DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
No claim limitations are interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.’
Claim Objections
Claims 17-18 and 23 are objected to because of the following informalities:
in claim 17, line 1: “wherein” should be inserted before “evaluating”;
in claim 17, line 2: “spectral” should be inserted before “tensor technique”;
in claim 18, line 5: “spectral” should be inserted before “tensor technique”; and
in claim 23, line 4: “breath” should be “breaths”.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
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 1-2, 4-11, 13, 15, 17-20, 22-23, and 29-30 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.
Claim 1 recites “the spectral images generated for each breath triplet” in line 11, which is indefinite. First, there is insufficient antecedent basis for “the spectral images” since claim 1, line 9 only recites a single spectral image, not a plurality of spectral images. Second, it is not clear if the single spectral image of claim 1, line 9 is part of the plurality of the spectral images of claim 1, line 11. Third, there is insufficient antecedent basis for the plurality of breath triplets implied in claim 1, line 11 since claim 1, lines 4-5 only recites a single breath triplet. Fourth, it is not clear if the single breath triplet is part of the plurality of breath triplets implied in claim 1, line 11. These issues need clarification and render claim 1 indefinite.
Claim 1 recites “a waveform” in line 14, but it is not clear if this recitation is referring to one of “a flow waveform, an airway pressure waveform, and/or an esophageal manometry waveform” of claim 1, lines 5-7. The relationship among these recitations should be made clear.
Claims 2 and 4-8 are rejected by virtue of their dependence from claim 1.
Claim 4 recites “a Fourier transform” in line 1 and “Fourier transforms” in line 3, but the relationship between these two recitations are not clear. Are they separate and distinct? If the former, is the recitation in line 1 a member of the recitation in line 3? These issues render claim 4 indefinite.
Claim 4 recites “the waveform” in line 4, but it is not clear if this recitation is referring to one of “a flow waveform, an airway pressure waveform, and/or an esophageal manometry waveform” of claim 1, lines 5-7 and/or “a waveform” in claim 1, line 14. The relationship among these recitations should be made clear.
Claim 5 is rejected by virtue of its dependence from claim 4.
Claim 5 recites “high frequency bins” in line 2, but it is not clear if this recitation is the same as, related to, or different from “high frequency bins” in claim 1, line 8. If they are the same, “high frequency bins” in claim 5 should be “the high frequency bins”. If they are different, their relationship should be made clear and they should be clearly distinguished from each other (e.g., when multiple elements have similar or the same labels, distinct identifiers such as “first” and “second” should be used to clearly differentiate the elements).
Claim 6 recites “each training waveform” in line 3, which is indefinite since claim 1, line 5 only recites a single training waveform, not a plurality of training waveforms. Also, it is not clear if the single training waveform of claim 1, line 5 is part of the plurality of the training waveforms implied by claim 6, line 3.
Claim 6 recites “excluding a breath triplet with a breath having a time greater or less than a pre-selected time period and/or a breath triplet with a middle breath annotated as normal and a dyssynchronous left or right breath” in lines 7-9, which renders the claim indefinite. It is not clear where the breath triplets come from. Are they generated too? If they are generated, why are they generated just so they can be “excluded”? If these breath triplets are excluded, how is the breath triplet generated as recited in claim 6, lines 1-2? That is, how is this excluding step used so as to generate a breath triplet? The connection between this recitation and the rest of claim 6 is not clear.
Claim 7 is rejected by virtue of its dependence from claim 6.
Claim 7 recites “inspiration, expiration, asynchronies, artifacts and/or a respiratory effort” in lines 1-2 and “inspiration, expiration, asynchronies, artifacts and/or a respiratory effort” in lines 4-5, but it is not clear if the respective inspirations are referring to each other and/or to “inspiration” of claim 6, if the respective expirations are referring to each other and/or to “expiration” of claim 6, if the respective asynchronies are referring to each other and/or to “asynchronies” of claim 6, if the respective artifacts are referring to each other and/or to “artifacts” of claim 6, and/or if the respective respiratory efforts are referring to each other and/or to “respiratory efforts” of claim 6. Clarification is required.
Claim 8 recites “spectral tensors” in lines 1-2, but it is not clear if this recitation is the same as, related to, or different from “a spectral tensor” of claim 1, line 2. The relationship between these two recitations should be made clear.
Claim 8 recites “wherein spectral tensors generated from a single person are allocated to one of a training set, a validation set, and a test set” in lines 1-3, but it is not clear what relationship this recitation has with the steps of claim 1. The recitation of claim 8 has no recited connection with any of the steps that have come before it. This ambiguity renders claim 8 indefinite.
Claim 9 recites “each spectral tensor” in lines 6-7, which is indefinite. First, there is insufficient antecedent basis for “each spectral tensor” since claim 9, line 6 only recites a single spectral tensor, not a plurality of spectral tensors. Second, it is not clear if the single spectral tensor of claim 9, line 6 is part of the plurality of spectral tensors implied by the recitation of claim 9, lines 6-7. These issues need clarification and render claim 9 indefinite.
Claim 9 recites “a flow waveform” in line 8, but it is not clear if this recitation is referring to one of “a flow waveform” of claim 9, lines 2-3. The relationship between these recitations should be made clear.
Claim 9 recites “an airway pressure waveform” in line 8, but it is not clear if this recitation is referring to one of “an airway pressure waveform” of claim 9, line 3. The relationship between these recitations should be made clear.
Claim 9 recites “the spectral images generated for each breath triplet” in line 16, which is indefinite. First, there is insufficient antecedent basis for “the spectral images” since claim 9, line 14 only recites a single spectral image, not a plurality of spectral images. Second, it is not clear if the single spectral image of claim 9, line 14 is part of the plurality of the spectral images of claim 9, line 16. Third, there is insufficient antecedent basis for the plurality of breath triplets implied in claim 9, line 16 since claim 9, line 7 only recites a single breath triplet. Fourth, it is not clear if the single breath triplet is part of the plurality of breath triplets implied in claim 9, line 16. These issue need clarification and render claim 9 indefinite.
Claims 10-11, 13, 15, and 17-20 are rejected by virtue of their dependence from claim 9.
Claim 10 recites “each training waveform” in line 2, which is indefinite. First, there is insufficient antecedent basis for the plurality of training waveforms implied in line 2 since claim 9, line 7 only recites a training waveform, not a plurality of training waveforms. Second, it is not clear if the single training waveform of claim 9, line 7 is part of the plurality of the training waveforms implied by claim 10, line 2. These issue need clarification and render claim 10 indefinite.
Claim 10 recites “excluding a breath triplet with a breath having a time greater or less than a pre-selected time period and/or a breath triplet with a middle breath annotated as normal and a dyssynchronous left or right breath” in lines 6-8, which renders the claim indefinite. It is not clear where the breath triplets come from. Are they generated too? If they are generated, why are they generated just so they can be “excluded”? If these breath triplets are excluded, how is the breath triplet generated as recited in claim 10, line 1? That is, how is this excluding step used so as to generate a breath triplet? The connection between this recitation and the rest of claim 10 is not clear.
Claim 11 is rejected by virtue of its dependence from claim 10.
Claim 11 recites “inspiration, expiration, asynchronies, artifacts and/or a respiratory effort” in lines 1-2 and “inspiration, expiration, asynchronies, artifacts and/or a respiratory effort” in lines 4-5, but it is not clear if the respective inspirations are referring to each other and/or to “inspiration” of claim 10, if the respective expirations are referring to each other and/or to “expiration” of claim 10, if the respective asynchronies are referring to each other and/or to “asynchronies” of claim 10, if the respective artifacts are referring to each other and/or to “artifacts” of claim 10, and/or if the respective respiratory efforts are referring to each other and/or to “respiratory efforts” of claim 10. Clarification is required.
Claim 15 recites “a Fourier transform” in line 2 and “Fourier transforms” in line 3, but the relationship between these two recitations are not clear. Are they separate and distinct? If the former, is the recitation of line 2 a member of the recitation of line 3? These issues render claim 15 indefinite.
Claim 15 recites “the waveform” in line 4, but it is not clear if this recitation is referring to one of “a new waveform” of claim 9, line 2, “a flow waveform and/or an airway pressure waveform” of claim 9, lines 2-3, “a training waveform” of claim 9, line 7 and/or “a flow waveform, an airway pressure waveform, and/or an esophageal manometry waveform” in claim 9, lines 8-9. The relationship among these recitations should be made clear.
Claim 19 recites “a pathologic breath” in line 2, but it is not clear if this recitation is the same as, related to, or different from “a pathologic breath” in claim 9, lines 4-5. If they are the same, “a pathologic breath” in claim 19 should be “the pathologic breath”. If they are different, their relationship should be made clear and they should be clearly distinguished from each other (e.g., when multiple elements have similar or the same labels, distinct identifiers such as “first” and “second” should be used to clearly differentiate the elements).
Claim 19 recites “pathologic breathing pattern” in lines 2-3, but it is not clear if this recitation is the same as, related to, or different from “pathologic breathing pattern” in claim 9, line 5. If they are the same, “a pathologic breathing pattern” in claim 19 should be “the pathologic breathing pattern”. If they are different, their relationship should be made clear and they should be clearly distinguished from each other (e.g., when multiple elements have similar or the same labels, distinct identifiers such as “first” and “second” should be used to clearly differentiate the elements).
Claim 22 recites “a flow waveform” in lines 9-10, but it is not clear if this recitation is referring to one of “a flow waveform” of claim 22, line 5. The relationship between these recitations should be made clear.
Claim 22 recites “an airway pressure waveform” in line 10, but it is not clear if this recitation is referring to one of “an airway pressure waveform” of claim 22, line 6. The relationship between these recitations should be made clear.
Claim 22 recites “the spectral images generated for each breath triplet” in line 15, which is indefinite. First, there is insufficient antecedent basis for “the spectral images” since claim 22, line 13 only recites a single spectral image, not a plurality of spectral images. Second, it is not clear if the single spectral image of claim 22, line 13 is part of the plurality of the spectral images of claim 22, line 15. Third, there is insufficient antecedent basis for the plurality of breath triplets implied in claim 22, line 15 since claim 22, line 8 only recites a single breath triplet. Fourth, it is not clear if the single breath triplet is part of the plurality of breath triplets implied in claim 22, line 15. These issue need clarification and render claim 22 indefinite.
Claim 22 recites “wherein the pathologic breath detection model was trained with a spectral tensor generated by a method comprising: generating a power spectrogram and a phase spectrogram for a breath triplet in a training waveform, wherein the training waveform is a flow waveform, an airway pressure waveform, and/or an esophageal manometry waveform; removing high frequency bins from each spectrogram; generating a spectral image by sizing each spectrogram to a pre-determined size; and assembling the spectral images generated for each breath triplet into the spectral tensor” in lines 6-16, which are action steps in an apparatus claim. A single claim which claims both an apparatus and the method steps of using the apparatus is indefinite under 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, second paragraph, because it creates confusion as to when direct infringement occurs. (MPEP 2173.05(p) citing In re Katz Interactive Call Processing Patent Litigation, 639 F.3d 1303, 97 USPQ2d 1737 (Fed. Cir. 2011)).
Claims 23 and 29-30 are rejected by virtue of their dependence from claim 22.
Claim 23 recites “wherein the breath triplet is generated by: collecting the training waveform, each training waveform comprises a plurality of breath; identifying inspiration, expiration, asynchronies, artifacts and/or a respiratory effort in the training waveform; and excluding a breath triplet with a breath having a time greater or less than a pre-selected time period and/or a breath triplet with a middle breath annotated as normal and a dyssynchronous left or right breath” in lines 2-9, which are action steps in an apparatus claim. A single claim which claims both an apparatus and the method steps of using the apparatus is indefinite under 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, second paragraph, because it creates confusion as to when direct infringement occurs. (MPEP 2173.05(p) citing In re Katz Interactive Call Processing Patent Litigation, 639 F.3d 1303, 97 USPQ2d 1737 (Fed. Cir. 2011)).
Claim 23 recites “each training waveform” in line 3, which is indefinite. First, there is insufficient antecedent basis for the plurality of training waveforms implied in line 3 since claim 22, line 9 only recites a training waveform, not a plurality of training waveforms. Second, it is not clear if the single training waveform of claim 22, line 9 is part of the plurality of the training waveforms implied by claim 23, line 3. These issue need clarification and render claim 23 indefinite.
Claim 23 recites “excluding a breath triplet with a breath having a time greater or less than a pre-selected time period and/or a breath triplet with a middle breath annotated as normal and a dyssynchronous left or right breath” in lines 7-9, which renders the claim indefinite. It is not clear where the breath triplets come from. Are they generated too? If they are generated, why are they generated just so they can be “excluded”? If these breath triplets are excluded, how is the breath triplet generated as recited in claim 23, line 2? That is, how is this excluding step used so as to generate a breath triplet? The connection between this recitation and the rest of claim 23 is not clear.
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 1-2, 4-11, 13, 15, 17-20, 22-23, and 29-30 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more. Claims 1-2, 4-11, 13, 15, 17-20, 22-23, and 29-30 are directed to a method of training a machine learning model and/or detecting a pathologic breath and/or pathologic breathing pattern in a waveform using a computational algorithm, which is an abstract idea. Claims 1-2, 4-11, 13, 15, 17-20, 22-23, and 29-30 do not include additional elements that integrate the exception into a practical application or that are sufficient to amount to significantly more than the judicial exception for the reasons provided below which are in line with the 2014 Interim Guidance on Patent Subject Matter Eligibility (Federal Register, Vol. 79, No. 241, p 74618, December 16, 2014), the July 2015 Update on Subject Matter Eligibility (Federal Register, Vol. 80, No. 146, p. 45429, July 30, 2015), the May 2016 Subject Matter Eligibility Update (Federal Register, Vol. 81, No. 88, p. 27381, May 6, 2016), and the 2019 Revised Patent Subject Matter Eligibility Guidance (Federal Register, Vol. 84, No. 4, page 50, January 7, 2019).
The analysis of claim 1 is as follows:
Step 1: Claim 1 is drawn to a process.
Step 2A – Prong One: Claim 1 recites an abstract idea. In particular, claim 1 recites the following limitations:
[A1] obtaining a spectral tensor, wherein the spectral tensor is generated by:
[B1] generating a power spectrogram and a phase spectrogram for a breath triplet of a training waveform, wherein the training waveform is a flow waveform, an airway pressure waveform, and/or an esophageal manometry waveform;
[C1] removing high frequency bins from each spectrogram;
[D1] generating a spectral image by sizing each spectrogram to a pre-determined size;
[E1] assembling the spectral images generated for each breath triplet into the spectral tensor; and
[F1] training a machine learning model to detect a pathologic breath and/or pathologic breathing pattern in a waveform using the spectral tensor as a training input.
These elements [A1]-[F1] of claim 1 are drawn to an abstract idea since they involve a mental process that can be practically performed in the human mind including observation, evaluation, judgment, and opinion and using pen and paper.
Step 2A – Prong Two: Claim 1 recites the following limitations that are beyond the judicial exception: a computing device.
The computing device of claim 1 does not integrate the exception into a practical application of the exception. It is merely an instruction to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.04(d) and MPEP 2106.05(f).
Step 2B: Claim 1 does not recite additional elements that amount to significantly more than the judicial exception itself. In particular, the computing device does not qualify as significantly more because this limitation is simply appending well-understood, routine and conventional activities previously known in the industry, specified at a high level of generality, to the judicial exception, e.g., a claim to an abstract idea requiring no more than a generic computer to perform generic computer functions that are well-understood, routine and conventional activities previously known in the industry (see Electric Power Group, 830 F.3d 1350 (Fed. Cir. 2016); Alice Corp. v. CLS Bank Int’l, 110 USPQ2d 1976 (2014)) and/or a claim to an abstract idea requiring no more than being stored on a computer readable medium which is a well-understood, routine and conventional activity previously known in the industry (see Electric Power Group, 830 F.3d 1350 (Fed. Cir. 2016); Alice Corp. v. CLS Bank Int’l, 110 USPQ2d 1976 (2014); SAP Am. v. InvestPic, 890 F.3d 1016 (Fed. Circ. 2018)).
In view of the above, the additional elements individually do not integrate the exception into a practical application and do not amount to significantly more than the above-judicial exception (the abstract idea). Looking at the limitations as an ordered combination (that is, as a whole) adds nothing that is not already present when looking at the elements taking individually. There is no indication that the combination of elements improves the functioning of a computer, for example, or improves any other technology. There is no indication that the combination of elements permits automation of specific tasks that previously could not be automated. There is no indication that the combination of elements includes a particular solution to a computer-based problem or a particular way to achieve a desired computer-based outcome. Rather, the collective functions of the claimed invention merely provide conventional computer implementation, i.e., the computer is simply a tool to perform the process.
Claims 2 and 4-8 depend from claim 1, and recite the same abstract idea as claim 1. Furthermore, these claims only contain recitations that further limit the abstract idea (that is, the claims only recite limitations that further limit the algorithm).
The analysis of claim 9 is as follows:
Step 1: Claim 9 is drawn to a process.
Step 2A – Prong One: Claim 9 recites an abstract idea. In particular, claim 9 recites the following limitations:
[A1] obtaining a new waveform, the new waveform being either a flow waveform and/or an airway pressure waveform:
[B1] evaluating the new waveform using a pathologic breath detection model to detect a pathologic breath and/or pathologic breathing pattern in the new waveform, wherein the pathologic breath detection model was trained using a spectral tensor as input, each spectral tensor generated from a breath triplet of a training waveform, wherein the training waveform is a flow waveform, an airway pressure waveform, and/or an esophageal manometry waveform, the spectral tensor generated by a spectral tensor technique comprising the steps of;
[C1] generating a power spectrogram and a phase spectrogram for the breath triplet;
[D1] removing high frequency bins from each spectrogram;
[E1] generating a spectral image by sizing each spectrogram to a pre-determined size; and
[F1] assembling the spectral images generated for each breath triplet into the spectral tensor.
These elements [A1]-[F1] of claim 9 are drawn to an abstract idea since they involve a mental process that can be practically performed in the human mind including observation, evaluation, judgment, and opinion and using pen and paper.
Step 2A – Prong Two: Claim 9 recites the following limitations that are beyond the judicial exception: a computer.
The computer of claim 9 does not integrate the exception into a practical application of the exception. It is merely an instruction to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.04(d) and MPEP 2106.05(f).
Step 2B: Claim 9 does not recite additional elements that amount to significantly more than the judicial exception itself. In particular, the computer does not qualify as significantly more because this limitation is simply appending well-understood, routine and conventional activities previously known in the industry, specified at a high level of generality, to the judicial exception, e.g., a claim to an abstract idea requiring no more than a generic computer to perform generic computer functions that are well-understood, routine and conventional activities previously known in the industry (see Electric Power Group, 830 F.3d 1350 (Fed. Cir. 2016); Alice Corp. v. CLS Bank Int’l, 110 USPQ2d 1976 (2014)) and/or a claim to an abstract idea requiring no more than being stored on a computer readable medium which is a well-understood, routine and conventional activity previously known in the industry (see Electric Power Group, 830 F.3d 1350 (Fed. Cir. 2016); Alice Corp. v. CLS Bank Int’l, 110 USPQ2d 1976 (2014); SAP Am. v. InvestPic, 890 F.3d 1016 (Fed. Circ. 2018)).
In view of the above, the additional elements individually do not integrate the exception into a practical application and do not amount to significantly more than the above-judicial exception (the abstract idea). Looking at the limitations as an ordered combination (that is, as a whole) adds nothing that is not already present when looking at the elements taking individually. There is no indication that the combination of elements improves the functioning of a computer, for example, or improves any other technology. There is no indication that the combination of elements permits automation of specific tasks that previously could not be automated. There is no indication that the combination of elements includes a particular solution to a computer-based problem or a particular way to achieve a desired computer-based outcome. Rather, the collective functions of the claimed invention merely provide conventional computer implementation, i.e., the computer is simply a tool to perform the process.
Claims 10-11, 13, 15, and 17-20 depend from claim 9, and recite the same abstract idea as claim 9. Furthermore, these claims only contain recitations that further limit the abstract idea (that is, the claims only recite limitations that further limit the algorithm).
The analysis of claim 22 is as follows:
Step 1: Claim 22 is drawn to a machine.
Step 2A – Prong One: Claim 22 recites an abstract idea. In particular, claim 22 recites the following limitations:
[A1] detect a pathologic breath and/or pathologic breathing pattern in a waveform, wherein the waveform is a flow waveform and/or an airway pressure waveform, wherein the pathologic breath detection model was trained with a spectral tensor generated by a method comprising:
[B1] generating a power spectrogram and a phase spectrogram for a breath triplet in a training waveform, wherein the training waveform is a flow waveform, an airway pressure waveform, and/or an esophageal manometry waveform;
[C1] removing high frequency bins from each spectrogram;
[D1] generating a spectral image by sizing each spectrogram to a pre-determined size;
[E1] assembling the spectral images generated for each breath triplet into the spectral tensor.
These elements [A1]-[E1] of claim 22 are drawn to an abstract idea since they involve a mental process that can be practically performed in the human mind including observation, evaluation, judgment, and opinion and using pen and paper.
Step 2A – Prong Two: Claim 22 recites the following limitations that are beyond the judicial exception: a computer program product comprising a non-transitory computer readable medium have embodied thereon a computer program comprising computer code comprising: code for a pathologic breath detection model.
The computer program product of claim 22 does not integrate the exception into a practical application of the exception. It is merely an instruction to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.04(d) and MPEP 2106.05(f).
Step 2B: Claim 22 does not recite additional elements that amount to significantly more than the judicial exception itself. In particular, the computer program product does not qualify as significantly more because this limitation is simply appending well-understood, routine and conventional activities previously known in the industry, specified at a high level of generality, to the judicial exception, e.g., a claim to an abstract idea requiring no more than a generic computer to perform generic computer functions that are well-understood, routine and conventional activities previously known in the industry (see Electric Power Group, 830 F.3d 1350 (Fed. Cir. 2016); Alice Corp. v. CLS Bank Int’l, 110 USPQ2d 1976 (2014)) and/or a claim to an abstract idea requiring no more than being stored on a computer readable medium which is a well-understood, routine and conventional activity previously known in the industry (see Electric Power Group, 830 F.3d 1350 (Fed. Cir. 2016); Alice Corp. v. CLS Bank Int’l, 110 USPQ2d 1976 (2014); SAP Am. v. InvestPic, 890 F.3d 1016 (Fed. Circ. 2018)).
In view of the above, the additional elements individually do not integrate the exception into a practical application and do not amount to significantly more than the above-judicial exception (the abstract idea). Looking at the limitations as an ordered combination (that is, as a whole) adds nothing that is not already present when looking at the elements taking individually. There is no indication that the combination of elements improves the functioning of a computer, for example, or improves any other technology. There is no indication that the combination of elements permits automation of specific tasks that previously could not be automated. There is no indication that the combination of elements includes a particular solution to a computer-based problem or a particular way to achieve a desired computer-based outcome. Rather, the collective functions of the claimed invention merely provide conventional computer implementation, i.e., the computer is simply a tool to perform the process.
Claims 23 and 29-30 depend from claim 22, and recite the same abstract idea as claim 22. Furthermore, these claims only contain recitations that further limit the abstract idea (that is, the claims only recite limitations that further limit the algorithm).
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, 8-9, 13, 17-20, 22, and 29-30 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent Application Publication No. 2019/0083001 (Stamatopoulos), in view of WO 2018/047058 (Borissovna), and further in view of U.S. Patent Application Publication No. 2021/0035590 (Miner).
Stamatopoulos teaches a method for determining lung pathology from an audio respiratory signal (paragraph 0019 of Stamatopoulos ). The method comprises (a) inputting a plurality of audio files comprising a training set into an artificial neural network, wherein the plurality of audio files comprise sessions with patients with known pathologies of known degrees of severity; (b) annotating the plurality of audio files in the training set with metadata relevant to the patients and the known pathologies; and (c) analyzing the plurality of audio files (paragraph 0019 of Stamatopoulos). The analyzing step comprises (a) extracting spectrograms for each of the plurality of audio files; (b) training the artificial neural network using the plurality of audio files, the spectrograms, the metadata and the plurality of descriptors; (c) inputting a recording of a new patient into the artificial neural network; and (d) determining a pathology and associated severity for the new patient using the artificial neural network (paragraphs 0017-0019, 0439, and 0452-0453 of Stamatopoulos).
Stamatopoulos teaches that an area of interest can be more than one breath cycle (paragraph 0303 of Stamatopoulos). Borissovna teaches that three breath cycles are an area of interest for machine learning applications (pages 12, 14, 20, and 22 of Borissovna). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use three breath cycles as an area of interest in the spectrograms, as suggested by Borissovna, since Stamatopoulos teaches that an area of interest can be more than one breath cycle and Borissovna teaches such an area of interest.
Stamatopoulos teaches that the analyzing step comprises the step of extracting spectrograms for each of the plurality of audio files (paragraph 0019 of Stamatopoulos). Miner teaches a method of extracting spectrograms from audio files by (1) first loading an audio file into a waveform; (2) transforming the waveform into a complex spectrogram; (3) decomposing the complex spectrogram into a magnitude spectrogram and a phase spectrogram; (4) splitting the magnitude spectrogram into K small fragments; (5) sending each of the K fragments through one or more deep neural networks to produce N sequences of K masks, where N corresponds to the number of sources that need to be segmented; (6) for each source, concatenating the mask fragments together in order to form a complete mask, which is the same length as the original magnitude spectrogram; (7) for each source, multiplying the complete mask with the original magnitude spectrogram to create a new magnitude spectrogram corresponding to the source; and (8) for each source, the new magnitude spectrogram is combined with the original phase spectrogram to produce a new complex spectrogram corresponding to the source (paragraphs 0006 and 0023-0024 of Miner). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use the spectrogram extraction process of Miner as the spectrogram extraction process of the combination since it creates spectrograms that correspond to the relevant sources of the audio needed for analysis and/or it is a simple substitution of one known element for another to obtain predictable results.
With respect to claim 1, the combination teaches or suggests a method comprising:
obtaining, by a computing device, a spectral tensor, wherein the spectral tensor is generated by:
generating a power spectrogram and a phase spectrogram (the generation of the magnitude and phase spectrograms of Miner) for a breath triplet (the breath triple of Borissovna) of a training waveform, wherein the training waveform is a flow waveform, an airway pressure waveform, and/or an esophageal manometry waveform (the training waveform of Stamatopoulos);
removing high frequency bins from each spectrogram (the use of the K masks of Miner; paragraph 0023 of Miner);
generating a spectral image by sizing each spectrogram to a pre-determined size (forming the complete mask of Miner, which is the same length as the original magnitude spectrogram);
assembling the spectral images generated for each breath triplet into the spectral tensor (the production of the new complex spectrogram of Miner); and
training a machine learning model to detect a pathologic breath and/or pathologic breathing pattern in a waveform using the spectral tensor as a training input (the training of the machine learning model of Stamatopoulos using the complex spectrogram of Miner).
With respect to claim 2, the combination teaches or suggests that the machine learning model is a convolutional neural network (the CNN of Stamatopoulos; paragraphs 0280 and 0294 of Stamatopoulos).
With respect to claim 8, the combination teaches or suggests that spectral tensors generated from a single person are allocated to one of a training set, a validation set, and a test set (the analysis of a recording of a new patient into the artificial neural network to determine the pathology and associated severity for the new patient using the artificial neural network; paragraph 0019 of Stamatopoulos).
With respect to claim 9, the combination teaches or suggests a computer-implemented analysis method comprising:
obtaining, by the computer, a new waveform, the new waveform being either a flow waveform and/or an airway pressure waveform (obtaining a recording of a new patient; paragraph 0019 of Stamatopoulos); and
evaluating the new waveform using a pathologic breath detection model to detect a pathologic breath and/or pathologic breathing pattern in the new waveform (evaluating the new waveform from the new patient to determine a pathology and associated severity for the new patient using the artificial neural network; paragraphs 0017-0019, 0439, and 0452-0453 of Stamatopoulos), wherein the pathologic breath detection model was trained using a spectral tensor as input, each spectral tensor generated from a breath triplet (the breath triple of Borissovna) of a training waveform (the training waveform of Stamatopoulos), wherein the training waveform is a flow waveform, an airway pressure waveform, and/or an esophageal manometry waveform, the spectral tensor generated by a spectral tensor technique comprising the steps of:
generating a power spectrogram and a phase spectrogram for the breath triplet (the generation of the magnitude and phase spectrograms of Miner);
removing high frequency bins from each spectrogram (the use of the K masks of Miner; paragraph 0023 of Miner);
generating a spectral image by sizing each spectrogram to a pre-determined size (forming the complete mask of Miner, which is the same length as the original magnitude spectrogram); and
assembling the spectral images generated for each breath triplet into the spectral tensor (the production of the new complex spectrogram of Miner).
With respect to claim 13, the combination teaches or suggests that the pathologic breath detection model comprises a convolutional neural network (the CNN of Stamatopoulos; paragraphs 0280 and 0294 of Stamatopoulos).
With respect to claim 17, the combination teaches or suggests that evaluating the new waveform further comprises utilizing the tensor technique to generate a spectral tensor for a breath triplet of the new waveform (evaluating the new waveform from the new patient to determine a pathology and associated severity for the new patient using the artificial neural network; paragraphs 0017-0019, 0439, and 0452-0453 of Stamatopoulos).
With respect to claim 18, the combination teaches or suggests that evaluating the new waveform further comprises: generating sequential breath triplets for a breath by breath analysis of the new waveform; and utilizing the tensor technique to generate a spectral tensor for each sequential breath triplet (evaluating the new waveform from the new patient to determine a pathology and associated severity for the new patient using the artificial neural network; paragraphs 0017-0019, 0439, and 0452-0453 of Stamatopoulos).
With respect to claim 19, the combination teaches or suggests generating a response when a pathologic breath and/or pathologic breathing pattern is detected by the pathologic breath detection model (the annotated procedure, classification, and/or the output of Stamatopoulos; paragraphs 0120, 0275, and 0281-0282 of Stamatopoulos).
With respect to claim 20, the combination teaches or suggests that the pathologic breath detection model is: a binary DC breath detection model; a multi-target dyssynchrony detection model; or a respiratory effort detection model (the binary hypothesis test of Stamatopoulos).
With respect to claim 22, the combination teaches or suggests a computer program product comprising a non-transitory computer readable medium have embodied thereon a computer program comprising computer code (paragraph 0017-0019 and 0073-0078 of Stamatopoulos) comprising:
code for a pathologic breath detection model to detect a pathologic breath and/or pathologic breathing pattern in a waveform (evaluating the new waveform from the new patient to determine a pathology and associated severity for the new patient using the artificial neural network; paragraphs 0017-0019, 0439, and 0452-0453 of Stamatopoulos), wherein the waveform is a flow waveform and/or an airway pressure waveform, wherein the pathologic breath detection model was trained with a spectral tensor generated by a method comprising:
generating a power spectrogram and a phase spectrogram (the generation of the magnitude and phase spectrograms of Miner) for a breath triplet (the breath triple of Borissovna) in a training waveform (the training waveform of Stamatopoulos), wherein the training waveform is a flow waveform, an airway pressure waveform, and/or an esophageal manometry waveform;
removing high frequency bins from each spectrogram (the use of the K masks of Miner; paragraph 0023 of Miner);
generating a spectral image by sizing each spectrogram to a pre-determined size (forming the complete mask of Miner, which is the same length as the original magnitude spectrogram); and
assembling the spectral images generated for each breath triplet into the spectral tensor (the production of the new complex spectrogram of Miner).
With respect to claim 29, the combination teaches or suggests that the pathologic breath detection model is: a binary DC breath detection model; a multi-target dyssynchrony detection model; or a respiratory effort detection model (the binary hypothesis test of Stamatopoulos).
With respect to claim 30, the combination teaches or suggests that the respiratory effort detection model is a: binary respiratory effort detection model; or a regression respiratory effort model (the binary hypothesis test of Stamatopoulos).
Claims 1-2, 8-9, 13, 17-20, 22, and 29-30 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent Application Publication No. 2019/0083001 (Stamatopoulos), in view of WO 2018/047058 (Borissovna), and further in view of U.S. Patent Application Publication No. 2021/0035590 (Miner), and further in view of U.S. Patent Application Publication No. 2016/0051201 (Maani).
Stamatopoulos teaches a method for determining lung pathology from an audio respiratory signal (paragraph 0019 of Stamatopoulos ). The method comprises (a) inputting a plurality of audio files comprising a training set into an artificial neural network, wherein the plurality of audio files comprise sessions with patients with known pathologies of known degrees of severity; (b) annotating the plurality of audio files in the training set with metadata relevant to the patients and the known pathologies; and (c) analyzing the plurality of audio files (paragraph 0019 of Stamatopoulos). The analyzing step comprises (a) extracting spectrograms for each of the plurality of audio files; (b) training the artificial neural network using the plurality of audio files, the spectrograms, the metadata and the plurality of descriptors; (c) inputting a recording of a new patient into the artificial neural network; and (d) determining a pathology and associated severity for the new patient using the artificial neural network (paragraphs 0017-0019, 0439, and 0452-0453 of Stamatopoulos).
Stamatopoulos teaches that an area of interest can be more than one breath cycle (paragraph 0303 of Stamatopoulos). Borissovna teaches that three breath cycles are an area of interest for machine learning applications (pages 12, 14, 20, and 22 of Borissovna). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use three breath cycles as an area of interest in the spectrograms, as suggested by Borissovna, since Stamatopoulos teaches that an area of interest can be more than one breath cycle and Borissovna teaches such an area of interest.
Stamatopoulos teaches that the analyzing step comprises the step of extracting spectrograms for each of the plurality of audio files (paragraph 0019 of Stamatopoulos). Miner teaches a method of extracting spectrograms from audio files by (1) first loading an audio file into a waveform; (2) transforming the waveform into a complex spectrogram; (3) decomposing the complex spectrogram into a magnitude spectrogram and a phase spectrogram; (4) splitting the magnitude spectrogram into K small fragments; (5) sending each of the K fragments through one or more deep neural networks to produce N sequences of K masks, where N corresponds to the number of sources that need to be segmented; (6) for each source, concatenating the mask fragments together in order to form a complete mask, which is the same length as the original magnitude spectrogram; (7) for each source, multiplying the complete mask with the original magnitude spectrogram to create a new magnitude spectrogram corresponding to the source; and (8) for each source, the new magnitude spectrogram is combined with the original phase spectrogram to produce a new complex spectrogram corresponding to the source (paragraphs 0006 and 0023-0024 of Miner). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use the spectrogram extraction process of Miner as the spectrogram extraction process of the combination since it creates spectrograms that correspond to the relevant sources of the audio needed for analysis and/or it is a simple substitution of one known element for another to obtain predictable results.
Maani teaches the use of a convolution of a spectrogram with a Gaussian kernel so as to provide a low pass filtering of the spectrogram (paragraphs 0057-0058, 0117, and 0122 of Maani). Such filtering can have the effect of enhancing the highest values of the peak points so that the peaks themselves are more readily defined (paragraphs 0057-0058, 0117, and 0122 of Maani). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention use a convolution of the spectrograms with Gaussian kernels so as to provide low pass filtering of the spectrograms so as to enhance the peaks in the spectrogram.
With respect to claim 1, the combination teaches or suggests a method comprising:
obtaining, by a computing device, a spectral tensor, wherein the spectral tensor is generated by:
generating a power spectrogram and a phase spectrogram (the generation of the magnitude and phase spectrograms of Miner) for a breath triplet (the breath triple of Borissovna) of a training waveform, wherein the training waveform is a flow waveform, an airway pressure waveform, and/or an esophageal manometry waveform (the training waveform of Stamatopoulos);
removing high frequency bins from each spectrogram (the low pass filtering of Maani);
generating a spectral image by sizing each spectrogram to a pre-determined size (forming the complete mask of Miner, which is the same length as the original magnitude spectrogram);
assembling the spectral images generated for each breath triplet into the spectral tensor (the production of the new complex spectrogram of Miner); and
training a machine learning model to detect a pathologic breath and/or pathologic breathing pattern in a waveform using the spectral tensor as a training input (the training of the machine learning model of Stamatopoulos using the complex spectrogram of Miner).
With respect to claim 2, the combination teaches or suggests that the machine learning model is a convolutional neural network (the CNN of Stamatopoulos; paragraphs 0280 and 0294 of Stamatopoulos).
With respect to claim 8, the combination teaches or suggests that spectral tensors generated from a single person are allocated to one of a training set, a validation set, and a test set (the analysis of a recording of a new patient into the artificial neural network to determine the pathology and associated severity for the new patient using the artificial neural network; paragraph 0019 of Stamatopoulos).
With respect to claim 9, the combination teaches or suggests a computer-implemented analysis method comprising:
obtaining, by the computer, a new waveform, the new waveform being either a flow waveform and/or an airway pressure waveform (obtaining a recording of a new patient; paragraph 0019 of Stamatopoulos); and
evaluating the new waveform using a pathologic breath detection model to detect a pathologic breath and/or pathologic breathing pattern in the new waveform (evaluating the new waveform from the new patient to determine a pathology and associated severity for the new patient using the artificial neural network; paragraphs 0017-0019, 0439, and 0452-0453 of Stamatopoulos), wherein the pathologic breath detection model was trained using a spectral tensor as input, each spectral tensor generated from a breath triplet (the breath triple of Borissovna) of a training waveform (the training waveform of Stamatopoulos), wherein the training waveform is a flow waveform, an airway pressure waveform, and/or an esophageal manometry waveform, the spectral tensor generated by a spectral tensor technique comprising the steps of:
generating a power spectrogram and a phase spectrogram for the breath triplet (the generation of the magnitude and phase spectrograms of Miner);
removing high frequency bins from each spectrogram (the low pass filtering of Maani);
generating a spectral image by sizing each spectrogram to a pre-determined size (forming the complete mask of Miner, which is the same length as the original magnitude spectrogram); and
assembling the spectral images generated for each breath triplet into the spectral tensor (the production of the new complex spectrogram of Miner).
With respect to claim 13, the combination teaches or suggests that the pathologic breath detection model comprises a convolutional neural network (the CNN of Stamatopoulos; paragraphs 0280 and 0294 of Stamatopoulos).
With respect to claim 17, the combination teaches or suggests that evaluating the new waveform further comprises utilizing the tensor technique to generate a spectral tensor for a breath triplet of the new waveform (evaluating the new waveform from the new patient to determine a pathology and associated severity for the new patient using the artificial neural network; paragraphs 0017-0019, 0439, and 0452-0453 of Stamatopoulos).
With respect to claim 18, the combination teaches or suggests that evaluating the new waveform further comprises: generating sequential breath triplets for a breath by breath analysis of the new waveform; and utilizing the tensor technique to generate a spectral tensor for each sequential breath triplet (evaluating the new waveform from the new patient to determine a pathology and associated severity for the new patient using the artificial neural network; paragraphs 0017-0019, 0439, and 0452-0453 of Stamatopoulos).
With respect to claim 19, the combination teaches or suggests generating a response when a pathologic breath and/or pathologic breathing pattern is detected by the pathologic breath detection model (the annotated procedure, classification, and/or the output of Stamatopoulos; paragraphs 0120, 0275, and 0281-0282 of Stamatopoulos).
With respect to claim 20, the combination teaches or suggests that the pathologic breath detection model is: a binary DC breath detection model; a multi-target dyssynchrony detection model; or a respiratory effort detection model (the binary hypothesis test of Stamatopoulos).
With respect to claim 22, the combination teaches or suggests a computer program product comprising a non-transitory computer readable medium have embodied thereon a computer program comprising computer code (paragraph 0017-0019 and 0073-0078 of Stamatopoulos) comprising:
code for a pathologic breath detection model to detect a pathologic breath and/or pathologic breathing pattern in a waveform (evaluating the new waveform from the new patient to determine a pathology and associated severity for the new patient using the artificial neural network; paragraphs 0017-0019, 0439, and 0452-0453 of Stamatopoulos), wherein the waveform is a flow waveform and/or an airway pressure waveform, wherein the pathologic breath detection model was trained with a spectral tensor generated by a method comprising:
generating a power spectrogram and a phase spectrogram (the generation of the magnitude and phase spectrograms of Miner) for a breath triplet (the breath triple of Borissovna) in a training waveform (the training waveform of Stamatopoulos), wherein the training waveform is a flow waveform, an airway pressure waveform, and/or an esophageal manometry waveform;
removing high frequency bins from each spectrogram (the low pass filtering of Maani);
generating a spectral image by sizing each spectrogram to a pre-determined size (forming the complete mask of Miner, which is the same length as the original magnitude spectrogram); and
assembling the spectral images generated for each breath triplet into the spectral tensor (the production of the new complex spectrogram of Miner).
With respect to claim 29, the combination teaches or suggests that the pathologic breath detection model is: a binary DC breath detection model; a multi-target dyssynchrony detection model; or a respiratory effort detection model (the binary hypothesis test of Stamatopoulos).
With respect to claim 30, the combination teaches or suggests that the respiratory effort detection model is a: binary respiratory effort detection model; or a regression respiratory effort model (the binary hypothesis test of Stamatopoulos).
Claims 4 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent Application Publication No. 2019/0083001 (Stamatopoulos), in view of WO 2018/047058 (Borissovna), and further in view of U.S. Patent Application Publication No. 2021/0035590 (Miner), and further in view of JP 2002-503134 (JP134), and further in view of EP 3534283 (Elkind). Citations to JP314 will refer to the machine English translation that accompanies this Office Action.
The combination teaches the use of short-time Fourier transform to formulate the spectrograms (paragraphs 00007, 0023, and 0026 of Miner). JP314 teaches the cosine-tapered windows are suitable windows for STFT (page 7 of JP314). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use the cosine-tapered windows of JP314 as the windows for the STFT since a window type is required and JP314 teaches one such window and/or it is a simple substitution of one known element for another to obtain predictable results.
Elkind teaches that the stride and windows can be fixed values in Fourier transforms (paragraph 0083 of Elkind). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use fixed windows and fixed strides between Fourier transforms since a window and stride methodology is required and Elkind teaches one such window and stride methodology.
With respect to claim 4, the combination teaches or suggests that generating each spectrogram comprises applying a Fourier transform with a tapered cosine window of a predetermined size (the fixed cosine-tapered windows of the combination) and at a predetermined stride between Fourier transforms (the fixed stride between the Fourier transforms of the combination) to generate a plurality of spectral columns from the waveform.
With respect to claim 15, the combination teaches or suggests that generating each spectrogram comprises applying a Fourier transform with a tapered cosine window of a predetermined size (the fixed cosine-tapered windows of the combination) and at a predetermined stride between Fourier transforms (the fixed stride between the Fourier transforms of the combination) to generate a plurality of spectral columns from the waveform.
Claim 4-5 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent Application Publication No. 2019/0083001 (Stamatopoulos), in view of WO 2018/047058 (Borissovna), and further in view of U.S. Patent Application Publication No. 2021/0035590 (Miner), and further in view of U.S. Patent Application Publication No. 2016/0051201 (Maani), and further in view of JP 2002-503134 (JP134), and further in view of EP 3534283 (Elkind). Citations to JP314 will refer to the machine English translation that accompanies this Office Action.
The combination teaches the use of short-time Fourier transform to formulate the spectrograms (paragraphs 00007, 0023, and 0026 of Miner). JP314 teaches the cosine-tapered windows are suitable windows for STFT (page 7 of JP314). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use the cosine-tapered windows of JP314 as the windows for the STFT since a window type is required and JP314 teaches one such window and/or it is a simple substitution of one known element for another to obtain predictable results.
Elkind teaches that the stride and windows can be fixed values in Fourier transforms (paragraph 0083 of Elkind). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use fixed windows and fixed strides between Fourier transforms since a window and stride methodology is required and Elkind teaches one such window and stride methodology.
With respect to claim 4, the combination teaches or suggests that generating each spectrogram comprises applying a Fourier transform with a tapered cosine window of a predetermined size (the fixed cosine-tapered windows of the combination) and at a predetermined stride between Fourier transforms (the fixed stride between the Fourier transforms of the combination) to generate a plurality of spectral columns from the waveform.
With respect to claim 5, the combination teaches or suggests that removing high frequency bins comprises applying a low pass filter (the low pass filtering of Maani).
Claims 6-7, 10-11, and 23 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent Application Publication No. 2019/0083001 (Stamatopoulos), in view of WO 2018/047058 (Borissovna), and further in view of U.S. Patent Application Publication No. 2021/0035590 (Miner), and further in view of U.S. Patent Application Publication No. 2015/0164375 (Schindhelm).
Stamatopoulos teaches the timestamps for each inhalation and exhalation event and for rest periods to be able to define a full breath cycle with four phases: inhalation, pause or transition, exhalation, and rest (paragraph 0116 of Stamatopoulos). These timestamps can be collected over several breath cycles (paragraph 0116 of Stamatopoulos). Schindhelm teaches that respiration intervals greater than or equal to a duration that is long compared to a typical breath interval, set in one implementation to 7 seconds, are removed, as these are likely to be associated with interruptions in breathing or with movements (paragraph 0261 of Schindhelm). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to remove respiration intervals greater than a typical breath interval, such as 7 seconds, since it removes readings that are associated with interruptions in breathing or with movements.
With respect to claim 6, the combination teaches or suggests that the breath triplet is generated by: collecting the training waveform (obtaining the training waveform of Stamatopoulos), each training waveform comprising a plurality of breaths (the breath triple of Borissovna); identifying inspiration, expiration, asynchronies, artifacts and/or a respiratory effort in the training waveform (the timestamps for each inhalation and exhalation event and for rest periods so as to be able to define a full breath cycle with four phases: inhalation, pause or transition, exhalation, and rest, as taught by Stamatopoulos); and excluding a breath triplet with a breath having a time greater or less than a pre-selected time period (remove respiration intervals greater than a typical breath interval, such as 7 seconds, as taught by Schindhelm) and/or a breath triplet with a middle breath annotated as normal and a dyssynchronous left or right breath.
With respect to claim 7, the combination teaches or suggests that identifying inspiration, expiration, asynchronies, artifacts and/or a respiratory effort in the training waveform includes: annotating the training waveform (the annotation of the breath phases of Stamatopoulos; paragraphs 0017-0019, 0130, 0426, 0428, and 0449 of Stamatopoulos); and/or collating data about inspiration, expiration, asynchronies, artifacts and/or a respiratory effort into a dataset (the collating of data of Stamatopoulos; paragraphs 0017-0019, 0130, 0426, 0428, and 0449 of Stamatopoulos).
With respect to claim 10, the combination teaches or suggests that the breath triplet is generated by: collecting the training waveform (obtaining the training waveform of Stamatopoulos), each training waveform comprising a plurality of breaths (the breath triple of Borissovna); identifying inspiration, expiration, asynchronies, artifacts and/or a respiratory effort in the training waveform (the timestamps for each inhalation and exhalation event and for rest periods so as to be able to define a full breath cycle with four phases: inhalation, pause or transition, exhalation, and rest, as taught by Stamatopoulos); and excluding a breath triplet with a breath having a time greater or less than a pre-selected time period (remove respiration intervals greater than a typical breath interval, such as 7 seconds, as taught by Schindhelm) and/or a breath triplet with a middle breath annotated as normal and a dyssynchronous left or right breath.
With respect to claim 11, the combination teaches or suggests that identifying inspiration, expiration, asynchronies, artifacts and/or a respiratory effort in the training waveform includes: annotating the training waveform (the annotation of the breath phases of Stamatopoulos; paragraphs 0017-0019, 0130, 0426, 0428, and 0449 of Stamatopoulos); and/or collating data about inspiration, expiration, asynchronies, artifacts and/or a respiratory effort into a dataset (the collating of data of Stamatopoulos; paragraphs 0017-0019, 0130, 0426, 0428, and 0449 of Stamatopoulos).
With respect to claim 23, the combination teaches or suggests that the breath triplet is generated by: collecting the training waveform (obtaining the training waveform of Stamatopoulos), each training waveform comprises a plurality of breath (the breath triple of Borissovna); identifying inspiration, expiration, asynchronies, artifacts and/or a respiratory effort in the training waveform (the timestamps for each inhalation and exhalation event and for rest periods so as to be able to define a full breath cycle with four phases: inhalation, pause or transition, exhalation, and rest, as taught by Stamatopoulos); and excluding a breath triplet with a breath having a time greater or less than a pre-selected time period (remove respiration intervals greater than a typical breath interval, such as 7 seconds, as taught by Schindhelm) and/or a breath triplet with a middle breath annotated as normal and a dyssynchronous left or right breath.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MATTHEW KREMER whose telephone number is (571)270-3394. The examiner can normally be reached Monday - Friday 8 am to 6 pm; every other Friday off.
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, JACQUELINE CHENG can be reached at (571) 272-5596. 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.
/MATTHEW KREMER/Primary Examiner, Art Unit 3791
Prosecution Insights