KR102195189B1 - Photoplethysmography apparatus and arrhythmia detection system using the same - Google Patents

Abstract

Provided is an arrhythmia detection system using photoplethysmogram which can be simply and easily used by a test subject. The arrhythmia detection system using photoplethysmogram comprises: a pulse wave measuring device which is worn on a finger to measure a raw pulse wave through an optical sensor, removes noise related to motion from the low pulse wave, and extracts peak data from the pulse wave from which the noise is removed; and an electronic device which extracts a plurality of feature values related to an arrhythmia using the peak data received from the pulse wave measuring device, and detects an arrhythmia using an artificial intelligence classifier which receives the plurality of feature values as inputs.

Description

Optical volume pulse wave measuring apparatus and arrhythmia detection system using the same

Embodiments of the present invention relate to an optical volume pulse wave measuring device and an arrhythmia detection system using the same.

In the heart, there is an electrical transmission system that generates regular electricity spontaneously and transmits electrical signals to the entire heart. Irregular heartbeat caused by such systemic changes or dysfunction is called arrhythmia.

In general, in order to detect arrhythmia, electrocardiogram measurement is used to measure a change in electric potential caused by the activity of the myocardium on the body surface. For example, an electrocardiogram test performed in an electrocardiogram laboratory in a hospital, or a Holter test that measures an electrocardiogram during activities in daily life are used.

Regarding the contraction of the heart, the electric current, which is the driving force of the heartbeat, conducts from the sinus node to the atrioventricular node, and is transmitted to the Purikine fibers through the hiss bundle. As a result of this observation of electrical conduction, the ECG waveforms of P, Q, R, S, and T are observed. If an abnormality occurs in an electrical signal, an abnormality occurs in the heartbeat, and any heart disease can be measured using the ECG waveform.

However, since heart disease occurs intermittently, it is difficult to detect arrhythmia with an electrocardiogram performed by visiting a hospital. In addition, in the case of the Holter test, the electrocardiogram measuring device that the test subject must wear is cumbersome and causes inconvenience in daily life such as difficulty for the test subject to wash.

The present invention has been conceived to improve the above problems, and an object of the present invention is to provide an optical volume pulse wave measuring device that can be used simply and easily by a subject, and an arrhythmia detection system using the same.

However, these problems are exemplary, and the scope of the present invention is not limited thereby.

The arrhythmia detection system using the optical volume pulse wave according to an embodiment of the present invention is worn on a finger and measures a raw pulse wave through an optical sensor, and removes motion noise from the low pulse wave, and the noise is A pulse wave measuring device for extracting peak data from the removed pulse wave; And an electronic device for extracting a plurality of feature values related to an arrhythmia by using the peak data received from the pulse wave measuring device and detecting an arrhythmia using an artificial intelligence classifier that receives the plurality of feature values as inputs. I can.

According to an embodiment, the system receives information about the detection of arrhythmia from the electronic device, and includes identification information of the electronic device, the type of the detected arrhythmia, and peak data during the detection of the arrhythmia. It may further include a server for interlocking and storing.

According to an embodiment, the optical sensor includes a first light source and a second light source having a center wavelength different from that of the first light source, and the pulse wave measuring device includes a first low pulse wave and the first low pulse wave for the first light source. 2 It is possible to measure the second low pulse wave of the light source.

According to an embodiment, the pulse wave measuring device measures an ambient light signal while the light source of the optical sensor is turned off, measures a motion signal of the pulse wave measuring device using an acceleration sensor, and measures the motion signal and the ambient light signal. The noise can be removed by using.

According to an embodiment, the plurality of feature values are the average number of pulsations during unit time, standard deviation of pulsation during unit time, average of pulsation-inter-time interval for unit time, and the pulsation-inter-time for unit time The standard deviation of the interval, the root mean square (rms) of the difference between the adjacent pulsation-inter-time intervals during the unit time, the number of times that the difference between the adjacent pulsation-inter-time intervals during unit time satisfies a specified time or more, unit time The ratio in which the difference between the adjacent pulsation-inter-time intervals during the period satisfies the specified time or more, the standard deviation of the difference between the adjacent pulsation-inter-time intervals during unit time, the size of the low-frequency component during unit time, and high frequency during unit time It may be selected from the size of the component, the ratio of the size of the high frequency component to the size of the low frequency component during a unit time, and Shannon entropy standardized during the unit time.

Other aspects, features, and advantages other than those described above will become apparent from the following drawings, claims, and detailed description of the invention.

According to an embodiment of the present invention made as described above, it is possible to conveniently and easily detect arrhythmia by solving the inconvenience of the existing Holter test equipment.

Specifically, through the arrhythmia detection system according to an embodiment of the present invention, it is possible to detect arrhythmia in real time by monitoring a pulse wave in daily life.

In addition, through the arrhythmia detection system according to an embodiment of the present invention, when an arrhythmia occurs, a notification about the occurrence of an arrhythmia may be immediately provided to a user.

Of course, the scope of the present invention is not limited by these effects.

1 shows an example of a functional configuration of an arrhythmia detection system 100 using a volumetric pulse wave according to an embodiment of the present invention.
2 is a flowchart of an arrhythmia detection system 100 using a volumetric pulse wave according to an embodiment of the present invention.
3 is an example of a signal flow between the pulse wave measuring device 10, the electronic device 20, and the server 30 according to an embodiment of the present invention.
4 shows an example of a noise removal operation according to an embodiment of the present invention.

Since the present invention can apply various transformations and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail in the detailed description. Effects and features of the present invention, and a method of achieving them will be apparent with reference to the embodiments described later in detail together with the drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various forms.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, and when describing with reference to the drawings, the same or corresponding constituent elements are assigned the same reference numerals, and redundant descriptions thereof will be omitted. .

In the following embodiments, terms such as first and second are not used in a limiting meaning, but are used for the purpose of distinguishing one component from another component.

In the following examples, the singular expression includes the plural expression unless the context clearly indicates otherwise.

In the following embodiments, terms such as include or have means that the features or elements described in the specification are present, and do not preclude the possibility of adding one or more other features or elements in advance.

In the following embodiments, when it is assumed that a component, a section, a block, a module, etc. are connected, not only the components, sections, blocks, and modules are directly connected, but also other components between components, sections, blocks, and modules. , Sub, blocks, modules are interposed and indirectly connected.

1 shows an example of a functional configuration of an arrhythmia detection system 100 using a volumetric pulse wave according to an embodiment of the present invention.

Referring to FIG. 1, the arrhythmia detection system 100 may include a pulse wave measuring device 10, an electronic device 20 and/or a server 30. However, the present invention is not limited thereto, and the system 100 may further include other components or some components may be omitted. Some components of the system 100 may be separated into a plurality of devices, or may be merged into a single device.

The pulse wave measuring device 10 is a wearable device, and may be, for example, in the form of a ring that can be worn on a finger. The pulse wave measuring device 10 may measure a change in blood flow of a finger artery, that is, a pulse wave. The pulse wave measuring apparatus 10 may transmit data on the pulse wave to the electronic device 20.

The electronic device 20 may detect arrhythmia by using data received from the pulse wave measuring device 10. The electronic device 20 may be a portable communication device or a user terminal. The electronic device 20 may include, for example, a smart phone, a tablet PC, a portable multimedia device, a portable medical device, or a wearable device (eg, a smart watch).

The server 30 may store and manage information on arrhythmia for each user.

The pulse wave measurement device 10 may include a communication module 11, a processor 12, and a sensor module 15, and the sensor module 15 includes an optical sensor 16 and an acceleration sensor 17. I can. However, the present invention is not limited thereto, and other components may be added to the pulse wave measuring apparatus 10 or some components may be omitted.

The communication module 11 of the pulse wave measuring apparatus 10 may support establishing a wireless communication channel between the pulse wave measuring apparatus 10 and the electronic device 20 and performing communication through the established communication channel.

The communication module 11 of the pulse wave measuring apparatus 10 is a wireless communication module, and may include, for example, a short-range wireless communication module. The communication module 11 is the electronic device 20 (for example, through a short-range communication network such as Bluetooth (BT), Bluetooth low energy (BLE), NFC (near field communication) network, WiFi-direct), for example. : Can communicate with the communication module (21). The communication module 11 may be implemented as a chip.

The sensor module 15 of the pulse wave measuring device 10 may include an optical sensor 16 and an acceleration sensor 17.

The optical sensor 16 irradiates light through the light emitting unit and senses reflected light or transmitted light through the light receiving unit, thereby measuring a change in blood flow of a finger artery, that is, a pulse wave. According to an embodiment, the optical sensor 16 may include a first light source and a second light source as a light emitting unit, and may include a photodiode as a light receiving unit. The first light source and the second light source may be light sources having different central wavelengths. According to an embodiment, the first light source may be a red light source, and the second light source may be an infrared light source.

According to an embodiment, the optical sensor 16 may measure a first raw pulse wave for the first light source, transmitted through a first light source (eg, a red light source) and received through a photodiode, A second low pulse wave of the second light source transmitted through the second light source (eg, an infrared light source) and received through the photodiode may be measured.

In addition, according to an embodiment, the optical sensor 16 may measure an ambient light signal through a photodiode in a state in which light sources (eg, the first light source and the second light source) are turned off. The ambient light signal may be used to remove noise from a raw pulse wave (eg, a first low pulse wave and a second low pulse wave).

According to an embodiment, the light source of the optical sensor 16 may be driven to alternately have an on state and an off state. The on/off driving of the light source may be repeated at a predetermined period, and the predetermined period may be several hundred us to several tens of ms, but is not limited thereto. The sensor module 15 (or processor 12) may collect or extract a signal received in the ON state as a low pulse wave, and collect or extract a signal measured in the off state as an ambient light signal.

According to an embodiment, the optical sensor 16 may be driven to repeat a first state in which only the first light source is turned on, a second state in which only the second light source is turned on, and a third state in which both light sources are turned off. The first, second, and third states may be repeated in a predetermined period (eg, hundreds of us to tens of ms).

The sensor module 15 (or processor 12) collects or extracts a signal received in a first state in which only the first light source is turned on, as a first low pulse wave, and receives a signal received in a second state in which only the second light source is turned on. The signal may be collected or extracted as a second low pulse wave, and a signal measured in a third state in which both light sources are turned off may be collected or extracted as an ambient light signal.

The acceleration sensor 17 may measure a motion signal according to a movement of a finger or a subject wearing the pulse wave measuring device 10.

The motion signal may represent, for example, displacement in the x, y, and z axis directions. The motion signal may be used to remove noise from a raw pulse wave (eg, a first low pulse wave and a second low pulse wave).

The sensor module 15 may generate, for example, an analog signal (eg, an electrical signal) or a data value (eg, a digital signal converted from an electrical signal) corresponding to the above-described sensing.

The processor 12 of the pulse wave measuring apparatus 10 may operate based on low power. For example, the processor 12 may be designed to be specialized for a designated function. For example, the processor 12 may perform predetermined data processing or operation.

The processor 12 may control functions related to, for example, components of the pulse wave measuring device 10 (eg, the communication module 11 and the sensor module 15). According to an embodiment, the processor 12 may remove noise from a raw pulse wave (ie, a data value or a digital signal related to the low pulse wave) measured through the optical sensor 16. The noise may be noise due to the movement of a subject or a finger and/or ambient light.

For example, the processor 12 may generate a reference value of noise using a motion signal and an ambient light signal, and may remove noise from the low pulse wave using the reference value.

The processor 12 may extract peak data from the pulse wave from which noise has been removed. Here, the peak may mean a pulsating component or an R peak. The peak data may be, for example, data indicating a time point of occurrence of a peak or data indicating a time interval between peaks.

According to an embodiment, the processor 12 may extract data representing a time interval between peaks as peak data extracted from a pulse wave and transmit it to the electronic device 20 through the communication module 11.

The electronic device 20 may include a communication module 21, a processor 22, a display device 23, and a memory 25. The memory 25 may store a program 26 that extracts a plurality of feature values related to an arrhythmia by using peak data and detects an arrhythmia from the plurality of feature values.

However, the present invention is not limited thereto, and of course, other components (eg, input devices) may be added to the electronic device 20.

The communication module 21 of the electronic device 20 may support establishing a wireless communication channel between the pulse wave measuring apparatus 10 and the electronic device 20 and performing communication through the established communication channel.

The communication module 21 of the electronic device 20 is a wireless communication module, and may include, for example, a short-range wireless communication module. The communication module 21 is a pulse wave measuring device 10 through a short-range communication network such as, for example, a Bluetooth (BT), a Bluetooth low energy (BLE), a near field communication (NFC) network, and a WiFi-direct. Example: Can communicate with the communication module 11).

The communication module 21 of the electronic device 20 establishes a communication link with the pulse wave measuring device 10, and receives peak data (eg, data indicating a time interval between peaks in a pulse wave signal) through the communication link. I can. The communication link may be based on at least one of Bluetooth, Bluetooth low power (BLE), and WiFi-direct.

According to an embodiment, the communication module 21 of the electronic device 20 may further include a long-distance wireless communication module to communicate with the server 30 through a cellular network or a long-distance communication network such as the Internet.

The communication module 21 may be implemented with one or more chips.

The processor 22 may execute, for example, software or a program 26 to perform various data processing or operations. The data processing or operation may include data processing or operation for extracting a plurality of feature values related to an arrhythmia from peak data of a pulse wave and detecting an arrhythmia using the plurality of feature values. The processor 22 may load instructions or data into the memory 25 (eg, volatile memory), process the stored commands or data, and store result data in the memory 25 (eg, nonvolatile memory).

A detailed description of the operation of the processor 22 extracting the plurality of feature values from peak data of the pulse wave will be described later in the description of FIG. 3.

The memory 25 may store various types of data used by at least one component of the electronic device 20 (eg, the processor 22). The data may include, for example, software (eg, the program 26) and input data or output data for commands related thereto.

According to an embodiment, the memory 25 may store a program 26 that extracts a plurality of feature values related to an arrhythmia from peak data of a pulse wave and detects an arrhythmia using the plurality of feature values. Program 26 may include one or more programs.

According to an embodiment, the program 26 is an algorithm for extracting the plurality of feature values from the peak data of the pulse wave, and an artificial intelligence algorithm that outputs the presence of arrhythmia or the type of the detected arrhythmia by inputting the plurality of feature values. It may include. The artificial intelligence algorithm may output whether or not atrial fibrillation, cardiac contractions, bradycardia, and tachycardia have occurred, for example.

The display device 23 may visually provide information to the outside of the electronic device 20 (eg, a user or a test subject). The display device 23 may include, for example, a display. For example, when the processor 22 detects an arrhythmia through execution of the program 26, the display device 23 may display information indicating that the arrhythmia is detected. The display device 23 may display a message or a notification indicating that an arrhythmia is detected.

For example, the display device 23 may display whether at least one of atrial fibrillation, cardiac contractions, bradycardia, and tachycardia occurs. For example, the display device 23 may display information on a time point at which an arrhythmia is detected, or information on a history of detection of an arrhythmia.

Meanwhile, when the arrhythmia is detected, the processor 22 may transmit information on the arrhythmia detection to the server 30 through the communication module 21.

The server 30 may store and manage information on arrhythmia for each user.

When the server 30 receives information about arrhythmia detection from the electronic device 20, the server 30 may store information on the type of arrhythmia and the timing of the arrhythmia detection in the database together with the identifier information of the electronic device 20. The server 30 may interlock and store peak data while arrhythmia is detected together with the identifier information of the electronic device 20. For example, the server 30 may store peak data for a predetermined time before and after including the time when the arrhythmia is detected. The peak data is pulsation component data, and may be, for example, data indicating a time point of occurrence of a peak or data indicating a time interval between peaks.

By using the information on the arrhythmia for each user stored in the server 30, the medical staff can monitor the trend of the occurrence of arrhythmia in the patient.

2 is a flowchart of an arrhythmia detection system 100 using a volumetric pulse wave according to an embodiment of the present invention.

Referring to FIG. 2, in S101, the pulse wave measuring apparatus 10 may measure a raw pulse wave. According to an embodiment, the pulse wave measuring apparatus 10 includes a first state in which only a first light source (eg, a red light source) is turned on, a second state in which only a second light source (eg, an infrared light source) is turned on, and a second state in which both light sources are turned off. The optical sensor 16 can be driven to repeat the three states. The first, second, and third states may be repeated in a predetermined period (eg, hundreds of us to tens of ms).

The pulse wave measuring apparatus 10 extracts the signal received in the first state as a first low pulse wave, extracts the signal received in the second state as a second low pulse wave, and uses the measured signal in the third state as an ambient light signal. By extracting to, the first low pulse wave signal, the second low pulse wave signal, and the ambient light signal can be measured.

In S102, the pulse wave measuring apparatus 10 (eg, the processor 12) may remove noise related to motion from the measured low pulse wave.

According to an embodiment, the pulse wave measuring device 10 may measure the motion signal of the pulse wave measuring device 10 through the acceleration sensor 17 in parallel while measuring the low pulse wave and the ambient light signal. .

The pulse wave measuring apparatus 10 may generate a reference value of a motion signal by standardizing the motion signal and the ambient light signal, and output a pulse wave from which the motion signal is removed from the low pulse wave by using the reference value.

According to an embodiment, a first pulse wave from which a motion signal is removed from the first low pulse wave (eg, a red light source pulse wave) is calculated, and a second pulse wave from which the motion signal is removed from the second low pulse wave (eg, an infrared light source pulse wave) Can be calculated.

In S103, the pulse wave measuring apparatus 10 (eg, the processor 12) may extract peak data from a pulse wave (eg, a first pulse wave and a second pulse wave) from which noise is removed.

The peak data may be, for example, data indicating a time point of occurrence of a pulsating component (or R peak), or data indicating a time interval between pulsating components. For example, the peak data may be data obtained by continuously and sequentially recording a time from an arbitrary first peak to a next second peak and a time from the second peak to a next third peak.

The pulse wave measuring device 10 may transmit the extracted peak data to the electronic device 20 through the communication module 11.

In S201, the electronic device 20 (eg, the processor 22) may extract a plurality of feature values related to an arrhythmia by using the peak data received from the pulse wave measuring device 10.

The plurality of feature values related to the arrhythmia may include feature values related to the pulse displacement degree. According to an embodiment, the plurality of feature values may include 12 feature values. Hereinafter, the pulsation may represent a peak.

According to an embodiment, the plurality of feature values are the average number of pulsations (ie, peaks) during a unit time (first feature value), a standard deviation of pulsations during unit time (second feature values), and pulsation during unit time- The mean (third characteristic value) of the inter-time interval (TI), the standard deviation of the pulsation-inter-time interval (TI) during the unit time (the fourth characteristic value), the adjacent pulsation-inter- The root mean square (rms) of the difference (△TI) between time intervals (TI) (the fifth feature value), and the difference (△TI) between the adjacent pulsation-inter-time intervals (TI) for a unit time is not less than a specified time. The number of times satisfied (the sixth feature value), the ratio (△TI) between the adjacent pulsation-inter-time interval (TI) during a unit time satisfies the specified time or more (the seventh feature value), adjacent to the unit time The standard deviation (the eighth feature value) of the difference (△TI) between the pulsation-inter-time intervals (TI), the size of the low-frequency component during the unit time (the ninth feature value), the size of the high-frequency component during the unit time (the tenth Feature value), a ratio of a size of a high frequency component to a size of the low frequency component during a unit time (11th feature value), and a Shannon entropy (12th feature value) standardized during a unit time. The designated time may be, for example, 50 ms. The unit time can be arbitrarily set.

For example, in the third and fourth feature values, the pulsation-inter-time interval TI is a time interval TI1 between the first pulsation and the second pulsation when the first, second, and third pulsations occur sequentially. ), and a time interval (TI2) between the second pulsation and the third pulsation.

In addition, in the 5th, 6th, 7, 8th feature values, the difference (ΔTI) between adjacent pulsations-inter-time intervals (TI) is, when the first, second, and third pulsations occur sequentially, When the time interval between the pulsations is TI1 and the time interval between the second pulsation and the third pulsation is TI2, it is a value expressed as ΔTI1 = |TI1-TI2|.

Therefore, the third feature value is the average of TI during the unit time, the fourth feature value is the standard deviation of TI during the unit time, the fifth feature value is the root mean square (rms) of ΔTI during the unit time, and the sixth feature The value is the number of times that ΔTI satisfies the specified time (eg, 50 ms) or more during the unit time, and the seventh characteristic value is the ratio in which ΔTI satisfies the specified time (eg 50 ms) or more during the unit time, and the eighth The feature value may be the standard deviation of ΔTI during unit time.

In S203, the electronic device 20 (eg, the processor 22) may detect an arrhythmia by inputting a plurality of feature values to an artificial intelligence classifier (eg, the program 26). For example, the electronic device 20 may input all of the above-described 12 feature values or input values selected from among 12 feature values to the artificial intelligence classifier.

For example, the artificial intelligence classifier may input 12 feature values and output the arrhythmia status or the type of arrhythmia. For example, when an arrhythmia is detected, the artificial intelligence classifier may classify or identify the type of arrhythmia as one of atrial fibrillation, cardiac atrophy, bradycardia, and tachycardia using the 12 feature values.

According to an embodiment of the present invention, S101, S102, and S103 may be performed by the pulse wave measuring apparatus 10, and S201 and S202 may be performed by the electronic device 20.

According to an embodiment of the present invention, it can be performed on a low power basis by transmitting/receiving and using only peak data extracted from a pulse wave, for example, data representing a time interval (TI) between pulses, and the pulse displacement calculated from the peak data Various types of arrhythmia may be detected using only a plurality of feature values related to the degree.

3 is an example of a signal flow between the pulse wave measuring device 10, the electronic device 20, and the server 30 according to an embodiment of the present invention.

Among the operations shown in FIG. 3, those corresponding to the operation of FIG. 2 used the same identification number.

Referring to FIG. 3, in S100, the pulse wave measuring device 10 and the electronic device 20 may establish a communication link. The communication link may be a short-range wireless communication link, and may be based on at least one of Bluetooth, Bluetooth Low Power (BLE), and WiFi-direct.

In S101, the pulse wave measuring device 10 may measure a raw pulse wave. The low pulse wave may represent a motion signal or a pulse wave mixed with noise. According to an embodiment, the pulse wave measuring apparatus 10 includes a first low pulse wave that is a reflected light (or transmitted light) signal for a first light source (eg, a red light source) and a reflected light (for example, an infrared light source). Alternatively, a second low pulse wave, which is a transmitted light) signal, may be obtained.

In S102, the pulse wave measuring device 10 can remove noise. 4 shows an example of a noise removal operation according to an embodiment of the present invention.

Referring to FIG. 4, in measuring the low pulse wave (S101), the pulse wave measuring apparatus 10 repeats on/off of the light source, and measures a signal sensed while the light source is turned on as a low pulse wave, while the light source is turned off. The sensed signal may be measured as an ambient light signal (S301). According to an embodiment, the pulse wave measuring apparatus 10 measures a signal sensed while turning on the first light source as a first low pulse wave, measures a signal sensed while turning on the second light source as a second low pulse wave, The signal sensed while all the light sources are turned off can be measured as an ambient light signal.

On the other hand, the pulse wave measuring device 10, while measuring the low pulse wave and the ambient light signal (S101, S301) in parallel or independently, by using the acceleration sensor 17, the motion signal of the pulse wave measuring device 10 Can measure (S302)

Thereafter, in S102, the pulse wave measuring apparatus 10 may remove noise related to motion from the low pulse wave (eg, the first low pulse wave and the second low pulse wave). Noise removal may be performed by the processor 12, for example, through an adaptive noise canceling filter 300.

In S303, the processor 12 of the pulse wave measuring device 10 may standardize the ambient light signal and the motion signal, respectively. Standardization can include normalization, for example.

In S304, the processor 12 (eg, the adaptive noise reduction filter 300) may remove noise from the low pulse wave by using a standardized motion signal and a standardized ambient light signal. According to an embodiment, the processor 12 may generate a reference value for motion by using an average of the standardized motion signal and the standardized ambient light signal. According to an embodiment, the processor 12 may calculate a pulse wave from which noise related to motion has been removed by removing the reference value from the low pulse wave (S305).

According to an embodiment, the processor 12 may calculate a first pulse wave from which motion noise is removed from the first low pulse wave, and may calculate a second pulse wave from which motion noise is removed from the second low pulse wave. .

In S103, the pulse wave measuring apparatus 10 may extract peak data from a pulse wave (eg, a first pulse wave and a second pulse wave). The peak data may continuously and sequentially represent a time interval (TI) between pulsations (ie, peaks).

Referring back to FIG. 3, in S104, the pulse wave measuring apparatus 10 may transmit peak data to the electronic device 20 through a communication link.

According to an embodiment of the present invention, the pulse wave measuring apparatus 10 may continuously repeatedly perform S101 to S103, and transmit peak data S104, which is updated each time the repetition, to the electronic device 20 in real time. have.

The electronic device 20 may continuously receive peak data updated in real time (ie, data indicating a pulsating interval).

In S201, the electronic device 20 may extract a plurality of feature values for arrhythmia by using the received peak data. The plurality of feature values may include the first to twelfth feature values described above.

In S202, the electronic device 20 may detect in real time whether an arrhythmia has occurred using an artificial intelligence classifier that inputs a plurality of feature values as inputs. According to an embodiment, when an arrhythmia occurs, the artificial intelligence classifier may classify or identify the type of arrhythmia as one of atrial fibrillation, cardiac atrophy, bradycardia, and tachycardia.

In S203, the electronic device 20 determines whether or not an arrhythmia is detected, and when the arrhythmia is detected, the electronic device 20 may transmit data related to the arrhythmia detection to the server 30 in S204. The data on the detection of arrhythmia may include, for example, a type of arrhythmia, a time point at which the arrhythmia is detected, and peak data while an arrhythmia is detected. When an arrhythmia is detected by the electronic device 20, the server 30 may receive data related to arrhythmia detection.

In S205, the server 30 interlocks with the identifier information of the electronic device 20, for example, the type of arrhythmia, the timing of the arrhythmia detection, and the peak data while the arrhythmia is detected, and stores it in the database based on the reception I can.

In addition, in S206, when the arrhythmia is detected, the electronic device 20 may provide a notification regarding the arrhythmia. For example, the electronic device 20 may display a message or a notification indicating the occurrence of an arrhythmia through the display device 23. According to an embodiment, the electronic device 20 may display the type of the generated arrhythmia through the display device 23, for example, to indicate that one of atrial fibrillation, cardiac contractility, bradycardia, and tachycardia is detected. I can.

Meanwhile, in S203, the electronic device 20 determines whether or not an arrhythmia is detected, and when the arrhythmia is not detected, operations of S204, S205, and S206 may be omitted.

The electronic device may continuously repeatedly perform the operations of S201 to S203, and may detect whether an arrhythmia occurs in real time using feature values that are updated each time it is repeatedly performed.

Although the present invention has been described with reference to an embodiment shown in the drawings, this is only exemplary, and those of ordinary skill in the art will understand that various modifications and variations of the embodiments are possible therefrom. Therefore, the true technical protection scope of the present invention should be determined by the technical spirit of the appended claims.

Claims (5)

An optical sensor worn on a finger and measuring a raw pulse wave while the light source is on and an ambient light signal while the light source is off, and an acceleration sensor that measures a motion signal while measuring the raw pulse wave and the ambient light signal And, by standardizing the ambient light signal and the motion signal, respectively, generating a reference value for motion using the standardized motion signal and the standardized ambient light signal, and removing the reference value from the low pulse wave, noise related to motion is reduced. A pulse wave measuring apparatus including a processor for calculating the removed pulse wave and extracting peak data from the pulse wave from which the noise has been removed; And
And an electronic device that extracts a plurality of feature values related to an arrhythmia using the peak data received from the pulse wave measuring device, and detects the arrhythmia using an artificial intelligence classifier that receives the plurality of feature values as inputs, and
The plurality of feature values are the root mean square (rms) of the difference (ΔTI) between adjacent pulsation-inter-time intervals (TI) during a unit time, and the pulsation-inter-time interval ( TI) including the number and ratio of the number and ratio of the difference (ΔTI) satisfying the specified time or more, and the standard deviation of the difference between adjacent pulsation-inter-time intervals during a unit time
Arrhythmia detection system using optical volume pulse waves. The method of claim 1,
A server for receiving information on the detection of arrhythmia from the electronic device, and storing the identifier information of the electronic device, the type of the detected arrhythmia, and peak data during the detection of the arrhythmia in conjunction with each other; ,
Arrhythmia detection system using optical volume pulse waves. The method of claim 1,
The optical sensor includes a first light source and a second light source having a center wavelength different from that of the first light source,
The pulse wave measuring device measures a first low pulse wave for the first light source and a second low pulse wave for the second light source,
Arrhythmia detection system using optical volume pulse waves. The method of claim 1,
The pulse wave measuring device measures an ambient light signal while the light source of the optical sensor is off, measures a motion signal of the pulse wave measuring device using an acceleration sensor, and measures the noise using the motion signal and the ambient light signal. Removed,
Arrhythmia detection system using optical volume pulse waves. The method of claim 1,
The plurality of characteristic values are the average number of pulsations during unit time, standard deviation of pulsation during unit time, average of pulsation-inter-time interval during unit time, standard deviation of the pulsation-inter-time interval during unit time, unit Further comprising at least one of the size of the low frequency component during time, the size of the high frequency component during unit time, the ratio of the size of the high frequency component to the size of the low frequency component during unit time, and Shannon entropy standardized during unit time,
Arrhythmia detection system using optical volume pulse waves.

Images