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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 04/09/2026 has been entered.
Response to Arguments
Applicant’s arguments filed 03/17/2026 have been fully considered and are moot in view of a new grounds of rejection.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
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, 3, 5-6, 8-10, 12, 15, 21-24, and 27-28 are rejected under 35 U.S.C. 103 as being unpatentable over Kang et al. (US 2020/0260977) in view of Rogers (US 2010/0198282) in view of Okuno et al. (US 2010/0099891).
In re claim 1, Kang discloses a system (fig. 1: combination of 100, 200, and 300) comprising:
a device (200) comprising one or more electroencephalogram (EEG) sensors [0050],
wherein the device is configured to collect, from a subject [0050], an EEG signal using the one or more EEG sensors [0050];
one or more processors (fig. 2: 110); and
a memory (120) storing instructions [0133, 0143-0144] that, when executed by the processors, cause the one or more processors to:
receive, from the one or more EEG sensors of the device, the EEG signal collected from the subject [0088];
apply a model to the EEG signal [0088] to determine a cognitive reserve of the subject ([0105]: cognitive impairment diagnosis modeling generates EEG model with respect to neurocognitive reserve; [0088, 0106-0107]),
wherein the model is trained using a plurality of sets of training data ([0091]: EEG signals that are input data are classified; [0088]: modeling device 10 receives EEG signals from plurality of devices 101, 102, and 103),
each set of training data including
a training EEG dataset collected from a training subject [0088] and
a training cognitive reserve score ([0088]: degree of cognitive impairment) corresponding to the training subject that is determined based on metrics separate from the training EEG dataset ([0081]: degree of cognitive impairment is part of each training data; [0091]: EEG signals are classified according to degree of the cognitive impairment),
wherein to train the model (see above), the instructions cause the one or more processors to:
receive tagging data indicating the training cognitive reserve score for each set of training data ([0091]: machine learning performer outputs data like the degree of cognitive impairment, which is part of each training data for the model and would provide tagging related to the data as well as other features such as brain image),
the training cognitive reserve score representing a subjective assessment of the training subject independent of the training EEG dataset collected from the training subject and independent of the model ([0091]: relationship is identified between EEG signal and degree of cognitive impairment based on factors such as brain image and a diagnostician’s opinion, which are metrics separate from the training EEG datasets and the model);
extract, from the training EEG dataset corresponding to each set of training data, one or more EEG-based metrics
([0129]: data learner 121 may be trained to detect EEG-based metrics such as cognitive impairment-related information from the EEG; [0067]: EEG-based metrics also includes data extracted from EEG in each frequency band and absolute power; [0090-0091]: frequency band extracted may be gamma, alpha, beta, delta, or theta waves)
independent of the training cognitive reserve score for the set of training data ([0091]: relationship is identified between EEG signal and degree of cognitive impairment based on factors such as brain image and a diagnostician’s opinion, which are metrics separate from the training EEG datasets; [0067]: EEG-based metrics includes data extracted from EEG; [0081, 0109, 0129]),
wherein the one or more EEG- based metrics comprise any one or combination of
slow oscillation amplitude,
slow oscillation slope,
an amount of slow oscillation spindle-coupling,
an amount of slow-wave sleep ([0165]: electroencephalogram is classified into different waves, including a delta wave, which occurs in deep sleep, and would provide an amount of slow-wave sleep), and
an amount of rapid eye movement (REM) sleep; and
train the model [0129] and
cause the device to deliver treatment ([0049]: based on cognitive impairment-related information, treatment may be provided; [0105]: cognitive impairment diagnosis modeling is made in respect to neurocognitive reserve; [0107]).
Kang fails to disclose
a device comprising one or more electroencephalogram (EEG) sensors and stimulation generation circuitry,
the instructions cause the one or more processors to:
identify one or more correlations between the one or more EEG-based metrics and the training cognitive reserve scores by:
identifying a first coefficient corresponding to the one or more EEG-based metrics; and
identifying a second coefficient corresponding to the training cognitive reserve scores,
wherein the first coefficient and the second coefficient maximize a correlation between a transformation of the one or more EEG-based metrics and a transformation of the training cognitive reserve scores; and
train the model based on the one or more correlations,
cause the device to deliver, via the stimulation generation circuitry, neurostimulation to the subject based on the cognitive reserve of the subject.
Rogers teaches an analogous invention of treating medical conditions [0012], and teaches
a device (fig. 13: 10; [0066]) comprising one or more electroencephalogram (EEG) sensors [0125-0126] and stimulation generation circuitry [0079],
cause the device to deliver, via the stimulation generation circuitry [0079], neurostimulation to the subject ([0037-0039]: treatment includes stimulation; Table 3: delivery across neuronal tissues; [0048]: stimulation delivered via electrode; [0106, 0145-0146]) based on the cognitive reserve of the subject ([0172]: stimulating cognitive enhancement improves cognitive reserves; [0037]: treatment increases cognitive reserve and may be administered prior to or after an onset of symptoms i.e. may be based on the cognitive reserve of the subject; [0079]: housing contains circuitry to deliver electric stimuli to the subject).
Rogers further teaches that stimulating cognitive enhancement in a subject enhances cognitive reserves [0172], as well as memory function [0172].
It would have been obvious to someone of ordinary skill in the art at the time the instant invention was filed to modify the system of Kang, to provide wherein a device comprising one or more electroencephalogram (EEG) sensors and stimulation generation circuitry and cause the device to deliver, via the stimulation generation circuitry, neurostimulation to the subject based on the cognitive reserve of the subject, as taught by Rogers, because stimulating cognitive enhancement in a subject enhances cognitive reserves as well as memory function.
Regarding the limitations,
“identify one or more correlations between the one or more EEG-based metrics and the training cognitive reserve scores by:
identifying a first coefficient corresponding to the one or more EEG-based metrics; and
identifying a second coefficient corresponding to the training cognitive reserve scores,
wherein the first coefficient and the second coefficient maximize a correlation between a transformation of the one or more EEG-based metrics and a transformation of the training cognitive reserve scores; and
train the model based on the one or more correlations,”
Okuno teaches a [0001] and teaches a data processing method [0002] for screening two types of chemical substance databases [0002]
identifying one or more correlations [0055] between a first variable ([0055]: variable X) and a a second variable ([0055]: variable Y) by:
identifying a first coefficient corresponding to the first variable ([0093]: one of a set of coefficient vectors; [0048]: ‘x’ has a coefficient M); and
identifying a second coefficient corresponding to the second variable ([0093]: a second one of a set of coefficient vectors; [0048]: ‘y’ has a coefficient N),
wherein the first coefficient and the second coefficient maximize a correlation [0093] between a transformation of the first variable ([0093-0094]: X receives transformation from a nonlinear model) and a transformation of the ([0093-0094]: Y receives transformation from a nonlinear model); and
wherein the first coefficient comprises a first set of coefficient values [0093, 0048] and the second coefficient comprises a second set of coefficient values [0093, 0048];
wherein the transformation of the first variable can include a linear transformation ([0048]: correlation may be based on linear combinations; [0054-0055]) or nonlinear transformation [0094], and
wherein the transformation of the training cognitive reserve scores can include a linear transformation ([0048]: correlation may be based on linear combinations; [0054-0055]) or a nonlinear transformation [0094]; and
training a model based on the one or more correlations [0106-0107].
Okuno further teaches a multivariate analysis technique [0057] can be used to maximize the correlation [0057] and to summarize complicated data [0096] by clarifying a correlation that affects results [0096].
It would have been obvious to someone of ordinary skill in the art at the time the instant invention was filed to modify the system yielded by the propped combination, to provide identify one or more correlations between the one or more EEG-based metrics and the training cognitive reserve scores by: identifying a first coefficient corresponding to the one or more EEG-based metrics; and identifying a second coefficient corresponding to the training cognitive reserve scores, wherein the first coefficient and the second coefficient maximize a correlation between a transformation of the one or more EEG-based metrics and a transformation of the training cognitive reserve scores; and train the model based on the one or more correlations, as taught by identifying correlations between the first and second variables of Okuno, because a multivariate analysis technique can be used to maximize the correlation and to summarize complicated data by clarifying a correlation that affects results.
The proposed combination would further yield
wherein the first coefficient comprises a first set of coefficient values and the second coefficient comprises a second set of coefficient values;
wherein the transformation of the first variable can include a linear transformation or nonlinear transformation, and
wherein the transformation of the training cognitive reserve scores can include a linear transformation or a nonlinear transformation,
so that the coefficients can be calculated and maximized for the first and second variables.
In re claim 3, the proposed combination in re claim 1 above yields wherein the neurostimulation enhances the cognitive reserve of the subject (Rogers: [0172]).
In re claim 5, regarding the limitations,
“wherein the stimulation generation circuitry comprises one or more stimulation electrodes, and
wherein to cause the device to deliver neurostimulation to the subject, the one or more processors cause the one or more stimulation electrodes of the device to deliver electrical stimulation to the subject in a way that stimulates a nervous system of the subject”,
see the proposed combination yielded in re claim 1 above.
In re claim 6, the proposed combination fails to yield wherein the one or more processors are further configured to determine one or more pharmaceutical interventions for the subject to treat cognitive reserve.
Rogers teaches wherein the one or more processors (see in re claim 1 above) are further configured to determine one or more pharmaceutical interventions ([0172]: stimulating cognitive enhancement; [0037]: treatment increases cognitive reserve; [0147]: treatments may be combined with pharmaceuticals for a combined treatment option) for the subject to treat cognitive reserve ([0172]: stimulating cognitive enhancement enhances cognitive reserves; [0037]).
Rogers further teaches that stimulators may be combined with pharmaceuticals to achieve a combined treatment effect [0147], and that treatment may be to increase cognitive reserve [0037, 0172].
It would have been obvious to someone of ordinary skill in the art at the time the instant invention was filed to modify the system yielded by the propped combination, to provide wherein the one or more processors are further configured to determine one or more pharmaceutical interventions for the subject to treat cognitive reserve, as taught by Rogers, because treatment that enhances cognitive reserves may be provided, for instance through a combined treatment that uses both stimulators and pharmaceuticals.
In re claim 8, the proposed combination yields (all mapping directed to Kang unless otherwise stated)
wherein the one or more processors are further configured to: process the EEG signal to determine features associated with
macro sleep architecture ([0165-0166]: EEG can be collected during different sleep stages (delta, theta, etc.) which are considered macro sleep architecture; [0050]) and/or
microsleep features ([0165-0166]: EEG waveform may have varying frequencies and amplitudes which are considered microsleep features),
including one or more slow-wave activity (SWA) metrics corresponding to the subject ([0091]: EEG may be a delta wave i.e. slow-wave activity), and
wherein to apply the model to the EEG signal, the one or more processors are configured to determine the cognitive reserve of the subject based on
the macro sleep features ([0091]: input data includes EEG wave classification; [0107]: modeling device analyzes input data, which would include EEG wave classification, to determine cognitive reserve) or
one or more SWA metrics corresponding to the subject ([0050]: EEG may be a delta wave; [0107]: cognitive reserve features extracted from input data, which may be based on a delta wave [0091]).
In re claim 9, the proposed combination yields (all mapping directed to Kang unless otherwise stated) wherein the device is configured to collect the EEG signal from the subject while the subject is asleep ([0042]: delta wave is an EEG which may be measured during sleep; [0165]).
In re claim 10, the proposed combination yields (all mapping directed to Kang unless otherwise stated) wherein the EEG signal corresponds to one sleep session of the subject ([0165-0166]: during a deep sleep state).
In re claim 12, the proposed combination yields (all mapping directed to Kang unless otherwise stated) wherein the one or more processors are further configured to:
process the EEG signal to determine
one or more sleep macrostructure metrics (see in re claim 8 above) and
one or more EEG-based sleep microstructure features corresponding to the subject (see in re claim 8 above), and
wherein to apply the model to the EEG signal, the one or more processors are configured to determine the cognitive reserve of the subject based on
the one or more sleep macrostructure metrics (see in re claim 8 above) and
the one or more EEG-based sleep microstructure features corresponding to the subject ([0042]: specific frequency is used to determine which wave the ECG is classified as; [0091]: input data includes wave classification which is based on frequency and is then used to determine cognitive reserve [0107]).
In re claim 15, the proposed combination yields (all mapping directed to Kang unless otherwise stated) wherein the one or more processors are configured to apply the model [0088]: model trained using EEG data and degree of cognitive impairment) to determine the cognitive reserve of the subject based on the one or more correlations ([0105]: cognitive impairment diagnosis modeling generates EEG-based model with respect to neurocognitive reserve; [0091-0092]: relationship between EEG signal and degree of cognitive impairment is used to determine EEG model).
In re claim 21, regarding the limitations, “a method comprising:
collecting, by a device comprising one or more electroencephalogram (EEG) sensors and stimulation generation circuitry,
an EEG signal from a subject using the one or more EEG sensors;
receiving, from the one or more EEG sensors of the device, the EEG signal collected from the subject;
applying a model to the EEG signal to determine a cognitive reserve of the subject,
wherein the model is trained using a plurality of sets of training data,
each set of training data including
a training EEG dataset collected from a training subject and
a training cognitive reserve score corresponding to the training subject that is determined based on metrics separate from the training EEG dataset;
training the model by:
receiving tagging data indicating the training cognitive reserve score for each set of training data, the training cognitive reserve score representing a subjective assessment of the training subject independent of the training EEG dataset collected from the training subject and independent of the model;
extracting, from the training EEG dataset corresponding to each set of training data, one or more EEG-based metrics independent of the training cognitive reserve score for the set of training data,
wherein the one or more EEG-based metrics comprise any one or combination of
slow oscillation amplitude,
slow oscillation slope,
an amount of slow oscillation spindle-coupling,
an amount of slow-wave sleep, and
an amount of rapid eye movement (REM) sleep;
identifying one or more correlations between the one or more EEG-based metrics and the training cognitive reserve scores by:
identifying a first coefficient corresponding to the one or more EEG- based metrics; and
identifying a second coefficient corresponding to the training cognitive reserve scores,
wherein the first coefficient and the second coefficient maximize a correlation between a transformation of the one or more EEG-based metrics and a transformation of the training cognitive reserve scores; and
training the model based on the one or more correlations; and
causing the device to deliver, via the stimulation generation circuitry, neurostimulation to the subject based on the cognitive reserve of the subject.
see in re claim 1 above.
In re claim 22, regarding the limitations, “a system comprising:
one or more processors; and
a memory storing instructions that, when executed by the processors, cause the one or more processors to:
receive, from one or more EEG sensors of a device, an EEG signal collected from a subject; and
apply a model to the EEG signal to determine a cognitive reserve of the subject,
wherein the model is trained using a plurality of sets of training data,
each set of training data including
a training EEG dataset collected from a training subject and
a training cognitive reserve score corresponding to the training subject that is determined based on metrics separate from the training EEG dataset,
wherein to train the model, the instructions cause the one or more processors to:
receive tagging data indicating the training cognitive reserve score for each set of training data, the training cognitive reserve score representing a subjective assessment of the training subject independent of the training EEG dataset collected from the training subject and independent of the model;
extract, from the training EEG dataset corresponding to each set of training data, one or more EEG-based metrics independent of the training cognitive reserve score for the set of training data,
wherein the one or more EEG-based metrics comprise any one or combination of
slow oscillation amplitude,
slow oscillation slope,
an amount of slow oscillation spindle-coupling,
an amount of slow-wave sleep, and
an amount of rapid eye movement (REM) sleep;
identifying one or more correlations between the one or more EEG-based metrics and the training cognitive reserve scores by:
identifying a first coefficient corresponding to the one or more EEG-based metrics; and
identifying a second coefficient corresponding to the training cognitive reserve scores,
wherein the first coefficient and the second coefficient maximize a correlation between a transformation of the one or more EEG-based metrics and a transformation of the training cognitive reserve scores; and
train the model based on the one or more correlations; and
cause the device to deliver, via stimulation generation circuitry of the device, neurostimulation to the subject based on the cognitive reserve of the subject”,
see in re claim 1 above.
In re claim 23, the proposed combination yields (all mapping directed to Kang unless otherwise stated)
a device comprising one or more sensors (see in re claim 1 above) and stimulation generation circuitry (see the proposed combination yielded in re claim 1 above),
wherein the device is configured to collect, from a subject, one or more physiological signals ([0050]: EEG signal) using the one or more sensors (see in re claim 1 above);
one or more processors (see in re claim 1 above); and
a memory storing instructions that, when executed by the processors, cause the one or more processors to (see in re claim 1 above):
receive, from the one or more sensors of the device, the one or more physiological signals collected from the subject [0050];
generate, based on the one or more physiological signals, a proxy ([0014]: hidden data is interpreted as a proxy) for an electroencephalogram (EEG) signal ([0014]: hidden data is based on inferences made by machine learning from factors included in the ECG signal); and
apply a model to the proxy for the EEG signal to determine a cognitive reserve of the subject ([0014]: model may be connected to hidden data and used by the machine learning to help with inferencing factors included in the ECG signal; [0091]: hidden data assists in output data related to cognitive impairment; [0107-0109]: model may classify input data based on extracted features which could be hidden values).
Regarding the limitations,
“wherein the model is trained using a plurality of sets of training data,
each set of training data including a training EEG dataset collected from a training subject and a training cognitive reserve score corresponding to the training subject that is determined based on metrics separate from the training EEG dataset,
wherein to train the model, the instructions cause the one or more processors to:
receive tagging data indicating the training cognitive reserve score for each set of training data, the training cognitive reserve score representing a subjective assessment of the training subject independent of the training EEG dataset collected from the training subject and independent of the model;
extract, from the training EEG dataset corresponding to each set of training data, one or more EEG-based metrics independent of the training cognitive reserve score for the set of training data,
wherein the one or more EEG-based metrics comprise any one or combination of
slow oscillation amplitude,
slow oscillation slope,
an amount of slow oscillation spindle-coupling,
an amount of slow-wave sleep, and
an amount of rapid eye movement (REM) sleep;
identifying one or more correlations between the one or more EEG-based metrics and the training cognitive reserve scores by:
identifying a first coefficient corresponding to the one or more EEG-based metrics; and
identifying a second coefficient corresponding to the training cognitive reserve scores,
wherein the first coefficient and the second coefficient maximize a correlation between a transformation of the one or more EEG-based metrics and a transformation of the training cognitive reserve scores; and train the model based on the one or more correlations; and
cause the device to deliver, via the stimulation generation circuitry, neurostimulation to the subject based on the cognitive reserve of the subject”,
see in re claim 1 above.
In re claim 27, regarding the limitations, “wherein
the first coefficient comprises a first set of coefficient values and
the second coefficient comprises a second set of coefficient values”,
see the proposed combination yielded in re claim 1 above.
In re claim 28, regarding the limitations,
“wherein the transformation of the one or more EEG-based metrics can include one of a linear transformation and a nonlinear transformation, and
wherein the transformation of the training cognitive reserve scores can include one of a linear transformation or a nonlinear transformation”,
see the proposed combination yielded in re claim 1 above.
In re claim 24, the proposed combination yields (all mapping directed to Kang unless otherwise stated) wherein the one or more physiological signals comprise one or more cardiac signals ([0109]: hidden data may include vascular damage and oxidative stress which are cardiac related signals).
Claim 4 is rejected under 35 U.S.C. 103 as being unpatentable over Kang et al. (US 2020/0260977) in view of Rogers (US 2010/0198282) in view of Okuno et al. (US 2010/0099891) in view of Black et al. (US 2021/0361943).
In re claim 4, the proposed combination fails to yield
wherein the stimulation generation circuitry comprises one or more audio transducers, and
wherein to cause the device to deliver neurostimulation to the subject, the one or more processors cause the one or more audio transducers of the device to deliver audio stimulation to the subject in a way that stimulates a nervous system of the subject.
Black teaches providing treatment to increase cognitive reserve [0046], and teaches
wherein a stimulation generation circuitry ([0105]: stimulation device 500 would include stimulation generation circuitry; fig. 5A; [0079]) comprises one or more audio transducers ([0108]: speakers attached to electrodes), and
wherein to cause the device to deliver neurostimulation to a subject [0108], one or more processors (510A; [0111, 0249]) cause the one or more audio transducers of the device to deliver audio stimulation [0108, 0111] to the subject in a way that stimulates [0108] a nervous system of the subject [0111].
Black further teaches that neurostimulation is therapeutic for the nervous system, and can either be stimulated electrically, or non-electrically (i.e. through light, sound, or temperature) [0003, 0108]. Black additionally teaches that the audio stimulation delivers galvanic vestibular stimulation [0106, 0108], which targets portions of a brain [0132], and that treatment can increase cognitive reserve [0046].
It would have been obvious to someone of ordinary skill in the art at the time the instant invention was filed to modify the system yielded by the proposed combination, to provide wherein the stimulation generation circuitry comprises one or more audio transducers, and wherein to cause the device to deliver neurostimulation to the subject, the one or more processors cause the one or more audio transducers of the device to deliver audio stimulation to the subject in a way that stimulates a nervous system of the subject, as taught by Black, because neurostimulation is therapeutic for the nervous system, and can either be stimulated electrically, or non-electrically, and can be used to increase cognitive reserve.
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Kang et al. (US 2020/0260977) in view of Rogers (US 2010/0198282) in view of Okuno et al. (US 2010/0099891) in view of Maxwell et al. (US 2009/0043662).
In re claim 7, the proposed combination yields (all mapping directed to Kang unless otherwise stated) wherein the one or more processors are further configured to determine one or more behavioral changes for the subject ([0116]: lifestyle habits may be recommended) to treat cognitive impairment.
The proposed combination fails to yield wherein the one or more processors are further configured to determine one or more behavioral changes for the subject to enhance cognitive reserve.
Maxwell teaches improving cognitive reserve [0006], and teaches determining one or more behavioral changes [0018] for a subject to enhance cognitive reserve [0018].
Maxwell further teaches that eating, physical, and mental activities may be used to enhance cognitive reserves [0018].
It would have been obvious to someone of ordinary skill in the art at the time the instant invention was filed to modify the system yielded by the proposed combination, to provide one or more behavioral changes for the subject to enhance cognitive reserve, as taught by Maxwell, because eating, physical, and mental activities may be used to enhance cognitive reserves.
Claim 11 is rejected under 35 U.S.C. 103 as being unpatentable over Kang et al. (US 2020/0260977) in view of Rogers (US 2010/0198282) in view of Okuno et al. (US 2010/0099891) in view of Garcia Molina (US 2021/0282698).
In re claim 11, the proposed combination fails to yield wherein the EEG signal corresponds to two or more sleep sessions of the subject.
Garcia Molina teaches detecting cognitive decline in a subject [0027] and teaches wherein EEG signal [0044] corresponds to two or more sleep sessions of a subject [0044].
Garcia Molina further teaches that EEG amplitude can be measured over years to depict changes such as different levels of cognitive impairment (fig. 4: EEG amplitude is used to determine a difference between mild cognitive impairment and dementia; [0041]).
It would have been obvious to someone of ordinary skill in the art at the time the instant invention was filed to modify the one or more actions of the system yielded by the proposed combination, to provide wherein the EEG signal corresponds to two or more sleep sessions of the subject, as taught by Garcia Molina, because EEG measured over time provides information about changes in cognitive impairment over a period of time.
Claim 13 is rejected under 35 U.S.C. 103 as being unpatentable over Kang et al. (US 2020/0260977) in view of Rogers (US 2010/0198282) in view of Okuno et al. (US 2010/0099891) in view of Islam et al. (US 2024/0117432).
In re claim 13, the proposed combination fails to yield wherein the cognitive reserve of the subject comprises a cognitive reserve value that indicates the cognitive reserve of the subject, the cognitive reserve value being on:
a scale that extends from a lower-bound cognitive reserve value to an upper-bound cognitive reserve value; or
a general classification of cognitive reserve comprising
low cognitive reserve,
medium cognitive reserve, or
high cognitive reserve.
Islam teaches a method for detecting a neurophysiological condition [0010], and teaches wherein a cognitive reserve [0092] of a subject comprises a cognitive reserve value that indicates the cognitive reserve of the subject ([0092]: low cognitive reserve is an example of a cognitive reserve value), the cognitive reserve value being on:
a scale that extends from a lower-bound cognitive reserve value to an upper-bound cognitive reserve value; or
a general classification [0092] of cognitive reserve comprising
low cognitive reserve [0092],
medium cognitive reserve, or
high cognitive reserve.
Islam further teaches that cognitive reserve is correlated with preserved cognitive function [0004], and that a low cognitive reserve would show risk to develop cognitive decline [0092].
It would have been obvious to someone of ordinary skill in the art at the time the instant invention was filed to modify the system yielded by the proposed combination, to provide wherein the cognitive reserve of the subject comprises a cognitive reserve value that indicates the cognitive reserve of the subject, the cognitive reserve value being on: a scale that extends from a lower-bound cognitive reserve value to an upper-bound cognitive reserve value; or a general classification of cognitive reserve comprising low cognitive reserve, medium cognitive reserve, or high cognitive reserve, as taught by Islam, because cognitive reserve is correlated with preserved cognitive function and having a general classification such as a low cognitive reserve can be correlated with a risk to develop cognitive decline.
Claim 16 is rejected under 35 U.S.C. 103 as being unpatentable over Kang et al. (US 2020/0260977) in view of Rogers (US 2010/0198282) in view of Okuno et al. (US 2010/0099891) in view of Bach et al. (US 2022/0133194) in view of Kawato et al. (US 2015/0294074).
In re claim 16, the proposed combination yields (all mapping directed to Kang unless otherwise stated) wherein to train the model, the one or more processors are configured to use machine learning [0091] to determine the one or more correlations between the one or more EEG-based metrics and the training cognitive reserve scores ([0091]: machine learning used to determine relationship; [0088]).
The proposed combination fails to yield wherein to train the model, the one or more processors are configured to use regularized canonical correlation analysis (RCCA) to identify the one or more correlations between the one or more EEG-based metrics and the training cognitive reserve scores.
Kawato teaches a brain activity detecting apparatus [0290] which uses EEG [0290] and teaches wherein to train a model [0057], one or more processors ([0112]: general purpose computer which executes functions) are configured to use regularized canonical correlation analysis (RCCA) [0062] to identify one or more correlations between brain activities [0062-0064].
Kawato further teaches that training without using a discriminator ([0154]: discriminator generated from result of the RCCA; [0159]: machine learning includes the discriminator) may cause the model to be over-fitted [0158].
The proposed combination would be for the machine learning of Kang to include the regularized canonical correlation analysis (RCCA) of Kawato.
It would have been obvious to someone of ordinary skill in the art at the time the instant invention was filed to modify the system yielded by the proposed combination, to provide the one or more processors are configured to use regularized canonical correlation analysis (RCCA) to identify the one or more correlations between the one or more EEG-based metrics and the training cognitive reserve scores, as taught by the RCCA in Kawato which is used to determine correlations between brain activity, because doing so prevents the training model to be over-fitted.
Claim 17 is rejected under 35 U.S.C. 103 as being unpatentable over Kang et al. (US 2020/0260977) in view of Rogers (US 2010/0198282) in view of Okuno et al. (US 2010/0099891) in view of Bach et al. (US 2022/0133194).
In re claim 17, the proposed combination yields (all mapping directed to Kang unless otherwise stated) wherein the model is a machine learning model [0046, 0091].
The proposed combination fails to yield wherein to train the machine learning model, the one or more processors are configured to generate one or more layers.
Bach teaches
a method of using a machine learning model [0009] to determine correlation between a person’s neurophysiological data [0009] and the person’s performance [0009],
wherein to train the machine learning model [0012], one or more processors [0603-0605] are configured to generate one or more layers [0012].
Bach further teaches that a second machine learning layer may be used for providing correlation between data [0012], for instance, the probability of a person performing an activity well [0012].
It would have been obvious to someone of ordinary skill in the art at the time the instant invention was filed to modify the system yielded by the proposed combination, to provide wherein to train the machine learning model, the one or more processors are configured to generate one or more layers, as taught by Bach, because having multiple layers provides additional analysis such as correlations to be made [0012].
Claims 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Kang et al. (US 2020/0260977) in view of Rogers (US 2010/0198282) in view of Okuno et al. (US 2010/0099891) in view of Goto et al. (US 2021/0358126) in view of Wischik et al. (US 2010/0280975).
In re claim 18, the proposed combination yields (all mapping directed to Kang unless otherwise stated)
wherein each set of training data of the plurality of sets of training data further includes
a performance score of the training subject ([0088]: input data includes qualitatively superior data determined using a test on an input user) and
a brain image of the training subject [0088],
wherein the training cognitive reserve score is determined based on the performance score and the brain image ([0094]: degree of impairment may output the degree of the cognitive impairment using features extracted; [0090]: brain image may be part of input; [0088, 0091, 0094]).
The proposed combination fails to yield
wherein each set of training data of the plurality of sets of training data further includes
a cognitive performance score of the training subject and
a level of a protein of the training subject,
wherein the training cognitive reserve score is determined based on the cognitive performance score and the level of the protein.
Goto teaches training a model to output functional change information of a subject [0009], and teaches
wherein each set of training data [0038] of a plurality of sets of training data [0038] further includes
a cognitive performance score of a training subject score ([0037]: MMSE is a cognitive performance score) and
a level of a protein of a training subject ([0071]: amount of amyloid beta peptide-related proteins; [0074)],
wherein a training dementia score ([0038]: functional change information; [0059-0060]: function change information is used to predict degree of progression of dementia; [0074-0075]) is determined based on the cognitive performance score ([0053]: functional change information ΔF includes score F regarding the MMSE; [0037]) and the level of the protein ([0071]: protein used in training data; [0074]: functional change information ΔF includes protein information; [0053]).
Goto further teaches that MMSE can be used for physiological examination for examination of dementia [0037], and that amyloid beta peptide-related proteins can be used to predict mild cognitive impairment [0071], and that functional change information of a person can be determined using MMSE [0053] as well as the level of protein [0074].
It would have been obvious to someone of ordinary skill in the art at the time the instant invention was filed to modify the system yielded by the proposed combination, to provide wherein each set of training data of the plurality of sets of training data further includes a cognitive performance score of the training subject and a level of a protein of the training subject, wherein a score is determined based on the cognitive performance score and the level of the protein, as taught by Goto, because the MMSE can be used for physiological examination for examination of dementia, and because amyloid beta peptide-related proteins can be used to predict mild cognitive impairment as well as functional change information of a person in combination with MMSE.
Regarding the limitation, “wherein the training cognitive reserve score is determined based on the cognitive performance score and the level of the protein” Wischik teaches an analogous invention directed to cognitive reserve [0029], and teaches wherein a cognitive reserve [0301] is based on a cognitive performance score [0301] and a level of protein ([0301]: Tau).
Wischik further teaches that MMSE may give false impressions about disease progress [0301], whereas Tau can be used to show functional consequences over time [0301]. Wischik further teaches that cognitive reserve may mask ongoing disease progression, so subjects do not appear to decline clinically [0029], therefore proteins such as Tau can be used to detect neurodegeneration such as dementia [0088-0089].
The proposed combination would yield wherein the training cognitive reserve score of Kang is determined based on the cognitive performance score and the level of the protein, as taught by Goto which teaches using the MMSE and the level of protein to functional change information, and as taught by Wischik, which teaches using MMSE and Tau to obtain information regarding cognitive reserve.
It would have been obvious to someone of ordinary skill in the art at the time the instant invention was filed to modify the training cognitive reserve score yielded by the proposed combination, to be determined based on the cognitive performance score and the level of the protein, as taught by Wischik, because MMSE may give false impressions about disease progress since cognitive reserve may mask ongoing disease progression, therefore, Tau can also be used to show neurodegeneration.
In re claim 19, regarding the limitation, “wherein the cognitive performance score comprises any one or combination of
a Montreal cognitive assessment (MOCA) score,
a mini-mental state examination (MMSE) score,
a National Institute of Health (NIH) cognitive test battery score, and
a neurophysiological test battery in the uniform data set score”,
see the proposed combination yielded in re claim 18 above.
In re claim 20, regarding the limitation, “wherein the protein comprises one of beta-amyloid (Ap), tau, and neurofilament light chains (NfL)”, see the proposed combination yielded in re claim 18 above.
Claims 25-26 are rejected under 35 U.S.C. 103 as being unpatentable over Kang et al. (US 2020/0260977) in view of Rogers (US 2010/0198282) in view of Okuno et al. (US 2010/0099891) in view of Das et al. (US 2020/0012665).
In re claim 25, the proposed combination yields (all mapping directed to Kang unless otherwise stated) wherein the one or more EEG based metrics comprise a plurality of EEG-based metrics ([0129]: EEG based metrics includes cognitive impairment-related information, which includes the degree of the cognitive impairment and the cause of the cognitive impairment, are based on the measured EEG signal; [0067]).
The proposed combination fails to yield wherein to train the model, the instructions further cause the one or more processors to:
select, using a sequential feature selection model, a proper subset of EEG-based metrics from the plurality of EEG-based metrics,
the sequential feature selection model identifying the proper subset of EEG-based metrics as more relevant for determining cognitive reserve of the subject that EEG-based metrics of the plurality of EEG-based metrics not selected for the proper subset of EEG-based metrics; and
train the model based on the proper subset of EEG-based metrics.
Das teaches an analogous method for clustering users using cognitive stress report [0002] and wherein to train a model [0004], instructions [0007] cause one or more processors [0007] to:
select, using a sequential feature selection model ([0040]: uses mRMR ranking scheme for feature importances), a proper subset of EEG-based metrics from a plurality of EEG-based metrics ([0040]: EEG features are ranked to determine top 5 EEG features; [0030]),
the sequential feature selection model identifying the proper subset of EEG-based metrics as more relevant for determining cognitive reserve of a subject that EEG-based metrics of the plurality of EEG-based metrics not selected for the proper subset of EEG-based metrics ([0040]: top 5 EEG features were ranked for their performance and are related to a cognitive stress classification module which is interpreted as being directly related to cognitive reserve because too much stress requires interventions to promote wellbeing and prevent chronic mental disorders [0003]); and
train the model based on the proper subset of EEG-based metrics ([0040]: model trained based on top features given by mRMR; [0030]).
Das further teaches that ranking the EEG features allows them to be associated with a primary cluster [0006], which is then used to select users for training [0006], and ensures that only the top EEG features are used for training [0040].
It would have been obvious to someone of ordinary skill in the art at the time the instant invention was filed to modify the system yielded by the proposed combination, to provide wherein to train the model, the instructions further cause the one or more processors to: select, using a sequential feature selection model, a proper subset of EEG-based metrics from the plurality of EEG-based metrics, the sequential feature selection model identifying the proper subset of EEG-based metrics as more relevant for determining cognitive reserve of the subject that EEG-based metrics of the plurality of EEG-based metrics not selected for the proper subset of EEG-based metrics; and train the model based on the proper subset of EEG-based metrics, as taught by Das, because ranking the EEG features allows them to be used to select users for training, and ensures that only the top EEG features are used for training.
In re claim 26, regarding the limitation, “wherein the sequential feature selection model uses Minimum Redundancy Maximum Relevance (mRMR) techniques to select the proper subset of EEG-based metrics”, see the proposed combination yielded in re claim 25 above.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure:
Kasahara et al. (US 2020/0170553) discloses a measuring apparatus (abstract) that measures blood glucose level (abstract) and teaches maximizing a correlation coefficient using a multiple linear regression model [0114].
Contact
Any inquiry concerning this communication or earlier communications from the examiner should be directed to RUMAISA R BAIG whose telephone number is (571)270-0175. The examiner can normally be reached Mon-Fri: 8am- 5pm.
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, David Hamaoui can be reached at (571) 270-5625. 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.
/RUMAISA RASHID BAIG/Examiner, Art Unit 3796
/DAVID HAMAOUI/SPE, Art Unit 3796
Prosecution Insights