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 .
Drawings
The drawings are objected to under 37 CFR 1.84(h)(5) because Figure 4 show(s) modified forms of construction in the same view. Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
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 are 21-30 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
The claim(s) recite(s) a mentally performable method of training a system for detecting noise in electrocardiogram ("ECG") data, comprising: dividing the ECG training data into a plurality of ECG training data blocks; annotating each of the plurality of ECG training data blocks with a classification, wherein the classification indicates one of valid data or noise data for each of the plurality of ECG training data blocks; inputting a plurality of annotated ECG training data blocks into the system, wherein the plurality of annotated ECG training data blocks is a subset of the plurality of ECG training data blocks. These steps are mentally performable by a cardiologist training to review ECG data for noise classification. The applicant, in fact, allows for annotation by human review (see claim 30).
This judicial exception is not integrated into a practical application because there are no improvements to the functioning of a computer, or to any other technology or technical field, as discussed in MPEP 2106.05(a); there is no application or use of
a judicial exception to effect a particular treatment or prophylaxis for disease or medical condition, but only training – see Vanda Memo; there is no application of the judicial exception with, or by use of, a particular machine, as discussed in MPEP 2106.05(b); there is no transformation or reduction of a particular article to a different state or thing, as discussed in MPEP 2106.05(c), but only data manipulation; and there is no application or use of the judicial exception in some other meaningful way beyond generally linking the use of the judicial exception to the particular technological environment of ECG noise detection, such that the claim as a whole is more than a drafting effort designed to monopolize the exception, as discussed in MPEP 2106.05(e) and the Vanda Memo issued in June 2018.
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because execution of the abstract idea would necessarily require the step of obtaining ECG training data. As stated in MPEP 2106.05(g), the selection of the particular data source or type of data to be manipulated (e.g., the use of data obtained from a monitor with a feedback button) is an example of an activity that the courts have found to be insignificant extra-solution activity. Such a step is therefore considered insignificant data gathering. Even if such a feature were to be considered significant, the claim itself does not reflect any disclosed improvement. As stated in MPEP 2106.05(a), the claim itself must reflect the disclosed improvement in technology. In the present case, the claims merely require obtaining ECG training data from an ECG monitor that has a feedback button, with no integration of the button into the abstract idea. The claims, for example, do not require the determination of noise data segments that overlap a button press, and the trimming of overlapping segments to align with a start or end of a button press window –features necessary for the asserted improvement. The trimming feature of claim 26 is not associated with any button press. The claims, in fact, don’t require that the data be obtained from operation of the feedback button at all –merely that the data come from a monitor that happens to have a feedback button.
Regarding claim 22, the source of the requisite ECG data (i.e., from a plurality of ECG monitors) represents insignificant data gathering. Training a system by collecting data from a number of different sources permits the system to learn from a broader selection of independent sources, thus enhancing the system’s robustness, reliability and performance by better generalizing real-world situations. As stated above, the selection of the particular data source or type of data to be manipulated is an example of an activity that the courts have found to be insignificant extra-solution activity. Generic ECG monitors are also WURC in the art, as is the use of a plurality of such monitors in the training process.
Claims 23-27 and 30 contain no new additional elements.
Regarding claims 28 and 29, the particular type of system used to implement the method is considered insignificant as the neural network (e.g., CNN) merely represents the tool upon which the abstract idea is implemented. Neural networks such as CNNs are also WURC in the machine learning art.
Claim Rejections - 35 USC § 103
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claim(s) 21-25 and 27-30 is/are rejected under 35 U.S.C. 103 as being unpatentable over Balda (Pub. No. 2012/0022387) in view of Rubin et al. (Rubin: Pub. No. 2020/0205687).
Regarding claim 21, Balda discloses a device which obtains ECG data from an ECG monitor 100 with a feedback button 403 (Fig. 6) for placement on a patient’s chest (see pars. 0007, 0053).
Balda does not discuss dividing the received ECG into training data blocks for classification, annotating each of the training blocks as one of noise data or valid data, and does not input a plurality of annotated blocks into the system, wherein the plurality is a subset of the plurality of ECG training data blocks. Rubin, however, discloses an ECG monitor that obtains ECG training data (par. 0039), where the data is divided into a plurality of ECG training blocks (pars. 0007, 0023, segments). Rubin annotates (labels) each of the plurality of training blocks wherein the classification indicates one of valid data or noise data (pars. 0019, 0039). A plurality of the annotated blocks is input into the system, wherein the plurality of training blocks is a subset of the plurality of ECG training blocks (annotated blocks used to train the system do not include those segments found to be too noisy, see for example Fig. 3). These features are taught to be advantageous in that they improve efficiency of diagnosis by avoiding transmitting and processing unacceptably noisy data sets (par. 0021) and allow the use of efficient neural networks (NN) to assign rhythm types to ECG datasets (par. 0013) –both decidedly important in any ECG monitoring method. Given the obvious advantages of noise reduction and the use of NNs to effectively process large amounts of ECG data, those of ordinary skill in the art would have considered the use of such features to be obvious in the ECG device of Balda which, like all ECG monitors, is also subject to the negative influence of noise.
Regarding claim 22, Rubin discloses that a variety of signal sources may be used for training purposes, including ambulatory recordings from Holter monitors (par. 0041), such as those disclosed by Balda (see for example pars. 0047 and 0053). Such a known process increases the robustness, generalizability and reliability in real-world clinical applications by including diverse data, and accounting for variations in equipment, as well as allowing input from a multitude of patients at various locations to the training process, and thus would have been considered a matter of obvious design.
Regarding claims 23 and 24, as disclosed by Rubin (note par. 0024) the use of either continuous data segments or overlapping data segments is old and well-known in the cardiac signal processing and machine learning arts. Trade-offs between data density, temporal resolution, data correlation between blocks/windows and computational costs would need to be weighed in this decision by those of ordinary skill in the art. If, for example, it was desirable to analyze events that happen at the transition points between sampling windows, an overlapping technique might be advantageous. If on the contrary it were desirable to reduce computational costs, then a continuous or non-overlapping technique might be advantageous by limiting the amount of data collected. To include such a well-known feature into the ECG monitor of Balda to improve ECG analysis would have therefore been considered obvious to those of ordinary skill in the art.
Regarding claim 25, while Balda is not concerned with sampling details, Rubin discloses that segments of length between 9 and 15 seconds may be extracted (pars. 0043, 0044). Clearly the length of time used for ECG training blocks would depend on the desired accuracy required, the amount of processing power available, and the characteristics of the signals and abnormalities being detected. The applicant discloses that while two to twelve seconds of training data is used, other durations are possible (see page 19, lines 3-13). Artisans of ordinary skill would have thus considered any amount of time sufficient to provide the necessary data to be suitable to the invention.
Regarding claims 28 and 29, as argued above, the use of NNs and particularly CNNs are well-known in the ECG monitoring art as disclosed by Rubin (see pars. 0019 and 0027). Such networks allow for pattern recognition and the processing of large amounts of incoming data –both recognized concerns of ECG monitoring systems. To allow analysis of ECG data by such means would have therefore been considered obvious to those of ordinary skill in the art.
Regarding claim 30, see par. 0039 of Rubin which discloses a known method of annotating ECG data. Any known means capable of providing suitable annotation would have been considered obvious to those of ordinary skill in the art, including those disclosed by Rubin.
Response to Arguments
Applicant's arguments filed December 15, 2025 have been fully considered but they are not persuasive.
The drawing corrections are acceptable. The Examiner apologizes for not including Fig. 4 in the original listing. Fig. 4 contains the same issue objected to in the previous Office Action (i.e., a modified form of construction shown by element 32). A correction similar to that made in Figs. 3 and 19 would be acceptable.
The terminal disclaimer has been approved, thus overcoming the obviousness-type double patenting rejection.
Regarding the rejection under §101, the Applicant argues that the present invention embodied by claim 21 is a practical improvement to existing systems. It is argued that claim 21 is similar to Example 39 of the 2019 Subject Matter Eligibility Guidelines, in that, like Example 39, the present claims do not recite a mental process that is practically performable in the human mind. The Applicant highlights the fact that the current invention is drawn to a method of training a neural network.
The Examiner respectfully disagrees. In Example 39, the claim requires application of one or more transformations to each digital facial image including mirroring, rotating, smoothing, or contrast reduction to create a modified set of digital images. Such a process is not practically performable within the human mind. The mere fact that the claim involves a method of training a neural network is not sufficient to convey eligibility. Claim 2 of Example 47 of the July 2024 Subject Matter Eligibility Examples, for instance, was found to be ineligible even though it too comprises a method of training an ANN based on input data. Claim 21 of the present invention merely requires one to divide obtained ECG training data into a plurality of blocks, annotate each of the blocks with a classification indicating valid data or noise data, and input a subset of the annotated blocks into a system for detecting noise. A human can readily divide incoming data into blocks, annotate the blocks and input a subset of the blocks into a system for detecting noise (e.g., training the human brain). The Applicant further discloses that the blocks can be annotated by a human (see claim 30), where a human is capable of reviewing the blocks to access whether or not each block is valid or noise. The claimed invention is thus considered to contain actions capable of being performed by a human, and consequently contains an abstract idea.
The Applicant further asserts that the review of ECG data by current methods involving paper ECG strips is overly burdensome and cumbersome. Claiming improved speed or efficiency inherent with applying the abstract idea on a computer, however, does not integrate the judicial exception into a practical application (MPEP 2106.05(f), (2)).
Furthermore, as discussed in the rejection under §101 above, the claims must reflect any asserted improvement in technology. In the present case, the claims merely require obtaining ECG training data from an ECG monitor that has a feedback button, with no integration of the button into the abstract idea. The claims, for example, do not require the determination of noise data segments that overlap a button press, and the trimming of said overlapping segments to align with a start or end of a button press window –features necessary for the asserted improvement. The trimming feature of claim 26 is not directly tied to any button press. The claims, in fact, don’t require that the data be obtained from operation of the feedback button at all –merely that the data come from a monitor that happens to have a feedback button. The data may, for example, be obtained continuously in a Holter monitor where the wearer may never press the feedback button.
Regarding the rejection of claims under §103 and the newly added feature of the feedback button, please refer to the discussion already presented above.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Sullivan ‘933 discloses a related ECG monitoring method including noise detection of segmented ECG data.
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 KENNEDY SCHAETZLE whose telephone number is (571)272-4954. The examiner can normally be reached 2nd Monday of the biweek and W-F.
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 E. 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.
/KENNEDY SCHAETZLE/Primary Examiner, Art Unit 3796
KJS
March 13, 2026