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 .
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 1-8 & 10, specifically independent claim 1, is rejected under 35 U.S.C 101 because the claimed invention is directed to an abstract idea, judicial exemption, without significantly more. Please see the below 2 step, prong analysis:
Step 1:
Claim 1 is directed to a computer device, which is a statutory category of invention.
Step 2A, prong 1:
Claim 1 recites limitations that are directed to an abstract idea, i.e. judicial exception
Claim 1 recites method steps directed to via a memory arranged to:
extract features from electrogram signals
generating a first array of probabilities indicating dispersion
generating a second array of probabilities
combining the arrays (e.g., via weighted averaging) to produce a third array of probabilities
using the probabilities for detection of cardiac areas
These limitations, under their broadest reasonable interpretation, describe analyzing electrogram data by extracting features, generating probability values, and combining those values to classify or detect conditions. This constitutes mathematical concepts (probabilities, weighted averages, numerical evaluation of data), certain method of organizing human activity/mental processes (e.g., evaluation and classification of data). Accordingly, the claim recites an abstract idea.
Step 2A, Prong 2:
The claim, as a whole, fails to integrate the abstract idea into a practical application. Claim 1 recites the following additional elements, which for the reasons set forth below, do not integrate the abstract idea into a practical application.
“…a memory arranged to…” which is directed to mere instructions to apply an exception, see MPEP 2106.05(f).
“…a first evaluator…” which is directed to mere instructions to apply an exception, see MPEP 2106.05(f).
“…one of a plurality of electrodes…” which is directed towards data gathering MPEP 2106.05(f).
“…an extractor…” which is directed to mere instructions to apply an exception, see MPEP 2106.05(f).
“…a second evaluator…” which is directed to mere instructions to apply an exception, see MPEP 2106.05(f).
“…a predictor…” which is directed towards data output, see MPEP 2106.05(f).
“…a gradient boosting based machine learning module…” which is directed to mere instructions to apply an exception, see MPEP 2106.05(f).
Therefore, the claim fails to integrate the abstract idea into a practical application. The examiner also notes that the additional elements recited in claim 1 do not apply or use the judicial exception to affect a particular treatment or prophylaxis for a disease or medical condition. The claim is silent to providing any treatment at all to a patient.
The examiner further notes that the “used for treatment” language in the preamble of the claim constitutes an intended use and does not impose a meaningful limitation on the claimed invention.
The claim applies known machine learning techniques and processes electrogram data using generic models. The claim, however, does not:
improve how electrograms are acquired
improve signal processing techniques
improve computer functionality
Instead, the claim uses conventional models to analyze data, i.e. generic elements such as “computer device”, “memory”, “evaluators” are used which provide no specialized hardware or transformation of matter.
In conclusion, the claim merely applies the abstract idea using generic computer components and does not integrate the exception into a practical application.
Step 2B:
The claim as a whole fails to recite an inventive concept. The additional elements, when considered individually and in combination, do not recite significantly more than the abstract idea for the reasons as set forth above in Step 2A, Prong 2. Upon re-evaluating the limitation that was previously identified as insignificant extra-solution activity in Step 2A, Prong 2, the following evidence to show that the limitation is well-understood, routine and conventional:
real-time discrete data obtained from a medical device/data previously collected from a medical device (i.e. body surface/unipolar electrodes) Presenting offers and gathering statistics, OIP Techs., 788 F.3d at 1362-63, 115 USPQ2d at 1092-93; Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network).
producing at said computer processor a human-readable output (i.e. processor) of the analysis of the gathered data, this is also WURC, as evidenced by Electric Power Group, LLC v. Alstom S.A., 830F.3d 1350, 119 USPQ2d 1739 (Fed.Cir. 2016), which discusses “conventional computer, network, and display technology” and states that “nothing in the patent contains any suggestion that the displays needed for that purpose are anything but readily available. We have repeatedly held that such invocations of computers and networks that are not even arguably inventive are “insufficient to pass the test of an inventive concept in the application” of an abstract idea”.” Similarly, there is nothing in Applicant’s specification that indicates that the device that is “producing at said computer processor a human-readable output indicating” the findings of the analysis is anything but readily available.
The ordered combination of elements amounts to no more than applying known data analysis and machine learning techniques to electrogram data to obtain a result. Therefore, the claims fail to recite significantly more than the abstract idea and claims 1, 8 & 15 are rejected under 35 U.S.C 101.
The examiner also notes that limitations of the dependent claims 2-8 & 10 further define the steps of extracting, arranging, predicting, etc., which further limits the claim limitations already indicated above as being directed to an abstract idea. Therefore, claims 2-8 & 10 are also directed to patient-ineligible subject matter.
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.
Claim(s) 1-8 & 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Durdez (FR 3079405) in view of Katouzian et al. (US 2019/0392547) and one having ordinary skill in the art.
Durdez discloses;
A computer device for real-time analysis of electrograms,
E.G. via the disclosed device for detecting cardiac rhythm disorders based on ECG data collected via electrodes; pp. 5-6, which constitutes analysis of ECG in real time during a procedure.
comprising a memory arranged to receive real-time electrograms signals each originating from a plurality of electrodes,
E.G. via receiving ECG data obtained from electrodes positioned within the heart and processing such data in packets for analysis; pp. 6
a first evaluator comprising an extractor…and a machine learning module…to output a first array of probabilities…”
E.G. via the disclosed first model applied to the ECG data for detecting cardiac rhythm disorders; pp. 5. Durdez further discloses that the application of the first model produces a value representing a probability that the ECG data corresponds to a cardiac rhythm disorder; pp. 6
a second evaluator…outputs a second array of probability
E.G. Durdez discloses a second model applied to the ECG data, distinct from the first, which likewise produces a value indicative of detection of a cardiac rhythm disorder; pp. 6. Thus, Durdez teaches two evaluators producing probability-based outputs.
a predictor…based on the first array of probabilities and the second array…returns a third array…based on a weighted average…”
E.G. Durdez explicitly teaches combining outputs from the models, i.e. value v2 can be a linear combination of the values v1; pp. 6. Durdez further teaches that weighting may be applied based on characteristics of the data, with a weighting more important than the values associated with a high index…pp. 6
…used for detection of cardiac areas promoting atrial fibrillation.
E.G. Durdez teaches detection of cardiac rhythm disorders (including atrial fibrillation) using ECG data; pp. 5-6
Durdez does not explicitly disclose that the second evaluator comprises a convolutional neural network (CNN). Katouzian et al. teaches that convolutional neural networks (CNNs) are well-known machine learning models that may be employed in physiological data processing systems [0068]. Katouzian et al. further teaches that a CNN may be used to extract features from said data and generate outputs representative of those features, wherein said outputs of such models are used in downstream classification processes; [0084]-[0085]. Accordingly, Katouzian provides evidence that CNNs are recognized and suitable machine learning models for feature extraction and classification tasks in medical contexts.
Therefore, it would have been obvious to one having ordinary skill in the art to implement at least one of the models of Durdez as a convolutional neural network as taught by Katouzian because CNNs are known and commonly used architecture for extracting features and performing classification in physiological data systems. Substituting one known machine learning model for another known machine learning model for the same purpose represents a predictable use of prior art elements. KSR Int’l Co v. Teleflex Inc, 550 U.S. 398 (2007).
2.
…the extractor is arranged to extract at least one timewise analysis feature…comprising a first cycle length estimation, a second cycle length estimation…
E.G. Durdez teaches segmenting ECG data into time-based windows using first duration and second duration and applying models to those segments; pp. 5-6. Durdez further teaches determining values from these time-based segments using estimators derived for ECG signal vector, which correspond to cycle-based temporal characteristic of the signal; pp. 5-6.
…and a frequency within the Fast Fourier Transform…having the highest amplitude.
E.G. Katouzian teaches extracting features from medial signal/image data using machine learning models, including CNNs, to generate feature vectors representative of the underlying data; [0084]-[0086].
It would have been obvious to one having ordinary skill in the art to include frequency-domain features, such as FFT peak frequency, as part of the extracted features because such features are well-known and routinely used in signal processing to improve classification performance.
3.
…extracting at least one morphological feature…comprising the Euclidean norm…”
E.G. Durdez explicitly teaches use of Euclidean norms in processing ECG signal vectors; pp. 5-6
…and the integrated absolute derivative…
E.G. Katouzian et al. teaches extracting numerical feature descriptors from physiological data using machine learning models; [0084]-[0086].
It would have been obvious to one having ordinary skill in the art to include additional morphological descriptors, such as integrated absolute derivative, as these are standard signal-processing features used to characterize waveform shape and improve classification.
4.
…divide a real-time electrogram signal into a series…having a chosen duration.
E.G. Durdez teaches receiving ECG data and splitting the data into segments based on a defined duration; pp. 5-6
5.
…provide a set of electrogram signals having the same chosen duration.
E.G. Durdez teaches repeatedly applying the model to segmented portions of ECG data defined by a fixed duration; pp. 5-6. Thereby inherently producing segments of equal duration.
6.
…when absolute difference between a probability…exceeds a threshold…”
E.G. Durdez teaches applying thresholds to model outputs to determine whether a condition is met; pp. 5-6
…to use the probability of the first array…in the third array…
Durdez further teaches combining outputs from multiple models and making decisions based on those outputs and threshold, thereby suggesting selection of one output over another based on threshold conditions; pp. 5-6
It would have been obvious to one having ordinary skill in the art to use one probability output in place of another based on threshold comparison, as such selection logic is a predictable use of known decision-making techniques in multi-modal systems.
7.
…determine a color associated to the values…and output…the color associated to the probability…
E.G. Durdez teaches generating detection outputs corresponding to ECG data and identifying areas of interest; pp. 5-6
It would have been obvious to one having ordinary skill in the art to display such results using color-coded visualization because mapping probability or intensity values to colors is a well-known technique used to improve interpretability of diagnostic outputs.
8.
A computer program product…instructions…cause processors to implement…
E.G. Durdez teaches a computer-implemented system performing the claimed functions of receiving ECG data, applying models, and generating outputs; pp. 5-6
It would have been obvious to one having ordinary skill in the art to implement such functionality as a computer program product stored on a non-transitory computer-readable medium, as this represents a routine implementation of software-based systems.
10.
…receiving real-time electrogram signals…executing the first evaluator…second evaluator…predictor…returning said third array…”
E.G. Durdez teaches receiving ECG data, applying a first model and second model and generating an output value corresponding to detection of cardiac conditions; pp. 5-6.
Note: The method steps correspond directly to the operation of the device of claim 1 as directed by Durdez in view of Katouzian.
Response to Arguments
Applicant's arguments filed February 25, 2026 have been fully considered but they are not persuasive. The applicant argues the following points in which the examiner provides a reason(s) as to why the arguments are not persuasive:
The applicant argues that claim 1 is not directed to an abstract idea because it is “used for treatment of atrial fibrillation” and detects “cardiac areas promoting atrial fibrillation,” and further asserts that the claim integrates any alleged abstract idea into a practical application. The applicant further contends that the claim includes an inventive concept.
These arguments have been considered but are not persuasive. Per Step 2A, Prong One (as recited in the above office action) the limitation of claim 1 collectively recite mathematical concepts and data analysis, including evaluation of data using mathematical relationships and algorithms, i.e. probability generation, weighted averaging and classification, which fall with the category of abstract ideas. See MPEP §2106.04(a)(2). The applicant does not persuasively dispute that such operations constitute mathematical processing of data.
Per Step 2A, Prong Two, the claim merely recites that the resulting probabilities are “used for the detection of cardiac areas promoting atrial fibrillation.” The claim does not recite any step of treatment, control or modification of a patient or device based on the result. As such, the claim does not effect a particular treatment or prophylaxis, does not improve the functioning of a computer or other technology and merely uses the result of data analysis for informational purposes. Accordingly, the additional element amount to insignificant extra-solution activity, namely the presentation or use of results of an abstract process. See MPEP §2106.05(g).
Per Step 2B, and the applicant’s assertion that the claim includes an inventive concept, the examiner further points out that the claim recites conventional data processing steps, which are well-understood, routine and conventional in the field of data analysis and machine learning. The claim does not cite a specific improvement to neural network architecture, unconventional training technique, or technical implementation that departs from routine practice. Rather, the claim applies known techniques, i.e. classifications, probability generation and combination of model outputs, to a particular type of data. Accordingly, when considered as an ordered combination, the claim does not amount to significantly more than the abstract idea itself. See MPEP §2106.05(d).
The applicant argues that Durdez does not disclose the claimed evaluators, neural networks or probability arrays.
The primary reference, Durdez teaches the following:
Receiving ECG data
Applying a first model and a second model to the data,
Generating values representing the likelihood of cardiac rhythm disorders, i.e. probabilities
And using threshold-based logic to evaluate such values.
The “values” produced by the models in Durdez represent probabilities or likelihoods, as they are compared to thresholds to determine detection outcomes. Further, Durdez discloses multiple models operating on ECG data and producing outputs that are combined or evaluated, which reasonably corresponds to the claimed evaluators and predictor. To the extent that Durdez does not explicitly disclose the use of a convolutional neural network or specific feature extraction techniques, such limitation are addressed in the rejection under 35 U.S.C. § 103 in the above office action.
Applicant’s arguments, filed February 25, 2026, with respect to the 35 U.S.C § 112, second paragraph and 101, being directed to/encompassing a human organism have been fully considered and are persuasive and have been withdrawn.
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 NICOLE F JOHNSON whose telephone number is (571)270-5040. The examiner can normally be reached Monday-Friday 8:00am-5:00pm 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, David Hamaoui can be reached at 571-270-5625. 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.
/NICOLE F JOHNSON/Primary Examiner, Art Unit 3796
Prosecution Insights