Prosecution Insights
Last updated: November 04, 2026
Application No. 19/170,334

METHODS AND SYSTEMS FOR ASSESSING NEUROLOGICAL CONDITIONS

Non-Final OA §101§102§103§112
Filed
Apr 04, 2025
Priority
Apr 10, 2024 — provisional 63/632,341
Examiner
WESTFALL, SARAH ANN
Art Unit
3791
Tech Center
3700 — Mechanical Engineering & Manufacturing
Assignee
Axon Interfaces Corp.
OA Round
1 (Non-Final)
9%
Grant Probability
At Risk
1-2
OA Rounds
1y 10m
Est. Remaining
42%
With Interview

Examiner Intelligence

Grants only 9% of cases
9%
Career Allowance Rate
2 granted / 23 resolved
-61.3% vs TC avg
Strong +33% interview lift
Without
With
+33.3%
Interview Lift
resolved cases with interview
Typical timeline
3y 5m
Avg Prosecution
31 currently pending
Career history
71
Total Applications
across all art units

Statute-Specific Performance

§101
17.3%
-22.7% vs TC avg
§103
36.1%
-3.9% vs TC avg
§102
17.3%
-22.7% vs TC avg
§112
26.6%
-13.4% vs TC avg
Black line = Tech Center average estimate • Based on career data from 23 resolved cases

Office Action

§101 §102 §103 §112
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 . 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. Specification The disclosure is objected to because of the following informalities: the phrase “Lemple-Ziv” is misspelled throughout the specification of the instant application. More specifically, Paragraphs [0007] and [0031] of the Applicant’s Specification recites “Lemple-Ziv” but should read “Lempel-Ziv”. Appropriate correction is required. Claim Objections Claims 1, 8, 10, and 17 are objected to because of the following informalities: typographical errors. The phrase “band pass filtering”, as recited in line 5 of Claim 1, should read “bandpass filtering” instead. The examiner notes that the phrase “band pass” is more widely accepted when written as a single phrase such as “bandpass”. Additionally, the phrase “Lemple-Ziv”, as recited in Claims 8, 10, and 17, is a misspelling and should read “Lempel-Ziv”. 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 1-20 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 term “approximately” is a relative term which renders the claim indefinite. The term “approximately” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. The parameter “0.5-32 Hz” is rendered indefinite based on the term “approximately”. For this examination, the examiner aimed to find prior art that included a passband within or close-to the recited range in order to teach on the limitation. Additionally, the term “large” in the phrase “large artifact” is a relative term which renders the claim indefinite. The term “large” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. The parameter “artifact” is rendered indefinite based on the term “large”. For this examination, the examiner aimed to find prior art that included any form of artifact removal in order to teach on the limitation. Furthermore, the limitation “the patient’s brain activity” recited in lines 13-14 lacks proper antecedent basis. For this examination, the examiner has interpreted this phrase to mean “brain activity of the patient”. Lastly, the limitation “the presence of a disease state” recited in the second to last line of the claim lacks proper antecedent basis. For this examination, the examiner has interpreted this phrase to mean “a presence of a disease state”. Regarding Claim 5, the limitation “the feature extraction” recited in the first line of the claim lacks proper antecedent basis. For this examination, the examiner has interpreted this phrase to mean “obtaining features from the extracted biomarkers”. Claims not explicitly rejected above are rejected due to their dependence on the above claims. Claim Rejections - 35 USC § 101 35 U.S.C. 101 reads as follows: Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title. Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claim(s) as a whole, considering all claim elements both individually and in combination, do not amount to significantly more than an abstract idea. A streamlined analysis of Claim 1 follows. STEP 1 Regarding Claim 1, the claim recites a series of steps or acts, including obtaining raw EEG resting state data, bandpass filtering the raw EEG data, subjecting the filtered EEG data to bad channel removal, performing large artifact removal, extracting biomarkers from the filtered EEG data, providing the extracted biomarkers as inputs to a machine learning engine that has been trained to distinguish disease states from non-disease states, and outputting a probability from 0 to 1 of the presence of a disease state. Thus, the claim is directed to a process, which is one of the statutory categories of invention. STEP 2A, PRONG ONE The claim is then analyzed to determine whether it is directed to any judicial exception. The steps of providing the extracted biomarkers as inputs to a machine learning engine that has been trained to distinguish disease states from non-disease states and outputting a probability from 0 to 1 of the presence of a disease state set forth a judicial exception. These steps describe a concept performed in the human mind (including an observation, evaluation, judgment, opinion). Thus, the claim is drawn to a Mental Process, which is an Abstract Idea. STEP 2A, PRONG TWO Next, the claim as a whole is analyzed to determine whether the claim recites additional elements that integrate the judicial exception into a practical application. The claim fails to recite an additional element or a combination of additional elements to apply, rely on, or use the judicial exception in a manner that imposes a meaningful limitation on the judicial exception. Claim 1 fails to recite any application of providing the extracted biomarkers as inputs to a machine learning engine that has been trained to distinguish disease states from non-disease states and outputting a probability from 0 to 1 of the presence of a disease state in a manner that imposes a meaningful limitation on the Abstract Idea. A machine learning engine used to distinguish disease states from non-disease states utilizes a generic computer program. According to section 2106.05(f) of the MPEP, merely using a computer as a tool to perform an abstract idea does not integrate the Abstract Idea into a practical application. Additionally, outputting the predicted at least one secondary characteristic is merely adding insignificant extra-solution activity to the judicial exception (MPEP 2106.05(g)). The Abstract Idea alone does not provide an improvement to the technological field, the method does not affect a particular treatment or effect a particular change based on the inputted extracted biomarkers into a machine learning engine, nor does the method use a particular machine to perform the Abstract Idea. STEP 2B Next, the claim as a whole is analyzed to determine whether any element, or combination of elements, is sufficient to ensure that the claim amounts to significantly more than the exception. Claim 1 recites the additional elements of: “one or more sensors affixed to the patient or a device worn by the patient” and “a machine learning engine”. Besides the Abstract Idea, Claim 1 recites additional steps of obtaining raw EEG resting state data, bandpass filtering the raw EEG data, subjecting the filtered EEG data to bad channel removal, performing large artifact removal, and extracting biomarkers from the filtered EEG data. The obtaining, filtering, and removal steps are recited at a high level of generality such that they amount to insignificant pre-solution activity, e.g., mere data gathering step necessary to perform the Abstract Idea. When recited at this high level of generality, there is no meaningful limitation, such as a particular or unconventional step that distinguishes it from well-understood, routine, and conventional data gathering activity engaged in by medical professionals prior to Applicant's invention. Furthermore, it is well established that the mere physical or tangible nature of additional elements such as the acquiring and inputting steps do not automatically confer eligibility on a claim directed to an abstract idea (see, e.g., Alice Corp. v. CLS Bank Int'l, 134 S.Ct. 2347, 2358-59 (2014)). Consideration of the additional elements as a combination also adds no other meaningful limitations to the exception not already present when the elements are considered separately. Unlike the eligible claim in Diehr in which the elements limiting the exception are individually conventional, but taken together act in concert to improve a technical field, the claim here does not provide an improvement to the technical field. Even when viewed as a combination, the additional elements fail to transform the exception into a patent-eligible application of that exception. Thus, the claim as a whole does not amount to significantly more than the exception itself. The claim is therefore drawn to non-statutory subject matter. Regarding Claims 19 and 20, the recited “processor” and “computer system” are generic computer devices with a generic computer program that is configured to perform obtaining raw EEG resting state data, bandpass filtering the raw EEG data, subjecting the filtered EEG data to bad channel removal, and performing large artifact removal as mere pre-solution data gathering; and outputting a probability from 0 to 1 of the presence of a disease state as mere post-solution data gathering. The generic computer and its program are configured to perform the above as well as the Abstract Idea. According to section 2106.05(f) of the MPEP, merely using a computer as a tool to perform an abstract idea does not integrate the Abstract Idea into a practical application. Dependent Claims 2-18 fail to add something more to the abstract independent claims as they generally recite steps pertaining to data gathering and processing. Regarding Claim 16, “a software-as-a-service platform” is a generic computer program. The obtaining, filtering, removing, extracting, providing, and outputting steps recited in the independent claim, Claim 1, maintain a high level of generality even when considered in combination with the dependent claims. Claim Rejections - 35 USC § 102 The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action: A person shall be entitled to a patent unless – (a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention. Claims 1, 3-5, 14, and 19-20 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Vardoulis et. al.'’768 (U.S. Patent Publication 20250169768). Regarding Claim 1, Vardoulis et. al.’768 discloses a method for processing raw electroencephalogram (EEG) resting state data (Paragraph [0022] - receive a raw EEG signal from the external EEG skin electrodes 106), the method comprising: obtaining the raw EEG resting state data from a patient using one or more sensors affixed to the patient or a device worn by the patient (Paragraph [0022] - receive a raw EEG signal from the external EEG skin electrodes 106); bandpass filtering the raw EEG data using a bandpass filter with a passband of approximately 0.5 - 32 Hz to obtain filtered EEG data, the filtered EEG data being made up of signals in a plurality of channels (Paragraph [0023] - The noise suppression lowpass or bandpass filter LPF/BPF circuitry 112 can be configured to remove or attenuate high frequency noise or other signal content outside of the frequency regions of interest… the noise suppression lowpass or bandpass filter LPF/BPF circuitry 112 can include a single pole or higher order filter having a lowpass cutoff frequency pole at or near 20 Hz); subjecting the filtered EEG data to bad channel removal so as to remove those of the signals in channels that exhibit poor signal-to-noise ratios, the poor signal-to-noise ratios being exhibited in a time domain by channel amplitudes that deviate by more than a specified amount and/or being exhibited in a frequency domain by deviations in channel spectral data (Paragraph [0023] - The noise suppression lowpass or bandpass filter LPF/BPF circuitry 112 can include a single channel or multi-channel output that can provide a noise-filtered artifact-filtered EEG signal as the acquired EEG signal for use by subsequent signal processing circuitry); following the bad channel removal, performing large artifact removal to remove artifacts from the filtered EEG data due to signals from electrical sources other than the patient's brain activity (Paragraph [0062] - At 610, the pool of valid event time-series data can be generated, such as with neurophysiologist-determined event labels including “Control,” representing pre-ischemia-episode portions of time-series data, and “Ischemia” representing ischemia-present episode portions of the time series data, which are deemed to be representative of stroke, for the purposes of training the learning model 124; Paragraph [0064] - At 614, the learning model 124 can be trained for stroke detection using the training data set after processing according to the EEG signal feature extraction of 612); following the large artifact removal, extracting biomarkers from the filtered EEG data, wherein for each channel of the filtered EEG data the biomarkers include spectral features, statistical features, time series features, and graph features (Paragraph [0062] - At 610, the pool of valid event time-series data can be generated, such as with neurophysiologist-determined event labels including “Control,” representing pre-ischemia-episode portions of time-series data, and “Ischemia” representing ischemia-present episode portions of the time series data, which are deemed to be representative of stroke, for the purposes of training the learning model 124; Paragraph [0064] - At 614, the learning model 124 can be trained for stroke detection using the training data set after processing according to the EEG signal feature extraction of 612); providing the extracted biomarkers as inputs to a machine learning engine that has been trained to distinguish disease states from non-disease states, and outputting from the machine learning engine a probability from 0 to 1 of the presence of a disease state as indicated by the extracted biomarkers (Paragraph [0004] - Stroke can be categorized as ischemic or hemorrhagic. Ischemic stroke, which constitutes roughly 87% of all strokes, is mainly secondary to atherothrombotic, embolic, and small-vessel diseases; Paragraph [0067] - The trained model 124 can be configured to output a Stroke Probability Metric, such as a value within a range of values extending between 0 and 1, inclusive, with a temporal shift (change over time) toward a higher value indicating a greater likelihood that an onset of stroke has been detected). Regarding Claim 3, Vardoulis et. al.’768 discloses the method outlined in Claim 1 above as well as wherein the large artifact removal is performed by eliminating channel data that exceeds a predefined amplitude threshold (Paragraph [0037] - One way of determining temporal shift is by determining a change spectral power amplitude from a corresponding baseline value of spectral power amplitude, at a specified one or more spectral bins, over a specified period of time. For example, a temporal dip (e.g., a decrease in spectral power amplitude over a specified period of time) in a mid-frequency sub-range of the specified overall frequency range can be indicative of a detected new or recent stroke condition, such as shown in FIG. 4). Regarding Claim 4, Vardoulis et. al.’768 discloses the method outlined in Claim 1 above as well as wherein the large artifact removal is performed by one or more of: regression methods, wavelet transformation methods, Blind Source Separation (BSS)-based methods, or Empirical-mode Decomposition (EMD) methods (Paragraph [0065] - More generally, training of the model 124 can include supervised learning (e.g., classification, regression)). Regarding Claim 5, Vardoulis et. al.’768 discloses the method outlined in Claim 1 above as well as wherein obtaining features from the extracted biomarkers is performed using one or more of: Fast Fourier Transforms (FFTs), discrete wavelet transform (DWT), time frequency distributions, eigenvector methods, or autoregressive methods (Paragraph [0033] - The Power Spectral Density PSD circuitry 202 can include single or multi-channel inputs receiving corresponding digital values from the analog-to-digital converter ADC 114, such as representing the various channels of pre-processed signals from the various EEG electrodes 106. The Power Spectral Density PSD circuitry 202 can convert such digitized signal values from the time-domain into the frequency-domain, such as by performing a Fast Fourier Transform (FFT) (or other transform such as a wavelet transform) using FFT transform or other transform circuitry included in the Power Spectral Density PSD circuitry 202). Regarding Claim 14, Vardoulis et. al.’768 discloses the method outlined in Claim 1 above as well as wherein the machine learning engine instantiated as a server instance of a software-as-a-service platform (Paragraph [0027] - The memory circuitry 118 can include learning model representation storage, such as for storing information associated with an artificial intelligence (AI) or machine learning (ML) or other statistical or other learning model 124 or representation thereof; Paragraph [0029] - The local or remote server system 134 can also be used to perform training of the model 124, such as based upon data received from the stroke device 102 of a particular patient, based upon population-based data, such as from other stroke devices 102 of other patients, or both. The trained model 124 can then optionally be manually or automatically pushed or downloaded to a particular stroke device 102, or data from a particular stroke device 102 can be streamed or otherwise communicated to a remote hub for signal-processing and analysis, such as can include using the trained model at the remote hub). Regarding Claim 19, Vardoulis et. al.’768 discloses comprising a processor and a memory coupled to the processor, the memory storing instructions which, when executed by the processor, cause the processor to execute the steps for processing raw EEG resting state data (Paragraph [0095] - an apparatus, device, method, system, article of manufacture, process, computer-readable medium with stored instructions; Paragraph [0129] - Some examples can include a computer-readable medium or machine-readable medium encoded with instructions operable to configure an electronic device to perform methods as described in the above examples). Regarding Claim 20, Vardoulis et. al.’768 discloses comprising a processor and a memory coupled to the processor, the memory storing instructions which, when executed by the processor, cause the processor to execute the steps for processing raw EEG resting state data (Paragraph [0095] - an apparatus, device, method, system, article of manufacture, process, computer-readable medium with stored instructions; Paragraph [0129] - Some examples can include a computer-readable medium or machine-readable medium encoded with instructions operable to configure an electronic device to perform methods as described in the above examples), and the server further comprising a communication interface configured to provide a two-way data communication channel with a computer network (Paragraph [0030] - The onboard or local auxiliary communications transceiver 128 can also be configured to communicate, such as via the mobile telephony communications network 132, Bluetooth, or other modality, with a user interface 136). Claim Rejections - 35 USC § 103 The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action: A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made. Claims 2 and 6 are rejected under 35 U.S.C. 103 as being unpatentable over Vardoulis et. al.’768 (U.S. Patent Publication 20250169768) as applied to Claim 1 above, and further in view of De Bruin et. al.'212 (U.S. Patent Publication 20110119212). Regarding Claim 2, Vardoulis et. al.’768 discloses the method outlined in Claim 1 above but fails to disclose wherein the bad channel removal is performed using one of: a k-nearest neighbor approach, anomaly detection, or a Local Outlier Probability (LoOP) approach. De Bruin et. al.'212 teaches using k-nearest neighbor to filter out data (Paragraph [0241] - When using only eyes-closed EEG data, in another clinical experiment, a comparison among different prediction/classification techniques is shown in Table 7…Using a grid search, the best parameters for each method are found, and Table 7 reflects the best performance attainable with each technique. For example, a polynomial kernel of degree 8 is used with the support vector machine (SVM) technique. The k-nearest-neighbor (kNN), least-squares (LS), and linear discriminant analysis (LDA) methods are other standard classification techniques used as references in our comparison, S. Theodoridis and K. Koutroumbas, Pattern Recognition, 2.sup.nd ed. USA: Elsevier Academic Press, 2003). It would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to have modified the method of Vardoulis et. al.’768 to include a classification filter such as k-nearest-neighbor in order to properly classify and filter channels using a standard classification technique known in the art as seen in De Bruin et. al.'212. Regarding Claim 6, Vardoulis et. al.’768 discloses the method outlined in Claim 1 above but fails to disclose wherein the spectral features comprise alpha peak frequency, band power, and delta/theta power ratio. De Bruin et. al.'212 teaches spectral features comprising peaks across various frequencies, band power, and ratio power in various frequencies (Paragraph [0097] - The EEG feature set may include (but is not limited to) statistical attributes, random process parameters, coherency measures, correlation, higher-order statistics, wavelet analysis coefficients, autoregressive modeling coefficients, absolute and relative spectrum power levels in various frequency bands, the ratio of left-to-right hemisphere power in various frequencies, and the anterior/posterior power gradient in various frequencies, mutual information between sensors, spatial and temporal data model attributes, time-series model attributes, linear and non-linear dynamic process modeling features, features representing and extracting geometrical information of high-dimensional data, attributes representing the data in transformed and mapped space, and clustering and low-dimensional representation attributes, and combinations and transformations thereof. Those skilled in the art may be able to identify further features, without limiting the scope of this patent). It would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to have modified the method of Vardoulis et. al.’768 to include spectral features comprising peaks across various frequencies, band power, and power ratios between various frequencies in order to identify features without going beyond the scope of practice for one of ordinary skill in the art as seen in De Bruin et. al.'212. Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable Vardoulis et. al.’768 (U.S. Patent Publication 20250169768) in view of De Bruin et. al.'212 (U.S. Patent Publication 20110119212), as applied to Claim 6 above, and further in view of Shoaran et. al.'397 (U.S. Patent Publication 20200388397). Regarding Claim 7, Vardoulis et. al.’768 in view of De Bruin et. al.'212 discloses the method outlined in Claim 6 above but fails to disclose wherein the statistical features comprise Hjorth activity, Hjorth mobility, and Hjorth complexity. Shoaran et. al.'397 teaches statistical parameters consisting of Hjorth parameters (Paragraph [0133] - The Hjorth parameters of a signal describe its statistical characteristics in the time domain and are commonly used in EEG studies. These parameters include the activity, mobility, and complexity. While the Hjorth activity indicates the signal variance, mobility is a measure of the average frequency. Furthermore, the variations in frequency within a given time period are presented by the Hjorth complexity). It would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to have modified the method of Vardoulis et. al.’768 in view of De Bruin et. al.'212 to include statistical features consisting of Hjorth parameters in order to apply a commonly used domain when analyzing EEG signals as seen in Shoaran et. al.'397. Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Vardoulis et. al.’768 (U.S. Patent Publication 20250169768), in view of De Bruin et. al.'212 (U.S. Patent Publication 20110119212), further in view of Shoaran et. al.'397 (U.S. Patent Publication 20200388397), as applied to Claim 7 above, and further in view of Geva et. al.'105 (U.S. Patent Publication 20040230105). Regarding Claim 8, Vardoulis et. al.’768 in view of De Bruin et. al.'212 and further in view of Shoaran et. al.'397 discloses the method outlined in Claim 7 above but fails to disclose wherein the time series features comprise normalized Lempel-Ziv complexity and fractal dimension. Geva et. al.'105 teaches utilizing Lempel-Ziv complexity and fractal dimension to compute redundancy sensitivity (Paragraph [0240] - in order to obtain an accurate prediction of pathological events, a combined linear and nonlinear dynamic feature extraction and manipulation process is performed…The higher the fractal dimension or the complexity measure, the more the related chaotic signal is considered complex. According to the present invention, the complexity evaluation is carried out by utilizing two known complexity analyzing tools; (1) Lempel-Ziv (LZ) complexity analysis; and (2) Fractal Dimension (FD) analysis)). It would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to have modified the method of Vardoulis et. al.’768 in view of De Bruin et. al.'212 and further in view of Shoaran et. al.'397 to include Lempel-Ziv complexity and fractal dimensions when analyzing EEG signals to include known complexity analyzing tools as seen in Geva et. al.'105. Claims 9-13 are rejected under 35 U.S.C. 103 as being unpatentable over Vardoulis et. al.’768 (U.S. Patent Publication 20250169768), in view of De Bruin et. al.'212 (U.S. Patent Publication 20110119212), further in view of Shoaran et. al.'397 (U.S. Patent Publication 20200388397), further in view of Geva et. al.'105 (U.S. Patent Publication 20040230105), as applied to Claim 8 above, and further in view of Pineda et. al.'2020 (Quantile Graphs for EEG-based Diagnosis of Alzheimer's Disease). Regarding Claim 9, Vardoulis et. al.’768 in view of De Bruin et. al.'212, further in view of Shoaran et. al.'397, and further in view of Geva et. al.'105 disclose the method outlined in Claim 8 above but fails to disclose wherein the graph features comprise mean jump length across a quantile graph (Delta score). Pineda et. al.'2020 teaches graph features comprising a mean jump length across graphs (Page 11 Paragraph 3 - For all groups and frequency bands, the mean jump length, which is the metric that best discriminates the groups in our analysis, was computed (Fig 6). Observe that the curves for normal controls (B) and patients with AD (D) are very similar for theta, alpha, and beta waves, regardless the value of k. On the other hand, there was statistically significant difference (95% confidence interval (CI) and a p-value of less than 0.05) between the sample means in groups B and D for delta waves. (Table 3). This result confirms the prior knowledge that all patients under study display clear symptoms of the disease and may have it in its late stage). It would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to have modified the method of Vardoulis et. al.’768 in view of De Bruin et. al.'212, further in view of Shoaran et. al.'397, and further in view of Geva et. al.'105 to include computing the mean jump length across EEG graphs in order to identify statistically significant differences across readings used to confirm or deny presence of a disease as seen in Pineda et. al.'2020. Regarding Claim 10, Vardoulis et. al.’768 discloses the method outlined in Claim 1 above but fails to disclose wherein the spectral features comprise alpha peak frequency, band power, and delta/theta power ratio; the statistical features comprise Hjorth activity, Hjorth mobility, and Hjorth complexity; the time series features comprise normalized Lemple-Ziv complexity and fractal dimension; and the graph features comprise mean jump length across a quantile graph (Delta score). De Bruin et. al.'212 teaches spectral features comprising peaks across various frequencies, band power, and ratio power in various frequencies (Paragraph [0097] - The EEG feature set may include (but is not limited to) statistical attributes, random process parameters, coherency measures, correlation, higher-order statistics, wavelet analysis coefficients, autoregressive modeling coefficients, absolute and relative spectrum power levels in various frequency bands, the ratio of left-to-right hemisphere power in various frequencies, and the anterior/posterior power gradient in various frequencies, mutual information between sensors, spatial and temporal data model attributes, time-series model attributes, linear and non-linear dynamic process modeling features, features representing and extracting geometrical information of high-dimensional data, attributes representing the data in transformed and mapped space, and clustering and low-dimensional representation attributes, and combinations and transformations thereof. Those skilled in the art may be able to identify further features, without limiting the scope of this patent). It would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to have modified the method of Vardoulis et. al.’768 to include spectral features comprising peaks across various frequencies, band power, and power ratios between various frequencies in order to identify features without going beyond the scope of practice for one of ordinary skill in the art as seen in De Bruin et. al.'212. Shoaran et. al.'397 teaches statistical parameters consisting of Hjorth parameters (Paragraph [0133] - The Hjorth parameters of a signal describe its statistical characteristics in the time domain and are commonly used in EEG studies. These parameters include the activity, mobility, and complexity. While the Hjorth activity indicates the signal variance, mobility is a measure of the average frequency. Furthermore, the variations in frequency within a given time period are presented by the Hjorth complexity). It would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to have modified the method of Vardoulis et. al.’768 in view of De Bruin et. al.'212 to include statistical features consisting of Hjorth parameters in order to apply a commonly used domain when analyzing EEG signals as seen in Shoaran et. al.'397. Geva et. al.'105 teaches utilizing Lempel-Ziv complexity and fractal dimension to compute redundancy sensitivity (Paragraph [0240] - in order to obtain an accurate prediction of pathological events, a combined linear and nonlinear dynamic feature extraction and manipulation process is performed…The higher the fractal dimension or the complexity measure, the more the related chaotic signal is considered complex. According to the present invention, the complexity evaluation is carried out by utilizing two known complexity analyzing tools; (1) Lempel-Ziv (LZ) complexity analysis; and (2) Fractal Dimension (FD) analysis)). It would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to have modified the method of Vardoulis et. al.’768 in view of De Bruin et. al.'212 and further in view of Shoaran et. al.'397 to include Lempel-Ziv complexity and fractal dimensions when analyzing EEG signals to include known complexity analyzing tools as seen in Geva et. al.'105. Pineda et. al.'2020 teaches graph features comprising a mean jump length across graphs (Page 11 Paragraph 3 - For all groups and frequency bands, the mean jump length, which is the metric that best discriminates the groups in our analysis, was computed (Fig 6). Observe that the curves for normal controls (B) and patients with AD (D) are very similar for theta, alpha, and beta waves, regardless the value of k. On the other hand, there was statistically significant difference (95% confidence interval (CI) and a p-value of less than 0.05) between the sample means in groups B and D for delta waves. (Table 3). This result confirms the prior knowledge that all patients under study display clear symptoms of the disease and may have it in its late stage). It would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to have modified the method of Vardoulis et. al.’768 in view of De Bruin et. al.'212, further in view of Shoaran et. al.'397, and further in view of Geva et. al.'105 to include computing the mean jump length across EEG graphs in order to identify statistically significant differences across readings used to confirm or deny presence of a disease as seen in Pineda et. al.'2020. Regarding Claim 11, Vardoulis et. al.’768 in view of De Bruin et. al.'212, further in view of Shoaran et. al.'397, further in view of Geva et. al.'105, and further in view of Pineda et. al.'2020 discloses the method outlined in Claim 10 above, but fails to disclose wherein the bad channel removal is performed using one of: a k- nearest neighbor approach, anomaly detection, or a Local Outlier Probability (LoOP) approach. De Bruin et. al.'212 teaches using k-nearest neighbor to filter out data (Paragraph [0241] - When using only eyes-closed EEG data, in another clinical experiment, a comparison among different prediction/classification techniques is shown in Table 7… Using a grid search, the best parameters for each method are found, and Table 7 reflects the best performance attainable with each technique. For example, a polynomial kernel of degree 8 is used with the support vector machine (SVM) technique. The k-nearest-neighbor (kNN), least-squares (LS), and linear discriminant analysis (LDA) methods are other standard classification techniques used as references in our comparison, S. Theodoridis and K. Koutroumbas, Pattern Recognition, 2.sup.nd ed. USA: Elsevier Academic Press, 2003). It would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to have modified the method of Vardoulis et. al.’768 to include a classification filter such as k-nearest-neighbor in order to properly classify and filter channels using a standard classification technique known in the art as seen in De Bruin et. al.'212. Regarding Claim 12, Vardoulis et. al.’768 in view of De Bruin et. al.'212, further in view of Shoaran et. al.'397, further in view of Geva et. al.’105, and further in view of Pineda et. al.'2020 discloses the method outlined in Claim 11 above. Vardoulis et. al.’768 further discloses wherein the large artifact removal is performed by one or more of: eliminating channel data that exceeds a predefined amplitude threshold, regression methods, wavelet transformation methods, Blind Source Separation (BSS)-based methods, or Empirical- mode Decomposition (EMD) methods (Paragraph [0037] - One way of determining temporal shift is by determining a change spectral power amplitude from a corresponding baseline value of spectral power amplitude, at a specified one or more spectral bins, over a specified period of time. For example, a temporal dip (e.g., a decrease in spectral power amplitude over a specified period of time) in a mid-frequency sub-range of the specified overall frequency range can be indicative of a detected new or recent stroke condition, such as shown in FIG. 4; Paragraph [0065] - More generally, training of the model 124 can include supervised learning (e.g., classification, regression)). Regarding Claim 13, Vardoulis et. al.’768 in view of De Bruin et. al.'212, further in view of Shoaran et. al.'397, further in view of Geva et. al.’105, and further in view of Pineda et. al.'2020 discloses the method outlined in Claim 12 above. Vardoulis et. al.’768 further discloses wherein the feature extraction is performed using one or more of: Fast Fourier Transforms (FFTs), discrete wavelet transform (DWT), time frequency distributions, eigenvector methods, or autoregressive methods (Paragraph [0033] - The Power Spectral Density PSD circuitry 202 can include single or multi-channel inputs receiving corresponding digital values from the analog-to-digital converter ADC 114, such as representing the various channels of pre-processed signals from the various EEG electrodes 106. The Power Spectral Density PSD circuitry 202 can convert such digitized signal values from the time-domain into the frequency-domain, such as by performing a Fast Fourier Transform (FFT) (or other transform such as a wavelet transform) using FFT transform or other transform circuitry included in the Power Spectral Density PSD circuitry 202). Claims 15-16 are rejected under 35 U.S.C. 103 as being unpatentable over Vardoulis et. al.’768 (U.S. Patent Publication 20250169768), as applied to Claim 1 above, and further in view of Gupta et. al.'2022 (Alzheimer's Disease and Stroke: A Tangled Neurological Conundrum). Regarding Claim 15, Vardoulis et. al.’768 discloses the method outlined in Claim 1 above but fails to disclose wherein the machine learning engine is trained to determine the presence of Alzheimer's disease from a disease-free condition based on the biomarkers. Gupta et. al.'2022 teaches identifying a presence of Alzheimer’s disease based on a plurality of factors (Abstract - A neurodegenerative disorder, Alzheimer's disease (AD), is characterized by dementia in which there is an age-related decline in cognition and higher functions. Stroke is a cerebrovascular disorder that frequently presents in old age and is a known risk factor for AD development; Figure 1 – Red arrows point out the causes of stroke connected to Alzheimer’s disease (ie. cerebral hypoperfusion and amyloid angiopathy); Page 3 Paragraph 1 - Stroke and AD are associated because cerebrovascular disorders such as stroke (both ischemic and hemorrhagic types) are among the well-known risk factors for developing AD). It would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to have modified the method of Vardoulis et. al.’768 to include training the machine learning model to determine the presence of Alzheimer’s disease based on a plurality of factors in order to account for the known association between users who suffer from strokes and Alzheimer’s disease as seen in Gupta et. al.'2022. Regarding Claim 16, Vardoulis et. al.’768 in view of Gupta et. al.'2022 discloses the method outlined in Claim 15 above. Vardoulis et. al.’768 further discloses wherein the machine learning engine instantiated as a server instance of a software-as-a-service platform (Paragraph [0027] - The memory circuitry 118 can include learning model representation storage, such as for storing information associated with an artificial intelligence (AI) or machine learning (ML) or other statistical or other learning model 124 or representation thereof; Paragraph [0029] - The local or remote server system 134 can also be used to perform training of the model 124, such as based upon data received from the stroke device 102 of a particular patient, based upon population-based data, such as from other stroke devices 102 of other patients, or both. The trained model 124 can then optionally be manually or automatically pushed or downloaded to a particular stroke device 102, or data from a particular stroke device 102 can be streamed or otherwise communicated to a remote hub for signal-processing and analysis, such as can include using the trained model at the remote hub). Claims 17 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Vardoulis et. al.’768 (U.S. Patent Publication 20250169768) in view of Gupta et. al.'2022 (Alzheimer's Disease and Stroke: A Tangled Neurological Conundrum), as applied to Claim 15 above, and further in view of De Bruin et. al.'212 (U.S. Patent Publication 20110119212), further in view of Shoaran et. al.'397 (U.S. Patent Publication 20200388397), further in view of Geva et. al.'105 (U.S. Patent Publication 20040230105), and further in view of Pineda et. al.'2020 (Quantile Graphs for EEG-based Diagnosis of Alzheimer's Disease). Regarding Claim 17, Vardoulis et. al.’768 in view of Gupta et. al.'2022 discloses the method outlined in Claim 15 above, but fails to disclose wherein the spectral features comprise alpha peak frequency, band power, and delta/theta power ratio; the statistical features comprise Hjorth activity, Hjorth mobility, and Hjorth complexity; the time series features comprise normalized Lemple-Ziv complexity and fractal dimension; and the graph features comprise mean jump length across a quantile graph (Delta score). De Bruin et. al.'212 teaches spectral features comprising peaks across various frequencies, band power, and ratio power in various frequencies (Paragraph [0097] - The EEG feature set may include (but is not limited to) statistical attributes, random process parameters, coherency measures, correlation, higher-order statistics, wavelet analysis coefficients, autoregressive modeling coefficients, absolute and relative spectrum power levels in various frequency bands, the ratio of left-to-right hemisphere power in various frequencies, and the anterior/posterior power gradient in various frequencies, mutual information between sensors, spatial and temporal data model attributes, time-series model attributes, linear and non-linear dynamic process modeling features, features representing and extracting geometrical information of high-dimensional data, attributes representing the data in transformed and mapped space, and clustering and low-dimensional representation attributes, and combinations and transformations thereof. Those skilled in the art may be able to identify further features, without limiting the scope of this patent). It would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to have modified the method of Vardoulis et. al.’768 in view of Gupta et. al.'2022 to include spectral features comprising peaks across various frequencies, band power, and power ratios between various frequencies in order to identify features without going beyond the scope of practice for one of ordinary skill in the art as seen in De Bruin et. al.'212. Shoaran et. al.'397 teaches statistical parameters consisting of Hjorth parameters (Paragraph [0133] - The Hjorth parameters of a signal describe its statistical characteristics in the time domain and are commonly used in EEG studies. These parameters include the activity, mobility, and complexity. While the Hjorth activity indicates the signal variance, mobility is a measure of the average frequency. Furthermore, the variations in frequency within a given time period are presented by the Hjorth complexity). It would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to have modified the method of Vardoulis et. al.’768 in view of Gupta et. al.'2022 and further in view of De Bruin et. al.'212 to include statistical features consisting of Hjorth parameters in order to apply a commonly used domain when analyzing EEG signals as seen in Shoaran et. al.'397. Geva et. al.'105 teaches utilizing Lempel-Ziv complexity and fractal dimension to compute redundancy sensitivity (Paragraph [0240] - in order to obtain an accurate prediction of pathological events, a combined linear and nonlinear dynamic feature extraction and manipulation process is performed…The higher the fractal dimension or the complexity measure, the more the related chaotic signal is considered complex. According to the present invention, the complexity evaluation is carried out by utilizing two known complexity analyzing tools; (1) Lempel-Ziv (LZ) complexity analysis; and (2) Fractal Dimension (FD) analysis)). It would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to have modified the method of Vardoulis et. al.’768 in view of Gupta et. al.'2022, further in view of De Bruin et. al.'212, and further in view of Shoaran et. al.'397 to include Lempel-Ziv complexity and fractal dimensions when analyzing EEG signals to include known complexity analyzing tools as seen in Geva et. al.'105. Pineda et. al.'2020 teaches graph features comprising a mean jump length across graphs (Page 11 Paragraph 3 - For all groups and frequency bands, the mean jump length, which is the metric that best discriminates the groups in our analysis, was computed (Fig 6). Observe that the curves for normal controls (B) and patients with AD (D) are very similar for theta, alpha, and beta waves, regardless the value of k. On the other hand, there was statistically significant difference (95% confidence interval (CI) and a p-value of less than 0.05) between the sample means in groups B and D for delta waves. (Table 3). This result confirms the prior knowledge that all patients under study display clear symptoms of the disease and may have it in its late stage). It would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to have modified the method of Vardoulis et. al.’768 in view of Gupta et. al.'2022, further in view of De Bruin et. al.'212, further in view of Shoaran et. al.'397, and further in view of Geva et. al.'105 to include computing the mean jump length across EEG graphs in order to identify statistically significant differences across readings used to confirm or deny presence of a disease as seen in Pineda et. al.'2020. Regarding Claim 18, Vardoulis et. al.’768 in view of Gupta et. al.'2022, further in view of De Bruin et. al.'212, further in view of Shoaran et. al.'397, further in view of Geva et. al.'105, and further in view of Pineda et. al.'2020 disclose the method outlined in Claim 17 above. Vardoulis et. al.’768 further discloses wherein the large artifact removal is performed by one or more of: eliminating channel data that exceeds a predefined amplitude threshold, regression methods, wavelet transformation methods, Blind Source Separation (BSS)-based methods, or Empirical- mode Decomposition (EMD) methods (Paragraph [0037] - One way of determining temporal shift is by determining a change spectral power amplitude from a corresponding baseline value of spectral power amplitude, at a specified one or more spectral bins, over a specified period of time. For example, a temporal dip (e.g., a decrease in spectral power amplitude over a specified period of time) in a mid-frequency sub-range of the specified overall frequency range can be indicative of a detected new or recent stroke condition, such as shown in FIG. 4; Paragraph [0065] - More generally, training of the model 124 can include supervised learning (e.g., classification, regression)). Vardoulis et. al.’768 further discloses wherein the feature extraction is performed using one or more of: Fast Fourier Transforms (FFTs), discrete wavelet transform (DWT), time frequency distributions, eigenvector methods, or autoregressive methods (Paragraph [0033] - The Power Spectral Density PSD circuitry 202 can include single or multi-channel inputs receiving corresponding digital values from the analog-to-digital converter ADC 114, such as representing the various channels of pre-processed signals from the various EEG electrodes 106. The Power Spectral Density PSD circuitry 202 can convert such digitized signal values from the time-domain into the frequency-domain, such as by performing a Fast Fourier Transform (FFT) (or other transform such as a wavelet transform) using FFT transform or other transform circuitry included in the Power Spectral Density PSD circuitry 202). Vardoulis et. al.’768 fails to disclose wherein the bad channel removal is performed using one of: a k-nearest neighbor approach, anomaly detection, or a Local Outlier Probability (LoOP) approach. De Bruin et. al.'212 teaches using k-nearest neighbor to filter out data (Paragraph [0241] - When using only eyes-closed EEG data, in another clinical experiment, a comparison among different prediction/classification techniques is shown in Table 7… Using a grid search, the best parameters for each method are found, and Table 7 reflects the best performance attainable with each technique. For example, a polynomial kernel of degree 8 is used with the support vector machine (SVM) technique. The k-nearest-neighbor (kNN), least-squares (LS), and linear discriminant analysis (LDA) methods are other standard classification techniques used as references in our comparison, S. Theodoridis and K. Koutroumbas, Pattern Recognition, 2.sup.nd ed. USA: Elsevier Academic Press, 2003). It would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to have modified the method of Vardoulis et. al.’768 in view of Gupta et. al.'2022, further in view of De Bruin et. al.'212, further in view of Shoaran et. al.'397, further in view of Geva et. al.'105, and further in view of Pineda et. al.'2020 to include a classification filter such as k-nearest-neighbor in order to properly classify and filter channels using a standard classification technique known in the art as seen in De Bruin et. al.'212. Conclusion The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Alkaitis et. al.'313 (U.S. Patent Publication 20240021313), Epelbaum et. al.'507 (U.S. Patent Publication 20220079507), and Rapp et. al.'328 (U.S. Patent Publication 20040243328) disclose EEG measurement analyzing devices utilizing various common methods. Any inquiry concerning this communication or earlier communications from the examiner should be directed to SARAH ANN WESTFALL whose telephone number is (571) 272-3845. The examiner can normally be reached Monday-Friday 7:30am-4:30pm EST. Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Jennifer Robertson can be reached at (571) 272-5001. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000. /SARAH ANN WESTFALL/Examiner, Art Unit 3791 /CHANEL J YOON/Examiner, Art Unit 3791
Read full office action

Prosecution Timeline

Apr 04, 2025
Application Filed
Oct 20, 2026
Non-Final Rejection mailed — §101, §102, §103 (current)

Strategy Recommendation AI-generated — please review before filing

Get a prosecution strategy drawn from examiner precedents, rejection analysis, and claim mapping.
Typically takes 5-10 seconds — AI-generated, attorney review required before filing

Prosecution Projections

1-2
Expected OA Rounds
9%
Grant Probability
42%
With Interview (+33.3%)
3y 5m (~1y 10m remaining)
Median Time to Grant
Low
PTA Risk
Based on 23 resolved cases by this examiner. Grant probability derived from career allowance rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month