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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after allowance or after an Office action under Ex Parte Quayle, 25 USPQ 74, 453 O.G. 213 (Comm'r Pat. 1935). Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, prosecution in this application has been reopened pursuant to 37 CFR 1.114. Applicant's submission filed on April 1, 2026 has been entered.
Allowable Subject Matter
The indicated allowability of claims 1, 4-20, 22, and 24-25 is withdrawn in view of the newly discovered references to “Blood pressure and its variability: classic and novel measurement techniques” (Schutte et al.) and US 20190298195 A1 (De Groot et al.). Rejections based on the newly cited references follow.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 26 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 26 is written as an incomplete sentence by reciting “using a first machine learning model configured to generate.” (lines 2-3), which renders the claim indefinite. What is being generated by the first machine learning model (i.e. the estimates or other data related to the estimates)? Further clarification is required.
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.
Claims 1, 4, 8-9, 11-13, 18-20, 22, and 25-34 are rejected under 35 U.S.C. 103 as being unpatentable over US 20190298195 A1 (De Groot et al.) in view of “Blood pressure and its variability: classic and novel measurement techniques” (Schutte et al.) further in view of US 20190104951 A1(Valys et al.).
Regarding claim 1, De Groot teaches an electronic device comprising:
an optical sensor ([0004] “photoplethysmographic (PPG) sensor”; [0021] “PPG sensor 104”);
a motion sensor ([0021] “motion sensor 106”); and
processing circuitry coupled to the optical sensor and the motion sensor ([0021] “processing circuitry 110”), the processing circuitry configured to:
generate a plurality of estimates of hypertension scores or parameters indicative of hypertension scores, each respective estimate of the plurality of estimates of hypertension scores or parameters indicative of the hypertension scores is generated for a first duration of a first period using a respective segment of data from the optical sensor and the motion sensor, wherein the first duration of the first period is a portion of a day ([0079] “store each blood pressure prediction for every 30 second epoch of PPG signal data”);
in accordance with a determination that a threshold number of plurality of estimates has been generated for a second duration of a second period, generate an aggregated hypertension score using the plurality of estimates, wherein the aggregated hypertension score is indicative of a hypertension score for a second duration of a second period ([0061] “In some embodiments, blood pressure determination component 224 is configured to aggregate the 30 second windows of PPG signal data throughout a 24 hour period to determine a blood pressure dip for the day.”; [0079] “blood pressure dip determination is performed by causing prediction model 424 to store each blood pressure prediction for every 30 second epoch of PPG signal data, along with awake/asleep conditions determined by physical state component 322. Responsive to aggregating a full 24 hour period of blood pressure predictions for individual PPG signal epochs, in some embodiments, prediction model 424 is caused to split the data into two categories”)
De Groot does not explicitly teach wherein the second duration of the second period is two days or more; in accordance with the aggregated hypertension score exceeding a threshold, generate a notification about possible hypertension and cause the notification to be output to a health application or to one or more output devices; and in accordance with the aggregated hypertension score failing to exceed the threshold, forgo generating the notification and forgoing causing the notification to be output to the health application or to the one or more output devices.
However,
Schutte teaches wherein the second duration of the second period is two days or more (BP snapshots versus BP profile - Page 646, Col. 1, “an average of HBPM readings taken for multiple days (at least 3 days with at least 12 readings)”).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the invention to have modified the device taught by De Groot to include aggregating hypertension scores from two days or more. One would have been motivated to make this modification because evaluating blood pressure over days provides more reliable data, as suggested by Schutte (Conclusions – Page 652, Col. 2).
Valys teaches in accordance with the aggregated hypertension score exceeding a threshold, generate a notification about possible hypertension and cause the notification to be output to a health application or to one or more output devices ([0026] “alerting or prompting the user to take an action if the difference between the predicted future time sequence and measured time sequences exceeds a threshold or criteria”; [0044] “exceeds a threshold, the user is notified his or her health-indicator data is not in a normal or healthy range”); and
in accordance with the aggregated hypertension score failing to exceed the threshold, forgo generating the notification and forgoing causing the notification to be output to the health application or to the one or more output devices ([0044] “exceeds a threshold, the user is notified his or her health-indicator data is not in a normal or healthy range”; Fig. 8; The user is only notified when the data exceeds a threshold).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the invention to have modified the device taught by De Groot to include generating notifications if the aggregated score is above a threshold. One would have been motivated to make this modification because notifying the user that a health indicator is not in a healthy range can aid in alerting the user to contact a health professional and inform diagnoses and future instructions, as suggested by Valys [0024-0025, 0029].
Regarding claim 4, De Groot teaches the electronic device of claim 1, wherein the processing circuitry comprises a first machine learning model configured to generate the plurality of estimates of hypertension scores or parameters indicative of the hypertension scores ([0005] “a method for determining blood pressure dip in a subject via machine learning models”; [0066] “BP prediction model is and/or includes machine learning models and/or algorithms, neural networks, and/or other prediction models”).
Regarding claim 8, De Groot teaches the electronic device of claim 1, wherein generating the aggregated hypertension score comprises computing statistical parameters using the plurality of estimates and generating the aggregated hypertension score using the statistical parameters ([0032-0034] “other statistics of the 24 hour ambulatory blood pressure readings are determined, including but not limited to blood-pressure variability, hyperbaric area index, minimum nocturnal blood pressure, morning surge, and/or other ambulatory blood pressure readings.”).
Regarding claim 9, De Groot teaches the electronic device of claim 1, the processing circuitry further configured to divide the respective segment of data from the optical sensor and the motion sensor into one or more pulse windows ([0043] “localization component 312 is configured to reject low-quality beats based on the morphology of the PPG pulses (e.g., ambient light) and registered motion (e.g., motion artifact) represented by the motion signal”).
Regarding claim 11, De Groot teaches the electronic device of claim 9, wherein the processing circuitry comprises a machine learning model configured to generate the plurality of estimates of hypertension scores or parameters indicative of the hypertension scores ([0005] “a method for determining blood pressure dip in a subject via machine learning models”; [0066] “BP prediction model is and/or includes machine learning models and/or algorithms, neural networks, and/or other prediction models”).
Regarding claim 12, De Groot teaches the electronic device of claim 11, wherein generating the respective estimate of the plurality of estimates of hypertension scores or parameters indicative of the hypertension scores using the respective segment of data from the optical sensor and the motion sensor comprises:
inputting a plurality of the pulse windows into the machine learning model to generate a feature vector of hypertension parameters for each of the plurality of the pulse windows ([0057-0058] “Feature extraction using HMMs comprises implementing a variety of wavelet transformation, frequency matching, and spectral analysis to extract feature vectors. In some embodiments, feature vectors are extracted every 10 ms (for example) using an overlapping analysis window of around 25 ms (for example)”); and
averaging the feature vectors for the plurality of the pulse windows to generate an aggregated feature vector for the respective segment ([0058] “each 30 second portion of the PPG signal is decomposed into a sequence of feature vectors. While HMMs are suited for feature extraction of features vectors for determining changing characteristics of the PPG signal over a period of time”; [0061]).
Regarding claim 13, De Groot teaches the electronic device of claim 12.
De Groot does not explicitly teach wherein generating the respective estimate of the plurality of estimates of hypertension scores or parameters indicative of the hypertension scores using the respective segment of data from the optical sensor and the motion sensor comprises: transforming the aggregated feature vector for the respective segment to generate the respective estimate with a scalar value.
However,
Valys teaches wherein generating the respective estimate of the plurality of estimates of hypertension scores or parameters indicative of the hypertension scores using the respective segment of data from the optical sensor and the motion sensor comprises: transforming the aggregated feature vector ([0051]) for the respective segment to generate the respective estimate with a scalar value ([0035] “the output could be a scalar value data point being predicted by the network”).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the invention to have modified the device taught by De Groot to include transforming a feature vector to generate a scalar value. One would have been motivated to make this modification because scalar values can be used to predict data over time, as suggested by Valys ([0051]).
Regarding claim 18, De Groot teaches the electronic device of claim 1, wherein generating the aggregated hypertension score comprises averaging the plurality of estimates to generate the aggregated hypertension score ([0032-0034] “average daytime values”; [0079] “average blood diurnal and nocturnal blood pressure”).
Regarding claim 19, De Groot teaches a method comprising:
generating a plurality of estimates of hypertension scores or parameters indicative of hypertension scores, each respective estimate of the plurality of estimates of hypertension scores or parameters indicative of the hypertension scores is generated for a first duration of a first period using a respective segment of data from an optical sensor and a motion sensor, wherein the first duration of the first period is a portion of a day ([0021] “PPG sensor 104 … motion sensor 106”; [0079] “store each blood pressure prediction for every 30 second epoch of PPG signal data”);
in accordance with a determination that a threshold number of plurality of estimates has been generated for a second duration of a second period, generating an aggregated hypertension score using the plurality of estimates, wherein the aggregated hypertension score is indicative of a hypertension score for a second duration of a second period ([0061] “In some embodiments, blood pressure determination component 224 is configured to aggregate the 30 second windows of PPG signal data throughout a 24 hour period to determine a blood pressure dip for the day.”; [0079] “blood pressure dip determination is performed by causing prediction model 424 to store each blood pressure prediction for every 30 second epoch of PPG signal data, along with awake/asleep conditions determined by physical state component 322. Responsive to aggregating a full 24 hour period of blood pressure predictions for individual PPG signal epochs, in some embodiments, prediction model 424 is caused to split the data into two categories”).
De Groot does not teach wherein the second duration of the second period is two days or more; in accordance with the aggregated hypertension score exceeding a threshold, generating a notification about possible hypertension and cause the notification to be output to a health application or to one or more output devices; and in accordance with the aggregated hypertension score failing to exceed the threshold, forgoing generating the notification and forgoing causing the notification to be output to the health application or to the one or more output devices.
However,
Schutte teaches wherein the second duration of the second period is two days or more (BP snapshots versus BP profile - Page 646, Col. 1, “an average of HBPM readings taken for multiple days (at least 3 days with at least 12 readings)”).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the invention to have modified the method taught by De Groot to include aggregating hypertension scores from two days or more. One would have been motivated to make this modification because evaluating blood pressure over days provides more reliable data, as suggested by Schutte (Conclusions – Page 652, Col. 2).
Valys teaches in accordance with the aggregated hypertension score exceeding a threshold, generate a notification about possible hypertension and cause the notification to be output to a health application or to one or more output devices ([0026] “alerting or prompting the user to take an action if the difference between the predicted future time sequence and measured time sequences exceeds a threshold or criteria”; [0044] “exceeds a threshold, the user is notified his or her health-indicator data is not in a normal or healthy range”); and
in accordance with the aggregated hypertension score failing to exceed the threshold, forgo generating the notification and forgoing causing the notification to be output to the health application or to the one or more output devices ([0044] “exceeds a threshold, the user is notified his or her health-indicator data is not in a normal or healthy range”; Fig. 8; The user is only notified when the data exceeds a threshold).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the invention to have modified the method taught by De Groot to include generating notifications if the aggregated score is above a threshold. One would have been motivated to make this modification because notifying the user that a health indicator is not in a healthy range can aid in alerting the user to contact a health professional and inform diagnoses and future instructions, as suggested by Valys [0024-0025, 0029].
Regarding claim 20, De Groot teaches a non-transitory computer readable storage medium storing instructions, which when executed by a device comprising processing circuitry ([0037] “erver 305 includes processing component 306, which is configured via machine-readable instructions (e.g., server code 319) to execute one or more computer program components”), cause the processing circuitry to:
generate a plurality of estimates of hypertension scores or parameters indicative of hypertension score, each respective estimate of the plurality of estimates of hypertension scores or parameters indicative of the hypertension scores is generated for a first duration of a first period using a respective segment of data from an optical sensor and a motion sensor, wherein the first duration of the first period is a portion of a day ([0021] “PPG sensor 104 … motion sensor 106”; [0079] “store each blood pressure prediction for every 30 second epoch of PPG signal data”);
in accordance with a determination that a threshold number of plurality of estimates has been generated for a second duration of a second period, generate an aggregated hypertension score using the plurality of estimates, wherein the aggregated hypertension score is indicative of a hypertension score for a second duration of a second period ([0061] “In some embodiments, blood pressure determination component 224 is configured to aggregate the 30 second windows of PPG signal data throughout a 24 hour period to determine a blood pressure dip for the day.”; [0079] “blood pressure dip determination is performed by causing prediction model 424 to store each blood pressure prediction for every 30 second epoch of PPG signal data, along with awake/asleep conditions determined by physical state component 322. Responsive to aggregating a full 24 hour period of blood pressure predictions for individual PPG signal epochs, in some embodiments, prediction model 424 is caused to split the data into two categories”).
De Groot does not teach wherein the second duration of the second period is two days or more; in accordance with the aggregated hypertension score exceeding a threshold, generate a notification about possible hypertension and cause the notification to be output to a health application or to one or more output devices; and in accordance with the aggregated hypertension score failing to exceed the threshold, forgo generating the notification and forgoing causing the notification to be output to the health application or to the one or more output devices.
However,
Schutte teaches wherein the second duration of the second period is two days or more (BP snapshots versus BP profile - Page 646, Col. 1, “an average of HBPM readings taken for multiple days (at least 3 days with at least 12 readings)”).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the invention to have modified the invention taught by De Groot to include aggregating hypertension scores from two days or more. One would have been motivated to make this modification because evaluating blood pressure over days provides more reliable data, as suggested by Schutte (Conclusions – Page 652, Col. 2).
Valys teaches in accordance with the aggregated hypertension score exceeding a threshold, generate a notification about possible hypertension and cause the notification to be output to a health application or to one or more output devices ([0026] “alerting or prompting the user to take an action if the difference between the predicted future time sequence and measured time sequences exceeds a threshold or criteria”; [0044] “exceeds a threshold, the user is notified his or her health-indicator data is not in a normal or healthy range”); and
in accordance with the aggregated hypertension score failing to exceed the threshold, forgo generating the notification and forgoing causing the notification to be output to the health application or to the one or more output devices ([0044] “exceeds a threshold, the user is notified his or her health-indicator data is not in a normal or healthy range”; Fig. 8; The user is only notified when the data exceeds a threshold).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the invention to have modified the invention taught by De Groot to include generating notifications if the aggregated score is above a threshold. One would have been motivated to make this modification because notifying the user that a health indicator is not in a healthy range can aid in alerting the user to contact a health professional and inform diagnoses and future instructions, as suggested by Valys [0024-0025, 0029].
Regarding claim 22, De Groot teaches the electronic device of claim 1, the processing circuitry further configured to:
after generating the aggregated hypertension score:
generate a second plurality of estimates of hypertension scores or parameters indicative of the hypertension scores, different from the plurality of estimates of hypertension scores or parameters indicative of the hypertension scores, each respective estimate of the second plurality of estimates of hypertension scores or parameters indicative of the hypertension scores generated using a respective segment of data from the optical sensor and the motion sensor ([0033] “In some embodiments the morning surge is calculated or determined by analyzing the increase in blood pressure in the first 2 hours of wake up compared to baseline measures from the last day.); and
generate a second aggregated hypertension score using the second plurality of estimates ([0061] “blood pressure determination component 224 is configured to aggregate the 30 second windows of PPG signal data throughout a 24 hour period to determine a blood pressure dip for the day. In some embodiments, determining the blood pressure dip for the day is also based on the physical state (e.g., asleep or awake) of the subject.”; [0079] “For each given day, the blood pressure dip is then output by processing component 306. In some embodiments, the blood pressure dip is categorized as either dipping, non-dipping, extreme dipping, or reverse dipping, as discussed above.”).
Regarding claim 25, De Groot teaches the method of claim 19, wherein generating the plurality of estimates of hypertension scores or parameters indicative of hypertension score is performed at a wearable device and wherein generating an aggregated hypertension score using the using the plurality of estimates is performed by a second device in communication with the wearable device ([0026] “PPG sensor 104 and motion sensor 106 are configured to communicate PPG signals and motion signals to server 105 and/or other devices via processing circuitry 110 and/or other components”; [0028]).
Regarding claim 26, De Groot teaches the method of claim 19, wherein the plurality of estimates of hypertension scores or parameters indicative of the hypertension scores are generated using a first machine learning model configured to generate ([0005] “a method for determining blood pressure dip in a subject via machine learning models”; [0066] “BP prediction model is and/or includes machine learning models and/or algorithms, neural networks, and/or other prediction models”).
Regarding claim 27, De Groot teaches the method of claim 26, wherein the aggregated hypertension score is generated using a second machine learning model ([0004] “a system for determining blood pressure dip in a subject via machine learning models.”; [0066] “the BP prediction model is and/or includes machine learning models and/or algorithms, neural networks, and/or other prediction models”).
Regarding claim 28, De Groot teaches the method of claim 19, wherein generating the aggregated hypertension score comprises computing statistical parameters using the plurality of estimates and generating the aggregated hypertension score using the statistical parameters ([0032-0034] “other statistics of the 24 hour ambulatory blood pressure readings are determined, including but not limited to blood-pressure variability, hyperbaric area index, minimum nocturnal blood pressure, morning surge, and/or other ambulatory blood pressure readings.”).
Regarding claim 29, De Groot teaches the method of claim 19, further comprising:
dividing the respective segment of data from the optical sensor and the motion sensor into one or more pulse windows ([0043] “localization component 312 is configured to reject low-quality beats based on the morphology of the PPG pulses (e.g., ambient light) and registered motion (e.g., motion artifact) represented by the motion signal”).
Regarding claim 30, De Groot teaches the method of claim 29, wherein the plurality of estimates of hypertension scores or parameters indicative of the hypertension scores is generated using a machine learning model ([0005] “a method for determining blood pressure dip in a subject via machine learning models”; [0066] “BP prediction model is and/or includes machine learning models and/or algorithms, neural networks, and/or other prediction models”).
Regarding claim 31, De Groot teaches the method of claim 30, wherein generating the respective estimate of the plurality of estimates of hypertension scores or parameters indicative of the hypertension scores using the respective segment of data from the optical sensor and the motion sensor comprises:
inputting a plurality of the pulse windows into the machine learning model to generate a feature vector of hypertension parameters for each of the plurality of the pulse windows ([0057-0058] “Feature extraction using HMMs comprises implementing a variety of wavelet transformation, frequency matching, and spectral analysis to extract feature vectors. In some embodiments, feature vectors are extracted every 10 ms (for example) using an overlapping analysis window of around 25 ms (for example)”); and
averaging the feature vectors for the plurality of the pulse windows to generate an aggregated feature vector for the respective segment ([0058] “each 30 second portion of the PPG signal is decomposed into a sequence of feature vectors. While HMMs are suited for feature extraction of features vectors for determining changing characteristics of the PPG signal over a period of time”; [0061]).
Regarding claim 32, De Groot teaches the method of claim 19, wherein generating the aggregated hypertension score comprises averaging the plurality of estimates to generate the aggregated hypertension score ([0032-0034] “average daytime values”; [0079] “average blood diurnal and nocturnal blood pressure”).
Regarding claim 33, De Groot teaches the non-transitory computer readable storage medium of claim 20, when executed by the device, further causing the processing circuitry to:
Divide the respective segment of data from the optical sensor and the motion sensor into one or more pulse windows ([0043] “localization component 312 is configured to reject low-quality beats based on the morphology of the PPG pulses (e.g., ambient light) and registered motion (e.g., motion artifact) represented by the motion signal”).
Regarding claim 34, De Groot teaches the non-transitory computer readable storage medium of claim 20, wherein the processing circuitry comprises a machine learning model configured to generate the plurality of estimates of hypertension scores or parameters indicative of the hypertension scores ([0005] “a method for determining blood pressure dip in a subject via machine learning models”; [0066] “BP prediction model is and/or includes machine learning models and/or algorithms, neural networks, and/or other prediction models”).
Claims 5-7, 10, and 14-17 are rejected under 35 U.S.C. 103 as being unpatentable over US 20190298195 A1 (De Groot et al.) in view of “Blood pressure and its variability: classic and novel measurement techniques” (Schutte et al.), further in view of US 20190104951 A1 (Valys et al.), further in view of US 20170181649 A1 (Carter et al.).
Regarding claim 5, De Groot teaches the electronic device of claim 4, with the first machine learning model.
De Groot does not teach the first machine learning model comprises a first prediction head configured to generate a systolic hypertension score or parameters indicative of the systolic hypertension score and a second prediction head configured to generate a diastolic hypertension score or parameters indicative of the diastolic hypertensions score.
However,
Carter teaches a first prediction head configured to generate a systolic hypertension score or parameters indicative of the systolic hypertension score and a second prediction head configured to generate a diastolic hypertension score or parameters indicative of the diastolic hypertensions score ([0045] “The predictive model for blood pressure determination can be implemented to determine blood pressure results 50 (e.g., systolic pressure, diastolic pressure, and/or mean arterial pressure) of the subject”).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the invention to have modified the first machine learning model taught by De Groot to include predictions for systolic and diastolic hypertension scores taught by Carter. One would have been motivated to make this modification because blood pressure can refer to systolic (or maximum) pressure over diastolic (or minimum) pressure, so both data are needed to predict blood pressure, as suggested by Carter ([0040]).
Regarding claim 6, De Groot teaches the electronic device of claim 4, wherein the processing circuitry generates the aggregated hypertension score wherein the processing circuitry comprises a second machine learning model configured to generate the aggregated hypertension score ([0004] “a system for determining blood pressure dip in a subject via machine learning models.”; [0066] “the BP prediction model is and/or includes machine learning models and/or algorithms, neural networks, and/or other prediction models”).
Regarding claim 7, De Groot teaches the electronic device of claim 6.
De Groot does not teach wherein the second machine learning model comprises one or more gradient-boosted decision trees or a regularized linear regression model.
However,
Carter teaches wherein the second machine learning model comprises one or more gradient-boosted decision trees or a regularized linear regression model ([0089] “a Gradient Boosting Regression (GBR) regression method is used to develop a predictive model for blood pressure. In some cases, the GBR regression method can be an additive ensemble model which learns new regression trees in each step”).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the invention to have modified the electronic device taught by De Groot to include a machine learning model comprising one or more gradient-boosted decision trees or a regularized linear regression model taught by Carter. One would have been motivated to make this modification because GBR regression can be used to generate a final predictive model for blood pressure that comprises an ensemble of ensembles of individual regression models, as suggested by Carter ([0089]).
Regarding claim 10, De Groot teaches the electronic device of claim 9 and the processing circuitry.
De Groot does not teach scaling the one or more pulse windows.
However,
Carter teaches scaling the one or more pulse windows ([0061] “scaling filtered beats 124 comprises further processing of the PPG data and scaling processed individual beats to a common scale”).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the invention to have modified the processing circuitry taught by Schutte to include scaling the pulse windows taught by Carter. One would have been motivated to make this modification because identifying individual beats and scaling them allows raw PPG data to be used to predict blood pressure within an accuracy of 10 mmHg, as suggested by Carter ([0006-0008]).
Regarding claim 14, De Groot teaches the electronic device of claim 13 and transforming the aggregated feature.
De Groot does not teach comprises applying one or more linear transforms.
However,
Carter teaches comprises applying one or more linear transforms ([0065] “scaling, translation, rotation, or any other similar transformation”).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the invention to have modified the transformation taught by De Groot to include one or more linear transforms taught by Carter. One would have been motivated to make this modification because linear transformations can be performed when using individual beat data to produce more accurate outputs, as suggested by Carter ([0062]).
Regarding claim 15, De Grrot teaches the electronic device of claim 14 and aggregated feature vector.
De Groot does not teach wherein the one or more linear transforms includes a transform to change a basis for the respective segment to a new basis.
However,
De Groot teaches wherein the one or more linear transforms ([0065] “scaling, translation, rotation, or any other similar transformation”) includes a transform to change a basis for the respective segment to a new basis ([0065] “a variation in these distinct shapes can be modeled to determine cardiovascular values such as blood pressure”).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the invention to have modified the electronic device taught by De Groot to include a transform to change a basis taught by Carter. One would have been motivated to make this modification because the transform allows the data to be compared to determine cardiovascular values such as blood pressure, as suggested by Carter ([0065]).
Regarding claim 16, De Groot teaches the electronic device of claim 15.
De Groot does not teach wherein the one or more linear transforms includes a transform to predict a systolic hypertension score or parameters indicative of the systolic hypertension score and a diastolic hypertension score or parameters indicative of the diastolic hypertension score from the aggregated feature vector for the respective segment in the new basis.
However,
De Groot teaches wherein the one or more linear transforms ([0065] “scaling, translation, rotation, or any other similar transformation”) includes a transform to predict a systolic hypertension score or parameters indicative of the systolic hypertension score and a diastolic hypertension score or parameters indicative of the diastolic hypertension score from the aggregated feature vector for the respective segment in the new basis ([0045] “The predictive model for blood pressure determination can be implemented to determine blood pressure results 50 (e.g., systolic pressure, diastolic pressure, and/or mean arterial pressure) of the subject”).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the invention to have modified the electronic device taught by De Groot to include linear transforms to predict systolic and diastolic hypertension score taught by Carter. One would have been motivated to make this modification because blood pressure can refer to systolic (or maximum) pressure over diastolic (or minimum) pressure, so both data are needed to predict blood pressure, as suggested by Carter ([0040]).
Regarding claim 17, De Groot teaches the electronic device of claim 16.
De Groot does not teach wherein the one or more linear transforms includes a transform to predict the respective estimate of the hypertension score from the systolic hypertension score or parameters indicative of the systolic hypertension score and the diastolic hypertension score or parameters indicative of the diastolic hypertension score.
However,
Carter teaches wherein the one or more linear transforms ([0065] “scaling, translation, rotation, or any other similar transformation”) includes a transform to predict the respective estimate of the hypertension score from the systolic hypertension score or parameters indicative of the systolic hypertension score and the diastolic hypertension score or parameters indicative of the diastolic hypertension score ([0045] “The predictive model for blood pressure determination can be implemented to determine blood pressure results 50 (e.g., systolic pressure, diastolic pressure, and/or mean arterial pressure) of the subject”).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the invention to have modified the electronic device taught by De Groot to include the linear transforms to predict the estimated hypertension score taught by Carter. One would have been motivated to make this modification because blood pressure can refer to systolic (or maximum) pressure over diastolic (or minimum) pressure, so both data are needed to predict blood pressure, as suggested by Carter ([0040]).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to EVELYN GRACE PARK whose telephone number is (571)272-0651. The examiner can normally be reached Monday - Friday, 9AM - 5:00PM.
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, Robert (Tse) Chen can be reached at (571)272-3672. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/EVELYN GRACE PARK/Examiner, Art Unit 3791 /TSE CHEN/Supervisory Patent Examiner, Art Unit 3791
Prosecution Insights