DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Amendment
The amendments filed August 5, 2025 have been entered. Claims 1 - 21 are pending. Applicant’s amendments have overcome each and every claim interpretation under 112(f) previously applied in the office action dated August 5, 2025.
Claim Objections
Applicant is advised that should claim 1 be found allowable, claim 21 will be objected to under 37 CFR 1.75 as being a substantial duplicate thereof. Likewise, Applicant is advised that should claim 21 be found allowable, claim 1 will be objected to under 37 CFR 1.75 as being a substantial duplicate thereof. When two claims in an application are duplicates or else are so close in content that they both cover the same thing, despite a slight difference in wording, it is proper after allowing one claim to object to the other as being a substantial duplicate of the allowed claim. See MPEP § 608.01(m). Claim 1 recites an apparatus having a memory storing program code which is operated by a processor, which is not substantially different than the recited computer readable medium storing a computer program executed by a processor of Claim 21.
Claim 21 is objected to because of the following informalities: There appears to be a typographical error such that there is an “a” missing in the term “A non-transitory computer readable storage medium storing computer program” between “storing” and “computer”. Addition of the “a” would yield “A non-transitory computer readable storage medium storing a computer program”. Appropriate correction is required.
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 - 21 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Regarding Claims 1 and 21, the claim recites an apparatus, which is one of the statutory categories of invention (Step 1). The claim is then analyzed to determine whether it is directed to any judicial exception (Step 2A, Prong 1).
Regarding Claim 11, the claim recites "an act or step, or series of acts or steps" and is therefore a process, which is a statutory category of invention (Step 1). The claims are then analyzed to determine whether they are directed to any judicial exception (Step 2A, Prong 1).
Each of Claims 1 – 21 has been analyzed to determine whether it is directed to any judicial exceptions.
Step 2A, Prong 1
Each of Claims 1 – 21 recites at least one step or instruction for observations, evaluations, judgments, and opinions, which are grouped as a mental process under the 2019 PEG. The claimed invention involves making observations, evaluations, judgments, and opinions, which are concepts performed in the human mind under the 2019 PEG.
Accordingly, each of Claims 1 - 21 recites an abstract idea.
Specifically, Claims 1 – 21 recite (underlined are observations, judgements, evaluations, or opinions, which are grouped as a mental process under the 2019 PEG) (additional elements bolded, see Step 2A, prong 2);
Claim
An apparatus for predicting a cardiovascular risk factor, the apparatus comprising:
at least one memory configured to store program code; and
at least one processor configured to read the program code and operate as instructed by the program code to:
produce, from a fundus image of a user, an initial prediction value, which is an initial predicted value of a target cardiovascular risk factor, the target cardiovascular risk factor being a factor related to inducing a cardiovascular disease;
produce, from the fundus image of the user, a prediction value, which is a predicted value of each of at least one related cardiovascular risk factor, the at least one related cardiovascular risk factor being a factor related to the target cardiovascular risk factor; and
produce a final prediction value as a final predicted value of the target cardiovascular risk factor, based on the initial prediction value of the target cardiovascular risk factor and the prediction value of each of the at least one related cardiovascular risk factor,
wherein the final prediction value of the target cardiovascular risk factor is used for predicting a cardiovascular disease of the user without separate electronic health record (EHR) information of the user.
Claim 11
A method for predicting a cardiovascular risk factor, the method comprising:
producing, from a fundus image of a user, an initial prediction value, which is an initial predicted value of a target cardiovascular risk factor, the target cardiovascular risk factor being a factor related to inducing a cardiovascular disease;
producing, from the fundus image of the user, a prediction value, which is a predicted value of each of at least one related cardiovascular risk factor, the at least one related cardiovascular risk factor being a factor related to the target cardiovascular risk factor; and
producing a final prediction value as a final predicted value of the target cardiovascular risk factor, based on the initial prediction value of the target cardiovascular risk factor and the prediction value of each of the at least one related cardiovascular risk factors
wherein the final prediction value of the target cardiovascular risk factor is used for predicting a cardiovascular disease of the user without separate electronic health record (EHR) information of the user.
Claim 21
A non-transitory computer- readable storage medium storing computer program, the computer program comprising at least one instruction,
wherein, when executed by a computing device having at least one processor, the computer program is configured for the computing device to:
produce, from a fundus image of a user, an initial prediction value, which is an initial predicted value of a target cardiovascular risk factor, the target cardiovascular risk factor being a factor related to inducing a cardiovascular disease
produce, from the fundus image of the user, a prediction value, which is a predicted value of each of at least one related cardiovascular risk factor, the at least one related cardiovascular risk factor being a factor related to the target cardiovascular risk factor; and
produce a final prediction value, as a final predicted value of the target cardiovascular risk factor, based on the initial prediction value of the target cardiovascular risk factor and the prediction value of each of the at least one related cardiovascular risk factors
wherein the final prediction value of the target cardiovascular risk factor is used for predicting a cardiovascular disease of the user without separate electronic health record (EHR) information of the user.
(observation, judgment or evaluation, which is grouped as a mental process under the 2019 PEG);
These underlined limitations describe a mathematical calculation and/or a mental process, as a skilled practitioner is capable of performing the recited limitations and making a mental assessment thereafter. Examiner notes that nothing from the claims suggests that the limitations cannot be practically performed by a medical, biomedical or engineering professional with the aid of a pen and paper; their knowledge gained from education, background, or experience; or by using a generic computer as a tool to perform mathematical calculations and/or mental process steps in real time. Examiner additionally notes that nothing from the claims suggests and undue level of complexity that the mathematical calculations and/or the mental process steps cannot be practically performed by a human with the aid of a pen and paper, or using a generic computer as a tool to perform mathematical calculations and/or mental process steps. For example, in Independent Claims 1, 11, and 21, these limitations include:
Judgment (as in diagnosis) to produce an initial prediction value for a target cardiovascular risk factor from observation of a fundus image;
Judgment (as in diagnosis) to produce a prediction value for each of at least one related cardiovascular risk factor from observation of the fundus image
Observation and Judgment (as in diagnosis) to produce a final prediction value for the target cardiovascular risk factor, based on the Judgment of the initial prediction value for the target cardiovascular risk factor and the prediction value for each of the at least one related cardiovascular risk factor
Observation and Judgment (as in diagnosis) to predict a cardiovascular disease of the user without separate electronic health record (EHR) information of the user using the final prediction value of the target cardiovascular risk factor
all of which are grouped as mental processes under the 2019 PEG.
Similarly, Dependent Claims 2, 4, 6, 12, 14, and 16 include the following abstract limitations, in addition to the aforementioned limitations in Independent Claims 1, 11, and 21 (underlined observation, judgment or evaluation, which is grouped as a mental process under the 2019 PEG):
produce the initial prediction value using a target cardiovascular risk factor prediction model and an actually measured value for the target cardiovascular risk factor corresponding to each of the plurality of pre-collected fundus images.
Observation and judgment (as in diagnosis) to produce the initial prediction value using a target cardiovascular risk factor prediction model (a person’s education, background, and experience for diagnosis steps) and observation and judgment of an actually measured value for the target cardiovascular risk factor corresponding to each of the plurality of pre-collected fundus images.
to produce the prediction value using a related cardiovascular risk factor prediction model, and an actually measured value for each of the at least one related cardiovascular risk factor corresponding to each of the plurality of pre-collected fundus images.
Observation and judgment (as in diagnosis) to produce the prediction value using a related cardiovascular risk factor prediction model (a person’s education, background, and experience for diagnosis steps) and observation and judgment of an actually measured value for each of the at least one related cardiovascular risk factor corresponding to each of the plurality of pre-collected fundus images.
produce the final prediction value using a prediction result binding model, a prediction value for each of the at least one related cardiovascular risk factor, and an actually measured value for the target cardiovascular risk factor, with regard to each of a plurality of pre-collected fundus images.
Observation and judgment (as in diagnosis) to produce the final prediction value using a prediction result binding model (a person’s education, background, and experience for diagnosis steps) and observation and judgment of a prediction value for each of the at least one related cardiovascular risk factor, and observation and judgment of an actually measured value for the target cardiovascular risk factor, with regard to observation and judgment of each of a plurality of pre-collected fundus images.
As claimed, the aforementioned limitations are mental processes that would be performed by a medical, biomedical or engineering professional using their education, background, and experience, and a pen and paper.
Accordingly, as indicated above, each of the above-identified claims recite an abstract idea.
Step 2A, Prong 2
The above-identified abstract ideas in Independent Claims 1, 11, and 21 (and their dependent Claims 2 – 10, and 12 - 20) are not integrated into a practical application under 2019 PEG because the additional elements (identified above in Claims 1 - 21), either alone or in combination, generally link the use of the above-identified abstract ideas to a particular technological environment or field of use. More specifically, within the independent Claims 1 and 21 and the dependent claims 2 - 10, the additional elements of:
“non-transitory computer- readable storage medium”
“at least one memory”
“computer program”
“computing device”
“processor”; “at least one processor”
Additional elements recited include a “non-transitory computer- readable storage medium” to store, and “at least one memory” to store, a “computing device” to execute, and a “processor”/”at least one processor” to read and operate. These components are recited at a high level of generality. These generic hardware component limitations for the “non-transitory computer- readable storage medium”, “at least one memory”, “computer program”, “computing device”, “processor”, and “at least one processor” are no more than mere instructions to apply the exception using a generic computer component. As such, these additional elements do not impose any meaningful limits on practicing the abstract idea.
Additional elements from independent Claims 1 and 21 include pre-solution activity limitations, such as:
at least one memory configured to store program code; and
at least one processor configured to read the program code and operate as instructed by the program code to:
A non-transitory computer- readable storage medium storing computer a program, the computer program comprising at least one instruction,
wherein, when executed by a computing device having at least one processor, the computer program is configured for the computing device to:
Additional elements from dependent Claims 2 – 10, and 12 - 20 include extra-solution activity limitations, such as:
pre-trained using a plurality of pre-collected fundus images
wherein the target cardiovascular risk factor prediction model is a convolutional neural network (CNN)-based prediction model.
wherein the related cardiovascular risk factor prediction model is a convolutional neural network (CNN)-based prediction model.
pre-trained using an initial prediction value for the target cardiovascular risk factor,
wherein the prediction result binding model is a prediction model based on one of a regression analysis or an artificial neural network.
wherein the target cardiovascular risk factor is a coronary artery calcification score (CACS).
wherein the target cardiovascular risk factor is a carotid artery intima thickness.
wherein the at least one related cardiovascular risk factor comprises at least one of age, sex, smoking, a glycosylated hemoglobin level, blood pressure, a pulse wave, blood sugar level, cholesterol level, creatinine level, insulin level, or intraocular pressure.
These pre-solution measurement elements are insignificant extra-solution activity, setting up the parameters of the system, and serve as data-gathering for the subsequent steps.
The “non-transitory computer- readable storage medium”, “at least one memory”, “computer program”, “computing device”, “processor”, and “at least one processor” as recited in independent Claims 1 and 21 and their dependent claims are generically recited computer and hardware elements which does not improve the functioning of a computer, or any other technology or technical field. Nor do these above-identified additional elements serve to apply the above-identified abstract idea with, or by use of, a particular machine, effect a transformation or apply or use the above-identified abstract idea in some other meaningful way beyond generally linking the use thereof to a particular technological environment, such that the claim as a whole is more than a drafting effort designed to monopolize the exception. Furthermore, the above-identified additional elements do not add a meaningful limitation to the abstract idea because they amount to simply implementing the abstract idea on a computer. For at least these reasons, the abstract ideas identified above in independent Claims 1, 11, and 21 (and their dependent claims) are not integrated into a practical application under 2019 PEG.
Moreover, the above-identified abstract idea is not integrated into a practical application under 2019 PEG because the claimed method and system merely implements the above-identified abstract idea (e.g., mental process and certain method of organizing human activity) using rules (e.g., computer instructions) executed by a computer processor as claimed. In other words, these claims are merely directed to an abstract idea with additional generic computer elements which do not add a meaningful limitation to the abstract idea because they amount to simply implementing the abstract idea on a computer. Additionally, Applicant’s specification does not include any discussion of how the claimed invention provides a technical improvement realized by these claims over the prior art or any explanation of a technical problem having an unconventional technical solution that is expressed in these claims. That is, like Affinity Labs of Tex. v. DirecTV, LLC, the specification fails to provide sufficient details regarding the manner in which the claimed invention accomplishes any technical improvement or solution. Thus, for these additional reasons, the abstract idea identified above in in independent Claims 1, 11, and 21 (and their dependent claims) is not integrated into a practical application under the 2019 PEG.
Accordingly, independent Claim 1, 11, and 21 (and their dependent claims) are each directed to an abstract idea under 2019 PEG.
Step 2B –
None of Claims 1 - 21 include additional elements that are sufficient to amount to significantly more than the abstract idea for at least the following reasons.
These claims require the additional elements of “non-transitory computer- readable storage medium”, “at least one memory”, “computer program”, “computing device”, “processor”, and “at least one processor” as recited in independent Claims 1 and 21 and their dependent claims.
The additional elements of the “non-transitory computer- readable storage medium”, “at least one memory”, “computer program”, “computing device”, “processor”, and “at least one processor” in claims 1 - 21, as discussed with respect to Step 2A Prong Two, amounts to no more than mere instructions to apply the exception using generic computer and hardware components. The same analysis applies here in 2B, i.e., mere instructions to apply an exception using a generic computer component cannot integrate a judicial exception into a practical application at Step 2A or provide an inventive concept in Step 2B.
The above-identified additional elements are generically claimed computer components which enable the above-identified abstract idea(s) to be conducted by performing the basic functions of automating mental tasks. The courts have recognized such computer functions as well understood, routine, and conventional functions when claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity. See, Versata Dev. Group, Inc. v. SAP Am., Inc. , 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015); and OIP Techs., 788 F.3d at 1363, 115 USPQ2d at 1092-93.
Per applicant’s specification, the “non-transitory computer-readable storage medium” is described generically as a “computer-readable recording medium” in [0033], including “The computer-readable recording medium may include a program instruction, a local data file, a local data structure, or the like, alone or in combination. The medium may be specially designed and configured for the present disclosure, or may be commonly used in the field of computer software.” There is nothing particular to the structure of the “non-transitory computer-readable storage medium” that deems it more than well-understood, routine, or conventional. The “non-transitory computer-readable storage medium”” is shown as “computer-readable storage medium” 16 generic box element in Figure 3.
Per applicant’s specification, the “at least one memory” is described generically at [0033] and [0068] as “the computer-readable storage medium 16 may be a memory (a volatile memory such as a random access memory, a non-volatile memory, or a suitable combination thereof), one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, other forms of storage medium accessed by the computing device 12 and capable of storing desired information, or a suitable combination thereof.” The “memory” is shown as “computer-readable storage medium 16” generic box element in Figure 3.
Per applicant’s specification, the “computer program” is described generically in [0033] as “a program for performing methods described in this specification on a computer” and “Examples of the program may include a high-level language code that may be executed by a computer using an interpreter or the like, as well as a machine language code such as those produced by a compiler.” The “computer program” is shown as generic box element “Program 20” in Figure 3.
Per applicant’s specification, the “computing device” is described generically in [0066] – [0070] as “computing device 12” including generic “processor” and “computer-readable storage medium”, where those individual generic components will be discussed further below, as well as a “communication bus”. There is nothing particular to the structure of the “computing device” that deems it more than well-understood, routine, or conventional. The “computing device” is shown as “computing device” 12 generic box element in Figure 3.
Per applicant’s specification, the “processor” and “at least one processor” is described generically in [0066] to “execute programs…” There is nothing particular to the structure of the “processor” that deems it more than well-understood, routine, or conventional. The “processor” is shown as “processor” 14 black-box generic rectangle in Figure 3.
Accordingly, in light of Applicant’s specification, the claimed terms “non-transitory computer- readable storage medium”, “at least one memory”, “computer program”, “computing device”, “processor”, and “at least one processor” are reasonably construed as a generic computing device or hardware. Like SAP America vs Investpic, LLC (Federal Circuit 2018), it is clear, from the claims themselves and the specification, that these limitations require no improved computer resources, just already available computers, with their already available basic functions, to use as tools in executing the claimed process.
Furthermore, Applicant’s specification does not describe any special programming or algorithms required for the “non-transitory computer- readable storage medium”, “at least one memory”, “computer program”, “computing device”, “processor”, and “at least one processor” This lack of disclosure is acceptable under 35 U.S.C. §112(a) since this hardware performs non-specialized functions known by those of ordinary skill in the computer arts. By omitting any specialized programming or algorithms, Applicant's specification essentially admits that this hardware is conventional and performs well understood, routine and conventional activities in the computer industry or arts. In other words, Applicant’s specification demonstrates the well-understood, routine, conventional nature of the above-identified additional elements because it describes these additional elements in a manner that indicates that the additional elements are sufficiently well-known that the specification does not need to describe the particulars of such additional elements to satisfy 35 U.S.C. § 112(a) (see Berkheimer memo from April 19, 2018, (III)(A)(1) on page 3). Adding hardware that performs “‘well understood, routine, conventional activit[ies]’ previously known to the industry” will not make claims patent-eligible (TLI Communications).
The recitation of the above-identified additional limitations in Claims 1 – 21 amounts to mere instructions to implement the abstract idea on a computer. Simply using a computer or other machinery in its ordinary capacity for economic or other tasks (e.g., to receive, store, or transmit data) or simply adding a general-purpose computer or computer components after the fact to an abstract idea (e.g., a fundamental economic practice or mathematical equation) does not provide significantly more. See Affinity Labs v. DirecTV, 838 F.3d 1253, 1262, 120 USPQ2d 1201, 1207 (Fed. Cir. 2016) (cellular telephone); and TLI Communications LLC v. AV Auto, LLC, 823 F.3d 607, 613, 118 USPQ2d 1744, 1748 (Fed. Cir. 2016) (computer server and telephone unit). Moreover, implementing an abstract idea on a generic computer, does not add significantly more, similar to how the recitation of the computer in the claim in Alice amounted to mere instructions to apply the abstract idea of intermediated settlement on a generic computer.
A claim that purports to improve computer capabilities or to improve an existing technology may provide significantly more. McRO, Inc. v. Bandai Namco Games Am. Inc., 837 F.3d 1299, 1314-15, 120 USPQ2d 1091, 1101-02 (Fed. Cir. 2016); and Enfish, LLC v. Microsoft Corp., 822 F.3d 1327, 1335-36, 118 USPQ2d 1684, 1688-89 (Fed. Cir. 2016). However, a technical explanation as to how to implement the invention should be present in the specification for any assertion that the invention improves upon conventional functioning of a computer, or upon conventional technology or technological processes. That is, the disclosure must provide sufficient details such that one of ordinary skill in the art would recognize the claimed invention as providing an improvement. Here, Applicant’s specification does not include any discussion of how the claimed invention provides a technical improvement realized by these claims over the prior art or any explanation of a technical problem having an unconventional technical solution that is expressed in these claims. Instead, as in Affinity Labs of Tex. v. DirecTV, LLC 838 F.3d 1253, 1263-64, 120 USPQ2d 1201, 1207-08 (Fed. Cir. 2016), the specification fails to provide sufficient details regarding the manner in which the claimed invention accomplishes any technical improvement or solution.
For at least the above reasons, the apparatuses and method of Claims 1 – 21 are directed to applying an abstract idea as identified above on a general-purpose computer without (i) improving the performance of the computer itself, or (ii) providing a technical solution to a problem in a technical field. None of Claims 1 - 21 provides meaningful limitations to transform the abstract idea into a patent eligible application of the abstract idea such that these claims amount to significantly more than the abstract idea itself.
Taking the additional elements individually and in combination, the additional elements do not provide significantly more. Specifically, when viewed individually, the above-identified additional elements for Step 2A Prong 2 in independent Claims 1, 11, and 21 (and their dependent claims) do not add significantly more because they are simply an attempt to limit the abstract idea to a particular technological environment. That is, neither the general computer elements nor any other additional element adds meaningful limitations to the abstract idea because these additional elements represent insignificant extra-solution activity. When viewed as a combination, these above-identified additional elements simply instruct the practitioner to implement the claimed functions with well-understood, routine and conventional activity specified at a high level of generality in a particular technological environment. As such, there is no inventive concept sufficient to transform the claimed subject matter into a patent-eligible application. When viewed as whole, the above-identified additional elements do not provide meaningful limitations to transform the abstract idea into a patent eligible application of the abstract idea such that the claims amount to significantly more than the abstract idea itself. Thus, Claims 1 – 21 merely apply an abstract idea to a computer and do not (i) improve the performance of the computer itself (as in Bascom and Enfish), or (ii) provide a technical solution to a problem in a technical field (as in DDR).
Therefore, none of the Claims 1 - 21 amounts to significantly more than the abstract idea itself. Accordingly, Claims 1 - 21 are not patent eligible and rejected under 35 U.S.C. 101.
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)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1 – 7, 10 – 17, and 20 - 21 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Poplin et. al., “Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning”, hereinafter Poplin.
Regarding Claims 1, 11, and 21, Poplin discloses
Claim 1: An apparatus for predicting a cardiovascular risk factor ([Bolded Abstract paragraph]), the apparatus comprising:
at least one memory ([Page 6, Right Column, “Code availability” section] “computing infrastructure…computers”; [Page 9, Top of Page, “Software” section”] “TensorFlow and python scripts”)(Examiner notes that Python and Tensorflow software runs on computers, which include memory to store and use the software libraries.) configured to store program code ([Page 6, Right Column, “Code availability” section] “standard model libraries and scripts…Custom code…”); and
at least one processor ([Page 6, Right Column, “Code availability” section] “computing infrastructure…computers”; [Page 9, Top of Page, “Software” section”] “TensorFlow and python scripts”)(Examiner notes that Python and Tensorflow software runs on computers, which include one or more processors to use the software.) configured to read the program code and operate as instructed by the program code ([Page 6, Right Column, “Code availability” section] “Custom code…data input/output and parallelization…”) to:
Claim 11: A method for predicting a cardiovascular risk factor ([Bolded Abstract paragraph]), the method comprising:
Claim 21: A non-transitory computer-readable storage medium ([Page 6, Right Column “Code availability” Section] “our computing infrastructure…computers”; [Page 9, Top of Page, “Software” section”] “TensorFlow and python scripts”)(Examiner notes that Python and Tensorflow software runs on computers, which include non-transitory computer-readable storage medium to store and use the software.) storing a computer program ([Page 9, Top of Page, “Software” section”] “TensorFlow and python scripts”), the computer program comprising at least one instruction ([Page 9, Top of Page, “Software” section”] “TensorFlow and python scripts”)(Examiner notes that python scripts are instructions within a computer program.),
wherein, when executed by a computing device having at least one processor ([Page 6, Right Column, “Code availability” section] “computing infrastructure…computers”; [Page 9, Top of Page, “Software” section”] “TensorFlow and python scripts”)(Examiner notes that Python and Tensorflow software runs on computers, which include one or more processors to use the software.) the computer program ([Page 9, Top of Page, “Software” section”] “TensorFlow and python scripts”), is configured for the computing device ([[Page 6, Right Column, “Code availability” section] “computing infrastructure”), to:
For the remainder of Claims 1, 11, and 21, Poplin discloses
produce, from a fundus image of a user [Page 1, Right Column, “Results” Section] “deep-learning models using retinal fundus images…patients from the UK Biobank”), an initial prediction value ([Page 4] Table 5: Predicting five-year MACE in the UK Biobank validation dataset using various input variables, “Algorithm only”, AUC 0.70 (0.65, 0.75); [Page 3, Right Column] “predict the onset of major adverse cardiovascular events (MACE) within five years)(Examiner notes that the prediction using the “Algorithm” alone is an initial prediction value that has not been further fine-tuned into a final prediction by including additional predictions. Further, the prediction value is a binary value whether or not a MACE will occur within 5 years, with “AUC” being a prediction value associated with the efficacy of the model at predicting.), which is an initial predicted value of a target cardiovascular risk factor ([Page 4] Table 5: “MACE”; [Page 3, Right Column, 1st First Paragraph] “trained a model to predict the onset of major adverse cardiovascular events (MACE) within five years”; [Page 3, Right Column] “predict the onset of major adverse cardiovascular events (MACE) within five years.”)(Examiner again notes that the prediction using the “Algorithm” alone is an initial prediction value that has not been further fine-tuned into a final prediction by including additional predictions.), the target cardiovascular risk factor being a factor related to inducing a cardiovascular disease ([Page 3, Right Column, 1st First Paragraph] “predict the onset of major adverse cardiovascular events (MACE)”)(Examiner notes that the MACE prediction is giving a probability score to the occurrence of major adverse cardiovascular event (such as a myocardial infarction) within five years, which are associated with inducing a cardiovascular disease.)
produce, from the fundus image of the user ([Page 2, Left Column, 1st full paragraph] “predict a variety of cardiovascular risk factors from retinal fundus images”; Tables 2 and 3; [Page 1, Right Column, “Results” Section] “deep-learning models using retinal fundus images…patients from the UK Biobank”), a prediction value ([Page 2, Left Column, 1st Full Paragraph] “..cardiovascular risk factors”; [Page 2, Right Column, 1st Full Paragraph] “age, SBP, diastolic blood pressure (DBP), and BMI), which is a predicted value of each of at least one related cardiovascular risk factor ([Page 2, Left Column, 1st Full Paragraph] “predict a variety of cardiovascular risk factors from retinal fundus images…age”; [Page 2, Right Column, 1st Full Paragraph] “algorithm…age, SBP, diastolic blood pressure (DBP), and BMI), the at least one related cardiovascular risk factor being a factor related to the target cardiovascular risk factor ([Page 2, Right Column, 1st Full Paragraph] “algorithm…age, SBP, diastolic blood pressure (DBP), and BMI; [Page 4, Left Column, Top] “…the combination of these risk factors was better at predicting MACE than individual risk factors alone”; Table 5: Predicting five-year MACE in the UK Biobank validation dataset using various input variables”, Algorithm only AUC = 0.70, Algorithm + age + SBP + BMI + gender + current smoker AUC = 0.73)(Examiner notes that the predicted cardiovascular risk factors of age, SBP, BMI, gender, and smoking status are related to the risk of developing “cardiovascular event”, particularly since they increased the accuracy of prediction for the model vs predicting the MACE score in the absence of these factors (AUC 0.73 is better than 0.70).); and produce a final prediction value ([Page 4] Table 5: Predicting five-year MACE in the UK Biobank validation dataset using various input variables, “Algorithm + age + SBP + BMI + gender + current smoker”, AUC 0.73 (0.69, 0.77);(Examiner notes that the prediction value using the “Algorithm” with the predictions of age, SBP, BBI, gender, and smoking has been fine-tuned into a final prediction by including the additional predictions. The prediction value is a binary value whether or not a MACE will occur within 5 years, with “AUC” being a prediction value associated with the efficacy of the model at predicting.)), as a final predicted value of the target cardiovascular risk factor ([Page 4] Table 5: Predicting five-year MACE in the UK Biobank validation dataset using various input variables, “Algorithm + age + SBP + BMI + gender + current smoker”, AUC 0.73 (0.69, 0.77))(Examiner again notes that the prediction value using the “Algorithm” with the predictions of age, SBP, BBI, gender, and smoking has been fine-tuned into a final prediction by including the additional predictions. the prediction value is a binary value whether or not a MACE will occur within 5 years, with “AUC” being a prediction value associated with the efficacy of the model at predicting.)), based on the initial prediction value of the target cardiovascular risk factor ([Page 4] Table 5: Predicting five-year MACE in the UK Biobank validation dataset using various input variables, “Algorithm only”)(Examiner again notes that the prediction using the “Algorithm” alone is an initial prediction value due to not being tuned by additional predictions.), and the prediction value of each of the at least one related cardiovascular risk factor (([Page 4] Table 5: Predicting five-year MACE in the UK Biobank validation dataset using various input variables, “Algorithm + age + SBP + BMI + gender + current smoker”)
wherein the final prediction value of the target cardiovascular risk factor is used for predicting a cardiovascular disease of the user ([Page 3, Right Column, 1st Full Paragraph] “several cardiovascular risk factors…correlated directly to cardiovascular events…predict the onset of major adverse cardiovascular events (MACE) within five years.”)(Examiner notes that the MACE prediction is giving a probability score to the occurrence of major adverse cardiovascular event (such as a myocardial infarction) within five years, which are associated with inducing a cardiovascular disease.) without separate electronic health record (EHR) information of the user ([Page 3, Right Column, 1st Full Paragraph] “retinal images alone were sufficient to predict several cardiovascular risk factors to varying degrees…the images could be correlated directly with cardiovascular events…(MACE)”).
Regarding Claims 2 and 12, Poplin discloses The apparatus of claim 1 and The method of claim 11, respectively. For the remainder of Claims 2 and 12, Poplin discloses wherein the producing the initial prediction value comprises producing the initial prediction value ([Page 4] Table 5: Predicting five-year MACE in the UK Biobank validation dataset using various input variables, “Algorithm only”, AUC 0.70 (0.65, 0.75); [Page 3, Right Column] “predict the onset of major adverse cardiovascular events (MACE) within five years)(Examiner notes that the prediction using the “Algorithm” alone is an initial prediction value that has not been further fine-tuned into a final prediction by including additional predictions. Further, the prediction value is a binary value whether or not a MACE will occur within 5 years, with “AUC” being a prediction value associated with the efficacy of the model at predicting.) using a target cardiovascular risk factor prediction model ([Page 6, Left Column, 2nd Full Paragraph] including “third classification network for predicting MACE”), pre-trained using a plurality of pre-collected fundus images and an actually measured value of the target cardiovascular risk factor corresponding to each of the plurality of pre-collected fundus images ([Page 5, Right Column; Bottom; “Model development” section] - [Page 6, Left Column, Top] “fundus image…”, “for each image, the prediction given by the model is compared with the known label from the training dataset,"; [Page 1, Right Column, “Results” Section] “developed deep-learning models using retinal fundus images from 48,101 patients from the UK Biobank”; [Page 4, Left Column, Top] “European SCORE risk calculator”; [Page 6, Left Column, 2nd Full Paragraph]).
Regarding Claims 3 and 13, Poplin discloses The apparatus of claim 2 and The method of claim 12, respectively. For the remainder of Claims 3 and 13, Poplin discloses wherein the target cardiovascular risk factor prediction model is a convolutional neural network (CNN)-based prediction model ([Page 1, Right Column, 1st Full Paragraph] “deep convolutional neural networks”; [Page 6, Left Column, “Mapping attention” section at bottom] “neural-network models…4 3 × 3 convolutional layers…”; [Page 6, Left Column, 2nd Full Paragraph] “classification network”).
Regarding Claims 4 and 14, Poplin discloses The apparatus of claim 1 and The method of claim 11, respectively. For the remainder of Claims 4 and 14, Poplin discloses wherein the at least one processor ([Page 6, Right Column, “Code availability” section] “computing infrastructure…computers”; [Page 9, Top of Page, “Software” section”] “TensorFlow and python scripts”)(Examiner notes that Python and Tensorflow software runs on computers, which include one or more processors to use the software.) is configured to produce the prediction value ([Page 2, Left Column, 1st Full Paragraph] “..cardiovascular risk factors”; [Page 2, Right Column, 1st Full Paragraph] “age, SBP, diastolic blood pressure (DBP), and BMI) using a related cardiovascular risk factor prediction model ([Page 6, Left Column, Top] “result is a model general enough to predict the labels (for example, cardiovascular risk factors) on new images”; [Page 6, Left Column, 2nd Full Paragraph] “a ‘classification model’ for predicting the binary risk factors (gender and
smoking status), a ‘regression model’ for the continuous risk factors (age, BMI, blood pressures and HbA1c)”), pre-trained ([Page 5, Right Column; Bottom; “Model development” section] “the process of learning the correct parameter values (training)”)(Examiner notes that the training occurs before the predicting with the fully-trained model occurs) using a plurality of pre-collected fundus images and an actually measured value of each of the at least one related cardiovascular risk factor ([Page 5, Right Column; Bottom; “Model development” section] - [Page 6, Left Column, Top] “fundus image…”, “for each image, the prediction given by the model is compared with the known label from the training dataset,"; [Page 1, Right Column, “Results” Section] “developed deep-learning models using retinal fundus images from 48,101 patients from the UK Biobank”) corresponding to each of the plurality of pre-collected fundus images ([Page 6, Left Column, Top] “the prediction given by the model is compared with the known label from the training dataset…process is repeated for every image in the training dataset.”)
Regarding Claims 5 and 15, Poplin discloses The apparatus of claim 4 and The method of claim 11, respectively. For the remainder of Claims 5 and 15, Poplin discloses wherein the related cardiovascular risk factor prediction model is a convolutional neural network (CNN)-based prediction model ([Page 1, Right Column, 1st Full Paragraph] “deep convolutional neural networks”; [Page 6, Left Column, “Mapping attention” section at bottom] “neural-network models…4 3 × 3 convolutional layers…”).
Regarding Claims 6 and 16, Poplin discloses The apparatus of claim 1 and The method of claim 11, respectively. For the remainder of Claims 6 and 16, Poplin discloses wherein the at least one processor ([Page 6, Right Column, “Code availability” section] “computing infrastructure…computers”; [Page 9, Top of Page, “Software” section”] “TensorFlow and python scripts”)(Examiner notes that Python and Tensorflow software runs on computers, which include one or more processors to use the software.) is configured to produce the final prediction value ([Page 4] Table 5: Predicting five-year MACE in the UK Biobank validation dataset using various input variables, “Algorithm + age + SBP + BMI + gender + current smoker”, AUC 0.73 (0.69, 0.77); [Page 3, Right Column] “predict the onset of major adverse cardiovascular events (MACE) within five years)(Examiner notes that the prediction using the “Algorithm” + the additional factors is a final prediction value that has been further fine-tuned by including additional predictions. Further, the prediction value is a binary value whether or not a MACE will occur within 5 years, with “AUC” being a prediction value associated with the efficacy of the model at predicting.) using a prediction result binding model ([Page 6, Left Column, 2nd Full Paragraph] including “third classification network for predicting MACE”), pre-trained using an initial prediction value of the target cardiovascular risk factor ([Page 4] Table 5: Predicting five-year MACE in the UK Biobank validation dataset using various input variables, “Algorithm only”, AUC 0.70 (0.65, 0.75); [Page 3, Right Column] “predict the onset of major adverse cardiovascular events (MACE) within five years)(Examiner notes that the prediction using the “Algorithm” alone is an initial prediction value that has not been further fine-tuned into a final prediction by including additional predictions. Further, the prediction value is a binary value whether or not a MACE will occur within 5 years, with “AUC” being a prediction value associated with the efficacy of the model at predicting.), a prediction value of each of the at least one related cardiovascular risk factor ([Page 2, Left Column, 1st Full Paragraph] “..cardiovascular risk factors”; [Page 2, Right Column, 1st Full Paragraph] “age, SBP, diastolic blood pressure (DBP), and BMI), and an actually measured value of the target cardiovascular risk factor ([Page 5, Right Column; Bottom; “Model development” section] - [Page 6, Left Column, Top] “for each image, the prediction given by the model is compared with the known label from the training dataset,"; [Page 4, Left Column, Top] “European SCORE risk calculator”; [Page 6, Left Column, 2nd Full Paragraph]), with regard to each of a plurality of pre-collected fundus images ([Page 5, Right Column; Bottom; “Model development” section] - [Page 6, Left Column, Top] “fundus image…”, “for each image, the prediction given by the model is compared with the known label from the training dataset,"; [Page 1, Right Column, “Results” Section] “developed deep-learning models using retinal fundus images from 48,101 patients from the UK Biobank”;.
Regarding Claims 7 and 17, Poplin discloses The apparatus of claim 6 and The method of claim 16, respectively. For the remainder of Claims 7 and 17, Poplin discloses wherein the prediction result binding model is a prediction model based on one of a regression analysis ([Page 6, Left Column, 2nd Full Paragraph] “‘regression model’ for the continuous risk factors (age, BMI, blood pressures and HbA1c”)(Examiner notes that the final prediction result model combines the MACE prediction with the predictions of related binary risk factors of gender and smoking status (classification model), the continuous risk factors of age, BMI, blood pressures, and HbA1c (regression model), thereby being at least partially based on a regression analysis). or an artificial neural network ([Page 1, Right Column, 1st Full Paragraph] “deep convolutional neural networks”; [Page 6, Left Column, “Mapping attention” section at bottom] “neural-network models…4 3 × 3 convolutional layers…”)(Examiner notes that a convolutional neural network is a type of artificial neural network.)
Regarding Claims 10 and 20, Poplin discloses The apparatus of claim 1 and The method of claim 11, respectively. For the remainder of Claims 9 and 19, Poplin discloses wherein the at least one related cardiovascular risk factor (([Page 2, Left Column, 1st Full Paragraph] “predict a variety of cardiovascular risk factors from retinal fundus images…age”; [Page 2, Right Column, 1st Full Paragraph] “algorithm…age, SBP, diastolic blood pressure (DBP), and BMI); [Page 6, Left Column, 1st Full Paragraph] “for multiple predictions simultaneously: age, gender, smoking status, BMI, SBP, DBP and HbA1c.”) comprises at least one of age ([Page 6, Left Column, 1st Full Paragraph] “…age”), sex ([Page 4, Left Column, 2nd Paragraph] “Models trained to predict gender”), smoking ([Page 6, Left Column, 1st Full Paragraph] “…smoking status”), a glycosylated hemoglobin level ([Page 6, Left Column, 1st Full Paragraph] “…HbA1c”), blood pressure ([Page 6, Left Column, 1st Full Paragraph] “…SBP, DBP”), a pulse wave, blood sugar level ([Page 6, Left Column, 1st Full Paragraph] “…HbA1c”), cholesterol level, creatinine level, insulin level, or intraocular pressure.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvio