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 .
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Information Disclosure Statement
The information disclosure statements (IDS) submitted on May 15, 2024 and July 25, 2024 are in compliance with the provisions of 37 CFR 1.97, and have been considered by the examiner.
Claim Objections
Claims 1-12 and 14 are objected to because of the following informalities:
- Claim 1 recites the limitation directed to "providing the input cardiac signal as an input to the machine-learning model based on the input cardiac signal, a ventricular arrhythmia risk score indicating a risk of future ventricular arrhythmia occurrence". However, this limitation appears to be missing the phrase "the machine-learning model being trained to predict" after the word "model". Specifically, the aforementioned limitation in claim 1 should be "providing the input cardiac signal as an input to the machine-learning model, the machine-learning model being trained to predict, based on the input cardiac signal, a ventricular arrhythmia risk score indicating a risk of future ventricular arrhythmia occurrence" instead (similar to the accompanying limitation in claim 14). Examiner suggests that Applicant amend this clause in claim 1 in accordance with this interpretation, or make some other appropriate correction of course. For examination purposes, the limitation directed to "providing the input cardiac signal as an input to the machine-learning model based on the input cardiac signal, a ventricular arrhythmia risk score indicating a risk of future ventricular arrhythmia occurrence" in claim 1 will be interpreted and read the same as "providing the input cardiac signal as an input to the machine-learning model, the machine-learning model being trained to predict, based on the input cardiac signal, a ventricular arrhythmia risk score indicating a risk of future ventricular arrhythmia occurrence". Appropriate correction is required.
Claims 2-12 are also objected to because of the minor informality identified above due to their individual dependencies on independent claim 1.
- Separately, claims 3, 11, and 12 are objected to because of the following informalities:
- The word arrhythmia is misspelled in claims 3, 11, and 12, it appears as "arrythmia" in the claims. Appropriate correction is required.
- Claim 14 recites the limitation directed to "determine a risk value describing a predicted risk of future ventricular arrhythmia occurrence for the subject based on the ventricular arrythmia score". However, this limitation appears to be missing the word "risk" after the last recitation of "arrhythmia" at the end of claim 14. Specifically, the aforementioned limitation in claim 14 should be "determine a risk value describing a predicted risk of future ventricular arrhythmia occurrence for the subject based on the ventricular arrythmia risk score" instead. Examiner suggests that Applicant amend this clause in claim 14 in accordance with this interpretation, or make some other appropriate correction of course. For examination purposes, the limitation directed to "determine a risk value describing a predicted risk of future ventricular arrhythmia occurrence for the subject based on the ventricular arrythmia score" in claim 14 will be interpreted and read the same as "determine a risk value describing a predicted risk of future ventricular arrhythmia occurrence for the subject based on the ventricular arrythmia risk score". Appropriate correction is required.
Claim Rejections - 35 USC § 112(b)
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 3, 8, and 11 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 pre-AIA the applicant regards as the invention.
Claim 3 recites the limitation “wherein determining the risk value based on the ventricular arrhythmia score comprises determining a percentage-likelihood of arrythmia occurrence in the near-future” in lines 1-3 of claim 3. The term "in the near-future" is a relative term which renders the claims indefinite. The term “in the near-future” implies that there is cutoff time period that differentiates what is considered in the near-future and what is not considered in the near-future (e.g., an arrythmia predicted to occur within the next ninety (90) days may be considered within the range of “in the near-future”, whereas any arrythmia predicted to occur more that ninety (90) days after the prediction may not be considered within the range of “in the near-future”). The term "in the near-future" is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. See MPEP § 2173.05(b). While the specification gives examples of what in the near-future could in line 13 of page of the originally filed specification, filed on May 15, 2024 (where Applicant discloses that in the near-future could mean “in the next month or two weeks or week or day, etc.”), this is not a definition with clear, definite boundaries. For examination purposes, the phrase “wherein determining the risk value based on the ventricular arrhythmia score comprises determining a percentage-likelihood of arrythmia occurrence in the near-future” will be interpreted and read as “wherein determining the risk value based on the ventricular arrhythmia score comprises determining a percentage-likelihood of arrythmia occurrence in future.”
Claim 8 recites the limitation "wherein the machine-learning model comprises a second random forest classifier, the second random forest classifier being trained to predict" in lines 1 to 2 of claim 8. However, there is insufficient antecedent basis for this limitation in the claims. See MPEP § 2173.05(e). A first random forest classifier was not previously recited in claim 8, nor was it previously recited in claims 1 or 7 (which claim 8 depends on). Examiner suggests that Applicant amend the phrase “a second random forest classifier, the second random forest classifier” in line 2 of claim 8 to “a claim 8 will be interpreted and read the same as “wherein the machine-learning model comprises a random forest classifier, the random forest classifier being trained to predict.”
Similarly, claim 11 recites the limitation "wherein the machine-learning model comprises a second neural network, the second neural network being trained to predict" in lines 1 to 2 of claim 11. However, there is insufficient antecedent basis for this limitation in the claims. See MPEP § 2173.05(e). A first neural network was not previously recited in claim 11, nor was it previously recited in claim 1 (which claim 11 depends on). Examiner suggests that Applicant amend the phrase “a second neural network, the second neural network” in lines 1 to 2 of claim 11 to “a claim 11 will be interpreted and read the same as “wherein the machine-learning model comprises a neural network classifier, the neural network being trained to predict.”
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 1-15 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. See MPEP § 2106 (hereinafter referred to as the “2019 Revised PEG”).
Separately, claim 13 is rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claim does not fall within at least one of the four categories of patent eligible subject matter because the claim recites “[a] computer program comprising code means for implementing the method of claim 1 when said program is run on a processing system.”
Applying the broadest reasonable interpretation to claim 13, a “computer program comprising code means” consists of transient signals. Signals are not patent eligible subject matter. See MPEP § 2106.03(I). As such, claim 13 does not fall within one of the four categories of patent eligible subject matter. Examiner suggests that Applicant amend claim 13 to change the focus of the claim to a non-transitory computer-readable storage medium, storing computer readable instructions configured to cause a computer device to […], or make some other appropriate, similar correction of course. For examination purposes, the computer program described in claim 13 will be interpreted and read as “a non-transitory computer-readable storage medium, storing computer readable instructions configured to cause a computer device to […].”
Step 1 of the Alice/Mayo Test
Following Step 1 of the 2019 Revised PEG, claims 1-12 are directed to a method for predicting a risk of ventricular arrhythmia in a subject, which is also within one of the four statutory categories (i.e., a process). See MPEP § 2106.03. Claim 14 is directed to a system for predicting a risk of ventricular arrhythmia in a subject, which is within one of the four statutory categories (i.e., a machine or apparatus). See id. Claim 15 is directed to a monitoring system, which is also within one of the four statutory categories (i.e., a machine or apparatus). See id. non-transitory computer-readable medium, which is also within one of the four statutory categories (i.e., an article of manufacture). See id.
Claim 13 is rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. As described above in the § 101 rejections of non-statutory subject matter, claim 13 does not fall within at least one of the four categories of patent eligible subject matter, because the claims recite a “computer program comprising code means for implementing the method of claim 1 when said program is run on a processing system”, which includes transient signals. Signals are not patent eligible subject matter. See MPEP § 2106.03(I). For examination purposes, the computer program comprising code means described in claim 13 will be interpreted and read as “a non-transitory computer-readable storage medium, storing computer readable instructions configured to cause a computer device to […].”
Step 2A of the Alice/Mayo Test – Prong One
Following Prong One of Step 2A of the 2019 PEG, the claim limitations are to be analyzed to determine whether they “recite” a judicial exception or in other words whether a judicial exception is “set forth” or “described” in the claims. See MPEP §2106.04. An “abstract idea” judicial exception is subject matter that falls within at least one of the following groupings: (1) Mathematical Concepts; (2) Certain Methods of Organizing Human Activity, and (3) Mental Processes. See MPEP § 2106.04(a).
Claims 1-15 are rejected under 35 U.S.C. § 101, because the claimed invention is directed to an abstract idea without significantly more. Representative independent claims 1, 13, and 14 include limitations that recite an abstract idea. Note that independent claim 14 is a system claim, while claim 1 covers the matching method claim and claim 13 covers the matching non-transitory computer-readable storage medium claim [based on the interpretation of the computer program, as described above]. Specifically, independent claim 14 recites (and claim 1 substantially recites the following limitations):
A system for predicting a risk of ventricular arrhythmia in a subject, the system comprising:
an input interface configured to:
obtain an input cardiac signal of the subject; and;
a processing unit configured to:
provide the input cardiac signal as an input to a machine-learning model, the machine-learning model being trained to predict, based on the input cardiac signal, a ventricular arrhythmia risk score indicating a risk of future ventricular arrhythmia occurrence; and
determine a risk value describing a predicted risk of future ventricular arrhythmia occurrence for the subject based on the ventricular arrythmia score.
However, the aforementioned limitations that are identified in underlined font comprise a process that, under its broadest reasonable interpretation, falls within the “Mental Processes” grouping of abstract ideas. See 2019 Revised PEG. The Mental Processes category covers concepts which are capable of being performed in the human mind or encompasses a human performing the step(s) mentally with the aid of a pen and paper (including an observation, evaluation, judgment, or opinion) (i.e., predicting a risk of ventricular arrhythmia in a subject; obtaining an input cardiac signal of the subject; predicting a ventricular arrhythmia risk score indicating a risk of future ventricular arrhythmia occurrence; and determining a risk value describing a predicted risk of future ventricular arrhythmia occurrence for the subject based on the ventricular arrhythmia risk score). That is, other than reciting some computer components and functions (the foregoing limitations in claim 1 which are not underlined), the context of claims 1 and 14 encompass concepts that are capable of being performed in the human mind or encompasses a human performing the steps mentally with the aid of a pen and paper (including an observation, evaluation, judgment, and/or opinion) (i.e., predicting a risk of ventricular arrhythmia in a subject; obtaining an input cardiac signal of the subject; predicting a ventricular arrhythmia risk score indicating a risk of future ventricular arrhythmia occurrence; and determining a risk value describing a predicted risk of future ventricular arrhythmia occurrence for the subject based on the ventricular arrhythmia risk score).
The aforementioned claim limitations described in claims 1 and 14 are analogous to claim limitations directed toward concepts which are capable of being performed in the human mind or encompasses a human performing the step(s) mentally with the aid of a pen and paper, because they merely recite limitations which encompass a person mentally and/or manually: (1) predicting a risk of ventricular arrhythmia in a subject (i.e., a type of observation, evaluation, judgment, and/or opinion where a person could mentally make a prediction of a subject’s risk of ventricular arrhythmia); (2) obtaining an input cardiac signal of the subject (a type of observation, evaluation, judgment, and/or opinion where a person could mentally and/or manually collect/obtain cardiac signal data); (3) predicting a ventricular arrhythmia risk score indicating a risk of future ventricular arrhythmia occurrence (a type of observation, evaluation, judgment, and/or opinion where a person could mentally predict a risk score for the subject experiencing a ventricular arrythmia); and (4) determining a risk value describing a predicted risk of future ventricular arrhythmia occurrence for the subject based on the ventricular arrhythmia risk score (a type of observation, evaluation, judgment, and/or opinion where a person could mentally and/or manually determine a risk value, such as a probability, that a subject will experience a ventricular arrhythmia based on the predicted risk score). Medical professionals, such as cardiologists, commonly make these types of observations, evaluations, judgments, or opinions with their medical knowledge mentally and/or manually using a pen and paper, by looking at a patient’s data, including the patient’s cardiac signal data, and making a prediction of patient’s risk of experiencing a ventricular arrhythmia.
Therefore, the aforementioned underlined claim limitations may reasonably be interpreted as mental/manual observations, evaluations, judgments, and/or opinions made by a person, such as healthcare provider. If a claim limitation, under its broadest reasonable interpretation, covers concepts which are capable of being performed in the human mind or encompasses a human performing the step(s) mentally with the aid of a pen and paper, then it falls within the “Mental Processes” grouping of abstract ideas. See 2019 Revised PEG. Examiner notes that the “obtaining”, “predicting”, and “determining” steps which are underlined above in claims 1 and 14 could also be interpreted to fall with the “Certain Methods of Organizing Human Activity” grouping of abstract ideas (i.e., managing personal behavior or relationships or interactions between people, including social activities, teaching, and following rules or instructions), because these limitations are similar to a mental process that a neurologist should follow when testing a patient for nervous system malfunctions. See MPEP § 2106.04(a)(2)(II)(C) (citing In re Meyer). Accordingly, claims 1 and 14 recite an abstract idea that falls within the Mental Processes and the Certain Methods of Organizing Human Activity categories.
Examiner notes that: claims 2-12, 13, and 15 further define the at least one abstract idea (and thus fail to make the abstract idea any less abstract) as set forth below. Examiner also notes that dependent claims 2 and 6-11 and claims 13 and 15 include limitations that are deemed to be additional elements, and require further analysis under Prong Two of Step 2A; and dependent claims 3-5 and 12 do not provide any additional limitations that are deemed to be additional elements which require further analysis under Prong Two of Step 2A. For example, claims 3 and 12 describe further mental or manual steps directed to determining the risk value comprises either determining a percentage-likelihood of arrhythmia occurrence in the near-future, or comparing the ventricular arrhythmia score to at least one threshold value. Next, claims 4 and 5 describe that input cardiac signal comprises either (1) at least one of: a single-lead ECG signal, an ambulatory monitoring signal, and a PPG signal, or (2) cardiac data for a window of at least one hour’s length, which are deemed to be part of the abstract mental process because it merely modifies the type of data that is obtained mentally and/or manually with the aid of pen and paper.
Step 2A of the 2019 Revised PEG – Prong Two
Regarding Prong Two of Step 2A of the 2019 Revised PEG, it must be determined whether the claim as a whole integrates the abstract idea into a practical application. As noted in the 2019 Revised PEG, it must be determined whether any additional elements in the claims are indicative of integrating the abstract idea into a practical application in a manner that imposes a meaningful limit on the judicial exception. The courts have indicated that additional elements merely using a computer to implement an abstract idea, adding insignificant extra solution activity, or generally linking use of a judicial exception to a particular technological environment or field of use do not integrate a judicial exception into a “practical application.” See MPEP §§ 2106.05 (f)-(h).
In the present case, for independent claim 14, the additional limitations beyond the above-noted at least one abstract idea are as follows (where the bolded portions are the “additional limitations” while the underlined portions continue to represent the at least one “abstract idea”):
A system (the Examiner submits that this additional element amounts to adding the words “apply it” (or an equivalent), or mere instructions to implement the abstract idea on a computer, see MPEP § 2106.05(f)) for predicting a risk of ventricular arrhythmia in a subject, the system comprising (the Examiner submits that this additional element amounts to adding the words “apply it” (or an equivalent), or mere instructions to implement the abstract idea on a computer, see MPEP § 2106.05(f)):
an input interface configured to (the Examiner submits that this additional element amounts to adding the words “apply it” (or an equivalent), or mere instructions to implement the abstract idea on a computer, see MPEP § 2106.05(f)):
obtain an input cardiac signal of the subject; and;
a processing unit configured to (the Examiner submits that this additional element amounts to adding the words “apply it” (or an equivalent), or mere instructions to implement the abstract idea on a computer, see MPEP § 2106.05(f)):
provide the input cardiac signal as an input to a machine-learning model, the machine-learning model being trained (the Examiner submits that this additional element amounts to adding the words “apply it” (or an equivalent), or mere instructions to implement the abstract idea on a computer, see MPEP § 2106.05(f); and the Examiner further submits that this additional element amounts to generally linking the abstract idea to a particular field of use or technological environment as noted below, see MPEP § 2106.05(h)) to predict, based on the input cardiac signal, a ventricular arrhythmia risk score indicating a risk of future ventricular arrhythmia occurrence; and
determine a risk value describing a predicted risk of future ventricular arrhythmia occurrence for the subject based on the ventricular arrythmia score.
However, the recitation of these limitations is made with a high-level of generality (i.e., using computer components and a machine learning model to perform the abstract mental process of: predicting a risk of ventricular arrhythmia in a subject; obtaining an input cardiac signal of the subject; predicting a ventricular arrhythmia risk score indicating a risk of future ventricular arrhythmia occurrence; and determining a risk value describing a predicted risk of future ventricular arrhythmia occurrence for the subject based on the ventricular arrhythmia risk score), such that it amounts to no more than: (1) adding the words “apply it” (or is the equivalent of) with the judicial exception; mere instructions to implement an abstract idea on a computer; or merely uses a computer as a tool to perform an abstract idea; (2) adding insignificant extra-solution activity to the judicial exception; and (3) generally linking the use of the judicial exception to a particular technological environment or field of use (i.e., merely linking the abstract mental process to the field of machine learning). See MPEP §§ 2106.05(f)-(h).
- The following are examples of court decisions that demonstrate merely applying instructions by reciting the computer structure as a tool to implement the claimed limitations (e.g., see MPEP § 2106.05(f)):
- Invoking computers or other machinery merely as a tool to perform an existing process, e.g. see, Affinity Labs v. DirecTV – similarly, the current invention invokes computers (i.e., the system, input interface, and processing unit) and other machinery to perform the existing process of determining a risk value describing a predicted risk of future ventricular arrhythmia; and
- Requiring the use of software to tailor information and provide it to the user on a generic computer, e.g. see, Intellectual Ventures I LLC v. Capital One Bank – similarly, the current invention merely requires the trained machine learning model to ultimately perform the abstract mental process of predicting a ventricular arrhythmia risk score, as described in claims 1 and 14.
- The following represent examples that courts have identified as generally linking the abstract idea to a particular technological environment (e.g., see MPEP § 2106.05(h)):
- Specifying that the abstract idea is executed in a computer environment, because this requirement merely limits the claims to a particular field, e.g., see FairWarning v. Iatric Sys. – similarly, the describing that the abstract idea is implemented with the aforementioned computer components and machine learning model, as described in claims 1 and 14, merely limits the claims to a computer environment and does not provide any meaningful limits to the abstract mental process described in the claims; and
- Limiting the abstract idea of collecting information, analyzing it, and displaying certain results of the collection and analysis to data related to the electric power grid, because limiting application of the abstract idea to power-grid monitoring is simply an attempt to limit the use of the abstract idea to a particular technological environment, e.g., see Electric Power Group, LLC v. Alstom S.A. – similarly, the limitations directed to “provide the input cardiac signal as an input to a machine-learning model, the machine-learning model being trained”, described in claims 1 and 14, merely limits the abstract idea to the field of machine learning technologies and does not provide any meaningful limits to the abstract mental process described in the claims.
Thus, the additional elements in independent claims 1 and 14 are not indicative of integrating the judicial exception into a practical application. Similarly, dependent claims 3-5 and 12 do not recite any additional elements outside of those identified as being directed to the abstract idea (or those additional elements which were already identified and analyzed in claim 1), described above. Examiner notes that dependent claims 2 and 6-11 and claims 13 and 15 recite the following additional elements (in bold font below):
wherein the machine-learning model comprises a plurality of machine-learning algorithms, wherein each machine-learning algorithm generates a respective ventricular arrhythmia risk prediction, and wherein the ventricular arrhythmia risk score comprises the plurality of ventricular arrhythmia risk predictions (the Examiner submits that this additional element amounts to adding the words “apply it” (or an equivalent), or mere instructions to implement the abstract idea on a computer, see MPEP § 2106.05(f); and the Examiner further submits that this additional element amounts to generally linking the abstract idea to a particular field of use or technological environment as noted below, see MPEP § 2106.05(h)) (as described in claim 2);
wherein the method further comprises obtaining demographic data of the subject, and wherein the machine-learning model comprises a first random forest classifier, the first random forest classifier being trained (the Examiner submits that this additional element amounts to adding the words “apply it” (or an equivalent), or mere instructions to implement the abstract idea on a computer, see MPEP § 2106.05(f); and the Examiner further submits that this additional element amounts to generally linking the abstract idea to a particular field of use or technological environment as noted below, see MPEP § 2106.05(h)) to predict, for the input cardiac signal and the demographic data, a demographic ventricular arrhythmia risk prediction (as described in claim 6);
prior to providing the at least one input cardiac signal as an input to the machine-learning model, the method further comprises: processing the input cardiac signal so that the input cardiac signal comprises at least one cardiac measurement value (the Examiner submits that this additional element amounts to adding the words “apply it” (or an equivalent), or mere instructions to implement the abstract idea on a computer, see MPEP § 2106.05(f)) (as described in claim 7);
wherein the machine-learning model comprises a second random forest classifier, the second random forest classifier being trained (the Examiner submits that this additional element amounts to adding the words “apply it” (or an equivalent), or mere instructions to implement the abstract idea on a computer, see MPEP § 2106.05(f); and the Examiner further submits that this additional element amounts to generally linking the abstract idea to a particular field of use or technological environment as noted below, see MPEP § 2106.05(h)) to predict, for the at least one cardiac measurement value, a measurement ventricular arrhythmia risk prediction (as described in claim 8);
wherein prior to providing the least one input cardiac signal as an input to the machine-learning model, the method further comprises: processing the input cardiac signal so that the input cardiac signal comprises a heart rate density plot (the Examiner submits that this additional element amounts to adding the words “apply it” (or an equivalent), or mere instructions to implement the abstract idea on a computer, see MPEP § 2106.05(f)) (as described in claim 9);
wherein the machine-learning model comprises a first neural network, the first neural network being trained (the Examiner submits that this additional element amounts to adding the words “apply it” (or an equivalent), or mere instructions to implement the abstract idea on a computer, see MPEP § 2106.05(f); and the Examiner further submits that this additional element amounts to generally linking the abstract idea to a particular field of use or technological environment as noted below, see MPEP § 2106.05(h)) to predict, for the heart rate density plot, a heart rate ventricular arrhythmia risk prediction (as described in claims 10);
wherein the machine-learning model comprises a second neural network, the second neural network being trained (the Examiner submits that this additional element amounts to adding the words “apply it” (or an equivalent), or mere instructions to implement the abstract idea on a computer, see MPEP § 2106.05(f); and the Examiner further submits that this additional element amounts to generally linking the abstract idea to a particular field of use or technological environment as noted below, see MPEP § 2106.05(h)) to predict, for the input cardiac signal, a raw ventricular arrythmia risk prediction (as described in claim 11);
A computer program comprising code means (the Examiner submits that this additional element amounts to adding the words “apply it” (or an equivalent), or mere instructions to implement the abstract idea on a computer, see MPEP § 2106.05(f)) for implementing the method of claim 1 when said program is run on a processing system (the Examiner submits that this additional element amounts to adding the words “apply it” (or an equivalent), or mere instructions to implement the abstract idea on a computer, see MPEP § 2106.05(f)) (as described in claim 13); and
A monitoring system (the Examiner submits that this additional element amounts to adding the words “apply it” (or an equivalent), or mere instructions to implement the abstract idea on a computer, see MPEP § 2106.05(f)) comprising a cardiac monitor (the Examiner submits that this additional element amounts to adding the words “apply it” (or an equivalent), or mere instructions to implement the abstract idea on a computer, see MPEP § 2106.05(f)) and the system of claim 14 (the Examiner submits that this additional element amounts to adding the words “apply it” (or an equivalent), or mere instructions to implement the abstract idea on a computer, see MPEP § 2106.05(f)) (as described in claim 15).
However, these additional elements in dependent claims 2 and 6-11 and claims 13 and 15 are deemed to be no more than (1) adding the words “apply it” (or is the equivalent of) with the judicial exception; mere instructions to implement an abstract idea on a computer; or merely uses a computer as a tool to perform an abstract idea; (2) adding insignificant extra-solution activity to the judicial exception; and (3) generally linking the use of the judicial exception to a particular technological environment or field of use (i.e., merely linking the abstract mental process to the medical field of machine learning and neural networks), for similar reasons as identified above. See analysis above; see also MPEP §§ 2106.05(f)-(h). As such, the additional elements in claims 1, 2, 6-11, and 13-15 are not indicative of integrating the judicial exception into a practical application.
Looking at the additional limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. For instance, unlike claims that have been held as a whole to be directed to an improvement or otherwise directed to something more than the abstract idea, claims 1-15: (1) are not directed to improvements to the functioning of a computer, or to any other technology or technical field similar to the Enfish, LLC v. Microsoft Corp. case (see MPEP § 2106.05(a)); (2) do not apply or use a judicial exception to effect a particular treatment or prophylaxis for a disease or medical condition (see MPEP § 2106.04(d)(2)); (3) do not apply the judicial exception with, or by use of, a particular machine (see MPEP § 2106.05(b)); (4) do not effect a transformation or reduction of a particular article to a different state or thing (see MPEP § 2106.05(c)); nor do they (5) apply or use the judicial exception in some other meaningful way beyond generally linking the use of the judicial exception to a particular technological environment, such that the claim as whole is more than a drafting effort designed to monopolize the exception (see MPEP § 2106.05(e) and MPEP § 2106.04(d)(2)). For these reasons, claims 1-15 do not recite additional elements that integrate the judicial exception into a practical application.
Step 2B of the 2019 Revised PEG
Regarding Step 2B of the 2019 Revised PEG, claims 1-15 do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above, with respect to whether the abstract idea is integrated into a practical application, the additional elements of claims 1, 2, 6-11, and 13-15 amount to no more than: (1) adding the words “apply it” (or is the equivalent of) with the judicial exception; mere instructions to implement an abstract idea on a computer; or merely uses a computer as a tool to perform an abstract idea; (2) adding insignificant extra-solution activity to the judicial exception; and (3) generally linking the use of a judicial exception to a particular technological environment or field of use. See MPEP §§ 2106.05(f)-(h). Further the additional elements, other than the abstract idea per se, when considered both individually and as an ordered combination, amount to no more than limitations consistent with what the courts recognize, or those having ordinary skill in the art would recognize, to be well-understood, routine, and conventional computer components. See MPEP §§ 2106.05 (d).
Specifically, the Examiner submits that the additional elements of claims 1, 2, 6-11, and 13-15, as recited, the system; input interface; processing unit; machine learning model; computer program comprising code means; processing system; monitoring system; cardiac monitor; and the steps of: “provide the input cardiac signal as an input to a machine-learning model, the machine-learning model being trained”; “training a machine learning model based on the historical cardiac signal patient data”; “wherein the machine-learning model comprises a plurality of machine-learning algorithms, wherein each machine-learning algorithm generates a respective ventricular arrhythmia risk prediction, and wherein the ventricular arrhythmia risk score comprises the plurality of ventricular arrhythmia risk predictions”; “wherein the machine-learning model comprises a first random forest classifier, the first random forest classifier being trained”; “prior to providing the at least one input cardiac signal as an input to the machine-learning model, the method further comprises: processing the input cardiac signal so that the input cardiac signal comprises at least one cardiac measurement value”; “wherein the machine-learning model comprises a second random forest classifier, the second random forest classifier being trained”; “wherein prior to providing the least one input cardiac signal as an input to the machine-learning model, the method further comprises: processing the input cardiac signal so that the input cardiac signal comprises a heart rate density plot”; “wherein the machine-learning model comprises a first neural network, the first neural network being trained”; and “wherein the machine-learning model comprises a second neural network, the second neural network being trained”, are well-understood, routine, and conventional functions. See MPEP § 2106.05(d)(II).
- Regarding the aforementioned additional elements, these additional elements or combination of elements in the claims, other than the abstract idea per se, amount to no more than well-understood, routine, and conventional activities previously known to the industry, because:
- Applicant generally describes the system for performing the functions of claimed invention as being implemented by a computer that includes but is not limited to, “PCs workstations, laptops, PDAs, palm devices, servers, storages, and the like”. See Applicant’s specification as filed on May 15, 2024, p. 16, lines 4-6. The Examiner asserts that PCs, workstations, laptops, PDAs, palm devices, servers, storages, and other similar computer devices are the equivalent of general purpose computer devices/components when claimed in a generic manner. Therefore, this disclosure shows that the system and its components may be part of a general purpose computer. A general purpose computer is a well-understood, routine, and conventional computing device in the medical industry. As such, the system; input interface; processing unit; machine learning model; computer program comprising code means; processing system; monitoring system; cardiac monitor are deemed to be well-understood, routine, and conventional computer components.
- The Examiner submits that these limitations amount to merely using a computer or other machinery as tools for performing their typical functionality in conjunction with performing the above-noted at least one abstract idea (see MPEP § 2106.05(f) and analysis of these limitations under Step 2A, Prong Two above).
- The Examiner submits that these limitations generally link the use of the judicial exception to a particular technological environment or field of use – for example, the limitations directed to: the machine learning model; and the steps of: “provide the input cardiac signal as an input to a machine-learning model, the machine-learning model being trained”; “training a machine learning model based on the historical cardiac signal patient data”; “wherein the machine-learning model comprises a plurality of machine-learning algorithms, wherein each machine-learning algorithm generates a respective ventricular arrhythmia risk prediction, and wherein the ventricular arrhythmia risk score comprises the plurality of ventricular arrhythmia risk predictions”; “wherein the machine-learning model comprises a first random forest classifier, the first random forest classifier being trained”; “wherein the machine-learning model comprises a second random forest classifier, the second random forest classifier being trained”; “wherein the machine-learning model comprises a first neural network, the first neural network being trained”; and “wherein the machine-learning model comprises a second neural network, the second neural network being trained”, amount to limiting the abstract idea to the fields of machine learning and neural networks (see MPEP § 2106.05(h) and analysis of these limitations under Step 2A, Prong Two above).
Therefore, these limitations are also deemed to be well-understood, routine, and conventional under Step 2B for similar reasons since they are claimed in a generic manner. As such, the additional elements described in claims 1, 2, 6-11, and 13-15 are deemed to be additional elements which do not amount to significantly more than the abstract idea identified above.
Thus, taken alone, the additional elements of claims 1, 2, 6-11, and 13-15 do not amount to significantly more than the above-identified judicial exception (the abstract idea). Furthermore, looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functionality of a computer or improves any other technology, and their collective functions merely provide conventional computer implementation. Therefore, whether taken individually or as an ordered combination, claims 1, 2, 6-11, and 13-15 are nonetheless rejected under 35 U.S.C. § 101 as being directed to non-statutory subject matter.
Additionally, dependent claims 3-5 and 12 (which individually depend on claim 1 due to their respective chains of dependency), do not include additional elements that are sufficient to amount to significantly more than the judicial exception. Examiner notes that dependent claims 3-5 and 12 do not include any additional elements beyond those identified as well-understood, routine, and conventional components as described above in the subject matter eligibility rejections of independent claim 1. Dependent claims 3-5 and 12 merely add limitations that further narrow the abstract idea described in independent claim 1. Therefore, claims 1-15 are nonetheless rejected under 35 U.S.C. § 101 as being directed to non-statutory subject matter.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1, 3, 5, 7, and 12-15 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by:
- Ravishankar et al. (Pub. No. US 2023/0238134).
Regarding claims 1 and 14,
- Ravishankar et al. (Pub. No. US 2023/0238134) discloses:
- a method for predicting a risk of ventricular arrhythmia in a subject (Ravishankar, paragraphs [0003] and [0050]; Paragraph [0003] discloses a method includes predicting an imminent onset of a cardiac arrhythmia in a patient. Paragraph [0050] discloses that the data from the cardiac arrhythmia group may be further divided based on the type of cardiac arrhythmia experienced (e.g., ventricular tachycardia, ventricular fibrillation, atrial tachycardia, atrial fibrillation, or another type of arrhythmia) (i.e., the predicted arrythmia is a risk of ventricular arrhythmia).), the method comprising (as described in claim 1):
- a system for predicting a risk of ventricular arrhythmia in a subject (Ravishankar, paragraph [0013]; Paragraph [0013] discloses a system for training deep neural networks and understanding the factors behind the arrhythmia predictions.), the system comprising: an interface (Ravishankar, paragraph [0030]; Paragraph [0030] discloses that the data processing device includes a display device (i.e., an interface).) configured to (as described in claim 14):
- receiving an input cardiac signal of the subject (as described in claims 1 and 14) (Ravishankar, paragraph [0016]; Paragraph [0016] discloses that FIG. 1 shows a patient monitoring system that may be used to acquire patient monitoring data, which may include electrocardiogram (ECG) data (i.e., receiving an input cardiac signal of the subject) or multi-modal data including the ECG data and data from a plurality of sensors acquiring vital signs.);
- collecting historical cardiac signal patient data for a plurality of patients (as described in claims 1 and 14) (Paragraph [0058] discloses that new patient monitoring data may continue to be acquired as previously acquired patient monitoring data is processed by the local and contextual feature extraction algorithm (i.e., acquiring and processing previously acquired patient monitoring data is interpreted as the equivalent of collecting historical cardiac signal patient data for a plurality of patients, because the previously acquired patient monitoring data described in Ravishankar is cardiac signal data.).);
- training a machine learning model based on the historical cardiac signal patient data (as described in claims 1 and 14) (Ravishankar, paragraphs [0049] and [0050]; Paragraph [0049] discloses that the method includes inputting a training data that may be annotated by clinical experts with ground truth labels and may include data acquired from a plurality of subjects, where the training dataset may include ECG data and vital sign data obtained over a same time duration with respect to each other (i.e., a training dataset which includes historical cardiac signal patient data). Paragraph [0050] discloses that a single tri-net deep learning model may be trained to predict the onset of multiple types of cardiac arrhythmias that follow similar morphology and cardiac activity (i.e., training a machine learning model based on the historical cardiac signal patient data that follow similar morphology and cardiac activity).);
- providing the input cardiac signal as an input to the machine-learning model, the machine learning model trained to predict, based on the input cardiac signal, a ventricular arrhythmia risk score indicating a risk of future ventricular arrhythmia occurrence (as described in claims 1 and 14) (Ravishankar, paragraphs [0036], [0059], and [0060]; Paragraph [0036] discloses that the multi-arm neural network 218 outputs an arrhythmia prediction 220, which may include a score for a likelihood of cardiac arrhythmia onset (i.e., predicting a ventricular arrhythmia risk score indicating a risk of future ventricular arrhythmia occurrence for the subject). Paragraph [0059] discloses that at 506, the method 500 includes inputting the extracted features into a trained tri-net deep learning model, where the tri-net deep learning model may be broadly trained to more generically predict cardiac arrhythmias (i.e., providing the input cardiac signal as input to the machine learning model, where the machine learning model is trained to predict, based on the cardiac signal, a ventricular arrhythmia). Paragraph [0060] discloses that at 508, the method 500 includes receiving an arrhythmia prediction score from the tri-net deep learning model (i.e., the model is trained to predict, based on the cardiac signal, a ventricular arrhythmia risk score), where the arrhythmia prediction score may range from zero to one, for example, where zero represents a lowest probability of the patient experiencing imminent cardiac arrhythmia (e.g., within a number of minutes) and one represents a highest probability of the patient experiencing imminent cardiac arrhythmia (i.e., the ventricular arrhythmia risk score indicating a risk of future ventricular arrhythmia occurrence for the subject).); and
- determining a risk value describing a predicted risk of future ventricular arrhythmia occurrence for the subject based on the ventricular arrhythmia score (as described in claims 1 and 14) (Ravishankar, paragraphs [0036], [0061], and [0062]; Paragraph [0036] discloses that the score may be compared to a threshold to alert clinicians to a patient developing a cardiac arrhythmia. Additionally or alternatively, the arrhythmia prediction 220 may indicate a presence or absence of an imminent onset of a cardiac arrhythmia (i.e., indicating a presence or absence of an imminent onset of a cardiac arrythmia is interpreted as the equivalent of determining a risk value describing the predicted risk of future ventricular arrhythmia occurrence for the subject, where the imminent determination is deemed to be the determined risk value). Paragraph [0061] discloses at 510, the method 500 includes determining if the arrhythmia prediction score is greater than a threshold, where if the arrhythmia prediction score is not greater than the threshold (e.g., the arrhythmia prediction score is less than or equal to the threshold), the method 500 proceeds to 512 and includes not outputting an arrhythmia event (i.e., determining risk values describing a predicted risk of future ventricular arrhythmia occurrence for the subject based on the ventricular arrhythmia score), and paragraph [0062] discloses that if the arrhythmia prediction score is greater than the threshold, the method 500 proceeds to 514 and includes outputting the arrhythmia event (i.e., determining risk values describing a predicted risk of future ventricular arrhythmia occurrence for the subject based on the ventricular arrhythmia score).).
Regarding claim 3,
- Ravishankar discloses the limitations of claim 1 (which claim 3 depends on), as described above.
- Ravishankar further discloses a method, wherein:
- determining the risk value based on the ventricular arrhythmia score comprises determining a percentage-likelihood of arrythmia occurrence in the near-future (Ravishankar, paragraph [0036]; Paragraph [0036] discloses that the score may be a probability value (e.g., ranging from zero to one) (i.e., determining a percentage-likelihood value), as will be further elaborated below with respect to FIG. 5. Paragraph [0036] further discloses that additionally or alternatively, the arrhythmia prediction 220 may indicate a presence or absence of an imminent onset of a cardiac arrhythmia (i.e., determining that the arrhythmia onset is imminent is interpreted as the equivalent of determining arrythmia occurrence in the near-future, because as described above, the term “near-future” is a relative term and Applicant has not provided any description or boundaries for this relative term).).
Regarding claim 5,
- Ravishankar discloses the limitations of claim 1 (which claim 5 depends on), as described above.
- Ravishankar further discloses a method, wherein:
- the input cardiac signal comprises cardiac data for a window of at least one hour’s length (Ravishankar, paragraph [0022]; Paragraph [0022] discloses that the ECG monitor 102 further comprises an energy storage subsystem 108, wherein electrical energy may be stored, enabling the ECG monitor 102 to operate while attached to a patient for hours (i.e., the input cardiac signal will comprise cardiac data for a window of at least one hour).).
Regarding claim 7,
- Ravishankar discloses the limitations of claim 1 (which claim 7 depends on), as described above.
- Ravishankar further discloses a method, wherein:
- prior to providing the at least one input cardiac signal as an input to the machine-learning model, the method further comprises: processing the input cardiac signal so that the input cardiac signal comprises at least one cardiac measurement value (Ravishankar, paragraph [0047]; Paragraph [0047] teaches that a photoplethysmogram (PPG) waveform obtained from a pulse oximeter may include morphology, amplitude, heart rate variability, other derived features, and raw waveforms (i.e., processing the input cardiac signal so that the input signal comprises at least one cardiac measurement value, where the heart rate variability is the at least one cardiac measurement value). These features may be categorized into the temporally varying feature set 302, the segment-level and statistical features 308, and the 2D spectrograms 314 in an analogous manner to that described above for the ECG data and fed to the corresponding arm of the tri-net neural network 301. For example, 2D spectrograms may be generated from the raw PPG waveforms. As another example, the segment-level and statistical features 308 may comprise features describing the heart rate variability (i.e., the input cardiac signal comprises at least one cardiac measurement value).).
Regarding claim 12,
- Ravishankar discloses the limitations of claim 1 (which claim 12 depends on), as described above.
- Ravishankar further discloses a method, wherein:
- determining a risk value comprises comparing the ventricular arrythmia score to at least one threshold value and determining the risk value based on the comparison result (Ravishankar, paragraph [0036]; Paragraph [0036] discloses that the score may be compared to a threshold to alert clinicians to a patient developing a cardiac arrhythmia (i.e., comparing the ventricular arrhythmia score to at least one threshold value in order to determine the risk value based on the comparison).).
Regarding claim 13,
- Ravishankar discloses:
- a computer program comprising code means for implementing the method of claim 1 when said program is run on a processing system (Ravishankar, paragraph [0025]; Paragraph [0025] discloses that the data processing device 120 may comprise a processor 124 configured to execute machine readable instructions stored in a non-transitory memory 126 (i.e., a non-transitory computer-readable storage medium that stores a computer programmable instructions which cause a computer device to implement said computer programmable instructions for implementing the method of claim 1). [NOTE: Claim Interpretation - Based on the analysis above under the Claim Rejections - 35 U.S.C. § 101 Section above, the computer program described in claim 13 is interpreted to be a non-transitory computer-readable storage medium, storing computer readable instructions configured to cause a computer device to implement the method of claim 1.]
Regarding claim 15,
- Ravishankar discloses the limitations of claim 14 (which claim 15 depends on), as described above.
- Ravishankar further discloses a monitoring system, comprising:
- a cardiac monitor (Ravishankar, paragraph [0017]; Paragraph [0017] discloses that the patient monitoring system 100 comprises an ECG monitor 102 (i.e., a cardiac monitor).) and the system of claim 14 (See analysis above for mapping of Ravishankar to the limitations of claim 14, which is incorporated herein by reference.).
Claim Rejections - 35 USC § 103
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim 2 is rejected under 35 U.S.C. 103 as being unpatentable over:
- Ravishankar et al. (Pub. No. US 2023/0238134), in view of:
- Haddad et al. (Pub. No. US 2020/0108260).
Regarding claim 2,
- Ravishankar discloses the limitations of claim 1 (which claim 2 depends on), as described above.
- Ravishankar does not explicitly teach, however, in analogous art of methods and systems for predicting the likelihood that a patient will suffer from cardiac tachyarrhythmia, Haddad et al. (Pub. No. US 2020/0108260) teaches a method, wherein:
- wherein the machine-learning model comprises a plurality of machine-learning algorithms, wherein each machine-learning algorithm generates a respective ventricular arrhythmia risk prediction (Haddad, paragraphs [0142]-[0144]; Paragraph [0142] teaches that the cloud computing network 808 applies long-term algorithm 802 (i.e., one of the plurality of machine-learning algorithms) to provider data for patient 14 to generate a long-term probability that cardiac arrhythmia will occur in patient 14 over a long-term time period. Paragraph [0143] teaches that the cloud computing network 808 transmits instructions causing external device 27 to apply mid-term algorithm 804 (i.e., one of the plurality of machine-learning algorithms) to parametric patient data for patient 14 to generate a mid-term probability that cardiac arrhythmia will occur in patient 14 over a mid-term time period. Paragraph [0144] teaches that the external device 27 transmits instructions causing IMD 16 to apply short-term algorithm 806 (i.e., one of the plurality of machine-learning algorithms) to parametric patient data for patient 14 to generate a short-term probability that cardiac arrhythmia will occur in patient 14 over a short-term time period (i.e., paragraphs [0142]-[0144] show that each machine-learning algorithm generates a respective probability that ventricular arrhythmia risk prediction for different time periods).), and wherein the ventricular arrhythmia risk score comprises the plurality of ventricular arrhythmia risk predictions (Haddad, paragraphs [0151] and [0152]; Paragraph [0151] teaches that the IMD [implantable medical device] may perform feature detection on one or more of electrocardiogram data, electrode impedance measurements, accelerometer data, temperature data for patient 14, audio data of a heart of patient 14, or risk scores computed by other algorithms of different levels (i.e., the risk scores comprise the plurality of ventricular arrythmia risk predictions). Such risk scores may include, e.g., the long-term probability PEMR generated by one or more computing devices 24 that a cardiac arrythmia will occur in patient 14 over a long-term time period and the mid-term probability PD24 generated by external device 27 that a cardiac arrythmia will occur in patient 14 over a mid-term time period (i.e., the risk scores comprise the plurality of ventricular arrythmia risk predictions). Paragraph [0152] teaches that this feature is beneficial for allowing for enhanced patient care and increasing the ability to prevent cardiac arrhythmias in a patient.).
Therefore, it would have been obvious to one of ordinary skill in the art of methods and systems for predicting the likelihood that a patient will suffer from cardiac tachyarrhythmia at the time of the effective filing date of the claimed invention to modify the method and system for cardiac arrhythmia prediction, taught by Ravishankar, to incorporate a configuration that utilizes a plurality of machine learning models that generate different predictions that are incorporated into the cardiac arrhythmia risk score, as taught by Haddad, in order to allow for enhanced patient care and increase the ability to prevent cardiac arrhythmias in a patient. See Haddad, paragraph [0152]; see also MPEP § 2143 G.
Claims 4 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over:
- Ravishankar et al. (Pub. No. US 2023/0238134), in view of:
- Fornwalt et al. (Pub. No. US 2021/0076960).
Regarding claim 4,
- Ravishankar discloses the limitations of claim 1 (which claim 4 depends on), as described above.
- Ravishankar does not explicitly teach, however, in analogous art of methods and systems for predicting the likelihood that a patient will suffer from atrial fibrillation, Fornwalt et al. (Pub. No. US 2021/0076960) teaches a method, wherein:
- the input cardiac signal comprises at least one of: a single-lead ECG signal; an ambulatory monitoring signal; and a PPG signal (Fornwalt, paragraph [0096]; Paragraph [0096] teaches that in some embodiments, the ECG can include a single lead (i.e., the input cardiac signal comprises a single-lead ECG signal). Paragraph [0096] teaches that this feature is beneficial for providing ECG signals through varying numbers of leads and different sampling rates and time periods.).
Therefore, it would have been obvious to one of ordinary skill in the art of methods and systems for predicting the likelihood that a patient will suffer from atrial fibrillation at the time of the effective filing date of the claimed invention to modify the method and system for cardiac arrhythmia prediction, taught by Ravishankar, to incorporate a single-lead ECG signal configuration, as taught by Fornwalt, in order to provide ECG signals through varying numbers of leads and different sampling rates and time periods. See Fornwalt, paragraph [0096]; see also MPEP § 2143 G.
Regarding claim 11,
- Ravishankar discloses the limitations of claim 1 (which claim 11 depends on), as described above.
- Ravishankar does not explicitly teach, however, in analogous art of methods and systems for predicting the likelihood that a patient will suffer from atrial fibrillation, Fornwalt et al. (Pub. No. US 2021/0076960) teaches a method, wherein:
- the machine-learning model comprises a second neural network, the second neural network being trained to predict, for the input cardiac signal, a raw ventricular arrythmia risk prediction (Fornwalt, paragraphs [0097] and [0098]; Paragraph [0097] teaches that the machine learning model may be generated by a feedforward neural network, such as a convolutional neural network, a radial basis function neural network, a recurrent neural network, a modular or associative neural network (i.e., the machine-learning model comprise a second neural network). In some examples, long-term prediction module 450 trains the machine learning model with parametric patient data and provider data for a plurality of patients to generate the long-term probability, where paragraph [0039] generally teaches that the parametric data includes a raw electromyogram of patient 14 and one or more features derived from the raw electromyogram (i.e., since the machine learning model is trained to predict the long-term probability that a cardiac arrythmia will occur in a patient with the raw electromyogram data, then it is interpreted that model is trained to predict a raw ventricular arrythmia risk prediction based on the collection and training with this raw data). Paragraph [0098] teaches that this feature is beneficial for providing more accurate predictions for a particular individual.).
Therefore, it would have been obvious to one of ordinary skill in the art of methods and systems for predicting the likelihood that a patient will suffer from atrial fibrillation at the time of the effective filing date of the claimed invention to modify the method and system for cardiac arrhythmia prediction, taught by Ravishankar, to incorporate a step and feature directed to incorporating a neural network that is trained to predict whether a cardiac arrythmia will occur in a patient using raw electromyogram data from the patient, as taught by Fornwalt, in order to provide more accurate predictions for a particular individual. See Fornwalt, paragraph [0098]; see also MPEP § 2143 G.
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over:
- Ravishankar et al. (Pub. No. US 2023/0238134), in view of:
- Sirendi et al. (Pub. No. US 2021/0353166).
Regarding claim 6,
- Ravishankar discloses the limitations of claim 1 (which claim 6 depends on), as described above.
- Ravishankar does not explicitly teach, however, in analogous art of methods and systems for predicting risks of cardiac events, Sirendi et al. (Pub. No. US 2021/0353166) teaches a method, wherein:
- the method further comprises obtaining demographic data of the subject (Sirendi, paragraph [0022]; Paragraph [0022] teaches that the method optionally further comprises providing further data relating to the patient, including demographic data.), and wherein the machine-learning model comprises a first random forest classifier (Sirendi, paragraph [0055]; Paragraph [0055] teaches that the one or more machine learning algorithms may comprise a random forest.), the first random forest classifier being trained to predict, for the input cardiac signal and the demographic data, a demographic ventricular arrhythmia risk prediction (Sirendi, paragraphs [0022], [0153], and [0308]; Paragraph [0153]; Paragraph [0153] teaches that the AI classifier [the random forest classifier] can be trained from a training dataset comprising known normal and abnormal heartbeats from which the system can learn to predict whether an arrhythmia is going to occur (and since paragraph [0022] teaches that the method includes using patient demographic data, the description in paragraph [0153] is interpreted as training the model to predict a demographic ventricular arrhythmia risk prediction. (i.e., these are examples of at least one cardiac measurement value). Paragraph [0308] teaches that this feature is beneficial for indicating that a patient may need more careful monitoring during a determined period, or that it may be valuable to analyze patient data in more detail and/or to carry out tests.).
Therefore, it would have been obvious to one of ordinary skill in the art of methods and systems for predicting risks of cardiac events at the time of the effective filing date of the claimed invention to modify the method and system for cardiac arrhythmia prediction, taught by Ravishankar, to incorporate steps and features directed to using a random forest machine learning model to analyze patient demographic data and make cardiac arrhythmia predictions based on the demographic data, as taught by Sirendi, in order to indicate that a patient may need more careful monitoring during a determined period, or that it may be valuable to analyze patient data in more detail and/or to carry out tests. See Sirendi, paragraph [0308]; see also MPEP § 2143 G.
Claims 8 is rejected under 35 U.S.C. 103 as being unpatentable over:
- Ravishankar et al. (Pub. No. US 2023/0238134), in view of:
- Thakur et al. (Pub. No. US 2020/0297230).
Regarding claim 8,
- Ravishankar discloses the limitations of claim 7 (which claim 8 depends on), as described above.
- Ravishankar does not explicitly teach, however, in analogous art of methods and systems for predicting risks of atrial arrhythmia, Thakur et al. (Pub. No. US 2020/0297230) teaches a method, wherein:
- wherein the machine-learning model comprises a second random forest classifier (Thakur, paragraph [0078]; Paragraph [0078] teaches that examples of the ML model may include a random forest model (i.e., the machine learning model comprises a second random forest classifier).), the second random forest classifier being trained to predict, for the at least one cardiac measurement value, a measurement ventricular arrhythmia risk prediction (Thakur, paragraphs [0066], [0068], [0069], and [0098]; Paragraph [0069] teaches that the arrhythmic risk stratifier 230 may assess a cardiac arrhythmia risk in a patient, and in some examples, predict a future cardiac arrhythmic event such as an AF event (i.e., the random forest classifier is trained to predict a measurement ventricular arrhythmia risk prediction), using the physiologic information received from the sensor circuit 210, where paragraph [0066] teaches that the cardiac parameters include heart rate variability (i.e., the at least one cardiac measurement value) and paragraph [0068] teaches that the this data is used for the arrhythmia risk stratification and AF event prediction (i.e., the prediction of the measurement ventricular arrhythmia risk prediction is based on the at least one cardiac measurement value). Paragraph [0098] teaches that this feature is beneficial for improving timely detection of AF as soon as it first occurs, as well as improving the identification of silent AF before patients become symptomatic.).
Therefore, it would have been obvious to one of ordinary skill in the art of methods and systems for predicting risks of cardiac events at the time of the effective filing date of the claimed invention to modify the method and system for cardiac arrhythmia prediction, taught by Ravishankar, to incorporate steps and features directed to using a random forest machine learning model to analyze patient cardiac data and make cardiac arrhythmia predictions based on the cardiac data, as taught by Thakur, in order to improve timely detection of atrial fibrillation as soon as it first occurs, as well as improve the identification of silent atrial fibrillation before patients become symptomatic. See Thakur, paragraph [0098]; see also MPEP § 2143 G.
Claims 9 and 10 are rejected under 35 U.S.C. 103 as being unpatentable over:
- Ravishankar et al. (Pub. No. US 2023/0238134), in view of:
- Laversin et al. (Pub. No. US 2022/0218259).
Regarding claim 9,
- Ravishankar discloses the limitations of claim 1 (which claim 9 depends on), as described above.
- Ravishankar does not explicitly teach, however, in analogous art of methods and systems for predicting the likelihood that a patient will suffer from a cardiac arrhythmia event, Laversin et al. (Pub. No. US 2022/0218259) teaches a method, wherein:
- prior to providing the at least one input cardiac signal as an input to the machine-learning model, the method further comprises: processing the input cardiac signal so that the input cardiac signal comprises a heart density plot (Laversin, paragraph [0125]; Paragraph [0125] teaches that FIG. 9 is a zoomed-in version of a heart rate density plot (i.e., the input cardiac signal comprises a heart density plot). Paragraph [0125] teaches that this feature is beneficial for providing visual references for the user permitting easy identification of a specific category of events and/or episodes along the cardiac signal.).
Therefore, it would have been obvious to one of ordinary skill in the art of methods and systems for predicting the likelihood that a patient will suffer from a cardiac arrhythmia event at the time of the effective filing date of the claimed invention to modify the method and system for cardiac arrhythmia prediction, taught by Ravishankar, to incorporate a step and feature directed to processing input cardiac signal data into at heart rate density plot prior to inputting the cardiac signal data into a machine learning model, as taught by Laversin, in order to provide visual references for the user permitting easy identification of a specific category of events and/or episodes along the cardiac signal. See Laversin, paragraph [0125]; see also MPEP § 2143 G.
Regarding claim 10,
- The combination of: Ravishankar, as modified in view of Laversin, teaches the limitations of claim 9 (which claim 10 depends on), as described above.
- Laversin further teaches a method, wherein:
- the machine-learning model comprises a first neural network Laversin, paragraph [0125]; Paragraph [0125] teaches the system may include an application that communicates with an ECG platform running on a server that processes and analyzes the ECG data, e.g., using neural networks for delineation of the cardiac signal and classification of various abnormalities, conditions and/or descriptors (i.e., the , machine-learning model comprises a first neural network).), the first neural network being trained to predict, for the heart rate density plot, a heart rate ventricular arrhythmia risk prediction (Laversin, paragraphs [0195] and [0196]; Paragraph [0196] teaches that at step 964, the patterns and/or trends may be used to determine a time period for which there is an increased risk and/or likelihood of an arrhythmia occurring (i.e., the first neural network is trained to determine a heart rake ventricular arrhythmia risk prediction using the heart rate density data that was disclosed in paragraph [0125].) Paragraph [0195] teaches that this feature is beneficial for determining a time period for recording ECG data likely to include an arrhythmia event.).
Therefore, it would have been obvious to one of ordinary skill in the art of methods and systems for predicting the likelihood that a patient will suffer from a cardiac arrhythmia event at the time of the effective filing date of the claimed invention to further modify the method and system for cardiac arrhythmia prediction, taught by Ravishankar, as modified in view of Laversin, to incorporate a step and feature directed to training a neural network to predict ventricular arrhythmia risks using a patient’s heart rate density data, as taught by Laversin, in order to determine a time period for recording ECG data likely to include an arrhythmia event. See Laversin, paragraph [0195]; see also MPEP § 2143 G.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Nicholas Akogyeram II whose telephone number is (571) 272-0464. The examiner can normally be reached Monday - Friday, between 8:00am - 5:00pm.
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, Jason Dunham can be reached at (571) 272-8109. 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.
Official replies to this Office action may now be submitted electronically by registered
users of the EFS-Web system. Information on EFS-Web tools is available on the Internet at:
http://www.uspto.gov/patents/processlfi!elefslguidance/index.isp. An EFS-Web Quick-Start
Guide is available at: http://www.uspto.gov/ebc/portallefslquick-start.pdf.
Alternatively, official replies to this Office Action may still be submitted by any one of fax, mail, or hand delivery.
Faxed replies should be directed to the central fax at (571) 273-8300.
Mailed replies should be addressed to:
United States Patent and Trademark Office:
Commissioner of Patents and Trademarks
P.O. Box 1450
Alexandria, VA 22313-1450
Hand delivered responses should be brought to the United States Patent and Trademark Office Customer Service Window:
Randolph Building
401 Dulany Street
Alexandria, VA 22314-1450
/N.A.A./Examiner, Art Unit 3686
/JONATHON A. SZUMNY/Primary Examiner, Art Unit 3686
Prosecution Insights