DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-2, 4-6, 15-16, 18-19, and 24 are rejected under 35 U.S.C. 103 as being unpatentable over WO 2016/053444 Oliver et al., hereinafter “Oliver” (cited previously), in view of US 2017/0196497 Ray et al., hereinafter “Ray”.
Regarding claim 1, Oliver discloses a method of determining physiological characteristics (Abstract and Para 17), the method comprising: obtaining an electromyography (EMG) signal representing muscle activity (Figure 1, element 1, Para 5, 17, and Abstract) from an EMG electrode disposed in or on a band of a wrist-worn device (Figure 2 shows wrist worn device 7 and EMG electrodes 8), and a photoplethysmography (PPG) signal (Figure 1, element 2 RAW PPG signal) using a PPG sensor (Figure 2, element 9) of the wrist-worn device (Figure 2, element 7); providing the EMG signal (Para 17); generating, an output signal (Para 17); generating a modified PPG signal by subtracting the output signal generated from the PPG signal (Figure 1, element 5 and Para 17), wherein the modified PPG signal corrects for motion artifacts in the PPG signal due to motion activity of a wearer of the wrist-worn device (Para 17); wherein obtaining the EMG signal provided to the processor (Para 17) for generating the modified PPG signal (Figure 1, element 5 and Para 17) includes selecting at least one EMG electrode from more than two EMG electrodes disposed in or on the band of the wrist- worn device (Figure 2, elements 8 at least 4 EMG are shown; Para 9, signals are captured using all the electrodes, therefore at least one electrode signal is selected and fed into pre-processing Figure 1, element 3); and determining at least one physiological characteristic based on the modified PPG signal (Figure 1, elements 6 and Para 17).
Oliver does not disclose a machine learning model that processes EMG signals and generates a modified PPG signal.
However, Ray discloses a method of determining physiological characteristics (Abstract) and teaches a machine learning model that processes EMG signals and generates a modified PPG signal (Para 30, 38, 41; see also Figure 1, element 154; Ray discloses what the claims state; an EMG signal is provided to a machine learning model, an output is generated and a modified PPG signal is generated by the machine learning model using the output signal, Examiner suggests amending the claim to state that the output signal is directly correlated to the EMG signal that is provided, under BRI the output signal can have nothing to do with the EMG as the claims are currently written. The claims do not state that the output signal is a result of the EMG signal provided; Ray uses output signals from motion detectors that are also fed into the machine learning model. An amendment like suggested would overcome the prior art).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed machine learning as taught by Ray, in the invention of Oliver, in order to perform the method using learnt data, thereby improving accuracy and efficiency (Ray; Para 41).
Regarding claim 2, Oliver discloses the at least one physiological characteristic is at least one of: a heart rate of the wearer, a blood pressure of the wearer, or an oxygen saturation of the wearer (Figure 1, elements 6 and Para 17).
Regarding claim 4, Oliver discloses the motion activity of the wearer comprises finger movements (Para 18).
Regarding claim 5, Oliver discloses an inertial measurement unit (IMU) of the wrist-worn device reports less motion activity than that associated with the EMG signal obtained (Para 4 and 22; sEMG signal as a reference outperforms using the accelerometer).
Regarding claim 6, Oliver discloses the EMG electrode is disposed proximate to an artery of the wearer of the wrist-worn device, and wherein the artery is one of an ulnar artery or a radial artery (Figure 2 shows the device on the inside of the wrist. There are multiple EMG electrodes 8 disposed on the entire wrist band, it is inherent that these electrodes are proximal to the radial or ulnar arteries which are known to be part of the wrist of a user).
Regarding claim 15, Oliver discloses a wrist-worn device (Abstract and Para 17 and Figure 2, element 7), the wrist-worn device comprising: at least one electromyography (EMG) electrode (Figure 2 shows wrist worn device 7 and EMG electrodes 8) configured to generate EMG signals (Figure 1, element 1, Para 5, 17, and Abstract); at least one photoplethysmography (PPG) sensor (Figure 2, element 9) configured to generate PPG signals (Figure 1, element 2 RAW PPG signal); and at least one controller (Para 19 and Figure 1, element 3) configured to: obtain an EMG signal representing muscle activity from the at least one EMG electrode disposed in or on a band of the wrist-worn device (Figure 1, element 1, Para 5, 17, and Abstract), and a PPG signal using the at least one PPG sensor of the wrist-worn device (Figure 1, element 2 RAW PPG signal), providing the EMG signal and the PPG signal (Para 17), generate a modified PPG signal (Figure 1, element 5 and Para 17), wherein the modified PPG signal corrects for motion artifacts in the PPG signal due to motion activity of a wearer of the wrist-worn device (Para 17), and determine at least one physiological characteristic based on the modified PPG signal (Figure 1, elements 6 and Para 17).
Oliver does not disclose a machine learning model that processes the signals; the machine learning model trained on (1) training PPG signals that include motion artifacts, (2) training EMG signals, and (3) ground truth PPG signals that correspond to the modified PPG signals.
However, Ray discloses a system for obtaining a PPG signal that can identify motion artifacts (Abstract) and teaches a machine learning model that processes the signals (Para 30, 38, 41; see also Figure 1, element 154; Ray discloses what the claims state; an EMG signal is provided to a machine learning model, an output is generated and a modified PPG signal is generated by the machine learning model using the output signal, Examiner suggests amending the claim to state that the output signal is directly correlated to the EMG signal that is provided, under BRI the output signal can have nothing to do with the EMG as the claims are currently written. The claims do not state that the output signal is a result of the EMG signal provided; Ray uses output signals from motion detectors that are also fed into the machine learning model. An amendment like suggested would overcome the prior art); the machine learning model trained on (1) training PPG signals that include motion artifacts (Para 30 and 38), (2) training EMG signals (Para 30 and 38), and (3) ground truth PPG signals that correspond to the modified PPG signals (Para 41; “using active learning—an approach that incorporates new labeled data to improve a classifier over time” therefore the modified PPG from Para 30 would be incorporated to retrain the model).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed machine learning as taught by Ray, in the invention of Oliver, in order to perform the method using learnt data, thereby improving accuracy and efficiency (Ray; Para 41).
Regarding claim 16, Oliver discloses the at least one physiological characteristic is at least one of: a heart rate of the wearer, a blood pressure of the wearer, or an oxygen saturation of the wearer (Figure 1, elements 6 and Para 17).
Regarding claim 18, Oliver discloses the motion activity of the wearer comprises finger movements (Para 18).
Regarding claim 19, Oliver discloses an inertial measurement unit (IMU) of the wrist-worn device reports less motion activity than that associated with the EMG signal obtained (Para 4 and 22; sEMG signal as a reference outperforms using the accelerometer).
Regarding claim 24, Oliver discloses all the limitations of claim 1.
Oliver does not disclose the machine learning model is trained on training EMG signals and corresponding ground truth signals indicating a signal to be subtracted out of the PPG signal.
However, Ray teaches the machine learning model is trained on training EMG signals (Para 30 and 38) and corresponding ground truth signals indicating a signal to be subtracted out of the PPG signal (Para 41; “using active learning—an approach that incorporates new labeled data to improve a classifier over time” therefore the modified PPG from Para 30 would be incorporated to retrain the model).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed machine learning as taught by Ray, in the invention of Oliver, in order to perform the method using learnt data, thereby improving accuracy and efficiency (Ray; Para 41).
Claim(s) 3 and 21 are rejected under 35 U.S.C. 103 as being unpatentable over WO 2016/053444 Oliver et al., hereinafter “Oliver”, in view of US 2017/0196497 Ray et al., hereinafter “Ray”, further in view of US 2015/0182160 Kim et al., hereinafter “Kim” (cited previously).
Regarding claim 3, Oliver discloses the muscle activity (Figure 1, element 1, Para 5, 17, and Abstract).
Oliver does not disclose activity from at least one wrist extensor muscle or at least one wrist flexor muscle.
However, Kim discloses a method/device that utilizes motion extraction using an EMG signal (Abstract and Para 86) and teaches activity from at least one wrist extensor muscle or at least one wrist flexor muscle (Para 53 and 67).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed activity from at least one wrist extensor muscle or at least one wrist flexor muscle as taught by Kim, in the invention of Oliver, in order to extract hand motions by signal analysis and obtain a clearer, noise-free signal (Kim; Para 53 and 86).
Regarding claim 21, Oliver discloses reporting of the physiological characteristics (Para 19).
Oliver does not disclose reporting of the physiological characteristic includes inhibiting presentation of an indication of the physiological characteristic.
However, Kim teaches reporting of the physiological characteristic includes inhibiting presentation of an indication of the physiological characteristic (Figure 14 shows data displayed, Para 208 discloses that the screen is adjusted based on user selections, so a user can choose to inhibit the presentation of an indication by clicking discard as shown in Figure 14).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed inhibiting presentation as taught by Kim, in the invention of Oliver, in order to preset a user’s selection (Kim; Para 208).
Claim(s) 9-11, 14, and 25 are rejected under 35 U.S.C. 103 as being unpatentable over WO 2016/053444 Oliver et al., hereinafter “Oliver”, in view of US 2019/0286233 Newberry, hereinafter “Newberry”, further in view of US 2017/0196497 Ray et al., hereinafter “Ray”.
Regarding claim 9, Oliver discloses a method of determining physiological characteristics (Abstract and Para 17), the method comprising: obtaining an electromyography (EMG) signal representing muscle activity (Figure 1, element 1, Para 5, 17, and Abstract) from an electromyography (EMG) electrode disposed in or on a band of a wrist-worn device (Figure 2 shows wrist worn device 7 and EMG electrodes 8), and a photoplethysmography (PPG) signal (Figure 1, element 2 RAW PPG signal) using a PPG sensor (Figure 2, element 9) of the wrist-worn device (Figure 2, element 7); characterizing motion activity of a wearer of the wrist-worn device based on the EMG signal (Figure 1, element 5 and Para 17); wherein characterizing the motion activity includes determining a type of motion activity (Para 18 discloses determining through the sEMG the difference in motion between finger flexion vs. extension); and reporting a physiological characteristic determined using the PPG signal (Figure 1, elements 6 and Para 17; elements 6 are determined by using motion activity that was subtracted from signals 2 to obtain a motion compensation signal 5).
Oliver does not disclose reporting a physiological characteristic determined based at least in part on the type of the motion activity of the wearer.
However, Newberry teaches reporting a physiological characteristic determined based at least in part on the type of the motion activity of the wearer (Para 79; One or more of the predetermined PPG patterns are recognized in the detected PPG signal and Control commands may be mapped to the motion data to generate an input to a device).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed a physiological characteristic determined based at least in part on the type of the motion activity of the wearer as taught by Newberry, in the invention of Oliver, in order to map the motion to the physiological characteristic thereby enabling motion artifact isolation (Newberry; Para 79 and 113).
Oliver does not disclose providing the EMG signal to a machine learning model.
However, Ray discloses a method of determining physiological characteristics (Abstract) and teaches providing the EMG signal to a machine learning model (Para 30, 38, 41; see also Figure 1, element 154; Ray discloses what the claims state; an EMG signal is provided to a machine learning model).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed machine learning as taught by Ray, in the invention of Oliver, in order to perform the method using learnt data, thereby improving accuracy and efficiency (Ray; Para 41).
Regarding claim 10, Oliver discloses the physiological characteristic is at least one of: a heart rate of the wearer, a blood pressure of the wearer, or an oxygen saturation of the wearer (Figure 1, elements 6 and Para 17).
Regarding claim 11, Oliver discloses determining a manner in which the physiological characteristic is to be reported based on a type of physiological characteristic (Claim 18; the physiological signals may or may not be displayed).
Regarding claim 14, Oliver discloses all the limitations of claim 13.
Oliver does not disclose comparing the PPG signal to an expected PPG signal selected based on the type of motion activity to form a comparison, wherein the reporting of the physiological characteristic is based on the comparison of the PPG signal to the expected PPG signal.
However, Newberry discloses a system for obtaining a PPG signal that can identify motion artifacts (Abstract) and teaches comparing the PPG signal to an expected PPG signal selected based on the type of motion activity to form a comparison (Para 8), wherein the reporting of the physiological characteristic is based on the comparison of the PPG signal to the expected PPG signal (Para 7 and 8).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed comparing the PPG signal to an expected PPG signal as taught by Newberry, in the invention of Oliver, in order to isolate the motion artifacts in the PPG signal (Newberry; Para 113).
Regarding claim 25, Oliver discloses reporting of the physiological characteristic includes reporting heart rate measurements and inhibiting presentation of blood pressure measurements or oxygen saturation measurements (Claims 18 and 20 disclose displaying at least one physiological parameter; therefore, the user can choose to display the HR and inhibit the display of BP or SP02 shown in Figure 1, element 6).
Oliver does not disclose reporting heart rate measurements with a warning.
However, Newberry teaches reporting heart rate measurements with a warning (Para 177-178).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed an alert for heart rate measurements as taught by Newberry, in the invention of Oliver, in order to alert the user when a heart rate passes a threshold (Newberry; Para 177-178).
Claim(s) 12 is rejected under 35 U.S.C. 103 as being unpatentable over WO 2016/053444 Oliver et al., hereinafter “Oliver”, in view of US 2019/0286233 Newberry, hereinafter “Newberry”, further in view of US 2017/0196497 Ray et al., hereinafter “Ray”, further in view of WO 2022/146883 Lokare et al., hereinafter “Lokare” (cited previously).
Regarding claim 12, Oliver discloses reporting of the physiological characteristic (Claim 18).
Oliver does not disclose presenting an indication of the physiological characteristic with a warning indicating that the reported physiological characteristic may be inaccurate.
However, Lokare discloses a system/method of generating biometric information for a user using PPG data (Abstract) and teaches presenting an indication of the physiological characteristic with a warning indicating that the reported physiological characteristic may be inaccurate (Page 31, lines 17-31).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed an indication of inaccuracy as taught by Lokare, in the invention of Oliver, in order to notify the user of an abnormal physiological parameter (Lokare; Page 31, lines 17-31).
Claim 22 is rejected under 35 U.S.C. 103 as being unpatentable over WO 2016/053444 Oliver et al., hereinafter “Oliver”, in view of US 2017/0196497 Ray et al., hereinafter “Ray”, further in view of WO 2022/146883 Lokare et al., hereinafter “Lokare” (cited previously).
Regarding claim 22, Oliver discloses reporting of the physiological characteristic (Claim 18).
Oliver does not disclose presenting an indication of the physiological characteristic with a warning indicating that the reported physiological characteristic may be inaccurate.
However, Lokare discloses a system/method of generating biometric information for a user using PPG data (Abstract) and teaches presenting an indication of the physiological characteristic with a warning indicating that the reported physiological characteristic may be inaccurate (Page 31, lines 17-31).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed an indication of inaccuracy as taught by Lokare, in the invention of Oliver, in order to notify the user of an abnormal physiological parameter (Lokare; Page 31, lines 17-31).
Claim 23 is rejected under 35 U.S.C. 103 as being unpatentable over WO 2016/053444 Oliver et al., hereinafter “Oliver”, in view of US 2019/0286233 Newberry, hereinafter “Newberry”, further in view of US 2017/0196497 Ray et al., hereinafter “Ray”, further in view of US 2015/0182160 Kim et al., hereinafter “Kim” (cited previously).
Regarding claim 23, Oliver discloses reporting of the physiological characteristic (Para 19) and includes modifying the reporting based on the characterization of the motion activity presentation of an indication of the physiological characteristic based on the type of motion activity that was determined in the characterization of the motion activity (Para 18).
However, Kim teaches inhibiting presentation of an indication of the physiological characteristic (Figure 14 shows data displayed, Para 208 discloses that the screen is adjusted based on user selections, so a user can choose to inhibit the presentation of an indication by clicking discard as shown in Figure 14).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed inhibiting presentation as taught by Kim, in the invention of Oliver, in order to preset a user’s selection (Kim; Para 208).
Response to Arguments
Applicant’s arguments have been considered but are moot because the new ground of rejection.
Kindly refer to the rejection above for the newly rejected claims and a suggestion to overcome the prior art.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AYA ZIAD BAKKAR whose telephone number is (313)446-6659. The examiner can normally be reached on 7:30 am - 5:00 pm M-Th.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Carl Layno can be reached on (571) 272-4949. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/AYA ZIAD BAKKAR/
Examiner, Art Unit 3796
/CARL H LAYNO/Supervisory Patent Examiner, Art Unit 3796
Prosecution Insights