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 .
DETAILED ACTION
In the supplemental response filed on 21 March 2026, the following has occurred: claims 16-40 have been newly added.
Now claims 1, 3 and 5-40 are pending.
Drawings
The drawings are objected to because
Figures 1-4 and 6 are objected to as failing to comply with 37 CFR 1.84(I) because the following figure(s) is/are unreadable and/or are unsatisfactory for reproduction.
Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
The Examiner has made an effort to uncover as many drawing issues as possible in the amount of time afforded for examination; however, it is possible that certain issues remain. It is incumbent upon the Applicant to review to Specification and Drawings to ensure that no addition objectionable issues remain.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are:
estimated model generation circuitry in claim 6.
data acquisition circuitry in claim 6
risk level evaluation circuity in claim 6
a pretreatment circuitry in claim 6
a main processing circuitry in claim 6
The various circuitry is being read from paragraph [0079].
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 16, 22-23, 35 and 38 are rejected for lack of adequate written description.
Claims 16, 22-23, 35 and 38 are rejected for lack of adequate written description. The claim recites functional steps for which the Applicant has not adequately described the steps in sufficient detail for one of ordinary skill in the art to conclude that the Applicant had possession of the invention.
MPEP 2161.01(I): When examining computer-implemented functional claims, examiners should determine whether the specification discloses the computer and the algorithm (e.g., the necessary steps and/or flowcharts) that perform the claimed function in sufficient detail such that one of ordinary skill in the art can reasonably conclude that the inventor invented the claimed subject matter. [...] If the specification does not provide a disclosure of the computer and algorithm in sufficient detail to demonstrate to one of ordinary skill in the art that the inventor possessed the invention including how to program the disclosed computer to perform the claimed function, a rejection under 35 U.S.C. 112(a) or pre-AIA 35 U.S.C. 112, first paragraph, for lack of written description must be made. For more information regarding the written description requirement, see MPEP § 2161.01- § 2163.07(b).
Specifically, the claim recites “generates a plurality of index data comprising at least one physical score and at least one functional score” and “wherein the seven index data comprise two physical scores and four functional scores”. The Applicant has provided no disclosure of how these scores are determined. Any scoring algorithm could potentially read on the as-claimed invention.
The Specification states: at paragraph [0104], “The seven newly created indexes are defined as physical score (two data) and functional score (four data)”
This is inadequate for a person of ordinary skill in the art at the time of the invention (or filing) to conclude that the Applicant had possession of the claimed algorithm. No algorithm is presented.
The Examiner prospectively notes that this written description rejection is not based on whether one skilled in the art would know how to program a computer to perform any form of scoring (i.e., an enablement rejection), but rather is directed to the Applicant’s lack of specificity as to how the scoring is specifically performed with respect to the Applicant’s claimed invention, i.e., would a potential infringer know the metes and bounds of the Applicant’s invention such that they could avoid infringing the Applicant’s claimed invention. In this case, they would not because the Applicant's description of scoring claims any and all types of scoring evidencing that the Applicant did not have possession of their invention at the time of filing.
Claim Rejections - 35 USC § 101
Claims 1, 3 and 5-40 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Claims 1 and 6-7 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claims recite method and system for evaluating risk of disease. The limitations of:
Claim 6, which is representative of claim 1 and 7
[…] generate an estimated model for estimating a disease risk by […] using (a) an attribute data, (b) physical finding data, (c) a blood examination data, and (d) a diagnosis result data; [… obtain …] (a) an attribute data of a subject, (b) physical finding data of the subject, and (c) a blood examination data of the subject; and […] input the data acquired by the data acquisition [… step …] into the estimated model generated by the estimated model generation [… step …], and obtaining an inferred disease risk of the subject, […] generate index data from the (a) attribute data, (b) physical finding data, and (c) blood examination data, [… organize data …] using the (a) attribute data, (b) physical finding data, and (c) blood examination data, and the index data calculated […] as an input layer, the inferred liver disease risk is the risk level for liver disease of the subject, generating the estimated model includes generating an estimated model for estimating the risk level of hepatic fibrosis by […] using (a) the attribute data including at least one selected from gender and age, (b) the physical finding data including at least one selected from height and weight, (c) the blood examination data including Type 4 collagen and at least one selected from AST (GOT), ALT (GPT), gamma-GTP, PLT, T-Cho and TG, and (d) the diagnostic result of a doctor, and obtaining the inferred disease risk includes obtaining the risk level of the hepatic fibrosis of the subject by inputting (a) the attribute data including at least one selected from gender and age of the subject, (b) the physical finding data including at least one selected from height and weight of the subject, and (c) the blood examination data including Type 4 collagen and at least one selected from AST (GOT), ALT (GPT), gamma-GTP, PLT, T-Cho and TG of the subject, into the estimated model in the estimated model generation step.
, as drafted, is a method, which under its broadest reasonable interpretation, covers a method of organizing human activity (i.e., managing personal behavior including following rules or instructions) via human interaction with generic computer components. That is, by a human user interacting with various circuitry (claim 6) a computer (claim 7), the claimed invention amounts to managing personal behavior or interaction between people, the Examiner notes as stated in 2106.04(a)(2), “certain activity between a person and a computer… may fall within the “certain methods of organizing human activity” grouping”. For example, via human interaction with various circuitry (claim 6) a computer (claim 7), the claim encompasses building a model and collecting patient data and organizing the collected data to make risk determinations for a patient about hepatic fibrosis. If a claim limitation, under its broadest reasonable interpretation, covers managing personal behavior or interactions between people but for the recitation of generic computer components, then it falls within the “method of organizing human activity” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements of various circuitry (claim 6) a computer (claim 7), which implements the abstract idea. The various circuitry (claim 6) a computer (claim 7) is recited at a high-level of generality (i.e., a general-purpose computers/ computer components implementing generic computer functions; see Applicant’s Specification paragraphs [0079]) such that it amounts no more than mere instructions to apply the exception using generic computer components. Accordingly, these 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. The claim is directed to an abstract idea.
The claim recites the additional elements of “by machine learning… perform machine learning”, “acquire…” and “a pretreatment step…” to implement the abstract idea. The “by machine learning… perform machine learning” steps are recited at a high-level of generality (i.e., using a generic off-the shelf model) and amounts to generally linking the abstract idea to a particular technological environment. The “acquire…” steps are recited at a high-level of generality (i.e., as a general means of receiving/transmitting data) and amounts to the mere transmission and/or receipt of data, which is a form of extra-solution activity. The “a pretreatment step…” steps are recited at a high-level of generality (i.e., doing anything at a time before another action) and amounts to generally linking the abstract idea to a particular technological environment. Accordingly, even in combination, these additional elements do not integrate the abstract idea into a practical application. The claim is directed to an abstract idea.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of various circuitry (claim 6) a computer (claim 7) to perform the noted steps amounts to no more than mere instructions to apply the exception using generic hardware components. Mere instructions to apply an exception using a generic hardware component cannot provide an inventive concept (“significantly more”).
Also, as discussed above with respect to integration of the abstract idea into a practical application, the additional elements of “by machine learning… perform machine learning”, “acquire…” and “a pretreatment step…” were considered generally linking the abstract idea to particular technological environment and/or extra-solution activity. The “machine learning” has been re-evaluated under the “significantly more” analysis and determined to amount to be well-understood, routine, and conventional elements/functions. As described in Park (2019/0172587): see below but at least paragraph [0012]; Feldstein (2015/0247149): see below but at least paragraph [0093]; use of machine learning to build a model is well-understood, routine and conventional. The “acquiring…” steps have been re-evaluated under the “significantly more” analysis and determined to amount to be well-understood, routine, and conventional elements/functions. As described in MPEP 2106.05(d)(II)(i) “Receiving or transmitting data over a network” is well-understood, routine, and conventional. The “a pretreatment step…” has been re-evaluated under the “significantly more” analysis and determined to amount to be well-understood, routine, and conventional elements/functions. As described in Allison (20100081971): paragraph [0089]; Bokan (20150216438): paragraph [0116]; Daw (20050096530): paragraph [0044]; Well-understood, routine, and conventional elements/functions cannot provide “significantly more.” As such the claim is not patent eligible.
Claims 2-5 and 8-40 are similarly rejected because either further define the abstract idea and/or do not further limit the claim to a practical application or provide as inventive concept such that the claims are subject matter eligible.
Claim 2, 8 and 12 further describes a liver disease as the disease, however does not recite any additional elements are therefore cannot provide a practical application and/or significantly more.
Claims 3-5, 9-11 and 13-15 further describes the features used in making liver disease predictions, however does not recite any additional elements are therefore cannot provide a practical application and/or significantly more.
Claims 16, 22, 35 and 38 further describe scoring data, however does not recite any additional elements are therefore cannot provide a practical application and/or significantly more.
Claims 17, 25, 36 and 39 describes determining multiple models, however training of machine learning models was already considered above and is incorporated herein.
Claim 18-19, 28-29, 37 and 40 further describes the machine learning model as a multilayer perceptron with various layers with back propagation and use of math, however use of math is not an additional element, and the high-level recitation of the multi-layer perceptron with a loss function and back propagation and are recited at a high-level of generality (i.e., using a generic off-the shelf neural network model) and amounts to generally linking the abstract idea to a particular technological environment. Accordingly, even in combination, these additional elements do not integrate the abstract idea into a practical application. The claim is directed to an abstract idea.
Also, as discussed above with respect to integration of the abstract idea into a practical application, the additional elements were considered generally linking the abstract idea to particular technological environment and/or extra-solution activity. These have been re-evaluated under the “significantly more” analysis and determined to amount to be well-understood, routine, and conventional elements/functions. As described in Park (2019/0172587): see below but at least paragraph [0063]-[0064], [0075]-[0076]; Fontanarava (20190298204): see below but at least paragraph [0093]; use of a multi-layer perceptron trained with back propagation is well-understood, routine and conventional. Well-understood, routine, and conventional elements/functions cannot provide “significantly more.” As such the claim is not patent eligible.
Claim 20 describes “posttreatment”, however it is analyzed similar to “pretreatment” above and incorporated herein.
Claims 21 and 31-33 describe using various thresholds for various categories, however does not recite any additional elements are therefore cannot provide a practical application and/or significantly more.
Claim 23, 26 and 34 describes the labels of data used, however does not recite any additional elements are therefore cannot provide a practical application and/or significantly more.
Claims 24 and 27 describe use of math (i.e., sensitivity and specificity), however does not recite any additional elements are therefore cannot provide a practical application and/or significantly more.
Claim 30 describes the number of epochs, however does not recite any additional elements are therefore cannot provide a practical application and/or significantly more.
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 obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claim(s) 1, 3, 6-10, 12-14, 16, 18-24, 31-32, 35 and 38 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent App. No. 2019/0172587 (hereafter “Park”), in view of U.S. Patent App. No. 2020/0005900 (hereafter “Cha”), in view of U.S. Patent App. No. 20180100867 (hereafter “Okanoue”).
Regarding (Currently Amended) claim 1, Park teaches a data processing method for evaluating [… using liver history a …] disease risk (Park: Figures 1-2, 10, paragraph [0001], “apparatus and is method for predicting a disease risk”, paragraphs [0025]-[0028], “the plurality of state variables including at least five of… fatty liver… a past history of fatty liver”) comprising:
an estimated model generation step of generating an estimated model for estimating a [… using liver history a …] disease risk by machine learning using (a) an attribute data, (b) physical finding data, (c) a blood examination data, and (d) a diagnosis result data (Park: Figures 1-2, 10, paragraph [0012], “a machine learning model generating unit which generates a machine learning model which learns a degree of a relationship between at least one of a plurality of state variables and genetic information and a disease risk of metabolic disorders with the plurality of state variables including a living condition variable and a health condition variable of a patient with a metabolic disorder, generic information, and the disease risk of the metabolic disorders as input”, paragraphs [0025]-[0028], “the plurality of state variables including at least five of age… fatty liver… an uric acid level in blood… a gender an age, a past history of hypertension, a past history of hyperlipidemia, a past history of myocardial infarction, a past history of chronic gastritis, a past history of fatty liver, a past history of cholecystitis, a past history of chronic bronchitis, a past history of asthma, a past history of allergy, arthritis, a past history of osteoporosis, a past history of cataract, a past history of depressive disorder, a past history of thyroid gland disease… a weight, a waist size, a hip circumference, a pulse rate, a diastolic blood pressure, a systolic blood pressure, and a body mass index”, paragraphs [0058]-[0056], “The machine learning model generating unit 120 may have a plurality of state variables including a living condition variable and a health condition variable of a patient with a metabolic disorder, gene information, and a disease risk of metabolic disorders as inputs”. The Examiner notes age/gender is attribute data, weight/BMI is physical finding data, blood pressure and levels in blood is blood examination data, and past diagnosis is diagnosis result data and all are used to train a model which teaches what is required of the claim under the broadest reasonable interpretation);
a data acquisition step of acquiring (a) an attribute data of a subject, (b) physical finding data of the subject, and (c) a blood examination data of the subject (Park: Figures 1-2, 10, paragraph [0012], “an information input unit which receives a subject state variable and subject genetic information of the subject”, paragraph [0056], “the state variables may be a living condition variable and a health condition variable of the subject including demographical characteristics such as an age, a gender, or a household income, epidemiological information such as a family history or a past disease history, a lifestyle such as a drinking history, a smoking history, a physical activity, or nutrition, physical measurement values such as a height, a weight, or a blood test result, and clinical information.”, paragraph [0201], “receive a subject state variable and subject genetic information of the subject”. Also see, paragraphs [0025]-[0028], [0055]-[0058]. The Examiner notes demographic (age/gender) is attribute data, heigh/weight is a physical finding, and genetic information/blood test is blood examination data under the broadest reasonable interpretation); and
a risk level evaluation step of inputting the data acquired in the data acquisition step into the estimated model generated in the estimated model generation step, and obtaining an inferred [… using liver history a …] disease risk of the subject (Park: Figures 1-2, 10, paragraph [0012], “a disease risk predicting unit which predicts a subject disease risk of the subject by applying the subject state variable and the subject genetic information of the subject to the machine learning model”, paragraph [0202], “the apparatus 100 for predicting a disease risk of metabolic disorders may predict a disease risk of the subject by applying a subject state variable and subject genetic information of the subject to the machine learning model”. Also see, paragraphs [0025]-[0028]),
wherein the estimated model generation step includes a […] step of generating [… probability …] data from the (a) attribute data, (b) physical finding data, and (c) blood examination data (Park: Figures 1-2, 10, paragraphs [0009]-[0013], “predict a probability of a future risk of developing metabolic disorders… calculate a probability value… generates a statistical probability model probabilistically representing the disease risk of the metabolic disorders depending on whether there are at least one of the plurality of state variables and genetic information or a value, with the plurality of state variables, the genetic information, and the disease risk of the metabolic disorder of a pattern with the metabolic disorder as inputs” paragraphs [0025]-[0028], “the plurality of state variables including at least five of age… fatty liver… an uric acid level in blood… a gender an age, a past history of hypertension, a past history of hyperlipidemia, a past history of myocardial infarction, a past history of chronic gastritis, a past history of fatty liver, a past history of cholecystitis, a past history of chronic bronchitis, a past history of asthma, a past history of allergy, arthritis, a past history of osteoporosis, a past history of cataract, a past history of depressive disorder, a past history of thyroid gland disease… a weight, a waist size, a hip circumference, a pulse rate, a diastolic blood pressure, a systolic blood pressure, and a body mass index”, paragraphs [0058]-[0056], “The machine learning model generating unit 120 may have a plurality of state variables including a living condition variable and a health condition variable of a patient with a metabolic disorder, gene information, and a disease risk of metabolic disorders as inputs”, paragraph [0202], “the apparatus 100 for predicting a disease risk of metabolic disorders may predict a disease risk of the subject by applying a subject state variable and subject genetic information of the subject to the machine learning model”), and
a main processing step of machine learning using the (a) attribute data, (b) physical finding data, and (c) blood examination data, and the […] data calculated in the pretreatment step as an input layer (Park: Figures 1-2, 10, paragraphs [0012]-[0014], “a machine learning model generating unit which generates a machine learning model which learns a degree of a relationship between at least one of a plurality of state variables and genetic information and a disease risk of metabolic disorders with the plurality of state variables including a living condition variable and a health condition variable of a patient with a metabolic disorder, generic information, and the disease risk of the metabolic disorders as inputs”, paragraphs [0058]-[0056], “The machine learning model generating unit 120 may have a plurality of state variables including a living condition variable and a health condition variable of a patient with a metabolic disorder, gene information, and a disease risk of metabolic disorders as inputs”),
the inferred […] disease risk is the risk level for […] disease of the subject (Park: Figures 1-2, 10, paragraphs [0009]-[0013], “predict a probability of a future risk of developing metabolic disorders… calculate a probability value… generates a statistical probability model probabilistically representing the disease risk of the metabolic disorders”, paragraphs [0025]-[0028], “the plurality of state variables including at least five of… fatty liver… a past history of fatty liver”),
the estimated model generation step includes generating an estimated model for estimating the risk level of [… a disease …] by machine learning using (a) the attribute data including at least one selected from gender and age, (b) the physical finding data including at least one selected from height and weight, (c) the blood examination data including […] at least one selected from AST (GOT), ALT (GPT), gamma-GTP, PLT, T-Cho and TG, and (d) the diagnostic result of a doctor (Park: Figures 1-2, 10, paragraph [0012], “a machine learning model generating unit which generates a machine learning model which learns a degree of a relationship between at least one of a plurality of state variables and genetic information and a disease risk of metabolic disorders with the plurality of state variables including a living condition variable and a health condition variable of a patient with a metabolic disorder, generic information, and the disease risk of the metabolic disorders as input”, paragraphs [0025]-[0028], “the plurality of state variables including at least five of age… fatty liver… an uric acid level in blood… a gender an age… a past history of fatty liver… a weight, a waist size, a hip circumference, a pulse rate, a diastolic blood pressure, a systolic blood pressure, and a body mass index… ALT”, paragraphs [0056]-[0058], “a past disease history… The machine learning model generating unit 120 may have a plurality of state variables including a living condition variable and a health condition variable of a patient with a metabolic disorder, gene information, and a disease risk of metabolic disorders as inputs”, Table 1, “Liver function test (ALT)”), and
the risk level evaluation step includes obtaining the risk level of the [… disease …] of the subject by inputting (a) the attribute data including at least one selected from gender and age of the subject, (b) the physical finding data including at least one selected from height and weight of the subject, and (c) the blood examination data […] of the subject, into the estimated model in the estimated model generation step (Park: Figures 1-2, 10, paragraph [0012], “a disease risk predicting unit which predicts a subject disease risk of the subject by applying the subject state variable and the subject genetic information of the subject to the machine learning model”, paragraphs [0025]-[0028], “the plurality of state variables including at least five of age… fatty liver… an uric acid level in blood… a gender an age… a past history of fatty liver… a weight, a waist size, a hip circumference, a pulse rate, a diastolic blood pressure, a systolic blood pressure, and a body mass index… ALT”, paragraph [0202], “the apparatus 100 for predicting a disease risk of metabolic disorders may predict a disease risk of the subject by applying a subject state variable and subject genetic information of the subject to the machine learning model”, Table 1, “Liver function test (ALT)”).
Park may not explicitly teach (underlined below for clarity):
an estimated model generation step of generating an estimated model for estimating a liver disease risk by machine learning using (a) an attribute data, (b) physical finding data, (c) a blood examination data, and (d) a diagnosis result data; […], and obtaining an inferred liver disease risk of the subject,
wherein the estimated model generation step includes a pretreatment step of generating index data from the (a) attribute data, (b) physical finding data, and (c) blood examination data, and
a main processing step of machine learning using the (a) attribute data, (b) physical finding data, and (c) blood examination data, and the index data calculated in the pretreatment step as an input layer,
the inferred liver disease risk is the risk level for liver disease of the subject,
Cha teaches an estimated model generation step of generating an estimated model for estimating a liver disease risk by machine learning using (a) an attribute data, (b) physical finding data, (c) a blood examination data, and (d) a diagnosis result data; […], and obtaining an inferred liver disease risk of the subject (Cha: Figures 1, 4, 6, paragraph [0008], “employ machine learning techniques to assess a likelihood or risk that one or more patients will experience an adverse outcome”, paragraph [0015], “Exemplary diagnoses may relate to… liver disease”, paragraph [0029], “machine learning embodiments are typically employed to determine risk information for patient outcomes”),
wherein the estimated model generation step includes a pretreatment step of generating index data from the (a) attribute data, (b) physical finding data, and (c) blood examination data (Cha: Figures 1, 4, 6, paragraphs [0049]-[0051], “During preprocessing, the system may perform any number of data manipulations on the initial data records to create preprocessed data records therefrom. Some exemplary manipulations may include… the system may correlate or index the various ingested raw input data… the system may perform various preprocessing steps to allow such information to be included in preprocessed data records”, paragraphs [0077]-[0080], “system may also aggregate DP information into one of a number of comorbidity groups to be employed as features. Generally, such comorbidity groups may correspond to specific comorbidities included in the Elixhauser Comorbidity Index (“ECI”)”. The Examiner notes preprocessing reads on at least pre-treatment as well, under the broadest reasonable interpretation), and
a main processing step of machine learning using the (a) attribute data, (b) physical finding data, and (c) blood examination data, and the index data calculated in the pretreatment step as an input layer (Cha: Figures 1, 4, 6, paragraph [0008], “employ machine learning techniques to assess a likelihood or risk”, paragraph [0049], “Although machine learning techniques are well-equipped to handle common problems of incomplete and/or inaccurate data, a significant amount of preprocessing, cleaning and/or regularization may be employed to ensure the creation of high-quality predictive features”, paragraph [0063], “various predictive features are created from the preprocessed patient information associated with each patient in the cohort. As discussed below, such features may be provided to the machine learning model to determine various risk information”, paragraph [0080], “It will be appreciated that any number of features relating to the above-described groups may be created and employed by the machine learning models”. The Examiner notes the index created in the pre-processing (i.e., a pre-treatment) step are used in a machine learning process to determine a risk of a liver disease, which in combination with teachings of Park above, teach what is required under the broadest reasonable interpretation),
the inferred liver disease risk is the risk level for liver disease of the subject (Cha: Figures 1, 4, 6, paragraph [0008], “employ machine learning techniques to assess a likelihood or risk that one or more patients will experience an adverse outcome”, paragraph [0015], “Exemplary diagnoses may relate to… liver disease”, paragraph [0029], “machine learning embodiments are typically employed to determine risk information for patient outcomes”),
One of ordinary skill in the art before the effective filing date would have found to obvious to include using indexing during a pretreatment step as taught by Cha within the determination of a probability value using various collected patient data as taught by Park with the motivation of “to ensure the creation of high-quality predictive features” and “provides enhanced interpretability… and allows for more efficient incorporation of such information into downstream operations” (Cha: paragraphs [0049] and [0080]).
Park and Cha may not explicitly teach (underlined below for clarity):
the estimated model generation step includes generating an estimated model for estimating the risk level of hepatic fibrosis by machine learning using (a) the attribute data including at least one selected from gender and age, (b) the physical finding data including at least one selected from height and weight, (c) the blood examination data including Type 4 collagen and at least one selected from AST (GOT), ALT (GPT), gamma-GTP, PLT, T-Cho and TG, and (d) the diagnostic result of a doctor, and the risk level evaluation step includes obtaining the risk level of the hepatic fibrosis of the subject by inputting (a) the attribute data including at least one selected from gender and age of the subject, (b) the physical finding data including at least one selected from height and weight of the subject, and (c) the blood examination data including Type 4 collagen and at least one selected from AST (GOT), ALT (GPT), gamma-GTP, PLT, T-Cho and TG of the subject, into the estimated model in the estimated model generation step.
Okanoue teaches the estimated model generation step includes generating an estimated model for estimating the risk level of hepatic fibrosis by machine learning using (a) the attribute data including at least one selected from gender and age, (b) the physical finding data including at least one selected from height and weight, (c) the blood examination data including Type 4 collagen and at least one selected from AST (GOT), ALT (GPT), gamma-GTP, PLT, T-Cho and TG, and (d) the diagnostic result of a doctor, and the risk level evaluation step includes obtaining the risk level of the hepatic fibrosis of the subject by inputting (a) the attribute data including at least one selected from gender and age of the subject, (b) the physical finding data including at least one selected from height and weight of the subject, and (c) the blood examination data including Type 4 collagen and at least one selected from AST (GOT), ALT (GPT), gamma-GTP, PLT, T-Cho and TG of the subject, into the estimated model in the estimated model generation step (Okanoue: Figures 12-16, paragraph [0001], “the present invention relates to a method for discriminating between nonalcoholic fatty liver (NAFL) and nonalcoholic steatohepatitis (NASH), and a method for determining the presence of hepatic fibrosis”, paragraph [0189], “COL4 (collagen 4), COL4-7S (type 4 collagen 7S)”, paragraph [0253], “the Human MAP method is used for measurement of VCAM1, CTSD, and COL4, and a radioimmunoassay with a “Type IV Collagen 7S Kit” is used for measurement of COL4-7S”, paragraph [0363]-[0366], “acquire the measurement data (measurement data of quantities of the above marker molecules) from the measurement apparatus 1… calculate the normalized score from the acquired measurement data based on the above formula 1 and to determine the index value… compare the index value… to determine the presence or absence of a hepatic disease based on the compared result”, paragraph [0427], “the preferable index value, the values calculated… determined by the neural network”. The Examiner notes a machine learning model uses blood examination data that comprises Type 4 collagen to make risk determinations of hepatic fibrosis, which in combination the machine learning model as taught by Park and Cha, above, teach what is required of the claim under the broadest reasonable interpretation).
One of ordinary skill in the art before the effective filing date would have found it obvious to include using type 4 collagen with machine learning models to make determinations about hepatic fibrosis as taught by Okanoue within the use of various types of data including blood examination data to train and utilize a machine learning to determine risk of liver disease as taught by Park and Cha with the motivation of “provide a noninvasive method for determining the disease type or determining the presence of a symptom of a hepatic disease such as nonalcoholic fatty liver disease with a higher diagnostic accuracy” and “improvement of the accuracy” (Okanoue: paragraphs [0009] and [0336]. Also see, paragraph [0002]).
Regarding (Currently Amended) claim 3, Park Cha and Okanoue teach the limitations of claim 1, and further teach wherein the estimated model generation step includes generating an estimated model for estimating the risk level of the non-alcoholic fatty liver by machine learning using (a) the attribute data including at least one selected from gender and age, (b) the physical finding data including at least one selected from height and weight, (c) the blood examination data including at least one selected from AST (GOT), ALT (GPT), gamma-GTP, PLT, T-Cho and TG, and (d) the diagnostic result of a doctor (Park: Figures 1-2, 10, paragraph [0012], “a machine learning model generating unit which generates a machine learning model which learns a degree of a relationship between at least one of a plurality of state variables and genetic information and a disease risk of metabolic disorders with the plurality of state variables including a living condition variable and a health condition variable of a patient with a metabolic disorder, generic information, and the disease risk of the metabolic disorders as input”, paragraphs [0025]-[0028], “the plurality of state variables including at least five of age… fatty liver… an uric acid level in blood… a gender an age… a past history of fatty liver… a weight, a waist size, a hip circumference, a pulse rate, a diastolic blood pressure, a systolic blood pressure, and a body mass index… ALT”, paragraphs [0058]-[0056], “The machine learning model generating unit 120 may have a plurality of state variables including a living condition variable and a health condition variable of a patient with a metabolic disorder, gene information, and a disease risk of metabolic disorders as inputs”, Table 1, “Liver function test (ALT)”; Okanoue: Figures 12-16, paragraphs [0001]-[0002], “a method for discriminating between nonalcoholic fatty liver (NAFL) and nonalcoholic steatohepatitis (NASH)… NAFLD ranges from nonalcoholic fatty liver (NAFL) with a good prognosis to nonalcoholic steatohepatitis (NASH) with a poor prognosis”, paragraph [0363]-[0366], “determine the presence or absence of a hepatic disease based on the compared result”, paragraph [0427], “the preferable index value, the values calculated… determined by the neural network”),
the risk level evaluation step includes obtaining the risk level of the non-alcoholic fatty liver of the subject by inputting (a) the attribute data including at least one selected from gender and age of the subject, (b) the physical finding data including at least one selected from height and weight of the subject, and (c) the blood examination data including at least one selected from AST (GOT), ALT (GPT), gamma-GTP, PLT, T-Cho and TG of the subject, into the estimated model in the estimated model generation step (Park: Figures 1-2, 10, paragraph [0012], “a disease risk predicting unit which predicts a subject disease risk of the subject by applying the subject state variable and the subject genetic information of the subject to the machine learning model”, paragraphs [0025]-[0028], “the plurality of state variables including at least five of age… fatty liver… an uric acid level in blood… a gender an age… a past history of fatty liver… a weight, a waist size, a hip circumference, a pulse rate, a diastolic blood pressure, a systolic blood pressure, and a body mass index… ALT”, paragraph [0202], “the apparatus 100 for predicting a disease risk of metabolic disorders may predict a disease risk of the subject by applying a subject state variable and subject genetic information of the subject to the machine learning model”, Table 1, “Liver function test (ALT)”; Okanoue: Figures 12-16, paragraphs [0001]-[0002], “a method for discriminating between nonalcoholic fatty liver (NAFL) and nonalcoholic steatohepatitis (NASH)… NAFLD ranges from nonalcoholic fatty liver (NAFL) with a good prognosis to nonalcoholic steatohepatitis (NASH) with a poor prognosis”, paragraph [0363]-[0366], “determine the presence or absence of a hepatic disease based on the compared result”, paragraph [0427], “the preferable index value, the values calculated… determined by the neural network”).
The motivation to combine is the same as in claim 1, incorporated herein.
REGARDING CLAIM(S) 6 and 7
Claim(s) 6 and 7 is/are analogous to Claim(s) 1, thus Claim(s) 6 and 7 is/are similarly analyzed and rejected in a manner consistent with the rejection of Claim(s) 1.
Regarding (Currently Amended) claim 8, Park Cha and Okanoue teach the limitations of claim 6, and further teach wherein the inferred disease risk is the risk level for liver disease of the subject (Park: Figures 1-2, 10, paragraphs [0009]-[0013], “predict a probability of a future risk of developing metabolic disorders… calculate a probability value… generates a statistical probability model probabilistically representing the disease risk of the metabolic disorders”, paragraphs [0025]-[0028], “the plurality of state variables including at least five of… fatty liver… a past history of fatty liver”; Cha: Figures 1, 4, 6, paragraph [0008], “employ machine learning techniques to assess a likelihood or risk that one or more patients will experience an adverse outcome”, paragraph [0015], “Exemplary diagnoses may relate to… liver disease”, paragraph [0029], “machine learning embodiments are typically employed to determine risk information for patient outcomes”; Okanoue: Figures 12-16, paragraphs [0001]-[0002], “the present invention relates to a method for discriminating between nonalcoholic fatty liver (NAFL) and nonalcoholic steatohepatitis (NASH), and a method for determining the presence of hepatic fibrosis”, paragraph [0363]-[0366], “acquire the measurement data (measurement data of quantities of the above marker molecules) from the measurement apparatus 1… calculate the normalized score from the acquired measurement data based on the above formula 1 and to determine the index value… compare the index value… to determine the presence or absence of a hepatic disease based on the compared result”).
The motivation to combine is the same as in claim 1, incorporated herein.
REGARDING CLAIM(S) 9 and 13
Claim(s) 9 and 13 are analogous to Claim(s) 3, thus Claim(s) 9, and 13 is/are similarly analyzed and rejected in a manner consistent with the rejection of Claim(s) 3.
Regarding (Currently Amended) claim 10, Park Cha and Okanoue teach the limitations of claim 8, and further teach wherein the estimated model generation circuitry is configured to generate an estimated model for estimating the risk level of hepatic fibrosis by machine learning using (a) the attribute data including at least one selected from gender and age, (b) the physical finding data including at least one selected from height and weight, (c) the blood examination data including Type 4 collagen and at least one selected from AST (GOT), ALT (GPT), gamma-GTP, PLT, T-Cho and TG, and (d) the diagnostic result of a doctor (Park: Figures 1-2, 10, paragraph [0012], “a machine learning model generating unit which generates a machine learning model which learns a degree of a relationship between at least one of a plurality of state variables and genetic information and a disease risk of metabolic disorders with the plurality of state variables including a living condition variable and a health condition variable of a patient with a metabolic disorder, generic information, and the disease risk of the metabolic disorders as input”, paragraphs [0025]-[0028], “the plurality of state variables including at least five of age… fatty liver… an uric acid level in blood… a gender an age… a past history of fatty liver… a weight, a waist size, a hip circumference, a pulse rate, a diastolic blood pressure, a systolic blood pressure, and a body mass index… ALT”, paragraphs [0056]-[0058], “a past disease history… The machine learning model generating unit 120 may have a plurality of state variables including a living condition variable and a health condition variable of a patient with a metabolic disorder, gene information, and a disease risk of metabolic disorders as inputs”, Table 1, “Liver function test (ALT)”; Okanoue: Figures 12-16, paragraph [0001], “the present invention relates to a method for discriminating between nonalcoholic fatty liver (NAFL) and nonalcoholic steatohepatitis (NASH), and a method for determining the presence of hepatic fibrosis”, paragraph [0189], “COL4 (collagen 4), COL4-7S (type 4 collagen 7S)”, paragraph [0253], “the Human MAP method is used for measurement of VCAM1, CTSD, and COL4, and a radioimmunoassay with a “Type IV Collagen 7S Kit” is used for measurement of COL4-7S”, paragraph [0363]-[0366], “acquire the measurement data (measurement data of quantities of the above marker molecules) from the measurement apparatus 1… calculate the normalized score from the acquired measurement data based on the above formula 1 and to determine the index value… compare the index value… to determine the presence or absence of a hepatic disease based on the compared result”, paragraph [0427], “the preferable index value, the values calculated… determined by the neural network”. The Examiner notes a machine learning model uses blood examination data that comprises Type 4 collagen to make risk determinations of hepatic fibrosis, which in combination the machine learning model as taught by Park and Cha, above, teach what is required of the claim under the broadest reasonable interpretation),
the risk level evaluation circuitry is configured to obtain the risk level of the hepatic fibrosis of the subject by inputting (a) the attribute data including at least one selected from gender and age of the subject, (b) the physical finding data including at least one selected from height and weight of the subject, and ( c) the blood examination data including Type 4 collagen and at least one selected from AST (GOT), ALT (GPT), gamma-GTP, PLT, T-Cho and TG of the subject, into the estimated model generated by the estimated model generation circuitry (Park: Figures 1-2, 10, paragraph [0012], “a disease risk predicting unit which predicts a subject disease risk of the subject by applying the subject state variable and the subject genetic information of the subject to the machine learning model”, paragraphs [0025]-[0028], “the plurality of state variables including at least five of age… fatty liver… an uric acid level in blood… a gender an age… a past history of fatty liver… a weight, a waist size, a hip circumference, a pulse rate, a diastolic blood pressure, a systolic blood pressure, and a body mass index… ALT”, paragraph [0202], “the apparatus 100 for predicting a disease risk of metabolic disorders may predict a disease risk of the subject by applying a subject state variable and subject genetic information of the subject to the machine learning model”, Table 1, “Liver function test (ALT)”; Okanoue: Figures 12-16, paragraph [0001], “the present invention relates to a method for discriminating between nonalcoholic fatty liver (NAFL) and nonalcoholic steatohepatitis (NASH), and a method for determining the presence of hepatic fibrosis”, paragraph [0189], “COL4 (collagen 4), COL4-7S (type 4 collagen 7S)”, paragraph [0253], “the Human MAP method is used for measurement of VCAM1, CTSD, and COL4, and a radioimmunoassay with a “Type IV Collagen 7S Kit” is used for measurement of COL4-7S”, paragraph [0363]-[0366], “acquire the measurement data (measurement data of quantities of the above marker molecules) from the measurement apparatus 1… calculate the normalized score from the acquired measurement data based on the above formula 1 and to determine the index value… compare the index value… to determine the presence or absence of a hepatic disease based on the compared result”, paragraph [0427], “the preferable index value, the values calculated… determined by the neural network”).
The motivation to combine is the same as in claim 1, incorporated herein.
REGARDING CLAIM(S) 12 and 14
Claim(s) 12 and 14 is/are analogous to Claim(s) 8 and 10, thus Claim(s) 12 and 14 is/are similarly analyzed and rejected in a manner consistent with the rejection of Claim(s) 8 and 10.
Regarding (New) claim 16, Park Cha and Okanoue teach the limitations of claim 1, and further teach wherein the pretreatment step generates a plurality of index data comprising at least one physical score and at least one functional score from the attribute data, physical finding data, and blood examination data (Park: paragraph [0056], “state variables may be a living condition variable and a health condition variable of the subject including demographical characteristics… a physical activity, or nutrition, physical measurement values”; Cha: paragraph [0136], “a significant renal function decline event 254… when a patient's eGFR value is determined to be less than a predetermined minimum value”).
The motivation to combine is the same as in claim 1, incorporated herein.
Regarding (New) claim 18, Park Cha and Okanoue teach the limitations of claim 1, and further teach wherein the main processing step comprises a multilayer perceptron having an input layer, at least one hidden layer, and an output layer, wherein the input layer receives both the attribute data, physical finding data, blood examination data, and the index data calculated in the pretreatment step (Park: paragraphs [0015]-[0020], “the machine learning model may perform first learning to learn a degree of a relationship between an input layer and a hidden layer… the output layer”, paragraphs [0063]-[0064], “The machine learning model generating unit 120 may additionally connect the multi-layer perceptron neural network to a last layer of the existing recurrent neural network to collectively input the genetic information collected at the single timing… the artificial neural network may be divided into three layers of an input layer, a hidden layer, and an output layer, each layer is configured by nodes and the input layer receives input data from the outside of the system to transmit the input data to the system”).
The motivation to combine is the same as in claim 1, incorporated herein.
Regarding (New) claim 19, Park Cha and Okanoue teach the limitations of claim 18, and further teach wherein the main processing step further comprises training the multilayer perceptron using error backpropagation with a plurality of training epochs until convergence (Park: paragraph [0075]-[0076], “Equation 3 is an error equation of the machine learning model generating unit 120 and learns a weight of the artificial neural network through a backpropagation algorithm… the machine learning model generating unit 120 divides patients (all subjects) with the metabolic disorders into three groups to verify the specificity(validity) of the constructed machine learning model (for example, the artificial neural network) to perform cross validation”, paragraph [0084], “the basic statistical probability model generating unit 131 may divide the subjects into a training set and a test set”).
The motivation to combine is the same as in claim 1, incorporated herein.
Regarding (New) claim 20, Park Cha and Okanoue teach the limitations of claim 1, and further teach further comprising a post-treatment step of assigning the inferred liver disease risk to one of a plurality of risk categories based on threshold values of an output layer (Cha: paragraph [0104], “The risk categories may represent quantitative stratifications or groupings of a patient population and/or patient cohorts, wherein each category is associated with an identifier… the system may associate various qualitative descriptors with such risk categories (e.g., very low risk, low risk, medium risk, high risk, very high risk or combinations thereof)”, paragraph [0118], “a risk score greater than a certain predetermined minimum threshold”; Okanoue: paragraph [0143], “a step of calculating a normalized score based on the quantity or quantities of the marker molecule or marker molecules before and after the application of the therapeutic drug and then determining that an effect of the application of the therapeutic drug”, paragraph [0363], “compare the index value determined by the normalization unit D2 with a reference value. The determination unit D4 is configured to determine the presence or absence of a hepatic disease based on the compared result”).
The motivation to combine is the same as in claim 1, incorporated herein.
Regarding (New) claim 21, Park Cha and Okanoue teach the limitations of claim 20, and further teach wherein the plurality of risk categories includes a gray zone category for intermediate risk levels that are not classified as low risk or high risk (Cha: paragraph [0104], “The risk categories may represent quantitative stratifications or groupings of a patient population and/or patient cohorts, wherein each category is associated with an identifier… the system may associate various qualitative descriptors with such risk categories (e.g., very low risk, low risk, medium risk, high risk, very high risk or combinations thereof)”).
The motivation to combine is the same as in claim 1, incorporated herein.
Regarding (New) claim 22, Park Cha and Okanoue teach the limitations of claim 1, and further teach wherein the pretreatment step generates seven index data from eleven data comprising the attribute data, physical finding data, and blood examination data, and wherein the seven index data comprise two physical scores and four functional scores assigned as independent variables in a decision tree for machine learning (Park: paragraph [0056], “state variables may be a living condition variable and a health condition variable of the subject including demographical characteristics… a physical activity, or nutrition, physical measurement values”; Cha: paragraphs [0077]-[0080], “system may also aggregate DP information into one of a number of comorbidity groups to be employed as features. Generally, such comorbidity groups may correspond to specific comorbidities included in the Elixhauser Comorbidity Index (“ECI”)”, paragraph [0136], “a significant renal function decline event 254… when a patient's eGFR value is determined to be less than a predetermined minimum value”; Okanoue: paragraph [0046], “the index value is calculated from normalized scores for the two groups by using any one of the following Decision trees 1 to 6”. With respect to the numbers of features chosen (i.e., seven and eleven), these numbers of features are a design choice in which the systems are capable of performing, and would be prima facie obvious to one of ordinary skill in the art to use as a design choice).
The motivation to combine is the same as in claim 1, incorporated herein.
Regarding (New) claim 23, Park Cha and Okanoue teach the limitations of claim 1, and further teach wherein the eleven data comprise age, sex, height, weight, waist circumference, aspartate aminotransferase (AST), alanine aminotransferase (ALT), gamma-glutamyl transferase (gamma-GTP), cholesterol, triglyceride, and platelet count (Park: paragraph [0025]-[0028], “state variables including at least five of age, an education level, a monthly average income, anemia, proteinuria, glucose in urine, cholesterol… a gender… a weight, a waist size, a hip circumference… ALT”, paragraph [0108], “γ-GTP… Triglyceride”, Table 6, “value C Triglyceride… γ-GTP”; Okanoue: paragraph [0024], “non-invasive markers (AST/ALT ratio”, paragraph [0066], “Platelet Ratio”).
The motivation to combine is the same as in claim 1, incorporated herein.
Regarding (New) claim 24, Park Cha and Okanoue teach the limitations of claim 1, and further teach wherein the estimated model is configured to distinguish between non-alcoholic fatty liver (NAFL) and non-alcoholic steatohepatitis (NASH) with fibrosis with at least 96% sensitivity and at least 99% specificity (Park: paragraph [0163], “the optimal cut-point, sensitivity, and specificity(validity) were confirmed”; Cha: paragraph [0153], “A number of metrics may be calculated to assess the performance of the disclosed models, including AUC of the ROC curve, sensitivity (recall), specificity and model coverage”, paragraph [0158], “at least about 96%... at least about 99%”; Okanoue: table 10, “Sensitivity 95% Specificity 95%”. With respect to the %’s chosen are a design choice in which the systems are capable of performing, and would be prima facie obvious to one of ordinary skill in the art to use as a design choice).
The motivation to combine is the same as in claim 1, incorporated herein.
Regarding (New) claim 31, Park Cha and Okanoue teach the limitations of claim 1, and further teach wherein the risk level evaluation step further comprises: calculating an output value from the estimated model; comparing the output value to a first threshold and a second threshold; classifying the subject as having a low risk level when the output value is less than the first threshold; classifying the subject as having an intermediate risk level when the output value is between the first threshold and the second threshold; and classifying the subject as having a high risk level when the output value is greater than the second threshold (Park: paragraph [0128], “The statistical probability model generating unit 130 classifies the risk evaluation result into the highest risk group, a high risk group, an intermediate risk group, and a low risk group to provide the risk evaluation result of the subject”; paragraph [0202], “the apparatus 100 for predicting a disease risk of metabolic disorders may predict a disease risk of the subject by applying a subject state variable and subject genetic information of the subject to the machine learning model”; Cha: paragraph [0119], “exceeds a certain threshold… risk score is below the threshold”, paragraph [0153], “summarizes the predictive performance across a full range of score thresholds”).
The motivation to combine is the same as in claim 1, incorporated herein.
Regarding (New) claim 32, Park Cha and Okanoue teach the limitations of claim 1, and further teach wherein the first threshold is 0.35 and the second threshold is 0.70, such that an output value less than 0.35 indicates non-alcoholic fatty liver (NAFL), an output value between 0.35 and 0.70 indicates a gray zone, and an output value greater than 0.70 indicates non-alcoholic steatohepatitis (NASH) (Okanoue: Park: paragraph [0128], “classifies the risk evaluation result into the highest risk group, a high risk group, an intermediate risk group, and a low risk group to provide the risk evaluation result of the subject”; paragraph [0001], “a method for discriminating between nonalcoholic fatty liver (NAFL) and nonalcoholic steatohepatitis (NASH)”, Table 25, “0.351… 0.711”. With respect to the values for the thresholds, these values are a design choice in which the systems are capable of performing, and would be prima facie obvious to one of ordinary skill in the art to use as a design choice. Additionally, The Examiner notes that “such that an output value less than 0.35 indicates non-alcoholic fatty liver (NAFL), an output value between 0.35 and 0.70 indicates a gray zone, and an output value greater than 0.70 indicates non-alcoholic steatohepatitis (NASH)” is an intended use of the various thresholds that is not required to occur. This feature has been fully considered by the Examiner; however, the limitation does not provide patentable distinction over the cited prior art because it is an intended use or result of the thresholds).
The motivation to combine is the same as in claim 1, incorporated herein.
REGARDING CLAIM(S) 35 and 38
Claim(s) 35 and 38 are analogous to Claim(s) 22, thus Claim(s) 35 and 38 are similarly analyzed and rejected in a manner consistent with the rejection of Claim(s) 22.
Claim(s) 5, 11 and 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent App. No. 2019/0172587 (hereafter “Park”), U.S. Patent App. No. 2020/0005900 (hereafter “Cha”) and U.S. Patent App. No. 20180100867 (hereafter “Okanoue”) as applied to claims 1, 6 and 7 above, and further in view of U.S. Patent App. No. 2015/0247149 (hereafter “Feldstein”).
Regarding (Currently Amended) claim 5, Park Cha and Okanoue teach the limitations of claim 1, and further teach wherein the estimated model generation step includes generating an estimated model for estimating the risk level of hepatic cancer by machine learning using (a) the attribute data including at least one selected from gender and age, (b) the physical finding data including at least one selected from height and weight, (c) the blood examination data including […] at least one selected from AST (GOT), ALT (GPT), gamma-GTP, PLT, T-Cho and TG, and (d) the diagnostic result of a doctor (Park: Figures 1-2, 10, paragraph [0012], “a machine learning model generating unit which generates a machine learning model which learns a degree of a relationship between at least one of a plurality of state variables and genetic information and a disease risk of metabolic disorders with the plurality of state variables including a living condition variable and a health condition variable of a patient with a metabolic disorder, generic information, and the disease risk of the metabolic disorders as input”, paragraphs [0025]-[0028], “the plurality of state variables including at least five of age… fatty liver… an uric acid level in blood… a gender an age… a past history of fatty liver… a weight, a waist size, a hip circumference, a pulse rate, a diastolic blood pressure, a systolic blood pressure, and a body mass index… ALT”, paragraphs [0058]-[0056], “The machine learning model generating unit 120 may have a plurality of state variables including a living condition variable and a health condition variable of a patient with a metabolic disorder, gene information, and a disease risk of metabolic disorders as inputs”, Table 1, “Liver function test (ALT)”; Okanoue: paragraph [0002], “When NASH has progressed, hepatic cirrhosis or liver cancer may be caused”, paragraph [0184], “It is known that NASH can cause hepatic cirrhosis or liver cancer when the symptoms have progressed”),
the risk level evaluation step includes obtaining the risk level of the hepatic cancer of the subject by inputting (a) the attribute data including at least one selected from gender and age of the subject, (b) the physical finding data including at least one selected from height and weight of the subject, and (c) the blood examination data including […] at least one selected from AST (GOT), ALT (GPT), gamma-GTP, PLT, T-Cho and TG of the subject, into the estimated model in the estimated model generation step (Park: Figures 1-2, 10, paragraph [0012], “a disease risk predicting unit which predicts a subject disease risk of the subject by applying the subject state variable and the subject genetic information of the subject to the machine learning model”, paragraphs [0025]-[0028], “the plurality of state variables including at least five of age… fatty liver… an uric acid level in blood… a gender an age… a past history of fatty liver… a weight, a waist size, a hip circumference, a pulse rate, a diastolic blood pressure, a systolic blood pressure, and a body mass index… ALT”, paragraph [0202], “the apparatus 100 for predicting a disease risk of metabolic disorders may predict a disease risk of the subject by applying a subject state variable and subject genetic information of the subject to the machine learning model”, Table 1, “Liver function test (ALT)”; Okanoue: paragraph [0002], “When NASH has progressed, hepatic cirrhosis or liver cancer may be caused”, paragraph [0184], “It is known that NASH can cause hepatic cirrhosis or liver cancer when the symptoms have progressed”).
Park Cha and Okanoue may not explicitly teach (underlined below for clarity):
wherein the estimated model generation step includes generating an estimated model for estimating the risk level of hepatic cancer by machine learning using (a) the attribute data including at least one selected from gender and age, (b) the physical finding data including at least one selected from height and weight, (c) the blood examination data including AIM and at least one selected from AST (GOT), ALT (GPT), gamma-GTP, PLT, T-Cho and TG, and (d) the diagnostic result of a doctor, the risk level evaluation step includes obtaining the risk level of the hepatic cancer of the subject by inputting (a) the attribute data including at least one selected from gender and age of the subject, (b) the physical finding data including at least one selected from height and weight of the subject, and (c) the blood examination data including AIM and at least one selected from AST (GOT), ALT (GPT), gamma-GTP, PLT, T-Cho and TG of the subject, into the estimated model in the estimated model generation step.
Feldstein teaches wherein the estimated model generation step includes generating an estimated model for estimating the risk level of hepatic cancer by machine learning using (a) the attribute data including at least one selected from gender and age, (b) the physical finding data including at least one selected from height and weight, (c) the blood examination data including AIM and at least one selected from AST (GOT), ALT (GPT), gamma-GTP, PLT, T-Cho and TG, and (d) the diagnostic result of a doctor (Feldstein: paragraph [0044], “detect or monitor the progression of other forms of liver disease, besides NAFLD, such as... cancer of the liver”, paragraph [0093], “The analytical process may be any type of learning algorithm with defined parameters, or in other words, a predictive model. Predictive models can be developed for a variety of NAFLD classifications by applying learning algorithms to the appropriate type of reference or control data. Multivariable modeling can be applied to generate a risk score for diagnosing NASH. A risk score can be derived”, paragraph [0239], “These results suggest that the circulating EVs carry a variety of different proteins, different in molecular function and biological process, and that reflect the pathological progression of NASH”, Table 3, “CD5L... CD5 antigen-like”. The Examiner notes use of CD5L is AIM (apoptosis inhibitor expressed bt macrophage) under the broadest reasonable interpretation),
the risk level evaluation step includes obtaining the risk level of the hepatic cancer of the subject by inputting (a) the attribute data including at least one selected from gender and age of the subject, (b) the physical finding data including at least one selected from height and weight of the subject, and (c) the blood examination data including AIM and at least one selected from AST (GOT), ALT (GPT), gamma-GTP, PLT, T-Cho and TG of the subject, into the estimated model in the estimated model generation step (Feldstein: paragraph [0007], “a method of detecting, predicting, monitoring, assessing diagnosing and treating liver damage associated with nonalcoholic fatty acid liver disease (NAFLD) in a subject, comprising: a) obtaining a biological sample of the subject... deriving a risk score”, paragraph [0044], “detect or monitor the progression of other forms of liver disease, besides NAFLD, such as... cancer of the liver”, paragraph [0093], “Multivariable modeling can be applied to generate a risk score for diagnosing NASH. A risk score can be derived”, paragraph [0239], “These results suggest that the circulating EVs carry a variety of different proteins, different in molecular function and biological process, and that reflect the pathological progression of NASH”, Table 3, “CD5L... CD5 antigen-like”. The Examiner notes use of CD5L is AIM (apoptosis inhibitor expressed bt macrophage) under the broadest reasonable interpretation).
It would have been prima facie obvious to one of ordinary skill in the art at the time of the invention was made to combine the noted features of use of AIM within use of a machine learning model for determination of risk of liver cancer as taught by Feldstein within teaching of training and using machine learning models for determination of risk of liver cancer as taught by Park Cha and Okanoue since the combination of the two references is merely simple substitution of one known element for another producing a predictable result (KSR rationale B). Since each individual element and its function are shown in the prior art, albeit shown in separate references, the difference between the claimed subject matter and the prior art rests not on any individual element or function but in the very combination itself—that is, in the substitution of the use of AIM with a machine learning model for risk of liver cancer as taught by Feldstein for the using machine learning models for determination of risk of liver cancer as taught by Park Cha and Okanoue. Thus, the simple substitution of one known element for another producing a predictable result renders the claim obvious.
REGARDING CLAIM(S) 11 and 15
Claim(s) 11 and 15 are analogous to Claim(s) 5, thus Claim(s) 11, and 15 is/are similarly analyzed and rejected in a manner consistent with the rejection of Claim(s) 5.
Claim(s) 17, 25-27, 33, 36 and 39 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent App. No. 2019/0172587 (hereafter “Park”), U.S. Patent App. No. 2020/0005900 (hereafter “Cha”) and U.S. Patent App. No. 20180100867 (hereafter “Okanoue”) as applied to claim 1 above, and further in view of U.S. Patent App. No. 20170138967 (hereafter “Abdelmalek”).
Regarding (New) claim 17, Park Cha and Okanoue teach the limitations of claim 1, and but may not explicitly wherein the estimated model generation step further comprises generating a plurality of estimated models corresponding to different fibrosis stages, each estimated model configured for a binary classification between different fibrosis stage groupings.
Abdelmalek teaches wherein the estimated model generation step further comprises generating a plurality of estimated models corresponding to different fibrosis stages, each estimated model configured for a binary classification between different fibrosis stage groupings (Abdelmalek: paragraph [0071], “First, Sparse logistic regression (Least Absolute Shrinkage and Selection Operator—LASSO), was used as a classification model for different binary partitions of fibrosis stage (e.g., 0,1,2, vs. 3,4). Second, we directly modeled fibrosis stage as an ordinal variable using sparse ordinal regression”, paragraphs [0090]-[0084], “We built sparse logistic regression models based on metabolic data to predict three distinct binary stratifications of fibrosis stage, namely, mild vs. advanced (B1: stage 0,1 vs. 3,4), mild/intermediate vs. advanced (B2: stage 0,1,2 vs. 3,4) and mild vs. intermediate/advanced (B3: stage 0,1 vs. 2,3,4). These specific strata were based on predictors which”. The Examiner notes these are machine learning models).
One of ordinary skill in the art before the effective filing date would have found it obvious to include using various binary classification models for fibrosis stage as taught by Abdelmalek with the liver disease risk evaluation as taught by Park Cha and Okanoue with the motivation of “reduce, inhibit, ameliorate and/or improve the onset of the symptoms or complications, alleviating the symptoms or complications of the tumor, or eliminating liver disease or liver fibrosis” (Abdelmalek: paragraph [0048]).
Regarding (New) claim 25, Park Cha and Okanoue teach the limitations of claim 1, but may not explicitly teach wherein generating the estimated model for estimating the risk level of hepatic fibrosis comprises generating a plurality of binary classification models including: a first binary classification model for distinguishing between F0 and Fl-4 fibrosis stages, a second binary classification model for distinguishing between F0-1 and F2-4 fibrosis stages, and a third binary classification model for distinguishing between F0-2 and F3-4 fibrosis stages.
Abdelmalek teaches wherein generating the estimated model for estimating the risk level of hepatic fibrosis comprises generating a plurality of binary classification models including: a first binary classification model for distinguishing between F0 and Fl-4 fibrosis stages, a second binary classification model for distinguishing between F0-1 and F2-4 fibrosis stages, and a third binary classification model for distinguishing between F0-2 and F3-4 fibrosis stages (Abdelmalek: paragraph [0071], “First, Sparse logistic regression (Least Absolute Shrinkage and Selection Operator—LASSO), was used as a classification model for different binary partitions of fibrosis stage (e.g., 0,1,2, vs. 3,4). Second, we directly modeled fibrosis stage as an ordinal variable using sparse ordinal regression”, paragraphs [0090]-[0084], “We built sparse logistic regression models based on metabolic data to predict three distinct binary stratifications of fibrosis stage, namely, mild vs. advanced (B1: stage 0,1 vs. 3,4), mild/intermediate vs. advanced (B2: stage 0,1,2 vs. 3,4) and mild vs. intermediate/advanced (B3: stage 0,1 vs. 2,3,4). These specific strata were based on predictors which”).
The motivation to combine is the same as in claim 17, incorporated herein.
Regarding (New) claim 26, Park Cha, Okanoue and Abdelmalek teach the limitations of claim 1, and further teach wherein the estimated model generation step includes the blood examination data further comprising Type 4 collagen 7S (T4C7S) levels, and wherein the pretreatment step generates index data including at least one fibrosis-specific index from the Type 4 collagen data (Okanoue: paragraph [0003], “type IV collagen 7S”, paragraph [0011], “COL4-7S”).
The motivation to combine is the same as in claim 17, incorporated herein.
Regarding (New) claim 27, Park Cha, Okanoue and Abdelmalek teach the limitations of claim 1, and further teach wherein the estimated model for estimating the risk level of hepatic fibrosis is configured to distinguish between FO and Fl-4 fibrosis stages with at least 96% sensitivity and at least 86% specificity (Park: paragraph [0163], “the optimal cut-point, sensitivity, and specificity(validity) were confirmed”; Cha: paragraph [0153], “A number of metrics may be calculated to assess the performance of the disclosed models, including AUC of the ROC curve, sensitivity (recall), specificity and model coverage”, paragraph [0158], “at least about 96%... at least about 99%”; Okanoue: table 10, “Sensitivity 95% Specificity 95%”. With respect to the %’s chosen are a design choice in which the systems are capable of performing, and would be prima facie obvious to one of ordinary skill in the art to use as a design choice).
The motivation to combine is the same as in claim 17, incorporated herein.
Regarding (New) claim 33, Park Cha and Okanoue teach the limitations of claim 1, but may nor teach explicitly teach wherein generating the estimated model for estimating the risk level of hepatic fibrosis comprises generating three binary classification models each having a threshold of 0.5, such that an output value less than 0.5 indicates a negative classification and an output value of 0.5 or greater indicates a positive classification for the respective fibrosis stage grouping.
Abdelmalek teaches wherein generating the estimated model for estimating the risk level of hepatic fibrosis comprises generating three binary classification models each having a threshold of 0.5, such that an output value less than 0.5 indicates a negative classification and an output value of 0.5 or greater indicates a positive classification for the respective fibrosis stage grouping (Abdelmalek: paragraph [0071], “First, Sparse logistic regression (Least Absolute Shrinkage and Selection Operator—LASSO), was used as a classification model for different binary partitions of fibrosis stage (e.g., 0,1,2, vs. 3,4). Second, we directly modeled fibrosis stage as an ordinal variable using sparse ordinal regression”, paragraphs [0090]-[0084], “We built sparse logistic regression models based on metabolic data to predict three distinct binary stratifications of fibrosis stage, namely, mild vs. advanced (B1: stage 0,1 vs. 3,4), mild/intermediate vs. advanced (B2: stage 0,1,2 vs. 3,4) and mild vs. intermediate/advanced (B3: stage 0,1 vs. 2,3,4), Table 1, “0.5”. With respect to the values for the thresholds, these values are a design choice in which the systems are capable of performing, and would be prima facie obvious to one of ordinary skill in the art to use as a design choice. Additionally, The Examiner notes that “such that an output value less than 0.5 indicates a negative classification and an output value of 0.5 or greater indicates a positive classification for the respective fibrosis stage grouping” is an intended use of the various thresholds that is not required to occur. This feature has been fully considered by the Examiner; however, the limitation does not provide patentable distinction over the cited prior art because it is an intended use or result of the thresholds).
The motivation to combine is the same as in claim 28, incorporated herein.
REGARDING CLAIM(S) 36 and 39
Claim(s) 36 and 39 are analogous to Claim(s) 25, thus Claim(s) 36 and 39 are similarly analyzed and rejected in a manner consistent with the rejection of Claim(s) 25.
Claim(s) 28-30, 37 and 40 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent App. No. 2019/0172587 (hereafter “Park”), U.S. Patent App. No. 2020/0005900 (hereafter “Cha”) and U.S. Patent App. No. 20180100867 (hereafter “Okanoue”) as applied to claim 1 above, and further in view of U.S. Patent App. No. 20190298204 (hereafter “Fontanarava”).
Regarding (New) claim 28, Park Cha and Okanoue teach the limitations of claim 1, and further teach wherein the main processing step comprises a multilayer perceptron with [… a …] hidden layers, and wherein the machine learning employs a sigmoid activation function and […] as a loss function (Park: paragraphs [0063]-[0064], “The machine learning model generating unit 120 may additionally connect the multi-layer perceptron neural network to a last layer of the existing recurrent neural network to collectively input the genetic information collected at the single timing”; Cha: paragraph [0093], “activation functions”; Okanoue: paragraph [0204], “Examples of the method for converting the distribution of the normalized data include conversion with a logarithmic function and conversion with a sigmoid function”).
Park Cha and Okanoue may not explicitly teach (underlined below for clarity):
wherein the main processing step comprises a multilayer perceptron with two hidden layers, and wherein the machine learning employs a sigmoid activation function and binary cross entropy as a loss function.
Fontanarava teaches wherein the main processing step comprises a multilayer perceptron with two hidden layers, and wherein the machine learning employs a sigmoid activation function and binary cross entropy as a loss function (Fontanarava: paragraph [0096], “Segmentation neural network NN.sub.2 27 also may include multiple hidden layers such as convolutional layers, pooling layers, fully connected layers and normalization layers”, paragraph [0106], “a binary cross-entropy”).
One of ordinary skill in the art before the effective filing date would have found it obvious to include using multiple hidden layers and entropy as taught by Fontanarava with the loss functions and mulit-layer perceptron as taught by Park Cha and Okanoue with the motivation of “improves the artificial neural network's performance” (Fontanarava: paragraph [0037]).
Regarding (New) claim 29, Park Cha, Okanoue and Fontanarava teach the limitations of claim 28, and further teach wherein the main processing step further comprises training the multilayer perceptron by repeating backpropagation of teacher data associated with the input layer for a plurality of training epochs until convergence, thereby improving learning accuracy (Park: paragraph [0075]-[0076], “Equation 3 is an error equation of the machine learning model generating unit 120 and learns a weight of the artificial neural network through a backpropagation algorithm… the machine learning model generating unit 120 divides patients (all subjects) with the metabolic disorders into three groups to verify the specificity(validity) of the constructed machine learning model (for example, the artificial neural network) to perform cross validation”, paragraph [0084], “the basic statistical probability model generating unit 131 may divide the subjects into a training set and a test set”).
The motivation to combine is the same as in claim 28, incorporated herein.
Regarding (New) claim 30, Park Cha, Okanoue and Fontanarava teach the limitations of claim 28, and further teach wherein the plurality of training epochs comprises 324 epochs with teacher data (Park: paragraph [0075]-[0076], “divides patients (all subjects) with the metabolic disorders into three groups to verify the specificity(validity) of the constructed machine learning model (for example, the artificial neural network) to perform cross validation”, paragraph [0084], “the basic statistical probability model generating unit 131 may divide the subjects into a training set and a test set”. With respect to the numbers of epochs chosen, this number is a design choice in which the systems are capable of performing, and would be prima facie obvious to one of ordinary skill in the art to use as a design choice).
The motivation to combine is the same as in claim 28, incorporated herein.
REGARDING CLAIM(S) 37 and 40
Claim(s) 37 and 40 are analogous to Claim(s) 28, thus Claim(s) 37 and 40 are similarly analyzed and rejected in a manner consistent with the rejection of Claim(s) 28.
Claim(s) 34 is/are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent App. No. 2019/0172587 (hereafter “Park”), U.S. Patent App. No. 2020/0005900 (hereafter “Cha”) and U.S. Patent App. No. 20180100867 (hereafter “Okanoue”) as applied to claim 1 above, and further in view of U.S. Patent App. No. 20170172120 (hereafter “Miyazaki”).
Regarding (New) claim 34, Park Cha and Okanoue teach the limitations of claim 1, and further teach […] wherein the estimated model generation step generates an estimated model for estimating the risk level of hepatic cancer (Park: paragraph [0009], “predicting a disease risk”; Okanuoue: paragraph [0002], “NASH has progressed, hepatic cirrhosis or liver cancer may be caused”).
Park Cha and Okanoue may not explicitly teach (underlined below for clarity):
wherein the blood examination data includes AIM selected from Total-AIM and Free-AIM, and wherein the estimated model generation step generates an estimated model for estimating the risk level of hepatic cancer.
Miyazaki teaches wherein the blood examination data includes AIM selected from Total-AIM and Free-AIM, and wherein the estimated model generation step generates an estimated model for estimating the risk level of hepatic cancer (Miyazaki: paragraph [0013], “a measurement method of the AIM concentration is an immunological method using an anti-AIM antibod”, paragraph [0088], “AIM is in a free form”).
One of ordinary skill in the art before the effective filing date would have found it obvious to include using AIM as taught by Miyazaki with the estimation of hepatic cancer risk as taught by Park Cha and Okanoue with the motivation of “fibrosis of kidney parenchyma and glomerulus associated therewith are obviously improved” (Miyazaki: paragraph [0193]).
Response to Arguments
Applicant's arguments filed 21 March 2026 have been fully considered but they are not persuasive. Applicants’ arguments will be addressed herein below in the order in which they appear in the response filed on 21 March 2026.
Drawings
The submitted drawing on 21 March 2026 do not cure any of the objections and appear to be the same images originally submitted on 26 January 2023, the Examiner is not able to make out the details of the various numbers in the various figures due to the quality, therefore the objection is maintained.
With respect to figures 15-25 as per MPEP 608.02(t), the figures filed on 03 March 2026 cancel the respective drawings.
Rejections under 35 U.S.C. § 101
Regarding claims 1, 3, 5-15, the Examiner has considered the Applicant’s arguments but does not find them persuasive. Any arguments inadvertently not addressed are unpersuasive for at least the following reasons:
Applicant argues:
Regarding Step 2A Prong One, the Office characterized the claims as directed to an abstract idea, but Applicant respectfully submits that claim 1 does not fall within any of the 2019 PEG's enumerated abstract idea groupings… Second, the claims are not directed to a method of organizing human activity… The claimed steps - generating an estimated model by machine learning, performing a pretreatment step to generate index data executing a main processing step using a hybrid input layer, and evaluating risk levels - are technical operations on data, not steps for organizing human activity. There is no management of human behavior, no commercial interaction, and no interpersonal activity recited… even assuming arguendo the claims touch on an abstract idea, they integrate it into a practical application. The specification identifies a concrete technical problem in the field of medical diagnostics… even assuming arguendo the claims touch on an abstract idea, they integrate it into a practical application. The specification identifies a concrete technical problem in the field of medical diagnostics. Paragraph [0061]… These are technical shortcomings of existing diagnostic methods that the claimed subject matter addresses… Claim 1 provides a specific technical solution to this problem. Paragraph [0062]… The claimed subject matter is also analogous to subject matter that the USPTO has identified as eligible in its published guidance. For example, in the 2019 PEG, Example 39… Additionally, claim 1 adds specific, unconventional limitations that confine any alleged exception to a particular useful application…. This specific combination of biomarkers is not arbitrary - it is derived from the technical analysis in the specification… Regarding preemption, the claims are narrowly tailored. They do not preempt all machine learning for liver disease diagnosis - only the specific hybrid input architecture using the recited biomarkers.
The Examiner respectfully disagrees.
It is respectfully submitted, that evaluation of liver disease risk is an activity that is performed by a care provider for a patient (i.e., a human activity), the claims collect, organize and output data for a human user to interact with via the generic computer components in their evaluation and care they provide a patient, which as stated in in 2106.04(a)(2), “certain activity between a person and a computer… may fall within the “certain methods of organizing human activity” grouping”. The claim is directed toward organizing how a care provider and patient interact with various computer components to organize data for an evaluation of liver disease risk and is an abstract idea.
Applicant’s specification does not recite a technical problem rooted in computer hardware technology, Applicant argues paragraph [0061], however the argued paragraph at best recites human activity problems of liver disease evaluation, the Examiner notes it is not a computer rooted problems to assess liver disease risk this is a human activity problem involving a care provider and a patient, in which generic computer components and computer techniques are being generally linked to a human activity problem. The claims may improve upon the abstract idea of determination of risk for a disease for a patient nevertheless an improved abstract is still an abstract idea as such the claim is not subject matter eligible.
With respect to claim 39, claim 39 is directed solely at training of a neural network and is not applicable to Applicant’s claim in which a generic off-the-shelf model is trained and used to perform an abstract idea of patient risk assessment. With respect to the labels of the data used, these are not additional elements and are not capable of providing a practical application. Applicant’s claimed additional elements do not recite a technical solution to a technical problem rooted in Applicant specification and is not subject matter eligible.
Rejections under 35 U.S.C. § 103
Regarding the rejection of claim 1-15, the Examiner has considered the applicant’s arguments; however, the arguments are not persuasive as addressed herein. Any arguments inadvertently not addressed are unpersuasive for at least the following reasons:
Applicant argues:
However, the Office failed to provide evidence that Cha utilizes "the index data calculated in the pretreatment step as an input layer," as recited in claim 1… The Office Action relies on Cha for teaching the pretreatment step and indexing. However, Cha's preprocessing is directed to data cleaning and standardization, not the generation of derived index data used together with raw data as an input layer… The claimed subject matter requires a specific technical architecture: the pretreatment step generates index data, and then the main processing step uses both the original raw data (attribute data, physical finding data, and blood examination data) AND the derived index data together as an input layer. This is not merely generic preprocessing - but is a particular way of structuring machine learning inputs that, as the specification demonstrates, improves learning accuracy… The claimed subject matter requires a specific technical architecture: the pretreatment step generates index data, and then the main processing step uses both the original raw data (attribute data, physical finding data, and blood examination data) AND the derived index data together as an input layer. This is not merely generic preprocessing - but is a particular way of structuring machine learning inputs that, as the specification demonstrates, improves learning accuracy…. For at least the following reasons, the applied references fail to establish a prima facie case of obviousness with respect to claim 1. First, Park fails to teach the pretreatment step of generating index data. Second, Cha's preprocessing is directed to data cleaning and standardization, not generating index data to be used together with raw data as an input layer. Cha teaches away from preserving raw data alongside derived features, as its preprocessing replaces raw data with cleaned data. Third, even if Okanoue teaches hepatic fibrosis risk evaluation (which Applicant does not concede), it does not teach the specific hybrid input architecture of using both raw data and derived index data together as an input layer. Fourth, there is no motivation to combine these references to arrive at the claimed subject matter.
The Examiner respectfully disagrees.
It is respectfully submitted, that the combination of Cha within Park teaches the argued use of both indexed and acquired data, in particular Applicant has not explicitly defined the index created, therefore the Examiner must treat the index under the broadest reasonable interpretation, in which in combination an index is created and used with the acquired data as input to a ML model (see above but at least Cha: paragraphs [0063] and [0080]). Finally, it would be prima facie obvious to combine the teachings of Okanoue directed at use of hepatic fibrosis (see above but at least paragraphs [0363]-[0366]), with the motivation of “provide a noninvasive method for determining the disease type or determining the presence of a symptom of a hepatic disease such as nonalcoholic fatty liver disease with a higher diagnostic accuracy” and “improvement of the accuracy” (Okanoue: paragraphs [0009] and [0336]. Also see, paragraph [0002]).
In addition, the Examiner respectfully notes that the cited reference was never applied as a reference under 35 U.S.C. 102 against the pending claims. As such, the Examiner respectfully submits that the issue at hand is not whether the applied prior art specifically teaches the claimed features, per se, but rather, whether or not the prior art, when taken in combination with the knowledge of average skill in the art, would put the artisan in possession of these features. Regarding this issue, it is well established that references are evaluated by what they suggest to one versed in the art, rather than by their specific disclosures, In re Bozek, 163 USPQ 545 (CCPA 1969). The issue of obviousness is not determined by what the references expressly state but by what they would reasonably suggest to one of ordinary skill in the art, as supported by decisions in In re DeLisle 406 Fed 1326, 160 USPQ 806; In re Kell, Terry and Davies 208 USPQ 871; and In re Fine, 837 F.2d 1071, 1074, 5 USPQ 2d 1596, 1598 (Fed. Cir. 1988) (citing In re Lalu, 747 F.2d 703, 705, 223 USPQ 1257, 1258 (Fed. Cir. 1988)). Further, it was determined in In re Lamberti et al, 192 USPQ 278 (CCPA) that:
(i) obviousness does not require absolute predictability;
(ii) non-preferred embodiments of prior art must also be considered; and
(iii) the question is not express teaching of references, but what they would suggest.
According to In re Jacoby, 135 USPQ 317 (CCPA 1962), the skilled artisan is presumed to know something more about the art than only what is disclosed in the applied references. In In re Bode, 193 USPQ 12 (CCPA 1977), every reference relies to some extent on knowledge of persons skilled in the art to complement that which is disclosed therein.
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 Andrew E Lee whose telephone number is (571)272-8323. The examiner can normally be reached M-Th 9-5:00 PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Shahid Merchant can be reached on 571-270-1360. 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.
/A.E.L./Examiner, Art Unit 3684
/Shahid Merchant/Supervisory Patent Examiner, Art Unit 3684
Prosecution Insights