DETAILED ACTION
The examiner notes that all references to the specifications will use the paragraph numbering found in the printed publication for ease of access.
Specification
The disclosure is objected to because of the following informalities:
Paragraphs [0067] and [0088] both refer to a “U.S. Pat. No. 201502725112”. Glossing over the fact that these numbers appear to be reciting the numbers of a printed publication (not a patent), no such printed publication exists; the numbers contain one more digit than a standard publication number and thus any subject matter that hasn’t been directly ported into the specifications has not been and cannot be incorporated by reference.
Appropriate correction is required.
Claim Objections
Claims 1, 6, 21, and 22 objected to because of the following informalities:
Claim 1 – line 1: “A apparatus” should be “An apparatus”
Claim 6 – line 10: “and deriving” should be “and derive” for grammatical consistency.
Claim 6 – lines 21-22: “between each the first and second” should be “between each of the first and second”
Claim 21 – line 2: “a real PVR waveforms” should be “a real PVR waveform”
Claim 22 – lines 2-3: “a real PVR waveforms” should be “a real PVR waveform”
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 6-13, 21, and 22 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
As to claim 6, the claim recites a cuff-based BP measuring apparatus “measuring a user’s heart rate” and a CBP (central aortic blood pressure) estimator that substitutes the “user’s heart rate” into a linear regression equation. However, the original disclosure describes the cuff-based apparatus as supplying real SBP/DBP to the PPG to BP estimator and calibrator ([0065]). It describes the HR supplied to the CBP estimator as an output of block 14, along with the calibrated-estimated SBP/DBP ([0018], [0066], [0088]). It does not describe the cuff based apparatus measuring heart rate, nor the CBP estimator using a cuff-measured heart rate.
As to claims 13, 21, and 22, these claims now recite assigning an identical numerical label to two respective peaks of the modeling-used PPG waveform and the real PVR waveform that occur at the same time along a time axis. The original disclosure fails to provide support for such a feature. It explicitly states that the PPG and PVR waveform signals are “asynchronous” with the occurrence of the two peaks are “about as close to each other along a time axis” ([0082]), which is not the same as “the same time” that is being currently recited. Similarly, Fig. 5C and 5D depicts the like-numbered PPG and PVR peaks at visibly different times and calls for a “dynamic time warping” for that very reason ([0082]).
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.
Claims 1-4, 6-19, and 21-22 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.
Claims 1, 6, and 14 recite that the modeling-used character parameters of the first prediction model are “more similar” to PPG characteristic parameters of the user so as to predict the BPs “more accurately”. “More similar” and “more accurately” are relative terms. Neither the claims nor the specifications provide a standard for measuring similarity between a model’s training parameters and a user’s parameters, or a baseline for the accuracy. While there is discussion of a “minimal mean error”, it’s used only in context of the cuff SBP ([0078]). Accordingly, it is unclear whether the similarity is a condition that the calibrator must evaluate or is merely a characterization of the result.
Claims 1, 6, and 14 recite training the first and second prediction models “in parallel”. The term does not appear in the original disclosure, which merely state that the different age groups are training as “different models” ([0072]). It is unclear whether the term requires concurrent execution of the training with respect to time, or merely require separate models trained for each respective age group. Applicant’s remarks appear to suggest that the term has a temporal meaning (p16). If so, applicant is required to identify written description support for the concurrent training in the original disclosure. For purposes of examination, the term is interpreted as training separate models for respective age groups, whether it is trained concurrently or not.
Claim 1 recites the limitation "the modeling-used characteristics of the first prediction model" in lines 25-26. There is insufficient antecedent basis for this limitation in the claim.
Claim 1 recites “a real BP of the user” twice, and it is unclear whether it is the same BP or a separate BP value.
Claim 6 recites the limitations "the modeling-sued characteristic parameters”, “the age parameter of the user”, “the optimal prediction model”, and “the BPs”. There are insufficient antecedent basis for these limitations in the claim.
Claim 7 recites “the PPG waveform signals”. It is unclear whether this refers to the modeling-used signals or to the user’s own signal.
Claim 13 recites the limitation "the real PVR waveforms". There is insufficient antecedent basis for this limitation in the claim.
Claim 14 recites the limitation "the user's real BPs". There is insufficient antecedent basis for this limitation in the claim.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-4, 6-19, and 21-22 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claim(s) recite(s) training prediction models using age and personal information parameters, calculating estimated BPs using the prediction models, calibrating the relationship between the estimated and real BPs, and selecting the prediction model that is more accurate to the individual. These limitations cover performance of the limitation in the mind but for the recitation of generic computer components, such as a circuit system. Accordingly, it falls within the “Mental Processes” grouping of abstract ideas.
This judicial exception is not integrated into a practical application. In particular, the claims only recite one additional element apart from the processor – a display unit for displaying the values. This additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The use of a display for outputting results is merely an insignificant extra-solution activity that does not amount to an inventive concept. The claims are not patent eligible.
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) 1-4, 14-19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chen et al. (“A data-driven model with feedback calibration embedded blood pressure estimator using reflective photoplethysmography”) in view of Li et al. (US 2019/0313947).
As to claim 1, Chen teaches an apparatus for improving accuracy in estimating and calibrating blood pressures (BPs) (Abstract) based on modeling-used photoplethysmography (PPG) waveform signals (Table 1) sensed by a PPG sensor included in a wearable apparatus from a plurality of subjects (Section 2.1 – reflective PPG wearable device), modeling-used personal information parameters derived from the plurality of subjects (Section 2.2 – 435 participants), and modeling-used characteristic parameters extracted from the modeling-used PPG waveform signals (Section 2.3; Table 2; p4 – morphological characteristic parameters extracted from the PPG, along with age and gender, as model inputs), the apparatus comprising: an estimator configured to: divide age parameters of the modeling-used personal information parameters into at least first and second age groups by ranges (Fig. 6 – step 1 being age grouping, the grouping being done in 15 year ranges for the DBP model and 30 year ranges for the SBP model); execute, by a circuit system, machine learning algorithms to train a first prediction model corresponding to the first age group and a second prediction model corresponding to the second age group in parallel based on the modeling-used characteristic parameters and the modeling-used personal information parameters (Fig. 6 – step 2 being models training; p14 – identifies exponential GPR method as the optimal machine learning model; and calculate a first estimated BP and a second estimated BP for a user respectively from the first prediction model and the second prediction model (Section 2.3 – all age-group models for the participant’s gender predicting BP values for said participant); a calibrator configured to: use a calibration model which approximately fits relationship between each of the first and second estimated BPs and a real BP of the user measured with a cuff-based BP measuring apparatus (Fig. 5 – step 2; Equation 7 in which a compensated value is incorporated into the GPR model for personal calibration), and compute, by the circuit system, a minimal mean error between each of the first and second estimated BPs and a real BP of the user through the calibration model and select the first prediction model among the first and second prediction models as an optimal prediction model when an age parameter of the user is within the second age group, the age parameter of the user is not within the first age group corresponding to the optimal prediction model, and the modeling-used characteristic parameters of the first prediction model are more similar to PPG characteristic parameters of the user so as to predicts the BPs more accurately (p12 – calculating minimal mean error, and corresponding optimal age group selected; example provided places a 25 year old (who should be in the age<30 category, into the 30<age<45 category instead, as it better suits the participant’s PPG parameters; p21-22 – best model among all age groups adapted for individual model since chronological age differs from physiological age); a display unit for displaying a calibrated-estimated SBP (systolic BP) and a calibrated-estimated DBP (diastolic BP) predicted by the first prediction model (Fig. 1 – B; Fig. 6 – Step 7).
Chen fails to expressly teach that the PPG sensor is included in an “upper-arm wearable apparatus” and teaches a device worn on the wrist (Fig. 1 – B). Li teaches an upper-arm wearable apparatus including a PPG sensor ([0074] – upper arm; [0108] – device measures using PPG). It would have been obvious to modify Chen to be worn on the upper-arm as taught by Li, as Li not only teaches that the device can be worn on various body parts ([0074]), it also notes that wearing the device on the wrist may result in noise due to sudden and unexpected motions ([0032]), to increase the accuracy of the device.
As to claim 2, Chen teaches the modeling-used characteristic parameters are derived by performing feature extraction on the modeling- used PPG waveform signals (Section 2.3; Table 2).
As to claim 3, Chen teaches wherein the modeling-used personal information parameters includes gender parameters of the plurality of subjects (Table 2).
As to claim 4, Chen teaches the estimator further divides the first and second age groups into subgroups by the gender parameters (Section 2.3).
As to claim 14, Chen teaches a system for improving accuracy in estimating blood pressures (BPs) using a photoplethysmography (PPG) signal analysis (Abstract; Section 2.1) comprising: a cuff-based BP measuring apparatus measuring a user's real BP from a user (Section 2.2 – use of JPN-700), a wearable apparatus including a PPG sensor adapted to sense modeling- used PPG waveform signals from a plurality of subjects wearing the wearable apparatus (Sections 2.1-2.2); a PPG to BP subsystem including: a PPG signal receiver and analyzer configured to: process the modeling-used PPG waveform signals and derive modeling-used characteristic parameters from the modeling-used PPG waveform signals (Section 2.1 – transimpedance filter, ADC converter; Section 2.3 – Table 2); and have modeling-used personal information parameters from the plurality of subjects wherein the modeling-used personal information parameters includes an age parameter of the plurality of subjects (Section 2.3; Table 2), a PPG to BP estimator and calibrator configured to: divide the age parameter of the modeling-used personal information parameters of the plurality of subjects into at least first and second age groups; execute, by a circuit system, machine learning algorithms to train a first prediction model corresponding to the first age group and a second prediction model corresponding to the second age group in parallel based on the modeling-used characteristic parameters and the modeling-used personal information parameters of the plurality of subjects; calculate a first estimated BP and a second estimated BP for the user respectively from the first prediction model and the second prediction model (see citations given for claim 1); store a calibration model which approximately fits relationship between each of the first and second estimated BPs and the user's real BPs (Section 2.1 – model parameters stored on the flash memory); and calculate a minimal mean error between each of the first and second estimated BPs and the user's real BP through the calibration model and select the first prediction model among the first and second prediction models as an optimal prediction model when an age parameter of the user is within the second age group, the age parameter of the user is not within the first age group corresponding to the optimal prediction model, and the modeling-used characteristic parameters of the first prediction model are more similar to PPG characteristic parameters of the user so as to predicts the BPs more accurately (see citations given for claim 1); wherein the PPG to BP subsystem obtains user's characteristic parameters from the upper-arm wearable apparatus so as to have a user's calibrated estimated BP from the first prediction model (Section 2.3 – optimal group used for further estimation), a display unit for displaying a calibrated-estimated SBP (systolic BP) and a calibrated-estimated DBP (diastolic BP) predicted by the first prediction model (Section 2.1; Fig. 1B-1C).
Chen fails to expressly teach that the PPG sensor is included in an “upper-arm wearable apparatus” and that the cuff measuring apparatus measures the real BP “by a pressure sensor included in the cuff-based measuring apparatus”. However, the examiner notes that Chen discloses the use of a specific sphygmomanometer (the Omron JPN-700) which likely does utilize a pressure sensor in its cuff-based BP measurement device, and gives official notice that it would be obvious to use a sphygmomanometer incorporating a pressure sensor, as it is the most direct way of measuring blood pressure).
Li teaches an upper-arm wearable apparatus including a PPG sensor ([0074] – upper arm; [0108] – device measures using PPG). It would have been obvious to modify Chen to be worn on the upper-arm as taught by Li, as Li not only teaches that the device can be worn on various body parts ([0074]), it also notes that wearing the device on the wrist may result in noise due to sudden and unexpected motions ([0032]), to increase the accuracy of the device.
As to claim 15, Chen teaches the wearable apparatus further includes a gravity sensor sensing a motion of the upper-arm of the subject when the subject wears the wearable apparatus (Section 2.2 – triaxial accelerometer).
As to claim 16, Chen teaches that during periods of motion, BP estimation was not available (Section 2.1). Similarly Li teaches that a biosignal is accepted only when user motion is at or below a predetermined threshold ([0087]). Accordingly, it would have been obvious to further modify the above combination to trigger an alert when the gravity sensor is sensing the motion, so that the user can get into a posture/state in which the measurements will be more accurate.
As to claim 17, Chen teaches the modeling-used personal information parameters include gender parameters of the plurality of subjects, and the first and second age groups are further categorized into more subgroups by the gender parameters (Section 2.3).
As to claim 18, Chen teaches wherein the PPG signal receiver and analyzer is a computer or smart phone (Section 2.1 – mobile application, on-board microcontroller unit).
As to claim 19, Chen teaches wherein wearable apparatus wirelessly transmits the modeling-used PPG waveform signals to the PPG signal receiver and analyzer (Section 2.1 – transmitted wirelessly to a mobile phone).
Claim(s) 6-13 and 21-22 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chen et al. (“A data-driven model with feedback calibration embedded blood pressure estimator using reflective photoplethysmography”) in view of Li et al. (US 2019/0313947), and further in view of Chen et al. (US 2015/0272512) (hereinafter Chen’512) and Ibtehaz (“PPG2ABP: Translating Photoplethysmogram (PPG) Signals to Arterial Blood Pressure (ABP) Waveforms using Fully Convolutional Neural Networks”).
As to claim 6, Chen teaches a system for improving accuracy in estimating blood pressures using a photoplethysmography (PPG) signal analysis (Abstract; Section 2.1) comprising: a cuff-based blood pressure (BP) measuring apparatus measuring a user’s real BP from a user (Section 2.2-2.3; Fig. 5, Step 2), a wearable apparatus including a PPG sensor adapted to sense modeling-used PPG waveform signals from a plurality of subjects (Sections 2.1-2.2), a PPG signal receiver and analyzer configured to: process the modeling-used PPG waveform signals and derive modeling-based characteristic parameters; and have modeling-used personal information parameters including an age parameter (Sections 2.1, 2.3; Fig. 4), a PPG to BP estimator and calibrator configured to divide; train first and second prediction models in parallel by a circuit system; calculate a first estimated BP and a second estimated BP; and store a calibration model (Section 2.1 – model parameters stored in flash memory; Section 2.3; Fig. 6, as applied to claim 1), designate the first prediction model as an optimal model after the calibration model calculates a minimal mean error when an age of the user is within the second age group, the age parameter of the user is not within the first age group corresponding to the optimal prediction model (Section 2.3; Section 4, as applied to claim 1), wherein the PPG to BP estimator and calibrator obtains user’s characteristic parameters from the wearable apparatus so as to have a user’s calibrated estimated BP from the optimal prediction model (Section 2.3), and a display unit (Section 2.1; Fig. 1B-1C).
Chen fails to expressly teach the following features: the upper-arm wearable apparatus, a cuff apparatus measuring a user’s heart rate by a pressure sensor included in the cuff-based BP measuring apparatus, the PPG to pulse volume recording (PVR) transformer, the CBP estimator, and estimating and displaying the central aortic blood pressures. However, the examiner notes that Chen discloses the use of a specific sphygmomanometer (the Omron JPN-700) which likely does utilize a pressure sensor in its cuff-based BP measurement device, and gives official notice that it would be obvious to use a sphygmomanometer incorporating a pressure sensor, as it is the most direct way of measuring blood pressure).
Li teaches an upper-arm wearable apparatus including a PPG sensor ([0074] – upper arm; [0108] – device measures using PPG). It would have been obvious to modify Chen to be worn on the upper-arm as taught by Li, as Li not only teaches that the device can be worn on various body parts ([0074]), it also notes that wearing the device on the wrist may result in noise due to sudden and unexpected motions ([0032]), to increase the accuracy of the device.
Chen’512 teaches a central BP estimation device in which a cuff wrapped around an upper arm ([0026], [0034]) captures a pressure oscillometric waveform. The waveform includes the PVR waveform, which is the recorded variation of cuff pressure ([0035]). Chen’512’s device also measures brachial DBP, SBP, average pressure, and a heart rate ([0035]). Chen’512 also teaches the CBP estimator: the analysis unit ([0010]) obtains a set of values including SBP2 (a pressure value of the late systolic shoulder), ESP (end-systolic pressure value), As (area under the waveform during systole), Ad (area under the waveform under diastole), DBP (pressure value at end-diastole), and heart rate and sub substitutes the set of values in a linear regression equation to obtain a central blood pressure value ([0029]), with the PVR waveform being calibrated to SBP and DBP ([0041]), a display unit for displaying the estimated CBP ([0046]). Moreover, Chen’512 specifies that central aortic pressure is a better predictor of cardiovascular events than brachial blood pressure ([0005-06]).
Ibtehaz teaches the PPG to PVR transformer as recited. It trains on PPG signals, a one-dimensional deeply supervised 1D U-Net approximation network that approximates the pressure waveform from PPG and applies it to a new PPG signal (Sections 2.1-2.23, 4.1).
It would’ve been obvious to modify the above combination with Chen’512 and Ibtehaz in the following fashion: Adding Chen’512’s CBP estimation to Chen’s modified system and obtain the PVR waveform required by Chen’512’s regression from the wearable PPG device, using Ibtehaz’s approximation and refinement networks trained with cuff-recorded PVR waveforms as the target, as it would allow continuous monitoring without cuff inflation and the training on the cuff PVR waveform instead of the ABP waveform substitutes one known pressure-pulse target waveform for another, with predictable results.
As to claim 7, Chen teaches the modeling-used characteristic parameters are derived by performing feature extraction on the PPG waveform signals (Section 2.3; Fig. 4).
As to claim 8, Chen teaches the modeling-used personal information parameters include gender parameters of the plurality of subjects, and the PPG to BP estimator and calibrator further divides the first and second age groups into subgroups by the gender parameters (Section 2.3).
As to claim 9, Chen teaches the wearable apparatus wirelessly or by wire transmits the modeling-used PPG waveform signals to the PPG signal receiver and analyzer (Section 2.1 – transmitted wirelessly to a mobile phone).
As to claim 10, Chen teaches a gravity sensor sensing a motion of the subject when the subject wears the wearable apparatus ([0039]).
As to claim 11, Chen teaches executing the stored GPR model on the device’s microcontroller (Section 2.1), but does not expressly teach integrating the receiver, analyzer, estimator and calibrator, the transformer, and the estimator into the wearable device.
Chen’512 teaches integrating its store and analysis units into a single IC chip ([0025]). It would have been obvious to integrate all the processing into the wearable device to provide a single self-contained device to minimize the need for multiple devices to be carried by the user and increase the convenience for the end user.
As to claim 12, Ibtehaz teaches splitting signals into episodes of identical intervals (Section 2.1 – 8.192 second segments). While the references do not explicitly teach that an initial episode is deleted or trimming an initial interval of the real PVR waveform, Chen teaches that during periods of motion, BP estimation was not available (Section 2.1). Similarly Li teaches that a biosignal is accepted only when user motion is at or below a predetermined threshold ([0087]). Accordingly, it would have been obvious to modify the above combination to delete the initial episode and trim the initial interval to use only stabilized portions of the signals to train and align the waveform-translation model. This is a predictable application of multiple references’ shared practice of excluding unstable start-up data.
As to claims 13, 21, and 22, Ibtehaz teaches that asynchronously acquired PPG and pressure waveforms exhibit a phase lag that must be accounted for in the model (Section 4.1). It would have been obvious to align the PPG and cuff-recorded PVR training waveforms by numbering the detected peaks of each waveform in order, so that like-numbered peaks can be paired as corresponding beats and applying dynamic time warping to improve the reliability and accuracy of alignment.
Response to Arguments
Applicant’s arguments have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
It is noted that applicant argues that a previously applied reference (Lu) fails to teach the training of the models in parallel. As stated in the above rejection, “in parallel” has not been currently interpreted as being “concurrent” (that is, done simultaneously with respect to time) as the original disclosure fails to provide for such a feature.
In addition, while largely moot as Li is not currently being relied upon for the machine learning feature, applicant characterizes Li’s model based on regression analysis as failing to teach training using machine learning algorithms. However, applicant’s own disclosure in [0077] calls the Gaussian Process Regression (GPR) algorithm a “type of ML method for statistically analyzing data”. It is unclear how Li’s model based on regression analysis would fail to be considered machine learning when GPR is considered to be machine learning by the inventors.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHRISTIAN JANG whose telephone number is (571)270-3820. The examiner can normally be reached Monday-Friday (7-3:30 EST).
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 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.
CHRISTIAN JANG
Primary Examiner
Art Unit 3791
/CHRISTIAN JANG/Primary Examiner, Art Unit 3791 10/8/26