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 on October 29, 2025 was considered by the examiner. Claims 1-22 are pending in the application.
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 1-22 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 recites “wherein the one or more predicted SO values each indicate a predicted value of the SO at the future time at which the SO will exhibit the target morphology” in lines 17-19, which is generally unclear. It appears as if this recitation is redundant, and it is not clear what is further limiting by this statement. The recitation “a predicted value of the SO” is recited in line 18, but it is not clear if this recitation is the same as, related to, or different from the recitation “one or more predicted SO values” in lines 15-16. The similar phraseology and context of the claim suggest that they are the same, but the indefinite article “a” suggests that they are different. These inconsistencies render claim 1 indefinite. Appropriate correction is required.
Claims 2-20 are rejected by virtue of their dependence from claim 1.
Claim 11 recites “a target SO morphology” in line 3, but it is not clear if this recitation is the same as, related to, or different from the recitation “a target morphology” in claim 1, line 17. The similar phraseology suggests that they are the same, but the indefinite article “a” suggests that they are different. The recitation of claim 1 “comprises a peak of the SO”; and the recitation of claim 11 “represent[s] an example of an SO morphology that conforms to a first SO wave morphology”. These modifying recitations are not mutually exclusive, so the relationship between the two recitations remains unclear. If the recitations are the same, the present recitation should be “the target SO morphology”. If the recitations are different, the relationship between these recitations should be made clear and they should be clearly distinguished from each other (e.g., when multiple elements have similar or the same labels, distinct identifiers such as “first” and “second” should be used to clearly differentiate the elements). For the purposes of examination, the examiner is interpreting that the recitations are different. Appropriate correction is required.
Claim 11 recites “a first SO” in line 7, but it is not clear if this recitation is the same as, related to, or different from the recitation “a first SO” in line 5. The similar phraseology suggests that they are the same, but the indefinite article “a” suggests that they are different. If the recitations are the same, the present recitation should be “the first SO”. If the recitations are different, the relationship between these recitations should be made clear and they should be clearly distinguished from each other (e.g., when multiple elements have similar or the same labels, distinct identifiers such as “first” and “second” should be used to clearly differentiate the elements). For the purposes of examination, the examiner is interpreting that the recitations are the same. Appropriate correction is required.
Claim 15 recites “one or more features” in line 7. A claim, although clear on its face, may also be indefinite when a conflict or inconsistency between the claimed subject matter and the specification disclosure renders the scope of the claim uncertain as inconsistency with the specification disclosure or prior art teachings may make an otherwise definite claim take on an unreasonable degree of uncertainty. See MPEP § 2173.03. In this case, the specification details that SO features are extracted from the SO (see specification ¶[0014]-[0015]), including SO morphological features (see specification ¶[0094]). This detail is reflected in the claim with the extracted SO parameters (which is not recited in the specification itself). Therefore, it is not clear what relation the “one or more features” of claim 15 line 7 has with the SO parameters; because, based on the specification, they appear to be the same thing. The confusion between the two terms renders claim 15 indefinite. Appropriate correction is required.
Claim 17 recites “a plurality of training SO samples” in line 2, but it is not clear if this recitation is the same as, related to, or different from the recitation “a set of training SO samples” in claim 16 line 3. The similar phraseology suggests that they are the same (plurality/set both describe multiple), but the indefinite article “a” suggests that they are different. If the recitations are the same, the present recitation should be “the set of training SO samples”. If the recitations are different, the relationship between these recitations should be made clear and they should be clearly distinguished from each other (e.g., when multiple elements have similar or the same labels, distinct identifiers such as “first” and “second” should be used to clearly differentiate the elements). For the purposes of examination, the examiner is interpreting that the recitations are the same. Appropriate correction is required.
Claim 20 recites the limitation "the one or more training features" in line 3. There is insufficient antecedent basis for this limitation in the claim. Amending the recitation to recite “the one or more training SO parameters” would overcome this rejection. The claim is being interpreted as such for the purposes of examination. Appropriate correction is required.
Claim 21 recites “wherein the one or more predicted SO values each indicate a predicted value of the SO at the future time at which the SO will exhibit the target morphology” in lines 9-11, which is generally unclear. It appears as if this recitation is redundant, and it is not clear what is further limiting by this statement. The recitation “a predicted value of the SO” is recited in line 10, but it is not clear if this recitation is the same as, related to, or different from the recitation “one or more predicted SO values” in line 7. The similar phraseology and context of the claim suggest that they are the same, but the indefinite article “a” suggests that they are different. These inconsistencies render claim 21 indefinite. Appropriate correction is required.
Claim 22 recites “wherein the one or more predicted SO values each indicate a predicted value of the SO at the future time at which the SO will exhibit the target morphology” in lines 9-11, which is generally unclear. It appears as if this recitation is redundant, and it is not clear what is further limiting by this statement. The recitation “a predicted value of the SO” is recited in line 10, but it is not clear if this recitation is the same as, related to, or different from the recitation “one or more predicted SO values” in line 7. The similar phraseology and context of the claim suggest that they are the same, but the indefinite article “a” suggests that they are different. These inconsistencies render claim 21 indefinite. 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 1-6, 9-15, and 21-22 are provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over claims 26 and 35-40 of copending Application No. 18/742,949 (reference application – US Patent Application 2024/0324942, cited by Applicant) in view of Choe et al. (US Patent Application Publication 2018/0221661), hereinafter Choe. Although the claims at issue are not identical, they are not patentably distinct from each other.
This is a provisional nonstatutory double patenting rejection because the patentably indistinct claims have not in fact been patented.
Regarding Claims 1-6, 9-15, and 21-22, all elements of application claims 1-6, 9-15, and 21-22 are present in and correspond to copending claims 26 and 35-40, except that the target morphology comprises a peak of the SO.
Choe teaches a system for synchronization of neurostimulation interventions (see abstract and Fig. 7), in which the system predicts upcoming events in sleep slow-wave oscillations, such as a peak, for the intervention to be delivered, at a specific point in time in the future (see ¶[0065], ¶[0069]-[0070], and ¶[0076]-[0078]; Figs. 4 and 6), in which the incoming signals (i.e., EEG signals) are classified (see ¶[0011], ¶[0062], and ¶[0068]; Fig. 3).
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to predict a future point in time with a target morphology (i.e., a predicted slow wave peak) utilizing the prediction in copending claims 26 and 35-40 as taught in Choe because (1) it is the application of a known technique to a known device/method ready for improvement to yield predictable results; and/or (2) predicting sleep stages at a future time point would give better understanding to how the user would react to the given stimulation; and/or (3) the output morphological features would better indicate how what type of sleep activity the user is experiencing, including a desired deeper sleep, slow wave oscillation period; and/or (4) the slow wave peak timing of stimulation would insure stimulation at the correct temporal targets (see Choe ¶[0076]-[0078]; Figs. 4 and 6).
Claims 7-8 are provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over claims 35-40 of copending Application No. 18/742,949 (reference application) in view of Choe as applied to claim 1 above, and in view of Garcia Molina (US Patent Application 2021/0138185 – cited in prior action), hereinafter Molina ‘185.
Regarding Claim 7, all elements of application claim 7 are present in and correspond to the modified copending claims 35-40, except the electrical stimulation.
Molina ‘185 teaches a prediction of a user’s slow wave response to stimulation and updating the stimulation based on the determination (see abstract and Figs. 1-4). Molina ‘185 teaches a system/method for providing stimulation to a user (see abstract and Fig. 4), the system comprising:
a device (¶[0028] the headset 201; Figs. 1-2) comprising:
one or more electroencephalogram (EEG) sensors (¶[0026] and ¶[0028] the sensor 14 comprising sensing electrodes for generation of the EEG signals; Figs. 1-2); and
stimulation generation circuitry configured to deliver the stimulation to a targeted area of the user (abstract and ¶[0028]-[0030] the stimulator 16 to deliver audio stimulation (such as via a speaker), electric and/or, visual stimulation; Figs. 1-2);
one or more processors (¶[0028] processor 20; Figs. 1-2); and
a memory storing instructions that, when executed by the one or more processors (¶[0028] and ¶[0066] electronic storage 22; Figs. 1-2), cause the one or more processors to:
receive, from the one or more EEG sensors of the device, an EEG signal that indicates ongoing brain activity of the user (¶[0026]-[0028] and ¶[0036]-[0038] the EEG signal output from the sensor 14, including sensing electrodes);
identify, based on the EEG signal, a slow oscillation (SO) of the ongoing brain activity (¶[0009]-[0010] stimulated and unstimulated slow wave brain activity is detected, ¶[0038] brain activity parameters are determined from the EEG signal, including slow wave parameters of amplitude, frequency, timing, ¶[0056]-[0058] the stimulation is delivered during a period after a zero-crossing, or second zero-crossing of a slow wave, calculate average and/or running average of data; Fig. 4);
extract one or more SO parameters from the SO of the ongoing brain activity (¶[0038] brain activity parameters are determined from the EEG signal, including slow wave parameters of amplitude, frequency, timing, ¶[0056]-[0058] the stimulation is delivered during a period after a zero-crossing, or second zero-crossing of a slow wave, calculate average and/or running average of data; Figs. 3-4);
determine, based on the one or more SO parameters (¶[0041] the output signals from the sensors, the EEG data, is input into the neural network model; Fig. 3), one or more predicted SO values, wherein the one or more predicted SO values each correspond to a prediction (¶[0041] and ¶[0051]-[0053] the output of the neural network model are values that are used to indicate the predicted sleep stage of the user based on the stimulation, ¶[0037] the predicted sleep stage relates to slow wave deep sleep); and
determine, based on the one or more predicted SO values, one or more parameters of the stimulation for delivery by the stimulation generation circuitry (¶[0042]-[0050] and ¶[0054]-[0055] the stimulation parameters are made and modulated based on the output from the neural network model, the stimulation is updated based on the neural network output and sensor output; Figs. 2-4).
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to utilize the electrical stimulation of Molina ‘185 with the stimulation in the modified copending claims 35-40 because (1) it is the application of a known technique to a known device/method ready for improvement to yield predictable results and/or (2) the electrical stimulation may provide added benefit to the user not achievable with the audio stimulation alone.
Regarding Claim 8, all elements of application claim 8 are present in and correspond to the modified copending claims 35-40, except the optical stimulation.
Molina ‘185 teaches a prediction of a user’s slow wave response to stimulation and updating the stimulation based on the determination (see abstract and Figs. 1-4). Molina ‘185 teaches a system/method for providing stimulation to a user (see abstract and Fig. 4), the system comprising:
a device (¶[0028] the headset 201; Figs. 1-2) comprising:
one or more electroencephalogram (EEG) sensors (¶[0026] and ¶[0028] the sensor 14 comprising sensing electrodes for generation of the EEG signals; Figs. 1-2); and
stimulation generation circuitry configured to deliver the stimulation to a targeted area of the user (abstract and ¶[0028]-[0030] the stimulator 16 to deliver audio stimulation (such as via a speaker), electric and/or, visual stimulation; Figs. 1-2);
one or more processors (¶[0028] processor 20; Figs. 1-2); and
a memory storing instructions that, when executed by the one or more processors (¶[0028] and ¶[0066] electronic storage 22; Figs. 1-2), cause the one or more processors to:
receive, from the one or more EEG sensors of the device, an EEG signal that indicates ongoing brain activity of the user (¶[0026]-[0028] and ¶[0036]-[0038] the EEG signal output from the sensor 14, including sensing electrodes);
identify, based on the EEG signal, a slow oscillation (SO) of the ongoing brain activity (¶[0009]-[0010] stimulated and unstimulated slow wave brain activity is detected, ¶[0038] brain activity parameters are determined from the EEG signal, including slow wave parameters of amplitude, frequency, timing, ¶[0056]-[0058] the stimulation is delivered during a period after a zero-crossing, or second zero-crossing of a slow wave, calculate average and/or running average of data; Fig. 4);
extract one or more SO parameters from the SO of the ongoing brain activity (¶[0038] brain activity parameters are determined from the EEG signal, including slow wave parameters of amplitude, frequency, timing, ¶[0056]-[0058] the stimulation is delivered during a period after a zero-crossing, or second zero-crossing of a slow wave, calculate average and/or running average of data; Figs. 3-4);
determine, based on the one or more SO parameters (¶[0041] the output signals from the sensors, the EEG data, is input into the neural network model; Fig. 3), one or more predicted SO values, wherein the one or more predicted SO values each correspond to a prediction (¶[0041] and ¶[0051]-[0053] the output of the neural network model are values that are used to indicate the predicted sleep stage of the user based on the stimulation, ¶[0037] the predicted sleep stage relates to slow wave deep sleep); and
determine, based on the one or more predicted SO values, one or more parameters of the stimulation for delivery by the stimulation generation circuitry (¶[0042]-[0050] and ¶[0054]-[0055] the stimulation parameters are made and modulated based on the output from the neural network model, the stimulation is updated based on the neural network output and sensor output; Figs. 2-4).
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to utilize the visual stimulation of Molina ‘185 with the stimulation in the modified copending claims 35-40 because (1) it is the application of a known technique to a known device/method ready for improvement to yield predictable results and/or (2) the visual stimulation may provide added benefit to the user not achievable with the audio stimulation alone.
Claims 16-17 and 20 are provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over claims 35-40 of copending Application No. 18/742,949 (reference application) in view of Choe, and in view of Garcia Molina et al. (US Patent Application 2019/0344042 – cited in prior action), hereinafter Molina ‘042.
Regarding Claims 16-17 and 20, all elements of application claims 16-17 and 20 are present in and correspond to the modified copending claims 35-40, except the SO classifier.
Molina ‘042 teaches a system and method for delivery sensory stimulation to a user during a sleep session based on sensor data, including EEG data from EEG electrodes (see abstract and ¶[0024]-[0025]; Fig. 2) in which a neural network uses brain activity parameters determined from the sensor data to predict sleep stages that will occur at future times during the sleep session of the user, so that stimulation may be applied during the appropriate sleep stage via the control component (see abstract and ¶[0037]-[0044]; Figs. 2-3), in which the deep sleep is related to slow wave activity of the user (see ¶[0034]-[0035]; see also ¶[0052] and Fig. 6, the output of the neural network may include frequency morphology output, including of the slow wave oscillations).
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to utilize the future time and morphological neural network prediction of Molina ‘042 for the prediction in the modified copending claims 35-40 because (1) it is the application of a known technique to a known device/method ready for improvement to yield predictable results; and/or (2) predicting sleep stages at a future time point would give better understanding to how the user would react to the given stimulation; and/or (3) the output morphological features would better indicate how what type of sleep activity the user is experiencing, including a desired deeper sleep, slow wave oscillation period; and/or (4) neural networks are known element in the art to provide the claimed function of predictions.
Claim 18 is provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over claims 35-40 of copending Application No. 18/742,949 (reference application) in view of Choe and Molina ‘042 as applied to claim 17 above, and in view of Molina et al. (US Patent Application 2020/0306494 – cited in prior action), hereinafter Molina ‘494.
Regarding Claim 18, all elements of application claim 18 are present in and correspond to the modified copending claims 35-40 in view of Molina ‘042, except the preprocessing of the SO samples.
Molina ‘494 teaches a system that utilizes a deep neural network and only frontal electrodes to detect N3 sleep (see abstract) in which bands of interest may be preprocessed via a band-pass filter (see ¶[0050] and ¶[0069], see also ¶[0073] filtering to boost a delta portion of the EEG signal for slow wave detection).
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to utilize the band-pass filtering of the band of interest of Molina ‘494 with the band of interest (i.e., the slow wave portion) in the modified copending claims 35-40 because (1) it is the application of a known technique to a known device/method ready for improvement to yield predictable results and/or (2) filtering out only the portion of interest in the EEG signal would help to reduce noise and other extraneous elements for less computationally intensive processing of the EEG signal.
Claim 19 is provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over claims 35-40 of copending Application No. 18/742,949 (reference application) in view of Choe, Molina ‘042, and Molina ‘494 as applied to claim 18 above, and in view of Fallahpour (US Patent Application Publication 2023/0321392 – cited in prior action), hereinafter Fallahpour.
Regarding Claim 19, all elements of application claim 19 are present in and correspond to the modified copending claims 35-40 in view of Molina ‘042 and Molina ‘494, except training the neural network with real-time data and associated filter.
Fallahpour teaches about a feedback system to help a subject achieve a target state of consciousness via real-time received EEG data (see abstract), in which an artificial-intelligence engine may be utilized to process the data (see ¶[0065]), and the machine-learning approach may be fine-tuned (i.e., the training is updated) with real-time EEG data from the subject so as to personalize and update the machine learning approach to the subject in real-time (see ¶[0067]).
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to utilize the real-time EEG fine-tuning of the model of Fallahpour with the real-time EEG data and neural network in the modified copending claims 35-40 because (1) it is the application of a known technique to a known device/method ready for improvement to yield predictable results and/or (2) fine-tuning the model in real-time with the real-time EEG data would improve the accuracy of the neural network by personalizing the model to the user (see Fallahpour ¶[0067]).
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 1-2, 5, 7-10, 14-17, and 21-22 are rejected under 35 U.S.C. 103 as being unpatentable over Garcia Molina (US Patent Application 2021/0138185 – cited in prior action), hereinafter Molina ‘185, and in view of Choe et al. (US Patent Application Publication 2018/0221661), hereinafter Choe.
Regarding Claims 1 and 21-22, Molina ‘185 teaches a prediction of a user’s slow wave response to stimulation and updating the stimulation based on the determination (see abstract and Figs. 1-4). Molina ‘185 teaches a system/method for providing stimulation to a user (see abstract and Fig. 4), the system comprising:
a device (¶[0028] the headset 201; Figs. 1-2) comprising:
one or more electroencephalogram (EEG) sensors (¶[0026] and ¶[0028] the sensor 14 comprising sensing electrodes for generation of the EEG signals; Figs. 1-2); and
stimulation generation circuitry configured to deliver the stimulation to a targeted area of the user (abstract and ¶[0028]-[0030] the stimulator 16 to deliver audio stimulation (such as via a speaker), electric and/or, visual stimulation; Figs. 1-2);
one or more processors (¶[0028] processor 20; Figs. 1-2); and
a memory storing instructions that, when executed by the one or more processors (¶[0028] and ¶[0066] electronic storage 22; Figs. 1-2), cause the one or more processors to:
receive, from the one or more EEG sensors of the device, an EEG signal that indicates ongoing brain activity of the user (¶[0026]-[0028] and ¶[0036]-[0038] the EEG signal output from the sensor 14, including sensing electrodes);
identify, based on the EEG signal, a slow oscillation (SO) of the ongoing brain activity (¶[0009]-[0010] stimulated and unstimulated slow wave brain activity is detected, ¶[0038] brain activity parameters are determined from the EEG signal, including slow wave parameters of amplitude, frequency, timing, ¶[0056]-[0058] the stimulation is delivered during a period after a zero-crossing, or second zero-crossing of a slow wave, calculate average and/or running average of data; Fig. 4);
extract one or more SO parameters from the SO of the ongoing brain activity (¶[0038] brain activity parameters are determined from the EEG signal, including slow wave parameters of amplitude, frequency, timing, ¶[0056]-[0058] the stimulation is delivered during a period after a zero-crossing, or second zero-crossing of a slow wave, calculate average and/or running average of data; Figs. 3-4);
determine, based on the one or more SO parameters (¶[0041] the output signals from the sensors, the EEG data, is input into the neural network model; Fig. 3), one or more predicted SO values, wherein the one or more predicted SO values each correspond to a prediction (¶[0041] and ¶[0051]-[0053] the output of the neural network model are values that are used to indicate the predicted sleep stage of the user based on the stimulation, ¶[0037] the predicted sleep stage relates to slow wave deep sleep); and
determine, based on the one or more predicted SO values, one or more parameters of the stimulation for delivery by the stimulation generation circuitry (¶[0042]-[0050] and ¶[0054]-[0055] the stimulation parameters are made and modulated based on the output from the neural network model, the stimulation is updated based on the neural network output and sensor output; Figs. 2-4).
Molina ‘185 does not specifically teach that the one or more predicted SO values corresponds to a future time in which the SO will exhibit a target morphology, wherein the target morphology comprises a peak of the SO.
Choe teaches a system for synchronization of neurostimulation interventions (see abstract and Fig. 7), in which the system predicts upcoming events in sleep slow-wave oscillations, such as a peak, for the intervention to be delivered, at a specific point in time in the future (see ¶[0065], ¶[0069]-[0070], and ¶[0076]-[0078]; Figs. 4 and 6), in which the incoming signals (i.e., EEG signals) are classified (see ¶[0011], ¶[0062], and ¶[0068]; Fig. 3).
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to predict a future point in time with a target morphology (i.e., a predicted slow wave peak) utilizing the neural network prediction in Molina ‘185 as taught in Choe because (1) it is the application of a known technique to a known device/method ready for improvement to yield predictable results; and/or (2) predicting sleep stages at a future time point would give better understanding to how the user would react to the given stimulation; and/or (3) the output morphological features would better indicate how what type of sleep activity the user is experiencing, including a desired deeper sleep, slow wave oscillation period; and/or (4) the slow wave peak timing of stimulation would insure stimulation at the correct temporal targets (see Choe ¶[0076]-[0078]; Figs. 4 and 6).
Regarding Claim 2, Molina ‘185 in view of Choe teaches the system of claim 1 as stated above. Molina ‘185 further teaches the stimulation generation circuitry comprises auditory stimulation generation circuitry, wherein the stimulation comprises auditory stimulation, and wherein the one or more processors are configured to determine the one or more parameters to include one or more auditory stimulation parameters of the auditory stimulation (abstract and ¶[0028]-[0030] the stimulator 16 to deliver audio stimulation (such as via a speaker), ¶[0030]-[0031], ¶[0049]-[0050], and ¶[0054] the audio stimulation may be modulated based on the output from the neural network; Figs. 1-2).
Regarding Claim 5, Molina ‘185 in view of Choe teaches the system of claim 2 as stated above. Molina ‘185 further teaches the auditory stimulation generation circuitry comprises one or more sound wave generators configured to deliver the auditory stimulation to the user based on the one or more auditory stimulation parameters (abstract and ¶[0028]-[0030] stimulator 16 to deliver audio stimulation (such as via a speaker); Figs. 1-2).
Regarding Claim 7, Molina ‘185 in view of Choe teaches the system of claim 1 as stated above. Molina ‘185 further teaches the stimulation generation circuitry comprises electrical stimulation generation circuitry, wherein the stimulation comprises electrical stimulation, and wherein the one or more processors are configured to determine the one or more parameters to include one or more electrical stimulation parameters of the electrical stimulation (abstract and ¶[0028]-[0030] the stimulator 16 to deliver electric stimulation, ¶[0030], ¶[0049]-[0050], and ¶[0054] the parameters of the sensory stimulation (including the electrical stimulation) are updated; Figs. 1-2).
Regarding Claim 8, Molina ‘185 in view of Choe teaches the system of claim 1 as stated above. Molina ‘185 further teaches the stimulation generation circuitry comprises optical stimulation generation circuitry, wherein the stimulation comprises optical stimulation, and wherein the one or more processors are configured to determine the one or more parameters to include one or more optical stimulation parameters of the optical stimulation (abstract and ¶[0028]-[0030] the stimulator 16 to deliver visual stimulation, ¶[0030], ¶[0049]-[0050], and ¶[0054] the parameters of the sensory stimulation (including the visual stimulation) are updated; Figs. 1-2).
Regarding Claim 9, Molina ‘185 in view of Choe teaches the system of claim 1 as stated above. The modified Molina ‘185 further teaches the stimulation generation circuitry is configured to: generate the stimulation based on the one or more parameters (see Molina ‘185 ¶[0042]-[0050] and ¶[0054]-[0055] the stimulation parameters are made and modulated based on the output from the neural network model, the stimulation is updated based on the neural network output and sensor output; Figs. 2-4); and deliver the stimulation so that the user receives the stimulation while the ongoing brain activity of the user indicates the SO (see Molina ‘185 ¶[0048]-[0050] and ¶[0054]-[0056] the stimulation is provided to the subject during deep sleep, ¶[0037] the predicted sleep stage deep sleep relates to slow wave deep sleep, Fig. 4; see Choe ¶[0065], ¶[0069]-[0070], and ¶[0076]-[0078], the system predicts upcoming events in sleep slow-wave oscillations, such as a peak, for the intervention to be delivered, at a specific point in time in the future, Figs. 4 and 6).
Regarding Claim 10, Molina ‘185 in view of Choe teaches the system of claim 9 as stated above. The modified Molina ‘185 further teaches the one or more processors are further configured to: determine, based on the one or more predicted SO values, a delay interval; and send a message to the stimulation generation circuitry to generate the stimulation upon expiration of the delay interval (see Choe ¶[0065], ¶[0069]-[0070], and ¶[0076]-[0078], the system predicts upcoming events in sleep slow-wave oscillations, such as a peak, for the intervention to be delivered, at a specific point in time in the future; Figs. 4 and 6). In this case, the stimulation in the modified Molina ‘185 (as taught by Choe) is applied when the slow wave peak is predicted, accounting for processing time delays (i.e., time delay), so that the stimulation is applied at the correct temporal target.
Regarding Claim 14, Molina ‘185 in view of Choe teaches the system of claim 1 as stated above. The modified Molina ‘185 further teaches the one or more processors are further configured to: identify, based on the one or more SO parameters, a decision point that represents a last point in time at which the one or more processors can output an instruction for the stimulation generation circuitry to deliver the stimulation; determine, based on the one or more SO parameters, the one or more parameters before the decision point; and output an instruction for the stimulation generation circuitry to deliver the stimulation (see Choe ¶[0065], ¶[0069]-[0070], and ¶[0076]-[0078], the system predicts upcoming events in sleep slow-wave oscillations, such as a peak, for the intervention to be delivered, at a specific point in time in the future; Figs. 4 and 6). Here, as the stimulation is delivered during the appropriate and desired point in time, taking into account processing times, the control component would necessarily deliver the stimulus before a decision point, as the stimulus given in the modified Molina ‘185 is timely delivered.
Regarding Claim 15, Molina ‘185 in view of Choe teaches the system of claim 1 as stated above. Molina ‘185 further teaches to determine the one or more predicted SO values, the one or more processors are configured to: determine a time corresponding to each SO parameter of the one or more SO parameters; determine a value of the EEG signal corresponding to the SO for each SO parameter of the one or more SO parameters; determine, based on the time and the value of the EEG signal corresponding to each SO parameter, one or more features that define a morphology of the SO of the ongoing brain activity (¶[0038] brain activity parameters are determined from the EEG signal, including slow wave parameters of amplitude, frequency, timing, ¶[0056]-[0058] the stimulation is delivered during a period after a zero-crossing, or second zero-crossing of a slow wave, calculate average and/or running average of data; Figs. 3-4); and determine the one or more predicted SO values based on the time corresponding to each SO parameter, the value of the EEG signal corresponding to each SO parameter, and the one or more features that define the morphology (¶[0041] and ¶[0051]-[0053] the output of the neural network model are values that are used to indicate the predicted sleep stage of the user based on the stimulation, ¶[0037] the predicted sleep stage relates to slow wave deep sleep).
Regarding Claim 16, Molina ‘185 in view of Choe teaches the system of claim 1 as stated above. The modified Molina ‘185 further teaches to determine the one or more predicted SO values, the one or more processors are configured to apply an SO classifier to the one or more SO parameters, the SO classifier trained using a set of training SO samples to recognize one or more patterns for determining the one or more predicted SO values (see Molina ‘185 ¶[0038]-[0040] brain activity parameters are determined from the EEG signal, including slow wave parameters of amplitude, frequency, timing, used as input into the neural network, ¶[0041] the output signals from the sensors, the EEG data, is input into the neural network model, ¶[0041] and ¶[0051]-[0053] the output of the neural network model are values that are used to indicate the predicted sleep stage of the user based on the stimulation, ¶[0037] the predicted sleep stage relates to slow wave deep sleep, Fig. 3; see Choe ¶[0065], ¶[0069]-[0070], and ¶[0076]-[0078], the system predicts upcoming events in sleep slow-wave oscillations, such as a peak, for the intervention to be delivered, at a specific point in time in the future, ¶[0011], ¶[0062], and ¶[0068], the incoming signals (i.e., EEG signals) are classified, Figs. 3-4 and 6). Here, the neural network of the modified Molina ‘185 that indicates slow wave based on sleep stage output/target morphology is a classifier.
Regarding Claim 17, Molina ‘185 in view of Choe teaches the system of claim 16 as stated above. The modified Molina ‘185 further teaches the memory is configured to store a plurality of training SO samples, and wherein the one or more processors are configured to: extract one or more training SO parameters from each training SO sample of the plurality of training SO samples; train the SO classifier based on the plurality of training SO samples and the one or more training SO parameters corresponding to each training SO sample of the plurality of training SO samples (see Molina ‘185 ¶[0038]-[0040] brain activity parameters are determined from the EEG signal, including slow wave parameters of amplitude, frequency, timing, used as input into the neural network, ¶[0041] the output signals from the sensors, the EEG data, is input into the neural network model, trained from historical data ¶[0041] and ¶[0051]-[0053] the output of the neural network model are values that are used to indicate the predicted sleep stage of the user based on the stimulation, ¶[0037] the predicted sleep stage relates to slow wave deep sleep, Fig. 3; see Choe ¶[0065], ¶[0069]-[0070], and ¶[0076]-[0078], the system predicts upcoming events in sleep slow-wave oscillations, such as a peak, for the intervention to be delivered, at a specific point in time in the future, ¶[0011], ¶[0062], and ¶[0068], the incoming signals (i.e., EEG signals) are classified, Figs. 3-4 and 6). Here, the historical sleep depth information used in the training of the neural network are the training SO samples. The same parameters that are used in the present neural network to predict sleep stages (slow waves) at a future time would necessarily need to be used to train the model with the historical data (i.e., same extracted parameters in historical data as present monitored EEG data); because otherwise, if different parameters were used between the historical and currently measured EEG data, the neural network would not be able to accurately make predictions.
Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Molina ‘185 in view of Choe as applied to claim 2 above, and in view of Wostyn et al. (“Can meditation-based approaches improve the cleansing power of the glymphatic system?”, Exploration of Neuroprotective Therapy, 2, 110-117, published June 20, 2022 – cited in prior action), hereinafter Wostyn.
Regarding Claim 3, Molina ‘185 in view of Choe teaches the system of claim 2 as stated above. The modified Molina ‘185 is silent regarding the stimulation generation circuitry is configured to determine the one or more auditory stimulation parameters so that delivering the auditory stimulation increases glymphatic flow of the user.
Wostyn teaches about meditation based approaches to enhancing the glymphatic system, such as immersive sound meditation, which may help to enhance glymphatic pathway transport and increase slow-wave activity (see abstract and pg. 114, § Immersive sound meditation as a candidate modulator of glymphatic function). Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to utilize the audio meditation stimulation of Wostyn for the audio stimulation in the modified Molina ‘185 because (1) it is the application of a known technique to a known device/method ready for improvement to yield predictable results and/or (2) the audio meditation stimulation may help to promote healthy brain aging and to help prevent neurodegenerative disorders such as Alzheimer’s disease (AD) (see Wostyn abstract and pg. 114, § Immersive sound meditation as a candidate modulator of glymphatic function).
Claim 4 is rejected under 35 U.S.C. 103 as being unpatentable over Molina ‘185 in view of Choe as applied to claim 2 above, and in view of Malchano et al. (US Patent Application 2023/0111776 – cited in prior action), hereinafter Malchano.
Regarding Claim 4, Molina ‘185 in view of Choe teaches the system of claim 2 as stated above. The modified Molina ‘185 is silent regarding the stimulation generation circuitry is configured to determine the one or more auditory stimulation parameters so that delivering the auditory stimulation increases memory function and cognitive function of the user.
Malchano teaches systems and methods directed towards non-invasive neural stimulation, including audio stimulation (see abstract and ¶[0127]-[0133]), in which the stimulation increases the memory and cognitive function of the user (see abstract and ¶[0068]-[0070]).
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to utilize the audio stimulation of Malchano for the audio stimulation in the modified Molina ‘185 because (1) it is the application of a known technique to a known device/method ready for improvement to yield predictable results and/or (2) the audio stimulation would help to improve memory and cognitive function of the user (see Malchano abstract and ¶[0068]-[0070]).
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over Molina ‘185 in view of Choe as applied to claim 5 above, and in view of Crow et al. (US Patent Application Publication 2019/0099582 – cited by Applicant), hereinafter Crow.
Regarding Claim 6, Molina ‘185 in view of Choe teaches the system of claim 5 as stated above. The modified Molina ‘185 is silent regarding the one or more sound wave generators are configured to deliver the auditory stimulation to an inner ear of the user.
Crow teaches about sleep performance systems and methods involving recommendations based on sleep metrics measured via EEG electrodes during the user’s sleep (see abstract), in which the system may utilize audio stimulation, provided via bone conduction by transmitting sound signals through bone to a user's inner ear (see ¶[0104]).
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to utilize the bone conduction audio stimulation of Crow for as the speaker audio stimulation in the modified Molina ‘185 because (1) it is the application of a known technique to a known device/method ready for improvement to yield predictable results; and/or (2) the modified Molina ‘185 requires a sound delivery device and Crow teaches one such device; and/or (3) providing the audio stimulation through the bone conduction would limit excess noise into the environment, such as to avoid disturbing anyone else sleeping adjacent to the user, such as a partner or child.
Claim 18 is rejected under 35 U.S.C. 103 as being unpatentable over Molina ‘185 in view of Choe as applied to claim 17 above, and in view of Molina et al. (US Patent Application 2020/0306494 – cited in prior action), hereinafter Molina ‘494.
Regarding Claim 18, Molina ‘185 in view of Choe teaches the system of claim 17 as stated above. The modified Molina ‘185 does not specifically teach that extracting the one or more training SO parameters from each training SO sample, the one or more processors are configured to apply one or more filters to preprocess each training SO sample of the plurality of training SO samples.
Molina ‘494 teaches a system that utilizes a deep neural network and only frontal electrodes to detect N3 sleep (see abstract) in which bands of interest may be preprocessed via a band-pass filter (see ¶[0050] and ¶[0069], see also ¶[0073] filtering to boost a delta portion of the EEG signal for slow wave detection).
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to utilize the band-pass filtering of the band of interest of Molina ‘494 with the band of interest (i.e., the slow wave portion) in the modified Molina ‘185 because (1) it is the application of a known technique to a known device/method ready for improvement to yield predictable results and/or (2) filtering out only the portion of interest in the EEG signal would help to reduce noise and other extraneous elements for less computationally intensive processing of the EEG signal. Here, as described above with claim 17, as the input to the neural network would include preprocessed filter data (i.e., the EEG signal in the modified Molina ‘185 is filtered, slow wave identified, and then parameters extracted from that are then input into the neural network), so to would the historical training data need to be preprocessed and parameters extracted for input for training the neural network, so that the present, trained, neural network will properly provide outputs (future sleep stage/slow wave/morphologies) based on the input (the prepossessed EEG signal with extracted parameters).
Claims 11 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Molina ‘185 in view of Choe as applied to claim 17 above, and in view Daly et al. (“On the Automated Removal of Artifacts Related to Head Movement From the EEG”, IEEE Transactions on Neural Systems and Rehabilitation Engineering, Vol. 21, No. 3, May 2013 – cited in prior action), hereinafter Daly.
Regarding Claim 11, Molina ‘185 in view of Choe teaches the system of claim 9 as stated above. Molina ‘185 further teaches the one or more processors are further configured to: compare, based on the one or more SO parameters, the SO with a target SO morphology representing an example of an SO morphology that conforms to a first SO wave morphology; determine, based on the comparison, whether the SO is a first SO; send, to the stimulation generation circuitry, a message to generate the stimulation based on determining that the SO is a first SO; and send, to the stimulation generation circuitry, a message to refrain from generating the stimulation based on determining that the SO is a second SO different from the first SO (see Molina ‘185 ¶[0009]-[0012] and ¶[0058]-[0062] based on the comparison of the stimulated slow wave activity to unstimulated slow wave activity, the stimulation parameters are updated, Figs. 4 and 7; see Choe ¶[0065], ¶[0069]-[0070], and ¶[0076]-[0078], the system predicts upcoming events in sleep slow-wave oscillations, such as a peak, for the intervention to be delivered, at a specific point in time in the future, Figs. 4 and 6). In this case, the stimulation in the modified Molina ‘185 (as taught by Choe) is applied when the slow wave peak is predicted; conversely and inherently, when a non-correct temporal target is predicted, no stimulation is applied (see for example, Choe ¶[0078]). Because otherwise, the modified Molina ‘185 would improperly stimulate at any detected morphology.
Alternatively and/or additionally, Daly teaches about removing motion artifacts from EEG signals via usage of an accelerometer (see abstract), in which signals highly correlated with the accelerometer motion are marked and removed, then the cleaned signal is reconstructed (see pg. 429 § E. Artifact Reduction). Here, the marked and removed artifact is the second SO and the non-artifact is the first SO.
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to utilize the artifact removal of Daly with the historical and real-time EEG data in the modified Molina ‘185 because (1) it is the application of a known technique to a known device/method ready for improvement to yield predictable results; and/or (2) removing the artifacts from the historical EEG data used to train the neural network would improve the accuracy of the neural network; and/or (3) removing the artifacts from the real-time EEG data would improve the accuracy of the prediction.
Regarding Claim 20, Molina ‘185 in view of Choe teaches the system of claim 17 as stated above. The modified Molina ‘185 is silent regarding the one or more processors are configured to: identify, based on the one or more training features extracted from each training SO sample of the plurality of training SO samples, whether each training SO sample of the plurality of training SO samples represents a first SO that is a candidate for stimulation or a second SO that is not a candidate for stimulation; label each training SO sample identified as the second SO that is not a candidate for stimulation for training the classifier; and label each training SO sample identified as a first SO that is a candidate for stimulation for training the classifier.
Daly teaches about removing motion artifacts from EEG signals via usage of an accelerometer (see abstract), in which signals highly correlated with the accelerometer motion are marked and removed, then the cleaned signal is reconstructed (see pg. 429 § E. Artifact Reduction). Here, the marked and removed artifact is the second SO and the non-artifact is the first SO.
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to utilize the artifact removal of Daly with the historical and real-time EEG data in the modified Molina ‘185 because (1) it is the application of a known technique to a known device/method ready for improvement to yield predictable results; and/or (2) removing the artifacts from the historical EEG data used to train the neural network would improve the accuracy of the neural network; and/or (3) removing the artifacts from the real-time EEG data would improve the accuracy of the prediction.
Claims 12-13 are rejected under 35 U.S.C. 103 as being unpatentable over Molina ‘185 in view of Choe as applied to claim 1 above, and in view of Molina et al. (US Patent Application 2020/0306495), hereinafter Molina ‘495, and in view of Mahadevan et al. (US Patent Application Publication 2017/0215789), hereinafter Mahadevan.
Regarding Claim 12, Molina ‘185 in view of Choe teaches the system of claim 1 as stated above. Molina ‘185 further teaches to extract the one or more SO parameters, the one or more processors are configured to determine, based on the SO of the ongoing brain activity: a positive-to-negative zero-crossing of the EEG signal corresponding to the SO; a negative-to-positive zero-crossing of the EEG signal corresponding to the SO (¶[0038] brain activity parameters are determined from the EEG signal, including slow wave parameters of amplitude, frequency, timing, ¶[0056]-[0058] the stimulation is delivered during a period after a zero-crossing, or second zero-crossing of a slow wave, calculate average and/or running average of data, the zero-crossing detections would necessarily include both positive-to-negative and negative-to-positive; Figs. 3-4).
The modified Molina ‘185 does not specifically teach a negative peak of the EEG signal corresponding to the SO.
Molina ‘495 teaches a system for delivering sensory stimulation including a sensor to measure brain activity, and to apply a stimulation profile during slow wave sleep in the patient (see abstract and Fig. 2), in which the system may detect negative peaks and zero-crossing in real-time (see ¶[0008] and ¶[0055]-[0058]; Fig. 1).
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to utilize the negative peak slow wave parameter of Molina ‘495 with the parameters of the modified Molina ‘185 because (1) it is the application of a known technique to a known device/method ready for improvement to yield predictable results; and/or (2) the additional parameter would help the modified Molina ‘185 detect the specific slow wave period for stimulation application; and/or (3) the modified Molina ‘185 requires parameters of the slow wave and Molina ‘495 teaches another such parameter.
The modified Molina ‘185 does not specifically teach one or both of: a point after the positive-to-negative zero-crossing at which a slope of the EEG signal corresponding to the SO falls under a negative slope threshold; and a point before the negative-to-positive zero-crossing at which a slope of the EEG signal corresponding to the SO falls under a positive slope threshold.
Mahadevan teaches a system configured to detect slow waves in a subject during a sleep session and sleep stages (see abstract), including analyzing the shape of the harmonic representation of the EEG output (see ¶[0019]-[0020]) in which one or more slopes are determined at one or more points, including at zero-crossing, as well as before and after a negative peak, approximated to frequency, and then compared to a frequency range (i.e., threshold) for a slow wave detection (see ¶[0038] and Figs. 2-3).
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to utilize the slope point slow wave parameter of Mahadevan with the parameters of the modified Molina ‘185 because (1) it is the application of a known technique to a known device/method ready for improvement to yield predictable results; and/or (2) the additional parameter would help the modified Molina ‘185 detect the specific slow wave period for stimulation application; and/or (3) the modified Molina ‘185 requires parameters of the slow wave and Mahadevan teaches another such parameter.
Regarding Claim 13, Molina ‘185 in view of Choe, Molina ‘495, and Mahadevan teaches the system of claim 12 as stated above. The modified Molina ‘185 further teaches the one or more processors are configured to determine, based on the one or more SO parameters, one or more slope values and one or more interval values (see Mahadevan ¶[0038], the one or more slopes are determined at one or more points, including at zero-crossing, as well as before and after a negative peak, approximated to frequency, and then compared to a frequency range (i.e., threshold) for a slow wave detection; Figs. 2-3).
Claim 19 is rejected under 35 U.S.C. 103 as being unpatentable over Molina ‘185 in view of Choe and Molina ‘494 as applied to claim 18 above, and in view of Fallahpour (US Patent Application Publication 2023/0321392 – cited in prior action), hereinafter Fallahpour.
Regarding Claim 19, Molina ‘185 in view of Choe and Molina ‘494 teaches the system of claim 18 as stated above. The modified Molina ‘185 further teaches to apply the one or more filters to preprocess each training SO sample of the plurality of training SO samples, the one or more processors are configured to: process each training SO sample of the plurality of training SO samples with an offline filter (see Molina ‘185 ¶[0038]-[0040] brain activity parameters are determined from the EEG signal, including slow wave parameters of amplitude, frequency, timing, used as input into the neural network, ¶[0041] the output signals from the sensors, the EEG data, is input into the neural network model, trained from historical data ¶[0041] and ¶[0051]-[0053] the output of the neural network model are values that are used to indicate the predicted sleep stage of the user based on the stimulation, ¶[0058] the EEG data may be filtered through a frequency block, ¶[0037] the predicted sleep stage relates to slow wave deep sleep, Fig. 3; see Molina ‘494 ¶[0050] and ¶[0069] which bands of interest may be preprocessed via a band-pass filter, see also ¶[0073] filtering to boost a delta portion of the EEG signal for slow wave detection). Here, the historical data that is filtered and used to train the neural network is the offline filter, as the data would be offline and not real-time.
The modified Molina ‘185 is silent regarding training the neural network with real-time data and associated filter.
Fallahpour teaches about a feedback system to help a subject achieve a target state of consciousness via real-time received EEG data (see abstract), in which an artificial-intelligence engine may be utilized to process the data (see ¶[0065]), and the machine-learning approach may be fine-tuned (i.e., the training is updated) with real-time EEG data from the subject so as to personalize and update the machine learning approach to the subject in real-time (see ¶[0067]).
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to utilize the real-time EEG fine-tuning of the model of Fallahpour with the real-time EEG data and neural network in the modified Molina ‘185 because (1) it is the application of a known technique to a known device/method ready for improvement to yield predictable results and/or (2) fine-tuning the model in real-time with the real-time EEG data would improve the accuracy of the neural network by personalizing the model to the user (see Fallahpour ¶[0067]). Here, as described above with claims 17-18, as the input to the neural network would include preprocessed filter data (i.e., the EEG signal in the modified Molina ‘185 is filtered, slow wave identified, and then parameters extracted from that are then input into the neural network), so to would the historical training data need to be preprocessed and parameters extracted for input for training the neural network, so that the present, trained, neural network will properly provide outputs (future sleep stage/slow wave) based on the input (the prepossessed EEG signal with extracted parameters). Therefore, the filtered real-time data used to fine-tune/train the neural network is considered the real-time filtered data.
Response to Arguments
Applicant’s arguments, objections to the claims
Applicant’s arguments, see pg. 10, filed October 29, 2025, with respect to the objection of claim 17 have been fully considered and are persuasive. Therefore, the objection has been withdrawn.
Applicant’s arguments, 35 U.S.C. § 112(b)
Applicant’s arguments, see pg. 10, filed October 29, 2025, with respect to the rejections of claims 11, 13, 15, 17, and 20 under 35 U.S.C. § 112(b) have been fully considered. The rejections to claims 11 and 13 have been addressed; therefore, those rejections have been withdrawn. The rejections to claims 15, 17, and 20 that have not been addressed are maintained. However, upon further consideration, a new grounds of rejection are made that were necessitated by Applicant’s amendment filed on October 29, 2025.
Applicant’s arguments, double patenting
Applicant’s arguments, see pg. 10, filed October 29, 2025, with respect to the rejections of claims 1-22 with respect to the provisional non-statutory double patenting rejections have been fully considered and are NOT persuasive. Therefore, the provisional non-statutory double patenting rejections have been maintained.
Applicant’s arguments, 35 U.S.C. § 103
Applicant’s arguments, see pg. 11-12, filed October 29, 2025, with respect to the rejections of claims 1-22 under 35 U.S.C. § 103 have been fully considered and are persuasive. Therefore, the rejections have been withdrawn. However, upon further consideration, a new grounds of rejection are made in view of Choe et al. (US Patent Application Publication 2018/0221661).
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 JONATHAN D. MORONESO whose telephone number is (571)272-8055. The examiner can normally be reached M-F: 8:30AM - 6:00 PM, MST.
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 M. 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.
/J.D.M./Examiner, Art Unit 3791
/JENNIFER ROBERTSON/Supervisory Patent Examiner, Art Unit 3791
Prosecution Insights