DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 08 July 2026 has been entered.
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, 6-13, and 15-19 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, it is unclear if two separate cross-frequency coupling method steps are performed as the claim first recites determining a characteristic value from C3/C4 data using a cross-frequency coupling method in lines 5-8, and then again in the “automatically evaluating” limitation. For this examination, the claim is being interpreted such that one cross-frequency coupling method is performed on C3/C4 data, the C3/C4 data being the measured and recorded brain electrical activity data.
Further regarding claim 1, the phrase “at least one measuring of the C3/C4 data brain electrical activity data by electroencephalography” renders the claim indefinite. For this examination, the phrase is being interpreted as “at least one measuring of the C3/C4 data of the EEG signal of the electroencephalography”.
Further regarding claim 1, the phrase “and recording of the C3/C4 data brain electrical activity data” renders the claim indefinite. For this examination, the phrase is being interpreted as “recording of the C3/C4 data of the EEG signal of the electroencephalography”.
Further regarding claim 1, the phrase “wherein said data blocks include brain electrical activity in the form C3/C4 data of EEG signals from the electroencephalography” renders the claim indefinite. It is unclear to what “brain electrical activity in the form C3/C4 data of EEG signals” is referring. For this examination, the claim is being interpreted such that the data blocks include the C3/C4 data of the EEG signal of the electroencephalography.
Further regarding claim 1, it is unclear if each evaluated data block is assigned to a sleep stage, or if all predetermined data blocks are assigned to a single sleep stage. Clarification is requested. For examination purposes, both interpretations are being applied.
Claims not explicitly rejected above are rejected due to their dependence on a rejected base claim.
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 1, 6, 9, and 15-17 are rejected under 35 U.S.C. 103 as being unpatentable over Sanders et al. (Sleep Stage Classification… – previously cited) in view of Gouveris et al. (Sleep Stage Classification Using Spectral Analyses… – previously cited).
Regarding claims 1 and 15, Sanders et al. discloses a method for classifying a polysomnography (PSG) recording into sleep stages (see TITLE), the method comprising the following steps: classifying the sleep of a human being into a grid with different sleep stages (II. METHODS); providing a characteristic value for a sleep stage (II. METHODS C. Cross-frequency-coupling method); collecting a plurality of information regarding bodily functions over a predetermined period of time in the form of data, wherein collecting the plurality of information comprises at least one measuring of brain electrical activity data by electroencephalography (EEG) and recording the brain electrical activity data with EEG measuring sensors over the predetermined period of time during sleep of the human being (II. METHODS – as EEG data is acquired over an approximately 8hr period [II. METHODS D. Classification], a plurality of information/EEG data points is collected); subdividing the collected data into time-dependent data blocks (II. METHODS - 30 second epoch windows); selecting a predetermined number of data blocks from the data blocks, wherein said data blocks include data on the electrical activity of the brain in the form of EEG signals; automatically evaluating the brain electrical activity data in each selected data block using a cross-frequency coupling method that determines the characteristic value that allows assignment to a sleep stage defined by the characteristic value, wherein the cross-frequency coupling method is applied to theta and gamma waves or to delta and alpha waves of the EEG signals (II. METHODS C. Cross-frequency-coupling method, and see Figure 3 and description thereof); and automatically assigning the evaluated data blocks to a sleep stage based on the characteristic value (II. METHODS C. Cross-frequency-coupling method and D. Classification). Official notice is being taken that it is well known in the art that EEG signals are acquired from brain electrical activity data on the skin of a skull surface of a human being using EEG sensors (see, for example, section [0005] of Huiku’338 – US Pub No. 2005/0182338 – previously cited, and sections [0003-0004] of Lapinlampi et al.’753 – US Pub No. 2008/0009753 – previously cited).
Sanders et al. discloses all of the elements of the current invention, as discussed above, except for the EEG data including C3/C4 EEG data. Gouveris et al. teaches performing sleep stage classification by analyzing EEG signals collected from the C3/C4 EEG electrode positions (Materials and Methods). It would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to have included collecting EEG data from C3/C4 EEG electrode positions in the method of Sanders et al., as Gouveris et al. teaches that signals from those locations can be used to perform sleep stage classification. The modification to Sanders et al. would merely be combining prior art elements according to known methods to yield predictable results. In the combination of Sanders et al. in view of Gouveris et al., the cross-frequency coupling method would be performed on EEG data including C3/C4 data, and the characteristic value would be determined using the cross-frequency coupling method results obtained from the C3/C4 data.
Regarding claim 6, Sanders et al. discloses that the cross-frequency coupling method comprises a phase-amplitude coupling (II. METHODS C. Cross-frequency-coupling method).
Regarding claims 9, 16, and 17, Sanders et al. discloses that the collected data are subdivided into defined time intervals (II. METHODS A. Average spectral power method and II. METHODS C. Cross-frequency-coupling method: 30 second epoch windows).
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Sanders et al. in view of Gouveris et al., as applied to claim 1, further in view of Low et al.’095 (US Pub No. 2007/0016095 – previously cited).
Sanders et al. in view of Gouveris et al. discloses that the selected data blocks (which includes some of the selected data blocks) are transmitted as training data blocks to a linear discriminant analysis (LDA) classifier for creating a classification in the LDA classifier, and that at least a portion of the data blocks not selected as training blocks are transmitted to the LDA classifier and automatically classified into the known sleep stages (II. METHODS D. Classification, and see Figure 4 and description thereof of Sanders et al.).
Sanders et al. in view of Gouveris et al. discloses all of the elements of the current invention, as discussed above and in paragraph 6 above, except for the classifier being a support vector machine. Low et al.’095 teaches that sleep stage classification based on EEG signals can be performed using either LDA classifiers or support vector machines (section [0164]). 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 Sanders et al. in view of Gouveris et al. by substituting a support vector machine for the LDA classifier as it would merely be the simple substitution of one known classification means for another to obtain predictable results.
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Sanders et al. in view of Gouveris et al. further in view of Low et al.’095, as applied to claim 7, further in view of Banerjee et al.’444 (US Pub No. 2018/0228444 – previously cited).
Sanders et al. in view of Gouveris et al. further in view of Low et al.’095 discloses all of the elements of the current invention, as discussed in paragraph 7 above, except for the support vector machine comprising an algorithm that uses a non-linear basis kernel function. Banerjee et al.’444 teaches that support vector machines comprising an algorithm that uses a non-linear basis kernel function produce optimum classification performance (section [0032]). 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 support vector machine of Sanders et al. in view of in view of Gouveris et al. further in view of Low et al.’095 such that it comprises an algorithm that uses a non-linear basis kernel function, as Banerjee et al.’444 teaches that this would produce optimum classification performance.
Claims 10-13 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Sanders et al. in view of Gouveris et al., as applied to claim 1, further in view of Kayyali et al.’399 (USPN 10,426,399 – previously cited).
Regarding claims 10 and 19, Sanders et al. in view of Gouveris et al. discloses all of the elements of the current invention, as discussed in paragraph 6 above, except for measuring and recording additional data on the following bodily functions during the predetermined period of time: cardiac activity, airflow of nasal and/or oral respiration, respiratory excursion of the thorax and abdomen, respiratory sounds, eye movement patterns, and electrical muscle activity in the chin region and on the lower leg, wherein the data is preferably collected by means of the following measuring methods or measuring devices: electrocardiography, microphone, air flow meter, electromyography electrodes.
Kayyali et al.’399 teaches a method for conducting sleep analysis, wherein the sleep analysis not only includes collecting, recording, and analyzing EEG data, but also, at the same time, data pertaining to: cardiac activity, airflow of nasal and/or oral respiration, respiratory excursion of the thorax and abdomen, respiratory sounds (which would include snoring when snoring occurs), eye movement patterns, and electrical muscle activity in the chin region and on the lower leg, wherein the data is preferably collected by means of the following measuring methods or measuring devices: electrocardiography, microphone, air flow meter, electromyography electrodes (col. 4, line 57 – col. 5, line 34, col. 9, lines 15-44). Kayyali et al.’399 teaches collecting, recording, and analyzing the plurality of different types of bodily function data in order to diagnose sleep disorders and other diseases or conditions with sleep signatures, such as Parkinson’s, epilepsy, chronic heart failure, chronic obstructive pulmonary disorder, or other neurological, cardiac, pulmonary, or muscular disorders (see ABSTRACT, col. 2, lines 47-59). 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 Sanders et al. in view of Gouveris et al. to include measuring and recording the additional data taught by Kayyali et al.’399 during the predetermined time period, as it would provide a comprehensive sleep study via PSG analysis, and would help diagnose sleep disorders and other diseases or conditions with sleep signatures, such as Parkinson’s, epilepsy, chronic heart failure, chronic obstructive pulmonary disorder, or other neurological, cardiac, pulmonary, or muscular disorders.
Regarding claim 11, the combined data of Sanders in view of Gouveris et al. further in view of Kayyali et al.’399 is all evaluated to assign a certain sleep stage.
Regarding claims 12 and 13, Kayyali et al.’399 teaches recording the data on bodily functions in a sleep laboratory within a subject’s home (col. 5, lines 26-27). Kayyali et al.’399 teaches that performing the PSG monitoring within a PSG laboratory set up within the subject’s home eliminates a “first night effect”, thus providing more accurate data for sleep diagnosis (col. 5, lines 27-31). Kayyali et al.’399 further teaches that subjects are more comfortable sleeping at home and are more willing to participate in a full PSG study that does not involve traveling or sleeping away from home (col. 5, lines 31-34). With these teachings by Kayyali et al.’399, it would have been obvious to one of ordinary skill in the art at the time the invention was effectively filed to have performed the PSG monitoring method of Sanders et al. in view of Gouveris et al. further in view of Kayyali et al.’399 in a sleep laboratory within the human being’s home, as it would (1) provide more accurate data for sleep diagnosis, and (2) make the human being more comfortable and more willing to participate in a full PSG study.
Claims 12 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Sanders et al. in view of Gouveris et al., as applied to claim 1, further in view of Burns et al.’373 (US Pub No. 2008/0262373 – previously cited).
Regarding claim 12, while Sanders et al. in view of Gouveris et al. discloses that the data on bodily functions is collected in a hospital (II. METHODS of Sanders et al.), it fails to explicitly disclose that the data is collected in a sleep laboratory. Burns et al.’373 teaches of method of automatically diagnosing or assessing rapid eye movement sleep behavior disorder (see ABSTRACT), wherein the method comprises acquiring data on bodily functions in a sleep laboratory for two consecutive nights (sections [0039] and [0068]). 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 Sanders et al. in view of Gouveris et al. so that it collects data on bodily functions of the human being in a sleep laboratory, as taught by Burns et al.’373, as this would allow for the diagnosis and assessment of rapid eye movement sleep behavior disorder.
Regarding claim 18, Burns et al.’373 teaches that the data is collected during a second night (sections [0039] and [0068] – two consecutive nights; and section [0056]).
Response to Arguments
Applicant's arguments filed 12 June 2026 have been fully considered.
Regarding the rejections of the claims under 35 U.S.C. 112(b), while the amendments have overcome some of the indefiniteness issues within the claims, as seen in paragraph 4 above, indefiniteness issues remain.
Regarding the rejections of the claims in view of the previously cited prior art, Applicant’s arguments are not persuasive.
Applicant argues on page 9 of the Remarks that “Nothing in Sanders teaches or contemplates classification performed in accordance with Applicant’s method in which classification requires cross-frequency coupling applied to theta and gamma waves or to delta and alpha waves.” This argument is not persuasive as Figure 3 of Sanders clearly shows the results of cross-frequency coupling applied to theta and gamma waves or to delta and alpha waves. Applicant’s argument on page 9 of the Remarks that Sanders “fails to teach or contemplate the use of other EEG signals, specifically failing to teach or contemplate use of C3/C4 data to obtain better results” is not persuasive as Sanders was not relied upon to teach using C3/C4 data; Gouveris et al. was relied up on for this teaching.
Applicant’s arguments on pages 9-10 of the Remarks that Gouveris fails to cure the deficiencies of Sanders are not persuasive. Applicant argues that Gouveris does not teach that C3/C4 EEG data signals are suitable for a sleep stage classification using cross-frequency coupling features. Gouveris need not teach a sleep stage classification using a cross-frequency coupling method; Sanders was relied upon for this teaching. Gouveris was merely relied upon to teach that it is known in the art to use C3/C4 EEG data to classify sleep stages. With this teaching by Gouveris, it would have been obvious to try using C3/C4 EEG data in the cross-frequency coupling method of Sanders as it would merely be choosing from a finite number of identified, predictable solutions (analyzing C3/C4 EEG data to perform sleep stage classification), with a reasonable expectation of success. Applicant’s argument that “a person skilled in the art would have no reason to exchange the Fpz-Cz EEG signals taught in Sanders for the C3/C4 EEG signals” is not persuasive as the rejection does not rely on substituting C3/C4 EEG signals for Fpz-Cz EEG signals. Instead, the modification to Sanders in view of Gouveris results in including an analysis of C3/C4 EEG signals with the analysis of Fpz-Cz EEG signals to classify sleep stage.
Applicant’s argument that the results in Sanders “actually teach away from a method using cross-frequency coupling features” is not persuasive. While Sanders teaches that manual visual sleep staging appears to provide better annotations than its automated scoring, it still teaches using a cross-frequency coupling method to perform sleep stage classification. A prior art reference need not teach that a particular disclosed method is the “best” method in order for the disclosed method to be used as prior art against claims.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Wang et al.’090 (US Pub No. 2019/0304090 – previously cited) teaches the advantages of using a non-linear kernel with a radial basis function algorithm in a support vector machine.
Javed et al.’257 (US Pub No. 2019/0231257 – previously cited) teaches that conventional PSG monitoring includes recording the data recited in claim 10, and that PSG monitoring comprises two nights of observation in a sleep laboratory.
Sotos et al.’981 (US Pub No. 2006/0063981 – previously cited) teaches that PSG monitoring typically includes recording the data recited in claim 10.
Bianchi et al.’937 (US Pub No. 2014/0213937 – previously cited) teaches that PSG monitoring typically includes recording the data recited in claim 10.
Grossman et al.’073 (US Pub No. 2019/0143073 – previously cited) teaches that PSG monitoring typically includes recording the data recited in claim 10.
Slonneger et al.’770 (US Pub No. 2014/0364770 – previously cited) teaches performing PSG monitoring in a home environment.
Murphy et al.’064 (US Pub No. 2021/0370064 – previously cited) teaches performing PSG monitoring in a home environment.
Li et al. (Deep learning in the cross-time frequency domain… – previously cited) teaches that the gold standard of sleep disorder diagnosis is PSG which includes recording the data recited in claim 10.
Chan et al.’086 (US Pub No. 2015/0190086 – previously cited) teaches that conventionally, sleep staging of a human being is done via a PSG study in a sleep laboratory, and that PSG studies include recording the data recited in claim 10.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ETSUB D BERHANU whose telephone number is (571)270-5410. The examiner can normally be reached Mon-Fri 9:00am-5:30pm 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.
/ETSUB D BERHANU/Primary Examiner, Art Unit 3791
