Biological data monitoring platform using a biological signal sensing ring

Abstract

A biometric data monitoring platform using a biometric signal sensing ring is provided, the platform includes a server, the server also includes a signal quality classification system including a first signal quality classification component configured to classify a signal quality of a first wavelength PPG signal into good and bad, a biometric data calculation system including an atrial fibrillation determination component configured to determine whether atrial fibrillation occurs from the first wavelength PPG signal using a deep learning model, and a biometric indicator calculation system including an atrial fibrillation indicator calculation component configured to calculate an atrial fibrillation indicator from the first signal quality classification result generated by the first signal quality classification component and the atrial fibrillation determination result generated by the atrial fibrillation determination component.

Description

Technical Field

[0001] The present invention relates to a biological data monitoring platform, and more specifically, to a biological data monitoring platform using a biological signal sensing ring.

Background Art

[0002] The continuous monitoring of biological signals and biological data obtained by processing biological signals is useful for disease prevention, early diagnosis, and management. In order to develop such a biological data monitoring platform, a biological signal sensing device that can measure biological signals with high reliability, simply and continuously in daily life is required.

Summary of the Invention

Problems to be Solved by the Invention

[0003] The problem to be solved by the present disclosure is to provide a biological data monitoring platform using a biological signal sensing ring.

Means for Solving the Problems

[0004] To solve the above problems, a biological data monitoring platform using a biological signal sensing ring according to an embodiment of the present disclosure includes a server. The server includes a signal quality classification system including a first signal quality classification component configured to classify the signal quality of a first wavelength PPG (photoplethysmography) signal as good or bad, a biological data calculation system including an atrial fibrillation determination component configured to determine the occurrence of atrial fibrillation from the first wavelength PPG signal using a deep learning model, and an atrial fibrillation index calculation component configured to calculate an atrial fibrillation index from the first signal quality classification result generated by the first signal quality classification component and the atrial fibrillation determination result generated by the atrial fibrillation determination component. The atrial fibrillation index can be defined by the ratio of the time when the first signal quality classification component classifies the quality of the first wavelength PPG signal as good and the atrial fibrillation determination component determines that atrial fibrillation has occurred to the time when the first signal quality classification component classifies the quality of the first wavelength PPG signal as good.

[0005] In some embodiments, the signal quality classification system further includes a second signal quality classification component configured to classify the signal quality of a second wavelength PPG signal as good or bad. The biological data calculation system further includes a signal feature extraction component configured to extract PPG features from the second wavelength PPG signal using a first deep learning model, a user feature extraction component configured to extract user features from the test PPG signal measured using the biological signal sensing ring, the systolic test blood pressure and diastolic test blood pressure measured simultaneously with the test PPG signal using a conventional sphygmomanometer, and user information using a second deep learning model, and a blood pressure estimation component configured to estimate the systolic blood pressure and diastolic blood pressure from the PPG features and the user features using a third deep learning model.

[0006] In one embodiment, the biological parameter calculation system further includes a blood pressure index calculation component configured to calculate a blood pressure index from the second signal quality classification result generated by the second signal quality classification component and the blood pressure estimated by the blood pressure estimation component. The blood pressure index may be defined by a ratio of the time when the systolic blood pressure is out of the first normal range or the diastolic blood pressure is out of the second normal range, and the time when the second signal quality classification component classifies the quality of the second wavelength PPG signal as good quality, where the second signal quality classification component classifies the quality of the second wavelength PPG signal as good quality.

[0007] In one embodiment, the signal quality classification system further includes a third signal quality classification component configured to classify the quality of the second wavelength PPG signal and the third wavelength PPG signal as good or bad. The biological data calculation system further includes an oxygen saturation estimation component configured to estimate oxygen saturation from the second wavelength PPG signal and the third wavelength PPG signal.

[0008] In one embodiment, the biological parameter calculation system further includes an oxygen saturation index calculation component configured to calculate an oxygen saturation index from the third signal quality classification result generated by the third signal quality classification component and the oxygen saturation estimated by the oxygen saturation estimation component. The oxygen saturation index may be defined by a ratio of the time when the oxygen saturation is out of the normal range and the time when the third signal quality classification component classifies the quality of the second wavelength PPG signal and the third wavelength PPG signal as good quality, where the third signal quality classification component classifies the quality of the second wavelength PPG signal and the third wavelength PPG signal as good quality.

[0009] In one embodiment, the first - wavelength PPG signal, the second - wavelength PPG signal, and the third - wavelength PPG signal are measured using the biosignal - sensing ring, and the server receives the first - wavelength PPG signal, the second - wavelength PPG signal, and the third - wavelength PPG signal from the biosignal - sensing ring via a terminal device. The biosignal - sensing ring includes a plurality of sensors configured to simultaneously measure a plurality of first - wavelength PPG signals, a plurality of second - wavelength PPG signals, and a plurality of third - wavelength PPG signals at different positions, respectively. Each of the plurality of sensors also includes a first - wavelength light source, a second - wavelength light source, a third - wavelength light source, and a photoelectric conversion device.

[0010] In one embodiment, the terminal device includes a light - source control component configured to control the first - wavelength light source, the second - wavelength light source, and the third - wavelength light source of each of the plurality of sensors such that the DC (direct current) component of each of the first - wavelength test PPG signals measured using the plurality of sensors is within a first predetermined range, the DC component of each of the plurality of second - wavelength test PPG signals measured using the plurality of sensors is within a second predetermined range, and the DC component of each of the plurality of third - wavelength test PPG signals measured using the plurality of sensors is within a third predetermined range.

[0011] In one embodiment, the terminal device further includes a sensor - selection component configured to select, from among the plurality of sensors, the sensor that measures the combination of the first - wavelength test PPG signal, the second - wavelength test PPG signal, and the third - wavelength test PPG signal with the highest signal quality among the plurality of first - wavelength test PPG signals, the plurality of second - wavelength test PPG signals, and the plurality of third - wavelength test PPG signals as the sensor for measuring the first - wavelength PPG signal, the second - wavelength PPG signal, and the third - wavelength PPG signal.

[0012] In one embodiment, the signal quality of the plurality of first-wavelength test PPG signals, the plurality of second-wavelength test PPG signals, and the plurality of third-wavelength test PPG signals can be evaluated by at least one of an acceleration signal magnitude, a signal-to-noise ratio, and an AC (alternating current) component magnitude to DC component magnitude ratio.

[0013] In one embodiment, the control of the first-wavelength light source, the second-wavelength light source, and the third-wavelength light source of each of the plurality of sensors by the light source control component and the sensor selection by the sensor selection component are performed sequentially, and the control of the first-wavelength light source, the second-wavelength light source, and the third-wavelength light source of each of the plurality of sensors by the light source control component and the sensor selection by the sensor selection component can be performed periodically.

[0014] A biological data monitoring platform using a biological signal sensing ring according to an embodiment of the present disclosure includes a terminal configured to receive the PPG signal from a biological signal sensing ring configured to measure the PPG signal and transmit the PPG signal to a server. The biological signal sensing ring includes a plurality of sensors configured to simultaneously measure a plurality of PPG signals at different positions, and each of the plurality of sensors also includes a light source and a photoelectric conversion device.

[0015] In one embodiment, the terminal also includes a light source control component configured to control the light source of each of the plurality of sensors such that the DC component of each of the plurality of test PPG signals measured using the plurality of sensors is within a predetermined range.

[0016] In one embodiment, the terminal further includes a sensor selection component configured to select, as a sensor for measuring the PPG signal, a sensor that measures a test PPG signal with the highest signal quality among the plurality of sensors.

[0017] In one embodiment, the signal quality of the plurality of test PPG signals can be evaluated by at least one of the magnitude of the acceleration signal, the signal-to-noise ratio, and the magnitude ratio of the AC component to the DC component.

[0018] In one embodiment, the control of the light source of each of the plurality of sensors by the light source control component and the sensor selection by the sensor selection component are performed sequentially, and the control of the light source of each of the plurality of sensors by the light source control component and the sensor selection by the sensor selection component can be performed periodically.

[0019] A biological data monitoring platform using a biological signal sensing ring according to an embodiment of the present disclosure includes a terminal. The terminal is configured to receive the first wavelength PPG signal, the second wavelength PPG signal, and the third wavelength PPG signal from a biological signal sensing ring configured to measure the first wavelength PPG signal, the second wavelength PPG signal, and the third wavelength PPG signal, and is configured to transmit the first wavelength PPG signal, the second wavelength PPG signal, and the third wavelength PPG signal to a server. The biological signal sensing ring includes a plurality of sensors configured to simultaneously measure a plurality of first wavelength PPG signals, a plurality of second wavelength PPG signals, and a plurality of third wavelength PPG signals at different positions. Each of the plurality of sensors also includes a first wavelength light source, a second wavelength light source, a third wavelength light source, and a photoelectric conversion device.

[0020] In one embodiment, the terminal also includes a light source control component configured to control the first wavelength light source, the second wavelength light source, and the third wavelength light source of each of the plurality of sensors such that the DC (direct current) component of each of the first wavelength test PPG signals measured using the plurality of sensors is within a first predetermined range, the DC component of each of the plurality of second wavelength test PPG signals measured using the plurality of sensors is within a second predetermined range, and the DC component of each of the plurality of third wavelength test PPG signals measured using the plurality of sensors is within a third predetermined range.

[0021] In one embodiment, the terminal further includes a sensor selection component configured to select, as a sensor for measuring the first wavelength PPG signal, the second wavelength PPG signal, and the third wavelength PPG signal, a sensor that measures a combination of the first wavelength test PPG signal, the second wavelength test PPG signal, and the third wavelength test PPG signal having the highest signal quality among the plurality of sensors.

[0022] In one embodiment, the signal quality of the plurality of first wavelength test PPG signals, the plurality of second wavelength test PPG signals, and the plurality of third wavelength test PPG signals can be evaluated by at least one of the magnitude of the acceleration signal, the signal-to-noise ratio, and the ratio of the magnitude of the AC component to the magnitude of the DC component.

[0023] In one embodiment, the control of the first wavelength light source, the second wavelength light source, and the third wavelength light source of each of the plurality of sensors by the light source control component and the sensor selection by the sensor selection component are performed sequentially, and the control of the first wavelength light source, the second wavelength light source, and the third wavelength light source of each of the plurality of sensors by the light source control component and the sensor selection by the sensor selection component can be performed periodically.

Advantages of the Invention

[0024] A biological data monitoring platform using a biological signal sensing ring that can simply and continuously measure biological signals with high reliability in daily life is provided.

Brief Description of the Drawings

[0025]

Figure 1

Figure 2

Figure 3A

Figure 3B

Figure 4A

Figure 4B

Figure 4C

Figure 4D

Figure 5A

Figure 5B

Figure 5C

Figure 5D

Figure 6A

Figure 6B

Figure 6C

Figure 6D

Figure 7

Embodiments for Carrying Out the Invention

[0026] FIG. 1 is a three-dimensional view of the biological signal sensing ring 100 according to an embodiment of the present disclosure. FIG. 2 is an exploded three-dimensional view of the biological signal sensing ring 100 according to an embodiment of the present disclosure. Referring to FIGS. 1 and 2, the biological signal sensing ring 100 also includes an external electrode 130, an internal electrode 140, an insulating unit 150, a top cover 110, an operation display unit 120, and a plurality of sensors 160.

[0027] The external electrode 130 may have an arc shape. The external electrode 130 is composed of a conductor and can function as an electrode for measuring an electrocardiogram (ECG). Further, the external electrode 130 forms the appearance of the biological signal sensing ring 100, and the external electrode 130 can be contacted with the user's body.

[0028] The internal electrode 140 has an annular shape and may have a plurality of openings 145 for the plurality of sensors 160. The internal electrode 140 is composed of a conductor and can function as an electrode for measuring an electrocardiogram. Further, the internal electrode 140 forms the inner appearance of the biological signal sensing ring 100, and the internal electrode 140 can be contacted with the user's finger.

[0029] The insulating unit 150 may be disposed between the external electrode 130 and the internal electrode 140. The insulating unit 150 can enable electrical insulation between the external electrode 130 and the internal electrode 140.

[0030] The top cover 110 has an arc shape and can form an annular shape together with the external electrode 130. The top cover 110 can form the appearance of the biological signal sensing ring 100.

[0031] The operation display unit 120 can be coupled to the top cover 110. The operation display unit 120 also includes a plurality of LEDs (light-emitting diodes), for example, those including green LEDs and red LEDs. The operation display unit 120 can utilize the plurality of LEDs to display the operation of the biological signal sensing ring 100. For example, in order to notify the start of measurement, the green LED can be turned on for 2 seconds, and in order to notify the end of measurement, the green LED can be turned on for 1 second. Also, in order to notify a failure, the red LED can repeatedly blink at a cycle of 1 second.

[0032] The plurality of sensors 160 can be arranged to contact the user's finger. The plurality of sensors 160 are respectively positioned within the plurality of openings 145 of the internal electrode 140 and can protrude from the surface of the internal electrode 140. The plurality of sensors 160 can be configured to acquire a plurality of first-wavelength PPG (photoplethysmography) signals, a plurality of second-wavelength PPG signals, and a plurality of third-wavelength PPG signals at different positions from each other. Each sensor 160 also includes a first-wavelength light source, a second-wavelength light source, and a third-wavelength light source that emit light of different wavelengths from each other, and a photoelectric conversion device.

[0033] In some embodiments, although not shown in FIGS. 1 and 2, the biological signal sensing ring 100 also further includes an acceleration sensor disposed between the external electrode 130 and the internal electrode 140.

[0034] FIG. 3A is a block diagram of a biological data monitoring platform 1000 using a biological signal sensing ring according to an embodiment of the present disclosure. FIG. 3B is a block diagram of a server 300 according to an embodiment of the present disclosure. FIGS. 4A and 4B are graphs showing examples of the first wavelength PPG signal before preprocessing. FIGS. 4C and 4D are graphs showing examples of the first wavelength PPG signals of FIGS. 4A and 4B after preprocessing, respectively. FIGS. 5A and 5B are graphs showing examples of the first wavelength PPG signals classified as good quality. FIGS. 5C and 5D are graphs showing examples of the first wavelength PPG signals classified as low quality. FIGS. 6A and 6B are graphs showing examples of the first wavelength PPG signals determined not to be atrial fibrillation. FIGS. 6C and 6D are graphs showing examples of the first wavelength PPG signals determined to be atrial fibrillation. FIG. 7 is a block diagram showing a signal feature extraction component 352A, a user feature extraction component 352B, and a blood pressure estimation component 353C.

[0035] Referring to FIGS. 3A, 3B, 4A to 4B, 5A to 5D, 6A to 6D, and 7, the biological data monitoring platform 1000 using the biological signal sensing ring also includes a biological signal sensing ring 100, a first terminal 200, a server 300, and a second terminal 400.

[0036] The biological signal sensing ring 100 can measure biological signals including an electrocardiogram and a PPG signal. The biological signal sensing ring 100 also includes a plurality of sensors, for example, a first sensor 160A and a second sensor 160B. Although FIG. 3A illustrates the biological signal sensing ring 100 as including two sensors, the number of sensors included in the biological signal sensing ring 100 is not limited to two. In some embodiments, although not illustrated in FIG. 3A, the biological signal sensing ring 100 may further include an acceleration sensor.

[0037] The first sensor 160A also includes a first-wavelength light source 161A, a second-wavelength light source 162A, a third-wavelength light source 163A, and a photoelectric conversion device 164A. The first sensor 160A can utilize the first-wavelength light source 161A and the photoelectric conversion device 164A to sense a first-wavelength PPG signal. The first sensor 160A can utilize the second-wavelength light source 162A and the photoelectric conversion device 164A to sense a second-wavelength PPG signal. The first sensor 160A can utilize the third-wavelength light source 163A and the photoelectric conversion device 164A to sense a third-wavelength PPG signal. The first-wavelength light source 161A includes, for example, a green LED, the second-wavelength light source 162A includes, for example, an infrared LED, the third-wavelength light source 163A includes, for example, a red LED, and the photoelectric conversion device 164A includes a photodiode.

[0038] The second sensor 160B also includes a first-wavelength light source 161B, a second-wavelength light source 162B, a third-wavelength light source 163B, and a photoelectric conversion device 164B. The first sensor 160B can utilize the first-wavelength light source 161B and the photoelectric conversion device 164B to sense a first-wavelength PPG signal. The second sensor 160B can utilize the second-wavelength light source 162B and the photoelectric conversion device 164B to sense a second-wavelength PPG signal. The second sensor 160B can utilize the third-wavelength light source 163B and the photoelectric conversion device 164B to sense a third-wavelength PPG signal. The first-wavelength light source 161B includes, for example, a green LED, the second-wavelength light source 162B includes, for example, an infrared LED, the third-wavelength light source 163B includes, for example, a red LED, and the photoelectric conversion device 164B includes a photodiode.

[0039] The acceleration sensor can sense the user's movement by measuring the acceleration of the biosignal sensing ring 100.

[0040] The first terminal device 200 can be used by a user. The first terminal device 200 can include, for example, a smartphone or a tablet PC (personal computer). The first terminal device 200 can be connected to the biosignal sensing ring 100 either by wire or wirelessly. For example, the first terminal device 200 can be connected to the biosignal sensing ring 100 using Bluetooth (registered trademark) or Wi-Fi (wireless fidelity). The first terminal device 200 can be connected to the server 300 either by wire or wirelessly. For example, the first terminal device 200 can be connected to the server 300 via Wi-Fi (wireless fidelity), or, for example, via mobile telecommunication technologies such as 3G (3 rd generation), LTE (long term evolution), 5G (5 th generation).

[0041] The first terminal device 200 can also include a light source control component 210, a sensor selection component 220, a measurement control component 230, and a display component 240. An application can be installed on the first terminal device 200. The light source control component 210, the sensor selection component 220, the measurement control component 230, and the display component 240 can be implemented by the application. As an alternative, the first terminal device 200 can connect to a website, and the light source control component 210, the sensor selection component 220, the measurement control component 230, and the display component 240 can be implemented on the website.

[0042] The light source control component 210 can control the first wavelength light source 161A, the second wavelength light source 162A, and the third wavelength light source 163A of the first sensor 160A, and the first wavelength light source 161B, the second wavelength light source 162B, and the third wavelength light source 163B of the second sensor 160B such that the DC (direct current) components of the first wavelength test PPG signals received from the first sensor 160A and the second sensor 160B are within a first predetermined range, the DC components of the second wavelength test PPG signals received from the first sensor 160A and the second sensor 160B are within a second predetermined range, and the DC components of the third wavelength test PPG signals received from the first sensor 160A and the second sensor 160B are within a third predetermined range.

[0043] After the light source control component 210 controls the first wavelength light source 161A, the second wavelength light source 162A, and the third wavelength light source 163A of the first sensor 160A, and the first wavelength light source 161B, the second wavelength light source 162B, and the third wavelength light source 163B of the second sensor 160B, the sensor selection component 220 can then select one of the first sensor 160A and the second sensor 160B as the sensor for subsequently measuring the first wavelength PPG signal, the second wavelength PPG signal, and the third wavelength PPG signal. The sensor selection component 220 can select, from among the first sensor 160A and the second sensor 160B, the sensor that measured the first wavelength test PPG signal, the second wavelength test PPG signal, and the third wavelength test PPG signal with the highest signal quality among the two first wavelength test PPG signals, two second wavelength test PPG signals, and two third wavelength test PPG signals from the first sensor 160A and the second sensor 160B. The signal quality can be evaluated by at least one of the acceleration signal magnitude, the signal-to-noise ratio (SNR), and the ratio of the AC component magnitude to the DC component magnitude. The smaller the acceleration signal magnitude, the higher the signal-to-noise ratio, and the higher the ratio of the AC component magnitude to the DC component magnitude, the higher the signal quality. Subsequently, the first wavelength PPG signal, the second wavelength PPG signal, and the third wavelength PPG signal can be measured using the sensor selected by the sensor selection component 220.

[0044] The control of the first wavelength light source 161A, the second wavelength light source 162A, and the third wavelength light source 163A of the first sensor 160A, and the first wavelength light source 161B, the second wavelength light source 162B, and the third wavelength light source 163B of the second sensor 160B by the light source control component 210, and the sensor selection by the sensor selection component 220 can be performed sequentially. That is, after the light source control component 210 controls the first wavelength light source 161A, the second wavelength light source 162A, and the third wavelength light source 163A of the first sensor 160A, and the first wavelength light source 161B, the second wavelength light source 162B, and the third wavelength light source 163B of the second sensor 160B, the sensor selection component 220 can select a sensor.

[0045] The control of the first wavelength light source 161A, the second wavelength light source 162A, and the third wavelength light source 163A of the first sensor 160A, and the first wavelength light source 161B, the second wavelength light source 162B, and the third wavelength light source 163B of the second sensor 160B by the light source control component 210, and the sensor selection by the sensor selection component 220 can be performed periodically. Since the biological signal sensing ring 100 can move or rotate with respect to the finger, the light source control component 210 can periodically control the light source, and the sensor selection component 220 can periodically select a sensor.

[0046] The measurement control component 230 can select a measurement mode, start, or end the measurement based on user input. For example, the user can use the measurement control component 230 to select the measurement mode from among a self-check mode and a background mode. In the self-check mode, the user can use the measurement control component 230 to start and end the measurement. In the background mode, the measurement starts and continues regardless of user input. In the background mode, the user can set or change the measurement period. In some embodiments, the measurement control component 230 is also included in the biosignal sensing ring 100. That is, the user can use the measurement control component 230 of the biosignal sensing ring 100 to select a measurement mode, start, or end the measurement. In some embodiments, the measurement control component 230 is also included in the server 300. That is, the service provider can use the measurement control component 230 of the server 300 to select a measurement mode, start, or end the measurement.

[0047] The display component 240 can display at least one of the biosignals measured by the biosignal sensing ring 100 and stored in the biosignal storage component 381 of the server 300, the measurement date and time of the biosignals stored in the biosignal storage component 381, the signal quality classification results classified by the signal quality classification system 320 of the server 300 and stored in the biological data storage component 382 of the server 300, the biological data calculated by the biological data calculation system 350 of the server 300 and stored in the biological data storage component 382 of the server 300, the biological indicators calculated by the biological indicator calculation system 360 of the server 300 and stored in the biological indicator storage component 383, and the disease occurrence probability calculated by the disease prediction system 380.

[0048] Here, the biological signal also includes at least one of an electrocardiogram, a first-wavelength PPG signal, a second-wavelength PPG signal, and a third-wavelength PPG signal. Also, the biological data also includes at least one of an atrial fibrillation determination result, blood pressure, and oxygen saturation. Further, the biological index also includes at least one of an atrial fibrillation index, a blood pressure index, and an oxygen saturation index.

[0049] The server 300 also includes a biological signal preprocessing system 310, a signal quality classification system 320, a biological data calculation system 350, a biological index calculation system 360, an alarm system 370, a disease prediction system 380, a biological signal storage component 381, a biological data storage component 382, and a biological index storage component 383.

[0050] The biological signal preprocessing system 310 can preprocess the biological signal received by the server 300 from the selected sensor of the biological signal sensing ring 100 via the first terminal 200. The biological signal preprocessing system 310 also includes a first biological signal preprocessing component 311, a second biological signal preprocessing component 312, and a third biological signal preprocessing component 313.

[0051] The first biological signal preprocessing component 311 can preprocess the first-wavelength PPG signal. For example, in order to preprocess the first-wavelength PPG signal, a low-pass filter, a high-pass filter, and normalization are used. FIGS. 4A and 4B are graphs showing examples of the first-wavelength PPG signal before preprocessing. FIGS. 4C and 4D are graphs showing examples of the first-wavelength PPG signals of FIGS. 4A and 4B after preprocessing, respectively.

[0052] The second biological signal preprocessing component 312 can preprocess the second-wavelength PPG signal. For example, in order to preprocess the second-wavelength PPG signal, a low-pass filter, a high-pass filter, and normalization can be used.

[0053] The third biosignal preprocessing component 313 can preprocess the second-wavelength PPG signal and the third-wavelength PPG signal. For example, a low-pass filter, a high-pass filter, and normalization can be used to preprocess the second-wavelength PPG signal and the third-wavelength PPG signal.

[0054] In some embodiments, the biosignal preprocessing system 310 further includes a fourth biosignal preprocessing component, and the fourth biosignal preprocessing component can preprocess the acceleration signal received by the server 300 from the acceleration sensor of the biosignal sensing ring 100 via the first terminal 200.

[0055] The signal quality classification system 320 can classify the signal quality of the biosignal preprocessed by the biosignal preprocessing system 310 as good or bad. The signal quality classification system 320 also includes a first signal quality classification component 321, a second signal quality classification component 322, and a third signal quality classification component 323.

[0056] The first signal quality classification component 321 can classify the signal quality of the first-wavelength PPG signal preprocessed by the first biosignal preprocessing component 311 as good or bad. FIGS. 5A and 5B are graphs showing examples of the first-wavelength PPG signal classified as good quality. FIGS. 5C and 5D are graphs showing examples of the first-wavelength PPG signal classified as low quality. In some embodiments, the first signal quality classification component 321 can refer to the acceleration signal to classify the signal quality of the first-wavelength PPG signal into one of good or bad.

[0057] In one embodiment, the first signal quality classification component 321 can classify the quality of the first wavelength PPG signal as good or bad by using a deep learning model. The deep learning model used for the first signal quality classification component 321 may include a convolutional neural network (CNN), long short-term memory (LSTM), fully connected network (FCN), encoder, decoder, or a combination thereof. The method for classifying signal quality is not limited to the method described in this specification.

[0058] The second signal quality classification component 322 can classify the signal quality of the second wavelength PPG signal preprocessed by the second biosignal preprocessing component 312 as good or bad. In some embodiments, the second signal quality classification component 322 may refer to the acceleration signal to classify the signal quality of the second wavelength PPG signal into one of good or bad. In some embodiments, the second signal quality classification component 322 can classify the quality of the second wavelength PPG signal as good or bad by using a deep learning model. The deep learning model used for the second signal quality classification component 322 may include a convolutional neural network (CNN), long short-term memory (LSTM), fully connected network (FCN), encoder, decoder, or a combination thereof. The method for classifying signal quality is not limited to the method described in this specification.

[0059] The third signal quality classification component 323 can classify the signal quality of the preprocessed second wavelength PPG signal and the third wavelength PPG signal as good or bad. In some embodiments, the third signal quality classification component 323 can refer to the acceleration signal to classify the signal quality of the third wavelength PPG signal into one of good or bad. In some embodiments, the third signal quality classification component 323 can utilize a deep learning model to classify the quality of the second wavelength PPG signal and the third wavelength PPG signal as good or bad. The deep learning model used for the third signal quality classification component 323 can also include a convolutional neural network (CNN), a long short-term memory (LSTM), a fully connected network (FCN), an encoder, a decoder, or a combination thereof. The method for classifying the signal quality is not limited to the methods described herein.

[0060] The biological data calculated from the biological signal classified as having low signal quality by the signal quality classification system 320 is determined to be untrustworthy and is not displayed by the display component 240 of the first terminal 200. The biological data calculated from the biological signal classified as having good quality is determined to be trustworthy and can be displayed by the display component 240 of the first terminal 200.

[0061] In an alternative embodiment, regardless of the signal quality classification result, the biological data calculated from the biological signal can be displayed by the display component 240 of the first terminal 200 together with the signal quality classification result. Also, regardless of the signal quality classification result, the biological data calculated from the biological signal can be displayed by the display component 420 of the second terminal 400 together with the signal quality classification result.

[0062] The biological data calculation system 350 can calculate biological data from biological signals. The biological signals include at least one of an electrocardiogram, a first-wavelength PPG signal, a second-wavelength PPG signal, and a third-wavelength PPG signal. The biological data also includes at least one of an atrial fibrillation determination result, blood pressure, and oxygen saturation. The biological data calculation system 350 also includes an atrial fibrillation determination component 351, a signal feature extraction component 352A, a user feature extraction component 352B, a blood pressure estimation component 352C, and an oxygen saturation estimation component 353.

[0063] The atrial fibrillation determination component 351 can use a deep learning model to determine the occurrence of atrial fibrillation from the first-wavelength PPG signal. FIGS. 6A and 6B are graphs showing examples of the first-wavelength PPG signal determined not to be atrial fibrillation. FIGS. 6C and 6D are graphs showing examples of the first-wavelength PPG signal determined to be atrial fibrillation.

[0064] The deep learning model used in the atrial fibrillation determination component 350 can include a convolutional neural network (CNN), a long short-term memory (LSTM), a fully connected network (FCN), an encoder, a decoder, or a combination thereof. The deep learning model can be learned using supervised learning. Data augmentation can be used to ensure sufficient data sets required for the supervised learning.

[0065] As shown in FIG. 7, the signal feature extraction component 352A can extract PPG features from the second wavelength PPG signal by using the first deep learning model. The user feature extraction component 352B can extract user features from the test PPG signal, systolic test blood pressure, diastolic test blood pressure, and user information by using the second deep learning model. The test PPG signal can be measured by using the second wavelength light source and the photoelectric conversion device of the selected sensor of the biosignal sensing ring 100. The systolic test blood pressure and the diastolic test blood pressure can be measured simultaneously with the test PPG signal by using a conventional sphygmomanometer. The user information also includes at least one of the user's age, weight, height, and gender. The blood pressure estimation component 352C can estimate the systolic blood pressure and the diastolic blood pressure from the PPG features and the user features by using the third deep learning model. The test PPG signal, the systolic test blood pressure, the diastolic test blood pressure, and the user information can be updated periodically.

[0066] Each of the first deep learning model, the second deep learning model, and the third deep learning model may include a convolutional neural network (CNN), a long short-term memory (LSTM), a fully connected network (FCN), an encoder, a decoder, or a combination thereof. The first deep learning model, the second deep learning model, and the third deep learning model can be learned by using supervised learning. Data augmentation can be used to ensure sufficient data sets required for the supervised learning.

[0067] The oxygen saturation estimation component 353 can estimate the oxygen saturation from the second wavelength PPG signal and the third wavelength PPG signal. Various methods can be used to estimate the oxygen saturation.

[0068] For example, the R value can be first calculated by Equation 1 as follows.

[0069]

Equation

[0070] Here, AC R is the magnitude of the AC component of the third-wavelength PPG signal, and DC R is the magnitude of the DC component of the third-wavelength PPG signal, and AC IR is the magnitude of the AC component of the second-wavelength PPG signal, and DC IR is the magnitude of the DC component of the second-wavelength PPG signal.

[0071] Next, the oxygen saturation can be calculated from the R value by the following mathematical formula 2.

[0072]

Equation

[0073] C0 and C1 are constants that can be determined using linear regression.

[0074] In mathematical formula 2, the oxygen saturation is described as being expressed by a linear equation with respect to the R value. However, the oxygen saturation can also be expressed by a polynomial of degree greater than 1, for example, a quadratic equation or a cubic equation, with respect to the R value. The method for estimating the oxygen saturation is not limited to the method described in this specification.

[0075] The biological parameter calculation system 360 can calculate biological parameters from the signal quality classification result generated by the signal quality classification system 320 and the biological data calculated by the biological data calculation system 350. Here, the biological parameter includes at least one of an atrial fibrillation parameter, a blood pressure parameter, and an oxygen saturation parameter. The biological parameter calculation system 360 also includes an atrial fibrillation parameter calculation component 361, a blood pressure parameter calculation component 362, and an oxygen saturation parameter calculation component 363.

[0076] The atrial fibrillation index calculation component 361 can calculate an atrial fibrillation index from the first signal quality classification result generated by the first signal quality classification component 321 and the atrial fibrillation determination result generated by the atrial fibrillation determination component 351. The atrial fibrillation index can be defined based on the time when the first signal quality classification component 321 classifies the quality of the first wavelength PPG signal as good quality and the time when the atrial fibrillation determination component 351 determines that atrial fibrillation has occurred among the time when the first signal quality classification component 321 classifies the quality of the first wavelength PPG signal as good quality. For example, the atrial fibrillation index can be defined by the ratio of the time when the atrial fibrillation determination component 351 determines that atrial fibrillation has occurred to the time when the first signal quality classification component 321 classifies the quality of the first wavelength PPG signal as good quality among the time when the first signal quality classification component 321 classifies the quality of the first wavelength PPG signal as good quality. That is, the atrial fibrillation index can mean the ratio of the time when atrial fibrillation has occurred to the time when a reliable atrial fibrillation determination result can be obtained.

[0077] The blood pressure index calculation component 362 can calculate a blood pressure index from the second signal quality classification result generated by the second signal quality classification component 322 and the blood pressure estimated by the blood pressure estimation component 352C. The blood pressure index can be defined based on the time when the second signal quality classification component 322 classifies the quality of the second wavelength PPG signal as good quality and the time when the systolic blood pressure deviates from the first normal range or the diastolic blood pressure deviates from the second normal range among the time when the second signal quality classification component 322 classifies the quality of the second wavelength PPG signal as good quality. For example, the blood pressure index can be defined by the ratio of the time when the systolic blood pressure deviates from the first normal range or the diastolic blood pressure deviates from the second normal range among the time when the second signal quality classification component 322 classifies the quality of the PPG signal as good quality to the time when the second signal quality classification component 322 classifies the quality of the second wavelength PPG signal as good quality. That is, the blood pressure index can mean the ratio of the time when abnormal blood pressure is indicated among the time when a reliable blood pressure estimation result can be obtained.

[0078] The oxygen saturation index calculation component 363 can calculate an oxygen saturation index from the third signal quality classification result generated by the third signal quality classification component 323 and the oxygen saturation estimated by the oxygen saturation estimation component 353. The oxygen saturation index can be defined based on the time when the third signal quality classification component 323 classifies the quality of the second wavelength PPG signal and the third wavelength PPG signal as good quality, and the time when the oxygen saturation estimated by the oxygen saturation estimation component 353 is out of the normal range among the time when the third signal quality classification component 323 classifies the quality of the second wavelength PPG signal and the third wavelength PPG signal as good quality. For example, the oxygen saturation index can be defined by the ratio of the time when the oxygen saturation estimated by the oxygen saturation estimation component 353 is out of the normal range to the time when the third signal quality classification component 323 classifies the quality of the second wavelength PPG signal and the third wavelength PPG signal as good quality among the time when the third signal quality classification component 323 classifies the quality of the second wavelength PPG signal and the third wavelength PPG signal as good quality. That is, the oxygen saturation index can mean the ratio of the time when the oxygen saturation related to the time when a reliable oxygen saturation can be obtained is out of the normal range.

[0079] The alarm system 370 can transmit an alarm to at least one of the first terminal 200 and the second terminal 400 if at least one of the biological signal, biological data, and biological index satisfies the alarm conditions preset by the alarm condition setting component 410 of the second terminal 400. The alarm system 370 also includes an atrial fibrillation alarm component 371, a blood pressure alarm component 372, and an oxygen saturation alarm component 373.

[0080] If the atrial fibrillation determination result determined by the atrial fibrillation determination component 351 satisfies the alarm condition set by the alarm condition setting component 410 of the second terminal device 400, the atrial fibrillation alarm component 371 can transmit an alarm to at least one of the first terminal device 200 and the second terminal device 400.

[0081] If the blood pressure estimated by the blood pressure estimation component 352C satisfies the alarm condition set by the alarm condition setting component 410 of the second terminal device 400, the blood pressure alarm component 372 can transmit an alarm to at least one of the first terminal device 200 and the second terminal device 400.

[0082] If the oxygen saturation estimated by the oxygen saturation estimation component 353 satisfies the alarm condition set by the alarm condition setting component 410 of the second terminal device 400, the oxygen saturation alarm component 373 can transmit an alarm to at least one of the first terminal device 200 and the second terminal device 400.

[0083] The disease prediction system 380 can calculate the disease occurrence probability from at least one of the temporal changes of biological signals such as, for example, an electrocardiogram, a first wavelength PPG signal, a second wavelength PPG signal, and a third wavelength PPG signal; biological data such as, for example, an atrial fibrillation determination result, blood pressure, and oxygen saturation; and biological indicators such as, for example, an atrial fibrillation index, a blood pressure index, and an oxygen saturation index. The disease prediction system 380 can use a deep learning model.

[0084] The biological signal storage component 381 can store the electrocardiogram, the first-wavelength PPG signal, the second-wavelength PPG signal, and the third-wavelength PPG signal received by the server 300 from the biological signal sensing ring 100 via the first terminal device 200. The biological signal storage component 381 can further store the measurement date and time of the electrocardiogram, the first-wavelength PPG signal, the second-wavelength PPG signal, and the third-wavelength PPG signal. The biological signal storage component 381 can further store the first-wavelength PPG signal, the second-wavelength PPG signal, and the third-wavelength PPG signal preprocessed by the biological signal preprocessing system 310. The biological signal storage component 381 can further store the acceleration signal received by the server 300 from the biological signal sensing ring 100 via the first terminal device 200. The biological signal storage component 381 can further store the acceleration signal preprocessed by the biological signal preprocessing system 310.

[0085] The biological data storage component 382 can store biological data such as, for example, the atrial fibrillation determination result generated by the atrial fibrillation determination component 351, the blood pressure estimated by the blood pressure estimation component 352C, and the oxygen saturation estimated by the oxygen saturation estimation component 353. The biological data storage component 382 can store the first signal quality classification result generated by the first signal quality classification component 321, the second signal quality classification result generated by the second signal quality classification component 322, and the third signal quality classification result generated by the third signal quality classification component 323. The biological index storage component 383 can store biological indices such as, for example, the atrial fibrillation index calculated by the atrial fibrillation index calculation component 361, the blood pressure index calculated by the blood pressure index calculation component 362, and the oxygen saturation index calculated by the oxygen saturation index calculation component 363.

[0086] The second terminal device 400 can be connected to the server 300 either by wire or wirelessly. For example, the second terminal device 400 can be connected to the server 300 via Wi-Fi (wireless fidelity) or, for example, mobile communication technologies such as 3G, LTE, or 5G. The second terminal device 400 can be used by a doctor. The second terminal device 400 can include, for example, a smartphone, a tablet PC, a computer, or a notebook computer.

[0087] The second terminal device 400 also includes an alarm condition setting component 410 and a display component 420. The second terminal device 400 can be connected to a website or an application can be installed. The alarm condition setting component 410 and the display component 420 can be implemented using a website or an application.

[0088] Using the alarm condition setting component 410, a doctor can set alarm conditions. For example, if atrial fibrillation persists for 10 minutes or more, the atrial fibrillation alarm component 371 can be set to transmit an alarm to at least one of the first terminal device 200 and the second terminal device 400. Also, for example, if the systolic blood pressure is over 140 mmHg or less than 90 mmHg, or if the diastolic blood pressure is over 90 mmHg or less than 60 mmHg and persists for 10 minutes or more, the blood pressure alarm component 372 can be set to transmit an alarm to at least one of the first terminal device 200 and the second terminal device 400. Also, for example, if the oxygen saturation is less than 90% and persists for 10 minutes or more, the oxygen saturation alarm component 373 can be set to transmit an alarm to at least one of the first terminal device 200 and the second terminal device 400.

[0089] In one embodiment, the alarm condition setting component 410 is also included in the server 300. That is, the service provider can use the alarm condition setting component 410 of the server 300 to set alarm conditions. In one embodiment, the alarm condition setting component 410 is also included in the first terminal 200. That is, the user can use the alarm condition setting component 410 of the first terminal 200 to set alarm conditions.

[0090] The display component 420 can display at least one of the biological signals measured by the biological signal sensing ring 100 and stored in the biological signal storage component 381 of the server 300, the measurement date and time of the biological signals stored in the biological signal storage component 381 of the server 300, the pre-processed biological signals stored in the signal storage component 381, the signal quality classification results classified by the signal quality classification system 320 of the server 300 and stored in the biological data storage component 382 of the server 300, the biological data calculated by the biological data calculation system 350 of the server 300 and stored in the biological data storage component 382 of the server 300, the biological indicators calculated by the biological indicator calculation system 360 of the server 300 and stored in the biological indicator storage component 383, and the disease occurrence probabilities calculated by the disease prediction system 380.

[0091] The embodiments disclosed in the present disclosure are not for limiting the technical idea of the present disclosure, but for explanation. Such embodiments do not limit the scope of the technical idea of the present disclosure. The protection scope of the present disclosure shall be construed according to the following claims, and all technical ideas within the equivalent scope shall be construed as being included in the scope of rights of the present disclosure.

Claims

A biological data monitoring platform using a biosignal sensing ring utilized for measuring a PPG (photoplethysmography) signal, the platform including a server, the server a signal quality classification system including a first signal quality classification component configured to classify the signal quality of a first wavelength PPG signal as good or bad, a biological data calculation system including an atrial fibrillation determination component configured to utilize a deep learning model to determine the occurrence of atrial fibrillation from the first wavelength PPG signal, a biological index calculation system including an atrial fibrillation index calculation component configured to calculate an atrial fibrillation index from the first signal quality classification result generated by the first signal quality classification component and the atrial fibrillation determination result generated by the atrial fibrillation determination component, The atrial fibrillation index is defined by the ratio of the time when the atrial fibrillation is determined to have occurred by the atrial fibrillation determination component and the time when the quality of the first wavelength PPG signal is classified as good by the first signal quality classification component, to the time when the quality of the first wavelength PPG signal is classified as good by the first signal quality classification component, in a biological data monitoring platform using a biosignal sensing ring.

2. The signal quality classification system further includes a second signal quality classification component configured to classify the signal quality of a second wavelength PPG signal as good or bad, The biological data calculation system a signal feature extraction component configured to extract PPG features from the second wavelength PPG signal using a first deep learning model, A test PPG signal measured using the biosignal sensing ring, a systolic test blood pressure and a diastolic test blood pressure measured using a conventional sphygmomanometer simultaneously with the test PPG signal, and user information, and a user feature extraction component configured to extract user features using a second deep learning model. The biosignal data monitoring platform using the biosignal sensing ring according to claim 1, further comprising a blood pressure estimation component configured to estimate a systolic blood pressure and a diastolic blood pressure from the PPG features and the user features using a third deep learning model.

3. The biosignal index calculation system further includes a blood pressure index calculation component configured to calculate a blood pressure index from the second signal quality classification result generated by the second signal quality classification component and the blood pressure estimated by the blood pressure estimation component. The blood pressure index is defined by the ratio of the time when the quality of the second wavelength PPG signal is classified as good by the second signal quality classification component and the systolic blood pressure is out of the first normal range or the diastolic blood pressure is out of the second normal range to the time when the quality of the second wavelength PPG signal is classified as good by the second signal quality classification component. The biosignal data monitoring platform using the biosignal sensing ring according to claim 2.

4. The signal quality classification system further includes a third signal quality classification component configured to classify the quality of the second wavelength PPG signal and the third wavelength PPG signal as good or bad. The biosignal data calculation system further includes an oxygen saturation estimation component configured to estimate oxygen saturation from the second wavelength PPG signal and the third wavelength PPG signal. The biosignal data monitoring platform using the biosignal sensing ring according to claim 1.

5. The biological index calculation system further includes an oxygen saturation index calculation component configured to calculate an oxygen saturation index from the third signal quality classification result generated by the third signal quality classification component and the oxygen saturation estimated by the oxygen saturation estimation component. The oxygen saturation index is classified by the third signal quality classification component as having good quality of the second wavelength PPG signal and the third wavelength PPG signal, and the oxygen saturation is outside the normal range for a time, and the third signal quality classification component classifies the second wavelength PPG signal and the third wavelength PPG signal as having good quality. The biological data monitoring platform using the biological signal sensing ring according to claim 4, characterized in that it is defined by the ratio of the time.

6. The first wavelength PPG signal, the second wavelength PPG signal, and the third wavelength PPG signal are measured using the biological signal sensing ring, and the server receives the first wavelength PPG signal, the second wavelength PPG signal, and the third wavelength PPG signal from the biological signal sensing ring via a terminal device. The biological signal sensing ring includes a plurality of sensors configured to simultaneously measure a plurality of first wavelength PPG signals, a plurality of second wavelength PPG signals, and a plurality of third wavelength PPG signals at different positions. The biological data monitoring platform using the biological signal sensing ring according to claim 1, characterized in that each of the plurality of sensors includes a first wavelength light source, a second wavelength light source, a third wavelength light source, and a photoelectric conversion device.

7. The terminal is configured to control the first wavelength light source, the second wavelength light source, and the third wavelength light source of each of the plurality of sensors such that the DC (direct current) component of each of the first wavelength test PPG signals measured using the plurality of sensors is within a first predetermined range, the DC component of each of the plurality of second wavelength test PPG signals measured using the plurality of sensors is within a second predetermined range, and the DC component of each of the plurality of third wavelength test PPG signals measured using the plurality of sensors is within a third predetermined range. The biological data monitoring platform using the biological signal sensing ring according to claim 6, characterized by including a light source control component.

8. The terminal further includes a sensor selection component configured to select, from among the plurality of sensors, a sensor that measures a combination of the first wavelength test PPG signal, the second wavelength test PPG signal, and the third wavelength test PPG signal with the highest signal quality among the plurality of first wavelength test PPG signals, the plurality of second wavelength test PPG signals, and the plurality of third wavelength test PPG signals as the sensor for measuring the first wavelength PPG signal, the second wavelength PPG signal, and the third wavelength PPG signal. The biological data monitoring platform using the biological signal sensing ring according to claim 7, characterized by this.

9. The signal quality of the plurality of first wavelength test PPG signals, the plurality of second wavelength test PPG signals, and the plurality of third wavelength test PPG signals is evaluated by at least one of the magnitude of the acceleration signal, the signal-to-noise ratio, and the ratio of the magnitude of the AC component to the magnitude of the DC component. The biological data monitoring platform using the biological signal sensing ring according to claim 8, characterized by this.

10. The control of the first wavelength light source, the second wavelength light source, and the third wavelength light source of each of the plurality of sensors by the light source control component and the sensor selection by the sensor selection component are performed sequentially. The control of the first wavelength light source, the second wavelength light source, and the third wavelength light source of each of the plurality of sensors by the light source control component, and the sensor selection by the sensor selection component are periodically performed. The biological data monitoring platform using the biological signal sensing ring according to claim 8, characterized in that.

Images