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 .
Response to Arguments
I. Claim Rejections under 35 U.S.C. § 101
Applicant’s remarks concerning the § 101 rejections have been fully considered but are not persuasive. Applicant first argues that the measurement and processing steps recited in the claims cannot practically be performed by the human mind and/or with a physical aid such as pen and paper since they involve using a sensing ring, processors and multiple deep learning models. The Examiner respectfully disagrees. The § 101 analysis separates limitations that constitute the judicial exception (in this case, mentally performable steps) and any additional elements, such as insignificant extra-solution activity and the recitation of generic processing component(s) for carrying out the mental steps. It is not required that the additional elements also be performable mentally. In this case, the measurement steps are considered insignificant pre-solution activity, which do not need to be mentally performed under the § 101 analysis for the rejection to be proper. Similarly, the recitation of physical/tangible computing elements to carry out mental step(s) does not change the fact that a mental step is recited. See MPEP § 2106.04(a)(2)(III)(C).
Applicant next argues that the claims recite “a specific practical application of technology (a platform that uses a sensing ring to establish atrial fibrillation).” The Examiner respectfully disagrees. The claims perform various mental steps (1) carried out using generic processing technology (e.g. processor(s) and deep learning models) and (2) using data obtained from conventional sensors which amounts to insignificant pre-solution activity, neither of which amounts to a practical application under the Step 2A, Prong 2 analysis.
Finally, Applicant argues that “when viewed as a whole, the claimed invention comprises a specific combination of elements that is not routine or conventional.” The Examiner respectfully disagrees; the combination of conventional PPG sensors and conventional processing technology (e.g. processor(s) and deep learning models) on a server is well-understood, routine and conventional in the medical diagnostic arts.
II. Claim Interpretation under 35 U.S.C. § 112(f)
Applicant’s remarks concerning the § 112(f) interpretation are persuasive in view of the claim amendments. The claims no longer recite any limitations that invoke § 112(f) interpretation.
III. Claim Rejections under 35 U.S.C. § 103
Applicant’s remarks concerning the § 103 rejections have been fully considered and are persuasive to the extent that the previous ground of rejection of claim 1 is overcome due to the claim amendments. Applicant argues that both Lee and Aliamiri fail to teach the claimed user feature extraction limitation. The Examiner agrees but notes that the rejection relies on Addison for the addition of this limitation. The rejections have been updated to address the claim amendments.
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.
Claims 1 and 3-10 are 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 1 requires both “a deep learning model” and “a first deep learning model.” It is unclear whether these are the same model. It is also unclear whether subsequent recitations of “the first deep learning model” refer to the original “a deep learning model.” As such, the scope of the claims is rendered indefinite.
Claim 4 recites “a second wavelength PPG signal” and “a third wavelength PPG signal” which are limitations already recited in claim 1. These limitations must be referred to as “the [signal]” or “said [signal]” if they are referring back to previously introduced limitations, otherwise it cannot be determined if new limitations are being added, thus rendering the scope of the claim indefinite.
The remaining claims are rejected by virtue of their dependence on claim 1.
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 and 3-10 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a mental process without significantly more.
Step 1: All of claims 1 and 3-10 are directed to a system/machine.
Step 2A, Prong One: The claims recite a mental process of data analysis steps such as “classify signal quality of a first wavelength photoplethysmography (PPG) signal as being good or bad” and “to determine whether atrial fibrillation has occurred” and “calculate an atrial fibrillation index from a first signal quality classification result of the first wavelength PPG signal and an atrial fibrillation determination result generated by the deep learning model, classify signal quality of a second wavelength PPG signal as being good or bad; extract, from the second wavelength PPG signal, a PPG feature by using a first deep learning model; extract a user feature by using a second deep learning model that receives, as inputs, user information, a test PPG signal measured by using the biometric signal sensing ring, and systolic and diastolic test blood pressure measured simultaneously with the test PPG signal by using a general blood pressure gauge; and estimate systolic and diastolic blood pressure by using a third deep learning model that receives, as inputs, the PPG feature output by the first deep learning model and the user feature output by the second deep learning model wherein the atrial fibrillation index is defined by a ratio of a time when quality of the first wavelength PPG signal is classified as being good by the first signal quality classification component to a time when the quality of the first wavelength PPG signal is classified as being good by the first signal quality classification component and the atrial fibrillation is determined to have occurred by the atrial fibrillation determination component” which could be performed by the human mind and/or by a human with a physical aid such as pen and paper.
Step 2A, Prong Two: This judicial exception is not integrated into a practical application because the claims merely implement the mental process using generic processing technology and add insignificant extra-solution activity. Specifically: the step of gathering diagnostic data via sensor(s), such as gathering PPG data, is considered insignificant pre-solution activity of mere data gathering, since it merely collects the data necessary to carry out the mental process. Furthermore, merely carrying out mental steps using generic computing technology such as a “sever” with one or more processors and deep learning models is well established to not amount to an integration into a practical application under the § 101 analysis. See, e.g., MPEP §§ 2106.04(a)(2)(III)(C) and 2106.04(d)(I) and 2106.05(f).
Step 2B: The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the only additional elements recited in the claims are generic processing/computing components and generic data collection components. The Examiner takes official notice that these are basic, generic components which are well-understood, routine and conventional both individually and in combination in the medical diagnostic arts, and the claims here merely use them for their well-understood, routine and conventional functions both individually and in combination. As such, those additional elements cannot be considered “significantly more” than the judicial exception in Step 2B of the § 101 analysis.
Dependent claims 3-10 merely add further types of insignificant pre-solution activity in the form of additional data gathering, and/or merely add further mental steps. As such, these claims follow the same analysis above.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1 and 3-5 are rejected under 35 U.S.C. 103 as being unpatentable over US 2019/0133468 A1 to Aliamiri et al. (hereinafter “Aliamiri”) in view of KR 10-2299035 B1 to Lee et al. (hereinafter “Lee”) in view of US 2021/0193311 A1 to Addison et al. (hereinafter “Addison”).
Regarding Claim 1, Aliamiri teaches a biometric data monitoring platform using a biometric signal sensing ring (140), the platform comprises one or more processors (see e.g. Para. 17; see “processor” throughout Aliamiri) configured to:
classify signal quality of a first wavelength photoplethysmography (PPG) signal as being good or bad (see e.g. Para. 38: “… In operation, the quality assessment network 210 generating a signal quality indicator as output where the signal quality indicator identifies each processed biosignal data sample segment as having good signal quality or poor signal quality. In practice, the quality assessment network 210 filters out PPG data sample segments with poor signal quality (node 214) and only allow the good signal quality PPG data sample segments (212) to move to the next stage for AFib prediction …”);
determine whether atrial fibrillation has occurred, from the first wavelength PPG signal by using a deep learning model (see e.g. Para. 47: “processed biosignal data sample segments having associated signal quality indicator designating good signal quality are provided to a AFib prediction network which implements a second deep learning model that was previously trained based on AFib annotations and one or more sets of AFib detection training data. At 316, the method 300 generates a prediction result being indicative of a probability that atrial fibrillation is present in a given segment of the biosignal data samples. In some embodiments, in response to detecting that AFib is present, the AFib detection method 300 sends a notification to the user”); and
Aliamiri fails to teach a “server” including the processor(s) for performing the calculations outlined above. However, it was extraordinarily well known in the medical diagnostic arts to use a separate computing device, including e.g. a server, to perform one or more of the data analysis steps instead of performing those steps locally on the processor on the sensor device. There are well understood tradeoffs to these options (e.g. using a server allows access to a more powerful computing device having more processing power, more memory, etc., but requires transmitting the data). It would have been obvious to one of ordinary skill in the art as of Applicant's effective filing date to modify Aliamiri to perform the data processing steps on a server because it would present predictable and well understood benefits, such as reducing the processing load required to be carried out by the sensor device.
Aliamiri fails to specifically teach “calculate an atrial fibrillation index from a first signal quality classification result of the first wavelength PPG signal and an atrial fibrillation determination result generated by the deep learning model, wherein the atrial fibrillation index is defined by a ratio of a time when quality of the first wavelength PPG signal is classified as being good to a time when the quality of the first wavelength PPG signal is classified as being good and the atrial fibrillation is determined to have occurred.” However, another reference, Lee, teaches determining an atrial fibrillation index using this ratio (see “As described above, the atrial fibrillation load is a numerical value expressed as a ratio of the total time of atrial fibrillation episodes to the analysis time” in the attached machine translation of Lee; the term “analysis time” means only those portions of the signal classified as being good, as noted in this other section in the attached machine translation of Lee: “Here, the analysis time is the total duration of the unit signals that can be analyzed among the actual collected bio-signals. Here, 'analysis is possible' means that it is possible to determine whether the corresponding unit signal is included in the AF episode or not. In other words, the analysis time means the total time of unit signals capable of determining whether or not they are included in the AF episode. If it can be determined whether a specific unit signal is included in the AF episode, the unit signal is classified as 'Analyzable'. -Analyzable)'. For example, suppose that a signal is collected for 5 minutes and all the collected unit signals are 'SQ Poor'. In this case, since it is not known whether or not AF has occurred for all the collected unit signals, it is also impossible to determine whether each of the unit signals includes an AF episode. Therefore, the analysis time for the collected 5 minutes becomes 0. That is, the analysis time is the total duration of each unit signal for determining whether 'included in the AF episode'.). It would have been obvious to one of ordinary skill in the art as of Applicant's effective filing date to modify Aliamiri to define an atrial fibrillation index using the ratio taught by Lee because Lee teaches that this is a known suitable equation for determining a diagnostically valuable indicator of this condition.
Aliamiri as modified further teaches collecting test data for the purpose of training multiple deep learning models (see e.g. Para. 50: “data may be provided to a deep learning model that has been trained using a plurality of classifiers (index, labels or annotations) and one or more sets of training data and/or testing data.”; see e.g. “first deep learning model” and “second deep learning model” throughout Aliamiri, such as in the abstract) and further teaches collecting blood pressure data (see Para. 24). However, Aliamiri as modified fails to specifically teach estimating, using a third deep learning model, blood pressure from a PPG feature and a user feature extracted from test PPG and BP data using a second deep learning model. Another reference, Addison teaches these limitations (see e.g. Para. 2: “a continuous non-invasive blood pressure model that is trained via machine learning with such determined calibration data so that the model may be able to receive the most recently determined calibration data along with the PPG signals to more accurately determine the blood pressures of patients”; also see e.g. Para. 84; Addison teaches in e.g. Para. 29 that multiple wavelengths can be used for PPG, as is known in the art). It would have been obvious to one of ordinary skill in the art as of Applicant's effective filing date to further modify Aliamiri to estimate BP from a PPG feature and an extracted user feature because it would enhance the overall usefulness of the device by providing additional diagnostically valuable information. In making such a modification, it would have been obvious to preserve the quality determinations made in Aliamiri for the BP data because it would predictably provide the same benefits, i.e. excluding “bad” data which would not produce reliable diagnostic data, and it would have been obvious to utilize multiple deep learning models since Aliamiri already teaches multiple of such models for different determinations.
Regarding Claim 3, as noted in the rejection of claim 1 above, Lee teaches detecting an index using a ratio based only on the “analysis time” which is time in which the data quality was deemed to be good. It would have been obvious to one of ordinary skill in the art as of Applicant's effective filing date to further modify Aliamiri to similarly use this same ratio for a BP index in view of the modification with Addison above so that poor quality data is not factored into the index calculation, which thereby predictably increases the accuracy of the index as a diagnostic indicator.
Regarding Claim 4, Addison further teaches using multiple wavelength PPG for determining oxygen saturation (see e.g. Paras. 28-29). It would have been obvious to one of ordinary skill in the art as of Applicant's effective filing date to further modify Aliamiri to use multiple wavelength PPG to determine oxygen saturation, as taught in Addison, since it would predictably enhance the overall usefulness of the device by collecting additional diagnostically valuable information. In making such a modification, it would have been obvious to preserve the quality determinations made in Aliamiri for the oxygen saturation data because it would predictably provide the same benefits, i.e. excluding “bad” data which would not produce reliable diagnostic data.
Regarding Claim 5, as noted in the rejection of claim 1 above, Lee teaches detecting an index using a ratio based only on the “analysis time” which is time in which the data quality was deemed to be good. It would have been obvious to one of ordinary skill in the art as of Applicant's effective filing date to further modify Aliamiri to similarly use this same ratio for an oxygen saturation index in view of the modification with Addison above so that poor quality data is not factored into the index calculation, which thereby predictably increases the accuracy of the index as a diagnostic indicator.
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over Aliamiri in view of Lee and Addison as applied to claim 1 above, and further in view of US 20200345252 A1 to Huijbregts et al. (hereinafter “Huijbregts”) and KR 20170019189 A to Noh et al. (hereinafter “Noh”).
Regarding Claim 6, Aliamiri as modified above fails to specifically teach a plurality of PPG sensors at different locations which each gather three wavelength PPG data. However, first, it was well known to gather three wavelength PPG data, as seen in e.g. Huijbregts (see e.g. Paras. 237-242). Furthermore, Noh teaches the use of multiple PPG sensors at different locations so that a best quality location can be selected (see e.g. the following portion from the attached machine translation: “For example, the sensor unit 120 may include a plurality of sensors for measuring the PPG signal at various sensing positions. At this time, the signal selector 130 may select a reference PPG signal to be used for blood pressure estimation among the PPG signals transmitted through a plurality of channels, and may transmit the selected reference PPG signal to the blood pressure estimator 140. The signal selector 130 may determine the PPG signal having the best signal quality (for example, a signal-to-noise ratio (SNR)) among the PPG signals as the reference PPG signal.”). It would have been obvious to one of ordinary skill in the art as of Applicant's effective filing date to further modify Aliamiri to use three wavelength PPG sensors since they were well known in the art and predictably yield a more comprehensive PPG signal, and to use multiple PPG sensors at multiple locations so that a higher quality signal could be used in different situations.
Claims 7-10 are rejected under 35 U.S.C. 103 as being unpatentable over Aliamiri in view of Lee and Addison and Huijbregts and Noh as applied to claim 6 above, and further in view of US 2018/0014737 A1 to Paulussen et al. (hereinafter “Paulussen”).
Regarding Claim 7, Aliamiri as modified above fails to specifically teach controlling the PPG light sources such that DC components are maintained within predetermined ranges. Another reference, Paulussen, teaches this limitation (see e.g. Paras. 16 and 99). It would have been obvious to one of ordinary skill in the art as of Applicant's effective filing date to further modify Aliamiri to control the PPG light sources such that DC components are maintained within predetermined ranges since Paulussen teaches that this helps ensure that a sufficient amount of light is detected (see e.g. Paras. 16 and 99 of Paulussen).
Regarding Claims 8 and 9, as noted in the rejection of claim 6 above, Noh teaches selecting the PPG sensor that has the highest quality, e.g. based on signal-to-noise ratio (see e.g. the following portion from the attached machine translation: “For example, the sensor unit 120 may include a plurality of sensors for measuring the PPG signal at various sensing positions. At this time, the signal selector 130 may select a reference PPG signal to be used for blood pressure estimation among the PPG signals transmitted through a plurality of channels, and may transmit the selected reference PPG signal to the blood pressure estimator 140. The signal selector 130 may determine the PPG signal having the best signal quality (for example, a signal-to-noise ratio (SNR)) among the PPG signals as the reference PPG signal.”). It would have been obvious to one of ordinary skill in the art as of Applicant's effective filing date to further modify Aliamiri to select the PPG sensor that has the highest quality based on SNR because it would produce a more accurate diagnostic result.
Regarding Claim 10, concerning the timing of these steps being “sequentially performed” or “continually performed,” it is clear in the combination above that these steps are performed sequentially (i.e. the data processing inherently must evaluate the data sequentially, at a minimum) and continually (i.e. the steps clearly repeat rather then being a one time measurement). Furthermore, one skilled in the art would have recognized that there were only a few options for how to select the timing of these actions, and various timings would have produced nothing beyond predictable results. As such, it would have been obvious to one of ordinary skill in the art as of Applicant's effective filing date to further modify Aliamiri to perform these steps sequentially and continually because it would merely involve selecting from among a few possible timing options.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
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 JOHN R DOWNEY whose telephone number is (571)270-7247. The examiner can normally be reached Monday-Friday 8:30am-5:00pm ET.
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, NIKETA PATEL can be reached at (571)-272-4156. 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.
/JOHN R DOWNEY/Primary Examiner, Art Unit 3792
Prosecution Insights