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 .
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-27 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 1-25 are drawn to a method, claim 26 is drawn to a non-transitory computer readable medium, and claim 27 is drawn to a system, each of which is within the four statutory categories.
Step 2A(1)
Claim 1 recites, in part, performing the steps of
(a) determining a causal effect of a first variable on a second variable by estimating an average treatment effect, wherein the average treatment effect is estimated by processing the first set of time series data and the second set of time series data using a model-twin randomization method, wherein the first set of time series data relates to a first variable indicative of a health behavior of a subject and wherein the second set of time series data relates to a second variable indicative of a health condition of the subject;
(b) generating a personalized treatment or intervention recommendation for the subject to change the health condition based at least in part on the causal effect determined in (a)
These steps amount to concepts performable in the human mind and therefore fall within the scope of a method of organizing human activity. Fundamentally the process is that of using time-series data related to a patient’s behavior and a health condition of the patient to determine a causal effect of the behavior on the health condition, and using the causal effect to recommend a treatment or intervention for the patient. A healthcare provider could perform these actions mentally or with a manual computational aid as part of using a patient’s behavior and health-condition history to recommend interventions for improving the health condition.
In addition to falling within the scope of a mental process, element (a) above also recites mathematical formulas, equations, or calculations, and additionally falls within the scope of an abstract idea in the form of mathematical concepts.
The above elements therefore recite an abstract idea.
Independent claims 26 and 27 recite similar limitations and also recite an abstract idea under the same analysis.
Step 2A(2)
This judicial exception is not integrated into a practical application because the additional elements within the claims only amount to:
A. Instructions to Implement the Judicial Exception. MPEP 2106.05(f)
Claim 26 recites the additional elements of a) one or more non-transitory computer readable media used to store computer-executable instructions, and b) a processor recited as executing the instructions to perform the subsequent data-processing steps.
Claim 27 recites the additional elements of a) one or more memories used to store computer-executable instructions, and b) a processor recited as executing the instructions to perform the subsequent data-processing steps.
Paragraphs 208-211 describe a computing system having one or more processors which may include any of CPUs, GPUs, or other processing units, and memory storing computer-readable instructions including RAM, ROM, optical media, solid-state memory, and other computer memory devices. The processors, memories, and non-transitory computer readable media are therefore construed as encompassing generic computing elements.
These elements only amount to mere instructions to implement functions within the abstract idea using computing elements as tools. For example, the non-transitory computer readable medium and memory are only recited at a high level of generality as used to store computer-executable instructions and are disclosed as encompassing any of a plurality of generic forms of memory, while the processor is likewise recited at a high level of generality as executing the instructions and disclosed as encompassing a plurality of forms of computer processor devices. These elements are therefore not sufficient to integrate the abstract idea into a practical application.
B. Insignificant Extra-Solution Activity. MPEP 2106.05(g)
Claims 1, 26, and 27 further recite the additional element of obtaining the first set of time series data associated with the subject and the second set of time series data associated with the subject. However, this step only amounts to insignificant extra-solution activity. Specifically, the additional element above amounts to mere data gathering required for performance of the abstract idea. See MPEP 2106.05(g)(3). This element is therefore not sufficient to integrate the abstract idea into a practical application.
The above claims, as a whole, are therefore directed to an abstract idea.
Step 2B
The present claims do not include additional elements that are sufficient to amount to more than the abstract idea because the additional elements or combination of elements amount to no more than a recitation of:
A. Instructions to Implement the Judicial Exception. MPEP 2106.05(f)
As explained above, claims 26 and 27 only recite the non-transitory computer readable medium, memory, and processor as tools for performing the steps of the abstract idea, and mere instructions to perform the abstract idea using a computer is not sufficient to amount to significantly more than the abstract idea. MPEP 2106.05(f)
B. Insignificant Extra-Solution Activity. MPEP 2106.05(g)
Likewise, as set out above, the additional element of obtaining the first set of time series data associated with the subject and the second set of time series data associated with the subject as recited in claims 1, 26, and 27 only amounts to insignificant extra-solution activity. Specifically, the additional element above amounts to mere data gathering required for performance of the abstract idea and is therefore not sufficient to amount to significantly more than the abstract idea. See MPEP 2106.05(g)(3).
C. Well-Understood, Routine and Conventional Activities. MPEP 2106.05(d)
The additional element of obtaining the first set of time series data associated with the subject and the second set of time series data associated with the subject as recited in claims 1, 26, and 27 further constitutes well-understood routine and conventional activity in the form of receiving or transmitting data over a network and/or storing and retrieving information. This element is claimed at a high level of generality and as insignificant extra-solution activity in the form of data gathering. See MPEP 2106.05(d)(II). The above element is therefore not sufficient to amount to significantly more than the abstract idea.
Depending Claims
Claim 2 recites wherein the model-twin randomization method comprises a sequential technique to implement g-formula for estimating the average treatment effect. These limitations fall within the scope of the abstract idea, which includes an abstract idea in the form of mathematical calculations, as set out above.
Claim 3 recites wherein implementing the g-formula comprises implementing extensions of the g-formula, wherein the extensions comprise one or both of targeted learning or targeted maximum likelihood estimation. These limitations fall within the scope of the abstract idea, which includes an abstract idea in the form of mathematical calculations, as set out above.
Claim 4 recites wherein the sequential technique comprises a simulation-based technique or a Monte Carlo technique. These limitations fall within the scope of the abstract idea, which includes an abstract idea in the form of mathematical calculations, as set out above.
Claim 5 recites wherein processing the first set of time series data and the second set of time series data using the model-twin randomization method comprises randomizing the first set of time series data for each time period or time point of the first set of time series data. These limitations fall within the scope of the abstract idea, which includes an abstract idea in the form of mathematical calculations, as set out above.
Claim 6 recites running a model-twin through the randomized first set of time series data for a number of iterations until a convergence condition is satisfied. These limitations fall within the scope of the abstract idea, which includes an abstract idea in the form of mathematical calculations, as set out above.
Claim 7 recites wherein the model-twin is an outcome model fitted to the first set of time series data and the second set of time series data. These limitations fall within the scope of the abstract idea, which includes mathematical formulas or equations, as set out above.
Claim 8 recites generating, by the model-twin, a predicted value of the second variable at each time point of the second set of time series data. These limitations fall within the scope of the abstract idea, which includes mathematical calculations, as set out above.
Claim 9 recites adding random noise to each predicted value of the second variable. These limitations fall within the scope of the abstract idea, which includes an abstract idea in the form of mathematical calculations, as set out above.
Claim 10 recites determining an average period treatment effect (APTE) from at least a subset of each of the predicted values for at least a subset of the set of time points. These limitations fall within the scope of the abstract idea as set out above.
Claim 11 recites estimating a confidence interval for the APTE. These limitations fall within the scope of the abstract idea, which includes an abstract idea in the form of mathematical calculations, as set out above.
Claim 12 recites calculating a cumulative average confidence interval, wherein the convergence condition relates to the cumulative average confidence interval. These limitations fall within the scope of the abstract idea, which includes an abstract idea in the form of mathematical calculations, as set out above.
Claim 13 recites wherein the model-twin comprises a generalized linear model. These limitations fall within the scope of the abstract idea, which includes an abstract idea in the form of mathematical formulas or equations, as set out above.
Claim 14 recites wherein the linear model comprises a generalized linear model. These limitations fall within the scope of the abstract idea, which includes an abstract idea in the form of mathematical formulas or equations, as set out above.
Claim 15 recites wherein the model-twin comprises a non-parametric model. These limitations fall within the scope of the abstract idea, which includes an abstract idea in the form of mathematical formulas or equations, as set out above.
Claim 16 recites wherein the model-twin comprises a machine learning model. These limitations fall within the scope of the abstract idea, which includes an abstract idea in the form of mathematical formulas or equations, as set out above.
Claim 17 recites wherein the machine learning model comprises a random forest. These limitations fall within the scope of the abstract idea, which includes an abstract idea in the form of mathematical formulas or equations, as set out above.
Claim 18 recites the additional element of wherein the first set of time series data is acquired from one or more data-collection instruments that comprise at least one wearable device worn by the subject.
Paragraph 45 describes wearable device or sensor data as including “physical or biometric statistics… such as length of time sleeping, heart rate, and step count.” Paragraph 54 states that “the wearable or ambient devices or sensors may be smartwatches (e.g., the data-collection instrument 110(1)), smartbands (e.g., a Fitbit®) device), smartclothing, smart jewelry, smartshoes, environmental sensors, or the like.” The one or more data-collection instruments that comprise at least one wearable device are therefore construed as encompassing generic forms of wearable devices.
The above element only amounts to mere instructions to implement the abstract idea using computing elements as tools. Specifically, the data-collection instruments comprising at least one wearable device are recited at a high level of generality as used to acquire the first set of time series data, and are disclosed broadly in the specification. This element is therefore not sufficient to integrate the abstract idea into a practical application or to amount to significantly more.
Claim 19 recites wherein the first set of time series data is indicative of sleep duration and wherein the second set of time series data is indicative of physical activity. These limitations fall within the scope of the abstract idea as set out above.
Claim 20 recites wherein the second set of time series data is indicative of speed of walking. These limitations fall within the scope of the abstract idea as set out above.
Claim 21 recites wherein the second set of time series data is indicative of sleep duration and wherein the first set of time series data is indicative of physical activity. These limitations fall within the scope of the abstract idea as set out above.
Claim 22 recites the additional element of wherein one or both of the first set of time series data or the second set of time series data is collected daily.
However, this element only amounts to insignificant extra-solution activity. Similarly to the analysis above setting out why the collection of the first and second sets of time series data amounts to insignificant extra-solution activity, performing the collection daily likewise only amounts to mere data gathering required for performance of the abstract idea.
This element further constitutes well-understood routine and conventional activity in the form of receiving or transmitting data over a network and/or storing and retrieving information. This element is claimed at a high level of generality and as insignificant extra-solution activity in the form of data gathering. See MPEP 2106.05(d)(II).
The above element is therefore not sufficient to integrate the abstract idea into a practical application or to amount to significantly more than the abstract idea.
Claim 23 recites wherein one or both of the first set of time series data or the second set of time series data comprise variables that cause, moderate, or contextualize data comprised in one or both of the first set of time series data or the second set of time series data. These limitations fall within the scope of the abstract idea as set out above.
Claim 24 recites wherein the personalized treatment or intervention recommendation comprises changing health behavior of the subject. These limitations fall within the scope of the abstract idea as set out above.
Claim 25 recites wherein changing the health behavior or the subject comprises estimating a plausible or suggested average treatment effect of the health behavior of the subject on the health condition of the subject. These limitations fall within the scope of the abstract idea as set out above.
Claims 1-25 are therefore rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 14, 17, and 26 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.
Claim 14 is indefinite because Examiner is unable to determine the metes and bounds of the claim based on the recitation of “wherein the linear model comprises a generalized linear model.” Specifically, the only previous recitation of a linear model is in the generalized linear model recited in claim 13. However, if the “linear model” of claim 14 is construed as referencing the generalized linear model of claim 13, then claim 14 effectively recites that the previously recited generalized linear model comprises a generalized linear model. Examiner requests that Applicant clarify the intended language and scope of the claim.
Claim 17 recites the limitation "the machine learning model" in line 1. There is insufficient antecedent basis for this limitation in the claim because there is no prior recitation of a machine learning model within the claim.
Claim 26 recites the limitation "the subject" in line 3. There is insufficient antecedent basis for this limitation in the claim because there is no prior recitation of a subject within the claim.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1, 2, 4, and 23-27 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Chang et al (US Patent Application Publication 2025/0125055).
With respect to claim 1, Chang discloses the claimed method for generating a personalized recommended intervention for a subject based at least in part on causal inference, comprising:
(a) obtaining a first set of time series data associated with the subject and a second set of time series data associated with the subject ([22], [26], [31], [63], and [66] describe receiving time series data related to a patient), wherein the first set of time series data relates to a first variable indicative of a health behavior of the subject and wherein the second set of time series data relates to a second variable indicative of a health condition of the subject ([26], [31], [51], [56], [63], and [66] describe receiving the time series data such as vital signs, physical observations, observed outcomes, outcome variables related to medical conditions, and others. Examiner notes paragraph 59 of Applicant’s specification as filed, which describes health behavior data including a user’s vital signs);
(b) determining a causal effect of the first variable on the second variable by estimating an average treatment effect, wherein the average treatment effect is estimated by processing the first set of time series data and the second set of time series data using a model-twin randomization method (Figures 1, 4, and 5, [10], [61]-[67], [80], and [82]-[88] describe applying causal inference algorithms including the g-formula and/or an inverse propensity weighted marginal structure model to the vectors of features and outcomes, including estimating outcomes for periods under different treatment options by averaging the estimated effects across Monte Carlo iterations, i.e. estimating an average treatment effect. Examiner notes that the disclosure does not define a “model-twin randomization method,” and the broadest reasonable interpretation of this term is construed as encompassing, though not limited to, applications of the g-formula utilizing randomization models such as Monte Carlo methods); and
(c) generating a personalized treatment or intervention recommendation for the subject to change the health condition based at least in part on the causal effect determined in (b) (Figure 1, [4], [22], [30], and [35] describe identifying an optimal treatment based on the modeled effects of the various treatments on patient outcome).
With respect to claim 2, Chang discloses the method of claim 1. Chang further discloses:
wherein the model-twin randomization method comprises a sequential technique to implement g-formula for estimating the average treatment effect (Figures 4 and 5, [62]-[67], [70], [80], [83], and [93] describe estimating the averaged treatment effect by implementing a g-formula technique applied to the sequential data as well as continuously applying the technique to new data as it is received, i.e. a sequential technique to implement g-formula).
With respect to claim 4, Chang discloses the method of claim 2. Chang further discloses:
wherein the sequential technique comprises a simulation-based technique or a Monte Carlo technique ([83]-[88] describe the technique comprising implementation of the g-formula using a Monte Carlo model. Examiner notes that a Monte Carlo approach is also a form of simulation technique).
With respect to claim 23, Chang discloses the method of claim 1. Chang further discloses:
wherein one or both of the first set of time series data or the second set of time series data comprise variables that cause, moderate, or contextualize data comprised in one or both of the first set of time series data or the second set of time series data ([26], [31], [51], [56], [63], [66], and [70] describe the time series data as including data such as vital signs, physical observations, observed outcomes, outcome variables related to medical conditions, and others, each of which may “cause, moderate, or contextualize” the others).
With respect to claim 24, Chang discloses the method of claim l. Chang further discloses:
wherein the personalized treatment or intervention recommendation comprises changing health behavior of the subject ([40] describes the treatment/intervention as including administering, adjusting, or removing a medication, where taking a medication falls within the broadest reasonable interpretation of a “health behavior”).
With respect to claim 25, Chang discloses the method of claim 24. Chang further discloses:
wherein changing the health behavior or the subject comprises estimating a plausible or suggested average treatment effect of the health behavior of the subject on the health condition of the subject (Figure 1, [61]-[67], [80], and [82]-[88] describe applying causal inference algorithms to the vectors of features and outcomes, and estimating outcomes under different treatment options by averaging the estimated effects across Monte Carlo iterations, i.e. estimating an average treatment effect; Figure 1, [4], [22], [30], and [35] describe identifying an optimal treatment based on the modeled effects of the various treatments on patient outcome).
With respect to claim 26, Chang discloses the claimed one or more non-transitory computer-readable media comprising computer-executable instructions that, when executed by at least one processor (Figure 2, [42], [43], [46], and [47] describe the system incorporating non-transitory computer readable media storing instructions executed by a processor), cause the at least one processor to:
(a) obtain a first set of time series data associated with the subject and a second set of time series data associated with the subject ([22], [26], [31], [63], and [66] describe receiving time series data related to a patient), wherein the first set of time series data relates to a first variable indicative of a health behavior of the subject and wherein the second set of time series data relates to a second variable indicative of a health condition of the subject ([26], [31], [51], [56], [63], and [66] describe receiving the time series data such as vital signs, physical observations, observed outcomes, outcome variables related to medical conditions, and others. Examiner notes paragraph 59 of Applicant’s specification as filed, which describes health behavior data including a user’s vital signs);
(b) determine a causal effect of the first variable on the second variable by estimating an average treatment effect, wherein the average treatment effect is estimated by processing the first set of time series data and the second set of time series data using a model-twin randomization method (Figures 1, 4, and 5, [10], [61]-[67], [80], and [82]-[88] describe applying causal inference algorithms including the g-formula and/or an inverse propensity weighted marginal structure model to the vectors of features and outcomes, including estimating outcomes for periods under different treatment options by averaging the estimated effects across Monte Carlo iterations, i.e. estimating an average treatment effect. Examiner notes that the disclosure does not define a “model-twin randomization method,” and the broadest reasonable interpretation of this term is construed as encompassing, though not limited to, applications of the g-formula utilizing randomization models such as Monte Carlo methods); and
(c) generate a personalized treatment or intervention recommendation for the subject to change the health condition based at least in part on the causal effect determined in (b) (Figure 1, [4], [22], [30], and [35] describe identifying an optimal treatment based on the modeled effects of the various treatments on patient outcome).
With respect to claim 27, Chang discloses the claimed computer system (Figure 2, [42], [43], [46], and [47] describe the system comprising a computer system for implementing the disclosed subject matter) for generating a personalized recommended intervention for a subject based at least in part on causal inference, comprising:
one or more processors (Figure 2, [25], and [42] describe the computer system incorporating a processor); and
one or more memories storing computer-executable instructions that, when executed, cause the one or more processors to (Figure 2, [42], [43], [46], and [47] describe the system comprising memory devices storing instructions executed by the processor):
(a) obtain a first set of time series data associated with the subject and a second set of time series data associated with the subject ([22], [26], [31], [63], and [66] describe receiving time series data related to a patient), wherein the first set of time series data relates to a first variable indicative of a health behavior of the subject and wherein the second set of time series data relates to a second variable indicative of a health condition of the subject ([26], [31], [51], [56], [63], and [66] describe receiving the time series data such as vital signs, physical observations, observed outcomes, outcome variables related to medical conditions, and others. Examiner notes paragraph 59 of Applicant’s specification as filed, which describes health behavior data including a user’s vital signs);
(b) determine a causal effect of the first variable on the second variable by estimating an average treatment effect, wherein the average treatment effect is estimated by processing the first set of time series data and the second set of time series data using a model-twin randomization method (Figures 1, 4, and 5, [10], [61]-[67], [80], and [82]-[88] describe applying causal inference algorithms including the g-formula and/or an inverse propensity weighted marginal structure model to the vectors of features and outcomes, including estimating outcomes for periods under different treatment options by averaging the estimated effects across Monte Carlo iterations, i.e. estimating an average treatment effect. Examiner notes that the disclosure does not define a “model-twin randomization method,” and the broadest reasonable interpretation of this term is construed as encompassing, though not limited to, applications of the g-formula utilizing randomization models such as Monte Carlo methods); and
(c) generate a personalized treatment or intervention recommendation for the subject to change the health condition based at least in part on the causal effect determined in (b) (Figure 1, [4], [22], [30], and [35] describe identifying an optimal treatment based on the modeled effects of the various treatments on patient outcome).
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.
Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Chang et al (US Patent Application Publication 2025/0125055) as applied to claim 2, and further in view of Adaptive Sequential Design for a Single Time-Series (hereinafter Malenica).
With respect to claim 3, Chang discloses the method of claim 2. Chang does not expressly disclose wherein implementing the g-formula comprises implementing extensions of the g-formula, wherein the extensions comprise one or both of targeted learning or targeted maximum likelihood estimation.
However, Malenica teaches that it was old and well known in the art of patient modeling before the effective filing date of the claimed invention to implement extensions of the g-formula comprising targeted maximum likelihood estimation (§2.3.2 and §4 describe implementing g-formula for causal inference and further implementing targeted maximum likelihood estimation).
Therefore it would have been obvious to one of ordinary skill in the art of patient modeling before the effective filing date of the claimed invention to modify the system of Chang to implement extensions of the g-formula comprising targeted maximum likelihood estimation as taught by Malenica since the claimed invention is only a combination of these old and well known elements which would have performed the same function in combination as each did separately. In the present case Chang already discloses implementing g-formula for causal analysis, and implementing targeted maximum likelihood estimation as taught by Malenica would perform that same function in Chang, making the results predictable to one of ordinary skill in the art (MPEP 2143).
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Chang et al (US Patent Application Publication 2025/0125055) as applied to claim 1, and further in view of Causal Analysis of Self-tracked Time Series Data Using a Counterfactual Framework for N-of-1 Trials (hereinafter Daza).
With respect to claim 5, Chang discloses the method of claim 1. Chang does not expressly disclose wherein processing the first set of time series data and the second set of time series data using the model-twin randomization method comprises randomizing the first set of time series data for each time period or time point of the first set of time series data.
However, Daza teaches that it was old and well known in the art of patient modeling before the effective filing date of the claimed invention to process a first set of time series data and a second set of time series data using a model-twin randomization method by randomizing the first set of time series data for each time period or time point of the first set of time series data (P.e12 Col.1, §3.1, and P.e13 Col.2-3 describe calculation of average period treatment effect by randomizing the time series of measurements {X} for corresponding time points during each period).
Therefore it would have been obvious to one of ordinary skill in the art of patient modeling before the effective filing date of the claimed invention to modify the system of Chang to process the first set of time series data and the second set of time series data using the model-twin randomization method by randomizing the first set of time series data for each time period or time point of the first set of time series data as taught by Daza since the claimed invention is only a combination of these old and well known elements which would have performed the same function in combination as each did separately. In the present case Chang already discloses receiving the first and second sets of time series data for each period as well as applying a Monte Carlo process to the time series data, and processing the first set of time series data and the second set of time series data by randomizing the first set of time series data for each time period or time point of the first set of time series data as taught by Daza would perform that same function in Chang, making the results predictable to one of ordinary skill in the art (MPEP 2143).
Claims 6-8, 13, 14, and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Chang et al (US Patent Application Publication 2025/0125055) in view of Causal Analysis of Self-tracked Time Series Data Using a Counterfactual Framework for N-of-1 Trials (hereinafter Daza) as applied to claim 5, and further in view of A Convergence Criterion for the Monte Carlo Estimates (hereinafter Ata).
With respect to claim 6, Chang/Daza teach the method of claim 5. Chang further discloses
running a model-twin through the first set of time series data for a number of iterations (Figure 5, [63], and [82]-[87] describe running the regression model portion of the g-formula across multiple generated trajectories of the feature time series);
but does not expressly disclose:
the first set of time series data being randomized; and
running the model-twin until a convergence condition is satisfied.
However, Daza teaches that it was old and well known in the art of patient modeling before the effective filing date of the claimed invention to process a first set of time series data and a second set of time series data using a model-twin randomization method by randomizing the first set of time series data for each time period or time point of the first set of time series data (P.e12 Col.1, §3.1, and P.e13 Col.2-3 describe calculation of average period treatment effect by randomizing the time series of measurements {X} for corresponding time points during each period).
Therefore it would have been obvious to one of ordinary skill in the art of patient modeling before the effective filing date of the claimed invention to modify the combination of Chang and Daza to process the first set of time series data and the second set of time series data using the model-twin randomization method by randomizing the first set of time series data for each time period or time point of the first set of time series data as taught by Daza since the claimed invention is only a combination of these old and well known elements which would have performed the same function in combination as each did separately. In the present case Chang and Daza already teach receiving the first and second sets of time series data for each period as well as applying a Monte Carlo process to the time series data, and processing the first set of time series data and the second set of time series data by randomizing the first set of time series data for each time period or time point of the first set of time series data as taught by Daza would perform that same function in Chang and Daza, making the results predictable to one of ordinary skill in the art (MPEP 2143).
As cited above, Chang discloses a process of running a model twin for a series of iterations and taking the Monte Carlo average across the iterations. Ata then further teaches that it was old and well known in the art of statistical modeling before the effective filing date of the claimed invention to run a Monte Carlo process until a convergence condition is satisfied (P.237-239 describe a process of running a Monte Carlo process based on a convergence criterion satisfying a stopping rule).
Therefore it would have been obvious to one of ordinary skill in the art of patient modeling before the effective filing date of the claimed invention to modify the combination of Chang and Daza to running the model-twin until a convergence condition is satisfied as taught by Ata since the claimed invention is only a combination of these old and well known elements which would have performed the same function in combination as each did separately. In the present case Chang and Daza already teach a process of running a model twin for a series of iterations and taking the Monte Carlo average across the iterations, and running the process until a convergence condition is satisfied as taught by Ata would perform that same function in Chang and Daza, making the results predictable to one of ordinary skill in the art (MPEP 2143).
With respect to claim 7, Chang/Daza/Ata teach the method of claim 6. Chang further discloses:
wherein the model-twin is an outcome model fitted to the first set of time series data and the second set of time series data (Figure 3, [30]-[34], [82], and [83] describe training the model using the series data).
With respect to claim 8, Chang/Daza/Ata teach the method of claim 7. Chang further discloses:
generating, by the model-twin, a predicted value of the second variable at each time point of the second set of time series data ([82]-[87] describe applying the outcome regression model to generate potential outcomes, i.e. predicting values of the second variable).
With respect to claim 13, Chang/Daza/Ata teach the method of claim 6. Chang further discloses:
wherein the model-twin comprises a generalized linear model ([82] and [83] describe the g-formula and outcome regression model as generalized linear models).
With respect to claim 14, Chang/Daza/Ata teach the method of claim 13. Chang further discloses:
wherein the linear model comprises a generalized linear model ([82] and [83] describe the g-formula and outcome regression model as generalized linear models).
With respect to claim 16, Chang/Daza/Ata teach the method of claim 6. Chang further discloses:
wherein the model-twin comprises a machine learning model ([82] and [83] describe the g-formula and outcome regression model as trained linear models).
Claims 9-12 are rejected under 35 U.S.C. 103 as being unpatentable over Chang et al (US Patent Application Publication 2025/0125055) in view of Causal Analysis of Self-tracked Time Series Data Using a Counterfactual Framework for N-of-1 Trials (hereinafter Daza) and A Convergence Criterion for the Monte Carlo Estimates (hereinafter Ata) as applied to claim 8, and further in view of Model-Twin Randomization (MoTR): A Monte Carlo Method for Estimating the Within-Individual Average Treatment Effect Using Wearable Sensors (hereinafter Daza MoTR).
With respect to claim 9, Chang/Daza/Ata teach the method of claim 8. Chang does not expressly disclose adding random noise to each predicted value of the second variable.
However, Daza MoTR teaches that it was old and well known in the art of patient modeling before the effective filing date of the claimed invention to add random noise to each predicted value of a second variable (§2.12 and §3.3 describe adding random noise to each predicted value of an outcome variable Yi.).
Therefore it would have been obvious to one of ordinary skill in the art of patient modeling before the effective filing date of the claimed invention to modify the combination of Chang, Daza, and Ata to add random noise to each predicted value of a second variable as taught by Daza MoTR since the claimed invention is only a combination of these old and well known elements which would have performed the same function in combination as each did separately. In the present case Chang, Daza, and Ata already teach predicting values of a second variable, and adding random noise to the predicted variable as taught by Daza MoTR would perform that same function in Chang, Daza, and Ata, making the results predictable to one of ordinary skill in the art (MPEP 2143).
With respect to claim 10, Chang/Daza/Ata/Daza MoTR teach the method of claim 9. Chang does not expressly disclose determining an average period treatment effect (APTE) from at least a subset of each of the predicted values for at least a subset of the set of time points.
However, Daza teaches that it was old and well known in the art of patient modeling before the effective filing date of the claimed invention to determine an average period treatment effect (APTE) from at least a subset of predicted values for at least a subset of a set of time points (P.e13 Col.2 - P.e14 Col.1 describes calculation of average period treatment effect by based on at least some subset of predicted outcome values).
Therefore it would have been obvious to one of ordinary skill in the art of patient modeling before the effective filing date of the claimed invention to modify the combination of Chang, Daza, Ata, and Daza MoTR to determine an average period treatment effect (APTE) from at least a subset of predicted values for at least a subset of a set of time points as taught by Daza since the claimed invention is only a combination of these old and well known elements which would have performed the same function in combination as each did separately. In the present case Chang, Daza, Ata, and Daza MoTR already teaches predicting outcome values, and determining an average period treatment effect (APTE) from at least a subset of predicted values for at least a subset of a set of time points as taught by Daza would perform that same function in Chang, Daza, Ata, and Daza MoTR, making the results predictable to one of ordinary skill in the art (MPEP 2143).
With respect to claim 11, Chang/Daza/Ata/Daza MoTR teach the method of claim 10. Chang does not expressly disclose estimating a confidence interval for the APTE.
However, Daza MoTR teaches that it was old and well known in the art of patient modeling before the effective filing date of the claimed invention to estimate a confidence interval for an APTE (§3.3 describes calculating an APTE and estimating a confidence interval).
Therefore it would have been obvious to one of ordinary skill in the art of patient modeling before the effective filing date of the claimed invention to modify the combination of Chang, Daza, Ata, and Daza MoTR to estimate a confidence interval for an APTE as taught by Daza MoTR since the claimed invention is only a combination of these old and well known elements which would have performed the same function in combination as each did separately. In the present case Chang, Daza, Ata, and Daza MoTR already teach determining an APTE, and estimating a confidence interval for the APTE as taught by Daza MoTR would perform that same function in Chang, Daza, Ata, and Daza MoTR, making the results predictable to one of ordinary skill in the art (MPEP 2143).
With respect to claim 12, Chang/Daza/Ata/Daza MoTR teach the method of claim 11. Chang does not expressly disclose calculating a cumulative average confidence interval, wherein the convergence condition relates to the cumulative average confidence interval.
However, Daza MoTR teaches that it was old and well known in the art of patient modeling before the effective filing date of the claimed invention to calculate a cumulative average confidence interval, wherein a convergence condition relates to the cumulative average confidence interval (§3.3 describes calculating a cumulative average confidence interval for each APTE and repeating until covergence).
Therefore it would have been obvious to one of ordinary skill in the art of patient modeling before the effective filing date of the claimed invention to modify the combination of Chang, Daza, Ata, and Daza MoTR to calculate a cumulative average confidence interval, wherein a convergence condition relates to the cumulative average confidence interval as taught by Daza MoTR since the claimed invention is only a combination of these old and well known elements which would have performed the same function in combination as each did separately. In the present case Chang, Daza, Ata, and Daza MoTR already teach estimating a confidence interval for the APTE, and calculating a cumulative average confidence interval relating to the cumulative average confidence interval as taught by Daza MoTR would perform that same function in Chang, Daza, Ata, and Daza MoTR, making the results predictable to one of ordinary skill in the art (MPEP 2143).
Claims 15 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Chang et al (US Patent Application Publication 2025/0125055) in view of Causal Analysis of Self-tracked Time Series Data Using a Counterfactual Framework for N-of-1 Trials (hereinafter Daza) and A Convergence Criterion for the Monte Carlo Estimates (hereinafter Ata) as applied to claim 6, and further in view of Person as Population: A Longitudinal View of Single-Subject Causal Inference for Analyzing Self-Tracked Health Data (hereinafter Daza Person).
With respect to claim 15, Chang/Daza/Ata teach the method of claim 6. Cheng does not expressly disclose wherein the model-twin comprises a non-parametric model.
However, Daza Person teaches that it was old and well known in the art of patient modeling before the effective filing date of the claimed invention to employ a non-parametric model as a model-twin (§2.4 describes modeling outcomes using a random forest model, i.e. a non-parametric model as a model-twin).
Therefore it would have been obvious to one of ordinary skill in the art of patient modeling before the effective filing date of the claimed invention to modify the combination of Chang, Daza, and Ata to employ a non-parametric model as a model-twin as taught by Daza Person since the claimed invention is only a combination of these old and well known elements which would have performed the same function in combination as each did separately. In the present case Chang, Daza, and Ata already teach predicting the value of an outcome variable using a digital twin, and doing so using a non-parametric model as the model-twin as taught by Daza Person would perform that same function in Chang, Daza, and Ata, making the results predictable to one of ordinary skill in the art (MPEP 2143).
With respect to claim 17, Chang/Daza/Ata/Daza Person teach the method of claim 15. Cheng does not expressly disclose wherein the machine learning model comprises a random forest.
However, Daza Person teaches that it was old and well known in the art of patient modeling before the effective filing date of the claimed invention to employ a machine learning model as a model twin comprising a random forest (§2.4 describes modeling outcomes using a random forest model).
Therefore it would have been obvious to one of ordinary skill in the art of patient modeling before the effective filing date of the claimed invention to modify the combination of Chang, Daza, Ata, and Daza Person to employ a machine learning model comprising a random forest as taught by Daza Person since the claimed invention is only a combination of these old and well known elements which would have performed the same function in combination as each did separately. In the present case Chang, Daza, Ata, and Daza Person already teach using a digital twin, and employing a machine learning model as a model twin comprising a random forest as taught by Daza Person would perform that same function in Chang, Daza, Ata, and Daza Person, making the results predictable to one of ordinary skill in the art (MPEP 2143).
Claims 18, 19, 21, and 22 are rejected under 35 U.S.C. 103 as being unpatentable over Chang et al (US Patent Application Publication 2025/0125055) as applied to claim 1, and further in view of Day‑to‑day associations between sleep and physical activity: a set of person‑specific analyses in adults with overweight and obesity (hereinafter Chevance).
With respect to claim 18, Chang discloses the method of claim l. Chang does not expressly disclose wherein the first set of time series data is acquired from one or more data-collection instruments that comprise at least one wearable device worn by the subject.
However, Chevance teaches that it was old and well known in the art of patient modeling before the effective filing date of the claimed invention to acquire time series data from at least one wearable device worn by a subject (Abstract, p.16 Col.1 describe collecting sleep and physical activity data using a FitBit, i.e. a wearable device).
Therefore it would have been obvious to one of ordinary skill in the art of patient modeling before the effective filing date of the claimed invention to modify the system of Chang to acquire time series data from one or more data-collection instruments that comprise at least one wearable device worn by the subject as taught by Chevance since the claimed invention is only a combination of these old and well known elements which would have performed the same function in combination as each did separately. In the present case Chang already discloses receiving the first and second sets of time series data for each period, and receiving the data from a wearable device worn by a subject as taught by Chevance would perform that same function in Chang, making the results predictable to one of ordinary skill in the art (MPEP 2143).
With respect to claim 19, Chang/Chevance teach the method of claim 18. Chang does not expressly disclose wherein the first set of time series data is indicative of sleep duration and wherein the second set of time series data is indicative of physical activity.
However, Chevance teaches that it was old and well known in the art of patient modeling before the effective filing date of the claimed invention to acquire a first set of time series data indicative of sleep duration and a second set of time series data indicative of physical activity (Abstract, p.16 Cols.1-2, and Table 1 describe collecting total sleep time and step count data and modeling the effect of sleep time on step count).
Therefore it would have been obvious to one of ordinary skill in the art of patient modeling before the effective filing date of the claimed invention to modify the combination of Chang and Chevance to acquire a first set of time series data indicative of sleep duration and a second set of time series data indicative of physical activity as taught by Chevance since the claimed invention is only a combination of these old and well known elements which would have performed the same function in combination as each did separately. In the present case Chang and Chevance already teach acquiring first and second sets of time series data, and having the first set of time series data be indicative of sleep duration and the second set of time series data be indicative of physical activity as taught by Chevance would perform that same function in Chang and Chevance, making the results predictable to one of ordinary skill in the art (MPEP 2143).
With respect to claim 21, Chang/Chevance teach the method of claim 18. Chang does not expressly disclose wherein the second set of time series data is indicative of sleep duration and wherein the first set of time series data is indicative of physical activity.
However, Chevance teaches that it was old and well known in the art of patient modeling before the effective filing date of the claimed invention to acquire a first set of time series data indicative of physical activity and a second set of time series data indicative of sleep duration (Abstract, p.16 Cols.1-2, and Table 1 describe collecting total sleep time and step count data and modeling the effect of step count on sleep time).
Therefore it would have been obvious to one of ordinary skill in the art of patient modeling before the effective filing date of the claimed invention to modify the combination of Chang and Chevance to acquire a first set of time series data indicative of physical activity and a second set of time series data indicative of sleep duration as taught by Chevance since the claimed invention is only a combination of these old and well known elements which would have performed the same function in combination as each did separately. In the present case Chang and Chevance already teach acquiring first and second sets of time series data, and having the first set of time series data be indicative of physical activity and the second set of time series data be indicative of sleep duration as taught by Chevance would perform that same function in Chang and Chevance, making the results predictable to one of ordinary skill in the art (MPEP 2143).
With respect to claim 22, Chang/Chevance teach the method of claim 18. Chang does not expressly disclose wherein one or both of the first set of time series data or the second set of time series data is collected daily.
However, Chevance teaches that it was old and well known in the art of patient modeling before the effective filing date of the claimed invention to collect one or both of a first set of time series data or a second set of time series data daily (Abstract, p.16 Cols.1-2, and pp.18-19 describe collecting the total sleep time for each night and step count data for each day).
Therefore it would have been obvious to one of ordinary skill in the art of patient modeling before the effective filing date of the claimed invention to modify the combination of Chang and Chevance to collect one or both of a first set of time series data or a second set of time series data daily as taught by Chevance since the claimed invention is only a combination of these old and well known elements which would have performed the same function in combination as each did separately. In the present case Chang and Chevance already teach acquiring first and second sets of time series data, and acquiring the data daily as taught by Chevance would perform that same function in Chang and Chevance, making the results predictable to one of ordinary skill in the art (MPEP 2143).
Claim 20 is rejected under 35 U.S.C. 103 as being unpatentable over Chang et al (US Patent Application Publication 2025/0125055) in view of Day‑to‑day associations between sleep and physical activity: a set of person‑specific analyses in adults with overweight and obesity (hereinafter Chevance) as applied to claim 18, and further in view of Hiroki et al (US Patent Application Publication 2017/0109641).
With respect to claim 20, Chang/Chevance teach the method of claim 18. Chang does not expressly disclose wherein the second set of time series data is indicative of speed of walking.
However, Hiroki teaches that it was old and well known in the art of patient modeling before the effective filing date of the claimed invention to collect data indicative of speed of walking ([25], [38], [39], and Tables 1-2 describe collecting walking speed data for use in a patient model).
Therefore it would have been obvious to one of ordinary skill in the art of patient modeling before the effective filing date of the claimed invention to modify the combination of Chang and Chevance to collect data indicative of speed of walking as taught by Hiroki since the claimed invention is only a combination of these old and well known elements which would have performed the same function in combination as each did separately. In the present case Chang and Chevance already teach acquiring time series data, including data about a subject’s walking (See Chevance P.16 Cols.1-2 describing collecting step count data from subjects), and acquiring data indicative of speed of walking as taught by Hiroki would perform that same function in Chang and Chevance, making the results predictable to one of ordinary skill in the art (MPEP 2143).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to WILLIAM G LULTSCHIK whose telephone number is (571)272-3780. The examiner can normally be reached 9am - 5pm.
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, Fonya Long can be reached at (571) 270-5096. 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.
/Gregory Lultschik/Examiner, Art Unit 3682