DETAILED ACTION
This action is pursuant to claims filed on 06/09/2025. Claims 1-3, 5-7, 11, 16, and 25-41 are pending. A first action on the merits of claims 1-3, 5-7, 11, 16, and 25-41 is as follows.
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 .
Drawings
The drawings are objected to as failing to comply with 37 CFR 1.84(p)(4) because the following reference characters has been used to designate different components:
Reference character “110” has been used to designate both “data module” in Figure 1 and “EEG signal acquisition” in Figure 2
Reference character “512” has been used to designate both “memoryless classifier” in multiple figures and the specification and “feature extraction” in Figure 6
Reference character “604” has been used to designate both “encoder” in multiple figures and the specification and “Conv. Net with Attention Layers” in Figure 7
Reference character “908” has been used to designate both “segmentation” in Figure 9 and the specification and “spectro-temporal features” in Figure 10
Reference character “1106” has been used to designate both “second feature-based model” in the specification and “stack features over time segments” in Figure 11
Reference character “1206” has been used to designate both “primary deep learning model” in the specification and “primary model output” in Figure 12
Reference character “1208” has been used to designate both “average probability” in the specification and “top 2 channels” in Figure 12
Reference character “1210” has been used to designate both “average probability” in the specification and “top 2 channels” in Figure 12
Reference character “1202” has been used to designate both “average probability” in the specification and “top 2 channels” in Figure 12
The drawings are objected to as failing to comply with 37 CFR 1.84(p)(5) because they do not include the following reference sign(s) mentioned in the description:
Reference character “1008” in paragraph [0127] does not appear in the figures
Reference character “1103” in paragraph [0146] does not appear in the figures
Reference character “1105” in paragraph [0146] does not appear in the figures
Reference character “1111” in paragraph [0146] does not appear in the figures
Reference character “1118” in paragraph [0146] does not appear in the figures
Reference character “1122” in paragraph [0146] does not appear in the figures
Reference character “1130” in paragraph [146] does not appear in the figures
The drawings are objected to as failing to comply with 37 CFR 1.84(p)(5) because they include the following reference character(s) not mentioned in the description:
Reference character “100” in Figure 1 does not appear in the specification
Reference character “240” in Figure 2 does not appear in the specification
Corrected drawing sheets in compliance with 37 CFR 1.121(d), or amendment to the specification to add the reference character(s) in the description in compliance with 37 CFR 1.121(b) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Claim Objections
Claims 1, 3, 11, and 25 are objected to because of the following informalities:
In claim 1, line 1, “EEG signals” should read “electroencephalography (EEG) signals”
In claim 1, lines 2-3, “electroencephalography (EEG) signals” should read “EEG signals”
In claim 3, line 1, “the one or more processors configured to” should read “the one or more processors further configured to”
In claim 11, lines 2, “electroencephalography (EEG) signals” should read “EEG signals”
In claim 25, line 2, “electroencephalography (EEG) signals” should read “EEG signals”
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-3, 5-7, 11, 16, and 25-41 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.
Regarding claim 1, the claim recites the limitation “generate a correction factor based on the first probability value” in line 11. It is unclear if this limitation requires a correction factor to be generated for each probability value, since multiple probability values are generated, or if only one correction factor is required to be generated. The broad and indefinite scope of the limitation fails to inform a person of ordinary skill in the art with reasonable certainty of the metes and bounds of the claimed invention, therefore the claim is rendered indefinite. For purposes of examination, it is being interpreted as only requiring one correction factor to be generated based off of one of the first probability values. Claims 2-3, 5-7, 11, 16, and 25-40 are also rejected due to their dependence on claim 1.
Regarding claim 16, the claim recites the limitation “about 1 second to about 10 minutes” in lines 1-2. It is unclear what constitutes as “about” these values, and how far away from these values will still constitute as teaching on this limitation. The broad and indefinite scope of the limitation fails to inform a person of ordinary skill in the art with reasonable certainty of the metes and bounds of the claimed invention, therefore the claim is rendered indefinite. For purposes of examination, any value that is plus or minus 5 will teach on this limitation.
Regarding claim 29, the claim recites the limitation “a temporal segment” in line 2. It is unclear if this limitation is meant to refer to the temporal segments from claim 1, line 5, or a different temporal segment. If it is meant to refer to the temporal segments from claim 1, it needs to refer back to it. If it is meant to refer to a different temporal segment, it needs to be distinguished from the temporal segment from claim 1. For purposes of examination, it is being interpreted as referring to the temporal segments from claim 1.
Regarding claim 30, the claim recites the limitation “a plurality of temporal segments” in lines 3-4. It is unclear if this limitation is meant to refer to the plurality of temporal segments from claim 1, line 5, or a different plurality of temporal segments from claim 1. If it is meant to refer to the plurality of temporal segments from claim 1, it needs to refer back to it. If it is meant to refer to a different plurality of temporal segments, it needs to be distinguished from the plurality of temporal segments from claim 1. For purposes of examination, it is being interpreted as referring to the plurality of temporal segments from claim 1. Claims 31-32 are also rejected due to their dependence on claim 30.
Regarding claim 32, the claim recites the limitation “about 3 to about 30 temporal segments” in line 2. It is unclear what constitutes as “about” these values, and how far away from these values will still constitute as teaching on this limitation. The broad and indefinite scope of the limitation fails to inform a person of ordinary skill in the art with reasonable certainty of the metes and bounds of the claimed invention, therefore the claim is rendered indefinite. For purposes of examination, any value that is plus or minus 5 will teach on this limitation.
Regarding claim 34, the claim recites the limitation “correction factors” in line 3. It is unclear if this limitation is meant to refer to the correction factor from claim 1, line 11, or different correction factors. If it is meant to refer to the correction factor from claim 1, it needs to refer back to it. If it is meant to refer to different correction factors, it needs to be distinguished from the correction factor from claim 1. For purposes of examination, it is being interpreted as referring to the correction factor from claim 1. Claims 35-40 are also rejected due to their dependence on claim 34.
Further regarding claim 34, the claim recites the limitation “each temporal segment” in lines 3-4. It is unclear if this limitation is meant to refer to the plurality of temporal segments from claim 1, line 5, or different temporal segments. If it is meant to refer to the temporal segments from claim 1, it needs to refer back to it. If it is meant to refer to different temporal segments, it needs to be distinguished from the temporal segments from claim 1. For purposes of examination, it is being interpreted as referring to the plurality of temporal segments from claim 1. Claims 35-40 are also rejected due to their dependence on claim 34.
Regarding claim 38, the claim recites the limitation “about 5 minutes” in lines 1-2 and “about 90%” in line 2. It is unclear what constitutes as “about” these values, and how far away from these values will still constitute as teaching on this limitation. The broad and indefinite scope of the limitation fails to inform a person of ordinary skill in the art with reasonable certainty of the metes and bounds of the claimed invention, therefore the claim is rendered indefinite. For purposes of examination, any value that is plus or minus 5 will teach on this limitation.
Further regarding claim 38, the claim recites the limitation “the seizure burden” in line 2. There is insufficient antecedent basis for this limitation in the claim. Additionally, it is unclear if this limitation is meant to read as “a seizure burden”, or if the claim is meant to depend on claim 35, which introduces the seizure burden. The broad and indefinite scope of the limitation fails to inform a person of ordinary skill in the art with reasonable certainty of the metes and bounds of the claimed invention, therefore the claim is rendered indefinite. For purposes of examination, it is being interpreted as reading as “a seizure burden”.
Regarding claim 40, the claim recites the limitation “about 10 minutes” in lines 1-2, “about 60 minutes” in line 2, “about 90%” in lines 2-3, and “about 20%” in line 3. It is unclear what constitutes as “about” these values, and how far away from these values will still constitute as teaching on this limitation. The broad and indefinite scope of the limitation fails to inform a person of ordinary skill in the art with reasonable certainty of the metes and bounds of the claimed invention, therefore the claim is rendered indefinite. For purposes of examination, any value that is plus or minus 5 will teach on this limitation.
Regarding claim 41, the claim recites the limitation “generating a correction factor based on the first probability value” in lines 9-10. It is unclear if this limitation requires a correction factor to be generated for each probability value, since multiple probability values are generated, or if only one correction factor is required to be generated. The broad and indefinite scope of the limitation fails to inform a person of ordinary skill in the art with reasonable certainty of the metes and bounds of the claimed invention, therefore the claim is rendered indefinite. For purposes of examination, it is being interpreted as only requiring one correction factor to be generated based off of one of the first probability values.
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 1-3, 5-7, 11, 16, and 25-41 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. Under the two-step 101 analysis, the claims fail to satisfy the criteria for subject matter eligibility.
Regarding Step 1, claims 1-3, 5-7, 11, 16, and 25-41 are all within at least one of the four statutory categories.
Claim 1 and its dependent claims disclose a system (machine).
Claim 41 discloses a method (process).
Regarding Step 2A, Prong One, the independent claims 1 and 41 recite an abstract idea. In particular, the claims generally recite the following:
receive data comprising a plurality of electroencephalography (EEG) signals recorded during a time window from a subject;
process the data by dividing each of the plurality of EEG signals into a plurality of temporal segments;
extract a plurality of features from each of the plurality of temporal segments;
generate a first probability value for each of the temporal segments derived from the plurality of extracted features;
generate a correction factor based on the first probability value;
transform the data into a plurality of vectors;
determine a second probability value based on the plurality of vectors;
determine one or more types of seizure activity based on the second probability value and the correction factor (claim 1);
determining a seizure classification for each of the temporal segments based on the second probability value and the correction factor (claim 41).
These elements recites in claims 1 and 41 are drawn to abstract ideas since they involve a mental process that can be practically performed in the human mine including observation, evaluation, judgement, and opinion and using pen and paper.
Receiving data comprising a plurality of electroencephalography (EEG) signals recorded during a time window from a subject is drawn to an abstract idea since it is a mental process that can be practically performed in the human mind, or with the aid of pen and paper. A person of ordinary skill in the art could reasonably receive the data verbally or recorded on a piece of paper. There is nothing to suggest an undue level of complexity in receiving data comprising a plurality of EEG signals recorded during a time window from a subject.
Processing the data by dividing each of the plurality of EEG signals into a plurality of temporal segments is drawn to an abstract idea since it is a mental process that can be practically performed in the human mind, or with the aid of pen and paper. A person of ordinary skill in the art could reasonably take the EEG signals and divide them into temporal segments mentally, or with the aid of pen and paper. These techniques are based on calculations, evaluation, and judgement, which can be performed by hand. The mathematics of dividing EEG signals into temporal segments are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas. There is nothing to suggest an undue level of complexity in processing the data by dividing the EEG signals into a plurality of temporal segments.
Extracting a plurality of features from each of the plurality of temporal segments is drawn to an abstract idea since it is a mental process that can be practically performed in the human mind or with the aid of pen and paper. A person of ordinary skill in the art could reasonably extract a plurality of features from the temporal segments mentally, or with the aid of pen and paper. These techniques are based on calculations, algorithms, mathematical principles, and evaluation, which can be performed by hand. The mathematics of extracting features from temporal segments are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas. There is nothing to suggest an undue level of complexity in extracting a plurality of features from each of the plurality of temporal segments.
Generating a first probability value for each of the temporal segments derived from the plurality of extracted features is drawn to an abstract idea since it is a mental process that can be practically performed in the human mind or with the aid of pen and paper. A person of ordinary skill in the art could reasonably generate a probability value for each segment using basic probability calculations mentally or with the aid of pen and paper. These techniques are based on calculations, algorithms, mathematical principles, and evaluation, which can be performed by hand. The mathematics of generating probability values are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas. There is nothing to suggest an undue level of complexity in generating a first probability value for each of the temporal segments derived from the plurality of extracted features.
Generating a correction factor based on the first probability value is drawn to an abstract idea since it is a mental process that can be practically performed in the human mind or with the aid of pen and paper. A person of ordinary skill could reasonably generate a correction factor based on the probability value mentally or with the aid of pen and paper. These techniques are based on calculations, algorithms, mathematical principles, and evaluation, which can be performed by hand. The mathematics generating a correction factor not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas. There is nothing to suggest an undue level of complexity in generating a correction factor based on the first probability value.
Transforming the data into a plurality of vectors is drawn to an abstract idea since it is a mental process that can be practically performed in the human mind or with the aid of pen and paper. A person of ordinary skill could reasonably transform he data into a plurality of vectors mentally or with the aid of pen and paper. These techniques are based on calculations, algorithms, mathematical principles, and evaluation, which can be performed by hand. The mathematics of transforming data into a plurality of vectors are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas. There is nothing to suggest an undue level of complexity in transforming the data into a plurality of vectors.
Determining a second probability value based on the plurality of vectors is drawn to an abstract idea since it is a mental process that can be practically performed in the human mind or with the aid of pen and paper. A person of ordinary skill in the art could reasonably generate a probability value for the plurality of vectors using basic probability calculations mentally or with the aid of pen and paper. These techniques are based on calculations, algorithms, mathematical principles, and evaluation, which can be performed by hand. The mathematics of determining a probability value are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas. There is nothing to suggest an undue level of complexity in determining a second probability value based on the plurality of vectors.
Determining one or more types of seizure activity based on the second probability value and the correction factor is drawn to an abstract idea since it is a mental process that can be practically performed in the human mind, or with the aid of pen and paper. A person of ordinary skill in the art could reasonably determine one or more types of seizure activity mentally, or with the aid of pen and paper. These techniques are based on calculations, evaluation, and judgement, which can be performed by hand. The mathematics of determining types of seizure activity are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas. There is nothing to suggest an undue level of complexity in determining one or more types of seizure activity based on the second probability value and the correction factor.
Determining a seizure classification for each of the temporal segments based on the second probability value and the correction factor is drawn to an abstract idea since it is a mental process that can be practically performed in the human mind, or with the aid of pen and paper. A person of ordinary skill in the art could reasonably determine a seizure classification mentally, or with the aid of pen and paper. These techniques are based on calculations, evaluation, and judgement, which can be performed by hand. The mathematics of determining seizure classification are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas. There is nothing to suggest an undue level of complexity in determining a seizure classification for each of the temporal segments based on the second probability value and the correction factor.
Regarding Step 2A, Prong Two, claims 1 and 41 do not recite additional elements that integrate the exception into a practical application. Therefore, the claims are directed to the abstract idea. The additional elements merely:
Recite the words “apply it” or an equivalent with the judicial exception, or include instructions to implement the abstract idea on a computer, or merely use the computer as a tool to perform the abstract idea (e.g., “a data module” (claim 1), “a seizure detection module” (claims 1 and 41), “a feature-based classifier” (claim 1), “an encoder” (claim 1), “a decoder” (claim 1), and “one or more processors” (claim 1)), and
Add insignificant extra-solution activity (the pre-solution activity of: using generic data-gathering components (e.g., “receiving EEG data from a plurality of electrodes” (claim 41))).
As a whole, the additional elements merely serve to gather information to be used by the abstract idea, while generically implementing it on a computer. There is no practical application because the abstract idea is not applied, relied on, or used in a meaningful way. The processing performed remains in the abstract realm, i.e., the result is not used for a treatment. No improvement to the technology is evident. Therefore, the additional elements, alone or in combination, do not integrate the abstract idea into a practical application.
Regarding Step 2B, claims 1 and 41 do not include additional elements, alone or in combination, that are sufficient to amount to significantly more than the judicial exception (i.e., an inventive concept) for the same reasons as described above.
Claims 1 and 41 do not recite additional elements that amount to significantly more than the judicial exception itself. In particular, “receiving EEG data from a plurality of electrodes” does not qualify as significantly more because this limitation merely describes a generic data gathering step.
The data gathering step of “receiving EEG data from a plurality of electrodes” is nothing more than a generic EEG device. Such devices are evidenced by:
US Patent Application No. 20190159735 (Rundo) discloses conventional means of EEG measurements including using a plurality of electrodes (Rundo, [0154]);
US Patent Application No. 20160150992 (Lee) discloses conventional EEG measurement devices including a plurality of electrodes (Lee, [0007]);
US Patent Application No. 20090312664 (Rodriguez) discloses conventional EEG monitoring approaches using a plurality of electrodes (Rodriguez, [0007]);
US Patent Application No. 20090134887 (Hu) discloses conventional electroencephalograms being measured by a plurality of electrodes (Hu, [0002]).
Further, the elements of “a data module” (claim 1), “a seizure detection module” (claims 1 and 41), “a feature-based classifier” (claim 1), “an encoder” (claim 1), “a decoder” (claim 1), and “one or more processors” (claim 1) do not qualify as significantly more because this limitation is simply appending well-understood, routine and conventional activities previously known in the industry, specified at a high level of generality, to the judicial exception, e.g., a claim to an abstract idea requiring no more than a generic computer to perform generic computer functions that are well-understood, routine and conventional activities previously known in the industry (see Electric Power Group, 830 F.3d 1350 (Fed. Cir. 2016); Alice Corp. v. CLS Bank Int’l, 110 USPQ2d 1976 (2014)) and/or a claim to an abstract idea requiring no more than being stored on a computer readable medium which is a well-understood, routine and conventional activity previously known in the industry (see Electric Power Group, 830 F.3d 1350 (Fed. Cir. 2016); Alice Corp. v. CLS Bank Int’l, 110 USPQ2d 1976 (2014); SAP Am. v. InvestPic, 890 F.3d 1016 (Fed. Circ. 2018)).
In view of the above, the additional elements individually do not integrate the exception into a practical application and do not amount to significantly more than the above judicial exception. Looking at the limitations as an ordered combination (that is, as a whole) adds nothing that is not already present when looking at the elements individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation, i.e., the computer is simply a tool to perform the process.
Regarding the dependent claims, claims 2-3, 5-7, 11, 16, and 25-40 depend on claim 1. The dependent claims merely further define the abstract idea or are additional data output that is well-understood, routine, and previously known to the industry.
For example, the following are dependent claims reciting abstract ideas and can be performed in the human mind:
(Claim 2): “wherein the one or more processors is further configured to subtract the correction factor from the second probability value” further defines the abstract idea as it can be performed mentally or with the aid of pen and paper. These techniques are based on algorithms and calculations and mathematical principles, which can be performed by hand. The mathematics are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas;
(Claim 3): “wherein the one or more processors is configured to subtract the correction factor from the second probability value when the first probability value is below a predetermined threshold” further defines the abstract idea as it can be performed mentally or with the aid of pen and paper. These techniques are based on algorithms and calculations and judgement, which can be performed by hand. The analysis involved with these techniques are based in observing the recorded data and performing calculations to determine the desired results. The mathematics are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas;
(Claim 5): “wherein the one or more types of seizure activity comprises seizures, seizure-like activity, electrographic seizure, status epilepticus, post- ictal activity, highly pathological EEGs with a high likelihood of epileptiform activity, and an abnormal EEG pattern” further defines the abstract idea since it simply further limits the types of seizure activity;
(Claim 6): “further comprising diagnosing epilepsy in the subject based on the detected seizure activity” further defines the abstract idea as it can be performed mentally or with the aid of pen and paper. These techniques are based on algorithms and calculations and evaluations and judgements, which can be performed mentally or by hand. The mathematics are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas;
(Claim 7): “wherein at least one of the encoder and the decoder are part of a convolutional neural network” further defines the abstract idea as it is based in mathematical concept that can be performed mentally or with the aid of pen and paper. These techniques are based on algorithms and calculations and mathematical principles, which can be performed by hand. The analysis involved with these techniques are based in observing the recorded data and performing calculations to determine the desired results. The mathematics are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas;
(Claim 11): “wherein the data module is configured to record the plurality of electroencephalography (EEG) signals over one or more channels” is insignificant pre-solution activity;
(Claim 16): “wherein a duration of the time window ranges from about 1 second to about 10 minutes” is insignificant pre-solution activity;
(Claim 25): “further comprising a headband, the headband comprising a plurality of electrodes from which the plurality of electroencephalography (EEG) signals is recorded” is insignificant pre-solution activity, as evidenced by:
US Patent Application No. 20160157777 (Attal) discloses a headband for measuring EEG signals with electrodes as well-known (Attal, [0006]);
US Patent Application No. 20090099474 (Pineda) discloses a headband for use of measuring EEG signals as conventional (Pineda, [0061]).
(Claim 26): “wherein the seizure detection module further comprises a spike detection module configured to: identify a spike within each of the plurality of temporal segments; classify the spike based on one or more spike parameters; and characterize each of the plurality of temporal segments as a physiological temporal segment or an artifactual temporal segment based on one or more spike metrics” further defines the abstract idea as it is based in mathematical concept that can be performed mentally or with the aid of pen and paper. These techniques are based on algorithms and calculations and mathematical principles, which can be performed by hand. The analysis involved with these techniques are based in observing the recorded data and performing calculations to determine the desired results. The mathematics are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas;
(Claim 27): “wherein the one or more spike parameters comprises a spike amplitude, a spike width, a spike prominence, or a spike polarity” further defines the abstract idea since it simply further limits the types of spike parameters;
(Claim 28): “wherein the one or more spike metrics comprises a spike frequency, a spike jitter, a spike polarity, or a spike count” further defines the abstract idea since it simply further limits the types of spike metrics;
(Claim 29): “wherein the seizure detection module is further configured to classify a temporal segment as an artifact when an impedance associated with an electrode used to record the EEG signals surpasses a threshold” further defines the abstract idea as it is based in mathematical concept that can be performed mentally or with the aid of pen and paper. These techniques are based on algorithms and calculations and mathematical principles, which can be performed by hand. The analysis involved with these techniques are based in observing the recorded data and performing calculations to determine the desired results. The mathematics are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas;
(Claim 30): “wherein the seizure detection module further comprises a contextual classifier configured to generate a plurality of context-based probability values based on a plurality of feature vectors extracted from a context window spanning a plurality of temporal segments” further defines the abstract idea as it is based in mathematical concept that can be performed mentally or with the aid of pen and paper. These techniques are based on algorithms and calculations and mathematical principles, which can be performed by hand. The analysis involved with these techniques are based in observing the recorded data and performing calculations to determine the desired results. The mathematics are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas;
(Claim 31): “wherein the contextual classifier comprises a recurrent neural network” further defines the abstract idea as it is based in mathematical concept that can be performed mentally or with the aid of pen and paper. These techniques are based on algorithms and calculations and mathematical principles, which can be performed by hand. The analysis involved with these techniques are based in observing the recorded data and performing calculations to determine the desired results. The mathematics are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas;
(Claim 32): “wherein the plurality of temporal segments within the context window comprises about 3 to about 30 temporal segments” is insignificant pre-solution activity;
(Claim 33): “wherein the encoder comprises one or more attention blocks” further defines the abstract idea as it is based in mathematical concept that can be performed mentally or with the aid of pen and paper. These techniques are based on algorithms and calculations and mathematical principles, which can be performed by hand. The analysis involved with these techniques are based in observing the recorded data and performing calculations to determine the desired results. The mathematics are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas;
(Claim 34): “wherein the seizure detection module further comprises a decision module configured to combine two or more seizure probability values generated by a plurality of classifiers and correction factors to generate an aggregated probability value for each temporal segment” further defines the abstract idea as it is based in mathematical concept that can be performed mentally or with the aid of pen and paper. These techniques are based on algorithms and calculations and mathematical principles, which can be performed by hand. The analysis involved with these techniques are based in observing the recorded data and performing calculations to determine the desired results. The mathematics are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas;
(Claim 35): “wherein the aggregated probability value corresponds to a seizure burden and is determined by one or more of a mean, a median, and a maximum of the seizure probability values generated by the plurality of classifiers” further defines the abstract idea as it is based in mathematical concept that can be performed mentally or with the aid of pen and paper. These techniques are based on algorithms and calculations and mathematical principles, which can be performed by hand. The analysis involved with these techniques are based in observing the recorded data and performing calculations to determine the desired results. The mathematics are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas;
(Claim 36): “wherein the plurality of classifiers comprises at least the feature-based classifier, a contextual classifier, and the decoder” further defines the abstract idea as it is based in mathematical concept that can be performed mentally or with the aid of pen and paper. These techniques are based on algorithms and calculations and mathematical principles, which can be performed by hand. The analysis involved with these techniques are based in observing the recorded data and performing calculations to determine the desired results. The mathematics are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas;
(Claim 37): “wherein the decision module is further configured to: compare a first moving average calculated over a first analysis window to a first threshold; and generate a seizure alert when the first moving average exceeds the first threshold” further defines the abstract idea as it is based in mathematical concept that can be performed mentally or with the aid of pen and paper. These techniques are based on algorithms and calculations and mathematical principles, which can be performed by hand. The analysis involved with these techniques are based in observing the recorded data and performing calculations to determine the desired results. The mathematics are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas;
(Claim 38): “wherein the first moving analysis window is about 5 minutes and the alert is generated when the seizure burden exceeds about 90%” is insignificant pre-solution activity;
(Claim 39): “herein the first moving analysis window is about 5 minutes and the alert is generated when the seizure burden exceeds about 90%” is insignificant pre-solution activity;
(Claim 40): “wherein the decision module is further configured to: compare a second moving average calculated over a second time window to a second threshold; compare a third moving average calculated over a third analysis window to a third threshold; and generate a status epilepticus alert when both the second moving average exceeds the second threshold and the third moving average exceeds the third threshold” further defines the abstract idea as it is based in mathematical concept that can be performed mentally or with the aid of pen and paper. These techniques are based on algorithms and calculations and mathematical principles, which can be performed by hand. The analysis involved with these techniques are based in observing the recorded data and performing calculations to determine the desired results. The mathematics are not overly complicated to perform using pen and paper given enough time, therefore these are defined as abstract ideas;
The dependent claims do not recite significantly more than the abstract ideas. Therefore, claims 1-3, 5-7, 11, 16, and 25-41 are rejected as being directed to non-statutory subject matter.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 5, 7, 11, 16, 25, 30-32, and 34-40 are rejected under 35 U.S.C. 103 as being unpatentable over Kamousi (US 20210085235) in view of Dong (CN 117562551) and Rodriguez (US 20090312664). Citations to CN 117562551 will refer to the English Machine Translation that accompanies this Office Action.
Regarding independent claim 1, Kamousi teaches a system for analyzing EEG signals (Abstract: “The present disclosure provides systems and methods for seizure detection”) comprising:
a data module ([0013]: “The preprocessing module may also be configured to preprocess the plurality of EEG signals by segmenting the plurality of EEG signals for each channel into a plurality of temporal data segments”. The preprocessing module is the component of the device that performs the processing steps, therefore includes the data module.) configured to receive data comprising a plurality of electroencephalography (EEG) signals recorded during a time window from a subject ([0013]: “The seizure detection system may include a preprocessing module configured to receive a plurality of electroencephalography (EEG) signals over a plurality of channels for a subject.”; [0008]: “the method may further comprise aggregating the seizure binary classifications for the plurality of temporal data segments for the plurality of channels over a moving time window.”); and
a seizure detection module, the seizure detection module configured to process the data by dividing each of the plurality of EEG signals into a plurality of temporal segments ([0013]: “The preprocessing module may also be configured to preprocess the plurality of EEG signals by segmenting the plurality of EEG signals for each channel into a plurality of temporal data segments”. The preprocessing module is the component of the device that performs the processing steps, therefore includes the seizure detection module.), and comprising:
a feature-based classifier ([0083]: “the method may include applying a machine learning classifier to any number of channels”. The machine learning classifier is the feature-based classifier.) configured to:
extract a plurality of features from each of the plurality of temporal segments ([0005]: “the method may extract a plurality of features from each temporal data segment for each channel”) and generate probability statistics for each of the temporal segments derived from the plurality of extracted features ([0094]: “the features may be prioritized on probability statistics based on the frequency and/or quantity of occurrence of the feature”).
However, Kamousi does not teach generating a first probability value and generating a correction factor based on the first probability value.
Dong discloses a method and device for predicting an epileptic seizure. Specifically, Dong teaches generating a first probability value; and generating a correction factor based on the first probability value ([0038]: “Extract the first probability value from the classification result corresponding to the fourth segment result, and smooth the first probability value”. The smoothed probability value is the correction factor.). Kamousi and Dong are analogous art as they are both related to the same field of endeavor of monitoring a user and predicting seizures.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the first probability value and generating a correction factor from Dong into the system from Kamousi as Kamousi is silent on the specific details of the probability statistics used, and Dong discloses suitable specific probability evaluation in an analogous device.
The Kamousi/Dong combination teaches an encoder (Kamousi, [0064]: “general dimensionality reduction techniques may be, for example, … autoencoder”) configured to transform the data into a plurality of vectors (Kamousi, [0063]: “feature extraction may involve reducing the number of resources required to describe a large set of data (e.g. EEG signals). In some cases, analysis with a large number of variables may require a large amount of memory and computation power. In some cases, it may cause a machine learning algorithm to overfit to training samples and generalize poorly to new samples. In some cases, feature extraction may construct combinations of the variables to accurately describe the data with sufficient accuracy. In some cases, feature extraction may construct combinations of the variables to accurately describe the data with sufficient accuracy while preventing overfitting”; [0065]: “a set of numeric features may be described by a feature vector. In some cases, a feature vector may be an n-dimensional vector of numerical features that represent some object”).
However, the Kamousi/Dong combination does not teach a decoder configured to determine a second probability value based on the plurality of vectors
Dong discloses determining a second probability value based on the plurality of vectors ([0052]: “Extract the second probability value from the classification result corresponding to the fifth segment result”).
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the second probability value from Dong into the Kamousi/Dong combination as it allows the device to determine an additional probability value, which can allow for further analysis of the EEG signals and more accurate prediction of seizure activity by including multiple probability values.
However, the Kamousi/Dong combination does not teach using a decoder.
Rodriguez discloses an apparatus and method for obtaining and analyzing EEG signals. Specifically, Rodriguez teaches the system containing a decoder ([0064]: “All the information is then present at the decoder to perfectly reconstruct the original signals”). Kamousi and Rodriguez are analogous art as they are both related to the same field of endeavor of measuring EEG of a user and determining their condition.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the decoder from Rodriguez into the Kamousi/Dong combination as the combination is silent on the specific components used for the processing, and Rodriguez discloses specific components within an analogous device.
The Kamousi/Dong/Rodriguez combination teaches wherein one or more processors is configured to determine one or more types of seizure activity (Kamousi, Abstract: “The method for seizure detection may include receiving a plurality of electroencephalography (EEG) signals over a plurality of channels for a subject, preprocessing the plurality of EEG signals by segmenting the plurality of EEG signals for each channel into a plurality of temporal data segments, extracting a plurality of features from each temporal data segment for each channel, and applying a machine learning algorithm to the plurality of features to perform a seizure binary classification for each temporal data segment for each channel. A control policy may be employed to determine a seizure burden on the aggregated seizure binary classifications”; [0030]: “the EEG signals provided to the machine learning algorithm may need to be given as features that describe a characteristic of the EEG signal that pertains to seizure activity”).
However, the Kamousi/Dong/Rodriguez combination does not teach how the probability values are used in the determination.
Dong teaches determining types of seizure activity based on the second probability value and the correction factor ([0053]-[0054]: “If the smoothed second probability value is greater than the preset threshold, then the predicted category corresponding to the second probability value in the classification result corresponding to the fifth segment result is determined to be the pre-onset stage. If the smoothed second probability value is less than or equal to the preset threshold, then the predicted category corresponding to the second probability value in the classification result corresponding to the fifth segment result is determined to be the interictal period”; [0170]-[0171]: “If the first probability value after smoothing is greater than the preset threshold, then the predicted category corresponding to the first probability value in the classification result corresponding to the fourth segment result is determined to be the pre-onset stage. Based on the seizure period corresponding to the fourth segment result and the predicted category corresponding to the first probability value in the classification result corresponding to the fourth segment result, the sensitivity and/or false alarm rate of the epileptic seizure prediction model are calculated”).
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the specific use of probability values in the determination from the Kamousi/Dong/Rodriguez combination as the combination is silent on the specific use of the probability values in the determination, and Dong teaches a suitable use in an analogous device.
Regarding claim 5, the Kamousi/Dong/Rodriguez combination teaches the system of claim 1, wherein the one or more types of seizure activity comprises seizures, seizure-like activity, electrographic seizure, status epilepticus, post-ictal activity, highly pathological EEGs with a high likelihood of epileptiform activity, and an abnormal EEG pattern (Kamousi, [0030]: “the EEG signals provided to the machine learning algorithm may need to be given as features that describe a characteristic of the EEG signal that pertains to seizure activity. Furthermore, post-classification of the features by the machine learning algorithm, a control policy comprising a set of rules along with a seizure burden calculation allows the method and/or system to more accurately depict that the subject is experiencing or potentially experiencing a seizure”. The seizure activity if the subject experiencing a seizure.).
Regarding claim 7, the Kamousi/Dong/Rodriguez combination teaches the system of claim 1, wherein at least one of the encoder and the decoder are part of a convolutional neural network (Kamousi, [0079]: “the machine learning algorithm may comprise a deep neural network (DNN). The deep neural network may comprise a convolutional neural network (CNN)”).
Regarding claim 11, the Kamousi/Dong/Rodriguez combination teaches the system of claim 1, wherein the data module is configured to record the plurality of electroencephalography (EEG) signals over one or more channels (Kamousi, [0013]: “The seizure detection system may include a preprocessing module configured to receive a plurality of electroencephalography (EEG) signals over a plurality of channels for a subject.”).
Regarding claim 16, the Kamousi/Dong/Rodriguez combination teaches the system of claim 1, wherein a duration of the time window ranges from about 1 second to about 10 minutes (Kamousi, [0008]: “the moving time window may range from about one minute to ten minutes”).
Regarding claim 25, the Kamousi/Dong/Rodriguez combination teaches the system of claim 1, further comprising a headband, the headband comprising a plurality of electrodes from which the plurality of electroencephalography (EEG) signals is recorded (Kamousi, [0038]: “A system for measuring bioelectrical signals may generally comprise one or more electrodes electrically coupled via corresponding conductive wires to a controller and/or output device. In other variations, the electrodes may be coupled to the controller and/or output device wirelessly. The electrodes may be contained within an electrode carrier system that is secured around the head of the patient. The electrode carrier system may be configured as a headband or incorporated into any number of other platforms or positioning mechanisms for maintaining the electrodes against the patient body. Individual electrode assemblies may be spaced apart from one another so that, when the headband is positioned upon the patient's head, the electrode assemblies may be aligned optimally for receiving EEG signals”).
Regarding claim 30, the Kamousi/Dong/Rodriguez combination teaches the system of claim 1, wherein the seizure detection module further comprises a contextual classifier (Kamousi, [0083]: “the method may include applying a machine learning classifier to any number of channels”. The machine learning classifier is the contextual classifier.) configured to generate a plurality of context-based probability values based on a plurality of feature vectors extracted from a context window spanning a plurality of temporal segments (Kamousi, [0014]: “The output module may be configured to aggregate the seizure binary classifications for the plurality of temporal data segments for the plurality of channels over a moving time window”. The aggregated seizure binary classifications are the probability values, therefore they include a plurality of temporal segments.; Dong, [0038]: “Extract the first probability value from the classification result corresponding to the fourth segment result, and smooth the first probability value”; [0052]: “Extract the second probability value from the classification result corresponding to the fifth segment result”).
Regarding claim 31, the Kamousi/Dong/Rodriguez combination teaches the system of claim 30, wherein the contextual classifier comprises a recurrent neural network (Kamousi, [0079]: “The supervised learning algorithm may be, for example, support vector machines, linear regression, logistic regression, linear discriminant analysis, decision trees, k-nearest neighbor algorithm, neural networks, similarity learning, or a combination thereof. In some embodiments, the machine learning algorithm may comprise a deep neural network (DNN). The deep neural network may comprise a convolutional neural network (CNN). The CNN may be, for example, … recurrent neural network”).
Regarding claim 32, the Kamousi/Dong/Rodriguez combination teaches the system of claim 30, wherein the plurality of temporal segments within the context window comprises about 3 to about 30 temporal segments (Kamousi, [0014]: “The output module may be configured to aggregate the seizure binary classifications for the plurality of temporal data segments for the plurality of channels over a moving time window”; [0045]: “the plurality of EEG signals may be segmented to between 1 to 100000 data segments”. The plurality of temporal segments can include any number between 2-100000, therefore can include between 3-30 segments.).
Regarding claim 34, the Kamousi/Dong/Rodriguez combination teaches the system of claim 1, wherein the seizure detection module further comprises a decision module (Kamousi, [0013]: “The processing module may be configured to receive the plurality of temporal data segments corresponding to the plurality of channels. The processing module may be configured to also extract a plurality of features from each temporal data segment for each channel. The processing module may be also configured to apply a machine learning algorithm to the plurality of features to perform a seizure binary classification for each temporal data segment for each channel”. The processing module can include the decision module.) configured to combine two or more seizure probability values generated by a plurality of classifiers and correction factors to generate an aggregated probability value for each temporal segment (Kamousi, [0008]: “the method may further comprise aggregating the seizure binary classifications for the plurality of temporal data segments for the plurality of channels over a moving time window”. The aggregated seizure binary classifications can be the aggregated probability value.).
Regarding claim 35, the Kamousi/Dong/Rodriguez combination teaches the system of claim 34, wherein the aggregated probability value corresponds to a seizure burden (Kamousi, [0011]: “the method may further comprise determining a seizure burden for the moving time window based on the aggregated seizure binary classifications”.) and is determined by one or more of a mean, a median, and a maximum of the seizure probability values generated by the plurality of classifiers (Kamousi, [0011]: “determining the seizure burden may comprise averaging the seizure-positive classifications over the moving time window.”).
Regarding claim 36, the Kamousi/Dong/Rodriguez combination teaches the system of claim 34, wherein the plurality of classifiers comprises at least the feature-based classifier, a contextual classifier, and the decoder (Kamousi, [0083]: “the method may include applying a machine learning classifier to any number of channels”. The machine learning classifier can contain the feature-based classifier and the contextual classifier; Rodriguez, [0064]: “All the information is then present at the decoder to perfectly reconstruct the original signals”).
Regarding claim 37, the Kamousi/Dong/Rodriguez combination teaches the system of claim 34, wherein the decision module is further configured to: compare a first moving average calculated over a first analysis window to a first threshold; and generate a seizure alert when the first moving average exceeds the first threshold (Kamousi, [0012]: “the method may further comprise generating one or more notifications when the seizure burden is equal to or exceeds one or more thresholds. In some cases, the one or more notifications may be usable by a healthcare practitioner to assess whether the subject is at risk of having a seizure. In some cases, the one or more notifications may be generated in the form of visual, audio, and/or textual alerts” The seizure burden is determined from the moving average calculated over a time window, therefore teaching on this limitation.).
Regarding claim 38, the Kamousi/Dong/Rodriguez combination teaches the system of claim 37, wherein the first moving analysis window is about 5 minutes (Kamousi, [0008]: “the moving time window may be about five minutes”) and the alert is generated when the seizure burden exceeds about 90% (Kamousi, [0012]: “a third notification indicative of continuous seizure activity may be generated when the seizure burden is equal to or exceeds a third threshold of 90%”.).
Regarding claim 39, the Kamousi/Dong/Rodriguez combination teaches the system of claim 37, wherein the decision module is further configured to: compare a second moving average calculated over a second time window to a second threshold; compare a third moving average calculated over a third analysis window to a third threshold; and generate a status epilepticus alert when both the second moving average exceeds the second threshold and the third moving average exceeds the third threshold (Kamousi, [0012]: “the method may further comprise generating one or more notifications when the seizure burden is equal to or exceeds one or more thresholds. In some cases, the one or more notifications may be usable by a healthcare practitioner to assess whether the subject is at risk of having a seizure. In some cases, the one or more notifications may be generated in the form of visual, audio, and/or textual alerts. In some cases, a first notification indicative of frequent seizure activity may be generated when the seizure burden is equal to or exceeds a first threshold of 10%. In some cases, a second notification indicative of abundant seizure activity may be generated when the seizure burden is equal to or exceeds a second threshold of 50%. In some cases, a third notification indicative of continuous seizure activity may be generated when the seizure burden is equal to or exceeds a third threshold of 90%”).
Regarding claim 40, the Kamousi/Dong/Rodriguez combination teaches the system of claim 39, wherein the second analysis window is about 10 minutes (Kamousi, [0008]: “the moving time window may range from about one minute to ten minutes”), the third moving analysis window is about 60 minutes (Kamousi, Claim 2: “the moving time window comprises a fixed period of time between about one minute and about one hour”), the second threshold is about 90%, and the third threshold is about 20% (Kamousi, [0012]: “a first notification indicative of frequent seizure activity may be generated when the seizure burden is equal to or exceeds a first threshold of 10%. In some cases, a second notification indicative of abundant seizure activity may be generated when the seizure burden is equal to or exceeds a second threshold of 50%. In some cases, a third notification indicative of continuous seizure activity may be generated when the seizure burden is equal to or exceeds a third threshold of 90%”; [0112]: “the threshold for notification may be of any percentage. The threshold for notification may be at least about 1%, 5%, 10%, 15%, 20%, 25%, 30%, 35%, 40%, 45%, 50%, 55%, 60%, 65%, 70%, 80%, 90%, 95%, 99% or more. The threshold for notification may be at most about 99%, 95%, 90%, 85%, 80%, 75%, 70%, 65%, 60%, 55%, 50%, 45%, 40%, 35%, 30%, 25%, 20%, 15%, 10%, 5%, 1% or less. The threshold for notification may be from about 0% to 100%, 1% to 99%, 5% to 95%, 10% to 90%, 20% to 80%, 30% to 70%, or 40% to 60%. The threshold for notification may also be user adjustable”. The thresholds are adjustable, therefore the second threshold can be chosen to be 90% and the third threshold can be chosen to be 20%.).
Claims 2-3 are rejected under 35 U.S.C. 103 as being unpatentable over the Kamousi/Dong/Rodriguez combination as applied to claim 1 above, and further in view of Girouard (US 20180160964).
Regarding claim 2, the Kamousi/Dong/Rodriguez combination teaches the system of claim 1.
However, the Kamousi/Dong/Rodriguez combination does not teach wherein the one or more processors is further configured to subtract the correction factor from the second probability value.
Girouard discloses a method of monitoring a patient for seizure activity. Specifically, Girouard teaches wherein the one or more processors is further configured to subtract the correction factor from the second probability value ([0055]: “an analysis protocol may include a peak detection program, which, for example, after band-pass filtering and rectification may identify and shape data. In some embodiments, peak detection may include data smoothing techniques (e.g., moving average filter, Savitzky-Golay filter, Gaussian filter, Kaiser Window, various wavelet transforms, and the like), baseline correction processes”. Baseline correction processes include subtracting a value (the smoothed probability value) from the raw value (the second probability value)). Kamousi, Dong, and Girouard are analogous art as they are all related to the same field of endeavor of monitoring a patient for seizure activity.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the baseline correction from Girouard into the Kamousi/Dong/Rodriguez combination as it allows the system to improve the clarity of the data and isolates a specific response in the data, which can allow for more accurate detection.
Regarding claim 3, the Kamousi/Dong/Rodriguez/Girouard combination teaches the system of claim 2, wherein the one or more processors is configured to subtract the correction factor from the second probability value when the first probability value is below a predetermined threshold (Kamousi, [0048]: “the one or more filtering steps may be applied before, during, and/or after the segmentation of the plurality of EEG signals. One or more of the filtering steps may include, for example, a digital filter, an analogue filter, or a combination thereof. One or more of the filtering steps may include, for example, a… low-pass filter” The baseline correction can be included in a low-pass filter, which only filters data below a predetermined threshold.).
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over the Kamousi/Dong/Rodriguez combination as applied to claim 1 above, and further in view of Duffy (US 20230079137).
Regarding claim 6, the Kamousi/Dong/Rodriguez combination teaches the system of claim 1, further comprising evaluating seizures in the subject based on the detected seizure activity (Kamousi, [0031]: “Seizure burden values equal to or exceeding one or more thresholds may be used by a healthcare practitioner as an indication of a medical condition, for example, status epilepticus”; [0030]: “the EEG signals provided to the machine learning algorithm may need to be given as features that describe a characteristic of the EEG signal that pertains to seizure activity. Furthermore, post-classification of the features by the machine learning algorithm, a control policy comprising a set of rules along with a seizure burden calculation allows the method and/or system to more accurately depict that the subject is experiencing or potentially experiencing a seizure”).
However, the Kamousi/Dong/Rodriguez combination does not specifically teach diagnosing epilepsy.
Duffy discloses methods and systems for evaluating seizures and epilepsy in a user. Specifically, Duffy teaches diagnosing epilepsy based on the seizure activity ([0059]: “Based on the type of behavior and brain activity, seizures are divided into two broad categories: generalized and partial (also called local or focal). Classifying the type of seizure helps doctors diagnose whether or not a patient has epilepsy”). Kamousi, Dong, and Duffy are analogous art as they are all related to the same field of endeavor of monitoring a patient for seizure activity.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the diagnosis of epilepsy from Duffy into the Kamousi/Dong/Rodriguez combination as it allows the system to not only monitor the seizure activity, but also allow the device to diagnose epilepsy, which can allow the user to have a more comprehensive overview of their health condition.
Claims 26-28 are rejected under 35 U.S.C. 103 as being unpatentable over the Kamousi/Dong/Rodriguez combination as applied to claim 1 above, and further in view of Crowder (US 20160228705) and Girouard.
Regarding claim 26, into the Kamousi/Dong/Rodriguez combination teaches the system of claim 1.
However, the Kamousi/Dong/Rodriguez combination does not teach wherein the seizure detection module further comprises a spike detection module configured to: identify a spike within each of the plurality of temporal segments; classify the spike based on one or more spike parameters; and characterize each of the plurality of temporal segments as a physiological temporal segment or an artifactual temporal segment based on one or more spike metrics.
Crowder discloses a system for seizure classification. Specifically, Crowder teaches wherein the seizure detection module further comprises a spike detection module configured to: identify a spike within each of the plurality of temporal segments; classify the spike based on one or more spike parameter ([0063]: “Seizure onsets may be classified into types based on the morphology (i.e. the combination of the waveform shape, rhythmicity, frequency and relative amplitude) of the electrographic signal or ECoG. Six of these types are referred to herein as the “hypersynchronous seizure onset,” the “high voltage beta seizure onset”, the “multiple seizure onset”, the “low voltage fast seizure onset,” the “spike and wave seizure onset, and the “attenuation seizure onset””). Kamousi, Dong, and Crowder are analogous art as they are all related to the same field of endeavor of monitoring a patient for seizure activity.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the seizure onset detection using spikes from Crowder into the Kamousi/Dong/Rodriguez combination as it is a known method for determining seizure onset, therefore it would be a simple substitution to provide predictable results.
However, the Kamousi/Dong/Rodriguez/Crowder combination does not teach characterizing each of the plurality of temporal segments as a physiological temporal segment or an artifactual temporal segment based on one or more spike metrics.
Girouard teaches characterizing each of the plurality of temporal segments as a physiological temporal segment or an artifactual temporal segment based on one or more spike metrics ([0028]: “methods for detecting samples of EMG signal including elevated signal amplitude over background and generating a statistical summary of detected samples are further described. Some of those embodiments may be particularly suited for detection of non-epileptic psychogenic events and differentiating those events from epileptic seizures. In addition, some of the embodiments described herein may be configured for pairing with one or more other seizure-detection routines. Some of those embodiments may be particularly suited for executing high sensitivity detection and classification of seizure activity while also minimizing rates of false detection during patient monitoring”; [0029]: “The elevated portion of a sample may sometimes be referred to as a peak, and in some embodiments, a sample including elevated signal amplitude over background may be detected using one or more peak detection algorithms. For example, some of the peak detection algorithms that may be used in methods described herein may detect peaks by identifying one or more peak edges, including, for example, a leading edge of a peak, a trailing edge of a peak, and/or both leading and trailing edges of a peak”; [0030]: “samples including elevated signal amplitude over background may be qualified to identify that the samples may properly be associated with the clonic phase of a seizure. For example, qualification may include determining one or more values for one or more properties of a sample or group of samples. Determined property values may further be compared to one or more qualification thresholds. For example, in some embodiments, if a property value of a sample meets a qualification threshold, the sample may be deemed to be qualified and may be referred to as a qualified-clonic-phase burst”; [0031]: “methods for detection of samples of EMG signal including elevated amplitude over background may include or be executed in combination with one or more routines configured to qualify whether one or more samples may meet one or more qualification criteria or thresholds suitable to identify samples that may be related to seizure activity or a certain part of seizure activity”).
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the characterization from Girouard into the Kamousi/Dong/Rodriguez/Crowder combination as it allows the combination to ensure that the measured values actually correlate to seizure activity, ensuring that the system is only processing accurate information and providing the most accurate result.
Regarding claim 27, the Kamousi/Dong/Rodriguez/Crowder/Girouard combination teaches the system of claim 26, wherein the one or more spike parameters comprises a spike amplitude, a spike width, a spike prominence, or a spike polarity (Crowder, [0063]: “Seizure onsets may be classified into types based on the morphology (i.e. the combination of the waveform shape, rhythmicity, frequency and relative amplitude) of the electrographic signal or ECoG. Six of these types are referred to herein as the “hypersynchronous seizure onset,” the “high voltage beta seizure onset”, the “multiple seizure onset”, the “low voltage fast seizure onset,” the “spike and wave seizure onset, and the “attenuation seizure onset””. The spike parameters include the amplitude.).
Regarding claim 28, the Kamousi/Dong/Rodriguez/Crowder/Girouard combination teaches the system of claim 26, wherein the one or more spike metrics comprises a spike frequency, a spike jitter, a spike polarity, or a spike count (Girouard, [0028]: “methods for detecting samples of EMG signal including elevated signal amplitude over background and generating a statistical summary of detected samples are further described. Some of those embodiments may be particularly suited for detection of non-epileptic psychogenic events and differentiating those events from epileptic seizures. In addition, some of the embodiments described herein may be configured for pairing with one or more other seizure-detection routines. Some of those embodiments may be particularly suited for executing high sensitivity detection and classification of seizure activity while also minimizing rates of false detection during patient monitoring”; [0029]: “The elevated portion of a sample may sometimes be referred to as a peak, and in some embodiments, a sample including elevated signal amplitude over background may be detected using one or more peak detection algorithms. For example, some of the peak detection algorithms that may be used in methods described herein may detect peaks by identifying one or more peak edges, including, for example, a leading edge of a peak, a trailing edge of a peak, and/or both leading and trailing edges of a peak”; [0030]: “samples including elevated signal amplitude over background may be qualified to identify that the samples may properly be associated with the clonic phase of a seizure. For example, qualification may include determining one or more values for one or more properties of a sample or group of samples. Determined property values may further be compared to one or more qualification thresholds. For example, in some embodiments, if a property value of a sample meets a qualification threshold, the sample may be deemed to be qualified and may be referred to as a qualified-clonic-phase burst”; [0031]: “methods for detection of samples of EMG signal including elevated amplitude over background may include or be executed in combination with one or more routines configured to qualify whether one or more samples may meet one or more qualification criteria or thresholds suitable to identify samples that may be related to seizure activity or a certain part of seizure activity””. Fig. 5 shows the peak count based on the displayed dots, which is used in the peak detection algorithm.).
Claim 29 is rejected under 35 U.S.C. 103 as being unpatentable over the Kamousi/Dong/Rodriguez/Crowder/Girouard combination as applied to claim 26 above, and further in view of Ennen (US 20020082513).
Regarding claim 29, the Kamousi/Dong/Rodriguez/Crowder/Girouard combination teaches the system of claim 26, wherein the seizure detection module is further configured to classify a temporal segment as an artifact (Kamousi, [0095]: “A system for measuring bioelectrical signals may generally comprise one or more electrodes electrically coupled via corresponding conductive wires to a controller and/or output device. In other variations, the electrodes may be coupled to the controller and/or output device wirelessly. The electrodes may be contained within an electrode carrier system that is secured around the head of the patient. The electrode carrier system may be configured as a headband or incorporated into any number of other platforms or positioning mechanisms for maintaining the electrodes against the patient body. Individual electrode assemblies may be spaced apart from one another so that, when the headband is positioned upon the patient's head, the electrode assemblies may be aligned optimally for receiving EEG signals”).
However, the Kamousi/Dong/Rodriguez/Crowder/Girouard combination does not teach classifying the artifact when an impedance associated with an electrode used to record the EEG signals surpasses a threshold.
Ennen discloses a system for monitoring EEG signals. Specifically, Ennen teaches classifying the artifact when an impedance associated with an electrode used to record the EEG signals surpasses a threshold ([0022]: “all channels [FP1, FPz', Pz, Cz] are processed by an ensemble of signal morphological classifiers 13 (artifact detectors). By continuously monitoring the impedance of the FP1 electrode 10 the Beta5 Observer's signal quality can be assessed. The FP1's signal quality is combined with Beta5 analysis 9 and evaluation 11 by the Beta5 Observer and propagated to the Observation Mediator. The outputs of the Signal Morphology Classifiers are four artifact free EEG data streams and a declaration of the types of artifacts detected”). Kamousi and Ennen are analogous art as they are both related to the same field of endeavor of measuring EEG of a user and determining their condition.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use the method of determining the artifact from Ennen into the Kamousi/Dong/Rodriguez/Crowder/Girouard combination as the combination is silent on the specific method used to determine the artifact, and Ennen discloses a suitable method in an analogous device.
Claim 33 is rejected under 35 U.S.C. 103 as being unpatentable over the Kamousi/Dong/Rodriguez combination as applied to claim 1 above, and further in view of Zhang (CN 115359909). Citations to CN 115359909 will refer to the English Machine Translation that accompanies this Office Action.
Regarding claim 33, the Kamousi/Dong/Rodriguez combination teaches the system of claim 1.
However, the Kamousi/Dong/Rodriguez combination does not teach wherein the encoder comprises one or more attention blocks.
Zhang discloses an epileptic seizure detection system. Specifically, Zhang teaches wherein the encoder comprises one or more attention blocks ([0036]: “the Transformer layer used in this invention consists of 6 encoder layers with coupled attention blocks”). Kamousi, Dong, and Zhang are analogous art as they are all related to the same field of endeavor of monitoring a patient for seizure activity.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the encoder comprising attention blocks from Zhang into the Kamousi/Dong/Rodriguez combination as the combination is silent on the structure of the encoder, and Zhang discloses a suitable structure in an analogous device.
Claim 41 is rejected under 35 U.S.C. 103 as being unpatentable over Kamousi in view of Dong.
Regarding independent claim 41, Kamousi teaches a method for detecting seizures (Abstract: “The present disclosure provides systems and methods for seizure detection”) comprising:
receiving data from a plurality of electrodes, the data comprising a plurality of electroencephalography (EEG) signals recorded during a time window ([0013]: “The seizure detection system may include a preprocessing module configured to receive a plurality of electroencephalography (EEG) signals over a plurality of channels for a subject.”; [0008]: “the method may further comprise aggregating the seizure binary classifications for the plurality of temporal data segments for the plurality of channels over a moving time window.”; [0038]: “A system for measuring bioelectrical signals may generally comprise one or more electrodes electrically coupled via corresponding conductive wires to a controller and/or output device. In other variations, the electrodes may be coupled to the controller and/or output device wirelessly. The electrodes may be contained within an electrode carrier system that is secured around the head of the patient. The electrode carrier system may be configured as a headband or incorporated into any number of other platforms or positioning mechanisms for maintaining the electrodes against the patient body. Individual electrode assemblies may be spaced apart from one another so that, when the headband is positioned upon the patient's head, the electrode assemblies may be aligned optimally for receiving EEG signals”); and
using a seizure detection module configured to process the data, wherein the processing comprises: dividing each of the plurality of EEG signals into a plurality of temporal segments ([0013]: “The preprocessing module may also be configured to preprocess the plurality of EEG signals by segmenting the plurality of EEG signals for each channel into a plurality of temporal data segments”. The preprocessing module is the component of the device that performs the processing steps, therefore includes the seizure detection module.);
extracting a plurality of features from each of the plurality of temporal segments ([0005]: “the method may extract a plurality of features from each temporal data segment for each channel”) and determining probability statistics for each of the temporal segments derived from the plurality of extracted features ([0094]: “the features may be prioritized on probability statistics based on the frequency and/or quantity of occurrence of the feature”).
However, Kamousi does not teach generating a first probability value and generating a correction factor based on the first probability value.
Dong discloses a method and device for predicting an epileptic seizure. Specifically, Dong teaches generating a first probability value; and generating a correction factor based on the first probability value ([0038]: “Extract the first probability value from the classification result corresponding to the fourth segment result, and smooth the first probability value”. The smoothed probability value is the correction factor.). Kamousi and Dong are analogous art as they are both related to the same field of endeavor of monitoring a user and predicting seizures.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the first probability value and generating a correction factor from Dong into the method from Kamousi as Kamousi is silent on the specific details of the probability statistics used, and Dong discloses suitable specific probability evaluation in an analogous device.
The Kamousi/Dong combination teaches transforming the processed data into a plurality of vectors (Kamousi, [0063]: “feature extraction may involve reducing the number of resources required to describe a large set of data (e.g. EEG signals). In some cases, analysis with a large number of variables may require a large amount of memory and computation power. In some cases, it may cause a machine learning algorithm to overfit to training samples and generalize poorly to new samples. In some cases, feature extraction may construct combinations of the variables to accurately describe the data with sufficient accuracy. In some cases, feature extraction may construct combinations of the variables to accurately describe the data with sufficient accuracy while preventing overfitting”; [0065]: “a set of numeric features may be described by a feature vector. In some cases, a feature vector may be an n-dimensional vector of numerical features that represent some object”).
However, the Kamousi/Dong combination does not teach a decoder configured to determine a second probability value based on the plurality of vectors
Dong discloses determining a second probability value based on the plurality of vectors ([0052]: “Extract the second probability value from the classification result corresponding to the fifth segment result”).
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the second probability value from Dong into the Kamousi/Dong combination as it allows the device to determine an additional probability value, which can allow for further analysis of the EEG signals and more accurate prediction of seizure activity by including multiple probability values.
The Kamousi/Dong combination teaches determining a seizure classification (Kamousi, Abstract: “The method for seizure detection may include receiving a plurality of electroencephalography (EEG) signals over a plurality of channels for a subject, preprocessing the plurality of EEG signals by segmenting the plurality of EEG signals for each channel into a plurality of temporal data segments, extracting a plurality of features from each temporal data segment for each channel, and applying a machine learning algorithm to the plurality of features to perform a seizure binary classification for each temporal data segment for each channel. A control policy may be employed to determine a seizure burden on the aggregated seizure binary classifications”; [0030]: “the EEG signals provided to the machine learning algorithm may need to be given as features that describe a characteristic of the EEG signal that pertains to seizure activity”).
However, the Kamousi/Dong combination does not teach how the probability values are used in the determination.
Dong teaches determining a seizure classification for each of the temporal segments based on the second probability value and the correction factor ([0053]-[0054]: “If the smoothed second probability value is greater than the preset threshold, then the predicted category corresponding to the second probability value in the classification result corresponding to the fifth segment result is determined to be the pre-onset stage. If the smoothed second probability value is less than or equal to the preset threshold, then the predicted category corresponding to the second probability value in the classification result corresponding to the fifth segment result is determined to be the interictal period”; [0170]-[0171]: “If the first probability value after smoothing is greater than the preset threshold, then the predicted category corresponding to the first probability value in the classification result corresponding to the fourth segment result is determined to be the pre-onset stage. Based on the seizure period corresponding to the fourth segment result and the predicted category corresponding to the first probability value in the classification result corresponding to the fourth segment result, the sensitivity and/or false alarm rate of the epileptic seizure prediction model are calculated”).
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the specific use of probability values in the determination from the Kamousi/Dong combination as the combination is silent on the specific use of the probability values in the determination, and Dong teaches a suitable use in an analogous device.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ERIN K MCCORMACK whose telephone number is (703)756-1886. The examiner can normally be reached Mon-Fri 7:30-5.
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, Jason Sims can be reached at 5712727540. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/E.K.M./Examiner, Art Unit 3791
/MATTHEW KREMER/Primary Examiner, Art Unit 3791
Prosecution Insights