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 § 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 9 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.
Regarding claim 9, it is unclear why the claim recites that “the computer system is configured to use the BP classifier” as claim 1 already requires the computer system to be configured to use the BP classifier. Further regarding claim 9, it is unclear what is meant by “the BP classifier stores data created from training of at least one model…”. For this examination, the phrase is being interpreted such that the BP classifier itself is data that is stored, the BP classifier being derived by “training of at least one model…”.
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 1-3, 9, 10, and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Lu et al.’982 (WO 2020/210982 – previously cited) in view of Arand et al.’164 (US Pub No. 2004/0158164 – previously cited).
Regarding claims 1 and 9, Figure 3 of Lu et al.’982 discloses a system comprising: a bed 4 having a mattress to support a user laying on the bed; a first ballistocardiograph (BCG) sensor 11 configured to collect first BCG data from a first location of the user laying on the bed due to pressure applied to the bed by the user (sections [0028-0033], [0040], [0042], [0049-0050]); a second BCG sensor 12 configured to collect second BCG data from a second location of a user (sections [0028-0033], [0040], [0042], [0049-0050]); and a computer system comprising a processor and memory, the computer system configured to: receive the first BCG data and the second BCG data (sections [0007-0009], [0013-0018], [0028-0033], [0042-0045]); and determine one or more blood pressure (BP) values for the user (sections [0001], [0004], [0007-0009], [0013-0018], [0028-0033], [0039], [0048]). In order to determine one or more BP values for the user, the computer system is configured to: determine a pulse transit time (PTT) for the user identifying a length of time between a pulse event in the first BCG data and the second BCG data representing the length of time between when a pulse of the user’s blood reaches the first location and the second location (sections [0012], [0038], [0047]); provide, as input, the PTT to a BP classifier (sections [0013], [0039], [0048]); and receive, as output, the one or more blood pressure values for the user (sections [0012-0013], [0048]).
Lu et al.’982 discloses all of the elements of the current invention, as discussed above, except for the BP classifier being trained using at least one model of the group consisting of: i) a linear model finding a fit between training PTT values and training BP values; ii) a polynomial model finding coefficients describing a function that relates the training PTT values with the training BP value; iii) a machine learning model that creates a data structure created by a machine learning process; and iv) a boosted decision tree regression model.
Arand et al.’164 teaches that a physiological classifier (an equation) can be trained using a linear model finding a fit between training values and training final values or using a polynomial model finding coefficients describing a function that relates two sets of values (sections [0035-0036]). It would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to have modified the BP classifier of Lu et al.’982 (the equation shown in section [0039]) such that it is trained using either a linear model finding a fit between training PTT values and training BP values or a polynomial model finding coefficients describing a function that relates the training PTT values with the training BP value, as Arand et al.’164 teaches that a classifier can be trained using a linear model finding a fit between two sets of values or a polynomial model finding coefficients describing a function that relates two values. The modification to Lu et al.’982 would merely be combining prior art elements according to known methods to yield predictable results.
Regarding claim 2, the first BCG sensor is a pressure sensor configured to sense pressure readings applied to the bed by the user due to weight and motion of the user (section [0010]).
Regarding claim 3, the first BCG sensor is one of the group consisting of a pressure transducer and a load cell (section [0010]).
Regarding claim 10, as Lu et al.’982 in view of Arand et al.’164 teaches using either model i) or model ii) to train its classifier, it need not teach the recitation in claim 10 further limiting model iii). Claim 10 provides a further limitation to an option of claim 9; when another option of claim 9 is used, claim 10 fails to provide a further limitation to the claimed invention.
Regarding claim 17, Lu et al.’982 in view of Arand et al.’164 discloses all of the elements of the current invention, as discussed above, except for explicitly stating that the computer system is configured to store the one or more BP values to the memory or generate an alert for output to a user output device. Official notice is being taken that it is well known in the art to store determined physiological values such as BP. Official notice is also being taken that it is well known in the art for a medical device to generate an alert for output to a user output device if a determined parameter (e.g., blood pressure, change in blood pressure) is outside of a predetermined range.
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Lu et al.’982 in view of Arand et al.’164, as applied to claim 1, further in view of Raisanen’741 (WO 2018/191741 – previously cited).
Lu et al.’982 in view of Arand et al.’164 discloses all of the elements of the current invention, as discussed in paragraph 5 above, except for the second BCG sensor being a device configured to be worn by the user on a specified location of the user’s body.
Raisanen’741 teaches a system comprising a first BCG sensor and a second BCG sensor, the second BCG being configured as device worn by a user on a specified location of the user’s body (Figure 1 shows the second BCG sensor being worn by the user around their chest; and page 15, lines 32-34 and page 17, lines 1-3). Data from the first BCG sensor and data from the second BCG sensor are used to determine one or more BP values for the user (page 15, lines 3-13, and page 27, line 25 – page 28, line 25). It would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to have modified the system of Lu et al.’982 in view of Arand et al.’164 such that its second BCG sensor is a device configured to be worn by the user on a specified location of the user’s body, as taught by Raisanen’741, as it would merely be substituting one known second BCG sensor type for another to obtain predictable results.
Claims 11-13 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Lu et al.’982 in view of Arand et al.’164, as applied to claim 1, in view of Burton’733 (US Pub No. 2007/0032733 – previously cited).
Regarding claim 11, Lu et al.’982 in view of Arand et al.’164 discloses all of the elements of the current invention, as discussed in paragraph 5 above, except for the computer system being configured to: identify a time window of a particular sleep stage of a sleep session of the user sleeping on the bed, and identify a representative BP for the sleep stage based on the one or more BP values for the user which are within the time window.
Burton’733 teaches a computer system configured to identify a time window of a particular sleep stage of a sleep session of a sleeping user, and identify a representative blood pressure value for the sleep stage based on one or more of blood pressure values which are within the time window (sections [0433-0435]; “blood pressure changes during one or more stages of sleep state” requires identifying representative blood pressure values for each sleep stage). Burton’733 teaches determining the representative BP for a determined sleep stage in order to alert a healthcare worker if a patient’s blood pressure is outside of safe limits of bounds during one or more stages of sleep, or to modify administration of therapeutic treatment based on an abnormal blood pressure in one or more stages of sleep (section [0436-0437]). It would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to have modified the computer system of Lu et al.’982 in view of Arand et al.’164 to be configured to identify a time window of a particular sleep stage of a sleep session of the user sleeping on the bed, and identify a representative BP for the sleep stage based on the one or more BP values for the user which are within the time window, as this would allow a healthcare worker to be alerted if safe limits or bounds of blood pressure are violated in one or more of the sleep stages, and it would also allow the modification of therapeutic intervention based on the identified blood pressure.
Regarding claim 12, the representative blood pressure for each sleep stage can be considered an Nth lowest BP value within the time window to represent a low BP value for the sleep stage (“N” can be any number as it is not defined by the claim).
Regarding claim 13, the representative blood pressure can be considered the Nth lowest percentile BP value (“N” can be any number as it is not defined by the claim).
Regarding claim 16, different sleep stages are capable of being identified within a time window of between 0 and 4 hours after sleep onset. The identification of a particular sleep stage depends entirely on when the user enters the sleep stage.
Claims 14 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Lu et al.’982 in view of Arand et al.’164 further in view of Burton’733, as applied to claim 12, further in view of Nakajima et al.’910 (US Pub No. 2019/0320910 – previously cited).
Regarding claim 14, Lu et al.’982 in view of Arand et al.’164 further in view of Burton’733 discloses all of the elements of the current invention, as discussed in paragraph 7 above, except for the computer system being configured to: receive an instant BP value for the user taken after the sleep session; and compare a low BP value for a sleep stage with the instant BP value to determine a BP dip value for the user.
Nakajima et al.’910 teaches receiving an instant BP value for a user taken after a sleep session, and comparing the instant BP value to a BP value taken during a previous sleep stage. Nakajima et al.’910 teaches performing these steps in order to diagnose early morning hypertension (section [0047]). It would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to have modified the computer system of Lu et al.’982 in view of Arand et al.’164 further in view of Burton’733 to be configured to compare an instant BP value of the user taken after a sleep session with a low BP value of the user during a sleep stage, as this would help in diagnosing early morning hypertension.
Regarding claim 15, Lu et al.’982 in view of Arand et al.’164 further in view of Burton’733 further in view of Nakajima et al.’910 discloses all of the elements of the current invention, as discussed above, except for explicitly stating that the computer system is configured to store a BP dip value to the memory or generate an alert for output to a user output device. Official notice is being taken that it is well known in the art to store determined physiological values such as BP changes. Official notice is also being taken that it is well known in the art for a medical device to generate an alert for output to a user output device if a determined parameter (e.g., blood pressure, change in blood pressure) is outside of a predetermined range.
Claim 18 is rejected under 35 U.S.C. 103 as being unpatentable over Lu et al.’982 in view of Arand et al.’164, as applied to claim 1, further in view of Soeseno et al.’720 (US Pub No. 2021/0282720).
Lu et al.’982 in view of Arand et al.’164 discloses all of the elements of the current invention, as discussed in paragraph 5 above, except for the system being configured to train a generic model from a training dataset containing ground-truth data from several individuals and to derive a personalized, more accurate, model from the generic one by transfer learning the generic model using a calibration dataset from the user for whom the personalization process is conducted that is collected via a device worn by the user, wherein the training dataset is larger than the calibration dataset.
Soeseno et al.’720 teaches training a generic model from a training dataset containing ground-truth data from several individuals and deriving a personalized, more accurate, model from the generic one by transfer learning the generic model using a calibration dataset from the user for whom the personalization process is conducted that is collected via a device worn by the user, wherein the training dataset is larger than the calibration dataset (sections [0014], [0018-0021]). This process is performed in order to derive a more accurate blood pressure model that is more suitable for a particular user (sections [0020], [0029], [0035]). It would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to have modified the system of Lu et al.’982 in view of Arand et al.’164 to be configured to train a generic model from a training dataset containing ground-truth data from several individuals and to derive a personalized, more accurate, model from the generic one by transfer learning the generic model using a calibration dataset from the user for whom the personalization process is conducted that is collected via a device worn by the user, wherein the training dataset is larger than the calibration dataset, as taught by Soeseno et al.’720, as it would provide for a more accurate blood pressure model (BP classifier) for the particular user.
Claim 19 is rejected under 35 U.S.C. 103 as being unpatentable over Lu et al.’982 in view of Arand et al.’164 further in view of Burton’733 further in view of Nakajima et al.’910.
See the rejection of claim 14 in paragraph 8 above.
Claim 20 is rejected under 35 U.S.C. 103 as being unpatentable over Lu et al.’982 in view of Soeseno et al.’720.
The sections of Lu et al.’982 cited in paragraph 5 above disclose a method comprising: receiving i) first BCG data from a first BCG sensor configured to collect the first BCG data from a first location of a user laying on a bed due to pressure applied to the bed by the user, and ii) second BCG data from a second BCG sensor configured to collect the second BCG data from a second location of the user; and determining one or more BP values for the user by: determining a PTT for the user identifying a length of time between a pulse event in the first BCG data and a pulse event in the second BCG data, the PTT representing the length of time between when a pulse of the user’s blood reaches the first location and the second location; providing, as input, the PTT to a BP classifier; and receiving, as output from the BP classifier, the one or more BP values for the user.
Lu et al.’982 fails to disclose that the BP classifier is a personalized BP classifier derived by training a generic blood pressure classifier to estimate blood pressure values from PTT values using a first dataset comprising ground-truth blood pressure data from a plurality of individuals, and personalizing the generic BP classifier by transfer learning using a calibration dataset comprising PTT values and blood pressure values obtained from a user. As discussed in paragraph 9 above, Soeseno et al.’720 teaches deriving a personalized BP classifier for a user by training a generic BP classifier to estimate blood pressure values from PTT values using a first dataset comprising ground-truth blood pressure data from a plurality of individuals, and personalizing the generic BP classifier by transfer learning using a calibration dataset comprising PTT values and blood pressure values obtained from a user (sections [0014], [0018-0021]). The personalized BP classifier provides a more accurate BP classifier for a particular user (sections [0020], [0029], [0035]). It would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to have modified the method of Lu et al.’982 such that the BP classifier is a personalized BP classifier derived by training a generic blood pressure classifier to estimate blood pressure values from PTT values using a first dataset comprising ground-truth blood pressure data from a plurality of individuals, and personalizing the generic BP classifier by transfer learning using a calibration dataset comprising PTT values and blood pressure values obtained from the user, as Soeseno et al.’720 teaches that this would provide a more accurate BP classifier for the user.
Response to Arguments
Applicant's arguments filed 27 May 2026 have been fully considered.
The amendments to the claims have overcome the previous rejections under 35 U.S.C. 112(b). However, as noted in paragraph 3 above, indefiniteness issues remain in claim 9.
With regard to the rejections of the claims under 35 U.S.C. 101, Applicant’s arguments are persuasive. The rejections have been withdrawn.
With regard to the rejection of claim 1 in view of the previously cited prior art, Applicant argues that “Lu does not recite any classifier, let alone a BP classifier. Moreover, Lu further fails to disclose the amended features of: providing ‘the PTT to a BP classifier that has been trained’ or receiving the one or more blood-pressure values for the user ‘as output from the BP classifier.’” The Examiner respectfully disagrees. According to section [00233] of the specification as filed, a BP classifier is a model that logically and mathematically correlates input PTT values with corresponding BP values. The function F(L, THI, TIJ, THIJ, AIJ, TJJ, TPPT) disclosed by Lu in section [0039] logically and mathematically correlates input PTT values (section [0038] teaches that TJJ is PTT) with corresponding BP values to output BP values. Based on the definition of a BP classifier provided by Applicant’s specification, the function taught by Lu is a BP classifier. As modified by Arand, the function of Lu is a BP classifier that is trained.
With regard to the prior art rejections of claims 19 and 20, the amendments to the claims have warranted new grounds of rejections under 35 U.S.C. 103.
It is noted that the Applicant has not traversed the Examiner’s previous assertions of Official Notice. As such, the Official Notice statements are taken to be admitted prior art.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure.
It is noted that claims 1-3, 9, 10, 17, and 18 could have been rejected under 35 U.S.C. 103 as being unpatentable over Lu et al.’982 in view of Soeseno et al.’720.
Watson et al.’353 (US Pub No. 2009/0326353 – previously cited) teaches determining a blood pressure dip value during sleep stages in order to detect one or more types of sleep events.
Inan et al.’847 (US Pub No. 2017/0238847 – previously cited) discloses a system and method that determines blood pressure values from BCG signals.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ETSUB D BERHANU whose telephone number is (571)270-5410. The examiner can normally be reached Mon-Fri 9:00am-5:30pm 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, Jennifer Robertson can be reached at (571) 272-5001. 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.
/ETSUB D BERHANU/Primary Examiner, Art Unit 3791
Prosecution Insights