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 .
Status of the claims
Currently, claims 2-21 are pending in the application. None of the claims are amended.
Response to Arguments / Amendments
Applicant’s arguments have been fully considered, but they are not persuasive, see discussion below.
Rejections under 35 U.S.C. § 103:
A. Haeusser is unavailable prior art as applied in the Office Action. The applicant argued that Haeusser is unavailable prior art as applied in the Office Action.
As to the above argument, Haeusser is available prior art as applied in the Office Action as of September 7, 2015.
PNG
media_image1.png
268
606
media_image1.png
Greyscale
B. Even if Haeusser were available prior art, the Office Action would fail to present a prima facie case of obviousness:
The applicant argued that Heusser fails to disclose or even suggest a linear regression model as a lead model for reconstruction of a particular signal.
As to the above argument, Haeusser teaches a linear regression model of the training sequences; and supplying the linear regression model as a lead model for reconstruction of a particular signal corresponding to a particular lead measurement of the one or more lead measurements with an input signal x to the machine learning model atrial discriminative trained (ADT) comprises data recorded from body surface electrodes BS (x) ([0298]FIG. 18)
Haeusser also teaches trained atrial discriminative machine learning model comprising one or more of: (a) a nearest neighbor model; (b) a naive Bayes model; (c) a decision tree model; (d) a linear regression model; (e) a support vector machine (SVM) model, and (f) a neural network) ([0306]).
It should be further noted that Applicant has not presented any specific arguments with regards to the rejections of the dependent claims.
Accordingly, Examiner maintains the rejection with regards to above arguments.
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 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 2-21 are rejected under 35 U.S.C. 103 as being unpatentable over Zhou et al. (US 20180183461, hereinafter Zhou) in view of Haeusser et al. (US 20220248956, hereinafter Haeusser).
Regarding Claim 2, Zhou discloses a device (FIG. 3), comprising:
receiving, from a sensor device, one or more lead measurements including respective signals, with a first signal of the respective signals being an electrocardiogram (ECG) signal ([0038] FIG. 3, At step 302, the data reconstruction block 131 receives first portion of compressive sensing (CS) ECG signal samples in the current mega block from the source electronic device 10 via the receive circuit 122);
generating a timing reference indicative of timing of the one or more peaks ([0037], a signal segment of the bio-signal within a time window is sampled at the ADC 106 and receives a portion of CS samples in a mega block (a signal segment of the bio-signal within a time window) from the source electronic device 10; [0038] FIG. 3, At step 304 current mega block is generated by applying digital compressive sensing to the data group composed of signal samples that are generated by sampling a signal segment of the bio-signal within a time window);
generating, based on the one or more lead measurements and the timing reference ([0037], a signal segment of the bio-signal within a time window is sampled at the ADC 106 and receives a portion of CS samples in a mega block (a signal segment of the bio-signal within a time window) from the source electronic device 10; [0038] FIG. 3, At step 304 current mega block is generated by applying digital compressive sensing to the data group composed of signal samples that are generated by sampling a signal segment of the bio-signal within a time window),
Zhou does not explicitly disclose recording, in a memory device, the respective signals as training sequences; identifying one or more peaks within a training sequence of the training sequences; a linear regression model of the training sequences; and supplying the linear regression model as a lead model for reconstruction of a particular signal corresponding to a particular lead measurement of the one or more lead measurements.
Haeusser teaches recording, in a memory device, the respective signals as training sequences; identifying one or more peaks within a training sequence of the training sequences; a linear regression model of the training sequences; and supplying the linear regression model as a lead model for reconstruction of a particular signal corresponding to a particular lead measurement of the one or more lead measurements ([0298]FIG. 18, an input signal x to the machine learning model atrial discriminative trained (ADT) comprises data recorded from body surface electrodes BS (x); [0306] , a trained atrial discriminative machine learning model comprising one or more of: (a) a nearest neighbor model; (b) a naive Bayes model; (c) a decision tree model; (d) a linear regression model; (e) a support vector machine (SVM) model, and (f) a neural network).
Therefore, it would have been obvious to one ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of linear regression model as a lead model for reconstruction of a particular signal as taught by Haeusser ([0298]) into the encoding system of Zhou in order to reduce the frequency and extent of cardiac ablation procedures to the minimum amount required to treat persistent atrial fibrillation (AF), and helps balance the benefits of decreased fibrillatory burden against the morbidity of increased lesion load (Haeusser, [0020]).
Regarding Claim 3, Zhou in view of Haeusser discloses the method of claim 2, Haeusser discloses wherein the lead model comprises a base for the particular signal that, when used in combination with a particular timing reference, yields the particular signal ([0298]FIG. 18, (15) a trained atrial discriminative machine learning model being generated at least partially using supervised learning or unsupervised learning; (16) a trained atrial discriminative machine learning model comprising convolutional layers; (17) conditioned electrogram signals being processed by the at least one computing device to remove or substantially remove at least portions of the QRS or QRST complex from at least some of the electrogram signals). The same reason or rational of obviousness motivation applied as used above in claim 2.
Regarding Claim 4, Zhou in view of Haeusser discloses the method of claim 2, Haeusser discloses wherein the identifying comprises identifying an R peak of the training sequence ([0298]FIG. 18, (15) a trained atrial discriminative machine learning model being generated at least partially using supervised learning or unsupervised learning; (16) a trained atrial discriminative machine learning model comprising convolutional layers; (17) conditioned electrogram signals being processed by the at least one computing device to remove or substantially remove at least portions of the QRS or QRST complex from at least some of the electrogram signals). The same reason or rational of obviousness motivation applied as used above in claim 2.
Regarding Claim 5, Zhou in view of Haeusser discloses the method of claim 2, Haeusser discloses wherein the identifying comprises identifying a first peak having a greatest magnitude within the training sequence ([0298]FIG. 18, (15) a trained atrial discriminative machine learning model being generated at least partially using supervised learning or unsupervised learning; (16) a trained atrial discriminative machine learning model comprising convolutional layers; (17) conditioned electrogram signals being processed by the at least one computing device to remove or substantially remove at least portions of the QRS or QRST complex from at least some of the electrogram signals). The same reason or rational of obviousness motivation applied as used above in claim 2.
Regarding Claim 6, Zhou in view of Haeusser discloses the method of claim 2, Haeusser discloses wherein the identifying comprises identifying at least one of a first peak having a greatest positive magnitude within the training sequence or a second peak having a greatest negative magnitude within the training sequence ([0298]FIG. 18, (15) a trained atrial discriminative machine learning model being generated at least partially using supervised learning or unsupervised learning; (16) a trained atrial discriminative machine learning model comprising convolutional layers; (17) conditioned electrogram signals being processed by the at least one computing device to remove or substantially remove at least portions of the QRS or QRST complex from at least some of the electrogram signals). The same reason or rational of obviousness motivation applied as used above in claim 2.
Regarding Claim 7, Analogous rejection as the rejection of Claim 2 applies.
Zhou further discloses performing reconstruction of a data group according to the first portion of CS samples in the current mega block, where the current mega block is generated by applying digital compressive sensing to the data group composed of signal samples that are generated by sampling a signal segment of the bio-signal within a time window ([0038] FIG. 3, step 304)
Regarding Claim 8, Zhou in view of Haeusser discloses the method of claim 7, Zhou discloses wherein the compressing comprises, determining a decimation map for the representation of the difference; and decimating the representation of the difference according to the decimation map ([0037] As mentioned above, a signal segment of the bio-signal within a time window is sampled at the ADC 106 to produce a data group composed of signal samples, the data group is compressed by compressive sensing at the sample generation block 117 to produce a mega block).
Regarding Claim 9, Zhou in view of Haeusser discloses the method of claim 7, Zhou discloses further comprising receiving the lead measurement from a sensor device having one or more electrodes configured to an ECG signal, with the ECG signal forming part of the lead measurement ([0027], perform compressive sensing in a digital domain performing analog-to-digital conversion upon the bio-signal to generating signal samples (e.g., ECG signal samples) according to a sampling rate and then performing digital compressive sensing upon the signal samples to generate CS samples).
Regarding Claim 10, Zhou in view of Haeusser discloses the method of claim 9, Zhou discloses further comprising generating a timing reference based on the ECG signal ([0027], perform compressive sensing in a digital domain performing analog-to-digital conversion upon the bio-signal to generating signal samples (e.g., ECG signal samples) according to a sampling rate and then performing digital compressive sensing upon the signal samples to generate CS samples).
Regarding Claim 11, Zhou in view of Haeusser discloses the method of claim 10, Zhou discloses wherein the generating the timing reference comprises, identifying one or more peaks within the ECG signal; and generating, using the one or more peaks, the timing reference as a time base indicative of timing of the one or more peaks ([0037], a signal segment of the bio-signal within a time window is sampled at the ADC 106 and receives a portion of CS samples in a mega block (a signal segment of the bio-signal within a time window) from the source electronic device 10; [0038] FIG. 3, At step 304 current mega block is generated by applying digital compressive sensing to the data group composed of signal samples that are generated by sampling a signal segment of the bio-signal within a time window).
Regarding Claim 12, Zhou in view of Haeusser discloses the method of claim 11, Haeusser discloses wherein the identifying comprises identifying an R peak within the ECG signal ([0333] FIG. 20, Metrics include number of QRS peaks detected per minute; [0349] FIG. 21, ECG traces picked up by neighboring electrodes G2 and G3). The same reason or rational of obviousness motivation applied as used above in claim 2.
Regarding Claim 13, Zhou in view of Haeusser discloses the method of claim 10, Zhou discloses wherein the generating the lead estimate comprises reconstructing, based on the timing reference and the lead model, the lead estimate ([0037], a signal segment of the bio-signal within a time window is sampled at the ADC 106 and receives a portion of CS samples in a mega block (a signal segment of the bio-signal within a time window) from the source electronic device 10; [0038] FIG. 3, At step 304 current mega block is generated by applying digital compressive sensing to the data group composed of signal samples that are generated by sampling a signal segment of the bio-signal within a time window).
Regarding Claims 14-21, Apparatus claims 14-21 of using the corresponding method claimed in claims 1 & 7-13, and the rejections of which are incorporated herein for the same reasons as used above.
Conclusion
THIS ACTION IS MADE FINAL. 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 Samuel D Fereja whose telephone number is (469)295-9243. The examiner can normally be reached 8AM-5PM.
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, DAVID CZEKAJ can be reached at (571) 272-7327. 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.
/SAMUEL D FEREJA/Primary Examiner, Art Unit 2487
Prosecution Insights