DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
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.
Response to Amendment
This is a response to Applicant’s amendment filed on 22 October 2025, wherein:
Claims 1, 3-6, 8-10, 13, 14, and 16-19 are amended.
Claims 2, 7, 11, 12, and 15 are original.
Claim 20 is new.
Claims 1-20 are pending.
Claim Objections
Claims 1-20 are objected to because of the following informalities:
Claims 1, 18, and 19 each include at least one amendment that does not conform with the guidance provided in MPEP 714. In particular, claim 1 is missing text that were in the preceding iteration (i.e., the originally filed claims). They should be in the amended claim with appropriate markings. Additionally, the addition of a single character is difficult to perceive (found in at least claims 1, 18, and 19). Hence the guidance “extra portions of text may be included before and after text being deleted, all in strike-through, followed by including and underlining the extra text with the desired change (e.g., number 14 as).” See MPEP 714(II)(C).
Claims 1 and 5 inconsistently lump multiple limitations together while others are separated and begin on a new line.
Dependent claims 2-17 and 20 inherit the deficiencies of their respective parent claims, and are thus objected to under the same rationale.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The text of those sections of Title 35, U.S. Code 112(b) not included in this action can be found in a prior Office action.
Claims 1-20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Regarding claim 1, it is unclear how the pretrained learning was claimed to be trained. In particular, the new limitation recites “the pretrained learning model having been trained by performing recursive feature eliminations on a plurality of cross-validated random forests on a training data set”. This is grammatically incorrect. In particular, were (1) the recursive feature eliminations performed on a plurality of cross-validated random forests, (2) the recursive feature eliminations performed on a training data set, (3) the recursive feature eliminations performed on a plurality of cross-validated random forests of a training data set, or (4) the recursive feature eliminations performed in a plurality of cross-validated random forests on a training data set? (Bolded and underlined for emphasis). Thus, one of ordinary skill in the art would not be apprised of the metes and bounds of the patent protection sought. Dependent claims 2-17 and 20 inherit the deficiencies of their respective parent claims, and are thus rejected under the same rationale.
Regarding claims 6 and 7, each of these claims recite “the at least one composite score”. However, in claim 5, the second limitation recites “combining the plurality of individual metrics into at least one composite score; aggregating the at least one composite score to determine a DCR score” while the last limitation recites “combining the DCR score with the collected performance parameters and the plurality of responses resulting in at least one composite score.” Therefore, there are two separate scores that are each called “at least one composite score” in claim 5. It is unclear which “at least one composite score” each recitation of the term in each of claims 6 and 7 is referring to. Thus, one of ordinary skill in the art would not be apprised of the metes and bounds of the patent protection sought. Dependent claim 7 inherits the deficiencies of its respective parent claims, and is thus rejected under the same rationale.
Regarding claims 18 and 19, each of these claims recites the new limitation “the pretrained learning model having been trained by performing recursive feature eliminations on a plurality of cross-validated random forest training data set”. This is grammatically incorrect. In particular, it is unclear what “a plurality of cross-validated random forest training data set” is and how recursive feature eliminations can be performed on it given its grammatically unclear status. It is further unclear how a singular “cross-validated random forest training data set” is a plurality. Thus, one of ordinary skill in the art would not be apprised of the metes and bounds of the patent protection sought.
The text of those sections of Title 35, U.S. Code 112(a) not included in this action can be found in a prior Office action.
Claims 1-20 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Regarding claims 1-5 and 18-20, the disclosure fails to provide sufficient written description for “providing the collected performance parameters and the plurality of responses to a pretrained machine learning model, the pretrained learning model having been trained by performing recursive feature eliminations on a plurality of cross-validated random forests on a training data set; receiving, from the pretrained machine learning model, a predicted likelihood of the patient having an impairment in daily activity; thresholding the predicted likelihood to thereby determine a functional impairment status of the patient in daily activity” in claims 1, 18, and 19, “wherein the machine learning model is a random forest classifier” in claim 2, “providing a likelihood of a functional deficit based on the functional impairment status” in claim 3, “wherein the battery of assessments includes at least a digital clock and recall (DCR) assessment, a lifestyle and health questionnaire, and/or a functional activity questionnaire” in claim 4, “combining the plurality of individual metrics into at least one composite score; aggregating the at least one composite score to determine a DCR score; and combining the DCR score with the collected performance parameters and the plurality of responses resulting in at least one composite score” in claim 5, and “wherein training the pretrained learning model further comprises using a Poisson regression” in claim 20 to show one of ordinary skill in the art that Applicant had possession of the claimed invention. Claims may lack written description when the claims define the invention in functional language specifying a desired result but the specification does not sufficiently describe how the function is performed or the result is achieved. For software, this can occur when the algorithm or steps/procedure for performing the computer function are not explained at all or are not explained in sufficient detail (simply restating the function recited in the claim is not necessarily sufficient). In other words, the algorithm or steps/procedure taken to perform the function must be described with sufficient detail so that one of ordinary skill in the art would understand how the inventor intended the function to be performed. It is not enough that one skilled in the art could write a program to achieve the claimed function because the specification must explain how the inventor intends to achieve the claimed function to satisfy the written description requirement. See MPEP 2161.01(I). In particular, the specification merely recites similar language as the claim without any meaningful description. See, for example, at least para. 40 and 42-44 which provide the most information yet recite that the functions are performed in results-based language as they summarize a study. For instance, while these paragraphs identify that random forests algorithms were used, which random forest algorithms and the parameters of such algorithms are not provided. Therefore, the disclosure at best merely recites that these limitations are performed in results-based language without providing the necessary description of the steps, calculations, or algorithms for performing the claimed functionality. Dependent claims 2-17 and 20 inherit the deficiencies of their respective parent claims, and are thus rejected under the same rationale.
Regarding claim 16, the originally filed disclosure is silent regarding the new limitation “determining a need for additional testing for a patient, based on the functional impairment status of the patient”. There are two statutory provisions that prohibit the introduction of new matter. The first provision is 35 USC 132, which provides that no amendment shall introduce new matter into the disclosure of the invention. If new matter is added to the claims, the examiner should reject the claims under 35 USC 112(a) – written description requirement. See MPEP 2163.06. Claims may lack written description when the claims define the invention in functional language specifying a desired result but the specification does not sufficiently describe how the function is performed or the result is achieved. For software, this can occur when the algorithm or steps/procedure for performing the computer function are not explained at all or are not explained in sufficient detail (simply restating the function recited in the claim is not necessarily sufficient). In other words, the algorithm or steps/procedure taken to perform the function must be described with sufficient detail so that one of ordinary skill in the art would understand how the inventor intended the function to be performed. It is not enough that one skilled in the art could write a program to achieve the claimed function because the specification must explain how the inventor intends to achieve the claimed function to satisfy the written description requirement. See MPEP 2161.01(I). In particular, Applicant asserts in pg. 11-12 of the Remarks filed 22 October 2025 that para. 37 and 40 of the specification provide particular support for this newly added limitation. However, para. 37 and 40 are particularly silent regarding “determining a need for additional testing for a patient”, let alone determining the need “based on the functional impairment status of the patient”. Thus, this is new matter.
Regarding claim 17, the disclosure fails to provide sufficient written description for “determining an ability to perform instrumental activities of daily living for a patient, based on the functional impairment status of the patient” to show one of ordinary skill in the art that Applicant had possession of the claimed invention. Claims may lack written description when the claims define the invention in functional language specifying a desired result but the specification does not sufficiently describe how the function is performed or the result is achieved. For software, this can occur when the algorithm or steps/procedure for performing the computer function are not explained at all or are not explained in sufficient detail (simply restating the function recited in the claim is not necessarily sufficient). In other words, the algorithm or steps/procedure taken to perform the function must be described with sufficient detail so that one of ordinary skill in the art would understand how the inventor intended the function to be performed. It is not enough that one skilled in the art could write a program to achieve the claimed function because the specification must explain how the inventor intends to achieve the claimed function to satisfy the written description requirement. See MPEP 2161.01(I). In particular, Applicant asserts in pg. 12 of the Remarks filed 22 October 2025 that para. 37 and 40 of the specification provide particular support for this newly added limitation. However, para. 40 is particularly silent regarding this limitation and para. 37 merely recites, in results-based language, that “embodiments of the present disclosure detect iADLs [instrumental activities of daily living] in older adults from the Functional Activities Questionnaire (FAQ) or similar instrument”. Therefore, the disclosure at best merely recites that this limitation is performed in results-based language without providing the necessary description of the steps, calculations, or algorithms for performing the claimed functionality.
Regarding new claim 20, the originally filed disclosure is silent regarding “wherein training the pretrained learning model further comprises using a Poisson regression”. There are two statutory provisions that prohibit the introduction of new matter. The first provision is 35 USC 132, which provides that no amendment shall introduce new matter into the disclosure of the invention. If new matter is added to the claims, the examiner should reject the claims under 35 USC 112(a) – written description requirement. See MPEP 2163.06. Claims may lack written description when the claims define the invention in functional language specifying a desired result but the specification does not sufficiently describe how the function is performed or the result is achieved. For software, this can occur when the algorithm or steps/procedure for performing the computer function are not explained at all or are not explained in sufficient detail (simply restating the function recited in the claim is not necessarily sufficient). In other words, the algorithm or steps/procedure taken to perform the function must be described with sufficient detail so that one of ordinary skill in the art would understand how the inventor intended the function to be performed. It is not enough that one skilled in the art could write a program to achieve the claimed function because the specification must explain how the inventor intends to achieve the claimed function to satisfy the written description requirement. See MPEP 2161.01(I). In particular, Applicant asserts in pg. 8 of the Remarks filed 22 October 2025 that para. 42-44 of the specification provide particular support for this newly added claim. However, the only mention of using a Poisson regression is found in para. 44, para. 42 and 43 are silent regarding using a Poisson regression. However, para. 44 only recites that a Poisson regression was used to analyze the results of a study, not in training the pretrained model. Thus, this is new matter.
Claim Rejections - 35 USC § 101
The text of those sections of Title 35, U.S. Code 101 not included in this action can be found in a prior Office action.
Claims 1-20 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 including additional elements that are sufficient to amount to significantly more than the judicial exception itself.
Step 1
The instant claims are directed to method and products which fall under at least one of the four statutory categories (STEP 1: YES).
Step 2A, Prong 1
Independent claim 1 recites:
A method for predicting a functional impairment status, comprising:
administering a battery of assessments to a patient, and receiving a plurality of responses thereto;
collecting performance parameters based on the patient's performance on the battery of assessments;
providing the collected performance parameters and the plurality of responses to a pretrained machine learning model, the pretrained model having been trained by performing recursive feature eliminations on a plurality of cross-validated random forests on a training data set;
receiving, from the pretrained machine learning model, a predicted likelihood of the patient having an impairment in daily activity; thresholding the predicted likelihood to thereby determine a functional impairment status of the patient in daily activity; and
outputting the functional impairment status.
Independent claim 18 recites:
A system for predicting an impairment status, the system comprising:
a computing node comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor of the computing node to cause the processor to perform a method comprising:
administering a battery of assessments to a patient, and receiving a plurality of response thereto;
collecting performance parameters based on the patient's performance on the battery of assessments;
providing the collected performance parameters and the plurality of responses to a pretrained machine learning model, the pretrained model having been trained by performing recursive feature eliminations on a plurality of cross-validated random forest training data set;
receiving, from the pretrained machine learning model, a predicted likelihood of the patient having an impairment in daily activity;
thresholding the predicted likelihood to thereby determine a functional impairment status of the patient in daily activity; and
outputting the cognitive impairment status.
Independent claim 19 recites:
A computer program product for predicting an impairment status, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform a method comprising:
administering a battery of assessments to a patient, and receiving a plurality of response thereto;
collecting performance parameters based on the patient's performance on the battery of assessments;
providing the collected performance parameters and the plurality of responses to a pretrained machine learning model, the pretrained model having been trained by performing recursive feature eliminations on a plurality of cross-validated random forest training data set;
receiving, from the pretrained machine learning model, a predicted likelihood of the patient having an impairment in daily activity;
thresholding the predicted likelihood to thereby determine a functional impairment status of the patient in daily activity; and
outputting the cognitive impairment status.
All of the foregoing underlined elements identified above, both individually and as a whole, amount to the abstract idea grouping of a certain method of organizing human activity because it is managing personal behavior or interactions between people (including social activities, teaching, and following rules or instructions) by collecting information, analyzing the information, and outputting the results of the collection and analysis. This also amounts to the abstract idea grouping of mental processes as the claims, under their broadest reasonable interpretation, cover performance of the limitations in the mind with the aid of pen and paper (including observation, evaluation, judgment, opinion) but for the recitation of generic computer components. See MPEP 2106.04(a)(2)(III)(C) - A Claim That Requires a Computer May Still Recite a Mental Process.
The dependent claims amount to merely further defining the judicial exception.
Therefore, the claims recite a judicial exception. (STEP 2A, PRONG 1: YES).
Step 2A, Prong 2
This judicial exception is not integrated into a practical application because the independent and dependent claims do not include additional elements that are sufficient to integrate the exception into a practical application under the considerations set forth in MPEP 2106.04(d). The elements of the claims above that are not underlined constitute additional elements.
The following additional elements, both individually and as a whole, merely generally link the judicial exception to a particular technological environment or field of use: a pretrained machine learning model having been trained by performing recursive feature eliminations on a plurality of cross-validated random forests on a training data set (claim 1), a pretrained machine learning model having been trained by performing recursive feature eliminations on a plurality of cross-validated random forest training data set (claim 18), a pretrained machine learning model having been trained by performing recursive feature eliminations on a plurality of cross-validated random forest training data set (claim 19), reciting the clock and recall assessment as “digital” (claim 4), a touchscreen (claim 15), a microphone (claim 15), a webcam (claim 15), a stylus (claim 15), a system comprising a computing node comprising a computer readable storage medium (claim 18), a processor (claims 18 and 19), and a computer program product comprising a computer readable storage medium (claim 19). This is evidenced by the manner in which these elements are disclosed. See, for example, Fig. 3 which illustrate the elements as non-descript black boxes and stock icons, while at least para. 45-62 in the specification merely provide stock descriptions of generic computer hardware and software components in any generic arrangement. This also evidences that the computer components are merely an attempt to link the abstract idea to a particular technological environment, but do not result in an improvement to the technology or computer functions employed. It should be noted that because the courts have made it clear that the mere physicality or tangibility of an additional element or elements is not a relevant consideration in the eligibility analysis, the physical nature of the computing device and associated hardware does not affect this analysis. See MPEP 2106.05(I) for more information on this point, including explanations from judicial decisions including Alice Corp. Pty Ltd. v. CLS Bank Int’l, 573 US 208, 224-26 (2014). Thus, none of the hardware offer a meaningful limitation beyond generally linking the performance of the steps to a particular technological environment, that is, implementation via computers. Again, this is evidenced by the manner in which these elements are disclosed in the instant specification. The claims do not recite any specific rules with specific characteristics that improve the functionality of the computer system. In particular, the mere use of a pretrained learning model is silent regarding any such specific rules, but in contrast acts only as a tool to attempt to link the abstract idea to a particular technological environment. Applicant admits as much in pg. 10 of the Remarks filed 22 October 2025 wherein Applicant asserts that “parameters of the algorithm are dependent on the input information; one of ordinary skill in the art would know how to apply suitable algorithms to the relevant data without needing specific parameters to do so…. the well known component of a random forest algorithm… is instead referring to a well-understood and routine element in the field of computer-based healthcare.” The specification provides further evidence in at least para. 33-37 which identify that the claimed invention is merely computerizing the traditional pen-and-paper testing to be more mobile and use less time and people. Additionally, the claims do not apply or use a judicial exception to effect a particular treatment or prophylaxis for a disease or medical condition nor do they apply or use a judicial exception in some other meaningful way beyond generally linking the use of the judicial exception to a particular technological environment. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Therefore, the claims are directed to the judicial exception. (STEP 2A, PRONG 2: NO).
Step 2B
The independent and dependent claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception under the considerations set forth in MPEP 2106.05. As identified in Step 2A, Prong 2, above, the claimed system and the process it performs does not require the use of a particular machine, nor does it result in the transformation of an article. The claims do not involve an improvement in a computer or other technology. Although claims recite computer components associated with performing at least some of the recited functions, these elements are recited at a high level of generality in a conventional arrangement for performing their basic computer functions (i.e., storing, processing, and outputting data). This is at least evidenced by the manner in which this is disclosed that indicates that Applicant believes the additional elements are sufficiently well-known that the specification does not need to describe the particulars of such additional elements to satisfy 35 USC 112(a) as identified in Step 2A, Prong 2, above. This also evidences that the computer components are merely an attempt to link the abstract idea to a particular technological environment, but do not result in an improvement to the technology or computer functions employed. Thus, the focus of the claimed invention is on the analysis of the collected data, which is itself at best merely an improvement within the abstract idea. See pg. 2-3 in SAP America Inc. v. lnvestpic, LLC (890 F.3d 1016, 126 USPQ2d 1638 (Fed. Cir. 2018) which proffered “[w]e may assume that the techniques claimed are groundbreaking, innovative, or even brilliant, but that is not enough for eligibility. Nor is it enough for subject-matter eligibility that claimed techniques be novel and nonobvious in light of prior art, passing muster under 35 U.S.C. §§ 102 and 103. The claims here are ineligible because their innovation is an innovation in ineligible subject matter. Their subject is nothing but a series of mathematical calculations based on selected information and the presentation of the results of those calculations.” Furthermore, the steps are merely recited to be performed by, or using, the elements while the specification makes clear that the computerized system itself is ancillary to the claimed invention as identified above. This further evidences that the claims do not recite any specific rules with specific characteristics that improve the functionality of the computer system. In particular, the mere use of a pretrained learning model is silent regarding any such specific rules, but in contrast acts only as a tool to attempt to link the abstract idea to a particular technological environment. Applicant admits as much in pg. 10 of the Remarks filed 22 October 2025 wherein Applicant asserts that “parameters of the algorithm are dependent on the input information; one of ordinary skill in the art would know how to apply suitable algorithms to the relevant data without needing specific parameters to do so…. the well known component of a random forest algorithm… is instead referring to a well-understood and routine element in the field of computer-based healthcare.” The specification provides further evidence in at least para. 33-37 which identify that the claimed invention is merely computerizing the traditional pen-and-paper testing to be more mobile and use less time and people. Thus, none of the hardware offer a meaningful limitation beyond generally linking the performance of the steps to a particular technological environment, that is, implementation via computers. Therefore, viewed as a whole, these additional claim elements do not provide any meaningful limitations to transform the abstract idea into a patent eligible application of the abstract idea such that the claims amount to significantly more than the abstract idea of itself (STEP 2B: NO).
Thus, the claims are rejected under 35 USC 101 as being directed to non-statutory subject matter.
35 USC § 102, Public Use, On Sale, or Otherwise Available
Applicant and the Assignee of this application are required under 37 CFR 1.105 to provide the following information that the examiner has determined is reasonably necessary to the examination of this application.
An issue of public use, on sale activity, or other public availability has been raised in this application. In order for the examiner to properly consider patentability of the claimed invention under 35 U.S.C. 102(a)(1), additional information regarding this issue is required as follows:
The trademark for Core Cognitive Evaluation recites that it includes “downloadable software featuring a series of questions and tests, all for analyzing brain and mental health data, detecting and tracking brain and mental health disorders, and facilitating communication among patient and medical and research professionals; downloadable software and software applications for analyzing brain and mental health data, detecting and tracking brain and mental health disorders, and facilitating communication among patients, medical and research professionals”1. The specification and at least one Assignee publication2 indicate the Core Cognitive Evaluation as the disclosed invention (see at least para. 3 in the specification which recites “[t]he present disclosure describes a proposed system and methods for predicting an individual's functional dependence during activities of daily life in older adults. This prediction method includes the analysis of components of the Linus Health Core Cognitive Evaluation”). Thus, the disclosed invention, identified as Applicant’s Core Cognitive Evaluation, has been commercially available and in public use since 31 January 20221. Information is required regarding the contents of Core Cognitive Evaluation owned by Applicant created to provide the goods and services identified in the associated trademark that was in public use, on sale, or publicly available prior to 21 August 2023. See MPEP 2120.02.
Applicant is reminded that failure to fully reply to this requirement for information will result in a holding of abandonment.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
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.
Claims 1-19 are rejected under 35 U.S.C. 103 as being unpatentable over Pascual-Leone et al. (WO 2022/067189, hereinafter referred to as PL) in view of Braudeau et al. (US 2021/0325409, hereinafter referred to as Braudeau).
Regarding claims 1, 18, and 19, PL teaches a method (claim 1), a system (claim 18), and a computer program product for predicting an impairment status, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform a method (claim 19) (PL, Title, Systems and Methods for Machine-Learning-Assisted Cognitive Evaluation and Treatment) comprising:
administering a battery of assessments to a patient, and receiving a plurality of response thereto (PL, para. 77, “the following multimodal data may be collected concurrently form several patients performing a battery of tasks and/or assessments: 1. Eye tracking data; 2. Voice recording data; 3. Drawing assessment data; 4. EEG data; 5. fMRI taken on for subject during the assessments and then uploaded to the platform.”);
collecting performance parameters based on the patient's performance on the battery of assessments (PL, para. 77, “the following multimodal data may be collected concurrently form several patients performing a battery of tasks and/or assessments: 1. Eye tracking data; 2. Voice recording data; 3. Drawing assessment data; 4. EEG data; 5. fMRI taken on for subject during the assessments and then uploaded to the platform.”);
providing the collected performance parameters and the plurality of responses to a pretrained machine learning model (PL, at least Fig. 11 illustrates this with all the collected performance parameters and plurality or responses organized into a Patient Data Model which is then fed into the Machine Learning Models Ensemble; para. 16, “The plurality of health data and/or the plurality of first order features are provided to the pre-trained learning system.” Para. 38, “the system may provide the second-order features to a pretrained machine learning system”), the pretrained learning model having been trained by performing feature reduction (also called “feature selection”) (PL, para. 41, “similar metrics that measure complementary aspects of physical, neurological, and/or psychological health may be combined into a reduced set of features that captures relevant information.” Feature Reduction/Selection is the process of picking a subset of the features in a dataset for use in a machine learning model in order to discover the features that are most relevant and significant for predicting the target variable. Thus, at least para. 41 of PL teaches this.) on a plurality of cross-validated random forests on a training data set (claims 18 and 19: a plurality of cross-validated random forest training data set) (PL, para. 43, “data structure can be learned in a supervised manner through clinical label such as diagnoses, neuropsychological testing scores, blood and brain biomarkers (e.g., amyloid, tau PET), and genetic risk factors (e.g., APoE). In various embodiments, various labels such as Alzheimer's, Parkinson's, progressive supranuclear palsy (PCP), mild cognitive impairment (MCI), pathological aging, or normal control can be assigned to samples through clinical diagnosis. In various embodiments, machine learning models such as… random forests… may be used to produce a prediction model for that clinical label, taking in either the raw data, or the computed second-order metrics which may allow faster processing and improved interpretability.” Para. 102, “machine learning models may be versioned, tracked, and regularly audited using cross-validation to track various measures over time”);
receiving, from the pretrained machine learning model, a predicted likelihood of the patient having an impairment in daily activity (PL, para. 71, “by clustering such individual factors and contextualizing them with other sources of data (e.g., genetic, behavioral, performance-based assessments and other types of health data), machine learning algorithms will enable improvements in the predictive ability to estimate risk for cognitive impairment and dementia”; para. 90, “using machine learning to predict the likelihood a subject may have Alzheimer's disease may be a driver of clinical decision-making, but may need to be considered along with other criteria when providing information to a clinician for making decisions.” Para. 105, “pre-trained machine learning models which predict biomarkers and/or health conditions for the subject”);
thresholding the predicted likelihood to thereby determine a functional impairment status of the patient in daily activity (PL, para. 100, “the patient data model may be used as input to a predictive model to predict the MoCA score”. One of ordinary skill in the art understands that the MoCA score is a measure of the severity of cognitive impairment that include standardized threshold ranges for normal (score=26+), mild impairment (score=18-25), moderate impairment (score=10-17), and severe impairment (score=0-9).), and
outputting the functional impairment status (PL, para. 56, “output a particular result (e.g., MoCA scores)”).
PL does not explicitly teach the feature reductions are recursive feature eliminations.
However, in a related art, Braudeau teaches the pretrained learning model having been trained by performing recursive feature eliminations on a plurality of cross-validated random forests on a training data set (claims 18 and 19: a plurality of cross-validated random forest training data set) (Braudeau, para. 462-469 describes the process for identifying relevant biomarkers. Specifically, para. 464 identifies performing random forests followed by the next step in para. 465 of performing “different recursive feature eliminations (RFE) with cross-validation using several algorithms that assign weights to features on the remaining biomarkers, and we finally selected those biomarkers. In more details, an RFE is a feature selection method that fits a model and removes recursively the weakest biomarkers until a relevant number of features is reached.”).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to use RFE as disclosed in Braudeau for the feature reductions in PL because RFE is one of a handful of known feature reduction algorithms and it is well within the knowledge of one of ordinary skill in the art to select a known algorithm on the basis of its suitability for the intended use as a matter of obvious design choice.
Regarding claim 2, PL teaches the method of claim 1, wherein the machine learning model is a random forest classifier (PL, para. 43, “machine learning models such as… random forests”).
Regarding claim 3, PL teaches the method of claim 1, further comprising:
providing a likelihood of a functional deficit based on the functional impairment status (PL, para. 100, “the patient data model may be used as input to a predictive model to predict the MoCA score”. One of ordinary skill in the art understands that the MoCA score is a measure of the severity of cognitive impairment that include standardized threshold ranges for normal (score=26+), mild impairment (score=18-25), moderate impairment (score=10-17), and severe impairment (score=0-9).” Para. 105, “4. The features are input into pre-trained machine learning models which predict biomarkers and/or health conditions for the subject”).
Regarding claim 4, PL teaches the method of claim 1, wherein the battery of assessments includes at least a digital clock and recall (DCR) assessment, a lifestyle and health questionnaire, and/or a functional activity questionnaire (PL, para. 33, “the tasks and/or assessments may include: drawing-based tasks, measures of decision making and reaction time, speech elicitation tasks, eye tracking-based memory assessments, gait and balance assessments, sleep measurements, and a lifestyle/health history questionnaire”).
Regarding claim 5, PL teaches the method of claim 4, further comprising:
receiving a response to the DCR assessment within the battery of assessments, wherein the response comprises a plurality of individual metrics (PL, Fig. 3 illustrates this; para. 40, “the system may begin by prompting a patient to complete two tasks: a clock drawing task and an item recall speech task. The behavior signal elicited from the tasks can be measured to collect modalities and first-order features. For example, a clock drawing task may allow the system to measure elements such as: drawing efficiency, correct component placement, drawing position, distribution of latencies, total ink used, drawing velocities, and oscillatory motion. An item recall speech test may allow the system to measure elements such as: percentage recalled, latency between items, hesitations, articulatory precision, average pitch, and unnecessary words count. In various embodiments, these first-order features may be provided with the raw data to a machine learning system used to generate second-order features, for example, a novel latent construct based on the combination of executive function measures from both the digital clock drawing task and the item recall task. In various embodiments, these second-order features may also be related to cognitive health measures including executive function, visuospatial reasoning, and memory.”);
combining the plurality of individual metrics into at least one composite score (PL, Fig. 3, First-Order Metrics);
aggregating the at least one composite score to determine a DCR score (PL, para. 53, “second order features defined from subject matter expertise as aggregates of 1st order metrics and raw data”; para. 106, “values for the clusters may be calculated as the aggregation of the contributions of their constituent features to the prediction output (e.g., weighted by feature importance).”); and
combining the DCR score with the collected performance parameters and the plurality of responses resulting in at least one composite score (PL, para. 41, “similar metrics that measure complementary aspects of physical, neurological, and/or psychological health may be combined into a reduced set of features that captures relevant information.” Para. 85, “composite of metrics that represent the overhaul state of cognitive health for a subject as defined by the various metrics and biomarkers described herein.”).
Regarding claim 6, PL teaches the method of claim 5, wherein the at least one composite score includes one or more of an information processing score, a drawing efficiency score, a simple and complex motor function score, and a spatial reasoning score (PL, para. 40, “a clock drawing task may allow the system to measure elements such as: drawing efficiency, correct component placement, drawing position, distribution of latencies, total ink used, drawing velocities, and oscillatory motion. An item recall speech test may allow the system to measure elements such as: percentage recalled, latency between items, hesitations, articulatory precision, average pitch, and unnecessary words count. In various embodiments, these first-order features may be provided with the raw data to a machine learning system used to generate second-order features, for example, a novel latent construct based on the combination of executive function measures from both the digital clock drawing task and the item recall task. In various embodiments, these second-order features may also be related to cognitive health measures including executive function, visuospatial reasoning, and memory.”).
Regarding claim 7, PL teaches the method of claim 6, wherein a weight for each of the at least one composite score is determined by an ability of the at least one composite score to predict cognitive impairment (PL, para. 106, “values for the clusters may be calculated as the aggregation of the contributions of their constituent features to the prediction output (e.g., weighted by feature importance).”).
Regarding claim 8, PL teaches the method of claim 4, wherein the lifestyle and health questionnaire comprises at least one question indicating the functional impairment status (PL, para. 132, “Lifestyle questionnaires:… the patient may be administered an activities of daily living (ADL) questionnaire. In another example, one questionnaire is adapted from the Barcelona Brain Health Initiative and includes up to 57 yes/no questions about the participant's lifestyle that are associated with cognitive performance.”).
Regarding claim 9, PL teaches the method of claim 8, further comprising using a response to the lifestyle and health questionnaire to derive an insight at a group level, wherein a group is based on patient age (PL, para. 93, “2. Run clustering as described in the prior section on this data set. In various embodiments, this will naturally classify patients into groups in a data driven way. In various embodiments, groups may be based on age, gender, or any of the features described above”).
Regarding claim 10, PL teaches the method of claim 9, further comprising using the response to the lifestyle and health questionnaire to derive an insight at an individual level (PL, para. 72, “routinely collected items of a comprehensive geriatric assessment (such as medical history and functional abilities) can be used to compute a frailty index, which gives insights into the degree of frailty for a particular individual.” Para. 74, “the patient models (using the model of Figs. 5A-5B) for each patient may be analyzed for the importance of the features for each patient.”).
Regarding claim 11, PL teaches the method of claim 1, wherein the functional impairment status is one of mild or moderate (PL, para. 43, “various labels such as Alzheimer's, Parkinson's, progressive supranuclear palsy (PCP), mild cognitive impairment (MCI), pathological aging, or normal control can be assigned to samples through clinical diagnosis”; para. 62, “diagnosis of mild cognitive impairment, which requires that the individual have cognitive deficits that are perceived to interfere with their activities of daily living”; para. 100, “the patient data model may be used as input to a predictive model to predict the MoCA score”. One of ordinary skill in the art understands that the MoCA score is a measure of the severity of cognitive impairment that include standardized threshold ranges for normal (score=26+), mild impairment (score=18-25), moderate impairment (score=10-17), and severe impairment (score=0-9).).
Regarding claim 12, PL teaches the method of claim 1, wherein the collected performance parameters comprise at least one of a response to a questionnaire, a geometry of a drawing, a stylus derived metric, and/or a speech feature (PL, Fig. 3 includes all of these collected performance parameters as discussed throughout PL’s disclosure.).
Regarding claim 13, PL teaches the method of claim 12, wherein the stylus derived metric includes a force measurement and a directional measurement (PL, para. 47, “recording positional data of user interactions such as inputs (i.e., time stamped X-axis and Y-axis coordinates on a touch screen) provided by a mobile device stylus while the patient performs a task or assessment on a mobile application, such as drawing a clock;” para. 49, “we capture the X-coordinate, Y-coordinate, Azimuth, Altitude, and Force”).
Regarding claim 14, PL teaches the method of claim 12, wherein the speech feature comprises a recording of the patient speaking (PL, para. 117, “automatic speech recognition (ASR) software may be used to determine the accuracy of the response(s). In various embodiments, the voice of the test taker is analyzed to derive speech metrics such as pause rate, pitch, and/or speed”; para. 128, “voice recordings captured and encrypted through a tablet, smartphone, or other voice-capturing device. Voice recordings are then uploaded to a secure, HIPAA compliant cloud server. Transcripts of the voice recordings are created, and an AI engine analyzes for finite but clinically relevant information. Algorithms apply signal processing and cognitive linguistic analysis to assess speech and fine motor skills and detect subtle changes in cognitive function. Extraction of linguistic and phonetic measures have been shown to correlate to Alzheimer's disease and cognitive function.”).
Regarding claim 15, PL teaches the method of claim 1, wherein collecting performance parameters comprises collecting data from at least a touchscreen, a microphone, a webcam, and/or a stylus (PL, para. 35, “a system may collect health data from tasks and/or assessments provided to the patient using suitable hardware (e.g., tablet, smartphone)”; para. 47, “inputs (i.e., time stamped X-axis and Y-axis coordinates on a touch screen) provided by a mobile device stylus while the patient performs a task or assessment on a mobile application, such as drawing a clock; eye tracking data while providing visual stimulus and requiring the patient to perform tasks that elicit their ability to perceive and respond to that stimulus; audio recording while providing audiovisual stimulus and requiring the patient to vocalize responses to that stimulus to elicit their ability to perceive and respond to such stimulus; video data recording of patients performing some task such as walking; accelerometer data recording of patients performing some task such as walking”; para. 128, “voice recordings captured and encrypted through a tablet, smartphone, or other voice-capturing device”).
Regarding claim 16, PL teaches the method of claim 1, further comprising determining a need for additional testing for a patient, based on the functional impairment status of the patient (PL, para. 38, “providing recommendations and/or diagnoses.” Para. 94, “the platform may support differential diagnosis and can recommend assessments based on its results... In various embodiments, a library of rules may be provided for evaluating features to recommend particular assessments based on their values.”).
Regarding claim 17, PL teaches the method of claim 1, further comprising determining an ability to perform instrumental activities of daily living for a patient, based on the functional impairment status of the patient (PL, para. 62, “the diagnosis of mild cognitive impairment, which requires that the individual have cognitive deficits that are perceived to interfere with their activities of daily living”; para. 100, “the patient data model may be used as input to a predictive model to predict the MoCA score”. One of ordinary skill in the art understands that the MoCA score is a measure of the severity of cognitive impairment that include standardized threshold ranges for normal (score=26+), mild impairment (score=18-25), moderate impairment (score=10-17), and severe impairment (score=0-9).).
Response to Arguments
Applicant's arguments with respect to the rejections of claims 4-8, 10, 13, and 14 under 35 USC 112(b) have been fully considered. The amendments to the claims obviate the associated rejections. Thus, these rejections have been withdrawn. However, the amendments necessitate new rejections.
Applicant's arguments with respect to the rejections of claims 5-10, 13, and 14 under 35 USC 112(d) have been fully considered. The amendments to the claims obviate the associated rejections. Thus, these rejections have been withdrawn.
Applicant's arguments with respect to the rejection of the claims under 35 USC 101 have been fully considered but they are not persuasive. In pg. 16-17, Applicant highlights text from amended claim 1 and asserts that every limitation is integrated into the specific practical application.
Examiner is not persuaded. Applicant is directed to the rejection which has been updated to address the amendments to the claims and identifies that each of these highlighted texts in claim 1, except for “the pretrained learning model having been trained…”, are wholly encompassed in the judicial exception and not any additional element, where “the pretrained learning model having been trained…” is assessed under Prong 2 of Step 2A and Step 2B to merely link the judicial exception to implementation with a computer. Furthermore, Applicant does not identify any “specific practical application” in the argument. Thus, this is at best a conclusory statement made without substantive support and is not persuasive.
In pg. 17, Applicant asserts that the claims do not recite a mental process or a method of organizing human activity because the entire claim recite[s] additional elements, but even if one or more abstract ideas are recited, Applicant highlights the same text as before from claim 1 and asserts they are additional elements.
Examiner is not persuaded. The rejection correctly identifies what language in the claims recite a judicial exception in Prong 1 of Step 2A. As identified above, “the pretrained learning model having been trained…” is the only text of the highlighted text that recites an additional element. However, this additional element is assessed under Prong 2 of Step 2A and Step 2B to merely link the judicial exception to implementation with a computer and thus neither integrates the judicial exception into a practical application nor add significantly more.
In pg. 18-19, Applicant briefly discusses Example 42 of the 2019 PEG Examples and asserts that, in the Example, anything that was not the recitation of the abstract idea itself, narrowly considered, counted as additional elements for “practical application” and “significantly more” consideration, and that given the same treatment, the instant claims are integrated into the practical application and exhibit significantly more.
Examiner is not persuaded. Applicant is directed to the rejection of the claims which identifies what recites the judicial exception with everything else assessed as additional elements under Prong 2 of Step 2A and Step 2B to neither integrate the judicial exception into a practical application nor add significantly more.
Applicant's arguments with respect to the rejections of the claims under 35 USC 112(a) have been fully considered but they are not persuasive. In pg. 9, 11, and 12, Applicant asserts that the claims have been amended to obviate the rejections.
Examiner is not persuaded. Applicant is directed to the rejections which have been updated to address the amendments to the claims.
In pg. 9-10, Applicant asserts that para. 42 of the specification provides support for the use of random forest algorithms and that the parameters of the algorithm are dependent on the input information while one of ordinary skill in the art would know how to apply suitable algorithms to the relevant data without need specific parameters to do so.
Examiner is not persuaded. As identified in the rejection, merely reciting in results-based language that random forest algorithms are used is insufficient with explicitly identifying para. 42 of the specification as exemplifying this insufficiency. As identified in MPEP 2161.01(I), claims may lack written description when the claims define the invention in functional language specifying a desired result but the specification does not sufficiently describe how the function is performed or the result is achieved. For software, this can occur when the algorithm or steps/procedure for performing the computer function are not explained at all or are not explained in sufficient detail (simply restating the function recited in the claim is not necessarily sufficient). In other words, the algorithm or steps/procedure taken to perform the function must be described with sufficient detail so that one of ordinary skill in the art would understand how the inventor intended the function to be performed. It is not enough that one skilled in the art could write a program to achieve the claimed function because the specification must explain how the inventor intends to achieve the claimed function to satisfy the written description requirement. (Bolded for emphasis). Thus, merely reciting that a non-descript random forest algorithm performs the function is not enough. The disclosure is silent regarding how a random forest algorithm is configured to perform the claimed function, not merely receive and output useful data.
Applicant's arguments with respect to the 37 CFR 1.105 request regarding an issue of public use, on sale activity, or other public availability made under the claim rejections under 35 USC 102 have been fully considered but they are not persuasive. In pg. 20-21, Applicant makes identical arguments as made in related application US 18/768,458. These arguments and Examiner’s response are reproduced below for Applicant’s convenience.
Applicant asserts that the summary of the present application is incorrect, that the components of CCE may furnish input to the prediction of functional dependence, and that the present application does not state that the claimed subject matter is equivalent to or is contained in the CCE and examples “[t]he present disclosure describes a proposed system and methods for predicting an individual’s PET Aβ± status using multimodal digital cognitive assessment technology that provides a quick, inexpensive, digital, noninvasive solution for predicting Aβ± obtained from the multimodal digital assessment technology.” Applicant also asserts that the present claims are directed towards a specific method related to determining functional impairment status.
Examiner is not persuaded. As identified in the 105 request the trademark for CCE recites that it includes "downloadable software featuring a series of questions and tests, all for analyzing brain and mental health data, detecting and tracking brain and mental health disorders, and facilitating communication among patient and medical and research professionals; downloadable software and software applications for analyzing brain and mental health data, detecting and tracking brain and mental health disorders, and facilitating communication among patients, medical and research professionals”. This directly coincides with Applicant’s example language – “system and methods for predicting an individual’s PET Aβ± status using multimodal digital cognitive assessment technology that provides a quick, inexpensive, digital, noninvasive solution for predicting Aβ± obtained from the multimodal digital assessment technology.” Further evidence is provided by the publication identified in the 105 request which recites “Linus Health’s Core Cognitive Evaluation™ (CCE™) is a digital assessment solution that combines objective assessment of cognitive function to detect early signs of cognitive impairment with an evaluation of brain health risk factors to assess the risk of developing dementia in the future. The CCE is composed of two components: The Digital Clock and Recall (DCR™) and the Life and Health Questionnaire (LHQ).” Thus publication also identifies that the CCE uses a “proprietary algorithm” as the evaluation of the results from the two components. Thus, Applicant’s assertions provide further evidence that the CCE is the disclosed invention.
Applicant's arguments with respect to the rejections of the claims under 35 USC 102 have been fully considered. In pg. 21-22, Applicant asserts that the claims have been amended to obviate the rejections.
Examiner notes the rejections have been updated under 35 USC 103 to address the amendments to the claims.
In pg. 23, Applicant asserts that dependent claims 2-17 are allowable due to their dependencies.
Examiner respectfully disagrees. Appellant is directed to the rejections which identify that neither the independent claims nor the dependent claims are allowable.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 DANIEL LANE whose telephone number is (303)297-4311. The examiner can normally be reached Monday - Friday 8:00 - 4:30 MT.
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, Xuan Thai can be reached at (571) 272-7147. 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.
/DANIEL LANE/Examiner, Art Unit 3715
/XUAN M THAI/Supervisory Patent Examiner, Art Unit 3715
1 Linus Health, Inc. (2023, May 2). Trademark for Core Cognitive Evaluation. Trademark Electronic Search System. Retrieved April 18, 2025, from https://tsdr.uspto.gov/#caseNumber=97522115&caseSearchType=US_APPLICATION&caseType=DEFAULT&searchType=statusSearch
2 Ciesla, M., Jannati, A., Gomes-Osman, J., & Pascual-Leone, A. (2022, June 17). Dementia risk estimation in the Linus Health Core Cognitive Evaluation. Linus Health. https://linushealth.com/dementia-risk-estimation-in-the-linus-health-core-cognitive-evaluation