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 .
Response to Amendment
The amendment filed July 23, 2026 has been entered. Claims 1-10 remain pending in the application. Applicant’s amendments to the Specification, and Claims have overcome most of the objections and 112(b) rejection previously set forth in the Non-Final Office Action mailed April 21, 2026. More details provided below.
Response to Arguments
35 USC § 112(f)
Examiner acknowledges claim interpretations submitted in arguments filed 07/23/2026.
35 USC § 112(b)
Claim 1 has been amended, therefore the previous 112(b) rejection is withdrawn.
Claim 2 has been amended, therefore the previous 112(b) rejection is withdrawn.
35 USC § 101
Applicant's arguments filed 07/23/2026 have been fully considered but they are not persuasive.
On pg. 9 of applicant’s response, applicant argues that a human cannot “perform encoder-decoder neural-network interference on an ECG signal in a point-by-point manner in the human mind”. Examiner respectfully disagrees, as a clinician, provided ECG data, could divide the ECG signal into regions, and determine which regions exhibit tremors or fibrillation, and could also provide probabilities for the specified regions. Therefore, the additional limitation recites mental processes and mathematical operations for assigning classifications to regions of the ECG data and evaluation.
Additionally, applicant argues that “applying point-by-point semantic segmentation via a trained encoder-decoder model to detect fibrillation waves and atrial fibrillation” is a meaningful improvement to the technology rather than invoking a generic processor merely as a tool to implement an abstract idea. Examiner respectfully disagrees as the claim does not recite an improved hardware/circuit, or how the encoder-decoder model itself it improved for the technology. Rather, the claim recites data gathering and computational components to perform the claim classification and evaluation of the ECG information. The use of the encoder-decoder model merely specifies the model use to perform the claimed classification and does not provide an inventive concept.
35 USC § 102 & 103
Applicant’s arguments, see pg.s 10-11, filed 07/23/2026, with respect to the rejection(s) of claims 1-2, 4-6, and 9-10 under 102(a)(1) have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Fontanarava et al. (US 11678831 B2).
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 1-10 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1:
Claim 1 is directed to an apparatus of evaluating arrhythmia in ECG data: thus, the claim falls within a statutory category of invention.
Step 2A, prong 1:
Claim 1 recites the following claim limitations:
applies segmentation to the ECG wave to check respective sections of the ECG wave, and labels classification values for the sections
classifies the ECG wave in a point-by-point manner using a segmentation model trained by an encoder-decoder type segmentation algorithm, and determines, for each point of the ECG wave, the classification value as a class having a highest classification probability value among classes output by the segmentation model;
selects a fibrillation wave labeled as tremors on the basis of the classification values for the respective sections;
the fibrillation wave being a section of the ECG wave of which the classification value corresponds to the tremors;
determines atrial fibrillation in a case where the fibrillation wave of a preset threshold or greater is included
These limitations, under their broadest reasonable interpretation, cover concepts that can be practically performed in the human mind. A human, provided an ECG data/graph, could observe, calculate and evaluate the ECG wave to detect and classify arrhythmia. For example, these limitations are nothing more than a medical professional making a judgement of a patient's condition using an ECG signal based on observed measurement data. The medical professional could also divide the ECG signal into regions, and determine which regions exhibit tremors or fibrillation, and could also provide probabilities for the specified regions. Applicant's specification, paragraph 5, provides further evidence by indicating that ECG signals can be interpreted and classified as arrhythmia by medical staff, using known techniques. Additionally, prior art of Datta et al (Patent No. US 10,750,968 B2) discloses that irregular RR intervals is a very common symptom present in atrial fibrillation patients, and lists several other measurements to identify atrial fibrillation (col. 7 lines 33-35, 44-50).
Additionally, labeling the classification value as a class having a highest classification probability value among classes and comparing with a threshold are drawn to mathematical concepts, that a human could do, provided pen and paper.
Thus, claim 1 recites limitations that fall within the ‘mental processes’ and ‘mathematical concepts’ grouping of abstract ideas.
Step 2A, prong 2:
Claim 1 recites the following additional elements:
an ECG wave acquisition unit
classification unit
fibrillation selection unit
atrial fibrillation determination unit
These claimed elements fail to recite any additional element or combination of additional elements that apply, rely on, or use the judicial exception in a manner that imposes a meaningful limitation on the judicial exception. As recited the acquisition, classification, selection, and determination unit, which upon review of the applicant's specification are processors in conjunction with a software for collecting data, classifying, data, selecting data, and evaluating data (see paragraph [55]), are a conventional component that does not impose any meaningful structural limitations on the apparatus used to implement the judicial exception. The recitation of the recited units in the claim does not integrate the judicial exception into a practical application because the claim merely uses the acquisition unit as a tool to perform the abstract idea.
Accordingly, even in combination, these additional elements do not integrate the abstract idea into a practical application. The claim is directed to an abstract idea.
Step 2B:
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to Step 2A Prong 2, the additional elements in the claim amount to no more than insignificant extra solution activity and mere data gathering. The same analysis applies here in 2B and does not provide an inventive concept.
The recitation of a processor is not sufficient to amount to significantly more than the judicial exception because they are recited at a high level of generality, there is no meaningful limitation, such as a particular or unconventional structure that distinguishes the elements from well-known, routine, and/or conventional elements. Recitation of a processor as a tool to perform the abstract idea does not add significantly more than what is well-known, routine, and/or conventional in view of Alice Corp. Pty. Ltd. V. CLS Bank Int'l, 573 U.S. 208, 223, 110 USPQ2d 1976, 1983 (2014). For these reasons, there is no inventive concept. The claim is not patent eligible. Even when viewed as a whole, nothing in the claim adds significantly more to the abstract idea.
Dependent claims
Claims 3-4, and 6-10 further limit the abstract idea by introducing limitations which are indicative of concepts practically performable in the human mind (verifying sections of an ECG wave, gathering and comparing data, using metrics to assign scores to the ROI section).
Claim 5 adds the additional element of "learning unit" which as above, a processor in conjunction with an algorithm. Recitation of a generic processor as a tool to perform the abstract idea does not add significantly more than what is well-known, routine, and/or conventional in view of Alice Corp. Pty. Ltd. V. CLS Bank Int'l, 573 U.S. 208, 223, 110 USPQ2d 1976, 1983 (2014). Even when viewed as whole in combination with independent claim 1, the learning unit in claim 5 fails to add significantly more to the abstract idea.
Claim Interpretation
For the purpose of this examination in the current Office action, claims have been interpreted as follows:
In light of the specification, the ECG wave acquisition unit under the broadest reasonable interpretations can be a software in conjunction with a processor per para. 0054 (The respective components included in the atrial fibrillation discriminating apparatus 500 may be connected to a communication path that connects software modules or hardware modules within the apparatus to be operated in combination with each other. These components perform communication using one or more communication buses or signal lines) and 0054 (acquires data, and converts the data into one-dimensional data).
In light of the specification, the classification unit under the broadest reasonable interpretations can be a software in conjunction with a processor per para. 0059 (classification unit 520 applies segmentation to the ECG wave and checks respective sections of the ECG wave) and 0054 (acquires data, and converts the data into one-dimensional data).
In light of the specification, the fibrillation selection unit under the broadest reasonable interpretations can be a software in conjunction with a processor per para. 0065 (fibrillation selection unit 530 selects the fibrillation wave (value 1). The fibrillation selection unit 530 selects only a fibrillation wave labeled as tremors on the basis of the classification values for the respective sections) and 0054 (acquires data, and converts the data into one-dimensional data).
In light of the specification, the atrial fibrillation determination unit under the broadest reasonable interpretations can be a software in conjunction with a processor per para. 0066 (atrial fibrillation determination unit 540 determines that the atrial fibrillation has occurred) and 0054 (acquires data, and converts the data into one-dimensional data).
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.
Claims 1-2, 4-6, and 9-10 are rejected under 35 U.S.C. 103 as being unpatentable over Hu et al. (CN 110826631A), hereinafter Hu, and in view of Fontanarava et al. (US 11678831 B2), hereinafter Fontanarava.
Regarding claim 1, Hu teaches an atrial fibrillation discriminating apparatus (Fig. 1, para. 0002, 0007 (apparatus for classifying arrhythmias)). The apparatus comprising an ECG wave acquisition unit (Fig. 6, element 61, para. 0182 (acquisition unit)) that acquires an ECG wave (para. 0020 (acquiring an ECG signal)) for each of a plurality of a person; a classification unit (Fig. 6, element 60, para. 0182 (classification device)) that applies segmentation to the ECG wave to check respective sections of the ECG wave (para. 0008 (extracting multiple signal features from the ECG signal)), and labels classification values for the sections (para. 0008 (analyzing each signal feature sequentially based on the classification rules), 0024 (type of arrhythmia is determined)); a fibrillation selection unit (Fig. 3, element S302, para. 0108 (filtering techniques are used to eliminate noise in the ECG signal)) that selects only a fibrillation wave labeled as tremors (Fig 1, element S104, para. 0044 (obtains an ECG signal of a predetermined frequency), 0047 (morphology of F waves) on the basis of the classification values for the respective sections (Fig. 6, element 62, para. 0184 (extraction unit)), the fibrillation wave being a section of the ECG wave of which the classification value corresponds to the tremors (para. 0047 (morphology of F waves)); and an atrial fibrillation determination unit (Fig. 6, element 63, para. 0185 (determination unit)) that determines atrial fibrillation (para. 0185 (arrhythmia is determined)) in a case where the fibrillation wave of a preset threshold or greater is included (para. 0009 - 0010 (signal is analyzed and goes through steps to satisfy corresponding thresholds to determine arrhythmia type), 0052-0053 (analyze signal until the type of arrhythmia is determined based on corresponding thresholds)).
Hu does not teach wherein the classification unit classifies the ECG wave in a point-by-point manner using a segmentation model trained by an encoder-decoder type segmentation algorithm, and determines, for each point of the ECG wave, the classification value as a class having a highest classification probability value among classes output by the segmentation model.
Fontanarava teaches classifying the ECG wave in a point-by-point manner (Fig. 6A) using a segmentation model trained by an encoder-decoder type segmentation algorithm (col. 20, lines 15-19 (convolutional neural network is applied to an ECG signal)), and determines, for each point of the ECG wave, the classification value as a class having a highest classification probability value among classes output by the segmentation model (col. 20, lines 24-28 (for each label a score is provided, including AFIB, RBBB, and PVC)).
Hu and Fontanarava are both considered to be analogous to the claimed invention because they are in the same field of classifying ECG signals to detect cardiac conditions. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Hu to incorporate the teachings of Fontanarava listed, and provide an encoder-decoder type segmentation algorithm for each point of the ECG wave, and having a probability value among classes. Doing so would allow a more enhanced analysis of the ECG wave, by providing exact regions where the tremors are located, as well as providing probability values that are associated with the tremors.
Regarding claim 2, Hu (in view of Fontanarava) teaches the apparatus according to claim 1, wherein the classification unit (Fig. 6, element 60, para. 0182 (classification device)) checks respective sections of a P wave, a Q wave, an R wave, an S wave, a T wave, and an ROI (Region of Interest) (para. 0056 (QRS wave to determine the R position), 0097 (F wave characteristics)) included in the ECG wave (Fig. 1, element S104, para. 0047 (disappearance of P waves and the generation of F waves)), and sets the ROI as a window section of a preset time unit on the ECG wave (para. 0112 (QRS wave positioning), 0115 (sample points), 0122 (sample points is used to slide within the filtered ECG signal)).
Regarding Claim 4, Hu (in view of Fontanarava) teaches the apparatus according to claim 3, wherein the classification unit (Fig. 6, element 60, para. 0182 (classification device)) labels the section having the value of 1 as the atrial fibrillation wave (Fig. 7, element 72, para. 0189 (displays the atrial arrhythmia type)).
Regarding Claim 5, Hu (in view of Fontanarava) teaches the apparatus according to claim 1, further comprising a learning unit (para. 0016 (classifier)) that performs learning using only the atrial fibrillation wave as input to generate an atrial fibrillation learning result (para. 0016 (classifier is trained using ECG signal samples and the corresponding arrhythmia type), 0050 (threshold can be determined by the feature distribution of the training set samples)).
Regarding Claim 6, Hu (in view of Fontanarava) teaches the apparatus according to claim 2, wherein the classification unit (Fig. 6, element 60, para. 0182 (classification device)) moves the ROI section to overlap on the ECG wave (para. 0112 (QRS wave positioning), 0115 (sample points), 0122 (sample points is used to slide within the filtered ECG signal)) to determine exact start and end points of the atrial fibrillation after the labeling is completed (Fig. 5, para. 0132 (amplitude of the sample point is the maximum value in the window)).
Regarding Claim 9, Hu (in view of Fontanarava) teaches the apparatus according to claim 3, wherein the atrial fibrillation determination unit (Fig. 6, element 63, para. 0185 (determination unit)) determines whether the atrial fibrillation has occurred by checking the proportion of the ROI section determined as the atrial fibrillation and labeled as 1 (Fig. 7, element 72, para. 0189 (displays the atrial arrhythmia type)) in the whole ECG wave (para. 0178 (extracts relevant information of F wave characteristics), 0185 (arrhythmia is determined based on signal features)).
Regarding Claim 10, Hu (in view of Fontanarava) teaches the apparatus according to claim 2, wherein the classification unit (Fig. 6, element 60, para. 0182 (classification device)) detects the atrial fibrillation wave according to an irregularity of an RR interval between the R wave and the next R wave and a morphological shape representing baseline fluctuation (para. 0055-0056 (R wave intervals)), in beat cycles of the ECG wave (Fig. 5, para. 0150 (morphology of F waves).
Claims 3 and 7-8 are rejected under 35 U.S.C. 103 as being unpatentable over Hu and in view of Fontanarava, and in further view of Datta et al. (US 10750968 B2), hereinafter Datta.
Regarding Claim 3, Hu (in view of Fontanarava) teaches the apparatus according to claim 2, wherein the classification unit (Fig. 6, element 60, para. 0182 (classification device)) labels, in a case where the fibrillation wave of the preset threshold or greater (para. 0052-0053 (analyze signal until the type of arrhythmia is determined based on corresponding thresholds)) is detected in the ROI section of the ECG wave and the ROI section is determined as the atrial fibrillation (para. 0056 (QRS wave to determine the R position), 0097 (F wave characteristics)), the ROI section as 1, and labels (Fig. 3, element S3034).
Hu does not teach a case where the classification unit labels the ROI section is determined as non-atrial fibrillation, the ROI section as 0.
Datta teaches an apparatus (col. 11, lines 40-44) wherein the classification unit (Fig. 1, element 100, col. 5, lines 49-54 (system stores parameters and features of the ECG signal)) labels, in a case where the fibrillation wave of the preset threshold or greater (col. 6, lines 35-45 (noise threshold)) is detected in the ROI section of the ECG wave and the ROI section is determined as the atrial fibrillation, the ROI section as 1 (Fig. 3), and labels, (col. 9, lines 5-8 (binary cascade classifier)) in a case where the fibrillation wave below the preset threshold is detected in the ROI section and the ROI section is determined as non-atrial fibrillation the ROI section as 0 (col. 9, lines 19-20 (normal output)).
Hu, Fontanarava, and Datta are all considered to be analogous to the claimed invention because they are in the same field of classifying ECG signals to detect cardiac conditions. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Hu to incorporate the teachings of Datta and provide a classification unit that labels ECG segments corresponding to non-atrial fibrillation conditions. Doing so would allow the classification unit to distinguish between atrial fibrillation and non- atrial fibrillation waveform segments, thereby improving the accuracy of the ECG classification results. Additionally, Datta teaches assigning a classification label to ECG waveform segments corresponding to non-atrial fibrillation conditions. Although Datta discloses labeling the output with letters, substituting a numerical value for the label would have been obvious, because both elements provide a simple output for distinguishing a non-atrial fibrillation waveform segment. A person of ordinary skill in the art could have substituted one known element for another, and the results of the substitution would have been predictable.
Regarding Claim 7, Hu (in view of Fontanarava) teaches the apparatus according to claim 6, wherein the classification unit (Fig. 6, element 60, para. 0182 (classification device)) detects the atrial fibrillation (para. 0008 (analyzing each signal feature sequentially based on the classification rules), 0024 (type of arrhythmia is determined)) while moving the ROI section wave (para. 0112 (QRS wave positioning), 0115 (sample points), 0122 (sample points is used to slide within the filtered ECG signal)) in a preset time (para. 0055 (RR time interval), 0068 (F wave time series)) unit after the labeling is completed.
Hu does not teach moving the ROI section in a preset time unit after the labeling is complete.
Datta teaches an apparatus (col. 11, lines 40-44) wherein the classification unit (Fig. 1, element 100, col. 5, lines 49-54 (system stores parameters and features of the ECG signal)) detects the atrial fibrillation (col. 7, lines 35-38 (classifying atrial fibrillation waves), col. 9, lines 5-8 (binary cascade classifier)) while moving the ROI section (col. 7, lines 25-27 (amplitude difference)) in a preset time unit (Fig. 5, col. 6 lines 47-50 (time axis), col. 7 lines 64-66 (RR interval time series), col. 8 lines 45-48 (time features for ECG signal)) after the labeling is completed.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Hu to incorporate the teachings of Datta and provide a preset time unit while moving the ROT section. Doing so, would have allowed for a simplified process, by allowing a more concise ECG window view. This will display important cardiac information by following the R points correspond to the peak over time, allowing for the signal to be safely marked as a signal or noise for further processing, thereby improving noise detection.
Regarding Claim 8, Hu (in view of Fontanarava) teaches the apparatus according to claim 6, wherein the classification unit (Fig. 6, element 60, para. 0182 (classification device)) determines a point at which the atrial fibrillation wave (para. 0008 (analyzing each signal feature sequentially based on the classification rules), 0024 (type of arrhythmia is determined)) is first detected in the ROI section as the start point (para. 0132 (amplitude of the sample point is the maximum value in the window)), and determines a point at which the atrial fibrillation wave is not detected as the end point of atrial fibrillation while moving the ROI section (para. 0112 (QRS wave positioning), 0115 (sample points), 0122 (sample points is used to slide within the filtered ECG signal)).
Hu does not teach moving the ROI section in a preset time unit.
Datta teaches an apparatus (col. 11, lines 40-44) wherein the classification unit (Fig. 1, element 100, col. 5, lines 49-54 (system stores parameters and features of the ECG signal)) determines a point at which the atrial fibrillation wave (col. 7, lines 35-38 (classifying atrial fibrillation waves), col. 9, lines 5-8 (binary cascade classifier)) is first detected in the ROI section as the start point, and determines a point at which the atrial fibrillation wave is not detected as the end point of atrial fibrillation (col. 7, lines 25-27 (amplitude difference)) while moving the ROI section in a preset time unit (Fig. 5, col. 6 lines 47-50 (time axis), col. 7 lines 64-66 (RR interval time series), col. 8 lines 45-48 (time features for ECG signal)).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Hu to incorporate the teachings of Datta listed, and provide a preset time unit while moving the ROT section to determine a start point (atrial fibrillation) and end point (non-atrial fibrillation). Doing so, would have allowed for a descriptive ECG view that displays a result while moving the ROI section through a time interval. This will improve diagnostic accuracy by viewing the time points of irregular fluctuations.
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 EILEEN ROBLES whose telephone number is (571)429-9383. The examiner can normally be reached Monday-Friday: 8:00 - 5:00 PM.
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, Niketa Patel can be reached at (571) 272-4156. 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.
/EILEEN ROBLES/Examiner, Art Unit 3792
/William J Levicky/Primary Examiner, Art Unit 3796
Prosecution Insights