DETAILED ACTION
Applicant' s arguments, filed 11/20/2025, have been fully considered. The following rejections and/or objections are either reiterated or newly applied. They constitute the complete set presently being applied to the instant application.
Applicants have amended their claims, filed 05/12/2025, and therefore rejections newly made in the instant office action have been necessitated by amendment.
Claims 1-4, 7-10, 13, 20, 22, 24-25, and 28-29 are the current claims hereby under examination.
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 .
Claim Objections
Claim 1 is objected to because of the following informalities:
Claim 1 it appears that “the a grid-search technique” should read “a grid-search technique”
Appropriate correction is required.
Applicant is advised that should claim 3 be found allowable, claim 28 will be objected to under 37 CFR 1.75 as being a substantial duplicate thereof. When two claims in an application are duplicates or else are so close in content that they both cover the same thing, despite a slight difference in wording, it is proper after allowing one claim to object to the other as being a substantial duplicate of the allowed claim. See MPEP § 608.01(m).
Claim Rejections - 35 USC § 112(b)
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 1-4, 7-10, 13, 20, 22, 24-25, and 28-29 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 1 recites “wherein the plurality of sets of values are patient-specifically selected through Neighbourhood Component Analysis applied to descriptive parameters obtained from previous EEG data of the same patient to identify parameters exhibiting highest correlation with the patient's neurological states” which appears to indicate that the plurality of extracted values are selected by using NCA on descriptive parameters to select the parameters with the highest correlation with the patient’s neurological state. The descriptive parameters have been obtained from previous EEG of the same patient. It is unclear what the descriptive parameters comprise and how they are obtained. For the purposes of this examination, the limitation will be interpreted as any generic feature extracted from raw EEG data.
Claim 1 recites “selecting internal configuration parameters of the classification model based on the a grid-search techniques” but it is unclear what internal configuration parameters are considered for each of the possible various types of classification models. For the purposes of this examination, the limitation will be interpreted as any and all possible parameters for each type being used in the grid-search technique.
Claim 1 recites “an auricular warning system” but it is unclear what this system entails. For the purposes of this examination, the system will be interpreted as any type of signal transmitter as this is the only structure required to carry out the recited controlling process of transmitting a signal.
Claims 2-4, 7-10, 13, 20, 22, 24-25, and 28-29 are rejected by virtue of their dependence on claim 1.
Claim 20 recites “wherein said selecting factors further comprises” but no factor selection step has been established in claim 1 and thus it is unclear what this claim is meant to further limit. It is unclear how this claim relates to the method of claim 1. For the purposes of this examination, the claim will be interpreted as describing how internal configuration parameters are determined using grid-search.
Claim 22 recites “a device … comprises at least one EEG sensor located in an intra-auricular body and configured for being in direct contact with an inside of an ear of the patient for measuring an EEG signal, and an electronics board in electrical contact with the at least one EEG sensor and configured for carrying out the method according to claim 1” but claim 1 requires at least one EEG sensor positioned within an ear canal. It is unclear if the EEG sensor of claim 22 which is positioned “in an intra-auricular body” is the EEG electrode in the ear canal required by claim 1 or if the EEG electrode of claim 22 are not positioned in the ear canal. For the purposes of this examination, the EEG electrode of claim 22 will be interpreted as being within the ear canal.
Claim 22 recites that the processor is configured for carrying out the method of claim 1 but claim 22 does not include “an auricular warning system” and thus it is unclear how the device of claim 22 is capable of carrying out the method of claim 1.
Claims 24-25 are rejected by virtue of their dependence on claim 22.
Claim 29 recites “the method of selecting parameters comprises” but it is unclear what parameter selection method is being referred to. Claim 1 established internal configuration parameters of the classification models and “descriptive parameters” obtained from previous EEG data segments. It is unclear which parameter selection method is meant to be limited by this recitation. For the purposes of this examination, the limitation will be interpreted as referring to the parameters of the previous EEG data.
Claim Rejections - 35 USC § 112(a)
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claim 1 is rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Claim 1 recites “selecting internal configuration parameters of the classification model based on the a grid-search techniques” but the specification does not appear to fully support the claimed scope of performing a grid-search technique on all of the possible types of classifiers to determine the internal configuration parameters. In particular, paragraph 0088 recites that the selection of factors may be performed by the grid-search technique. Paragraphs 0065-0077 and 0111-0120 describe various matrixes of factors which may be considered. It would seem that the specification does not fully support the claimed selection of internal configuration parameters through any grid-search technique but rather the specification is directed towards using particular factors in the grid-search to determine the internal parameters of the classifier The specification further does not appear to describe how these factors may vary based on the particular classifier utilized or what the internal configuration parameters comprise.
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 1-4, 7-10, 13, 20, 22, 24, and 28-29 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. Claims 1-4, 7-10, 13, 20, 22, 24, and 28-29 are directed to a method of processing EMG signals using a computational algorithm, which is an abstract idea. Claims 1-4, 7-10, 13, 20, 22, 24, and 28-29 do not include additional elements that integrate the exception into a practical application or that are sufficient to amount to significantly more than the judicial exception for the reasons provided below which are in line with the 2014 Interim Guidance on Patent Subject Matter Eligibility (Federal Register, Vol. 79, No. 241, p 74618, December 16, 2014), the July 2015 Update on Subject Matter Eligibility (Federal Register, Vol. 80, No. 146, p. 45429, July 30, 2015), the May 2016 Subject Matter Eligibility Update (Federal Register, Vol. 81, No. 88, p. 27381, May 6, 2016), the 2019 Revised Patent Subject Matter Eligibility Guidance (Federal Register, Vol. 84, No. 4, page 50, January 7, 2019), and the 2024 Update on Subject Matter Eligibility (Federal Register, Vol 89, No. 137, page 58128, July 17, 2024).
The analysis of claim 1 is as follows:
Step 1: Claim 1 is drawn to a process
Step 2A – Prong One: Claim 1 recites an abstract idea. In particular, claim 1 recites the following limitations:
[A1] processing measured values of the EEG signal to obtain a conditioned signal specifically adapted for auricular EEG measurement constraints,
[B1] performing EEG time segmentation to obtain a plurality of overlapping time segments of the EEG signal
[C1] extracting from the conditioned signal a plurality of sets of values, each of the plurality of sets of values being extracted from a different one of the plurality of overlapping time segments wherein the plurality of sets of values are patient-specifically selected through Neighbourhood Component Analysis applied to descriptive parameters obtained from previous EEG data of the same patient to identify parameters exhibiting highest correlation with the patient's neurological states
[D1] selecting at least one classification model from the group consisting of SVM, LSBoost, Random Forest, KNN, Neural Networks, Naive Bayes, Gaussian process and ANN,
[E1] selecting internal configuration parameters of the classification model based on a grid search techniques
[F1] calculating for each of the plurality of overlapping time segments a risk level of the patient suffering a crisis due to the neurological condition, by applying the at least one classification model with the internal configuration parameters, to a corresponding one of the plurality of sets of values according to values
[G1] classifying the state of the patient by classifying at least one of the plurality of overlapping time segments as either a preictal state or a non-preictal state, based on comparison of the risk level to a predefined threshold level,
[H1] automatically controlling an auricular warning system by transmitting a control signal to initiate a seizure warning when the state of the patient is classified as preictal state, wherein the control signal is transmitted when at least one of the overlapping time segments is classified as preictal state
These elements [A1]-[H1] of claim 1 are drawn to an abstract idea since they involve a mental process that can be practically performed in the human mind including observation, evaluation, judgment, and opinion and using pen and paper. Additionally, the element [D1] drawn to a classification model is nothing more than the computer implementation/automation of an abstract mental process of screening a patient, which is what a physician typically does with a patient in a diagnostic setting. As such, the model itself and characteristics of the model are considered to be part of the abstract idea since the model serves as a mere computer implementation/automation of the pattern recognition and/or decision making capabilities of the human mind.
Step 2A – Prong Two: Claim 1 recites the following limitations that are beyond the judicial exception:
[A2] an auricular device
[B2] at least one EEG sensor positioned within an ear canal
[C2] measuring an EEG signal of the patient by the at least one EEG sensor
These elements [A2]-[C2] of claim 1 do not integrate the exception into a practical application of the exception. In particular, the element [A2] merely generally links the use of the judicial exception to a particular technological environment or field of use – see MPEP 2106.05(h). Furthermore, elements [B2]-[C2] are merely adding insignificant extra-solution activity to the judicial exception, i.e., mere data gathering at a higher level of generality - see MPEP 2106.04(d) and MPEP 2106.05(g).
Step 2B: Claim 1 does not recite additional elements that amount to significantly more than the judicial exception itself. In particular, the recitations “at least one EEG sensor positioned within an ear canal” and “measuring EEG signal of the patient by the at least one EEG sensor” is merely insignificant extrasolution activity to the judicial exception, e.g., mere data gathering in conjunction with the abstract idea that uses conventional, routine, and well known elements or simply displaying the results of the algorithm that uses conventional, routine, and well known elements. In particular, the data acquirer is nothing more than a generic EEG sensor for recording brainwaves being placed in the ear. Such EEG sensors are conventional as evidenced by:
U.S. Patent Application Publication No. US 2018/0263562 A1 (Laplante-Levesque) discloses that conventional electrodes may be located within the ear canal for measuring EEG signals (paragraph 0121 of Laplante-Levesque)
U.S. Patent Application Publication No. US 2017/0180882 A1 (Lunner) discloses that conventional electrodes may be located within the ear canal to serve as EEG electrodes (paragraph 0119 of Lunner)
US Patent Number US 4741344 A (Danby) discloses that in the ear electrodes for recording brain signals are conventional (Col 1 lines 64-68 of Danby)
Additionally, since element [A2] is defined only as being comprised by the element [B2], it is also considered to be routine, conventional, and well-known as each element comprising the auricular device is well-known and the device itself is not further described.
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 (the abstract idea). 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 taking individually. There is no indication that the combination of elements improves the functioning of a computer, for example, or improves any other technology. There is no indication that the combination of elements permits automation of specific tasks that previously could not be automated. There is no indication that the combination of elements includes a particular solution to a computer-based problem or a particular way to achieve a desired computer-based outcome. Rather, the collective functions of the claimed invention merely provide conventional computer implementation, i.e., the computer is simply a tool to perform the process.
Claims 2-4, 7-10, 13, 20, 22, 24, and 28-29 depend from claim 1, and recite the same abstract idea as claim 1. Furthermore, these claims only contain recitations that further limit the abstract idea (that is, the claims only recite limitations that further limit the algorithm), with the following exceptions:
Claim 13: the at least one EEG sensor comprising more than one EEG sensor each of which measures the EEG signal of the patient;
Claim 22: A device comprising at least one EEG sensor located in an intra-auricular body and configured for being in direct contact with an inside of an ear of the patient for measuring an EEG signal, and an electronics board in electrical contact with the at least one EEG sensor and configured for carrying out the method according to claim 1 including at least one processing unit and one wireless communication unit configured for communicating with a smartphone-type portable device; and
Claim 24: a shell housing the electronics board and a flexible body attaching the shell to the intra-auricular body, said flexible body integrating therein connection cables between the electronics board and the at least one EEG sensor.
Each of these claim limitations does not integrate the exception into a practical application. In particular, the elements of claim 13 is merely adding insignificant extra-solution activity to the judicial exception, i.e., mere data gathering at a higher level of generality - see MPEP 2106.04(d) and MPEP 2106.05(g). In particular, EEG electrodes are well-known, routine, and conventional in the art and are used for nothing more than mere data gathering as evidenced by Laplante-Levesque, Lunner, and Danby as presented above.
Furthermore, the elements “an electronics board”, “at least one processing unit” and “one wireless communication unit” of claim 22 are merely an instruction to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.04(d) and MPEP 2106.05(f). These elements do not qualify as significantly more because these limitations are 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)).
Also, each of the limitations of claims 22 and 24 do not recite additional elements that amount to significantly more than the judicial exception itself because they are merely insignificant extrasolution activity to the judicial exception, e.g., mere data gathering in conjunction with the abstract idea that uses conventional, routine, and well known elements or simply displaying the results of the algorithm that uses conventional, routine, and well known elements. In particular, the recited structure of the device, placement of the EEG electrodes, and required components when considered as a whole are routine, conventional, well-known, and/or commercially available prior to the effective filing data of the invention as evidenced by
U.S. Patent Application Publication No. US 2018/0263562 A1 (Laplante-Levesque) discloses a device comprising a number of EEG electrodes located in the ear for collecting electrical signals and for transmitting the electrical signals to an auxiliary device (Paragraphs 0121-0122). The device includes circuitry located within a housing and configured to wireless communication with an auxiliary device such as a smartphone (Paragraphs 0027 and 0087). The device further comprises a flexible body attaching the shell to the intra-auricular body which integrate the cable connecting the EEG sensors to the circuitry (Fig. 2A; paragraphs 0027, 0087, and 0121-0122: the electrodes communicate with the circuitry in the housing)
U.S. Patent Application Publication No. US 2017/0048626 A1 (Jenson) teaches a device comprising a shell housing an electronics board and wireless communication circuitry (Paragraph 0088). The device communicates wirelessly with a smartphone type device (Paragraph 0082) The device further includes EEG electrodes (Paragraph 0029).
Eliza “Wireless Earbuds Will Record Your EEG, Send Brainwave Data To Your Phone” published by IEEE on May 17th 2016 pages 1-6 teaches earbuds comprising EEG electrodes in the ear canal (Page 2 paragraph 3 – page 3 paragraph 1). The device further includes a housing which encloses electronics such as a processor and wireless communication circuitry for communicating with smartphone type devices (Page 2 paragraph 2; Pages 1-2 Fig. 1: the shell and circuitry required to carry out the recited functions)
Strickland “In-Ear EEG Makes Unobtrusive Brain-Hacking Gadgets a Real Possibility” published by IEEE on July 7th 2016 pages 1-7 teaches in the ear electrodes (Page 3 paragraph 3 – page 4 paragraph 2). The electrodes are connected by a flexible wire to a housing (Pages 1-2 Fig. 1: the blue wire connecting the in the ear portion to the headset.)
U.S. Patent Application Publication No. US 2012/0238856 A1 (Westermann) teaches a device utilizing in the ear electrodes for detecting EEG signal (Paragraph 0054). The device includes a base part or housing which comprises the communication means and processing unit for analyzing the EEG signal (Paragraph 0050) The ear canal part which includes the electrodes is connected to the base part by a wire (Paragraph 0051; Fig. 3).
U.S. Patent Application Publication No. US 2013/0296731 A1 (Ungstrup) teaches an EEG monitoring device including in the ear electrodes that contact the ear canal of the user and are connected to a behind the ear part by a wire (Paragraph 0060; Fig 3). The behind the ear part includes a housing which encloses a processing unit and wireless communication means for transmitting notifications to an external unit (Paragraphs 0035-0036 and Fig 3)
U.S. Patent Application Publication No. US 2017/0180882 A1 (Lunner) teaches a device with EEG electrodes on a mould surface for insertion into an ear canal. The electrodes are connected by a wire to a behind the ear part (Paragraph 0119; Fig. 5). The behind the ear part includes a housing which encloses processing circuitry and wireless communication circuitry for communicating with a smartphone type device (Paragraphs 0041 and 0150-0152).
In light of the teachings of Laplante-Levesque, Jenson, Eliza, Strickland, Westermann, Ungstrup, and Lunner, it is asserted that each of the claimed elements of the device of claims 22 and 24 and their combination are well-known, routine, and conventional in the art.
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 (the abstract idea). Looking at the limitations of each claim as an ordered combination in conjunction with the claims from which they depend (that is, as a whole) adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer, for example, or improves any other technology. There is no indication that the combination of elements permits automation of specific tasks that previously could not be automated. There is no indication that the combination of elements includes a particular solution to a computer-based problem or a particular way to achieve a desired computer-based outcome. Rather, the collective functions of the claimed invention merely provide conventional computer implementation, i.e., the computer is simply a tool to perform the process.
Claim 25 is not rejected under 35 USC 101 because the addition of a ball joint in combination with the previously established structure of claims 22 and 24 is not considered a routine and conventional construction.
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, 4, 7-9, 13, 22, 24, and 28 are rejected under 35 U.S.C. 103 as being unpatentable over Kidmose US Patent Application Publication Number US 2012/0209101 A1 hereinafter Kidmose in view of Sackellares US Patent Application Publication Number US 2004/0127810 A1 hereinafter Sackellares in view of Snyder US Patent Application Publication Number US 2008/0183096 A1 hereinafter Snyder in view of Mirowski US Patent Application Publication Number US 2011/0218950 A1 hereinafter Mirowski in view of Sobol US Patent Application Publication Number US 2019/0209022 A1 hereinafter Sobol further in view of Su US Patent Application Publication Number US 2019/0209050 A1 hereinafter Su.
Regarding claim 1, Kidmose discloses a method for real-time monitoring and evaluation of a state of a patient with a neurological condition (Paragraph 0020: the user’s brainwaves are utilized to determine a health state), using an auricular device comprising at least one EEG sensor positioned within an ear canal (Abstract; Fig. 2 references 201-205; Paragraphs 0071-0072 and 0094: the ear plug device including at least one electrode for contacting an ear canal), the method comprising:
measuring an EEG signal of the patient (Paragraph 0012: EEG is measured) by the least one EEG sensor positioned within the ear canal (Paragraph 0094: electrodes 601, 603)
processing measured values of the EEG signal using signal amplification, digitization to obtain a conditioned signal specifically adapted for auricular EEG measurement constraints (Paragraph 0094: The analog front end with an amplifier and analog to digital converter. The resultant signal is used by an auricular device and thus the signal is considered to be “specifically adapted” for auricular EEG measurement constraints),
extracting from the conditioned signal a plurality of sets of values (Paragraph 0094: The feature extraction unit reduces the dimensionality of the data while maintaining the relevant information, or indicative parameters. Paragraph 0095: Data, or sets of values, from the feature extraction are sent to the classifier),
selecting at least one classification model (Paragraph 0096: the classifier) and
calculating a risk level of the patient suffering a crisis due to the neurological condition, by applying the at least one classification model, to a corresponding one of the plurality of sets of values (Paragraph 0095: the classification unit is a trained unit trained to interpret how the individual responds to each situation, medical condition, or crisis such as what frequencies can be grouped together for a given patient; Paragraph 0096: the classifier continuously receives data and describes the probability, or risk level, that the signal belongs to a given class)
classifying the state of the patient by classifying, based on comparison of the risk level to a predefined threshold level, and automatically controlling an auricular warning system by transmitting a control signal to initiate a medical event warning when the state of the patient is classified to a certain class (Paragraph 0096: The classifier compares incoming data to a threshold limit of when to take action. The classifier calculates a probability, or risk level, that the signals received are of a certain class. The classifier issues a warning when a certain number of samples indicate a medical event within a certain timeframe. Paragraph 0097: the system warns of a medical event), and
transmitting a signal (Paragraph 0093: wireless connecting means to a portable surveillance device) indicative of the classification of the state of the patient according to an outcome of the classifying (Paragraph 0030: When the user’s health state is determined to be developing in an undesired way, a warning may be transmitted or the health data may be transmitted to a monitoring device; Paragraph 0097) of the at least one of the plurality of time segments.
Kidmose fails to further disclose the method comprising; processing the measured values of the EEG includes conditioning for filtering electrical interferences, atypical values and independent source signal; performing EEG time segmentation to obtain a plurality of overlapping time segments of the EEG signal, wherein the overlapping time segments have an overlap window; each of the plurality of sets of values being extracted from a different one of the plurality overlapping of time segments, wherein the plurality of sets of values are patient-specifically selected through Neighborhood Component Analysis applied to descriptive parameters obtained from previous EEG data of the same patient to identify parameters exhibiting highest correlation with the patient’s neurological states; selecting at least one classification model from the group consisting of SVM, LSBoost, Random Forest, KNN, Neural Networks, Naive Bayes, Gaussian process and ANN; selecting internal configuration parameters of the classification model based on a grid-search technique; calculating for each of the plurality of overlapping time segments a risk level, the classification model being applied with the internal configuration parameters; the classification being performed on at least one of the plurality of overlapping time segments and being either a preictal state or a non-preictal state, the control signal being transmitted when at least one of the overlapping time segments is classified as preictal
Sackellares teaches a system for characterizing the behavior of a chaotic, multi-dimensional system by measuring a number of signals associated with the system and generating therefrom, a spatio-temporal response based on each signal. Multiple dynamic profiles are generated for each response. Each profile corresponds to a different dynamic parameter. The parameters are compared over a time period to determine if a certain level of entrainment exists which can be used to predict seizures (Abstract). Thus, Sackellares falls within the same field of endeavor as the applicant’s invention.
Sackellares teaches a method comprising processing the measured values of the EEG includes conditioning for filtering electrical interferences, atypical values and independent source signals (Fig. 3 step 305; Paragraph 0045: The acquired EEG data is then pre-processed which includes digitization, filtering and amplification. Filtering is considered to render the limitation of “conditioning” as obvious because it would seem that “conditioning” is carried out by filtering data); performing EEG time segmentation to obtain a plurality of overlapping time segments of the EEG signal, wherein the overlapping time segments have an overlap window (Paragraphs 0045-0047: The system evaluates the incoming EEG signals in parallel over given time windows, which may be overlapping or non-overlapping, to produce the dynamic profiles for each signal); each of the plurality of sets of values being extracted from a different one of the plurality overlapping of time segments (Paragraph 0047: the dynamic profiles may be generated for each time window which includes overlapping or sliding time windows), wherein the plurality of sets of values are patient-specifically selected applied to descriptive parameters obtained from previous EEG data of the same patient to identify parameters exhibiting highest correlation with the patient’s neurological states (Paragraphs 0045-0047 and 0054-0056: The dynamic profiles are generated during an initialization period for each new patient and then the best dynamic profile, or plurality of sets of values, are used for future processing); performing calculations and classifications for each of the plurality of overlapping time segments (Paragraphs 0045-0047 and 0054-0056: the dynamic profiles are generated for each window. Thus the subsequent calculations and classifications are also performed for each window); and the classification being either a preictal state or a non-preictal state (Paragraph 0054 and 0056: the algorithm may detect a number of states including pre-ictal and non-preictal), the control signal being transmitted when at least one of the overlapping time segments is classified as preictal (Paragraph 0057: the algorithm determines when conditions reflect entrainment transition, or determines the users state, and may issue an impending seizure warning (ISW))
It would have been obvious to one of ordinary skill in the art prior to the effective filling date of the invention to incorporate the processing of EEG signals from epochs and selection of the most sensitive index profiles as taught by Sackellares into the system of Kidmose because processing sampled signals in given timeframes may be less computationally intense than the continuous processing of Kidmose and utilizing the X2 index profiles of Sackellares as the features extracted from the signal may improve the sensitivity of the system since Sackellares describes how these profiles are the parameters that allow for the most sensitive detection of medical events (Sackellares: Paragraph 0054) Furthermore, it would be obvious to one of ordinary skill in the art to alter the system of Kidmose in view of Sackellares to subsequently perform each of the extraction, calculation, and classification steps using the sampled epochs and subsequent X2 index profiles of Sackellares rather than the continuous signal of Kidmose because the reduced number of samples would save processing power while still allowing classification of seizure, or medical event, states. Finally, it would be obvious to one of ordinary skill in the art to classify the calculated data as being indicative of a preictal of non-preictal state because Kidmose already classifies the data as being indicative or non-indicative of a medical event and contemplates the device being used for seizure detection (Kidmose: Paragraph 0020: detecting the onset of epileptic seizure) and Sackellares teaches several states of interest in regards to seizures, a medical event, including ictal and preictal and inter-ictal which are each distinguished from “normal” states (Sackellares: paragraphs 0040 and 0054).
Kidmose in view of Sackellares fails to further teach the method where the plurality of sets of values are selected using Neighborhood Component Analysis; selecting at least one classification model from the group consisting of SVM, LSBoost, Random Forest, KNN, Neural Networks, Naive Bayes, Gaussian process and ANN; selecting internal configuration parameters of the classification model based on the a grid-search technique, and the classification model being applied with the internal configuration parameters,
Snyder teaches a method for monitoring a subject’s neurological condition. The system analyses a neurological signal from a subject to determine the condition of the subject and provides an indication of the subject’s condition (Abstract). Thus, Snyder falls within the same field of endeavor as the applicant’s invention.
Snyder teaches that the classifiers utilized may be KNN, binary and higher order space partitions, linear or non-linear regression, Bayesian, mixture models based on Gaussians or other basis functions, neural networks, and support vector machines ("SVM") (Paragraph 0065),
It would have been obvious to one of ordinary skill in the art prior to the effective filling date of the invention to incorporate one of the classifiers utilized by Snyder into the method of Kidmose in view of Sackellares because Snyder shows they are appropriate classifiers to use in the identification of patient seizure states and thus it is a simple substitution of one known element for another.
Kidmose in view of Sackellares further in view of Snyder fails to further teach the method where the plurality of sets of values are selected using Neighborhood Component Analysis; selecting internal configuration parameters of the classification model based on the a grid-search technique, and the classification model being applied with the internal configuration parameters,
Mirowski teaches a method for receiving physiological data for the subject, extracting one or more patterns of features from the physiological data, and classifying the at least one state of the subject using a spatial structure and a temporal structure of the one or more patterns of features, wherein at least one of the at least one state is an ictal state (Abstract). Thus Mirowski falls within the same field of endeavor as Applicant’s invention.
Mirowski teaches a method which utilizes classification algorithm to classify a state of a subject based on EEG features. The classification algorithm may distinguish normal states from preictal and interictal states. Mirowski teaches that the classification algorithm may be one of three different types of classification algorithms (Paragraph 0075). A first classification algorithm is based on logistic regression and is parameterized by weights and biases which serve to optimize a loss function (Paragraph 0076). A second classification algorithm may be built on convolutional networks designed to extract and classify high-dimensional patterns from multivariate time series. The layers of the network may be trained simultaneously using back-propagation learning algorithms. The convolutional network classifier may have a number of different layers which perform different functions (Paragraphs 0077-0079). The third type of classification model may be a support vector machine which serves as a pattern matching-based classifier which compares an input pattern to a set of support vectors using kernel functions and a decision function which may be a weighted combination of kernel functions (Paragraphs 0080-0082). The different classification algorithms are tested to determine which inputs result in the highest sensitivity for each type of classification algorithm (Paragraph 0083)
It would have been obvious to one of ordinary skill in the art prior to the effective filling date of the invention to implement the different internal configurations for different types of classification algorithms as taught by Mirowski into the method of Kidmose in view of Sackellares further in view of Snyder because the different types of classification algorithms and their respective internal configuration parameters can each be tested to determine which produces the most accurate results given the extracted indicative parameters of Kidmose in view of Sackellares further in view of Snyder. The classification algorithm and its corresponding internal configuration parameters may then be selected based on the most desirable accuracy and/or sensitivity. This may result in better patient outcomes since some types of classification algorithms may be more effective than others for a given patient (Mirowski: paragraph 0084).
Kidmose in view of Sackellares in view of Snyder further in view of Mirowski fails to further teach the method where the plurality of sets of values are selected using Neighborhood Component Analysis; and selecting internal configuration parameters of the classification model based on the a grid-search technique.
Sobol teaches a wearable electronic device. The device includes a hybrid wireless communication module with wireless communication sub-modules to selectively acquire location data from both indoor and outdoor sources, as well as a wireless communication sub-module to selectively transmit an LPWAN signal to provide location information based on the acquired data. The device may also include one or more sensors to collect one or more of environmental data, activity data and physiological data. The device may transmit some or all of its acquired data to a larger system, including a cloud-based server to, in addition to providing location-based data, be used as a part of a predictive health care protocol to correlate changes in acquired data to salient indicators of the health of a wearer of the device. In one form, the predictive health care protocol uses a machine learning model (Abstract). Thus, Sobol is reasonably pertinent to the problem at hand.
Sobol teaches that there are a plurality of ways to reduce the dimensionality of received data especially by extracting highly correlated features from the total amount of data. The reduction of data dimensionality may be part of, a predecessor to, or both part of and a predecessor to feature selection which involves finding a subset of the original variables that contain accurate, relevant input data. Examples of methods to perform these processes include neighborhood component analysis, regularization, sequential feature selection, stepwise regression or the like (Paragraph 0233). It is noted that while Sobol is not directed towards the processing of EEG data, its teachings of feature selections are applicable to virtually any type of data processing.
It would have been obvious to one of ordinary skill in the art prior to the effective filling date of the invention to utilize neighborhood component analysis (NCA) to reduce the dimensionality of data and perform feature selection as taught by Sobol into the method of Kidmose in view of Sackellares in view of Snyder further in view of Mirowski as a method to determine the plurality of sets of values to utilize because Sobol teaches that NCA is effective at reducing data dimensionality and finding a subset of the original variables that contain accurate, relevant input data (Sobol: Paragraph 0233). Thus utilizing NCA to carry out the feature selection, or dynamic profile selection, of Kidmose in view of Sackellares in view of Snyder further in view of Mirowski would allow the system to reduce data processing requirements and may further be a simple substitution of one known feature selection method for another.
Kidmose in view of Sackellares in view of Snyder in view of Mirowski further in view of Sobol fails to further teach the method including selecting internal configuration parameters of the classification model based on a grid-search technique.
Su teaches system and method directed towards a wearable device and a method of its operation (Abstract; Paragraph 0002). Thus, Su is reasonably pertinent to the problem at hand.
Su teaches that the optimal configuration parameters for classification models including an SVM classification model may be determined by using a cross-validation based grid search method which searches different combinations of parameters and selects the combination that produces the highest accuracy as the optimal set of parameters (Paragraph 0123). It is noted that while Su is not directed towards the processing of EEG data, its teachings of classifier parameter selection are applicable to virtually any type of classifier usage.
It would have been obvious to one of ordinary skill in the art prior to the effective filling date of the invention to utilize the grid-search method of internal parameter selection as taught by Su in the method of Kidmose in view of Sackellares in view of Snyder in view of Mirowski further in view of Sobol to select the internal configuration parameters of the classifier because Su teaches that this method of parameter selection allows for the determination of the parameters with the highest accuracy (Su: paragraph 0123) which may improve classifier performance.
It is noted that Kidmose in view of Sackellares in view of Snyder in view of Mirowski in view of Sobol further in view of Su (hereinafter modified Kidmose) teaches the processing of values extracted from signals in EEG time windows. All dependent claims are rejected with the understanding that the above presented rejection of claim 1 describes how modified Kidmose teaches the signal processing being performed on values from these time windows.
Regarding claim 2, modified Kidmose teaches the method according to claim 1. Modified Kidmose fails to further disclose the method characterized in that the at least one mathematical classification model comprising more than one mathematical classification model each of which is applied to a respective one of the plurality of sets of values of each of the plurality of time segments and risk levels calculated respective of each of the at least one mathematical classification model are weighted with previously selected factors of the indicative parameters corresponding to weights so as to obtain a weighted value of the risk level for each of the plurality of time segment.
Snyder teaches that EEG signals are gathered and sent to feature extractors which extract desired characteristics from the signal (Paragraph 0063). The extracted characteristics are sent to one or more classifiers which analyze the data either alone or in combination. The classifiers may provide a variety of outputs such as a logical result or a weighted result. The classifiers may be customized for a given individual and are trained by exposing them to training measurement vectors (Paragraph 0065). Thus, the weights for the different models may be preset by the training.
It would have been obvious to one of ordinary skill in the art prior to the effective filling date of the invention to incorporate the one or more classifiers outputting a weighted result as taught by Snyder into the method of modified Kidmose because the use of multiple classifiers rather than a single classifier allows the system greater flexibility and accuracy since a single classifier may struggle to recognize certain scenarios which can be easily identified by another.
Regarding claim 4, modified Kidmose teaches the method according to claim 1. Modified Kidmose fails to further disclose the method wherein the overlap window is between 20% and 60%.
Sackellares teaches a system for analyzing EEG signals. The system evaluates the incoming EEG signals in parallel over given time windows called epochs (Paragraph 0045). epochs may be overlapping or non- overlapping, to produce dynamic profiles for each signal (Paragraph 0064).
It would have been obvious to one of ordinary skill in the art prior to the effective filling date of the invention to incorporate the processing of EEG signals from overlapping time windows as taught by Sackellares into the method of modified Kidmose because processing signals in overlapping time periods ensures that events occurring at the start or end of one time period are not missed since another time period will encompass them. Furthermore, it would have been obvious to one of ordinary skill in the art to overlap the time windows between 20% to 60% of the time because the degree of overlap utilized is mere optimization of the system that depends upon user preference, desired completeness of the data, and computational limitations.
Regarding claims 7-9, modified Kidmose teaches the method according to claim 1. Modified Kidmose further suggests the method wherein a warning signal is transmitted when 2 or more of the plurality of time segments are classified as preictal consecutively, a group of between 3 to 30 consecutive segments from the plurality of time segments, 3 or more time segments are classified as preictal, and/or a single one of the plurality of time segments is classified as preictal.
It is noted that the detection of the time segments as being indicative of a preictal state is taught by the system of Kidmose in view of Sackellares further in view of Mirowski as explained above in the rejection of claim 1. Kidmose further suggests that a warning signal is transmitted to the patient when a number of time segments are classified as preictal in a given timeframe in paragraph 0096 which indicates that a warning will be sent out after a number of samples indicating the situation within a given timeframe are detected. Thus, the number of samples may be two in a given timeframe of two sampling periods, 3 in a timeframe of 3 to 30, or one sample in a time frame of one time period. The exact number of samples indicating a preictal space and the given timeframe in which they must appear is a matter of routine optimization and experimentation that depends upon user preference, desired completeness of the data, and computational limitations.
Regarding claim 13, modified Kidmose teaches the method according to claim 1. Modified Kidmose further discloses the method wherein the at least one EEG sensor comprising more than one EEG sensor each of which measures the EEG signal of the patient (Paragraph 0094: electrodes 601 and 603) and wherein the processing, extracting and calculating are performed for each of the at least one EEG sensor (Paragraphs 0094-0096: the recited steps of claim 1 are performed on the incoming EEG signal) and the classifying is performed for plurality of sets of values extracted for each of the at least one EEG sensor (Paragraph 0095: the data from the feature extraction unit is sent to the classifier)
Regarding claim 22, modified Kidmose teaches the method according to claim 1. Modified Kidmose further discloses a device for real-time monitoring and evaluation of a state of a patient with a neurological condition (Abstract: an ear plug, or device; See the 35 USC 103 rejection of claim 1 for capability of carrying out said method) the device comprises:
at least one EEG sensor located in an intra-auricular body and configured for being in direct contact with an inside of an ear of the patient for measuring an EEG signal (Fig. 2 References 201-205; Paragraphs 0071-0072), and
an electronics board in electrical contact with the at least one EEG sensor, and configured for carrying out the method according to claim 1 (Kidmose in view of Sackellares further in view of Mirowski as described in the above rejection of claim 1) including at least one processing unit (Fig. 1 References 101-103; Paragraphs 0068-0070: The ear plug 103 transmits electrical signals via the connecting means 102 to the BTE-component 101 for further processing. The processor is inherently taught by the limitation of “further processing”) and one wireless communication unit configured for communicating with a smartphone-type portable device (Paragraph 0093: the wireless connecting means for connecting to external units and other signal processing means).
Regarding claim 24, modified Kidmose teaches the device according to claim 22. Modified Kidmose further discloses the device further comprises a shell housing the electronics board (Fig. 1 Reference 101; Paragraphs 0068-0070: signals are transmitted to the BTE- component 101 for further processing. The processor is inherently taught by the limitation of “further processing”), and a flexible body attaching the shell to the intra-auricular body, said flexible body integrating therein connection cables between the electronics board and the at least one EEG sensor (Fig. 1 References 101-103; Paragraphs 0068-0070: the connecting means 102 attaches the shell 101 to the intra-auricular body 103; Paragraph 0033: the connecting means comprise conductive wiring. The limitation of “flexible” is relative and thus any material may be sufficiently flexible to satisfy this limitation).
Regarding claims 3 and 28, modified Kidmose teaches the device according to claim 1. Modified Kidmose fails to further disclose the method wherein the plurality of indicative parameters further comprise at least one member from the group consisting of: Band energy ratio; Entropy; Mutual information; Katz fractal dimension; Kolmogorov complexity; Means and medians; Spectral kurtosis; Spectral skewness; Cross-correlation; Weighted phase lag index; Spectral coherence; Imaginary coherence; and Correlation matrix
Sackellares teaches a method wherein one of the dynamical parameters, or indicative parameters, may include entropy or other chaoticity measures (Paragraphs 0037 and 0076).
It would have been obvious to one of ordinary skill in the art prior to the effective filling date of the invention to incorporate entropy as an indicative parameter as taught by Sackellares into the method of modified Kidmose because Sackellares teaches that entropy has been shown to be a critical summary statistic and is widely used in distinguishing normal and abnormal medical time series data (Sackellares: Paragraph 0076) and thus may be an effective indicative parameter for the method to utilize.
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over modified Kidmose as applied to claim 7 above and further in view of Dracup US Patent Application publication Number US 2013/0060167 A1 hereinafter Dracup.
Regarding claims 10, modified Kidmose teaches the method according to claim 7. Modified Kidmose fails to further disclose the method wherein following an elapsed time of between 10 to 30 of the plurality of time segments after transmitting the warning signal, a query is transmitted to confirm if the patient has suffered the crisis.
Dracup teaches a method for predicting and detecting seizures and other events. The method may be incorporated in conjunction with a mobile device which may alert and communicate health information to various parties (Abstract). Thus, Dracup falls within the same field of endeavor as the applicant’s invention.
Dracup teaches a method for abnormal motion detection wherein an electromyogram measuring unit periodically measures a muscle tension through two sensors (Paragraph 0043). When the system detects muscle tension that is greater thana predetermined value and there is body position frequency change that increases fora predetermined time interval, the system will issue a warning to the user and/or emergency services (Paragraph 0045). The method may further include querying the user about a seizure status or cause and recording a response to the query to create a user log of historical seizure data. The query may be sent at any suitable sequence in the method (Paragraph 0046)
It would have been obvious to one of ordinary skill in the art prior to the effective filling date of the invention to incorporate the user querying of Dracup into the method of modified Kidmose because the collected data may be used to further train the classification algorithms or create a historical log of their accuracy. Furthermore, it would have been obvious to one of ordinary skill in the art to optimize the method of modified Kidmose further in view of Dracup to send the query after 10 to 30 time segments have passed since the timing of the query is merely an optimization of the method that depends upon user preference, desired completeness of the data, and computational limitations.
Claim 25 is rejected under 35 U.S.C. 103 as being unpatentable over modified Kidmose as applied to claim 24 above and further in view of JP1 Japanese Patent Application publication Number JP 2018-527997 A hereinafter JP1
Regarding claim 25, modified Kidmose teaches the method according to claim 24. Modified Kidmose further discloses the device wherein an attachment between the intra-auricular body and the flexible body allows electrical contact between the at least one EEG sensor and cables coming from the electronics board (Paragraph 0068 -0070: the ear plug is connected to the BTE component by the connecting means and the brainwave signals detected by the electrodes on the ear plug are transmitted to the BTE for further processing. Thus, the interface between the intra-auricular body, or ear plug, and the flexible body, or connecting means, must allow for electrical contact between the sensors and processor since the electrical signals are communicated from the ear plug to the BTE for further processing)
Modified Kidmose fails to further disclose the device characterized in that the attachment between the intra-auricular body and the flexible body comprises a ball joint allowing rotation and spherical movement with respect to one another.
JP1 teaches a medical device for imaging the ear canal including a flexible extension into the ear canal for positioning the device and allowing imaging access (Page 43 Paragraph 6). Thus, JP1 falls within the same field of endeavor as the applicant’s invention.
JP1 teaches that the structure of the extension of the device may incorporate joints to allow the structure to better conform to the ear. These joints include ball joints which allows movement in any direction and allows deflection by differently shaped anatomical structures (Page 44 Paragraph 3).
It would have been obvious to one of ordinary skill in the art prior to the effective filling date of the invention to incorporate the ball joint as taught by JP1 into the system of modified Kidmose because the ball joint of JP1 could allow for more degrees of freedom and thus more adaptability to conform to different anatomical structures for the interface between the ear plug and connecting means of Kidmose.
Claim 29 is rejected under 35 U.S.C. 103 as being unpatentable over modified Kidmose as applied to claim 1 above and further in view of Coleman US Patent Application Publication Number US 2019/0113973 Al hereinafter Coleman
Regarding claim 29, modified Kidmose teaches the method according to claim 1. Modified Kidmose fails to further discloses the method wherein the method of selecting parameters comprises at least one member from the group consisting of: Neighborhood Component Analysis, Stepwise Regression, Relief-Fand Laplacian Score.
Coleman teaches a computer network implemented system for improving the operation of one or more biofeedback computer systems. The system includes an intelligent bio-signal processing system that is operable to: capture bio-signal data; and analyze the bio-signal data, so as to: extract one or more features related to at least one individual interacting with the biofeedback computer system; classify the individual based on the features by establishing one or more brain wave interaction profiles for the individual for improving the interaction of the individual with the one or more biofeedback computer systems, and initiate the storage of the brain waive interaction profiles to a database; and access one or more machine learning components or processes for further improving the interaction of the individual with the one or more biofeedback computer systems by updating automatically the brain wave interaction profiles based on detecting one or more defined interactions between the individual and the one or more of the biofeedback computer systems (Abstract). Thus, Coleman is reasonably pertinent to the problem at hand.
Coleman teaches a system and method for collecting EEG data from a patient (Paragraph 0053). The EEG data is then processed and classified either in real-time or after recording and storing the patient data (Paragraphs 0131-0133). The analysis of the EEG data involves feature extraction and the selection of these features may be performed using advanced methods in order to yield highly discriminative features the yield much better machine learning performance through greater separability (Paragraph 0135). One potential feature selection method includes stepwise regression (Paragraph 0137).
It would have been obvious to one of ordinary skill in the art prior to the effective filling date of the invention to implement the feature selection method of Coleman into the method of modified Kidmose because Coleman teaches that performing advanced feature selection methods such as stepwise regression can yield highly discriminative features that yield much better machine learning performance (Coleman: Paragraph 0135)
Claim 20 is not presently rejected over the prior art but it nonetheless rejected under 35 USC 1112 and 101 as described above.
Response to Arguments
In regards to the rejections presented under 35 USC 112:
Applicant’s amendments have overcome some of the previously presented grounds of rejection but necessitated new grounds of rejection.
In regards to the rejections presented under 35 USC 101:
Applicant argues that the amended language of the auricular device with at least one electrode positioned within an ear canal integrates the abstract idea into a practical application by incorporating unconventional hardware placement.
This argument is not found to be persuasive because, as indicated in the above presented 35 USC 101 rejection, the auricular device is only limited by the electrode placed in the user’s ear and comprises no additional structure. Furthermore, electrodes being placed in a user’s ear is a well-known electrodes placement.
Applicant’s arguments directed towards the technical challenges of single channel measurement are not found to be persuasive because they are not commensurate in scope with the claimed invention.
Applicant argues that the use of neighborhood component analysis (NCA) to select descriptive parameters and the use of grid search optimization to select configuration parameters employs specific technological methodology for personalized optimization. This argument is not found to be persuasive because NCA is a well-known method of dimensionality reduction and feature selection and grid-search optimization is another well-known method of brute force parameter selection by trying all possible combinations of parameters and selecting the best one. Additionally, these steps are part of the abstract idea itself as a human mind may perform these processes.
Applicant argues that the recitation drawn towards automatic control of an auricular warning system implements the abstract idea into a practical application by showing active control of specific technological systems. This argument is not found to be persuasive because the auricular warning system is not defined and the control of such a system is merely transmitting a signal which is not considered to constitute active control of specific technological systems.
Applicant argues that the abstract idea is integrated into a practical application by addressing a specific technological problem. This argument is not found to be persuasive because Applicant’s characterization of prior art system do not reflect the state of the art. Non-invasive seizure detection systems such as Sackellares, are known and in the ear device which may be used for seizure detection are explicitly contemplated by Kidmose.
Applicant argues that the abstract idea is incorporated into a practical application by specifically improving computer capabilities. This argument is not found to be persuasive because the claimed system does not improve the functionality of a computer. Rather the computer is merely adapted to a particular use.
Applicant argues that the abstract idea is incorporated into a practical application by actively controlling specific technology. This argument is not found to be persuasive because, as described above, the auricular warning system itself id not described and the automatic control is the mere transmittal of a signal.
Applicant argues that the abstract idea is incorporated into a practical application by applying more than a natural law or abstract idea using conventional elements. This argument is not found to be persuasive because each element of the system is routine, conventional, or well-known as described and evidenced in the above presented 35 USC 101 rejection. The placement of electrodes in a user’s ear is a well-known placement.
Applicant argues that the abstract idea is incorporated into a practical application by being analogous to Example 46 which applicant claims is drawn towards database management and shows that specific technological adaptations for particular hardware constraints constitute practical applications. This argument is not found to be persuasive because there are no particular hardware constraints imposed on the system. In particular the electrode in the ear and the controller may be any generic electrode and any type of controller. The claimed system does not limit itself to specific memory, power, or processing usages.
Applicant asserts that Examiner’s reliance on Electric Power Group and Alice Corp is misplaced because the amended claims operate on unconventional hardware with specific technological constraints. This argument is not found to be persuasive because the hardware of the claimed system is not considered to be unconventional as described above.
Applicant argues that the abstract idea is incorporated into a practical application by the use of an electrode specifically placed in the ear canal, patient-specific NCA, grid-search optimization, and single channel processing which creates an unconventional technological approach. This argument is not found to be persuasive because the placement of the electrode, feature selection using NCA and parameter selection using grid-search optimization are all known in the art. Additionally the claims are not limited to single channel measurement.
Applicant’s arguments directed towards single-channel constraints are not found to be persuasive because they are not commensurate in scope with the claimed invention.
Applicant argues that the cited references to illustrate what is known in the art in the above presented 35 USC 101 rejection do not defeat the claimed invention because these reference do not teach the specific technological integration claimed including the patient specific NCA and grid search technique. This argument is not found to be persuasive because the cited references serve to illustrate that the claimed hardware is well known and thus the abstract idea implemented thereon does not qualify as significantly more than the abstract idea itself. The patient specific NCA and grid search are part of the abstract idea itself and there are no particular hardware constraints for the implementation of the abstract idea which would preclude it from being incorporated on the cited systems.
Applicant argues that the present invention overcomes significant problems in the prior art and is thus a practical application by being non-invasive and not requiring specialized surgeries. These arguments are not found to be persuasive because they misconstrue what is taught by the prior art. Non-invasive seizure monitoring devices are known in the art as evidenced by at least Sackellares above.
In regards to the rejections presented under 35 USC 103:
Applicant’s arguments have been fully considered but are not found to be persuasive because they are not commensurate in scope with the claimed invention.
In particular, Applicant argues that Kidmose nor Sackellares teaches patient-specific parameter selection optimized for a single channel auricular EEG measurement.
This argument is not found to be persuasive because the claimed method and system are not limited to a single channel EEG measurement. Claim 1 recites “at least one EEG sensor” and claim 13 further expands the number of sensors to more than one. There are no limitations limiting the claimed system or method to a single channel of EEG measurement. Kidmose teaches the use of auricular EEG measurements and Sackellares teaches how EEG measurements may be processed and further teaches patient-specific feature selection.
Applicant’s arguments directed towards the use of Neighborhood component analysis and grid-search optimization have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Applicant argues that each of Kidmose, Sackellares and Mirowski address fundamentally different technical problems and that the Examiner’s combination of these references fails KSR’s requirements for proper motivation because the references address fundamentally incompatible technical approaches. In particular, Applicant argues that Sackellares is directed towards multi-channel intracranial EEG systems required multiple electrode arrays and requires that multiple channels be used for accurate analysis.
This argument is not found to be persuasive because Sackellares is not limited to intracranial EEG placements and explicitly recites that surface electrodes may be used and that the particular placement locations are dependent upon the patient and the particular application (Sackellares: paragraph 0058: “Electrode placement may include, for example, surface locations, wherein an electrode is placed directly on a patient's scalp. Alternatively, subdural electrode arrays and/or depth electrodes are sometimes employed when it is necessary to obtain signals from intracranial locations. One skilled in the art will appreciate; however, that the specific placement of the electrodes will depend upon the patient, as well as the application for which the signals are being recorded”). Applicant cites paragraphs 0045-0047 to support Applicant’s assertion that Sackellares requires multiple channels but no such recitation appears to be present. Instead, paragraphs 0045-0047 appear to describe how the recites processing method of Sackellares is applied to each single EEG channel which corresponds to a single electrode. Thus it would seem that the processing methods of Sackellares are well suited for single channel usages but the present claims are not limited to such usages.
Applicant argues that Kidmose is directed towards portable health monitoring rather than complex seizure prediction.
This argument is not found to be persuasive because seizure prediction is one of several explicitly contemplates uses of Kidmose (Kidmose: paragraph 0020: “an example of such a use of brain wave measurements, namely to detect onsets of epileptic seizures”)
In response to applicant's argument that the examiner's conclusion of obviousness is based upon improper hindsight reasoning, it must be recognized that any judgment on obviousness is in a sense necessarily a reconstruction based upon hindsight reasoning. But so long as it takes into account only knowledge which was within the level of ordinary skill at the time the claimed invention was made, and does not include knowledge gleaned only from the applicant's disclosure, such a reconstruction is proper. See In re McLaughlin, 443 F.2d 1392, 170 USPQ 209 (CCPA 1971).
Applicant’s arguments further directed towards the use of multiple channels have been considered but are not found to be persuasive because they are not commensurate in scope with the claimed invention.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MATTHEW ERIC OGLES whose telephone number is (571)272-7313. The examiner can normally be reached M-F 8:00AM - 5:30PM.
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 on Monday-Friday from 9:00AM – 4:00PM at (571) 272 – 7540. 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.
/MATTHEW ERIC OGLES/ Examiner, Art Unit 3791
/JASON M SIMS/Supervisory Patent Examiner, Art Unit 3791