴设备检测到用户在平地行走6分钟出现呼吸率和心率升高过快的状态，即穿戴设备评估用户具有慢阻肺症状，在评估具有慢阻肺症状的第一总次数大于20次后，终端设备的显示屏显示如图7b所示的界面内容。
在一些实施例中，以前述例举的“行走”对应第一预设模型，“跑步”对应第二预设模型，“爬楼梯”对应第三预设模型为例，“静息状态”如夜间睡眠对应第四预设模型’获取用户每次运动状态时的第一生理参数，并根据不同的运动行为将获取的第一生理参数输入对应的预设模型。假设用户在一个月内总共运动60次，行走次数为40次，爬楼梯次数为3次，跑步次数为17次，则将40次行走行为对应的第一生理参数输入第一预设模型，将3次爬楼梯行为对应的第二生理参数输入第二预设模型，将17次跑步行为对应的第三生理参数输入第三预设模型，将30次夜间睡眠行为对应的第四生理参数输入第四预设模型，分别得到每次运动状态下慢阻肺症状风险得分，之后将第一预设模型的40次评估结果、第二预设模型的3次评估结果、第三预设模型的17次评估结果和第四预设模型的30次评估结果输入预设的综合评估模型中，根据每次行为得分和频次，综合得到更为准确的用户是否具有慢阻肺症状的结果。
与相关技术相比，本申请的实施例至少具有以下优点：由于用户在不同运动行为下的运动数据不同，通过获取用户的第一运动数据，在多个预设模型中选择与第一运动数据匹配的目标模型，能够对用户不同的运动行为采用不同的预设模型，提高了慢阻肺风险评估方法的准确性。由于目标模型是根据历史一运动数据、历史第一生理参数和第一生理参数参考值训练得到，能够确保模型输出结果的准确率，通过将第一生理参数输入目标模型中得到用户是否具有慢阻肺症状的评估结果，进一步提高了慢阻肺风险评估方法的准确性。此外，此种评估方式能够在用户没有进行肺功能检查的情况下，也能基于用户日常的运动情况对慢阻肺进行及时预警，实现了对慢阻肺的早发现，使得慢阻肺能够早诊断、早治疗，有效地保障了用户的身体健康。
请参考图8，为本申请一实施例提供的慢阻肺风险评估方法的流程图，本实施例是对前述实施例的进一步改进，主要改进之处在于：本实施例中，还会检测用户是否在吸烟，并在检测到用户多次吸烟时发送第二提示信息。由于慢阻肺的主要诱因是吸烟，通过此种方式，能够在用户多次吸烟后提醒用户，使得用户在接收到第二提示信息后能够减少吸烟频率，进一步保障了用户的身体健康。
本实施例应用于用户佩戴的穿戴设备，如图8所示，包括以下步骤：
步骤S301：获取用户的第一运动数据和第一生理参数。
步骤S302：确定与第一运动数据对应的运动行为。
步骤S303：根据运动行为和第一生理参数，确定评估结果。
本实施例的步骤S301至步骤S303与前述实施例的步骤S101至步骤S103类似，为了避免重复，此处不再赘述。
步骤S304：获取用户的第二运动数据和第二生理参数。
在一些实施例中，第二运动数据可以为用户穿戴设备的感测到的ACC值。
在一些实施例中，第二生理参数包括以下之一或其任意组合：心率、呼吸率。用户在进行吸气动作时，身体会具有如下特征：(1)心率变化：咳嗽后的短时间内人体的心率会显著上升，随后缓慢降至正常心率；(2)吸烟时，有深呼吸动作，呼吸率短时间有变化。
如图9所示，为穿戴设备为耳机时，用户吸烟时的ACC值变化图。具体的说，在用户吸烟时，用户会有吸气/呼吸动作，以及可能伴随低头、抬头动作，会引起ACC传感 器、陀螺仪传感器的变化。
如图10所示，为穿戴设备为手表或手环时，用户吸烟时的ACC值变化图。具体的说，当佩戴手表或手环的手吸烟时，会伴随着抬手动作，也会引起ACC等传感器的变化。
步骤S305：将第二运动数据和第二生理参数输入预设吸烟检测模型，得到用户是否正在吸烟的检测结果。
请参见图11，为吸烟动作捕捉算法框图。通过穿戴设备记录用户的ACC变化、心率变化、呼吸率变化以及心率变化。首先根据ACC、时间变化，确定用户是否处于吸烟状态；之后对该时间范围内的呼吸率、心率，提取相应的原始特征，包括但不限于时频域、近似熵、拟合系数等特征；然后结合用户ACC动作变化，对生理参数的原始特征库提取聚合特征，包括但不限于中位数、方差、变异系数等；最后将聚合特征集输入目标模型中进行机器/深度学习，再由预设吸烟检测模型输出用户是否正在吸烟的检测结果。
具体的说，本实施例中的第二预设模型与前述实施例中的第一预设模型可以为相同的模型，也可以为不同的模型，本实施例并不对此作具体限定。
S306：若在第二预设周期内，检测结果为用户正在吸烟的第二总次数大于第二预设次数，发送第二提示信息。
在一些实施例中，第二提示信息可以为语音提示、显示界面文字提示等，本实施例并不对第二提示信息的展现形式做具体限定。
为了便于理解，下面结合图12对本实施例如何发送第二提示信息的过程进行具体说明：
如图12所示，为第二提示信息在穿戴设备上的效果图。假设预设次数为7次，第二预设周期为12个小时。穿戴设备在12个小时内评估用户正在吸烟的次数超过7次时，发送第二提示信息。
与相关技术相比，本申请的实施例至少具有以下优点：由于用户在不同运动行为下的运动数据和生理参数均不相同，通过获取用户的第一运动数据，从而能够确定与第一运动数据对应的运动行为，再根据运动行为和第一生理参数，确定用户慢阻肺风险的评估结果，提高了慢阻肺风险评估方法的准确性。此外，此种评估方式能够在用户没有进行肺功能检查的情况下，也能基于用户日常的运动情况对慢阻肺进行及时预警，实现了对慢阻肺的早发现，使得慢阻肺能够早诊断、早治疗，有效地保障了用户的身体健康。
请参考图13，为本申请一实施例提供的慢阻肺风险评估方法的流程图，本实施例是对前述实施例的进一步改进，主要改进之处在于：本实施例中，还会结合用户的吸烟频率评估用户是否具有慢阻肺症状，能够进一步提高评估用户是否具有慢阻肺的准确性，从而提高了慢阻肺风险评估方法的可靠性。
本实施例应用于用户佩戴的穿戴设备，如图13所示，包括以下步骤：
步骤S401：获取用户的第二运动数据和第二生理参数。
步骤S402：将第二运动数据和第二生理参数输入预设吸烟检测模型，得到用户是否正在吸烟的检测结果。
步骤S403：若在第二预设周期内，检测结果为用户正在吸烟的第二总次数大于第二预设次数，发送第二提示信息。
步骤S404：获取用户的第一运动数据和第一生理参数，确定与第一运动数据对应的运动行为。
步骤S405：根据运动行为和第二总次数，在多个综合评估模型中选择目标综合评估模型。
步骤S406：将第一生理参数和第二总次数输入目标综合评估模型，确定评估结果。
请参见图14，为慢阻肺无感检测算法流程图。通过穿戴设备记录用户在运动过程中的心率变化、呼吸率变化以及血氧饱和度变化，并记录用户的吸烟次数。首先根据 ACC、时间变化，确定用户处于何种运动状态；之后对该时间范围内的呼吸率、HRV、心率等生理参数，提取相应的原始特征，包括但不限于时频域、近似熵、拟合系数等特征；然后对原始特征库提取聚合特征，包括但不限于中位数、方差、变异系数等；最后将聚合特征集以及记录的用户吸烟频次输入目标模型中进行机器/深度学习，再由目标模型输出用户是否具有慢阻肺症状的评估结果。可以理解的是，频繁吸烟的用户患慢阻肺的风险更大，通过将用户的吸烟次数作为目标综合评估模型深度学习的参数，能够进一步提高目标综合评估模型输出结果的准确性，从而提高了本实施例慢阻肺风险评估方法的可靠性。
具体的说，假设用户前一天内抽烟8次，大于预设次数，穿戴设备向用户发送第二提示信息。用户在第二天运动一次，如果根据用户运动行为和第一生理参数，则有可能评估用户不具有慢阻肺症状，但综合考虑用户前一天抽烟8次，根据用户运动行为、第一生理参数以及抽烟的总次数，评估用户具有慢阻肺症状。
具体的说，本实施例中的目标综合评估模型与前述实施例中的目标模型可以为相同的模型，也可以为不同的模型，本实施例并不对此作具体限定。
与相关技术相比，本申请的实施例至少具有以下优点：由于用户在不同运动行为下的运动数据不同，通过获取用户的第一运动数据，在多个预设模型中选择与第一运动数据匹配的目标模型，能够对用户不同的运动行为采用不同的预设模型，提高了慢阻肺风险评估方法的准确性。由于目标模型是根据历史一运动数据、历史第一生理参数和第一生理参数参考值训练得到，能够确保模型输出结果的准确率，通过将第一生理参数输入目标模型中得到用户是否具有慢阻肺症状的评估结果，进一步提高了慢阻肺风险评估方法的准确性。此外，此种评估方式能够在用户没有进行肺功能检查的情况下，也能基于用户日常的运动情况对慢阻肺进行及时预警，实现了对慢阻肺的早发现，使得慢阻肺能够早诊断、早治疗，有效地保障了用户的身体健康。
请参考图15，为本申请一实施例提供的慢阻肺风险评估方法的流程图，本实施例是对前述实施例的进一步改进，主要改进之处在于：本实施例中，在向用户发送第一提示信息后，还会根据用户的生理音进一步确认用户是否具有慢阻肺，从而进一步提高了慢阻肺风险评估方法的可靠性。
本实施例应用于用户佩戴的穿戴设备，如图15所示，包括以下步骤：
步骤S501：在第一预设周期内，实时获取第一运动数据和第一生理参数。
步骤S502：在每次获取第一运动数据后，均确定与第一运动数据对应的运动行为。
步骤S503：在每次确定运动行为后，均从多个预设模型中选择与运动行为匹配的目标模型，并将与运动行为对应的第一生理参数输入目标模型，在目标模型的评估结果为用户具有慢阻肺症状的第一总次数大于第一预设次数时，发送第一提示信息。
本实施例的步骤S501至步骤S503与前述实施例的步骤S201至步骤S203类似，为了避免重复，此次不再赘述。
步骤S504：获取用户的生理音。
在一些实施例中，如前述的图7a、图7b所示，第一提示信息的显示界面具有“开始测量”按键，用户点击“开始测量”按键后，穿戴设备开始获取用户的生理音。
具体的说，慢阻肺患者由于气道受阻导致呼吸困难，通过咳嗽音、吹气音等生理音可以进行用户的肺功能评估。如图16所示，为健康人和慢阻肺患者的咳嗽音差异图。咳嗽音：患者呼吸道粘液高分泌、纤毛功能障碍，引发咳嗽；和正常人相比，患者咳嗽时域上分布不均匀，每次咳嗽后拖有短时尾声；频域上慢阻肺患者音频能量集中在低频段。吹气音：患者气道狭窄，用力吹气时，吹气音持续时间短，强度衰减快。
步骤S505：对生理音进行特征提取，将特征提取的结果输入声音特征检测模型，得到用户的肺功能评估结果。
请参见图17，为本实施例的肺功能评估算法框图。首先对生理音进行信号预处理，包括语音增强、滤波以及预加重，以增强生理音信号，并滤除背景噪音及无效频段；之 后对预处理后的生理音进行原始特征提取，包括梅尔倒谱系数及差分、谱对比度、谱熵、线性预测系数、频谱质心、频谱带宽等时、频域特征，然后对原始特征库提取聚合特征，包括但不限于中位数、方差、变异系数等；最后将聚合特征集输入声音特征检测模型中进行机器/深度学习，得到用户的肺功能评估结果。
步骤S506：在肺功能评估结果不满足第二预设要求时，发送第三提示信息。
在一些实施例中，第三提示信息可以为语音提示、显示界面文字提示等，本实施例并不对第三提示信息的展现形式做具体限定。
如图18a和图18b所示，为第三提示信息在穿戴设备及终端设备上的效果图。图18a为第三提示信息在穿戴设备上的效果图；图18b为第三提示信息在终端设备上的效果图。肺功能评估结果以肺功能综合评分的形式展现，当肺功能综合评分低于预设分数时，表明肺功能评估结果不满足第二预设要求，发送图18a和图18b所示的第三提示信息。
与相关技术相比，本申请的实施例至少具有以下优点：由于用户在不同运动行为下的运动数据不同，通过获取用户的第一运动数据，在多个预设模型中选择与第一运动数据匹配的目标模型，能够对用户不同的运动行为采用不同的预设模型，提高了慢阻肺风险评估方法的准确性。由于目标模型是根据历史一运动数据、历史第一生理参数和第一生理参数参考值训练得到，能够确保模型输出结果的准确率，通过将第一生理参数输入目标模型中得到用户是否具有慢阻肺症状的评估结果，进一步提高了慢阻肺风险评估方法的准确性。此外，此种评估方式能够在用户没有进行肺功能检查的情况下，也能基于用户日常的运动情况对慢阻肺进行及时预警，实现了对慢阻肺的早发现，使得慢阻肺能够早诊断、早治疗，有效地保障了用户的身体健康。
请参考图19，为本申请一实施例提供的慢阻肺风险评估方法的流程图，本实施例是对前述实施例的进一步改进，主要改进之处在于：本实施例中，在发送第三提示信息之后，还会向用户发送用于表征慢阻肺发病可能性的问卷调查表，通过问卷调查表进一步确认用户是否具有慢阻肺，从而进一步提高了评估用户是否具有慢阻肺的准确性。
本实施例应用于用户佩戴的穿戴设备，具体流程如图19所示，包括以下步骤：
步骤S601：获取用户的第一运动数据和第一生理参数。
步骤S602：在每次获取第一运动数据后，均确定与第一运动数据对应的运动行为。
步骤S603：在每次确定运动行为后，均从多个预设模型中选择与运动行为匹配的目标模型，并将与运动行为对应的第一生理参数输入目标模型，在目标模型的评估结果为用户具有慢阻肺症状的第一总次数大于第一预设次数时，发送第一提示信息。
步骤S604：获取用户的生理音。
步骤S605：对生理音进行特征提取，将特征提取的结果输入声音特征检测模型，得到用户的肺功能评估结果。
步骤S606：在肺功能评估结果不满足第二预设要求时，发送第三提示信息。
本实施例的步骤S601至步骤S606与前述实施例的步骤S501至步骤S506类似，为了避免重复，此次不再赘述。
步骤S607：向用户发送用于表征慢阻肺发病可能性的问卷调查表。
在一些实施例中，如前述的图18a、图18b所示，第三提示信息的显示界面具有“开始筛查”按键，用户点击“开始筛查”按键后，穿戴设备向用户发送问卷调查表。
如图20a及图20b所示，为问卷调查表在终端设备上的效果图。穿戴设备与用户的终端设备连接，穿戴设备需要发送问卷调查表时，将问卷调查表发送至终端设备，以使终端设备的显示界面显示问卷调查表。图20a及图20b所示的终端设备为手机，问卷调查表涉及用户吸烟、日常生活中胸闷、气喘、粘液或痰、睡眠质量等问题。
步骤S608：获取问卷调查表的填写结果，在填写结果不满足第三预设要求时，发送第四提示信息。
在一些实施例中，第四提示信息可以为语音提示、显示界面文字提示等，本实施例 并不对第四提示信息的展现形式做具体限定。
如图21a和图21b所示，为第四提示信息在穿戴设备及终端设备上的效果图。图21a为第四提示信息在穿戴设备上的效果图；图21b为第四提示信息在终端设备上的效果图。第四提示信息会参照图2所示的呼吸困难症状评估等级标准显示用户的呼吸困难症状评估等级，以直观告知用户慢阻肺的严重程度。
与相关技术相比，本申请的实施例至少具有以下优点：由于用户在不同运动行为下的运动数据不同，通过获取用户的第一运动数据，在多个预设模型中选择与第一运动数据匹配的目标模型，能够对用户不同的运动行为采用不同的预设模型，提高了慢阻肺风险评估方法的准确性。由于目标模型是根据历史一运动数据、历史第一生理参数和第一生理参数参考值训练得到，能够确保模型输出结果的准确率，通过将第一生理参数输入目标模型中得到用户是否具有慢阻肺症状的评估结果，进一步提高了慢阻肺风险评估方法的准确性。此外，此种评估方式能够在用户没有进行肺功能检查的情况下，也能基于用户日常的运动情况对慢阻肺进行及时预警，实现了对慢阻肺的早发现，使得慢阻肺能够早诊断、早治疗，有效地保障了用户的身体健康。
请参考图22，为本申请实施例提供的慢阻肺风险评估装置的功能模块示意图。如图22所示，慢阻肺风险评估装置包括：
运动数据获取模块1，运动数据获取模块1用于获取用户的第一运动数据；生理参数获取模块2，生理参数获取模块2用于获取用户的第一生理参数；运动行为确定模块3，运动行为确定模块3用于确定与所述第一运动数据对应的运动行为，所述运动行为包括行走、跑步、爬楼梯以及静息中的至少一种；慢阻肺评估模块4，慢阻肺评估模块4用于根据所述运动行为和所述第一生理参数，确定评估结果。
请参考图23，为本申请实施例提供的电子设备1000的硬件结构示意图。如图23所示，电子设备1000可以包括处理器1001、存储器1002。存储器1002用于存储一个或多个计算机程序1003。一个或多个计算机程序1003被配置为被该处理器1001执行。该一个或多个计算机程序1003包括指令，上述指令可以用于实现在电子设备1000中执行上述的慢阻肺风险评估方法。
可以理解的是，本实施例示意的结构并不构成对电子设备1000的具体限定。在另一些实施例中，电子设备1000可以包括比图示更多或更少的部件，或者组合某些部件，或者拆分某些部件，或者不同的部件布置。
处理器1001可以包括一个或多个处理单元，例如：处理器1001可以包括应用处理器(application processor，AP)，调制解调器，图形处理器(graphics processing unit，GPU)，图像信号处理器(image signal processor，ISP)，控制器，视频编解码器，数字信号处理器(digital signal processor，DSP)，基带处理器，和/或神经网络处理器(neural-network processing unit，NPU)等。其中，不同的处理单元可以是独立的器件，也可以集成在一个或多个处理器中。
处理器1001还可以设置有存储器，用于存储指令和数据。在一些实施例中，处理器1001中的存储器为高速缓冲存储器。该存储器可以保存处理器1001刚用过或循环使用的指令或数据。如果处理器1001需要再次使用该指令或数据，可从该存储器中直接调用。避免了重复存取，减少了处理器1001的等待时间，因而提高了系统的效率。
在一些实施例中，处理器1001可以包括一个或多个接口。接口可以包括集成电路(inter-integrated circuit，I2C)接口，集成电路内置音频(inter-integrated circuit sound，I2S)接口，脉冲编码调制(pulse code modulation，PCM)接口，通用异步收发传输器(universal asynchronous receiver/transmitter，UART)接口，移动产业处理器接口(mobile industry processor interface，MIPI)，通用输入输出(general-purpose input/output，GPIO)接口，SIM接口，和/或USB接口等。
在一些实施例中，存储器1002可以包括高速随机存取存储器，还可以包括非易失性存储器，例如硬盘、内存、插接式硬盘，智能存储卡(Smart Media Card,SMC)，安 全数字(Secure Digital,SD)卡，闪存卡(Flash Card)、至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。
本实施例还提供一种计算机可读存储介质，该存储介质中存储有计算机指令，当该指令在电子设备上运行时，使得电子设备执行上述相关方法步骤实现上述实施例中的慢阻肺风险评估方法。
其中，本实施例提供的电子设备、计算机存储介质均用于执行上文所提供的对应的方法，因此，其所能达到的有益效果可参考上文所提供的对应的方法中的有益效果，此处不再赘述。
实际应用中，可以根据需要而将上述功能分配由不同的功能模块完成，即将装置的内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。
在本申请所提供的几个实施例中，所揭露的装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例是示意性的，例如，该模块或单元的划分，为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个装置，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
该作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是一个物理单元或多个物理单元，即可以位于一个地方，或者也可以分布到多个不同地方。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
该集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个可读取存储介质中。基于这样的理解，本申请实施例的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该软件产品存储在一个存储介质中，包括若干指令用以使得一个设备(可以是单片机，芯片等)或处理器(processor)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何在本申请揭露的技术范围内的变化或替换，都应涵盖在本申请的保护范围之内。

Claims (13)

  1. 一种慢阻肺风险评估方法，其特征在于，包括：
    获取用户的第一运动数据和第一生理参数；
    确定与所述第一运动数据对应的运动行为，所述运动行为包括行走、跑步、爬楼梯以及静息中的至少一种；
    根据所述运动行为和所述第一生理参数，确定评估结果。
  2. 如权利要求1所述的慢阻肺风险评估方法，其特征在于，所述根据所述运动行为和所述第一生理参数，确定评估结果，包括：
    在多个预设模型中选择与所述运动行为匹配的目标模型，所述目标模型是根据第一历史运动数据、与所述第一历史运动数据对应的历史第一生理参数和第一生理参数参考值训练得到，所述第一生理参数参考值为非慢阻肺患者与所述第一历史运动数据对应的生理参数值；
    将所述第一生理参数输入所述目标模型，确定所述评估结果。
  3. 如权利要求2所述的慢阻肺风险评估方法，其特征在于，所述获取用户的第一运动数据和第一生理参数，包括：
    在第一预设周期内，实时获取所述第一运动数据和所述第一生理参数；
    所述确定与所述第一运动数据对应的运动行为，包括：
    在每次获取所述第一运动数据后，均确定与所述第一运动数据对应的运动行为；
    所述在多个预设模型中选择与所述运动行为匹配的目标模型，将所述第一生理参数输入所述目标模型，确定所述评估结果，包括：
    在每次确定所述运动行为后，均从多个所述预设模型中选择与所述运动行为匹配的目标模型，并将与所述运动行为对应的第一生理参数输入所述目标模型；在所述目标模型的所述评估结果为所述用户具有慢阻肺症状的第一总次数大于第一预设次数时，发送第一提示信息。
  4. 如权利要求1所述的慢阻肺风险评估方法，其特征在于，所述根据所述运动行为和所述第一生理参数，确定评估结果，包括：
    确定与所述运动行为匹配的生理参数标准值，所述生理参数标准值为非慢阻肺患者与所述运动行为对应的生理参数值；
    根据所述第一生理参数和所述生理参数标准值，确定所述评估结果。
  5. 如权利要求1至4任一项所述的慢阻肺风险评估方法，其特征在于，所述方法还包括：
    获取所述用户的第二运动数据和第二生理参数；
    将所述第二运动数据和所述第二生理参数输入预设吸烟检测模型，得到所述用户是否正在吸烟的检测结果，其中，所述预设吸烟检测模型根据历史第二运动数据、与所述历史第二运动数据对应的历史第二生理参数和第二生理参数参考值训练得到，所述第二生理参数参考值为所述用户非吸烟状态下与所述第二运动数据对应的生理参数值；
    若在第二预设周期内，所述检测结果为用户正在吸烟的第二总次数大于第二预设次数，发送第二提示信息。
  6. 如权利要求5所述的慢阻肺风险评估方法，其特征在于，所述根据所述运动行为和所述第一生理参数，确定评估结果，包括：
    根据所述运动行为、所述第一生理参数和所述检测结果为所述用户正在吸烟的第二总次数，确定所述评估结果。
  7. 如权利要求6所述的慢阻肺风险评估方法，其特征在于，所述根据所述运动行为、所述第一生理参数和所述检测结果为所述用户正在吸烟的第二总次数，确定所述评估结果，包括：
    根据所述运动行为和所述第二总次数，在多个综合评估模型中选择目标综合评估模型；
    将所述第一生理参数和所述第二总次数输入所述目标综合评估模型，确定所述评估结果。
  8. 如权利要求3所述的慢阻肺风险评估方法，其特征在于，在所述发送第一提示信息之后，还包括：
    获取所述用户的生理音；
    对所述生理音进行特征提取，将所述特征提取的结果输入声音特征检测模型，得到所述用户的肺功能评估结果；
    在所述肺功能评估结果不满足第二预设要求时，发送第三提示信息。
  9. 如权利要求8所述的慢阻肺风险评估方法，其特征在于，在所述发送第三提示信息之后，还包括：
    向所述用户发送用于表征慢阻肺发病可能性的问卷调查表；
    获取所述问卷调查表的填写结果，在所述填写结果不满足第三预设要求时，发送第四提示信息。
  10. 如权利要求1所述的慢阻肺风险评估方法，其特征在于，所述第一生理参数包括以下之一或其任意组合：
    心率、血氧饱和度、呼吸率以及心率变异性。
  11. 一种慢阻肺风险评估装置，其特征在于，包括：
    运动数据获取模块，所述运动数据获取模块用于获取用户的第一运动数据；
    生理参数获取模块，所述生理参数获取模块用于获取所述用户的第一生理参数；
    运动行为确定模块，所述运动行为确定模块用于确定与所述第一运动数据对应的运动行为，所述运动行为包括行走、跑步、爬楼梯以及静息中的至少一种；
    慢阻肺评估模块，所述慢阻肺评估模块用于根据所述运动行为和所述第一生理参数，确定评估结果。
  12. 一种计算机可读存储介质，其特征在于，包括计算机指令，当所述计算机指令在电子设备上运行时，使得所述电子设备执行如权利要求1至权利要求10中任一项所述的慢阻肺风险评估方法。
  13. 一种电子设备，其特征在于，所述电子设备包括处理器和存储器，所述存储器用于存储指令，所述处理器用于调用所述存储器中的指令，使得所述电子设备执行权利要求1至权利要求10中任一项所述的慢阻肺风险评估方法。
PCT/CN2023/129131 2022-11-14 2023-11-01 一种慢阻肺风险评估方法、装置、电子设备及存储介质 WO2024104176A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211426393.3 2022-11-14
CN202211426393.3A CN118072948A (zh) 2022-11-14 2022-11-14 一种慢阻肺风险评估方法、装置、电子设备及存储介质

Publications (1)

Publication Number Publication Date
WO2024104176A1 true WO2024104176A1 (zh) 2024-05-23

Family

ID=91083778

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/129131 WO2024104176A1 (zh) 2022-11-14 2023-11-01 一种慢阻肺风险评估方法、装置、电子设备及存储介质

Country Status (2)

Country Link
CN (1) CN118072948A (zh)
WO (1) WO2024104176A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119296795A (zh) * 2024-12-12 2025-01-10 宁波大学 一种慢阻肺患者肺结节风险预测系统及方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013162975A (ja) * 2012-02-13 2013-08-22 Toyota Motor Corp 喫煙推定装置
US20160174903A1 (en) * 2014-12-23 2016-06-23 Michael Cutaia System and method for outpatient management of chronic disease
CN110875087A (zh) * 2018-09-03 2020-03-10 广州呼吸健康研究院 一种慢性肺疫病管理系统
US20210287806A1 (en) * 2020-03-13 2021-09-16 AIRx Health, Inc. Devices and methods of remotely monitoring and triaging patients
CN113838575A (zh) * 2020-06-24 2021-12-24 安徽华米健康科技有限公司 基于健康风险评估的预警方法、装置和终端设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013162975A (ja) * 2012-02-13 2013-08-22 Toyota Motor Corp 喫煙推定装置
US20160174903A1 (en) * 2014-12-23 2016-06-23 Michael Cutaia System and method for outpatient management of chronic disease
CN110875087A (zh) * 2018-09-03 2020-03-10 广州呼吸健康研究院 一种慢性肺疫病管理系统
US20210287806A1 (en) * 2020-03-13 2021-09-16 AIRx Health, Inc. Devices and methods of remotely monitoring and triaging patients
CN113838575A (zh) * 2020-06-24 2021-12-24 安徽华米健康科技有限公司 基于健康风险评估的预警方法、装置和终端设备

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119296795A (zh) * 2024-12-12 2025-01-10 宁波大学 一种慢阻肺患者肺结节风险预测系统及方法

Also Published As

Publication number Publication date
CN118072948A (zh) 2024-05-24

Similar Documents

Publication Publication Date Title
JP5878067B2 (ja) 呼吸事象検出システムおよび方法
CN109843183B (zh) 检测装置
JP5153770B2 (ja) いびき検知及び確認のためのシステム及び方法
CN104739412B (zh) 一种对睡眠呼吸暂停进行监测的方法和设备
WO2021208656A1 (zh) 睡眠风险预测方法、装置和终端设备
CN111938573A (zh) 睡眠生理系统
CN107595259B (zh) 一种报警方法、装置、穿戴设备及存储介质
CN109308443A (zh) 用于检测呼吸模式的方法和装置
WO2024104176A1 (zh) 一种慢阻肺风险评估方法、装置、电子设备及存储介质
JP2012523249A (ja) ラベル検証による明示的なラベリングを用いた呼吸フェーズ分類方法およびシステム
CN114730629A (zh) 基于语音的呼吸预测
KR20170079765A (ko) 매트리스에서의 수면 측정 및 분석 방법
CN118430751A (zh) 基于呼吸检测的疼痛缓解系统和实现方法、装置及介质
EP4017351A1 (en) A method and apparatus for processing asthma patient cough sound for application of appropriate therapy
WO2020220142A1 (en) System for measuring breath and for adapting breath exercises
Belsare et al. Computation of cigarette smoke exposure metrics from breathing
Ramos-Garcia et al. Recognizing cigarette smoke inhalations using hidden Markov models
US20210282736A1 (en) Respiration rate detection metholody for nebulizers
JP6676877B2 (ja) 食事時間推定方法、食事時間推定装置及び食事時間推定プログラム
CN114176512A (zh) 一种通过终端app检测阻塞性呼吸睡眠暂停的方法
CN114867538A (zh) 游戏装置以及计算机可读记录介质
US20250082297A1 (en) Respiration rate detection methodology for nebulizers
CN105030241B (zh) 一种移动终端的肺活量测试方法和测试装置
CN111481189A (zh) 睡眠评估方法及装置
US20230157637A1 (en) Intraoral electronic sensing for health monitoring

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23890612

Country of ref document: EP

Kind code of ref document: A1