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 Amendment
The amendment filed May 12, 2026 has been entered. Claims 1-20 remain pending in the application. Applicant’s amendments to the Specification, Drawings, and Claims have overcome most objections previously set forth in the Non-Final Office Action mailed Feb. 13, 2026. More details provided below.
Response to Arguments
Claim Objections:
Applicant amended claims and addressed all previous objections and the previous objections have been withdrawn.
Specification:
Applicant amended specification and addressed all previous objections and the previous objections have been withdrawn.
Drawings:
Applicant amended drawings and addressed most of the previous objections and those objections have been withdrawn.
Applicant amended drawings have not addressed the following reference character not mentioned in the description: Element 122 in Fig. 1. This objection has been maintained.
Double Patenting:
Applicant’s arguments, see pg. 11-12, filed May 12, 2026, with respect to double patenting have been fully considered but are moot based on new ground of rejection.
On pg. 11-12 of Applicant’s response, applicant argues that Anderson does not disclose the newly amended features in amended claims 1, 7, and 13. Examiner agrees, however the amended claims are an obvious variant of the Patented claims of Anderson. The additional limitations therefore do not make a patentably distinct invention.
35 USC § 101:
Applicant's arguments filed May 12, 2026 regarding 35 USC 101 have been fully considered but they are not persuasive.
On pg. 12-14 of Applicant’s response, applicant argues that even under the broadest reasonable interpretation the amended claims cannot be interpreted as human beings or being actions performed in a human mind. Examiner respectfully disagrees, as the additional limitations of “updating one or more model parameters of a predictive model during the first time period based on the information identifying the brain activity with the stimulus artifact signal for the first time period that was received” and “predicting…using the one or more model parameters of the predictive model that is updated for the first time period” do not add significantly more and can be done in the mind. MPEP 2106(I) Gottschalk v. Benson "held that simply implementing a mathematical principle on a physical machine, namely a computer, was not a patentable application of that principle"). Further, there is nothing the applicant’s specification that recites a structurally technologically improved circuit/computer system as the claims are directed to the use of a model applying gathered data. These added limitations could be done by a human learning from the first stimulation signal and applying that knowledge to the second signal.
On pg. 13-14 of Applicant’s response, applicant argues that the features are unlike any method of organizing human behavior and cites MPEP list of recognized methods. Examiner agrees that these limitations are not directed towards organizing human behavior, but towards mental processes. It is further noted that MPEP 2106.04(a) states the following:
To facilitate examination, the Office has set forth an approach to identifying abstract ideas that distills the relevant case law into enumerated groupings of abstract ideas. The enumerated groupings are firmly rooted in Supreme Court precedent as well as Federal Circuit decisions interpreting that precedent, as is explained in MPEP § 2106.04(a)(2). This approach represents a shift from the former case-comparison approach that required examiners to rely on individual judicial cases when determining whether a claim recites an abstract idea. By grouping the abstract ideas, the examiners’ focus has been shifted from relying on individual cases to generally applying the wide body of case law spanning all technologies and claim types.
The enumerated groupings of abstract ideas are defined as:
1) Mathematical concepts – mathematical relationships, mathematical formulas or equations, mathematical calculations (see MPEP § 2106.04(a)(2), subsection I);
2) Certain methods of organizing human activity – fundamental economic principles or practices (including hedging, insurance, mitigating risk); commercial or legal interactions (including agreements in the form of contracts; legal obligations; advertising, marketing or sales activities or behaviors; business relations); managing personal behavior or relationships or interactions between people (including social activities, teaching, and following rules or instructions) (see MPEP § 2106.04(a)(2), subsection II); and
3) Mental processes – concepts performed in the human mind (including an observation, evaluation, judgment, opinion) (see MPEP § 2106.04(a)(2), subsection III).
Examiners should determine whether a claim recites an abstract idea by (1) identifying the specific limitation(s) in the claim under examination that the examiner believes recites an abstract idea, and (2) determining whether the identified limitations(s) fall within at least one of the groupings of abstract ideas listed above. The groupings of abstract ideas, and their relationship to the body of judicial precedent, are further discussed in MPEP § 2106.04(a)(2).
For mental process, MPEP 2106.04(a)(2), subsection III states that “The courts consider a mental process (thinking) that "can be performed in the human mind, or by a human using a pen and paper" to be an abstract idea.” As stated above and in the 101 rejection, claims recite limitations that are nothing more than a person looking at a waveform, noting the first time period, learning from it, and mapping out a second time period, and deciding on a treatment plan. While not required to rely on individual cases for Step 2A, Prong One, the MPEP lists examples of claims that recite mental processes; see MPEP 2106.04(a)(2)(III)(A) “a claim to collecting and comparing known information (claim 1), which are steps that can be practically performed in the human mind, Classen Immunotherapies, Inc. v. Biogen IDEC, 659 F.3d 1057, 1067, 100 USPQ2d 1492, 1500 (Fed. Cir. 2011)”.
35 USC § 102:
Applicant’s arguments, see pg. 14-15, filed May 12, 2026 have overcome the 35 USC 102 rejections with respect to Anderson from the Feb. 13, 2026 Office Action. A new 35 USC 103 rejection below is being applied using Anderson in light of the amendments to the claim.
Applicant argues on pg. 15 that Withrow does not disclose the amended features. Examiner cannot comment as there does not appear to be a Withrow citation on record.
Drawings
The drawings are objected to as failing to comply with 37 CFR 1.84(p)(5) because they include the following reference character(s) not mentioned in the description: element 122 in Fig. 1. Corrected drawing sheets in compliance with 37 CFR 1.121(d), or amendment to the specification to add the reference character(s) in the description in compliance with 37 CFR 1.121(b) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Claim Objections
Claims 2, 8, and 14 are objected to because of the following informalities: “using the one more model parameters” should be changed to -- using the one or more model parameters --. Appropriate correction is required.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1-5, 7-11, and 13-17 are rejected on the ground of nonstatutory obviousness-type double patenting as being unpatentable over claims 1, 2, and 3 of U.S. Patent No. 11,975,199 (hereinafter referred to as “’199”) in view of Anderson et al. (WO2020/163177 published August 13, 2020, hereinafter referred to as “Anderson”) and further in view of Najafabadi et al. (Neurosci. 14:709, hereinafter referred to as “Najafabadi”). For the Anderson reference, US 11,975,199 has been used as an equivalent document for WO2020/163177.
Regarding claims 1, 7, and 13, immediately below is a reproduction of original claim 1 of the instant application on the left and claim 1 of ’199 on the right. Amended independent claims contains the additional limitations of: updating one or more model parameters of a predictive model during the first time period based on the information identifying the brain activity with the stimulus artifact signal for the first time period that was received and using the one or more model parameters of the predictive model that is updated for the first time period.
PNG
media_image1.png
328
747
media_image1.png
Greyscale
On the left, round-cornered boxes in the instant claim 1 (on the left) illustrate what is not found in claim 1 of the ‘199 (on the right). The amended limitations are also not found in the patented claim 1 (‘199).
Anderson discloses the control device may determine an artifact during the first time period associated with a prior brain stimulus, determine an artifact-removed brain activity for the first time period based on the artifact; and predict the brain activity for the second time period based on the artifact-removed brain activity (Col. 7 ln. 29-34). Anderson further discloses to reduce or eliminate the stimulus artifact from recordings, an optimized auto-regressive (AR) model (or another model) may be utilized for predicting the recorded signal during stimulation events. The predicted signal may be substituted for the stimulus artifact during active stimulation (Col. 10 ln. 23-28).
Therefore, it would have been obvious to a person having ordinary skill in the art before the filing date to have specified the brain activity as a stimulus artifact signal and predict the brain activity as a second time period without the stimulus artifact signal and insert the predicted activity into the second time period as taught by Anderson in the method of ‘199 in order to remove the effect of the stimulus and know when the apply future stimulants.
Najafabadi’s study relates to an optimal Wiener filter algorithm to predict neural recording artifacts upon delivering electrical stimulation currents on a multi-channel stimulating electrode array. The predicted artifacts are then subtracted from the actual neural recording trace to yield a noise reduced estimate of the neural activity (pg. 2-3). Compared with other artifact removal methods, the novelty of our approach is two-fold. First, it requires establishing linear filter coefficients that account for the transfer functions of each stimulus-recording interface, a process that needs only a modest amount of recording data (10−100 s). An added benefit is that the filter coefficients can be easily updated as needed to account for the temporal drifting of the stimulus-recording coupling, thus potentially allowing for adaptive artifact removal over a long recording periods (e.g., days to months). Our method is able to remove artifacts in neural recordings evoked by arbitrary stimulus waveforms (e.g., variable amplitudes, multiple channels etc.), which is not possible with conventional artifact removal algorithms. The multi-site stimulation experiments, which successfully removed the electrical artifacts using multi-channel linear Wiener filters (Figures 3, 5, 6), suggest that electrical artifacts summate linearly thus further supporting the linearity assumption (pg. 16). By numerically estimating the linear transformation between each stimulation and recording channel and accounting for the input current waveforms, our procedure is able to generalize and accurately predict artifacts that dynamically vary over time. Such an adaptive approach can potentially account for the drifting of the stimulus-recording that will be investigated in a future study. In theory, it allows the filter to be updated and optimized at any time by introducing new training data or by continuously using the recorded data itself to estimate the filter coefficients in real-time. Such iterative implementations would also allow for quantitative estimation of the stimulus-recording conditions over time, which may exhibit non-stationary behaviors for chronic recordings (e.g., due to changing electrode impedance over days or movement of electrodes, etc.) (pg. 17).
Therefore, it would have been obvious to a person having ordinary skill in the art at the time of filing to update model parameters of a predictive model during the first time period based on the information identifying the brain activity with the stimulus artifact signal for the first time period and predict using the one or more model parameters of the predictive model that is updated for the first time period as taught by Najafabadi in the method and device of Anderson and ‘199 in order to allowing for adaptive artifact removal over a long recording periods that vary overtime.
Claim 7 introduces the limitation of a device, comprising: one or more memories; and one or more processor communicatively coupled to the one of more memories. Anderson discloses a device may include one or more memories and one or more processors communicatively coupled to the one or more memories (Col. 1 ln. 39-41). Therefore, it would have been obvious to a person having ordinary skill in the art before the filing date to include one or more memories and one or more processors communicatively coupled to the one or more memories as taught by Anderson in order to carry out various method steps (Col. 6 ln. 11-20).
Claim 13 adds the limitation of a non-transitory computer readable medium comprising instructions that when executed by a hardware processor cause the hardware processor perform the method. Anderson discloses in Fig. 3 the device 300 may perform these processes based on processor 320 executing software instructions stored by a non-transitory computer-readable medium, such as memory 330 and/or storage component 340 (Col. 6 ln. 11-16). Therefore, it would have been obvious to a person having ordinary skill in the art before the filing date to use non-transitory computer readable medium comprising instructions of Anderson so that when executed by a hardware processor cause the hardware processor perform the method steps (Col. 6 ln. 11-20).
Regarding claim 2, 8, and 14, it is noted that they are recited in the square box illustrated in the screenshot of claim 1 of ‘199 above. The amended claims add the limitation of using the one more model parameters of the predictive model that is updated.
Najafabadi teaches the benefit of using one or more model parameters in claims 1, 7, and 13 rejection above. It would have been obvious to a person having ordinary skill in the art at the time of filing to incorporate the one or more model parameters of the predictive model as taught by Najafabadi into the phase determination of Anderson and ‘199 in order to improve accuracy for changing characteristics.
Claim 3-4, 9-10, and 15-16 corresponds to claim 2 of ‘199. Amended claims add the limitations of estimating one or more predictive model parameters using a brain signal as determined from the brain activity from the first time period with no stimulation artifact and a most recent updated predictive model.
Najafabadi teaches the NxM matrix containing the impulse response vectors (hnm) between all stimulation and recording channels. The goal is to derive the filter matrix h using experimental measurements. The estimated filter matrix can then be used to predict the recorded artifacts. The predicted artifacts are subtracted from the recorded data yielding the noise-reduced estimate of the neural traces… this does not distort the neural signal (pg. 3). Essentially, they collect recorded signals, correlate the data with stimulation and recording data, and predict the parameters.
Therefore, it would have been obvious to a person having ordinary skill in the art at the time of filing to estimate predictive model parameters using a brain signal as determined from the brain activity from the first time period with no stimulation artifact as taught by Najafabadi in the method and device of Anderson and ‘199 in order to properly remove stimulus-evoked artifacts that overwhelm the small neural signals of interest (pg. 1, abstract).
Najafabadi teaches by numerically estimating the linear transformation between each stimulation and recording channel and accounting for the input current waveforms, our procedure is able to generalize and accurately predict artifacts that dynamically vary over time. Such an adaptive approach can potentially account for the drifting of the stimulus-recording that will be investigated in a future study. In theory, it allows the filter to be updated and optimized at any time by introducing new training data or by continuously using the recorded data itself to estimate the filter coefficients in real-time. Such iterative implementations would also allow for quantitative estimation of the stimulus-recording conditions over time, which may exhibit non-stationary behaviors for chronic recordings (e.g., due to changing electrode impedance over days or movement of electrodes, etc.) (pg. 17).
Therefore, it would have been obvious to a person having ordinary skill in the art at the time of filing to predict based on most recent updated predictive model as taught by Najafabadi in the method and device of Anderson and ‘199 in order to allow for quantitative estimation of the stimulus-recording conditions over time since it can change over time, and therefore improves the recordings.
Claims 5 and 11 corresponds to claim 3 of ‘199.
Claim 17 adds the additional limitation of wherein the brain stimulus is caused to occur during a period of rhythmic brain activity to claim 3 of ‘199.
Claims 6, 12, and 18 are rejected on the ground of nonstatutory obviousness-type double patenting as being unpatentable over claim 5 of ’199 in view of Anderson and Najafabadi and in even further view of Park et al. (2013 6th International IEEE/EMBS Conference on Neural Engineering (NER), 2013, pg. 1410-1413, hereinafter referred to as “Park”).
Claims 6, 12, and 18 corresponds to claim 5 of ‘199. Amended claims add the limitation of the technique being adaptive and time varying.
Park’s study relates to exploring an adaptive (time-varying) parametric ARMA approach for tracking spectral changes in neural signals based on the fixed-interval Kalman smoother (pg. 1410, abstract). First, short and abrupt bursts in LFP power in epochs prior to seizures were smoothed out in the adaptive parametric estimation methods. Also, spectral changes around 20-60 Hz during ictal epochs, which were important discriminative features of epileptic seizures in the studied participant’s LFPs, became more distinct in the adaptive parametric approach. In addition, the pseudo-online approach with the fixed-interval Kalman smoother performed comparably to the offline analysis with the fixed-interval smoother, which cannot be directly applied to online applications. The advantages of the proposed adaptive parametric approach, including the improvement in separability of interictal and ictal epochs, may ultimately lead to better seizure detection schemes (pg. 1411).
Therefore, it would have been obvious to a person having ordinary skill in the art at the time of filing to use an adaptive and time varying spectral estimation technique as taught by Park in the method and device of Anderson, Najafabadi, and ‘199 in order to improve the separability of different signals and smooth the data.
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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to the abstract ideas of “updating one or more model parameters of a predictive model during the first time period based on the information identifying the brain activity with the stimulus artifact signal for the first time period that was received”; “predicting, based on the information identifying the brain activity for the first time period and using the one or more model parameters of the predictive model that is updated for the first time period, predicted brain activity without the stimulus artifact signal for a second time period that is to occur after the first time period”; “inserting the predicted brain activity into the information for a second time period”; and “determining, based on the predicted brain activity for the second time period, a brain stimulus for the second time period” without significantly more.
Step 1
Claims 1, 7, and 13 recite a method and devices, and therefore, they are a product and method, and fall within the statutory category.
Step 2A, Prong 1
Claims 1, 7, and 13 recite the limitations of updating one or more model parameters of a predictive model during the first time period based on the information identifying the brain activity with the stimulus artifact signal for the first time period that was received; predicting, based on the information identifying the brain activity for the first time period and using the one or more model parameters of the predictive model that is updated for the first time period, predicted brain activity without the stimulus artifact signal for a second time period that is to occur after the first time period; inserting the predicted brain activity into the information for a second time period; and determining, based on the predicted brain activity for the second time period, a brain stimulus for the second time period. The limitations, as drafted, are a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of “receiving, from one or more electrodes, information identifying brain activity with a stimulus artifact signal for a first time period”. Claim 7 additionally recites “one or more memories”, and “one or more processors”, which is a computer processor. Further, claim 13 additionally recites “a non-transitory computer readable medium comprising instructions that when executed by a hardware processor cause the hardware processor perform a method”.
That is, other than reciting “receiving, from one or more electrodes, information identifying brain activity with a stimulus artifact signal for a first time period”, “one or more memories”, “one or more processors”, and “a non-transitory computer readable medium comprising instructions that when executed by a hardware processor cause the hardware processor perform a method”, nothing in the claim precludes the steps from practically being performed in the human mind. MPEP 2106.04(a)(2)(III) states that the courts consider a mental process (thinking) that "can be performed in the human mind, or by a human using a pen and paper" to be an abstract idea. For example, aside from the “one or more electrodes”, “brain stimulus”, “one or more memories”, “one or more processors” and “non-transitory computer readable medium” language, the claims encompasses the user inspecting a brain signal output, identifying the brain activity for a first period of time, predicting what the next period of time will look like based on the first time period and determining when to activate another brain stimulus. For example, these limitations are nothing more than a person looking at a waveform, noting the first time period, learning from it, and mapping out a second time period, and deciding on a treatment plan. The limitation of “causing the brain stimulus to be applied the second time period” under BRI is nothing more than a treatment plan being developed mentally or being provided to a patient, which do not necessarily include the active treatment being given to a patient. This is a mental process.
Step 2A, Prong 2
The claims recites additional elements: “receiving, from one or more electrodes, information identifying brain activity with a stimulus artifact signal for a first time period”, “causing the brain stimulus to be applied the second time period”, “one or more memories”, “one or more processors”, and “a non-transitory computer readable medium comprising instructions that when executed by a hardware processor cause the hardware processor perform a method” to perform the abstract steps.
The system for determining predicting brain activity consisting of the “memories”, “processor” and “non-transitory computer readable medium” read on a computer implemented system and are recited at a high level of generality, i.e., as a generic processor with memory, performing a generic computer function of processing and storing data and displaying that data. This generic limitation is no more than mere instructions to apply the exception using generic computer components (see ¶[0065], ¶[0066], ¶[0068]). Accordingly, this additional limitation does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
The “receiving, from one or more electrodes, information identifying brain activity with a stimulus artifact signal for a first time period” is recited at a high level of generality (i.e., claimed broadly encompassing “a measurement electrode… for sensing a phase, a frequency, and amplitude, cross-frequency coupling, and/or the like of brain activity… mounted onto a head, a measurement device surgically implanted into a head of the patient, or and/or the like” ¶[0041], and other options capable of this type of measurement) and amount to no more than pre-solution activity of data gathering by the system to analyze the brain activity.
Step 2B
As discussed with respect to Step 2A Prong Two, the additional elements in the claim amount to no more than mere instructions to apply the exception using a generic computer component, pre solution activity and a post solution activity that is not directed by the abstract idea. The same analysis applies here in 2B, i.e., mere instructions to apply an exception on a generic computer cannot integrate a judicial except into a practical application at Step 2A or provide an inventive concept in Step 2B.
Under 2019 PEG, a conclusion that an additional element is insignificant extra-solution activity in Step 2A should be re-evaluated in Step 2B to determine if it is more than what is well- understood, routine, conventional activity in the field. The specification in ¶[0065], ¶[0066], and ¶[0068] does not provide any indication that the computer processor, memory, and non-transitory computer readable medium is anything other than a generic, off-the shelf computer component. Court decisions cited in MPEP 2106.05(d)(II) indicate that computer‐ implemented processes not to be significantly more than an abstract idea (and thus ineligible) where the claim as a whole amounts to nothing more than generic computer functions merely used to implement an abstract idea, such as an idea that could be done by a human analog (i.e., by hand or by merely thinking). Accordingly, a conclusion that the generic computer functions merely being used to implement an abstract idea is well- understood, routine, conventional activity is supported under Berkheimer Option 2.
As discussed with respect to Step 2A Prong Two, the “receiving, from one or more electrodes, information identifying brain activity with a stimulus artifact signal for a first time period” is recited at a high level of generality (i.e., “a measurement electrode” ¶[0041]) which individually and in combination amount to no more than pre-solution activity of data gathering by the system to analyze brain activity. This pre- solution activity of obtaining brain activity using electrodes is well- understood, routine, and conventional technology in the field of neurology: “Intracranial EEG (iEEG) is the most effective method for functional localization of the [seizure onset zones]; invasive electrodes are implanted and monitored for several days” (Miller K. et al. “Chapter 7 Biomechanical Modelling of the Brain for Neuronavigation in Epilepsy Surgery”. Biomechanics of the Brain, Biological and Medical Physics. pg 166. 2019. https://doi.org/10.1007/978-3-030-04996-6_7 ). All uses of the recited abstract idea require the pre-solution of data gathering.
Dependent claims 2-6, 8-12, and 14-20 add additional abstract limitations or further limit the process of updating one or more model parameters of a predictive model during the first time period based on the information identifying the brain activity with the stimulus artifact signal for the first time period that was received; predicting, based on the information identifying the brain activity for the first time period and using the one or more model parameters of the predictive model that is updated for the first time period, predicted brain activity without the stimulus artifact signal for a second time period that is to occur after the first time period; inserting the predicted brain activity into the information for a second time period; and determining, based on the predicted brain activity for the second time period, a brain stimulus for the second time period. Therefore, these claims further limit the abstract idea already indicated in independent claims 1, 7, and 13 and they are ineligible for the same reasons provided for claims 1, 7, and 13 above.
For these reasons, there is no inventive concept in the claims and thus they are ineligible.
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.
Claims 1-5, 7-11, and 13-17 are rejected under 35 U.S.C. 103 as being unpatentable over Anderson et al. (WO 2020163177 A1, published August 13, 2020, hereinafter referred to as “Anderson”), in view of Najafabadi et al. (Neurosci. 14:709, hereinafter referred to as “Najafabadi”).
Regarding claims 1, 7, and 13, Anderson teaches a method and a device (Fig. 3 “device 300” in ¶[0024]), comprising: one or more memories (Fig. 3 “memory 330” in ¶[0024]); and one or more processors (Fig. 3 “processor 320” in ¶[0024]) communicatively coupled to the one or more memories (“a device may include one or more memories and one or more processors communicatively coupled to the one or more memories” in ¶[0033]), configured to: receive, from one or more electrodes, information identifying brain activity with a stimulus artifact signal for a first time period (“Fig. 4, process 400 may include receiving, from one or more electrodes, information identifying brain activity for a first time period (block 410)” in ¶[0033] and “the control device may determine an artifact during the first time period associated with a prior brain stimulus” in ¶[0038]); predict, based on the information identifying the brain activity for the first time period, predicted brain activity without the stimulus artifact signal for a second time period that is to occur after the first time period (“Fig. 4, process 400 may include predicting, based on the information identifying the brain activity for the first time period, predicted brain activity for a second time period that is to occur after the first time period (block 420)” in ¶[0034] and “determine an artifact-removed brain activity for the first time period based on the artifact; and predict the brain activity for the second time period based on the artifact-removed brain activity” in ¶[0038]); insert the predicted brain activity into the information for a second time period (Fig. 10A “to reduce or eliminate the stimulus artifact from recordings, an optimized auto-regressive (AR) model (or another model) may be utilized for predicting the recorded signal during stimulation events. The predicted signal may be substituted for the stimulus artifact during active stimulation” in ¶[0068]); determine, based on the predicted brain activity for the second time period, a brain stimulus for the second time period (“Fig. 4, process 400 may include determining, based on the predicted brain activity for the second time period, a brain stimulus for the second time period … (block 430)” in ¶[0035]); and cause the brain stimulus to be applied the second time period (“Fig. 4, process 400 may include causing the brain stimulus to be applied in accordance with the frequency and the phase during the second time period (block 440)” in ¶[0036]).
Anderson further teaches the claim 13 limitation a non-transitory computer readable medium comprising instructions that when executed by a hardware processor cause the hardware processor perform the method (Fig. 3 “Device 300 may perform these processes based on processor 320 executing software instructions stored by a non-transitory computer-readable medium, such as memory 330 and/or storage component 340” in ¶[0029]).
Anderson does not disclose updating one or more model parameters of a predictive model during the first time period based on the information identifying the brain activity with the stimulus artifact signal for the first time period that was received, and predicting using the one or more model parameters of the predictive model that is updated for the first time period.
Najafabadi’s study relates to an optimal Wiener filter algorithm to predict neural recording artifacts upon delivering electrical stimulation currents on a multi-channel stimulating electrode array. The predicted artifacts are then subtracted from the actual neural recording trace to yield a noise reduced estimate of the neural activity (pg. 2-3). Compared with other artifact removal methods, the novelty of our approach is two-fold. First, it requires establishing linear filter coefficients that account for the transfer functions of each stimulus-recording interface, a process that needs only a modest amount of recording data (10−100 s). An added benefit is that the filter coefficients can be easily updated as needed to account for the temporal drifting of the stimulus-recording coupling, thus potentially allowing for adaptive artifact removal over a long recording periods (e.g., days to months). Our method is able to remove artifacts in neural recordings evoked by arbitrary stimulus waveforms (e.g., variable amplitudes, multiple channels etc.), which is not possible with conventional artifact removal algorithms. The multi-site stimulation experiments, which successfully removed the electrical artifacts using multi-channel linear Wiener filters (Figures 3, 5, 6), suggest that electrical artifacts summate linearly thus further supporting the linearity assumption (pg. 16). By numerically estimating the linear transformation between each stimulation and recording channel and accounting for the input current waveforms, our procedure is able to generalize and accurately predict artifacts that dynamically vary over time. Such an adaptive approach can potentially account for the drifting of the stimulus-recording that will be investigated in a future study. In theory, it allows the filter to be updated and optimized at any time by introducing new training data or by continuously using the recorded data itself to estimate the filter coefficients in real-time. Such iterative implementations would also allow for quantitative estimation of the stimulus-recording conditions over time, which may exhibit non-stationary behaviors for chronic recordings (e.g., due to changing electrode impedance over days or movement of electrodes, etc.) (pg. 17).
Therefore, it would have been obvious to a person having ordinary skill in the art at the time of filing to update model parameters of a predictive model during the first time period based on the information identifying the brain activity with the stimulus artifact signal for the first time period and predict using the one or more model parameters of the predictive model that is updated for the first time period as taught by Najafabadi in the method and device of Anderson in order to allowing for adaptive artifact removal over a long recording periods that vary overtime.
Regarding claims 2, 8, and 14, Anderson teaches wherein the brain stimulus is associated with a frequency and a phase determined based on the predicted brain activity for the second time period (“Fig. 4, process 400 … wherein the brain stimulus is associated with a frequency and a phase determined based on the predicted brain activity for the second time period (block 430)” in ¶[0035]).
Anderson does not disclose phase determination using the one or more model parameters of the predictive model that is updated.
Najafabadi teaches the benefit of using one or more model parameters in claims 1, 7, and 13 rejection above. It would have been obvious to a person having ordinary skill in the art at the time of filing to incorporate the one or more model parameters of the predictive model as taught by Najafabadi into the phase determination of Anderson in order to improve accuracy for changing characteristics.
Regarding claims 3, 9, and 15, Anderson teaches wherein the method and one or more processors communicatively coupled to the one or more memories are further configured to: determining the stimulus artifact signal during the first time period associated with a prior brain stimulus; and determining an artifact-removed brain activity for the first time period based on the artifact (“the control device may determine an artifact during the first time period associated with a prior brain stimulus; determine an artifact-removed brain activity for the first time period based on the artifact” in ¶[0038]).
Anderson does not disclose estimating one or more predictive model parameters using a brain signal as determined from the brain activity from the first time period with no stimulation artifact.
Najafabadi teaches the NxM matrix containing the impulse response vectors (hnm) between all stimulation and recording channels. The goal is to derive the filter matrix h using experimental measurements. The estimated filter matrix can then be used to predict the recorded artifacts. The predicted artifacts are subtracted from the recorded data yielding the noise-reduced estimate of the neural traces… this does not distort the neural signal (pg. 3). Essentially, they collect recorded signals, correlate the data with stimulation and recording data, and predict the parameters.
Therefore, it would have been obvious to a person having ordinary skill in the art at the time of filing to estimate predictive model parameters using a brain signal as determined from the brain activity from the first time period with no stimulation artifact as taught by Najafabadi in the method and device of Anderson in order to properly remove stimulus-evoked artifacts that overwhelm the small neural signals of interest (pg. 1, abstract).
Regarding claims 4, 10, and 16, Anderson teaches wherein predicting the brain activity for the second time period further comprises: predicting the brain activity for the second time period based on the artifact- removed brain activity (“predict the brain activity for the second time period based on the artifact-removed brain activity” in ¶[0038]).
Anderson does not disclose predicting based on a most recent updated predictive model.
Najafabadi teaches by numerically estimating the linear transformation between each stimulation and recording channel and accounting for the input current waveforms, our procedure is able to generalize and accurately predict artifacts that dynamically vary over time. Such an adaptive approach can potentially account for the drifting of the stimulus-recording that will be investigated in a future study. In theory, it allows the filter to be updated and optimized at any time by introducing new training data or by continuously using the recorded data itself to estimate the filter coefficients in real-time. Such iterative implementations would also allow for quantitative estimation of the stimulus-recording conditions over time, which may exhibit non-stationary behaviors for chronic recordings (e.g., due to changing electrode impedance over days or movement of electrodes, etc.) (pg. 17).
Therefore, it would have been obvious to a person having ordinary skill in the art at the time of filing to predict based on most recent updated predictive model as taught by Najafabadi in the method and device of Anderson in order to allow for quantitative estimation of the stimulus-recording conditions over time since it can change over time, and therefore improves the recordings.
Regarding claims 5, 11, and 17, Anderson teaches wherein the brain stimulus is caused to occur during a period of rhythmic brain activity (“the brain stimulus is caused to occur during a period of rhythmic brain activity in accordance with the frequency” in ¶[0040]).
Claims 6, 12, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Anderson in view of Najafabadi (hereinafter referred to as “modified Anderson”) as applied to claims 1, 7, and 13, and in further view of Park et al. (2013 6th International IEEE/EMBS Conference on Neural Engineering (NER), 2013, pg. 1410-1413, hereinafter referred to as “Park”).
Regarding claims 6, 12, and 18, modified Anderson teaches the method and device of claims 1, 7, and 13. Anderson also teaches wherein predicting the brain activity for the second time period further comprises: predicting the brain activity using a parametric spectral estimation technique for modeling band limited oscillations (“the control device may predict the brain activity using a parametric spectral estimation technique for modeling band limited oscillations” in ¶[0042]).
Modified Anderson does not disclose the parametric spectral estimation technique being adaptive and time varying.
Park’s study relates to exploring an adaptive (time-varying) parametric ARMA approach for tracking spectral changes in neural signals based on the fixed-interval Kalman smoother (pg. 1410, abstract). First, short and abrupt bursts in LFP power in epochs prior to seizures were smoothed out in the adaptive parametric estimation methods. Also, spectral changes around 20-60 Hz during ictal epochs, which were important discriminative features of epileptic seizures in the studied participant’s LFPs, became more distinct in the adaptive parametric approach. In addition, the pseudo-online approach with the fixed-interval Kalman smoother performed comparably to the offline analysis with the fixed-interval smoother, which cannot be directly applied to online applications. The advantages of the proposed adaptive parametric approach, including the improvement in separability of interictal and ictal epochs, may ultimately lead to better seizure detection schemes (pg. 1411).
Therefore, it would have been obvious to a person having ordinary skill in the art at the time of filing to use an adaptive and time varying spectral estimation technique as taught by Park in the method and device of modified Anderson in order to improve the separability of different signals and smooth the data.
Claims 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over modified Anderson as applied to claim 1, and in further view of Liu et al. (Ind. Eng. Chem. Res. 2021, 60, 7, 2971–2982, hereinafter referred to as “Liu”).
Regarding claims 19-20, modified Anderson teaches the method of claim 1.
Modified Anderson does not teach wherein the predictive model comprises a state prediction model that analyzes brain recording signals and a parameter prediction model that estimates model parameters, wherein the state prediction model and the parameter prediction model operate simultaneously and are interconnected.
Liu’s study relates to state and parameter estimation. State and parameter estimation is essential for process monitoring and control. This paper concerns the simultaneous state and parameter estimation when the augmented system is not fully observable (abstract). State and parameter estimation is essential for process modeling, monitoring, control, and fault diagnosis, which has been extensively applied in various fields including petrochemical, oil refining, paper making, electric power, and aerospace (pg. 2971). For simultaneous state and parameter estimation of system we consider augmenting the parameters as states, which is a rather standard approach in simultaneous state and parameter estimation (pg. 2974).
Therefore, it would have been obvious to a person having ordinary skill in the art at the time of filing to have the predictive model comprise a state prediction model that analyzes the brain recording signals and a parameter prediction model that estimates the model parameters, wherein the state prediction model and the parameter prediction model operate simultaneously and are interconnected as taught by Liu in the method of modified Anderson because state and parameter prediction models are essential for process modeling, monitoring, etc. and simultaneous systems are a standard approach.
Conclusion
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 Emily N Cirulnick whose telephone number is (571)272-9734. The examiner can normally be reached M-F 8-4:30 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, Unsu Jung can be reached at (571) 272-8506. 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.
/E.N.C./Patent Examiner, Art Unit 3792
/UNSU JUNG/Supervisory Patent Examiner, Art Unit 3792
Prosecution Insights