DETAILED ACTION
This action is made FINAL in response to the amendments filed on 11/24/2025.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1 – 11 and 21 - 29 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
As to claim 1,
Step 2A, Prong One
The claim recites in part:
deriving, by a deep learning autoencoder of the electrocardiogram analysis module, disease vectors for a plurality of diseases using electrocardiogram training data from both disease-negative individuals and disease-positive individuals for the plurality of diseases, wherein each disease vector corresponds to a respective disease of the plurality of diseases within a lower-dimensional latent space
generating, by a statistical modeling algorithm of the electrocardiogram analysis module, at least one disease risk score for the individual for the plurality of diseases based on the embedding and the disease vectors in the lower-dimensional latent space
Under the broadest reasonable interpretation, these limitations are process steps that cover a mathematical relationship, mathematical formula, or algorithm, which is identified as an abstract idea. Specifically, the recited vectors recites a data processing step involving organization and manipulation of data. A vector can be involves human thought, visualization, and/or mathematical calculation. The concept of a vector is abstract and mathematical, and the human brain is thought to represent concepts in a way that can be modeled as vector spaces
Accordingly, at Step 2A, Prong One, the claim is directed to an abstract idea.
Step 2A, Prong Two
The judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements of:
generating, via a data preprocessor of the electrocardiogram analysis module, a standardized input from an electrocardiogram recorded from an individual
which amounts to extra-solution activity of gathering data for use in the claimed process. As described in MPEP 2106.05(g), limitations that amount to merely adding insignificant extra-solution activity to a judicial exception do not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application.
The claim further recites:
encoding, by the deep learning autoencoder of the electrocardiogram analysis module, the standardized input into an embedding, the embedding being a representation of features extracted from the standardized input in the lower-dimensional latent space
these elements are recited at a high-level of generality and amounts to no more than adding the words “apply it” to the judicial exception. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f)). These limitations also amount to extra solution activity because it is a mere nominal or tangential addition to the claim, amounting to mere data output (see MPEP 2106.05(g)).
The claim further recites analysis module, non-transitory computer-readable storage medium, data preprocessor, and deep learning autoencoder which are recited at a high-level of generality and amounts to no more than mere instructions to apply the exception using a generic computer component (See MPEP 2106.05(f)).
In addition, the recitation of electrocardiogram training data, standardized input, embedding being a lower-dimensional latent space, and statistical modeling algorithm amounts to generally linking the use of the judicial exception to a particular environment of field of use (See MPEP 2106.05(h)). As such, the claim does not integrate the judicial exception into a practical application.
Accordingly, at Step 2A, Prong Two, the additional elements individually or in combination do no integrate the judicial exception into a practical application.
Step 2B
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. As discussed above, the additional elements of:
generating, via a data preprocessor of the electrocardiogram analysis module, a standardized input from an electrocardiogram recorded from an individual
are recited at a high level of generality and amounts to extra-solution activity of receiving data i.e. pre-solution activity of gathering data for use in the claimed process. The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. The limitations:
encoding, by the deep learning autoencoder of the electrocardiogram analysis module, the standardized input into an embedding, the embedding being a representation of features extracted from the standardized input in the lower-dimensional latent space
are recited at a high-level of generality and amounts to no more than adding the words “apply it” to the judicial exception. These limitations also amount to extra solution activity because it is a mere nominal or tangential addition to the claim, amounting to mere data output (see MPEP 2106.05(g)). The courts have similarly found limitations directed to displaying a result, recited at a high level of generality, to be well-understood, routine, and conventional. See (MPEP 2106.05(d)(II), "presenting offers and gathering statistics.", “determining an estimated outcome and setting a price”).
The electrocardiogram analysis module, non-transitory computer-readable storage medium, data preprocessor, and deep learning autoencoder are recited at a high-level of generality and amounts to no more than mere instructions to apply the exception using a generic computer component (See MPEP 2106.05(f)).
The recitation of electrocardiogram training data, standardized input, embedding being a lower-dimensional latent space, and statistical modeling algorithm amounts to generally linking the use of the judicial exception to a particular environment of field of use (See MPEP 2106.05(h)).
Accordingly, at Step 2B the additional elements individually or in combination do not amount to significantly more than the judicial exception.
As to claim 2,
Step 2A, Prong One
The claim does not recite an abstract idea or any other judicial exception and therefore passes Step 2A, Prong of the Alice/Mayo analysis.
Step 2A, Prong Two
The judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements of:
reconstructing, via a decoder network of the deep learning autoencoder, the electrocardiogram from the embedding
which is recited at a high-level of generality with no detail of the reconstructing process and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f))
The claim further recites a decoder network which is recited at a high-level of generality and amounts to no more than mere instructions to apply the exception using a generic computer component (See MPEP 2106.05(f)).
In addition, the recitation of an electrocardiogram amounts to generally linking the use of the judicial exception to a particular environment of field of use (See MPEP 2106.05(h)). As such, the claim does not integrate the judicial exception into a practical application.
Accordingly, at Step 2A, Prong Two, the additional elements individually or in combination do no integrate the judicial exception into a practical application.
Step 2B
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. The limitations:
reconstructing, via a decoder network of the deep learning autoencoder, the electrocardiogram from the embedding
which is recited at a high-level of generality with no detail of the reconstructing process and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f))
The decoder network is recited at a high-level of generality and amounts to no more than mere instructions to apply the exception using a generic computer component (See MPEP 2106.05(f)).
The recitation of an electrocardiogram amounts to generally linking the use of the judicial exception to a particular environment of field of use (See MPEP 2106.05(h)).
Accordingly, at Step 2B the additional elements individually or in combination do not amount to significantly more than the judicial exception.
As to claim 3, the limitations “wherein the deep learning autoencoder comprises an encoder network and a decoder network, the encoder network and the decoder network each including multiple convolutional blocks with skip connections” amounts to generally linking the use of the judicial exception to a particular environment of field of use (See MPEP 2106.05(h)). The decoder network and encoder network recited at a high-level of generality and amounts to no more than mere instructions to apply the exception using a generic computer component (See MPEP 2106.05(f)).
As to claim 4,
Step 2A, Prong One
The claim recites in part:
generating, via the deep learning autoencoder, disease-positive embeddings and disease-negative embeddings from the electrocardiogram training data;
plotting the disease-positive embeddings and the disease-negative embeddings in a two-dimensional space projection of the lower-dimensional latent space;
determining a disease-positive centroid and a disease-negative centroid in the two-dimensional projection based on the plotted disease-positive embeddings and the plotted disease-negative embeddings, respectively; and
defining a given disease vector by connecting the disease-negative centroid
to the disease-positive centroid in the two-dimensional projection
Under the broadest reasonable interpretation, these limitations are process steps that cover a mathematical relationship, mathematical formula, or algorithm, which is identified as an abstract idea. Specifically, the recited vectors recites a data processing step involving organization and manipulation of data. A vector can be involves human thought, visualization, and/or mathematical calculation. The concept of a vector is abstract and mathematical, and the human brain is thought to represent concepts in a way that can be modeled as vector spaces
Accordingly, at Step 2A, Prong One, the claim is directed to an abstract idea.
Step 2A, Prong Two
Further the claim does not include additional elements that integrate this abstract idea into a practical application. “Deriving vectors” is performed using generic computer components performing their typical functions and does not provide a meaningful technological improvement.
Accordingly, at Step 2A, Prong Two, the additional elements individually or in combination do no integrate the judicial exception into a practical application.
Step 2B
Nothing in the claim adds “significantly more” beyond generic computing.
Accordingly, at Step 2B the additional elements individually or in combination do not amount to significantly more than the judicial exception.
As to claim 5, the limitations “wherein generating the standardized input comprises at least one of normalizing, upsampling, or zero-padding the electrocardiogram recorded from the individual” amounts to generally linking the use of the judicial exception to a particular environment of field of use (See MPEP 2106.05(h)).
As to claim 6,
Step 2A, Prong One
The claim recites in part:
wherein generating the at least on disease risk score comprises:
determining a vector component score for a given disease of the plurality of diseases by projecting the embedding onto a respective disease vector in the lower-dimensional latent space, wherein a magnitude of the vector component score quantifies a relationship between the electrocardiogram recorded from the individual and the given disease;
generating the at least one disease risk score for the given disease based on the vector component score
Under the broadest reasonable interpretation, these limitations are process steps that cover a mathematical relationship, mathematical formula, or algorithm, which is identified as an abstract idea. Specifically, the recited vector component score recites a data processing step involving organization and manipulation of data. Determining a score is a mental process and/or mathematical calculation.
Accordingly, at Step 2A, Prong One, the claim is directed to an abstract idea.
Step 2A, Prong Two
Further the claim does not include additional elements that integrate this abstract idea into a practical application. “Determining a vector component score” can be performed using generic computer components performing their typical functions and does not provide a meaningful technological improvement.
In addition, the recitation of vector component score, embedding, and disease risk score amounts to generally linking the use of the judicial exception to a particular environment of field of use (See MPEP 2106.05(h)). As such, the claim does not integrate the judicial exception into a practical application.
Accordingly, at Step 2A, Prong Two, the additional elements individually or in combination do no integrate the judicial exception into a practical application.
Step 2B
Nothing in the claim adds “significantly more” beyond generic computing.
The recitation of vector component score, embedding, and disease risk score amounts to generally linking the use of the judicial exception to a particular environment of field of use (See MPEP 2106.05(h)).
Accordingly, at Step 2B the additional elements individually or in combination do not amount to significantly more than the judicial exception.
As to claim 7, the limitations “wherein the electrocardiogram recorded from the individual comprises a 12-lead electrocardiogram” are recited at a high-level of generality and amounts to no more than mere instructions to apply the exception using a generic computer component (See MPEP 2106.05(f)).
As to claim 8, the limitations “wherein the electrocardiogram recorded from the individual comprises a single-lead electrocardiogram” are recited at a high-level of generality and amounts to no more than mere instructions to apply the exception using a generic computer component (See MPEP 2106.05(f)).
As to claims 9, the limitations “wherein the at least one disease risk score indicates a likelihood of the individual having or developing at least one disease of the plurality of diseases within a specified time frame” are process steps that cover mental processes including an observation, evaluation, judgment or opinion that could be performed in the human mind or with the aid of pencil and paper. If a claim, under its broadest reasonable interpretation, covers a mental process but for the recitation of generic computer components, then it falls within the “Mental Process” grouping of abstract ideas.
As to claim 9,
Step 2A, Prong One
The claim recites in part:
wherein generating the at least on disease risk score comprises:
wherein the at least one disease risk score indicates a likelihood of the individual having or developing at least one disease of the plurality of diseases within a specified time frame, and wherein the plurality of diseases includes cardia and non-cardiac diseases
As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components. For example, a human can easily determine a disease risk score which is a likelihood of the individual having or developing a disease. Determining likelihood is a core mental process. It involves cognition, which is the mental action or process of acquiring knowledge and understanding through thought, experience, and the senses.
Accordingly, at Step 2A, Prong One, the claim is directed to an abstract idea.
Step 2A, Prong Two
Further the claim does not include additional elements that integrate this abstract idea into a practical application. “Determining the disease risk score” can be performed using generic computer components performing their typical functions and does not provide a meaningful technological improvement.
Accordingly, at Step 2A, Prong Two, the additional elements individually or in combination do no integrate the judicial exception into a practical application.
Step 2B
Nothing in the claim adds “significantly more” beyond generic computing.
Accordingly, at Step 2B the additional elements individually or in combination do not amount to significantly more than the judicial exception.
As to claim 10,
Step 2A, Prong One
The claim does not recite an abstract idea or any other judicial exception and therefore passes Step 2A, Prong of the Alice/Mayo analysis.
Step 2A, Prong Two
The judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements of:
training the deep learning autoencoder using a training sample portion of a model derivation subset of the electrocardiogram training data;
refining the trained deep learning autoencoder using a development sample portion of the model derivation subset of the electrocardiogram training data; and
validating the deep learning autoencoder using both an internal sample portion of the model derivation subset of the electrocardiogram training data and an external test subset of the electrocardiogram training data.
which is recited at a high-level of generality with no detail of the training process and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f))
Accordingly, at Step 2A, Prong Two, the additional elements individually or in combination do no integrate the judicial exception into a practical application.
Step 2B
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. The limitations:
training the deep learning autoencoder using a training sample portion of a model derivation subset of the electrocardiogram training data;
refining the trained deep learning autoencoder using a development sample portion of the model derivation subset of the electrocardiogram training data; and
validating the deep learning autoencoder using both an internal sample portion of the model derivation subset of the electrocardiogram training data and an external test subset of the electrocardiogram training data.
which is recited at a high-level of generality with no detail of the training process and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f))
Accordingly, at Step 2B the additional elements individually or in combination do not amount to significantly more than the judicial exception.
As to claim 11,
Step 2A, Prong One
The claim does not recite an abstract idea or any other judicial exception and therefore passes Step 2A, Prong of the Alice/Mayo analysis.
Step 2A, Prong Two
The judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements of:
generating, by the deep learning autoencoder, a reconstructed electrocardiogram based on an input electrocardiogram from the training sample portion; and
updating weights and biases of the deep learning autoencoder based on a loss between the reconstructed electrocardiogram and the input electrocardiogram from the training sample portion.
these elements are recited at a high-level of generality and amounts to no more than adding the words “apply it” to the judicial exception. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f)). These limitations also amount to extra solution activity because it is a mere nominal or tangential addition to the claim, amounting to mere data output (see MPEP 2106.05(g)).
Accordingly, at Step 2A, Prong Two, the additional elements individually or in combination do no integrate the judicial exception into a practical application.
Step 2B
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. The limitations:
generating, by the deep learning autoencoder, a reconstructed electrocardiogram based on an input electrocardiogram from the training sample portion; and
updating weights and biases of the deep learning autoencoder based on a loss between the reconstructed electrocardiogram and the input electrocardiogram from the training sample portion.
are recited at a high-level of generality and amounts to no more than adding the words “apply it” to the judicial exception. These limitations also amount to extra solution activity because it is a mere nominal or tangential addition to the claim, amounting to mere data output (see MPEP 2106.05(g)). The courts have similarly found limitations directed to displaying a result, recited at a high level of generality, to be well-understood, routine, and conventional. See (MPEP 2106.05(d)(II), "presenting offers and gathering statistics.", “determining an estimated outcome and setting a price”).
Accordingly, at Step 2B the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Claim 21 has similar limitations as claim 1. Therefore, the claim is rejected for the same reasons as above.
Claim 22 has similar limitations as claim 2. Therefore, the claim is rejected for the same reasons as above.
Claim 23 has similar limitations as claim 3. Therefore, the claim is rejected for the same reasons as above.
Claim 24 has similar limitations as claim 4. Therefore, the claim is rejected for the same reasons as above.
Claim 25 has similar limitations as claim 6. Therefore, the claim is rejected for the same reasons as above.
Claim 26 has similar limitations as claim 9. Therefore, the claim is rejected for the same reasons as above.
Claim 27 has similar limitations as claim 10. Therefore, the claim is rejected for the same reasons as above.
Claim 28 has similar limitations as claim 11. Therefore, the claim is rejected for the same reasons as above.
Claim 29 has similar limitations as claim 9. Therefore, the claim is rejected for the same reasons as above.
Response to Arguments
Applicant's arguments filed 11/24/2025 have been fully considered but they are not persuasive.
Claim Rejections - 35 USC § 102 & 103
The newly added limitations overcome the 102 & 103 Rejections as applied. The 102 & 103 Rejections have been withdrawn.
Claim Rejections - 35 USC § 101
The 101 Rejection still has not been overcome. The claims are abstract and the steps in the claims can be completed with a mental process and/or generic computer components. Additionally, the steps in the claims do not describe an improvement of technology in any way.
The applicant argues:
In the rejection of claim 1, the Office alleges that the claim limitations “deriving disease vectors for a plurality of diseases using electrocardiogram training data from both disease-negative individuals and disease-positive individuals for the plurality of diseases” and “generating, by a statistical modeling algorithm of the electrocardiogram analysis module, at least one disease risk score for the individual for the plurality of diseases based on the embedding and the disease vectors” are mental processes but fails to identify how these claim limitations constitute “an observation, evaluation, judgment or opinion.” Although Applicants disagree with the Office’s assertions, these features of claim 1 have been amended to further highlight the subject matter eligibility, and Applicants respectfully submit that the amended claim 1 elements of “deriving, by a deep learning autoencoder of the electrocardiogram analysis module, disease vectors for a plurality of diseases using electrocardiogram training data from both disease-negative individuals and disease- positive individuals for the plurality of diseases, wherein each disease vector corresponds to a respective disease of the plurality of diseases within a lower- dimensional latent space” and “generating, by a statistical modeling algorithm of the electrocardiogram analysis module, at least one disease risk score for the individual for the plurality of diseases based on the embedding and the disease vectors in the lower-dimensional latent space” are impossible to perform in the human mind, much less practically so. The human mind is not equipped to derive disease-specific vectors within a lower-dimensional latent space, nor is it equipped to generate at least one disease risk score based on an embedding encoded from a standardized electrocardiogram and the disease vectors in the lower-dimensional latent space. These are computational processes that are beyond human cognitive capabilities, even when aided by pencil and paper.
The examiner disagrees. The limitations “deriving, by a deep learning autoencoder of
the electrocardiogram analysis module, disease vectors for a plurality of diseases using electrocardiogram training data from both disease-negative individuals and disease- positive individuals for the plurality of diseases, wherein each disease vector corresponds to a respective disease of the plurality of diseases within a lower- dimensional latent space” and “generating, by a statistical modeling algorithm of the electrocardiogram analysis module, at least one disease risk score for the individual for the plurality of diseases based on the embedding and the disease vectors in the lower-dimensional latent space”” under the broadest reasonable interpretation, these limitations are process steps that cover a mathematical relationship, mathematical formula, or algorithm, which is identified as an abstract idea. Specifically, the recited vectors recites a data processing step involving organization and manipulation of data. A vector involves human thought, visualization, and/or mathematical calculation. The concept of a vector is abstract and mathematical, and the human brain is thought to represent concepts in a way that can be modeled as vector spaces. The statistical algorithm is seen as a mere mathematical formula or a fundamental concept rather than a specific application and not demonstrating how the algorithm is not applied to solve a problem in a non-generic way.
Further, a "lower dimensional latent space" is deemed i an abstract idea without a specific, practical application or a technical improvement to a machine or process. Merely applying a mathematical concept or a statistical algorithm, is generally considered an unpatentable abstract idea unless it is integrated into a specific, non-generic technical solution
As per MPEP 2106.04(a)(2)(III)(C)), a claim that requires a computer may still recite a mental process.In evaluating whether a claim that requires a computer recites a mental process, examiners should carefully consider the broadest reasonable interpretation of the claim in light of the specification. For instance, examiners should review the specification to determine if the claimed invention is described as a concept that is performed in the human mind and applicant is merely claiming that concept performed 1) on a generic computer, or 2) in a computer environment, or 3) is merely using a computer as a tool to perform the concept. In these situations, the claim is considered to recite a mental process.
PNG
media_image1.png
18
19
media_image1.png
Greyscale
The applicant argues:
Moreover, the claimed deep learning autoencoder and statistical modeling algorithm are not generic computer components, as alleged by the Office. By way of example, Applicants’ Specification describes a specifically configured deep learning autoencoder that is specifically trained to encode and reconstruct EGCs. See, e.g., Application, [0098]-[0145]. The statistical modeling algorithm is similarly specialized, being specifically configured to analyze “the relationships between the latent space representations and known disease outcomes to build predictive models for various medical conditions” (Application, [0082]). These are not generic computers performing routine functions, but rather specifically configured and trained technical components designed for the particular technical problem of electrocardiogram-based disease profiling.
The examiner disagrees. The examiner respectfully disagrees with the applicant’s position, as the arguments presented rely on limitations that are neither explicitly recited in the claims nor reasonably inferred from them. At no point in the pending claims does the appellant assert, describe, or even suggest the limitation of “The statistical modeling algorithm is similarly specialized, being specifically configured to analyze “the relationships between the latent space representations and known disease outcomes to build predictive models for various medical conditions.” Rather, the appellant appears to have introduced this language as part of the argument, but such a limitation cannot be read into the claims when it is not supported by the actual claim language.
A statistical algorithm becomes “specialized”, not generic, through its assumptions about data (e.g., normality), specific goals (prediction vs. inference), type of output (categorical vs. continuous), and inherent modeling approach (e.g., k-means vs. DBSCAN), which dictate what it models and how it performs, unlike generic algorithms that aim for broad applicability or simply process data without deep structure. The statistical algorithm generating at least one disease risk score is very generic that provides a generalized risk assessment
The applicant argues:
Applicants’ Specification includes numerous examples of practical applications provided by the features recited in claim 1. As an example, Applicants’ Specification describes that “a need exists for a system, method and device that allows systematic evaluation of associations between waveform data, such as ECG- based features, and a broad range of disease phenotypes that uses a deep learning model to encode and reconstruct waveform data, including both 12-lead and single lead (lead 1) ECG data” (Application, [0043]). The approach of claim 1 improves diagnostic technology, for example, by “detect[ing] features in waveform data that could not be detected by a human merely by reading a waveform data printout” and “provide[s] a specific improvement over current methods . . . which do not provide encoding and reconstructing waveform data obtained from a patient to detect and differentiate a wide variety of diseases, including cardiac and non-cardiac disease” (/d.). Accordingly, the claims provide a new technical approach to disease profiling that enables a systematic evaluation of disease risk across a plurality of diseases using electrocardiogram data, which represents a technological advancement in the fields of medical diagnostics and disease monitoring.
The examiner disagrees. The examiner respectfully disagrees with the applicant’s position, as the arguments presented rely on limitations that are neither explicitly recited in the claims nor reasonably inferred from them. At no point in the pending claims does the appellant assert, describe, or even suggest the limitation of “a need exists for a system, method and device that allows systematic evaluation of associations between waveform data, such as ECG- based features, and a broad range of disease phenotypes that uses a deep learning model to encode and reconstruct waveform data, including both 12-lead and single lead (lead 1) ECG data.” Rather, the applicant appears to have introduced this language as part of the argument, but such a limitation cannot be read into the claims when it is not supported by the actual claim language. The claims never even mentions the limitation waveform data and disease phenotypes so it is not clear how these limitations lead to an improvement of technology in the current invention.
The applicant argues:
The Specification further explains that by “[u]sing data derived from large samples, a complex architectural environment informed by disease status was constructed, 11 which each ECG encoding represents a single individual and occupies a unique position in the latent space. Projection of new ECGs from independent individuals can therefore be used to generate likelihoods of disease at scale” (Application, [0318], emphasis added). This approach may have “several potential advantages when compared to training a large number of individual disease-specific classifiers (e.g., the requirement to train and implement only a single model) or a single large multi-task disease classifier (e.g., simpler architecture, lower requirements on model capacity, no dependence on a varying frequency of disease labels)” (/d.). Accordingly, the system of claim 1 provides a specific modeling architecture that enables broad disease risk monitoring at scale in an improved manner compared to alternative strategies.
The examiner disagrees. The examiner respectfully disagrees with the applicant’s
position, as the arguments presented rely on limitations that are neither explicitly recited in the claims nor reasonably inferred from them. At no point in the pending claims does the appellant assert, describe, or even suggest the limitation of ““[u]sing data derived from large samples, a complex architectural environment informed by disease status was constructed, 11 which each ECG encoding represents a single individual and occupies a unique position in the latent space. Projection of new ECGs from independent individuals can therefore be used to generate likelihoods of disease at scale.” Rather, the applicant appears to have introduced this language as part of the argument, but such a limitation cannot be read into the claims when it is not supported by the actual claim language. At no point does the claims mention the size of the sample data being processed or exactly what limitations are considered to be “a complex architectural environment.”
The applicant argues:
Furthermore, with respect to Prong Two, the Office alleges that the limitation “encoding, by a deep learning autoencoder of the electrocardiogram analysis module, the standardized input into an embedding, the embedding being a lower- dimensional latent space representation of features extracted from the standardized input” is “recited at a high-level of generality and amounts to no more than adding the words ‘apply it’ to the judicial exception” and is an “extra solution activity because it is a mere nominal or tangential addition to the claim, amounting to mere data output” (Office Action, pp. 3 and 4). Applicants respectfully disagree. As a first FIG 15 BI-11232-US PATENTS Yast matter, this limitation is not recited at a high level of generality but rather specifies a particular technical process of using a deep learning autoencoder to encode electrocardiogram data into “an embedding” that, as amended, is “a representation of features extracted from the standardized input in the lower-dimensional latent space” (e.g., the same lower-dimensional latent space as the disease vectors in the “deriving” limitation). This is not a generic “apply it” instruction, but rather a specific type of data transformation on a specific type of data (e.g., a standardized input generated from an electrocardiogram) using a particular type of neural network architecture (e.g., a deep learning autoencoder). Additionally, claim 1 as amended requires “generating, by a statistical modeling algorithm of the electrocardiogram analysis module, at least one disease risk score for the individual for the plurality of diseases based on the embedding and the disease vectors in the lower-dimensional latent space.” Accordingly, the “encoding” limitation is not tangential to the claim or mere data output, but converts information from an electrocardiogram into a form that is usable by the statistical modeling algorithm to generate the at least one risk score.
The examiner disagrees. The limitations “encoding, by the deep learning autoencoder of the electrocardiogram analysis module, the standardized input into an embedding, the embedding being a representation of features extracted from the standardized input in the lower-dimensional latent space” are recited at a high-level of generality and amounts to no more than adding the words “apply it” to the judicial exception. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f)). These limitations also amount to extra solution activity because it is a mere nominal or tangential addition to the claim, amounting to mere data output (see MPEP 2106.05(g)).
The applicant argues:
Applicants submit that even assuming arguendo that claim | is directed to a judicial exception, which it is not, claim 1 remains patent eligible because the recited features include an inventive concept.
In the rejection of claim 1 with respect to Step 2B, the Office uses similar reasoning as discussed above with respect to Step 2A, e.g., alleging the limitations are high-level, generic, and constitute field of use limitations (Office Action, pp. 5 and 6). Accordingly, Applicants disagree with the Office’s assertions at Step 2B for at least the same reasons discussed above with respect to Step 2A, Prong Two. Additionally, with regard to the previously presented claim 1 limitation of “encoding, by a deep learning autoencoder of the electrocardiogram analysis module, the standardized input into an embedding, the embedding being a lower- dimensional latent space representation of features extracted from the standardized input,” the Office further alleges that “[t]he courts have similarly found limitations directed to displaying a result, recited at a high level of generality, to be well- understood, routine, and conventional. See (MPEP 2106.05(d)(ID), ‘presenting offers and gathering statistics’, “determining an estimated outcome and setting a price’) (Office Action, p. 6).
Applicants disagree with the Office’s interpretation of the “encoding” limitation. As a first matter, Applicants submit that “encoding, by a deep learning autoencoder of the electrocardiogram analysis module, the standardized input into an embedding, the embedding being a _ lower-dimensional latent space representation of features extracted from the standardized input” is not “directed to displaying a result,” as alleged by the Office. Additionally, Applicants respectfully request clarification regarding how the cited examples of presenting offers and gathering statistics or determining estimated outcomes and setting prices relate to the claimed limitation. The Office provides no explanation for how “encoding, by a deep learning autoencoder of the electrocardiogram analysis module, the standardized input into an embedding, the embedding being a lower-dimensional latent space representation of features extracted from the standardized input” corresponds to these activities.
Moreover, Applicants submit that claim 1 recites a specific combination of technical features involving “deriving, by a deep learning autoencoder of the electrocardiogram analysis module, disease vectors for a plurality of diseases using electrocardiogram training data from both disease-negative individuals and disease- positive individuals for the plurality of diseases, wherein each disease vector corresponds to a respective disease of the plurality of diseases within a lower- dimensional latent space,” “generating, via a data preprocessor of the electrocardiogram analysis module, a standardized input from an electrocardiogram recorded from an individual,” “encoding, by the deep learning autoencoder of the electrocardiogram analysis module, the standardized input into an embedding, the embedding being a representation of features extracted from the standardized input in the lower-dimensional latent space,” and “generating, by a statistical modeling algorithm of the electrocardiogram analysis module, at least one disease risk score for the individual for the plurality of diseases based on the embedding and the disease vectors in the lower-dimensional latent space.” This combination represents a non-conventional approach to disease profiling that goes beyond routine data processing. The specific use of a deep learning autoencoder to create an embedding as a representation of electrocardiogram data in latent space, combined with the derivation of disease-specific vectors in the latent space for a plurality of diseases and the generation of at least one disease risk score based on the embedding and the disease-specific vectors, represents a technical advancement that is significantly more than conventional computer implementation of known processes. Accordingly, for at least these additional reasons, claim 1 is not directed to an abstract idea and is patent eligible under Step 2B, and Applicants respectfully request that the § 101 rejection of claims 1-11 be withdrawn.
The examiner disagrees. The claims address problems in electrocardiogram-based disease profiling, but we find no evidence that any nongeneric or unconventional computing or database technology would be needed in order to perform the claimed invention.
Moreover, while the claims may recite a specific way for deriving and encoding, narrowing the recited abstract idea or limiting it to a particular field of use in this way does not change our overall understanding of the claims and, thus, does not render the claims non-abstract. See Rev. Guid., 84 Fed. Reg. at 55 n.32; see also e.g., Ultramercial, Inc. v. Hulu,LLC, 772 F.3d 709, 716 (Fed. Cir. 2014) (determining that even though “some of the eleven steps were not previously employed in this art,” that was “not enough—standing alone—to confer patent eligibility upon the claims at issue.”). Nor is the fact that the data being modified is of a technological advance. Rather, it merely reflects the manipulation or reorganization of data, which fails to transform an otherwise patent-ineligible concept into an eligible one. See CyberSource Corp. v. Retail Decisions, Inc., 654 F.3d 1366, 1375 (Fed. Cir. 2011)).
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BRANDON S COLE whose telephone number is (571)270-5075. The examiner can normally be reached Mon - Fri 7:30pm - 5pm EST (Alternate Friday's 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, Omar Fernandez can be reached at 571-272-2589. 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.
/BRANDON S COLE/ Primary Examiner, Art Unit 2128