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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 19 May 2026 has been entered.
Response to Amendment
The amendments filed 19 May 2026 have been entered. Claims 1 – 6 and 9 – 10 are pending. Applicant’s amendments to the claims have overcome each and every objection to the specification previously applied in the office action dated 20 February 2026. Applicant’s amendments have not overcome each and every rejection under 35 U.S.C. 112 previously-applied in the office action dated 20 February 2026.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are:
A “machine learning unit” in Claim 1 (and dependent claims) “for determining”.
The claim limitation is interpreted according to paragraphs [0028], [0035], [0036], [0039], [0041], and [0044] of the instant specification. The machine learning unit includes at least one classifier based on a SVM, adaptive boost, or neural network architecture, “but the invention is not limited thereto”. It has a training mode and an interpretation mode. It is identified as both generic box component “machine learning unit” 105 in FIG 1 and “machine learning unit” 225 in FIG 2. There is insufficient disclosure present of the corresponding structure that performs the claimed function “to connect” and “for determining”.
A “signal pre-processing unit” in Claims 2, 3, and 5 (and their dependent claims) for “signal pre-processing”).
The claim limitation is interpreted according to paragraphs [0028], [0030], [0031], [0041], and [0042], of the instant specification. The signal pre-processing unit is used to pre-process the EEG signals, which could include down sampling and band pass filtering. At [0031] under a certain condition, “the signal pre-processing unit 102 might not be necessary for the auxiliary determination device 100 and might be removed.” It is identified as a generic box component “signal pre-processing unit” 102 in FIG 1 and “signal pre-processing unit” 222. There is insufficient disclosure present of the corresponding structure that performs the claimed function “for performing” or “to connect”.
A “frequency band screening unit” in Claim 3 (and dependent claims) “for screening”
The claim limitation is interpreted according to paragraphs [0028], [0032], [0033], [0041], and [0042 of the instant specification. It is “electrically connected” to the feature extraction unit and used to screen EEG signals transmitted from the EEG unit. If the “interpretation” is “performed for all frequency bands” of the EEG signals, then “the frequency band screening unit 103 might not be necessary and might be removed.” The frequency band screening unit uses mathematical transform methods like wavelets. It is identified as a generic box component “frequency band screening unit” 103 in FIG 1 and “frequency band screening unit” 223 in FIG 2. There is insufficient disclosure present of the corresponding structure that performs the claimed function “for screening”.
An “EEG signal measuring unit” in Claim 5 (and dependent claims) “for measuring” and Claim 6 (“to acquire”).
The claim limitation is interpreted according to paragraphs [0020], [0028] – [0032], and [0041] – [0043] of the instant specification. It is described as a dry or wet electrode EEG signal measuring device with 32, 64, or 128 electrodes, and “the invention is not limited by the type of the electroencephalography signal measuring device”. It is identified as a generic box component “electroencephalography signal measuring unit” 101 in FIG 1, “electroencephalography signal measuring unit” 211 in FIG 2, and “electroencephalography signal measuring unit” scalp electrode layout in Fig 3.
Because these claim limitations are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, they are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1 – 6 and 9 – 10 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Claim 1 recites the limitation “machine learning unit”. Here, the claim recites the function of determining whether the TMS is effective for the patient according to at least one feature of the EEG signals, but the specification never discloses if this is accomplished using physical or software means. The term “machine learning unit”/”at least one classifier” is treated as a black box and the specification does not describe the specifics of how to achieve the above-recited functions of “electrically connecting” to the frequency band screening unit with this algorithm. It is not specified how the “machine learning unit” is “electrically connected to the feature extraction unit”, or which part is connected by the electricity, particularly if the signal pre-processing unit is software/algorithms and not physical structure. It is not enough that a skilled artisan could devise a way to accomplish the function because this is not relevant to the issue of whether the inventor has shown possession of the claimed invention. See MPEP 2161.01(I). Therefore, adequate disclosure is needed. Claims 2 – 6 and 9 – 10 are similarly rejected due to their dependence on Claim 1.
Claims 2 and 5 recite the limitation “signal pre-processing unit”. The specification notes that signal pre-processing unit is used to pre-process the EEG signals, which could include down sampling and band pass filtering in paragraphs [0028], [0030], [0031], [0041], and [0042], but provides no description of the structural components associated with performing this “pre-processing”. It is not specified if the bandpass filtering is software filtering or component filtering. It is also not specified how the “signal pre-processing unit” is “electrically connected to the feature extraction unit”, or which part is connected by the electricity, particularly if the signal pre-processing unit is software/algorithms and not physical structure. Therefore, adequate disclosure is needed. Claims 3 – 6 are similarly rejected due to their dependence on Claim 2 and 5.
Claim 3 recites the limitation “frequency band screening unit”. The specification notes in paragraphs [0028], [0032], [0033], [0041], and [0042] that the frequency band screening unit is “electrically connected” to the feature extraction unit, is used to screen EEG signals transmitted from the EEG unit, and is sometimes “not needed”, but provides no description of the steps or hardware necessary to accomplish these steps. It is not specified if this is a software or hardware component. It is also not specified how the “signal pre-processing unit”, “machine learning unit”, and “frequency band screening unit” are each “electrically connected to the feature extraction unit”, or which parts are connected by the electricity, particularly if the different units are software/algorithms and not physical structure. Therefore, adequate disclosure is needed. Claim 4 is similarly rejected due to its dependence on Claim 3.
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 – 6 and 9 - 10 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 1 recites the term “EEG signals are EEG signals of the patient after” in line 10. It is unclear if the “EEG signals of the patient” are same or different than the previously-recited “EEG signals of the patient”. For the purposes of examination, the term “EEG signals are EEG signals of the patient after” is deemed to claim “EEG signals are the EEG signals of the patient after”. Claims 2 – 6 and 9 – 10 are similarly rejected due to their dependence on Claim 1.
Claim 1 recites the term “the group consisting of a band power” in line 19 - 20. There is insufficient antecedent basis for the “group” limitation. For the purposes of examination, the term “the group consisting of a band power” is deemed to claim “a group consisting of a band power”. Claims 2 – 6 and 9 – 10 are similarly rejected due to their dependence on Claim 1.
Claim limitations
“machine learning unit” in Claim 1 and its dependent claims
“signal pre-processing unit” in Claims 2, 3, and 5 and their dependent claims
“frequency band screening unit” in Claim 3 and its dependent claims
invoke 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. However, the written description fails to disclose the corresponding structure, material, or acts for performing the entire claimed function and to clearly link the structure, material, or acts to the function.
As described in the 112(f) claim interpretation above, “machine learning unit” is described with functions and no structure in specification paragraphs [0028], [0035], [0036], [0039], [0041], and [0044]. The component is disclosed as a generic box component “machine learning unit” 105 in FIG 1 and “machine learning unit” 225 in FIG 2. It is unclear what part of the machine learning unit is intended to be “electrically connected to the feature extraction unit”, or connected by electricity, particularly if the machine learning unit is software/algorithms. For the purposes of examination, the term “a machine learning unit electrically connected to the feature extraction unit” is deemed to claim “a machine learning unit in communication with the feature extraction unit.”
As described in the 112(f) claim interpretation above, “signal pre-processing unit” is described with functions and no structure in specification paragraphs [0028], [0030], [0031], [0041], and [0042]. The component is disclosed as a generic box component “signal pre-processing unit” 102 in FIG 1 and “signal pre-processing unit” 222. It is unclear what part of the signal pre-processing unit is intended to be “electrically connected to the feature extraction unit”, or connected by electricity, particularly if the signal pre-processing unit is software/algorithms. For the purposes of examination, the term “a signal pre-processing unit electrically connected to the feature extraction unit” is deemed to claim “a signal pre-processing unit in communication with the feature extraction unit.”
As described in the 112(f) claim interpretation above, “frequency band screening unit” is described with functions and no structure in specification paragraphs [0028], [0032], [0033], [0041], and [0042]. The component is disclosed as a generic box component “frequency band screening unit” 103 in FIG 1 and “frequency band screening unit” 223 in FIG 2. It is unclear what part of the frequency band screening unit is intended to be “electrically connected to the feature extraction unit”, or connected by electricity, particularly if the frequency band screening unit is software/algorithms. For the purposes of examination, the term “a frequency band screening unit electrically connected to the feature extraction unit” is deemed to claim “a frequency band screening unit in communication with the feature extraction unit.”
Therefore, the claim is indefinite and is rejected under 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, second paragraph.
Applicant may:
(a) Amend the claim so that the claim limitation will no longer be interpreted as a limitation under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph;
(b) Amend the written description of the specification such that it expressly recites what structure, material, or acts perform the entire claimed function, without introducing any new matter (35 U.S.C. 132(a)); or
(c) Amend the written description of the specification such that it clearly links the structure, material, or acts disclosed therein to the function recited in the claim, without introducing any new matter (35 U.S.C. 132(a)).
If applicant is of the opinion that the written description of the specification already implicitly or inherently discloses the corresponding structure, material, or acts and clearly links them to the function so that one of ordinary skill in the art would recognize what structure, material, or acts perform the claimed function, applicant should clarify the record by either:
(a) Amending the written description of the specification such that it expressly recites the corresponding structure, material, or acts for performing the claimed function and clearly links or associates the structure, material, or acts to the claimed function, without introducing any new matter (35 U.S.C. 132(a)); or
(b) Stating on the record what the corresponding structure, material, or acts, which are implicitly or inherently set forth in the written description of the specification, perform the claimed function. For more information, see 37 CFR 1.75(d) and MPEP §§ 608.01(o) and 2181.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1 – 6 and 9 - 10 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Regarding Claim 1, the claims recites an apparatus, which is one of the statutory categories of invention (Step 1). The claim is then analyzed to determine whether it is directed to any judicial exception (Step 2A, Prong 1).
Each of Claims 1 – 6 and 9 - 10 has been analyzed to determine whether it is directed to any judicial exceptions.
Step 2A, Prong 1
Each of Claims 1 – 6 and 9 - 10 recites at least one step or instruction for observations, evaluations, judgments, and opinions, which are grouped as a mental process under the 2019 PEG. The claimed invention involves making observations, evaluations, judgments, and opinions, which are concepts performed in the human mind under the 2019 PEG.
Accordingly, each of Claims 1 – 6 and 9 - 10 recites an abstract idea.
Specifically, Independent Claim 1 recites (underlined are observations, judgements, evaluations, or opinions, which are grouped as a mental process under the 2019 PEG) (additional elements bolded, see Step 2A, prong 2);
An auxiliary determination device for evaluating whether a transcranial magnetic stimulation is effective for a patient with depression, the auxiliary determination device comprising:
a feature extraction unit comprising a processor configured to perform a non-linear extraction process and a linear extraction process on electroencephalography (EEG) signals of the patient in an interpretation mode to generate a plurality of feature values, wherein the EEG signals are EEG signals of the patient after being driven by a cognitive operation or a difference between the EEG signals of the patient before and after being driven by the cognitive operation, and the plurality of feature values comprise:
at least one non-linear feature value generated by the non-linear extraction process, the at least one non-linear feature value being a detrended fluctuation; and
at least one linear feature value generated by the linear extraction process, the at least one linear feature value being selected from the group consisting of a band power of fast Fourier transform and a band power of Welch periodogram; and
a machine learning unit electrically connected to the feature extraction unit and comprising at least one classifier configured to classify the EEG signals into a category indicating an efficacy of the transcranial magnetic stimulation for the patient according to the plurality of feature values in the interpretation mode, wherein the at least one classifier is based on a support vector machine, an adaptive boost, or a neural network architecture.
(observation, judgment or evaluation, which is grouped as a mental process under the 2019 PEG);
These underlined limitations describe a mathematical calculation and/or a mental process, as a skilled practitioner is capable of performing the recited limitations and making a mental assessment thereafter. Examiner notes that nothing from the claims suggests that the limitations cannot be practically performed by a human with the aid of a pen and paper, or by using a generic computer as a tool to perform mathematical calculations and/or mental process steps in real time. Examiner additionally notes that nothing from the claims suggests and undue level of complexity that the mathematical calculations and/or the mental process steps cannot be practically performed by a human with the aid of a pen and paper, or using a generic computer as a tool to perform mathematical calculations and/or mental process steps. For example, in Independent Claim 1, these limitations include:
Observation and judgment to evaluate using a non-linear extraction process and a linear extraction process on electroencephalography (EEG) signals of the patient in an interpretation mode to generate a plurality of feature values
Observation and judgment to classify the EEG signals into a category indicating an efficacy of the transcranial magnetic stimulation for the patient according to the plurality of feature values in the interpretation mode
Similarly, Dependent Claims 2 – 6 and 9 - 10 include the following abstract limitations, in addition the aforementioned limitations in Independent Claim 1 (underlined observation, judgment or evaluation, which is grouped as a mental process under the 2019 PEG):
perform a signal pre-processing on the EEG signals in the interpretation mode.
Evaluating a signal pre-processing on the EEG signals in the interpretation mode
which is grouped as mental processes or mathematical algorithm under the 2019 PEG.
Accordingly, as indicated above, each of the above-identified claims recite an abstract idea.
Step 2A, Prong 2
The above-identified abstract ideas in each of Independent Claim 1 (and their Dependent Claims 2 – 6 and 9 - 10) are not integrated into a practical application under 2019 PEG because the additional elements (identified in Claims 1 – 6 and 9 - 10), either alone or in combination, generally link the use of the above-identified abstract ideas to a particular technological environment or field of use. More specifically, the additional elements of:
“feature extraction unit”
“processor”
“machine learning unit”
“at least one classifier”
“signal pre-processing unit”
“frequency band screening unit”
“EEG signal measuring unit”
“support vector machine”
“adaptive boost”
“neural network architecture”
Additional elements recited include “feature extraction unit”, “processor”, “machine learning unit”, “at least one classifier”, “signal pre-processing unit”, “frequency band screening unit”, “EEG signal measuring unit”, “support vector machine”, “adaptive boost”, and ”neural network architecture” in Independent Claim 1, (and its Dependent Claims). These components are recited at a high level of generality, i.e., as a generic “feature extraction unit” for extracting features and “EEG signal measuring unit” for measuring signals. These generic component limitations for “feature extraction unit”, “processor”, “machine learning unit”, “at least one classifier”, “signal pre-processing unit”, “frequency band screening unit”, “EEG signal measuring unit”, “support vector machine”, “adaptive boost”, and ”neural network architecture” are no more than mere instructions to apply the exception using generic computer software and hardware components. As such, these additional elements do not impose any meaningful limits on practicing the abstract idea.
Further additional elements from Independent Claim 1 includes pre-solution activity limitations, such as:
wherein the EEG signals are EEG signals of the patient after being driven by a cognitive operation or a difference between the EEG signals before and after being driven by the cognitive operation, a machine learning unit electrically connected to the feature extraction unit
the plurality of feature values comprise: at least one non-linear feature value generated by the non-linear extraction process, the at least one non-linear feature value being a detrended fluctuation; and at least one linear feature value generated by the linear extraction process, the at least one linear feature value being selected from the group consisting of a band power of fast Fourier transform and a band power of Welch periodogram
a machine learning unit electrically connected to the feature extraction unit and comprising at least one classifier
the at least one classifier is based on a support vector machine, an adaptive boost, or a neural network architectures.
In addition the aforementioned extra-solution activity limitations in Independent Claim 1, additional extra-solution activity limitations recited in Dependent Claims 2 - 10 include:
wherein the signal pre-processing comprises at least one of a bandpass filtering, a resampling, and an independent component analysis.
a frequency band screening unit electrically connected to the feature extraction unit and the signal pre-processing unit for screening frequency bands of the EEG signals in the interpretation mode to acquire the EEG signals within particular frequency bands for subsequent feature extraction and signal interpretation.
wherein the particular frequency bands are α (alpha) ,β (beta),y (gamma) ,Θ (theta) and δ (delta) frequency bands.
an EEG signal measuring unit electrically connected to or communicated with the signal pre-processing unit for measuring the EEG signals
wherein the EEG signals are acquired through at least one electrode of Fp1, Fp2, F3, F4, F7, F8, and Fz of the EEG signal measuring unit.
These pre-solution measurement elements are insignificant extra-solution activity, setting up the parameters of the system, and serve as data-gathering for the subsequent steps.
The “feature extraction unit”, “processor”, “machine learning unit”, “at least one classifier”, “signal pre-processing unit”, “frequency band screening unit”, “EEG signal measuring unit”, “support vector machine”, “adaptive boost”, and ”neural network architecture” as recited in Independent Claim 1 (and its Dependent Claim) are generically recited computer and hardware elements which do not improve the functioning of a computer, or any other technology or technical field. Nor do these above-identified additional elements serve to apply the above-identified abstract idea with, or by use of, a particular machine, effect a transformation or apply or use the above-identified abstract idea in some other meaningful way beyond generally linking the use thereof to a particular technological environment, such that the claim as a whole is more than a drafting effort designed to monopolize the exception. Furthermore, the above-identified additional elements do not add a meaningful limitation to the abstract idea because they amount to simply implementing the abstract idea on a computer. For at least these reasons, the abstract ideas identified above in Independent Claim 1 (and its dependent claims) is not integrated into a practical application under 2019 PEG.
Moreover, the above-identified abstract idea is not integrated into a practical application under 2019 PEG because the claimed method and system merely implements the above-identified abstract idea (e.g., mental process and certain method of organizing human activity) using rules (e.g., computer instructions) executed by a computer processor as claimed. In other words, these claims are merely directed to an abstract idea with additional generic computer elements which do not add a meaningful limitation to the abstract idea because they amount to simply implementing the abstract idea on a computer. Additionally, Applicant’s specification does not include any discussion of how the claimed invention provides a technical improvement realized by these claims over the prior art or any explanation of a technical problem having an unconventional technical solution that is expressed in these claims. That is, like Affinity Labs of Tex. v. DirecTV, LLC, the specification fails to provide sufficient details regarding the manner in which the claimed invention accomplishes any technical improvement or solution. Thus, for these additional reasons, the abstract idea identified above in Independent Claim 1 (and its dependent claims) is not integrated into a practical application under the 2019 PEG.
Accordingly, Independent Claim 1 (and its dependent claims) are each directed to an abstract idea under 2019 PEG.
Step 2B –
None of Claims 1 – 6 and 9 - 10 include additional elements that are sufficient to amount to significantly more than the abstract idea for at least the following reasons.
These claims require the additional elements of: “feature extraction unit”, “processor”, “machine learning unit”, “at least one classifier”, “signal pre-processing unit”, “frequency band screening unit”, “EEG signal measuring unit”, “support vector machine”, “adaptive boost”, and ”neural network architecture” as recited in Independent Claim 1 (and its dependent claims).
The additional elements of the “feature extraction unit”, “processor”, “machine learning unit”, “at least one classifier”, “signal pre-processing unit”, “frequency band screening unit”, “EEG signal measuring unit”, “support vector machine”, “adaptive boost”, and ”neural network architecture” in Independent Claim 1 (and its dependent claims), as discussed with respect to Step 2A Prong Two, amounts to no more than mere instructions to apply the exception using generic computer and hardware components. The same analysis applies here in 2B, i.e., mere instructions to apply an exception using a generic computer component cannot integrate a judicial exception into a practical application at Step 2A or provide an inventive concept in Step 2B.
The above-identified additional elements are generically claimed computer components which enable the above-identified abstract idea(s) to be conducted by performing the basic functions of automating mental tasks. The courts have recognized such computer functions as well understood, routine, and conventional functions when claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity. See, Versata Dev. Group, Inc. v. SAP Am., Inc. , 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015); and OIP Techs., 788 F.3d at 1363, 115 USPQ2d at 1092-93.
Per Applicant’s specification, the “feature extraction unit” is described generically in [0028], [0034], [0041], and [0042]. The feature extraction unit “extracts the feature value” of the EEG signals through mathematical processes of linear extraction and/or non-linear extraction. It is identified as both generic box component “feature extraction unit” 104 in FIG 1 and “feature extraction unit 224” in FIG 2.
Per Applicant’s specification, there is no “processor” clearly described. Per Applicant’s arguments filed 24 OCTOBER 2025, it is described that the “processor” is potentially part of the generically described “platform server” in [0040] – [0041].
Per Applicant’s specification, the “machine learning unit” is described generically in [0028], [0035], [0036], [0039], [0041], and [0044]. The machine learning unit includes at least one classifier based on a SVM, adaptive boost, or neural network architecture, “but the invention is not limited thereto”. It has a training mode and an interpretation mode. It is identified as both generic box component “machine learning unit” 105 in FIG 1 and “machine learning unit” 225 in FIG 2.
Per Applicant’s specification, the “at least one classifier”, “support vector machine”, “adaptive boost”, and ”neural network architecture” are described generically in [0015], [0024], [0035], and [0036] as part of the machine learning unit and based on a support vector machine (SVM), an adaptive boost (Adaboost), or a neural network (NN) architecture (but it not limited to these forms). It is identified as part of generic box component “machine learning unit” 105 in FIG 1 and “machine learning unit” 225 in FIG 2.
Per Applicant’s specification, the “signal pre-processing unit” is described generically in [0028], [0030], [0031], [0041], and [0042]. The signal pre-processing unit is used to pre-process the EEG signals, which could include down sampling and band pass filtering. At [0031] under a certain condition, “the signal pre-processing unit 102 might not be necessary for the auxiliary determination device 100 and might be removed.” It is identified as a generic box component “signal pre-processing unit” 102 in FIG 1 and “signal pre-processing unit” 222.
Per Applicant’s specification, the “frequency band screening unit” is described generically in [0028], [0032], [0033], [0041], and [0042]. It is “electrically connected” to the feature extraction unit and used to screen EEG signals transmitted from the EEG unit. If the “interpretation” is “performed for all frequency bands” of the EEG signals, then “the frequency band screening unit 103 might not be necessary and might be removed.” The frequency band screening unit uses mathematical transform methods like wavelets. It is identified as a generic box component “frequency band screening unit” 103 in FIG 1 and “frequency band screening unit” 223 in FIG 2.
Per Applicant’s specification, the “EEG signal measuring unit” is described in [0020], [0028] – [0032], and [0041] – [0043]. It is described as a non-specific dry or wet electrode EEG signal measuring device with 32, 64, or 128 electrodes, and “the invention is not limited by the type of the electroencephalography signal measuring device”. It is identified as a generic box component “electroencephalography signal measuring unit” 101 in FIG 1, “electroencephalography signal measuring unit” 211 in FIG 2, and “electroencephalography signal measuring unit” scalp electrode layout in Fig 3.
Accordingly, in light of Applicant’s specification, the claimed terms “feature extraction unit”, “processor”, “machine learning unit”, “at least one classifier”, “signal pre-processing unit”, “frequency band screening unit”, “EEG signal measuring unit”, “support vector machine”, “adaptive boost”, and ”neural network architecture” are reasonably construed as a generic computing and hardware devices. Like SAP America vs Investpic, LLC (Federal Circuit 2018), it is clear, from the claims themselves and the specification, that these limitations require no improved computer resources, just already available computers, with their already available basic functions, to use as tools in executing the claimed process.
Furthermore, Applicant’s specification does not describe any special programming or algorithms required for the “feature extraction unit”, “processor”, “machine learning unit”, “at least one classifier”, “signal pre-processing unit”, “frequency band screening unit”, “EEG signal measuring unit”, “support vector machine”, “adaptive boost”, and ”neural network architecture”. This lack of disclosure is acceptable under 35 U.S.C. §112(a) since this hardware performs non-specialized functions known by those of ordinary skill in the computer arts. By omitting any specialized programming or algorithms, Applicant's specification essentially admits that this hardware is conventional and performs well understood, routine and conventional activities in the computer industry or arts. In other words, Applicant’s specification demonstrates the well-understood, routine, conventional nature of the above-identified additional elements because it describes these additional elements in a manner that indicates that the additional elements are sufficiently well-known that the specification does not need to describe the particulars of such additional elements to satisfy 35 U.S.C. § 112(a) (see Berkheimer memo from April 19, 2018, (III)(A)(1) on page 3). Adding hardware that performs “‘well understood, routine, conventional activit[ies]’ previously known to the industry” will not make claims patent-eligible (TLI Communications).
The recitation of the above-identified additional limitations in Independent Claim 1 (and its dependent claims) amounts to mere instructions to implement the abstract idea on a computer. Simply using a computer or other machinery in its ordinary capacity for economic or other tasks (e.g., to receive, store, or transmit data) or simply adding a general-purpose computer or computer components after the fact to an abstract idea (e.g., a fundamental economic practice or mathematical equation) does not provide significantly more. See Affinity Labs v. DirecTV, 838 F.3d 1253, 1262, 120 USPQ2d 1201, 1207 (Fed. Cir. 2016) (cellular telephone); and TLI Communications LLC v. AV Auto, LLC, 823 F.3d 607, 613, 118 USPQ2d 1744, 1748 (Fed. Cir. 2016) (computer server and telephone unit). Moreover, implementing an abstract idea on a generic computer, does not add significantly more, similar to how the recitation of the computer in the claim in Alice amounted to mere instructions to apply the abstract idea of intermediated settlement on a generic computer.
A claim that purports to improve computer capabilities or to improve an existing technology may provide significantly more. McRO, Inc. v. Bandai Namco Games Am. Inc., 837 F.3d 1299, 1314-15, 120 USPQ2d 1091, 1101-02 (Fed. Cir. 2016); and Enfish, LLC v. Microsoft Corp., 822 F.3d 1327, 1335-36, 118 USPQ2d 1684, 1688-89 (Fed. Cir. 2016). However, a technical explanation as to how to implement the invention should be present in the specification for any assertion that the invention improves upon conventional functioning of a computer, or upon conventional technology or technological processes. That is, the disclosure must provide sufficient details such that one of ordinary skill in the art would recognize the claimed invention as providing an improvement. Here, Applicant’s specification does not include any discussion of how the claimed invention provides a technical improvement realized by these claims over the prior art or any explanation of a technical problem having an unconventional technical solution that is expressed in these claims. Instead, as in Affinity Labs of Tex. v. DirecTV, LLC 838 F.3d 1253, 1263-64, 120 USPQ2d 1201, 1207-08 (Fed. Cir. 2016), the specification fails to provide sufficient details regarding the manner in which the claimed invention accomplishes any technical improvement or solution.
For at least the above reasons, the apparatuses of Claims 1 – 6 and 9 - 10 are directed to applying an abstract idea as identified above on a general-purpose computer without (i) improving the performance of the computer itself, or (ii) providing a technical solution to a problem in a technical field. None of Claims 1 – 6 and 9 - 10 provides meaningful limitations to transform the abstract idea into a patent eligible application of the abstract idea such that these claims amount to significantly more than the abstract idea itself.
Taking the additional elements individually and in combination, the additional elements do not provide significantly more. Specifically, when viewed individually, the above-identified additional elements for Step 2A Prong 2 in Independent Claim 1 (and its dependent claims) do not add significantly more because they are simply an attempt to limit the abstract idea to a particular technological environment. That is, neither the general computer elements nor any other additional element adds meaningful limitations to the abstract idea because these additional elements represent insignificant extra-solution activity. When viewed as a combination, these above-identified additional elements simply instruct the practitioner to implement the claimed functions with well-understood, routine and conventional activity specified at a high level of generality in a particular technological environment. As such, there is no inventive concept sufficient to transform the claimed subject matter into a patent-eligible application. When viewed as whole, the above-identified additional elements do not provide meaningful limitations to transform the abstract idea into a patent eligible application of the abstract idea such that the claims amount to significantly more than the abstract idea itself. Thus, Claims 1 – 6 and 9 - 10 merely apply an abstract idea to a computer and do not (i) improve the performance of the computer itself (as in Bascom and Enfish), or (ii) provide a technical solution to a problem in a technical field (as in DDR).
Therefore, none of the Claims 1 – 6 and 9 - 10 amounts to significantly more than the abstract idea itself. Accordingly, Claims 1 – 6 and 9 - 10 are not patent eligible and rejected under 35 U.S.C. 101.
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.
Claims 1 – 2, 5 – 6, and 9 are rejected under 35 U.S.C. 103 as being unpatentable over Hasanzadeh, et. al., (“Prediction of rTMS treatment response in major depressive disorder using machine learning techniques and nonlinear features of EEG signal”), in view of Etkin et. al., (United States Patent Application Publication US 2020/0054888 A1), hereinafter Etkin 2020, further in view of Mumtaz et. al., (“Detrended Fluctuation Analysis for Major Depressive Disorder”).
Regarding Claim 1, Hasanzadeh discloses An auxiliary determination device for evaluating whether a transcranial magnetic stimulation is effective for a patient with depression (Title, [Abstract]), the auxiliary determination device comprising:
a feature extraction unit ([Page 134, “2.4. Feature extraction” section) “…feature extraction”)(Examiner notes that the feature extraction unit is the portion of the method as described that uses the electronic data from the EEG to extract features.) configured to perform a non-linear extraction process ([Page 134, Right Column, “2.4. Feature Extraction” Section] “After EEG data preparation, the next step in the prediction of treatment response to rTMS is extracting features… a total number of 21 features categorized into four groups including nonlinear…”) and a linear extraction process ([Page 134, Right Column, “2.4. Feature Extraction” Section] “After EEG data preparation… extracting features… a total number of 21 features categorized into four groups including…spectral”) on electroencephalography (EEG) signals of the patient ([Page 134, Left Column, “2.3. EEG recoding and pre-processing” section] “EEG was recorded…”) in an interpretation mode to generate a plurality of feature values ([Page 134, “2.4. Feature extraction” section] “a total number of 21 features…”)(Examiner notes that Merriam-Webster defines “mode” as “a possible, customary, or preferred way of doing something”. Therefore, a broadest reasonable interpretation of interpretation mode would include a manner of interpreting data, which is “analysis”), wherein the EEG signals are EEG signals of the patient after being driven by a cognitive operation ([Page 134, “2.2. Procedure” Section] “left DLPFC 10 Hz rTMS treatment…Resting EEG was recorded from the participants at…the end of the treatment…In every session, EEG was acquired for five minutes…”) or a difference between the EEG signals of the patient before and after being driven by the cognitive operation ([Page 134, “2.2. Procedure” Section] “Resting EEG was recorded from the participants at baseline and the end of the treatment.”), and the plurality of feature values comprise:
at least one non-linear feature value generated by the non-linear extraction process ([Page 134, Right Column, “2.4. Feature Extraction” Section] “…extracting features… a total number of 21 features categorized into four groups including nonlinear…”),
at least one linear feature value generated by the linear extraction process ([Page 134, Right Column, “2.4. Feature Extraction” Section] “After EEG data preparation… extracting features… a total number of 21 features categorized into four groups including…spectral”), the at least one linear feature value being selected from the group consisting of a band power of fast Fourier transform and a band power of Welch periodogram ([Page 134, Right Column, “2.4.1. Power spectrum features” features” Section] “…power of EEG signals was estimated…frequency bands by the Welch method..”); and
a machine learning unit electrically connected to the feature extraction unit ([Page 135, Left Column, “2.5. Classification” section] “…toolbox available at Matlab source codes exchange site”)(Examiner notes that the classification occurs using the overall MATLAB® script (which runs on a computer) that accepts the extracted features of the electric signal, therefore electrically connected) and comprising at least one classifier ([Page 135, “3.1. Classification analysis” section, Paragraph 1] “KNN classifier”) configured to classify the EEG signals into a category indicating an efficacy of the transcranial magnetic stimulation for the patient ([Page 136] “4. Discussion” Section] “depression level…based on our results…high beta power of EEG may indicates a lower probability of responding to treatment.”; [Page 139, “5. Conclusion” Section] “…prediction of rTMS treatment outcome by applying KNN classifier…discriminating responders and non-responders”), according to the plurality of feature values in the interpretation mode ([Page 135, “3.1. Classification analysis” section, Paragraph 1] “we applied feature sets to KNN classifier in the following forms:…the combination of measures in each group of nonlinear, spectral, bispectral and cordance measures, and the combination of all features.”);
Hasanzadeh does not specifically disclose a feature extraction unit comprising a processor and wherein the at least one classifier is based on a support vector machine, an adaptive boost, or a neural network architecture. Hasanzadeh does broadly describe using a Matlab script during the method for preprocessing steps, and Matlab is used on a computer with a processor. Further, Hasanzadeh discloses that the effectiveness of a treatment for major depressive disorder can be analyzed using classification methods including “linear support vector machines (LVSM), linear discriminant analysis (LDA), and neural networks” [Page 133, Left column, Top].
Etkin 2020 teaches a system and method for obtaining clean TMS-associated EEG data, using machine learning to determine TMS parameters for effective treatment of conditions like depression. Specifically for Claim 1, Etkin 2020 teaches a feature extraction unit comprising a processor ([0092] “transcranial magnetic stimulation electroencephalogram data processor 135A may further extract a second spectral feature”) and wherein the at least one classifier is based on a support vector machine, an adaptive boost, or a neural network architecture ([0056] “one or more machine learning models”; [0073] “machine learning model may be a classifier including… additional types of machine learning models (e.g., a neural network).”
Hasanzadeh is open to combine with a “processor” for feature extraction, as it does broadly describe using a Matlab script during the method for preprocessing steps (and Matlab is used on a computer with a processor). Etkin 2020 specifically teaches using a “processor 135A” for extracting spectral features. A person having ordinary skill in the art before the effective filing date of the claimed invention would recognize that using a processor would be beneficial for performing computational tasks on electric signals, as taught by Etkin 2020.
Regarding the neural network, Hasanzadeh provides one motivation to combine at [Page 133, Left column, Top] that that the effectiveness of a treatment for major depressive disorder can be analyzed using classification methods including “linear support vector machines (LVSM), linear discriminant analysis (LDA), and neural networks” [Page 133, Left column, Top]. A person having ordinary skill in the art before the effective filing date of the claimed invention would recognize that using neural network machine learning would be an algorithmic option as a classifier for analyzing EEG signal from TMS signaling in order to broadly determine the efficacy of TMS treatment from EEG features. Etkin 2020 provides an additional motivation to combine at [0041] “electroencephalogram data associated with transcranial magnetic stimulation (henceforth transcranial magnetic stimulation electroencephalogram data) tends to include a variety of artifacts that can skew subsequent analysis of the data” and [0073] “The…processor may perform artifact rejection by applying a machine learning model…The machine learning model may be a classifier including… additional types of machine learning models (e.g., a neural network)…Artefactual independent components may be removed from the transcranial magnetic stimulation electroencephalogram data used to perform real-time adjustments to the parameters of a transcranial magnetic stimulation procedure,” and [0004]. A person having ordinary skill in the art before the effective filing date of the claimed invention would recognize that neural network machine learning classifiers can be used to additionally analyze the EEG signal data from TMS signaling in order to obtain a clean signal from which efficacy of the TMS can be determined for depression, to perform real-time adjustments to the parameters of the TMS procedure (in accordance with Etkin 2020: [0041]) “electroencephalogram measurements of the brain's immediate responses to one or more transcranial magnetic stimuli may provide real-time guidance during a transcranial magnetic stimulation procedure.”) This data processing is consistent with the recitation of “at least one classifier” including a neural network architecture.
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to substitute the KNN classifier disclosed by Hasanzadeh with the “one or more machine learning models”, including a neural network as part of a classifier taught by Etkin 2020, creating a single device with a processor that can perform analysis of extracted values with a neural network-associated classifier for real-time adjustment of TMS procedure parameters for treatment of depression.
Etkin 2020 does not specifically teach the at least one non-linear feature value being a detrended fluctuation.
Mumtaz teaches a machine learning method to identify major depressive disorder patients from controls from EEG data feature analysis, wherein the features are extracted using de-trended fluctuation analysis (DFA) ([Abstract]). Specifically for Claim 1, Mumtaz teaches the at least one non-linear feature value being a detrended fluctuation ([Page 4162, Right Column, 1st – 3rd Full Paragraph] “EEG data are considered as time-series and analyzed with detrended fluctuation analysis (DFA) to compute long-range temporal correlations *LRTC)…”, “The feature extraction involves scaling exponents (self-similarity parameters) computed by DFA…”).
Hasanzadeh discloses a model that uses multiple types of extracted features to feed into a machine learning classifier, including non-linear features [Hasanzadeh: Page 135, “3.1. Classification analysis” section, Paragraph 1]. For a non-linear feature, Mumtaz provides a motivation to combine at [Abstract] “Based on the results, it was concluded that the DFA provided useful information to discriminate the MDD patients and with further validation can be employed in clinics for diagnosis of MDD…” and [Page 4165, Right Column, Top] “The features presented in the study have the capability to discriminate the MDD patients and healthy controls with statistical significance.” A person having ordinary skill in the art before the effective filing date of the claimed invention would recognize that using DFA for as a source of extracted features from EEG would be useful for use in a machine learning model for determining depression, as it has been shown to have success in identifying patients with major depressive disorder in such an application.
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to combine the multiple types of extracted features (including nonlinear features) extracted from EEG for a machine learning model disclosed by Hasanzadeh with the de-trended fluctuation analysis feature extraction from EEG for a machine learning model taught by Mumtaz in view of Etkin 2020, creating a single device that can perform analysis of multiple types of extracted values with a classifier to identify depression levels from EEG data for real-time adjustment of TMS procedure parameters for treatment of depression.
Regarding Claim 2, Hasanzadeh in view of Etkin 2020 and Mumtaz discloses as described above, The auxiliary determination device of claim 1. For the remainder of Claim 2, Hasanzadeh discloses a signal pre-processing unit ([Page 134,[2.3. EEG recording and pre-processing” section] “For preprocessing of recorded EEG data, EEGLAB Toolbox…used”) electrically connected to the feature extraction ([Page 134, “2.4. Feature extraction” Section] “After EEG data preparation, the next step in the prediction of treatment response to rTMS is extracting features.”)(Examiner notes that feature extraction portion of the method accepts and further processes electronic signals from the EEGLAB plug-in (that runs on a computer), therefore electrically connected) and configured to perform a signal pre-processing on the EEG signals in the interpretation mode ([Page 134,[2.3. EEG recording and pre-processing” section] “For preprocessing of recorded EEG data, EEGLAB Toolbox…used”; [Page 134, “2.4. Feature extraction” section]), wherein the signal pre-processing comprises at least one of a bandpass filtering ([Page 134,[2.3. EEG recording and pre-processing” section] “…a bandpass FIR filter…has been used”), a resampling, and an independent component analysis ([Page 134,[2.3. EEG recording and pre-processing” section] “ICA algorithm…”)
Regarding Claim 5, Hasanzadeh in view of Etkin 2020 and Mumtaz discloses as described above, The auxiliary determination device of claim 2. For the remainder of Claim 5, Hasanzadeh discloses an EEG signal measuring unit ([Page 134,[2.3. EEG recording and pre-processing” section] “EEG was recorded by a Mitsar-EEG 201…”) electrically connected to or communicated with the signal pre-processing unit for measuring the EEG signals ([Page 134,”2.3. EEG recording and pre-processing” section] “For preprocessing of recorded EEG data, EEGLAB Toolbox (Delorme and Makeig, 2004) have been used..”)(Examiner notes that the units must have been electrically connected to or communicated with such that the signal information from the measurements that were taken makes it to the computer using EEGLAB Toolbox for the preprocessing that occurred.)
Regarding Claim 6, Hasanzadeh in view of Etkin 2020 and Mumtaz discloses as described above, The auxiliary determination device of claim 2. For the remainder of Claim 6, Hasanzadeh discloses wherein the EEG signals are acquired through at least one electrode of Fp1, Fp2, F3, F4, F7, F8, and Fz ([Page 134, “2.3. EEG recording and pre-processing” section] “Channel location that was based on International 10–20 system includes Fp1, Fp2, F7, F3, Fz, F4, F8…”), of the EEG signal measuring unit ([Page 134,[2.3. EEG recording and pre-processing” section] “EEG was recorded by a Mitsar-EEG 201…”)
Regarding Claim 9, Hasanzadeh in view of Etkin 2020 and Mumtaz discloses as described above, The auxiliary determination device of claim 1. For the remainder of Claim 9, Hasanzadeh in view of Etkin 2020 does not disclose wherein the at least one classifier is a plurality of classifiers, and each of the plurality of classifiers is corresponding to a set of parameters of a transcranial magnetic stimulator.
Etkin 2020 teaches characterized in that, wherein the at least one classifier is a plurality of classifiers ([0046] “one or more machine learning models…classifier…perform artifact rejection”; [0073] “The machine learning model may be a classifier”) and each of the plurality of classifiers is corresponding to a set of parameters of a transcranial magnetic stimulator ([0073] “…perform artifact rejection”, “perform real-time adjustments to the parameters of the transcranial magnetic stimulation procedure”).
Hasanzadeh and Etkin 2020 both include systems and methods for obtaining TMS-associated EEG data and analyzing the data using machine learning. Etkin 2020 then uses that analysis of the response data to modify parameters of the TMS treatment. Etkin 2020 gives motivation to combine to use “one or more machine learning model” including classifiers in particular with [0073] that the classifiers can be used to “perform artifact rejection”, and that it would be used “to perform real-time adjustments to the parameters of a transcranial magnetic stimulation procedure.” A person having ordinary skill in the art before the effective filing data of the claimed invention would recognize that a classifier is a common example of a type of machine learning model, and it would be useful for applying the EEG data analysis calculations to make real-time adjustments of TMS treatment parameters.
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to combine the single KNN classifier for analysis of TMS-EEG data disclosed in Hasanzadeh with the “one or more classifiers” machine learning model for adjusting TMS parameters taught by Etkin 2020, creating a single device for that uses analysis from a plurality of classifiers for real-time adjustment of TMS procedure parameters.
Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Hasanzadeh in view of Etkin 2020 and Mumtaz, further in view of Doidge et. al., (WO 2006/122398 A1).
Regarding Claim 3, Hasanzadeh in view of Etkin 2020 and Mumtaz discloses as described above, The auxiliary determination device of claim 2. For the remainder of Claim 3, Hasanzadeh discloses further comprising:
a frequency band screening unit ([Page 134,”2.3. EEG recording and pre-processing” and “2.4. Feature extraction” sections]) electrically connected to the feature extraction unit and the signal pre-processing unit ([Page 134,[2.3. EEG recording and pre-processing” section] “For preprocessing of recorded EEG data, EEGLAB Toolbox…used”)(Examiner notes that feature extraction portion of the method accepts and further processes electronic signals from the EEGLAB plug-in (that runs on a computer), for particular frequency bands, therefore electrically connected) to acquire the EEG signals within particular frequency bands ([Page 134, “2.3. EEG recording and pre-processing” section] “bandpass FIR filter…ICA algorithm…power spectrum of ICs”; [Page 134, “2.4.2. Power Spectrum features” section] “EEG signals was estimated in delta (1–4 Hz), theta (4–8 Hz), alpha (8–12 Hz) and beta (12–30 Hz) frequency bands”) for subsequent feature extraction and signal interpretation ([Page 134, “2.4.2. Power Spectrum features” section] “For every channel…average power of frequencies…was computed…four feature sets”).
Hasanzadeh does not specifically disclose is configured to screen frequency bands of the EEG signals. Hasanzadeh broadly discloses in [Page 134, “2.4.2. Power spectrum features” section] that the EEG signals are measured within different frequency ranges for alpha, beta, delta, and theta bands. Hasanzadeh does not specify how the bands are filtered into the aforementioned frequency ranges, other than ICA algorithm processing.
Doidge teaches a method and apparatus for processing EEG signals obtained from a subject’s scalp, including separating the signal into frequency bands of interest using filtering. Specifically for Claim 3, Doidge teaches a frequency band screening unit ([00052] “filters”) is configured to screen frequency bands of the EEG signals for subsequent feature extraction and signal interpretation ([00052] “…filters may include…low, high, band-pass…”, “..an example of this would be a band-pass filter between 8 and 12 Hz”; [00073] “original EEGs have been filtered with multiple frequency parameters in near-real time; the top left image has been filtered between 1-3 Hz, top right 4-7 Hz, bottom left 8-12 Hz, bottom right 12-16 Hz.”).
Doidge provides a motivation to combine at [00052] with “…the signal that is output by the amplifier/recorder (EEG) is unusable in its raw state…data may be subjected to near real-time component and feature isolation and artifact (noise removal)” A person having ordinary skill in the art before the effective filing data of the claimed invention would recognize that in order to make the EEG data usable, particularly useable to investigate particular well-known theta (5-8 Hz), alpha (8-12 Hz), beta (12-30 Hz)”), or gamma (30-60 Hz)) waves, a band pass filter could be used to filter the raw data. It would have been predictable to specifically use a low, high, or band-pass filter as taught by Doidge for this purpose, as this is a well-known filtering method in the art for screening frequency bands of EEG signals.
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to combine the broadly disclosed measurement and analysis of EEG data at different frequency bands of Hasanzadeh with the specific low, high, and band-pass filtering taught by Doidge, for a single device to obtain useful EEG signals separated by bands of interest for further processing and study.
Claim 4 is rejected under 35 U.S.C. 103 as being unpatentable over Hasanzadeh in view of Etkin 2020 and Mumtaz, further in view of Doidge, further in view of Etkin et. al., (WO 2017/189757), hereinafter Etkin 2017.
Regarding Claim 4, Hasanzadeh in view of Etkin 2020 and Mumtaz, further in view of Doidge discloses as described above, The auxiliary determination device of claim 3. For the remainder of Claim 4, Hasanzadeh discloses wherein the particular frequency bands are α ([Page 134, “2.4.2. Power spectrum features” Section] “alpha (8 – 12 Hz)”), β ([Page 134, “2.4.2. Power spectrum features” Section] “beta (12 – 30 Hz)”), Θ ([Page 134, “2.4.2. Power spectrum features” Section] “theta (5 - 8 Hz)”) and δ (delta)) frequency bands ([Page 134, “2.4.2. Power spectrum features” Section] “delta (1 – 4 Hz) frequency bands”).
Hasanzadeh does not disclose y (gamma) frequency bands.
Etkin 2017 teaches systems and methods for controlling TMS therapy parameters using analysis of EEG signals measured from a subject in different bands. Specifically for claim 4, Etkin 2017 teaches y (gamma) frequency bands ([0070] “gamma (30 – 60 Hz),
Etkin 2017 provides a motivation to combine at ([0094] “Baseline gamma power correlated with clinical outcome in the left angular gyms, left visual, as well as bilateral ventromedial prefrontal cortices, whereas the strength of early gamma modulation correlated with clinical outcome in left visual as well as right ventromedial prefrontal cortex..”) A person having ordinary skill in the art before the effective filing data of the claimed invention would recognize that separating the EEG signal into another common bandwidth, gamma, would allow for additional diagnostic capabilities to determine if rTMS induced a significant clinical outcome in a particular portion of the brain that includes the left visual and right ventromedial prefrontal cortex. It would have been predictable to use the filtering taught by Etkin 2017 to also separate gamma frequency band data in any EEG signal obtaining device and processing method, as it would continue to operate with the function of separating an EEG signal into commonly studied frequency bands.
Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to combine the “alpha (8 – 12 Hz)”, “beta (12 – 30 Hz)”), “delta (5 – 8 Hz), and “theta (5 - 8 Hz)” bands from the EEG signal disclosed in Hasanzadeh with the “gamma” (30 - 60 Hz) frequency band taught by Etkin 2017, creating a single apparatus with analysis capability to increase the diagnostic versatility for the EEG signal analysis device.
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Hasanzadeh in view of Etkin 2020 and Mumtaz, further in view of Etkin 2017.
Regarding Claim 10, Hasanzadeh in view of Etkin 2020 and Mumtaz, discloses as described above, The auxiliary determination device of claim 9. For the remainder of Claim 10, Hasanzadeh does not disclose wherein the parameters of the transcranial magnetic stimulator comprise mode, frequency, burst period, burst duration, rest interval, signal strength, and pulse number of each burst.
Etkin 2020 teaches wherein the parameters of the transcranial magnetic stimulator comprise mode ([0044] “… configured to administer one or more types of transcranial magnetic stimulation …single-pulse transcranial magnetic stimulation (spTMS), paired-pulse transcranial magnetic stimulation (ppTMS),
repetitive transcranial magnetic stimulation (rTMS)”), frequency ([0103] “real-time adjustments to one or more transcranial magnetic stimulation parameters…administered by the transcranial magnetic stimulation device 110… transcranial magnetic stimulation parameters including…stimulation frequency…”), burst duration ([0103] “…stimulation duration”), rest interval ([0103] “…time interval between stimuli…”) signal strength ([0103] “…stimulation magnitude…”), and pulse number of each burst ([0050] “a single, a pair, and/or a train of transcranial magnetic stimuli (e.g., magnetic pulses) at a time.”)
The motivation for Claim 10 to combine Hasanzadeh is the similar as that described in more detail in Claim 9. In summary, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to combine the single KNN classifier for analysis of TMS-EEG data disclosed in Hasanzadeh with the “one or more classifiers” machine learning model for adjusting particular TMS parameters taught by Etkin 2020, creating a single device for that uses analysis from a plurality of classifiers for real-time adjustment of TMS procedure parameters.
Etkin 2020 does not particularly teach burst period. Etkin does broadly disclose that the “stimulation duration” and “time interval between stimuli” can be adjusted by the system ([0103], and that burst-type stimulation can be delivered [0044], hence broadly teaching a burst period.
For a specific teaching of burst period, Etkin 2017 teaches parameters of the transcranial magnetic stimulator comprise mode ([0042] “stimulation types”, “repetitive TMS (rTMS), single pulse TMS (spTMS), or paired pulse TMS (ppTMS).”), frequency (Fig 1 B, “10 Hz”; [0007]), burst period (Fig 1 B, including bursts occurring over a period of 6 minutes, 480 pules, at top; [0007]), burst duration (Fig 1 B, “4 second stimulation period in a burst; [0007]), rest interval (Fig 1 B, “26 s REST”; [0007]), signal strength ([0073] “intensity (e.g. a power) of non-invasive brain stimulation (e.g. TMS)), and pulse number of each burst (Fig 1 B, “40 pulses” in a burst before the rest period; [0007])
Hasanzadeh in view of Etkin 2020 and Etkin 2017 each teach particular TMS parameters: the Etkin 2020 portion (as described above) with “stimulation duration, stimulation frequency, stimulation magnitude, stimulation area, time interval between stimuli, and/or the like”, and Etkin 2017 with stimulation types, frequency, burst period, burst duration, rest interval, signal strength, and pulse number of each burst. Etkin 2017 provides a more specific teaching of burst period, which a person with ordinary skill in the art would recognize as a helpful parameter for controlling TMS parameters for burst-type TMS (such as repetitive TMS, rTMS).
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to combine the real-time adjustment of TMS parameters and rTMS disclosed in Hasanzadeh in view of Etkin 2020 with the particularly-specified burst period adjustment taught by Etkin 2017, creating a single device for that uses analysis from a plurality of classifiers for real-time adjustment of rTMS procedure burst period parameters.
Response to Arguments
Applicant's arguments filed 19 May 2026 have been fully considered but they are not persuasive.
Regarding 35 U.S.C. 112 Rejections:
Based on Applicant’s arguments at [Page 4, “Rejections under 35 USC 112” Section, Paragraphs 1 – 4] that the processor is part of the platform server disclosed in Applicant’s specification at [0041] as would be understood by a person with ordinary skill in the art, the previously-applied rejections under 112(a) for “processor” have been withdrawn.
Applicant argues [Page 4, Bottom] – [Page 6, 1st Full Paragraph] that the machine learning unit takes input training data and utilizes classifiers based on supervised learning techniques based on known algorithms, such that it cannot be characterized as an undefined black box. Based on the recitation in the claims, it is recited that this “machine learning unit” is “electrically connected to the feature extraction unit”. Such that the clarification in the argument indicates that utilizing classifiers based on supervised learning techniques is known, it remains undisclosed how these elements are particularly “electrically connected” to each other if they are purely algorithmic elements. As described above in the maintained 112(a) rejection, it is not enough that a skilled artisan could devise a way to accomplish the function because this is not relevant to the issue of whether the inventor has shown possession of the claimed invention. See MPEP 2161.01(I). Therefore, adequate disclosure is needed. Further, based on the “electrically connected” recitation, it remains unclear what parts of the “machine learning unit” and the “feature extraction units” are physically connected by this electricity. The argument is not persuasive.
Regarding 35 U.S.C. 101 Rejections:
Applicant argues at [Page 3, “Claim Rejection 35 U.S.C. 101” Section], Paragraphs 1 – 3] that claims recite significantly more than an abstract idea under 35 U.S.C. 101 because the machine learning unit in the claim is implemented through an algorithmic training mode, where the machine learning unit defines the training mode and logic, and trains classifiers so that the machine learning unit predicting TMS efficacy is based on combined linear and non-linear EEG features. For the abstract idea of performing a non-linear extraction process and performing a linear extraction process using mathematical computation, the concept of performing a non-linear extraction process and linear extraction process on EEG data recites broadly an abstract idea that can be accomplished by a human interpreting, (or as described in the 35 U.S.C. 101 analysis above, observing and judging) the EEG data to decide which feature values should be the plurality of feature values from the EEG data. The information about the signal is mathematically manipulated in analysis to learn information about the signal. Per the 35 U.S.C. 101 analysis above, the non-linear and linear feature vales themselves are extra-solution data gathering activity to be used in the subsequently-recited abstract idea. The limitation of “to classify the EEG signals into a category indicating an efficacy of the transcranial magnetic stimulation for the patient according to the plurality of feature values in the interpretation mode” is a recited judicial exception abstract idea, as it recites observation and judgement to classify or sort the EEG signals into categories indicating an efficacy of tRMS based on their observation and judgement. The claims recite a series of limitations that encompass an abstract idea of manipulating variables obtained from electronic components used in a usual way, and that variable manipulation can be accomplished with the aid of time, equations, and paper.
The classifiers as broadly recited are used in a well-understood, routine, and conventional way (to classify data that has been fed into them). The processor is also recited as a well-understood, routine, and conventional component performing a routine task of processing data. As for computational steps, From MPEP 2106.05(a): It is important to note, the judicial exception alone cannot provide the improvement. The improvement can be provided by one or more additional elements. See the discussion of Diamond v. Diehr, 450 U.S. 175, 187 and 191-92, 209 USPQ 1, 10 (1981)) in subsection II, below. In addition, the improvement can be provided by the additional element(s) in combination with the recited judicial exception. See MPEP § 2106.04(d) (discussing Finjan, Inc. v. Blue Coat Sys., Inc., 879 F.3d 1299, 1303-04, 125 USPQ2d 1282, 1285-87 (Fed. Cir. 2018)). The argument is not persuasive.
Regarding 35 U.S.C. 103 Rejections:
Applicant argues at [Page 6, “Rejections under 35 USC 103” Section] – [Page 7, 4th Full Paragraph] and [Page 7, 6th Full Paragraph] that Hasanzadeh does not disclose the feature of detrended fluctuation analysis (DFA) of that DFA is used specifically for long-range correlation-based TMS adaptation. There is nothing particularly recited in the claim that the DFA is used specifically for long-range correlation-based TMS adaptation. Based amendments to the claim, a newly-added reference of Mumtaz is combined with Hasanzadeh in view of Etkin 2020 to teach the non-linear extraction by DFA. In response to applicant's arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986). The argument is not persuasive.
Applicant argues at [Page 7, 5th Full Paragraph] that one of ordinary skill in the art would not be motivated to make the combination because there is not motivation to substitute the predictive classifier of Hasanzadeh with the noise-filtering model of Etkin 2020. As recited, the machine learning unit comprises ”at least one classifier”, which includes a classifier of a neural network architecture. The inclusion of the neural network as taught by Etkin 2020 allows for the further processing of the EEG-associated data to classify the broad “efficacy” of the treatment by ensuring that the data being used to draw the conclusion is clean. As described above, a person having ordinary skill in the art would be motivated to combine the disclosure of Hasanzadeh and Etkin 2020 in order to obtain clean EEG data that is properly classified according to depression-associated features in the EEG data so that (Etkin 2020: [0041]) “electroencephalogram measurements of the brain's immediate responses to one or more transcranial magnetic stimuli may provide real-time guidance during a transcranial magnetic stimulation procedure.” The argument is not persuasive.
Applicant argues at [Page 7, 6th Full Paragraph] – [[Page 8, top] that the combination of Hasanzadeh with Etkin 2020 does not allow the system to analyze data variations across different time scales. There appears to be nothing particularly recited in the claim that indicates that the system must analyze data variations across different time scales. As recited, the machine learning unit classified EEG signals into a category according to the plurality of feature values, which include at least one non-linear feature and one linear features. This is disclosed by the combination of Hasanzadeh with Etkin 2020, as described above in the 35 U.S.C. 103 rejection for Claim 1 (including Hasanzadeh’s disclosed ([Page 135, “3.1. Classification analysis” section, Paragraph 1] “we applied feature sets to KNN classifier in the following forms:…the combination of measures in each group of nonlinear, spectral, bispectral and cordance measures, and the combination of all features.”). The argument is not persuasive.
Applicant summarily argues at [Page 8, 1st – 3rd full paragraph] that claim 1 should be patentable over Hasanzadeh and Etkin 2020, and that the dependent claims set forth additional limitations not found in the prior art and are also allowable based at least on their dependency from claim 1. There is no particular feature from the dependent claims that is argued as not being found in the prior art. This part of the argument amounts to a general allegation that the claims define a patentable invention without specifically pointing out how the language of the claims patentably distinguishes them from the references. Regarding claim 1, based on the 35 U.S.C 103 rejection herein and the discussion of arguments above, Claim 1 is not patentable under 35 U.S.C. 103, as it is disclosed by Hasanzadeh in view of Etkin 2020 and Mumzaz. The argument is not persuasive.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MELISSA J MONTGOMERY whose telephone number is (571)272-2305. The examiner can normally be reached Monday - Friday 7:30 - 5:00 ET.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Alexander Valvis can be reached at (571) 272 - 4233. 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.
/MELISSA JO MONTGOMERY/ Examiner, Art Unit 3791
/JUSTIN XU/Examiner, Art Unit 3791
Prosecution Insights