Physiological monitoring systems and methods of estimating vital-sign data

The invention relates to a physiological monitoring system, and more particularly to a physiological monitoring system which detects vital-sign data of a user based on the biological information about the personal identification of the user.

With aging societies, more and more burden is placed on hospital resources. Moreover, cardiovascular diseases are increasing, as people age and stress increases for modern day living. Thus, vital-sign self-measurement devices have become an important target for development in the healthcare industry. Through sensing or detecting medically health information, such as electrocardiography (ECG), photoplethysmogram (PPG), heart rate, and blood pressure of patients in bio-signal self-measurement manners, the patients can monitor their own physiology status anytime, to relieve strain on hospital resources and provide needed medical attention to patients. Generally, to enhance the accuracy of a vital-sign self-measurement device, a user needs to input his/her biological features, such as age, gender, weight, height, and race, such that the vital-sign self-measurement device can select an appropriate model or adjust parameters of a reference model to estimate the user's health information. However, some biological features, such as the age, weight, and height, may change over time, and the user has to update these biological features every once in a while, which is inconvenient, especially for the elderly. In some situations, one vital-sign self-measurement device is shared by several users, such as a family. Since these users may be of different ages, genders, weight, height, or races, the appropriate models for estimating the health information are also different. Every time the vital-sign self-measurement device operates to estimate one of these users, the user has to manually switch the vital-sign self-measurement device to an appropriate model, which is inconvenient and is also easy to switch to the wrong model.

Thus, it is desired to provide a physiological monitoring system which detects vital-sign data of a user based on biological features which is obtained from information about the personal identification of the user, thereby enhancing the accuracy of the detection result.

An exemplary embodiment of a physiological monitoring system is provided. The physiological monitoring system comprises a feature extraction device, an identifier, a processor, a physiological sensing device, and a vital-sign detector. The feature extraction device extracts biological information of an object to generate an extraction signal. The identifier receives the extraction signal and verifies an identity of the object according to the extraction signal. The processor receives the extraction signal and obtains at least one biological feature of the user according to the extraction signal. The physiological sensing device senses a physiological feature to generate a bio-signal. The vital-sign detector estimates vital-sign data of the object according to the bio-signal and the at least one biological feature.

An exemplary embodiment of a method of estimating vital-sign data. The method comprises the steps of extracting biological information of an object to generate an extraction signal for verifying an identity of the object; obtaining at least one biological feature of the user according to the extraction signal; sensing a physiological feature to generate a bio-signal; and estimating vital-sign data of the object according to the bio-signal and the at least one biological feature.

A detailed description is given in the following embodiments with reference to the accompanying drawings.

The invention can be more fully understood by reading the subsequent detailed description and examples with references made to the accompanying drawings, wherein:

FIG. 1 shows one exemplary embodiment of a physiological monitoring system;

FIG. 2 shows another exemplary embodiment of a physiological monitoring system;

FIG. 3 shows another exemplary embodiment of a physiological monitoring system;

FIG. 4 shows a flow chart of estimating a blood pressure according to the bio-signal(s) and bio-tag(s) according to an exemplary embodiment;

FIG. 5 shows a flow chart of estimating a body-fat percentage according to the bio-signal(s) and bio-tag(s) according to an exemplary embodiment; and

FIG. 6 shows a flow chart of estimating an OSA risk according to the bio-signal(s) and bio-tag(s) according to an exemplary embodiment.

The following description is of the best-contemplated model of carrying out the invention. This description is made for the purpose of illustrating the general principles of the invention and should not be taken in a limiting sense. The scope of the invention is best determined by reference to the appended claims.

FIG. 1 shows one exemplary embodiment of a physiological monitoring system. As shown in FIG. 1 , a physiological monitoring system 1 is provided to operate to monitor at least one vital-sign of an object, such as a user, to generate vital-sign data. The physiological monitoring system 1 comprises a feature extraction device 10 , a processor 11 , an identifier 12 , a vital-sign detector 13 , a speaker 14 , a displayer 15 , and a physiological sensing device 16 . In an embodiment, the feature extraction device 10 operates to extract the biological information of the user to generate at least one extraction signal S 10 . The extracted biological information of the user comprises the facial profile, a fingerprint, and/or voiceprint which are unique to the user. In an embodiment, as shown in FIG. 2 , the feature extraction device may comprise a camera 10 A, a voice detector 10 B, and a fingerprint scanner 10 C. The camera 10 A captures an image of the face of the user which is facing the camera 10 A and generates an extraction signal S 10 A according to the captured image. In an embodiment, the camera 10 A may be a TrueDepth camera. The extraction signal S 10 A comprises data related to the facial profile of the user. The voice detector 10 B detects sound transmitted from the user. The voice detector 10 B analyzes the features of the detected sound to obtain the voiceprint of the user and generates an extraction signal S 10 B according to the obtained voiceprint. In an embodiment, the voice detector 10 B comprises a microphone to receive sound. The fingerprint scanner 10 C scans an image of one finger of the user which is contacting a touch panel of the fingerprint scanner 10 C, such as the fingerprint of the right thumb. The fingerprint scanner 10 C analyzes scanned the scanned image and detects the fingerprint of the finger, and generates an extraction signal 10 C according to the detected fingerprint. The touch panel of the fingerprint scanner 10 C is dedicated for fingerprint scanning on a portion of a touch screen. The camera 10 A, the voice detector 10 B, and the fingerprint scanner 10 C operate at different times. Alternatively, at least two of camera 10 A, the voice detector 10 B, and the fingerprint scanner 10 C operate at the same time.

Since the facial profile, the fingerprint, and the voiceprint are unique to the user, the identifier 12 can verify the identity of the user according to at least one of the extraction signals S 10 A˜S 10 C. In the cases where the physiological monitoring system 1 is in a locked mode, the identifier 12 unlocks the physiological monitoring system 1 when the identity of the user is verified successfully. In other cases, the identifier 12 can determine the authority of the user to access the physiological monitoring system 1 based the verified identify. In the embodiment, the identifier 12 may use any biometrics manners to verify the identity of the user according to at least one of the extraction signals S 10 A˜S 10 C.

Referring to FIGS. 1-2 , the processor 11 also receives at least one of the extraction signals S 10 A˜S 10 C and obtains at least one biological feature of the user according to the received extraction signal(s). Generally, a person's age, gender, body information (including weight and height), and race can be learned from the facial profile. Thus, in the embodiment, when the camera 10 A operates to capture an image of the face of the user, the processor 11 receives the extraction signal S 10 A which comprises the data related to the facial profile of the user and analyzes the extraction signal S 10 A to obtain at least one of the age, the gender, the body information, and the race of the user as at least one biological feature. After obtaining the at least one biological feature, the processor 11 generates at least one corresponding bio-tag for the vital-sign detector 13 . In the embodiment, the bio-tags related to the age, the gender, the body information, and the race are represented by T 11 ˜T 14 , respectively. Since the bio-tags T 11 ˜T 14 are derived from the biological information of the user, one bio-tag or a combination of at least two bio-tags serves as an identification of the user.

Moreover, a person's age and gender can be learned from his/her voiceprint. Thus, in the embodiment, when the voice detector 10 B detects sound transmitted from the user, the processor 11 receives the extraction signal S 10 B and analyzes the extraction signal S 10 B to obtain at least one of the age and the gender of the user as at least one biological feature. After obtaining the at least one biological feature, the processor 11 generates at least one corresponding bio-tag T 11 or T 12 for the vital-sign detector 13 .

Generally, as people age, the fingerprints of the fingers become shallower. Thus, a person's age or age range can be learned from his/her fingerprint. In the embodiment, when the fingerprint scanner 10 C detects the fingerprint of one finger of the user, the processor 13 receives the extraction signal S 10 C and analyzes the extraction signal S 10 C to obtain the age or the age range of the user as a biological feature. After obtaining the biological feature, the processor 11 generates a corresponding bio-tag T 11 for the vital-sign detector 13 .

The physiological sensing device 16 operates to sense at least one physiological feature of the user who is wearing, holding or contacting the physiological sensing device 16 , such as the motion, photoplethysmogram (PPG), electrocardiography (ECG), the body fat, and amount of red light (R) and infrared (IR) received by the blood of the user. The physiological sensing device 16 generates at least one bio-signal according to the at least one sensed physiological feature. Referring to FIG. 2 , in an embodiment, the physiological sensing device 16 comprises a motion sensor 16 A, a photoplethysmogram (PPG) sensor 16 B, an electrocardiography (ECG) sensor 16 C, a body-fat sensor 16 D, and a SPO2 sensor 16 E. The motion sensor 16 A is disposed on a specific portion of the body of the user, such as one arm, one wrist, or one leg of the user, to sense the motion or activity of the user and generate a bio-signal S 16 A. The PPG sensor 16 B illuminates the skin of the user (for example, the skin of the right wrist) by a red light (R) source, a green light (G) source, or infrared (IR) source, detects the changes in light absorption of the blood under the skin, and generates a bio-signal S 16 B based on the measured changes. The ECG sensor 16 C senses the electrical activity of the heart of the user through electrodes contacting the skin of the user and generates a bio-signal S 16 C. The body-fat sensor 16 D provides a small electric current to the body of the user through two conductors attached to the body and measures the resistance between the two conductors to generate a bio-signal S 16 D.

The SPO2 sensor 16 E comprises a probe, such as a clip-type probe. The clip-type probe grips a specific portion of the body of the user, such as the right index finger of the user. A red light (R) source and an infrared (IR) source are disposed on one side of the probe, and a photo detector is disposed on the other side thereof. The light emitted by the R and IR sources travels through the tissue and blood and is then collected in the photo detector. The photo detector generates a bio-signal S 16 E according to the amount of received R and IR. Since the deoxyhemoglobin (Hb) and the oxyhemoglobin (HbO2) in the blood have different capacities for R and IR having different wavelengths, the bio-signal S 16 E is related to the amount of the deoxyhemoglobin (Hb) and the amount of the oxyhemoglobin (HbO2) in the blood.

In the above embodiment, the processor 11 receives at least one of the extraction signals S 10 A˜S 10 C indicating at least one biological feature and generates at least one bio-tag according to the received extraction signal(s). In another embodiment, the processor 11 further receives at least one of the bio-signals S 16 A˜S 16 E and generates at least one bio-tag according to the received extraction signal(s) and the received bio-signal(s). In this embodiment, since the bio-signals S 16 A˜S 16 E indicate the physiological features of the user, the bio-tag(s) indicating the biological feature(s) of the user can be determined more accurately when at least one bio-signal is also considered.

The vital-sign detector 13 receives the bio-tag(s) from the processor 11 and the bio-signal(s) from the physiological sensing device 16 and detects vital-sign data of the user according to the received the bio-tag(s) and the received bio-signal(s). In the embodiment, the vital-sign data comprises at least one of an index representing an obstructive sleep apnea (OSA) risk, a blood pressure, a body-fat percentage, an index representing an incidence of cardiovascular diseases, an index representing a sleep stage, a value representing a heart rate, an index representing heart rate variability, an index representing atrial fibrillation, and a value representing blood oxygen saturation. As described above, the bio-tags represent the different biological features, such as the age, the gender, the body information, and the race. In the embodiment, the vital-sign detector 13 can select an appropriate estimation model or change parameters of a reference estimation model according to at least one bio-tag, so that the vital-sign detector 13 can accurately estimate vital-sign data of the user.

In an embodiment, the physiological monitoring system 1 is implemented in an apparatus, such as a physiological monitoring apparatus or a smart phone. In another embodiment, the physiological monitoring system 1 is implemented in different apparatuses. As shown in FIG. 3 , there are a smart phone 30 and a wearable device 31 with healthcare functions, such as a smart watch. In this embodiment, the feature extraction device 10 , the processor 11 , and the identifier 12 are disposed in the smart phone 30 , while the vital-sign detector 13 , the speaker 14 , the displayer 15 , and the physiological sensing device 16 are disposed in the smart watch 31 . The smart phone 30 transmits the bio-tags to the smart watch 31 in a wireless manner.

In the following paragraphs, the detail of the operation of the vital-sign detection device 13 will be described with reference to several embodiments.

According to an embodiment, the vital-sign detection device 13 stores a plurality of estimation models for cardiovascular diseases in the memory 130 . When vital-sign detection device 13 receives at least one of the bio-tags T 11 ˜T 14 , such as the bio-tag (age) T 11 and the bio-tag (gender) T 12 , and further receives the bio-signal S 16 C, the vital-sign detection device 13 selects one estimation model from the memory 130 according to the received bio-tags T 11 and T 12 and then estimates an index representing an incidence of cardiovascular diseases according to the bio-signal S 16 C related to the electrical activity of the heart by using the selected estimation model. The estimated index may be transmitted to the displayer 15 through a corresponding image signal S 13 B and shown on the displayer 15 .

In an embodiment where the user which is wearing, holding or contacting the physiological sensing device 16 is sleeping, when the vital-sign detection device 13 receives at least one of the bio-tags T 11 ˜T 14 and further receives the bio-signals S 16 A and S 16 B, the vital-sign detection device 13 selects one estimation model from the memory 130 according to the received bio-tag(s) and then estimates an index representing a sleep stage of the user according to the bio-signals S 16 A and S 16 B by using the selected estimation model. The estimated index may be transmitted to the displayer 15 through a corresponding image signal S 13 B and shown on the displayer 15 .

In another embodiment, when the vital-sign detection device 13 receives at least one of the bio-tags T 11 ˜T 14 and further receives at least one of the bio-signals S 16 B˜S 16 C, the vital-sign detection device 13 selects one estimation model from the memory 130 according to the received bio-tag(s) and then estimates a value representing the heart rate of the user or an index representing the heart rate variability of the user according to the at least one of the bio-signals S 16 B˜S 16 C by using the selected estimation model. The estimated value or index may be transmitted to the displayer 15 through a corresponding image signal S 13 B and shown on the displayer 15 .

In an embodiment, when the vital-sign detection device 13 receives at least one of the bio-tags T 11 ˜T 14 and further receives the bio-signals S 16 A˜S 16 B, the vital-sign detection device 13 selects one estimation model from the memory 130 according to the received bio-tag(s) and then estimates an index representing the atrial fibrillation of the user according to the bio-signals S 16 A˜S 16 B by using the selected estimation model. In another embodiment, an index representing the atrial fibrillation of the user can be estimated according to the bio-signal S 16 C. In detail, when the vital-sign detection device 13 receives at least one of the bio-tags T 11 ˜T 14 and further receives the bio-signal S 16 C, the vital-sign detection device 13 selects one estimation model from the memory 130 according to the received bio-tag(s) and then estimates an index representing the occurrence of the atrial fibrillation on the user according to the bio-signal S 16 C by using the selected estimation model. The estimated index may be transmitted to the displayer 15 through a corresponding image signal S 13 B and shown on the displayer 15 .

In an embodiment, when the SPO2 is connecting through the probe, when the vital-sign detection device 13 receives at least one of the bio-tags T 11 ˜T 14 and further receives the bio-signal S 16 D, the vital-sign detection device 13 selects one estimation model from the memory 130 according to the received bio-tag(s) and then estimates a value representing the blood oxygen saturation (SPO2) according to the bio-signal S 16 D by using the selected estimation model. The estimated value may be transmitted to the displayer 15 through a corresponding image signal S 13 B and shown on the displayer 15 .

FIG. 4 shows a flow chart of estimating a blood pressure according to the bio-signal(s) and bio-tag(s) according to an exemplary embodiment. The vital-sign detection device 13 stores a plurality of estimation models for blood pressures in the memory 130 . When vital-sign detection device 13 receives at least one of the bio-tags T 11 ˜T 14 (step S 40 ), such as the bio-tag (age) T 11 , the bio-tag (gender) T 12 , the bio-tag (body information) T 13 , and further receives the bio-signal S 16 B from the PPG sensor 16 B (step S 41 ), the vital-sign detection device 13 selects one estimation model from the memory 130 according to the received bio-tags T 11 ˜T 13 (step S 42 ) and then estimates the blood pressure according to the bio-signal S 16 B by using the selected estimation model (step S 43 ). The value of the blood pressure may be transmitted to the displayer 15 through an image signal S 13 B and shown on the displayer 15 . According to another embodiment, the memory 130 may store historical estimation models which were used in the previous estimation of the blood pressures of different users. In this embodiment, at the step S 42 , the vital-sign detection device 13 reads the historical estimation model for the previous estimation of the blood pressure of the user from the memory 130 according to the bio-tags T 11 ˜T 13 .

FIG. 5 shows a flow chart of estimating a body-fat percentage according to the bio-signal(s) and bio-tag(s) according to an exemplary embodiment. In an embodiment, the vital-sign detection device 13 stores a plurality of estimation models for body-fat percentages in the memory 130 . When vital-sign detection device 13 receives at least one of the bio-tags T 11 ˜T 14 (step S 50 ), such as the bio-tag (age) T 11 , the bio-tag (gender) T 12 , the bio-tag (body information) T 13 , and further receives the bio-signal S 16 D from the body-fat sensor 16 D (step S 51 ), the vital-sign detection device 13 selects one estimation model from the memory 130 according to the received bio-tags T 11 ˜T 13 (step S 52 ) and then estimates the body-fat percentage according to the bio-signal S 16 C by using the selected estimation model (step S 53 ). The value of the body-fat percentage may be transmitted to the displayer 15 through an image signal S 13 B and shown on the displayer 15 . After estimating the body-fat percentage, the vital-sign detection device 13 adjusts an upper threshold of a normal range according to the bio-tag (gender) T 12 (step S 54 ). The vital-sign detection device 13 determines whether the body-fat percentage is larger than the adjusted upper threshold (step S 55 ). In response to determining that the body-fat percentage is larger than the adjusted upper threshold, the vital-sign detection device 13 generates a control signal S 13 A to control the speaker 14 to play a warning sound.

FIG. 6 shows a flow chart of estimating an OSA risk according to the bio-signal(s) and bio-tag(s) according to an exemplary embodiment. In an embodiment, the vital-sign detection device 13 stores a plurality of estimation models for OSA risks in the memory 130 . When vital-sign detection device 13 receives at least one of the bio-tags T 11 ˜T 14 (step S 60 ), such as the bio-tag (age) T 11 , the bio-tag (gender) T 12 , the bio-tag (body information) T 13 , and the bio-tag (race) T 14 , and further receives the bio-signal S 16 A from the motion sensor 16 A (step S 61 ), the vital-sign detection device 13 selects one estimation model from the memory 130 according to the received bio-tags T 11 ˜T 14 (step S 62 ). For example, when the bio-tag (age) T 11 indicates that the age of the user is more than 40 years old, the bio-tag (gender) T 12 indicate that the user is a male, the bio-tag (body information) T 13 indicates that the weight of the user is great, and the bio-tag (race) T 14 indicates that the user is an Asian, the vital-sign detection device 13 selects a high-risk estimation model which includes a lower threshold. In other cases, the vital-sign detection device 13 may selects a low-risk estimation model. The vital-sign detection device 13 then estimates the OSA risk according to the bio-signal S 16 A by using the selected estimation model (step S 63 ). The value of the vital-sign detection device 13 may be transmitted to the displayer 15 through an image signal S 13 B and shown on the displayer 15 . After estimating the body-fat percentage, the vital-sign detection device 13 determines whether the OSA risk is larger than the threshold of the selected estimation model. In response to determining that the OSA risk is larger than the threshold, the vital-sign detection device 13 generates a control signal S 13 A to control the speaker 14 to play a warning sound.

According to an embodiment, the memory 130 may store databases of different users. Each database comprises the historical estimation models and/or the historical parameters which were used in the previous estimation of the vital-sign data of a user and further comprises the historical vital-sign data which was estimated in the previous estimation. When the physiological monitoring system 1 operates to estimate vital-sign data of a user, the vital-sign detection device 13 may access a database exclusive to the user from the memory 130 according to at least one bio-tag of the user. Thus, the user can estimate vital-sign data by referring to the historical estimation model or parameters and by taking the historical vital-sign data as reference data, thereby enhancing of the accuracy of the estimation of the vital-sign data. Moreover, each time the vital-sign detection device 13 estimates vital-sign data of a user, the vital-sign detection device 13 stores the estimated vital-sign data into a database exclusive to the user which is determined according to at least one bio-tag of the user.

While the invention has been described by way of example and in terms of the preferred embodiments, it is to be understood that the invention is not limited to the disclosed embodiments. On the contrary, it is intended to cover various modifications and similar arrangements (as would be apparent to those skilled in the art). Therefore, the scope of the appended claims should be accorded the broadest interpretation so as to encompass all such modifications and similar arrangements.