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 Arguments
Applicant’s arguments filed 7/24/2026 with respect to the rejection of claims 1, 2 and 11 under 35 USC 112(a) as failing to comply with the written description requirement have been fully considered and are persuasive. The term “check” which invoked the rejection has been deleted, and the Examiner agrees that the prior issue has thereby been resolved. Therefore, the rejection has been withdrawn.
Applicant’s arguments regarding the rejection of Claims 1-11 under 35 USC 112(b) as indefinite have been fully considered and are persuasive. The Examiner agrees that the foregoing amendments have resolved the prior cited indefiniteness issues. Therefore, the rejection has been withdrawn.
Applicant’s arguments regarding the rejection of Claims 1-11 under 35 USC 101 have been fully considered but are not persuasive. Applicant argues that the claims sufficiently integrate the recited abstract ideas into a practical application because the claimed subject matter represents such an improvement to a computer or other technology contemplated by MPEP 2106.05(a). The Examiner respectfully disagrees. The improvement highlighted by Applicant is the recited judicial exception itself. However, “…the judicial exception alone cannot provide the improvement. The improvement can be provided by one or more additional elements.” MPEP 2106.05(a). Applicant’s arguments are thus unpersuasive. Applicant’s arguments regarding the semantic segmentation algorithm recited by Claim 1 as amended being incapable of being executed in the human mind are moot, as this new limitation is herein appropriately deemed a mathematical calculation.
Applicant’s arguments regarding the rejection of Independent Claim 1 under 35 U.S.C. 102(a)(1) as being anticipated by US 2016/0089047 A1 to Jonnada et al. (“Jonnada”) have been fully considered and are persuasive. Claim 1 has been amended significantly to include several limitations which the Examiner agrees Jonnada does not disclose. Therefore, the rejection has been withdrawn. However, upon further consideration, new grounds of rejection is made in view of CN 110384482 A and CN 111110228 A.
Applicant’s arguments regarding the rejection of dependent Claims 2-11 under 35 USC 102 and 35 USC 103 respectively are based on Applicant’s arguments regarding Independent Claim 1. Applicant’s arguments have been fully considered and are persuasive for the same reasons as explained above with respect to Claim 1. Therefore, the rejection has been withdrawn. However, upon further consideration, new grounds of rejection is made in view of CN 110384482 A and CN 111110228 A.
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 1-11 are rejected under 35 U.S.C. § 101 because the claimed invention is directed to a judicial exception (i.e., an abstract idea) without significantly more.
Eligibility Step 1 – The Four Categories of Statutory Subject Matter
Claims 1-11 each fall within one of the four categories of statutory subject matter. Claims 1-11 are drawn to an “apparatus” (i.e., a machine), and thus fall within one of the four statutory categories.
Eligibility Step 2A, Prong One
Claims 1-11 recite abstract ideas:
Regarding Independent Claim 1:
“apply a one-dimensional (1D) semantic segmentation algorithm to the ECG wave to output a classification probability value for each of a plurality of classes for each point of the ECG wave” recites an abstract idea (i.e., mathematical calculation) when afforded its broadest reasonable interpretation. Such a one-dimensional (1D) semantic segmentation algorithm is a mathematical calculation. See MPEP 2106.04(a)(2)(I).
“label, for each point, a classification value corresponding to a class having a highest classification probability value among the plurality of classes, the plurality of classes including a P wave, a Q wave, an R wave, an S wave, a T wave, and a noise wave” recites an abstract idea (i.e., a mental process) when afforded its broadest reasonable interpretation. Such labeling is practically performable in the human mind, as it is a judgment. See MPEP 2106.04(a)(III).
“select only the noise wave labeled as the noise wave on the basis of the classification value for each point; and remove only the noise wave labeled as the noise wave” recites an abstract idea (i.e., a mental process) when afforded its broadest reasonable interpretation. Such selecting is practically performable in the human mind, as it is an evaluation. See MPEP 2106.04(a)(III). For example, a human could evaluate the data to determine which portion is labeled as noise.
Regarding Claim 2:
“identify features…” recites an abstract idea (i.e., a mental process) when afforded its broadest reasonable interpretation. Such identifying features is practically performable in the human mind, as it is an observation. See MPEP 2106.04(a)(III).
Regarding Claim 3:
“calculate a noise probability value…” recites an abstract idea (specifically, a mathematical calculation) when afforded its broadest reasonable interpretation in light of the Specification. See MPEP 2106.04(a)(2)(I)(C).
“determine, in a case where the noise probability value is… determine, in a case where the noise probability value is…” recites an abstract idea (i.e., a mental process) when afforded its broadest reasonable interpretation. Such determining as claimed is practically performable in the human mind, as it is a judgment. See MPEP 2106.04(a)(III).
Regarding Claim 4:
“labels the section…” recites an abstract idea (i.e., a mental process) when afforded its broadest reasonable interpretation for the same reasons as explained above with respect to the similar limitation of Claim 1.
Regarding Claim 5:
“generate an ECG learning result…” recites an abstract idea (specifically, a mathematical calculation) when afforded its broadest reasonable interpretation in light of the Specification. See MPEP 2106.04(a)(2)(I)(C).
Regarding Claim 6:
“label: a specific point of the ECG wave as…” (i.e., each of the labeling recitations) recites an abstract idea (i.e., a mental process) when afforded its broadest reasonable interpretation for the same reasons as explained above with respect to the similar limitation of Claim 1.
Regarding Claim 7:
“label: a specific point of the ECG wave as…” (i.e., each of the labeling recitations) recites an abstract idea (i.e., a mental process) when afforded its broadest reasonable interpretation for the same reasons as explained above with respect to the similar limitation of Claim 1.
Regarding Claims 8-10, Claims 8-10 depend from and further limit Claim 1, and recite abstract ideas for the same reasons as does Claim 1.
Regarding Claim 11:
“determine an abnormal state by evaluating the classification value…” recites an abstract idea (i.e., a mental process) when afforded its broadest reasonable interpretation for the same reasons as explained above with respect to the similar limitation of Claim 2.
Eligibility Step 2A, Prong Two
Claims 1-11 do not recite additional elements that integrate the judicial exception into a practical application.
Regarding Independent Claim 1:
“acquire an ECG wave for each of a plurality of persons” amounts to necessary data gathering in conjunction with the recited mental process, and is insignificant extra-solution activity insufficient to integrate the recited abstract ideas into a practical application. See MPEP 2106.05(g).
“remove only the noise wave labeled as the noise wave” amounts to necessary data outputting in conjunction with the recited mental process, and is insignificant extra-solution activity insufficient to integrate the recited abstract ideas into a practical application. See MPEP 2106.05(g).
The term “a processor” is a generic computer structures for performing a generic computer functions, and thus simply amounts to using a computer as a tool to implement the abstract idea. See MPEP 2106.05(f).
Regarding Claims 2-11, Claims 2-11 do not recite any additional elements.
Eligibility Step 2B
Claims 1-11 do not amount to significantly more than the abstract ideas recited therein:
Regarding Independent Claim 1:
““acquire an ECG wave for each of a plurality of persons” does not contribute an inventive concept. Such ECG acquisition is well-understood, routine and conventional in the art. See, e.g., US 6171256 B1 at Col. 5, Ln. 56-61.
“remove only the noise wave labeled as the noise wave” does not contribute an inventive concept. Such noise removal is well-understood, routine and conventional in the art. See, e.g., US 20160228640 A1 at Para. [0031].
The term “a processor” does not contribute an inventive concept. The processor is a generic computer component for performing a generic computer function, and is recited at a high level of generality. Contextually, the inclusion of such a processor amounts to mere instructions to implement an abstract an abstract idea on a computer, which “the courts have found not to be enough to qualify as ‘significantly more’ when recited in a claim with a judicial exception.” See MPEP 2106.05(I(A), citing Alice Corp., 573 U.S. at 225-26, 110 USPQ2d at 1984.
Regarding Claims 2-11, Claims 2-11 do not recite any additional elements.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1, 2 and 6-7, and Claims 3-5 and 8-11 by dependency, are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Regarding Independent Claim 1:
Claim 1 recites “apply a one-dimensional (1D) semantic segmentation algorithm to the ECG wave to output a classification probability value for each of a plurality of classes for each point of the ECG wave.”
The Present Specification expands upon this limitation at Para. [0080], but does not describe what a “class” is envisioned to entail, and thus does not describe the output of the one-dimensional (1D) semantic segmentation algorithm in such a way as to apprise one of ordinary skill in the art of what is being done.
The limitation “a classification value corresponding to a class having a highest classification probability value among the plurality of classes” is not described in such a way as to reasonably convey to one skilled in the relevant art that the inventor had possession of the claimed invention at the time the application was filed for the same reasons.
The Present Specification does not describe what the term “classification probability value” entails in such manner as would apprise one of ordinary skill in the art of what is being done.
As best understood by the Examiner, Claim 1 is using a one dimensional semantic segmentation algorithm to classify various segments of an ECG wave as one of a P wave, a Q wave, a R wave, a S wave, a T wave, and a noise wave. The noise wave is then removed.
Claim 1 uses probability of each to accomplish this, but the Present Specification does not describe the manner in which probability is used in such a way as would enable one of ordinary skill in the art to discern what is being done.
Overarchingly, the Present Specification fails to sufficiently describe the inputs and outputs of the recited “semantic segmentation algorithm” in such a way as to reasonably convey to one skilled in the relevant art that the inventor had possession of the claimed invention at the time the application was filed.
Regarding Claim 2, Claim 2 recites “wherein the processor is further configured to identify features of respective sections of the P wave, the Q wave, the R wave, the S wave, the T wave, and the noise wave included in the ECG wave.” The Present Specification does not describe what is being identified or where it is being identified (i.e., what “respective sections” means) in such a way as would allow one of ordinary skill in the art would is being done. Typically in the art, the P wave, the Q wave, the R wave, the S wave and the T wave are referred to as features. However, the language of Claim 2 makes clear that the identified features are not the P wave, the Q wave, the R wave, the S wave and the T wave. The Present Specification fails to sufficiently describe the inputs and outputs of the recited algorithm in such a way as to reasonably convey to one skilled in the relevant art that the inventor had possession of the claimed invention at the time the application was filed.
Regarding Claims 6 and 7:
Claims 6 and 7 recite “a specific point.” The Present Specification does not include this phrase, and provides no guidance with respect to what such “a specific point” entails. The Present Specification fails to sufficiently describe the inputs and outputs of the recited algorithm in such a way as to reasonably convey to one skilled in the relevant art that the inventor had possession of the claimed invention at the time the application was filed.
Claims 6 and 7 recite “label: a specific point of the ECG was as [x].” The Present Specification describes the process of Claim 7 at Paras. [0054] through [0057], but describes sections rather than points being labeled. That Claims 6 an 7 recite points rather than sections as being so-labeled constitutes new matter.
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, 4, and 6-7, and Claims 2-3, 5 and 8-11 by dependency 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 Independent Claim 1:
Claim 1 recites “acquire an ECG wave for each of a plurality of persons.” It is unclear in what sense “an ECG wave” can be acquired for “each of a plurality of persons.” That is, Claim 1 requires a single ECG wave (as evidenced by the subsequent recitation “apply … to the ECG wave…”), but requires that this single ECG wave be acquired for “each of a plurality of persons.” The scope of ECG waves upon which the invention of Claim 1 is performed is thus unclear.
For purposes of this Office Action, the phrase “acquire an ECG wave for each of a plurality of persons” is being interpreted to mean that the device acquires a single ECG wave and performs all subsequent operations upon said single ECG wave, but is able to acquire such a single ECG wave from multiple patients (i.e., at different times).
Claim 1 recites “to output a classification probability value for each of a plurality of classes for each point of the ECG wave.” It is grammatically unclear which claim element is modified by the term “for each point of the ECG wave.” The scope of Claim 1 thus cannot be discerned, and Claim 1 is indefinite.
For purposes of this Office Action, and in view of the above written description issues regarding the term “classes,” the above limitation is being interpreted to mean that a probability that a particular segment of the wave represents a particular feature (e.g., P wave, Q wave, R wave, S wave, T wave, noise wave) is output.
Claim 1 recites “and label, for each point, a classification value corresponding to a class having a highest classification probability value among the plurality of classes, the plurality of classes including a P wave, a Q wave, an R wave, an S wave, a T wave, and a noise wave.” It is grammatically unclear what is being labeled.
For purposes of this Office Action, the above limitation is being interpreted to mean that “P wave, a Q wave, an R wave, an S wave, a T wave, and a noise wave” are labeled as such if the determined probability indicates a particular segment represents a particular feature.
Claim 1 recites “select only the noise wave labeled as the noise wave on the basis of the classification value for each point.” It is grammatically unclear which claim element the term “on the basis of the classification value for each point” is intended to modify.
For purposes of this Office Action, the above limitation is being interpreted to mean that the noise wave is selected on the basis of having been classified a noise wave.
Regarding Claim 4, Claim 4 recites “label the point.” The term “the point” derives its antecedent basis from the Claim 3 recitation “each point of the ECG wave.” Claim 3 requires multiple points, whereas Claim 4 references one of those points as “the point.” It is unclear what the term “the point” is intended to reference.
For purposes of this Office Action, Claim 4 is being interpreted to mean that portions of the ECG signal determined to be noise are identified as such.
Regarding Claim 6, Claim 6 recites “a specific point” several times. It is unclear whether the several “a specific point[s]” of Claim 6 are the same or different. It is thus unclear what Claim 6 requires to be done.
For purposes of this Office Action, Claim 6 is being interpreted to mean that sections of the ECG wave are labeled according to their classifications.
Regarding Claim 7, Claim 7 recites “a specific point” several times. It is unclear whether the several “a specific point[s]” of Claim 7 are the same or different. It is thus unclear what Claim 7 requires to be done.
Claim 7 is being interpreted similarly to Claim 6.
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, 2 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over CN 110384482 A (“CN’482”) in view of CN 111110228 A (“CN ‘228”).
Regarding Independent Claim 1, CN ‘482 teaches:
An electrocardiogram (ECG) noise discriminating apparatus comprising: (CN ‘482 Machine Translation at Pg. 2 of 31, Third Paragraph from Bottom of Page, “…the invention provides a signal classification device for electrocardiogram…”);
a processor configured to: (CN ‘482, Machine Translation at Pg. 3 of 31, Fourth Paragraph, “…this invention provides a computer device comprising a memory and a processor, the memory storing a computer program…”);
acquire an ECG wave for each of a plurality of persons; (CN ‘482 Machine Translation at Pg. 4 of 31, “…ECG signal type detection method provided by the invention can be applied to the computer device as shown in FIG. 1. … with the wearable device, the portable electrocardiograph equipment such as communication, receive electrocardiograph signal sent by these devices and other information.”);
As explained above, the phrase “acquire an ECG wave for each of a plurality of persons” is being interpreted to mean that the device acquires a single ECG wave and performs all subsequent operations upon said single ECG wave, but is able to acquire such a single ECG wave from multiple patients (i.e., at different times).
apply a … algorithm to the ECG wave to output a classification probability value for each of a plurality of classes for each point of the ECG wave, (CN ‘482 Machine Translation at Pg. 17 of 31, Second Paragraph from Bottom of Page);
As explained above, this limitation is being interpreted to mean that a probability that a particular segment of the wave represents a particular feature (e.g., P wave, Q wave, R wave, S wave, T wave, noise wave) is output.
CN ‘482 describes making such a determination with respect to the above features based on probability at CN ‘482 Machine Translation at Pg. 17 of 31, Second Paragraph from Bottom of Page.
The Examiner notes that CN ‘482 does not use a “semantic segmentation algorithm,” but instead employs a different algorithm. This deficiency is addressed below.
and label, for each point, a classification value corresponding to a class having a highest classification probability value among the plurality of classes, the plurality of classes including a P wave, a Q wave, an R wave, an S wave, a T wave, and a noise wave; (CN ‘482 Machine Translation at Pg. 4 of 31, First Paragraph, referencing “storing feature information”);
As explained above, this limitation is being interpreted to mean that “P wave, a Q wave, an R wave, an S wave, a T wave, and a noise wave” are labeled as such if the determined probability indicates a particular segment represents a particular feature.
CN ‘482 describes “storing feature information” at CN ‘482 at Pg. 4 of 31, First Paragraph. Storing feature information is such “labeling” as claimed when the term is afforded its broadest reasonable interpretation.
select only the noise wave labeled as the noise wave on the basis of the classification value for each point; and remove only the noise wave labeled as the noise wave. (CN ‘482 Machine Translation at Pg. 6 of 31, First Paragraph, describing removing noise ahead of using “wave transforming technology [to] extract waveform of each wave band in electrocardiogram signal.”).
CN ‘482 does not disclose:
a one-dimensional (1D) semantic segmentation algorithm
That is, CN ‘482 teaches applying an algorithm in the manner clamed, but does not disclose “wherein the algorithm is a one-dimensional (1D) semantic segmentation algorithm.”
CN ‘228 describes “an electro-cardio signal detecting technology” (Abstract). CN ‘228 is analogous art.
CN ‘228 teaches:
a one-dimensional (1D) semantic segmentation algorithm (CN ‘228 Machine Translation at Pg. 5 of 8, Fifth Paragraph, “The preferred embodiment uses semantic segmentation network to learn the original electrocardiogram signal based on network structure dividing the existing semantic network is improved, the semantic segmentation adding bidirectional GRU layer in the network. Specifically, as shown in FIG. 3, the semantic of the present embodiment uses the dividing network is U-Net network for one-dimensional signal…”).
It would have been obvious for a person of ordinary skill in the art before the effective filing date of the claimed invention to modify the device of CN ‘482 with the teachings of CN ‘228 (i.e.., to employ such a semantic segmentation algorithm as taught by CN ‘228 in place of CN ‘482’s algorithm) in order to eliminate the need for pre-processing ECG data (CN ‘228 Machine Translation at Pg. 2 of 8, Second Paragraph).
Regarding Claim 2, the combination of CN ‘482 and CN ‘228 renders obvious the entirety of Claim 1 as explained above.
CN ‘482 additionally teaches:
wherein the processor is further configured to identify features of respective sections of the P wave, the Q wave, the R wave, the S wave, the T wave, and the noise wave included in the ECG wave (CN ‘482 Machine Translation at Pg. 7 of 31, Third Paragraph).
As best understood by the Examiner, Claim 2 requires some aspect of the recited sections to be determined. CN ‘482 describes determining “number, mean, maximum value, minimum value, median, variance, skewness, kurtosis, width, etc.” of similar such sections at CN ‘482 Machine Translation at Pg. 7 of 31, Third Paragraph.
Regarding Claim 11, the combination of CN ‘482 and CN ‘228 renders obvious the entirety of Claim 1 as explained above.
CN ‘482 additionally teaches:
wherein the processor is further configured to determine an abnormal state by evaluating the classification value for each point in time series in a state where the noise wave labeled as the noise wave is removed. (CN ‘482 Machine Translation at Pg. 6 of 31, Fifth and Sixth Paragraphs, describing determining normal or abnormal based on characteristics of extracted features)
Claims 3-4 are rejected under 35 U.S.C. 103 as being unpatentable over CN 110384482 A (“CN’482”) in view of CN 111110228 A (“CN ‘228”) as applied to Claim 1 above, and further in view of previously cited US 2017/0340288 A1 to Bae et al. (“Bae”).
Regarding Claim 3,the combination of CN ‘482 and CN ‘228 renders obvious the entirety of Claim 1 as explained above.
The combination of CN ‘482 and CN ‘228 does not disclose:
wherein the processer is further configured to calculate a noise probability value having a maximum value of 1 of the feature for each point of the ECG wave, and determine, in a case where the noise probability value is equal to or higher than a threshold, that the point corresponds to the noise and gives a value of 1, and determine, in a case where the probability value is lower than the threshold, that the section is not the noise wave and give a value of 0.
Bae describes “A method and an apparatus to remove a noise from an electrocardiography (ECG) sensor signal…” (Abstract). Bae is analogous art.
Bae teaches:
wherein the processer is further configured to calculate a noise probability value having a maximum value of 1 of the feature for each point of the ECG wave, and determine, in a case where the noise probability value is equal to or higher than a threshold, that the point corresponds to the noise and gives a value of 1, and determine, in a case where the probability value is lower than the threshold, that the section is not the noise wave and give a value of 0. (Para. [0062], “ In operation 820, the noise removing apparatus extracts an ECG estimation signal from the sensor signal based on a peak value of the sensor signal. In operation 830, the noise removing apparatus determines a first comparison value between the ECG estimation signal and a first reference signal indicating an average form of ECG signals. … Each of the first threshold value and the first comparison value corresponding to the cosine distance between the ECG estimation signal and the first reference signal may have a value between zero and one. In a case in which first threshold value is determined to be a value greater than an appropriate value, a probability of removing a noise from the sensor signal increases, but an individual characteristic of the ECG signal may also be removed, thereby making it more difficult to classify users based on the ECG signal. … The first threshold value of 0.357 is an optimal value…”);
It would have been obvious for a person of ordinary skill in the art before the effective filing date of the claimed invention to modify the device of CN ‘482 and CN ‘228 with the teachings of Bae (i.e., to determine noise probabilistically via comparison to a threshold in the manner of Bae) in order to increase reliability (Bae at Para. [0003]).
Regarding Claim 4, the combination of CN ‘482, CN ‘228 and Bae renders obvious the entirety of Claim 3 as explained above.
Bae additionally teaches:
wherein the processor is further configured to label the point having the value of 1 as the noise (Para. [0062], “Each of the first threshold value and the first comparison value corresponding to the cosine distance between the ECG estimation signal and the first reference signal may have a value between zero and one. In a case in which first threshold value is determined to be a value greater than an appropriate value, a probability of removing a noise from the sensor signal increases…”).
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over CN 110384482 A (“CN’482”) in view of CN 111110228 A (“CN ‘228”) as applied to Claim 1 above, and further in view of previously cited US 2019/0357794 A1 to Bardy et al. (“Bardy”) and Galeotti L, Scully CG. A method to extract realistic artifacts from electrocardiogram recordings for robust algorithm testing. J Electrocardiol. 2018 Nov-Dec;51(6S):S56-S60. doi: 10.1016/j.jelectrocard.2018.08.023. Epub 2018 Aug 18 (“Galeotti”).
Regarding Claim 5, the combination of CN ‘482 and CN ‘228 renders obvious the entirety of Claim 1 as explained above.
The combination of CN ‘482 and CN ‘228 does not disclose:
wherein the processor is further configured to generate an ECG learning result by performing learning using only the noise wave as input.
Bardy describes “A system for facilitating a cardiac rhythm disorder diagnosis with the aid of a digital computer…” (Abstract). Bardy is analogous art.
Bardy teaches:
further comprising: a learning unit that generates an ECG learning result by performing learning using … the noise wave as input (Para. [0093], “The noise can be identified by a reviewer or automatically via a classifier or artificial intelligence, such as by machine learning or based on one or more thresholds.”).
It would have been obvious for a person of ordinary skill in the art before the effective filing date of the claimed invention to modify the device of CN ‘428 and CN ‘228 with the teachings of Bardy (i.e., to incorporate such a learning unit as taught by Bardy in the device of CN ‘428 and CN ‘228) in order to increase accuracy of ECG-based diagnoses (Bardy at Para. [0093]).
The combination of CN ‘428 and CN ‘228 and Bardy does not teach:
only the noise wave as input
Galeotti describes “A method to extract realistic artifacts from electrocardiogram recordings for robust algorithm testing” (Title). Galeotti is analogous art.
Galeotti teaches:
only the noise wave as input (Abstract, “Recordings of signal noise and artifacts can be added to clean electrocardiogram (ECG) records to assess the performance of ECG and arrhythmia analysis algorithms in the presence of noise. We present a method to estimate device-specific signal noise and artifacts from ECG records. … Estimating noise from ECG records is a viable approach to generate noise and artifacts-only signals.”).
It would have been obvious for a person of ordinary skill in the art before the effective filing date of the claimed invention to modify the device of combined CN ‘428, CN ‘228 and Bardy with the teachings of Galeotti (i.e., to train the learning model of combined CN ‘428, CN ‘228 and Bardy using only noise as an input in the manner taught by Galeotti) in order to facilitate device-specific ECG recording (Galeotti at Abstract, “Objective” section).
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over CN 110384482 A (“CN’482”) in view of CN 111110228 A (“CN ‘228”) as applied to Claim 1 above, and further in view of previously cited Aziz, S., Ahmed, S. & Alouini, MS. ECG-based machine-learning algorithms for heartbeat classification. Sci Rep 11, 18738 (2021). https://doi.org/10.1038/s41598-021-97118-5 (“Aziz”).
Regarding Claim 6, the combination of CN ‘482 and CN ‘228 renders obvious the entirety of Claim 1 as explained above.
The combination of CN ‘482 and CN ‘228 does not disclose:
wherein the processor is further configured to label, a specific point of the ECG wave as 0 in a case where a the specific point of the ECG wave is classified as a baseline on the basis of the classification value; the specific point of the ECG wave as 1 in a case where a the specific point of the ECG wave is classified as the P wave on the basis of the classification value; the specific point of the ECG wave as 5 in a case where a the specific section point of the ECG wave is classified as the peak of the R wave on the basis of the classification value; the specific section point of the ECG wave as 6 in a case where a the specific point of the ECG wave is classified as the T wave on the basis of the classification value; and the specific section point of the ECG wave as 7 in a case where the specific point of the ECG wave is classified as the noise wave on the basis of the classification value.
Aziz describes “ECG-based machine-learning algorithms for heartbeat classification” (Title). Aziz is analogous art.
Aziz teaches:
wherein the processor is further configured to label, a specific point of the ECG wave as 0 in a case where a the specific point of the ECG wave is classified as a baseline on the basis of the classification value; the specific point of the ECG wave as 1 in a case where a the specific point of the ECG wave is classified as the P wave on the basis of the classification value; the specific point of the ECG wave as 5 in a case where a the specific section point of the ECG wave is classified as the peak of the R wave on the basis of the classification value; the specific section point of the ECG wave as 6 in a case where a the specific point of the ECG wave is classified as the T wave on the basis of the classification value; and the specific section point of the ECG wave as 7 in a case where the specific point of the ECG wave is classified as the noise wave on the basis of the classification value. (Pg. 2, “Figure 1. Morphology of a normal ECG”).
Aziz’s Figure 1 depicts a “normal ECG” wave which is labeled at the claimed sections.
Aziz does not label “the specific section as 1” with respect to the P wave, and does not label the other identified sections with numerals 1-7. However, the particular numerical labels recited by Claim 6 are being interpreted as printed matter which bears no functional relationship with the underlying apparatus. Accordingly, the particular numerical labels 1-7 are not afforded patentable weight. See MPEP 2111.05(I)(A) (“To be given patentable weight, the printed matter and associated product must be in a functional relationship.”); MPEP 2111.05(I)(B), (“Where a product merely serves as a support for printed matter, no functional relationship exists.”); See also Ex parte Gwinn, 112 USPQ 439, 446-47 (Bd. Pat. App. & Int. 1955) (Court held that claims directed to a set of dice which differed from the prior art solely by the printed matter in the dice were properly rejected on prior art because there was no new feature of physical structure and no new relation of printed matter to physical structure.).
It would have been obvious for a person of ordinary skill in the art before the effective filing date of the claimed invention to modify the device of CN ‘482 and CN ‘228 with the teachings of Aziz (i.e., to label the ECG of CN ‘482 and CN ‘228 in the manner of Aziz) in order to facilitate peak detection (Aziz at Pg. 2, First Paragraph).
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over CN 110384482 A (“CN’482”) in view of CN 111110228 A (“CN ‘228”) as applied to Claim 1 above, and further in view of previously cited US 2016/0089047 A1 to Jonnada et al. (“Jonnada”).
Regarding Claim 7, the combination of CN ‘482 and CN ‘228 renders obvious the entirety of Claim 1 as explained above.
The combination of CN ‘482 and CN ‘228 does not disclose:
wherein the processor is further configured to label: a specific point of the ECG wave as 2 in a case where a the specific point of the ECG wave is classified as a normal beat (N) of a QRS complex on the basis of the classification value; the specific point of the ECG wave as 3 in a case where a the specific
Jonnada describes “Electrocardiograph (ecg) signal processing” (Title). Jonnada is analogous art.
Jonnada teaches:
wherein the processor is further configured to label: a specific point of the ECG wave as 2 in a case where a the specific point of the ECG wave is classified as a normal beat (N) of a QRS complex on the basis of the classification value; the specific point of the ECG wave as 3 in a case where a the specificsupraventricular beat (S) of the QRS complex on the basis of the classification value; and the specific point of the ECG wave as 4 in a case where a the specific point of the ECG wave is classified as a ventricular beat (V) of the QRS complex on the basis of the classification value. (Paras. [0034] through [0035]).
Jonnada discusses identifying characteristics of the QRS complex, what such characteristics are representative of, and estimating time-domain features based thereupon at Paras. [0034] through [0035].
Jonnada does not label “the specific section as 1,” and does not label the other identified sections with numerals 1-4. However, the particular numerical labels recited by Claim 7 are being interpreted as printed matter which bears no functional relationship with the underlying apparatus. Accordingly, the particular numerical labels 1-4 are not afforded patentable weight. See MPEP 2111.05(I)(A) (“To be given patentable weight, the printed matter and associated product must be in a functional relationship.”); MPEP 2111.05(I)(B), (“Where a product merely serves as a support for printed matter, no functional relationship exists.”); See also Ex parte Gwinn, 112 USPQ 439, 446-47 (Bd. Pat. App. & Int. 1955) (Court held that claims directed to a set of dice which differed from the prior art solely by the printed matter in the dice were properly rejected on prior art because there was no new feature of physical structure and no new relation of printed matter to physical structure.).
It would have been obvious for a person of ordinary skill in the art before the effective filing date of the claimed invention to modify the device of combined CN ‘482 and CN ‘228 with the teachings of Jonnada (i.e., to identifying characteristics of the QRS complex, what such characteristics are representative of, and estimating time-domain features based thereupon in the manner of Jonnada) in order to facilitate the identification of useful health metrics (Jonnada at Para. [0002]).
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over CN 110384482 A (“CN’482”) in view of CN 111110228 A (“CN ‘228”) as applied to Claim 1 above, and further in view of US 5730142 A to Sun et al. (“Sun”).
Regarding Claim 8, the combination of CN ‘482 and CN ‘228 renders obvious the entirety of Claim 1 as explained above.
The combination of CN ‘482 and CN ‘228 does not disclose:
wherein the processor is further configured to acquire 256 samples of the ECG waves per second for each of the plurality of persons.
Sun describes “A method and apparatus for detecting tachycardia in a patient…” (Abstract). Sun is analogous art.
Sun teaches:
wherein the ECG wave acquisition unit acquires 256 samples of the ECG waves per second for each of the plurality of persons. (Col. 3, Ln. 12-14, “FIG. 1 is representative of the technique of applying HMM to arryhythmia detection as described in the above-referenced Coast et al. articles. The ECG is sampled at a sample frequency, e.g. 256 Hz. or about every 4 ms…”)
It would have been obvious for a person of ordinary skill in the art before the effective filing date of the claimed invention to modify the device of CN ‘482 and CN ‘228 with eth teachings of Sun (i.e., to record ECG at a sampling rate of 256 Hz in the manner of Sun) in order to “retain morphological information.” (Sun at Col. 3, Ln. 28-30).
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over CN 110384482 A (“CN’482”) in view of CN 111110228 A (“CN ‘228”) as applied to Claim 1 above, and further in view of US 2020/0237246 A1 to Hu et al. (“Hu”)
Regarding Claim 9, the combination of CN ‘482 and CN ‘228 renders obvious the entirety of Claim 1 as explained above.
The combination of CN ‘482 and CN ‘228 does not disclose:
wherein the processor is further configured to convert the ECG wave for each of the plurality of persons into one-dimensional data.
Hu describes “An automatic recognition and classification method for electrocardiogram heartbeat based on artificial intelligence…” (Abstract). Hu is analogous art.
Hu teaches:
wherein the processor is further configured to convert the ECG wave for each of the plurality of persons into one-dimensional data (Para. [0034], “…data combination is performed on the lead heart beat analysis data to obtain the one-dimensional heart beat analysis array…”).
It would have been obvious for a person of ordinary skill in the art before the effective filing date of the claimed invention to modify the device of CN ‘482 and CN ‘228 with the teachings of Hu (i.e., to convert ECG data to one-dimensional data in the manner of Hu) in order to enhance the accuracy of heart beat classification (Hu at Para. [0034]).
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over CN 110384482 A (“CN’482”) in view of CN 111110228 A (“CN ‘228”) as applied to Claim 1 above, and further in view of US 2014/0276160 A1 to Zhang et al. (“Zhang”).
Regarding Claim 10, the combination of CN ‘482 and CN ‘228 renders obvious the entirety of Claim 1 as explained above
The combination of CN ‘482 and CN ‘228 does not disclose:
wherein the processor is further configured to record values for the P wave, a QRS complex including a normal beat (N) , a supraventricular beat (S) , and a ventricular beat (V), and the T wave in the ECG wave as multiple beats
Zhang describes “…an apparatus and method for avoiding ventricular fibrillation undersensing” (Para. [0001]). Zhang is analogous art.
Zhang teaches:
wherein the processor is further configured to record values for the P wave, a QRS complex including a normal beat (N) , a supraventricular beat (S) , and a ventricular beat (V), and the T wave in the ECG wave as multiple beats (Para. [0043], “ The beat may be classified as a normal supraventricular beat, an abnormal ventricular beat, or an unidentified beat based on comparisons of a morphology match metric and/or one or more beat features to a classification threshold. Beats are classified as ventricular beats, for example, when a beat morphology metric has a weak correlation to an analogous metric of a normal supraventricular beat and thus has a relatively stronger correlation to an analogous metric of an abnormal, ventricular beat. Threshold ranges may be defined to classify a beat as supraventricular, ventricular or unidentified, which could be noise.”).
It would have been obvious for a person of ordinary skill in the art before the effective filing date of the claimed invention to modify the device of CN ‘482 and CN ‘228 with the teachings of Zhang (i.e., to classify beats in the manner of Zhang) in order to prevent undersensing of ventricular signals (Zhang at Para. [0003]).
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 CHRISTOPHER J MUTCHLER whose telephone number is (571)272-8012. The examiner can normally be reached M-F 7:00 am - 4:00 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, Jennifer McDonald can be reached at 571-270-3061. 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.
/C.J.M./Examiner, Art Unit 3796
/Jennifer Pitrak McDonald/Supervisory Patent Examiner, Art Unit 3796
