DETAILED ACTION
Claims 1-20 are pending and hereby under examination.
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 .
Drawings
The drawings are objected to as failing to comply with 37 CFR 1.84(p)(4) because reference character “304”, “404”, and “504” has been used to designate both the “transmitter” and “receiver” in Figs. 3-5. Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Claim Objections
Claim 6 is objected to because of the following informalities:
Claim 6 has two instances of the world “predication” that should read “prediction”.
Appropriate correction is required.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-7, 11-13, and 17 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.
Analysis of independent claims 1, 11, and 17:
Step 1 of the subject matter eligibility test (see MPEP 2106.03).
Claim 1 is directed to a computer implemented method, which describes one of the four statutory categories of patentable subject matter, i.e., a method. Claims 11 and 17 are directed to a non-transitory computer-program software product, which describes one of the four statutory categories of patentable subject matter, i.e., a machine. Therefore, further consideration is necessary regarding the claims.
Step 2A of the subject matter eligibility test (see MPEP 2106.04).
Prong One: Claims 1, 11, and 17 recite an abstract idea. In particular, the claims generally recite
the following:
determining, by the one or more processors, an excursion start time of the CGM data based at least in part on an excursion initiation probability for a first temporal unit associated with the CGM data;
determining, by the one or more processors, an excursion end time based at least in part on an excursion termination probability for a second temporal unit that occurs after the excursion start time;
identifying, by the one or more processors, a time interval within the CGM data that corresponds to a glucose surge excursion based at least in part on the excursion start time and the excursion end time; and
determining, by the one or more processors and a machine learning model that is trained using ground-truth data corresponding to the glucose surge excursion, one or more glucose-insulin predictions based at least in part on the glucose surge excursion;
These elements recited in claims 1, 11, and 17 are drawn to an abstract idea since they are directed towards mathematical concepts – mathematical relationships, mathematical formulas or equations, mathematical calculations (see MPEP § 2106.04(a)(2), subsection I) and mental processes – concepts performed in the human mind (including an observation, evaluation, judgment, opinion) (see MPEP § 2106.04(a)(2), subsection III).
“determining an excursion start time of the CGM data based at least in part on an excursion initiation probability for a first temporal unit associated with the CGM data” is drawn to an abstract idea since it is a mental process that can be practically performed in the human mind, with the aid of pen and paper or a generic computer. A person of ordinary skill in the art could reasonably review CGM data and determine when the glucose measurement level starts an excursion. There is nothing to suggest an undue level of complexity in “determining an excursion start time of the CGM data based at least in part on an excursion initiation probability for a first temporal unit associated with the CGM data”.
“determining an excursion end time based at least in part on an excursion termination probability for a second temporal unit that occurs after the excursion start time” is drawn to an abstract idea since it is a mental process that can be practically performed in the human mind, with the aid of pen and paper or a generic computer. A person of ordinary skill in the art could reasonably review CGM data and determine when the glucose measurement level ends an excursion. There is nothing to suggest an undue level of complexity in “determining an excursion end time based at least in part on an excursion termination probability for a second temporal unit that occurs after the excursion start time”.
“identifying a time interval within the CGM data that corresponds to a glucose surge excursion based at least in part on the excursion start time and the excursion end time” is drawn to an abstract idea since it is a mental process that can be practically performed in the human mind, with the aid of pen and paper or a generic computer. A person of ordinary skill in the art could reasonably review a start time and an end time for a glucose excursion to determine the time interval of the excursion. There is nothing to suggest an undue level of complexity in “identifying a time interval within the CGM data that corresponds to a glucose surge excursion based at least in part on the excursion start time and the excursion end time”.
“determining, by the one or more processors and a machine learning model that is trained using ground-truth data corresponding to the glucose surge excursion, one or more glucose-insulin predictions based at least in part on the glucose surge excursion” is drawn to an abstract idea since it is a mathematical concept. A person of ordinary skill could reasonably apply a generic machine learning model to a set of data to determine a glucose-insulin prediction.
Prong Two: Claims 1, 11, and 17 do not recite additional elements that integrate the exception into a practical application. Therefore, the claims are "directed to" the abstract idea. The additional elements merely:
Add insignificant extra-solution activity (the pre-solution activity of: using generic data gathering components (e.g., "receiving, by one or more processors and originating from a continuous glucose monitoring (CGM) device, CGM data for an end-user" (claim 1), "receiving, originating from a continuous glucose monitoring (CGM) device, CGM data for an end-user" (claim 11), and “receive, originating from a continuous glucose monitoring (CGM) device, CGM data for an end-user” (claim 17)); the post-solution activity of: (e.g. “based at least in part on the one or more glucose-insulin predictions, initiating, by the one or more processors, one or more prediction-based actions for the end-user” (claim 1), “based at least in part on the one or more glucose-insulin predictions, initiating one or more prediction-based actions for the end-user” (claim 11), and “based at least in part on the one or more glucose-insulin predictions, initiate one or more prediction-based actions for the end-user” (claim 17))).
As a whole, the additional elements merely serve to gather information to be used by the abstract idea, while generically implementing it on a computer. There is no practical application because the abstract idea is not applied, relied on, or used in a meaningful way. The processing performed remains in the abstract realm, i.e., the result is not used for a treatment. No improvement to the technology is evident. Therefore, the additional elements, alone or in combination, do not integrate the abstract idea into a practical application.
Step 2B of the subject matter eligibility test (see MPEP 2106.05).
Claims 1, 11, and 17 do not include additional elements, alone or in combination, that are sufficient to amount to significantly more than the judicial exception (i.e., an inventive concept) for the same reasons as described above. E.g., all elements are directed to implementing the abstract ideas on generic processing components, the pre-solution activity of using generic data-gathering components, and generic post-solution activities, which merely facilitate the abstract idea.
Per the Berkheimer requirement, the additional elements are well-understood, routine, and conventional. For example, a “continuous glucose monitoring (CGM) device” as disclosed in the Applicant’s specification in paragraph 0077, “the glucose monitoring computing entity 101 includes one or more CGM sensors. Some CGM monitors use a small, disposable sensor inserted just under the skin. The sensor must be calibrated with a traditional finger-stick test and the glucose levels in the interstitial fluid may lag five or more minutes behind blood glucose levels. Other CGM monitors may use non-invasive techniques such as transmission and reflection spectroscopy. In some embodiments, the glucose monitoring computing entity 101 includes a display device that is configured to display a user interface”.
A “machine learning model” is described as various types of machine learning models such as a convolutional neural network (Paragraph 0027), neural network machine learning models (Paragraph 0028), recurrent neural network (Paragraph 0059), support vector machines, gradient boosts, Markov models, adaptive Bayesian techniques, and statistical models (Paragraph 0064).
Further, “one or more processors”, “one or more memories”, and “processor-executable instructions” do not qualify as significantly more because this limitation is simply appending well understood, routine and conventional activities previously known in the industry, specified at a high level of generality, to the judicial exception, e.g., a claim to an abstract idea requiring no more than a generic computer to perform generic computer functions that are well-understood, routine and conventional activities previously known in the industry (see Electric Power Group, 830 F.3d 1350 (Fed. Cir. 2016); Alice Corp. v. CLS Bank Int'/, 110 USPQ2d 1976 (2014)) and/or a claim to an abstract idea requiring no more than being stored on a computer readable medium which is a well understood, routine and conventional activity previously known in the industry (see Electric PowerGroup, 830 F.3d 1350 (Fed. Cir. 2016); Alice Corp. v. CLS Bank Int'/, 110 USPQ2d 1976 (2014); SAP Am. v. lnvestPic, 890 F.3d 1016 (Fed. Circ. 2018)).
In view of the above, the additional elements individually do not integrate the exception into a practical application and do not amount to significantly more than the above-judicial exception (the abstract idea). Looking at the limitations as an ordered combination (that is, as a whole) adds nothing that is not already present when looking at the elements taking individually. There is no indication that the combination of elements improves the functioning of a computer, for example, or improves any other technology. There is no indication that the combination of elements permits automation of specific tasks that previously could not be automated. There is no indication that the combination of elements include a particular solution to a computer-based problem or a particular way to achieve a desired computer-based outcome. There is no indication that the machine learning model performs a specialized, unique processing program. There is no indication that the continuous glucose monitor is a specialized, unique sensor or sensor system. Rather, the collective functions of the claimed invention merely provide conventional computer implementation, i.e., the computer is simply a tool to perform the process.
Analysis of dependent claims 2-10, 12-16, and 18-20:
Claim 7 recites mental steps that may be performed in the human mind with the aid of pen and paper or a generic computer, which add to the abstract idea. The mental steps are identified as:
wherein determining the excursion end time comprises: determining one or more potential excursion end times based at least in part on the excursion initiation probability; determining one or more excursion probabilities for the one or more potential excursion end times, wherein an excursion probability of the one or more excursion probabilities for a potential excursion end time of the one or more potential excursion end times is based at least in part on a temporal deviation between the excursion start time and the potential excursion end time; and determining the excursion end time based at least in part on the one or more excursion probabilities for the one or more potential excursion end times (claim 7);
Claims 2, 4-5, and 13 recite steps that are mathematical concepts, which add to the abstract idea. The mathematical concepts are identified as:
the excursion initiation probability is determined based at least in part on one or more of (i) a first comparison between a neighboring CGM moving average and a neighboring CGM moving average threshold, (ii) a first comparison between a CGM first derivative approximation and a CGM first derivative approximation threshold, and (iii) a first comparison between a CGM z-score and a CGM z-score threshold; the excursion termination probability is determined based at least in part on one or more of (i) a second comparison between the neighboring CGM moving average and the neighboring CGM moving average threshold, (ii) a second comparison between the CGM first derivative approximation and the CGM first derivative approximation threshold, and (iii) a second comparison between the CGM z-score and the CGM z-score threshold; the neighboring CGM moving average threshold is determined based at least in part on a CGM measurement for a temporal unit of the first temporal unit and one or more CGM measurements for one or more temporal units of the first temporal unit preceding the temporal unit (claim 2);
the excursion initiation probability is determined by providing CGM measurements to the machine learning model, the machine learning model is configured to process the CGM measurements to generate the excursion initiation probability (claims 4 and 13); and
the excursion termination probability is determined by providing CGM measurements associated with the first temporal unit to the machine learning model, the machine learning model is configured to process the CGM measurements to generate the excursion termination probability (claim 5);
Claims 3-6 and 12-13 recite limitation in addition to the abstract idea: they merely
Further describe the abstract idea (“wherein the excursion termination probability is determined based at least in part on one or more user-supplied meal session termination indicators” (claims 3 and 12) and “wherein the machine learning model comprises a steady-state glucose-insulin prediction machine learning model, a glucose-biased glucose-insulin predication machine learning model, a hybrid glucose-insulin predication machine learning model, an excursion termination detection machine learning model, a parameter space refinement machine learning model, or any combination thereof” (claim 6)),
Further describe the pre-solution activity (“the machine learning model is trained using the ground-truth data, wherein the ground-truth data is determined based at least in part on one or more user-supplied meal session initiation indicators” (claims 4 and 13), and “the machine learning model is trained using the ground-truth data, wherein the ground-truth data is determined based at least in part on one or more user-supplied meal session termination indicators” (claim 5)).
Taken alone or in combination, the additional elements do not integrate the judicial exception into a practical application at least because the abstract idea is not applied, relied on, or used in a meaningful way. The additional elements do not add anything significantly more than the abstract idea. The collective functions of the additional elements merely provide computer/electronic implementation and processing, and no additional elements beyond those of the abstract idea. There is no indication that the combination of elements permits automation of specific tasks that previously could not be automated. There is no indication that the combination of elements improves the functioning of a computer, output device, improves technology other than the technical field of the claimed invention, etc. The result of the abstract idea does not cause the computing device and/or application to perform differently.
Examiner notes that the limitation of “the one or more prediction based actions comprise administration of an insulin sensitizing drug or an insulin stimulating drug to the end-user” moves the abstract idea into a practical application. The claim requires that, due to the determination by the computer/model, the system reacts to administer a treatment. As such, claims 8-10, 14-16, and 18-20 are directed toward statutory subject matter.
Therefore, claims 1-7, 11-13, and 17 are rejected as being directed to non-statutory subject matter.
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 1-2, 4, 6, 8, 11, 13-14, and 17-18 are rejected under 35 U.S.C. 103 as being unpatentable over Kölle et. al. (“Pattern Recognition Reveals Characteristic Postprandial Glucose Changes: Non-Individualized Meal Detection in Diabetes Mellitus Type 1”), hereinafter Kölle, and Cappon et. al. (“Classification of Postprandial Glycemic Status with Application to Insulin Dosing in Type 1 Diabetes—An In Silico Proof-of-Concept”), hereinafter Cappon.
Regarding claim 1, Kölle discloses a computer-implemented method comprising:
receiving, by one or more processors and originating from a continuous glucose monitoring (CGM) device, CGM data for an end-user (Page 595, Col 2, paragraph 2, “The data set consists of CGM measurements from a subcutaneous sensor”);
determining, by the one or more processors, an excursion start time of the CGM data based at least in part on an excursion initiation probability for a first temporal unit associated with the CGM data (Page 596, Col 2, paragraph 1, wherein the beginning of the meals was marked when the CGM changed with more than 1mg/dL/min; Page 601, Col 1, paragraph 2, wherein a pattern recognition performed by LDA was used to differentiate between meal onset and no meal onset based on CGM data and estimated glucose rate of appearance Ra. The LDA assigns posterior probabilities that an observation belongs to the class “meal onset”. “Meal onset” is interpreted to be an excursion start time as Kölle focuses on the glucose excursion caused by meals);
determining, by the one or more processors, an excursion end time (Page 596, Col 2, paragraph 2, wherein the window defining the meal ends no later than 60 min after meal onset);
identifying, by the one or more processors, a time interval within the CGM data that corresponds to a glucose surge excursion based at least in part on the excursion start time and the excursion end time (Page 596, Col 2, paragraph 1, wherein the meal is defined by the “meal onset”, or the beginning of the CGM data changing by more than 1mg/dL/min; Page 596, Col 2, paragraph 4, wherein the meal is considered having ended no later than 60 min after meal onset; The “meal onset” to the meal end no later than 60 min is interpreted as a glucose surge excursion as the measured glucose rapidly rises and is marked by both the meal onset and the end of the meal, where glucose would be elevated).
Kölle does not disclose calculating an excursion termination probability for the excursion end time. While Kölle discusses that meal detection and classification may be used to estimate an appropriate insulin bolus (Page 599, Col 1, paragraph 5) and that meal detection with subsequent insulin bolus administration can improve the outcomes of fully automated closed-loop glucose control (Page 594, Col 1, paragraph 1), Kölle fails to disclose generating a glucose-insulin prediction and initiating one or more prediction-based actions.
Kölle and Cappon are in the same field of endeavor of measuring glucose. Cappon teaches identifying maximum and minimum post-prandial levels to classify post-prandial glycemic status. The classification is based off of, among other variables, user input data (i.e., “ground-truth data”), including estimated amount of ingested carbohydrates (Page 4, section 2.2.1). The glycemic status is defined by the minimum postprandial CGM level within a predefined postprandial time window. This time window is chosen as two – six hours after mealtime to determine the minimum glucose level after the glucose peak time (Page 2, paragraph 4; Fig. 1). Cappon further teaches that glycemic control can be obtained by adjusting the insulin bolus according to the predicted glycemic status (Page 2, paragraph 2), and that a classifier for forecasting the post-prandial glycemic status can be used to generate alerts for future adverse events, suspend basal insulin delivery, suggest carbohydrate intake to prevent hypoglycemia, and/or further modulate the insulin dose to be delivered at mealtime (Page 6, paragraph 5 – Page 7, paragraph 1). Cappon discusses this management system is accurate at discriminating between the different post-prandial glycemic classes and improve post-prandial glycemic control (Pages 8-9, discussion and conclusions). As Kölle discusses their method may be applied for insulin bolus administration to improve the outcomes of fully automated closed-loop glucose control, Cappon teaches the method of classifying future postprandial glycemic status to modulate insulin doses to be delivered at mealtime. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Kölle with the future postprandial glycemic status classification as taught by Cappon, the benefit being improving postprandial glycemic control.
Regarding claim 2, the combination of Kölle and Cappon disclose the method of claim 1. Kölle further discloses wherein: the excursion initiation probability is determined based at least in part on a first comparison between a neighboring CGM moving average and a neighboring CGM moving average threshold (Page 596, Col 2, paragraph 4, wherein a moving horizon estimator is used to estimate the glucose rate of appearance. A meal is detected if the current glucose rate of appearance exceeds a threshold).
the neighboring CGM moving average threshold is determined based at least in part on a CGM measurement for a temporal unit of the first temporal unit and one or more CGM measurements for one or more temporal units of the first temporal unit preceding the temporal unit (Page 596, Col 2, paragraph 5, “The last 20 nodes of the estimated glucose rate of appearance horizons, a period of the most current 100 minutes, are used for detection” for the meal onset determination).
Kölle does not explicitly disclose calculating an excursion termination probability for the excursion end time. However, Kölle does disclose calculating the excursion initiation probability using a moving average as described above. Kölle discusses that the moving horizon estimation method is useful due to slightly fewer false alarms and faster detection (Page 599, Col 1, paragraph 2). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of determining an excursion termination probability as disclosed by Kölle and Cappon to incorporate the moving average horizon method disclosed by Kölle, the benefit being faster detection and fewer false alarms.
Regarding claim 4, the combination of Kölle and Cappon disclose the method of claim 1. Kölle further discloses wherein:
the excursion initiation probability is determined by providing CGM measurements to the machine learning model,
the machine learning model is configured to process the CGM measurements to generate the excursion initiation probability, and
the machine learning model is trained using the ground-truth data, wherein the ground-truth data is determined based at least in part on one or more user-supplied meal session initiation indicators (Page 596, Col 2, paragraph 3 – Page 597, Col 1, paragraph 2: wherein the Bergman model uses the moving horizon estimator and LDA to determine/classify “meal onset”; Page 599, Col 1, paragraph 3, “The classification method (LDA), on the other hand, could adapt automatically: The user would need to confirm the onset of meals occasionally”. Examiner interprets this step as training the classification method based in part of the user confirming the onset of meals as the method would calibrate the CGM per user input).
Regarding claim 6, the combination of Kölle and Cappon disclose the method of claim 1. Kölle further discloses wherein the machine learning model comprises a steady-state glucose-insulin prediction machine learning model, a glucose-biased glucose-insulin prediction machine learning model, a hybrid glucose-insulin prediction machine learning model, an excursion termination detection machine learning model, a parameter space refinement machine learning model, or any combination thereof (Page 599, Col 2, paragraph 6 – Page 600, Col 1, wherein the Bergman model describes glucose-insulin dynamics. The model uses data such as glucose concentration in plasma, the action of insulin, the rate of appearance of glucose in plasma, insulin sensitivity as inputs/outputs; Applicant defines, for example, a “glucose-biased glucose-insulin prediction machine learning model” as a model that relates current glucose concentration to a current exogenous glucose infusion rate (Paragraph 0040 of the instant application). As such, Examiner interprets this model to read on at least one of the claimed “glucose-insulin” prediction machine learning models).
Regarding claim 8, the combination of Kölle and Cappon disclose the method of claim 1. Cappon discloses, as described above, wherein the one or more prediction-based actions comprise administration of an insulin sensitizing drug or an insulin stimulating drug to the end-user (Page 6, paragraph 5 – Page 7, paragraph 1, wherein the XGB classifier is used to adjust meal insulin bolus. Applicant described an insulin stimulating drug as being exogenous insulin an insulin sensitizing drug as any suitable chemical, substance, compound, or combination thereof that increases the rate at which glucose is removed from the blood stream (Paragraph 0253 of the instant application) and. The method of Cappon uses the forecast of the glycemic status to adjust the insulin delivery, which Examiner interprets as adjusting the administration of an insulin stimulating/sensitizing drug, i.e., exogenous insulin).
Regarding claim 11, Kölle discloses a system comprising one or more processors and one or more memories storing processor-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
receiving, originating from a continuous glucose monitoring (CGM) device, CGM data for an end-user (Page 595, Col 2, paragraph 2, “The data set consists of CGM measurements from a subcutaneous sensor”);
determining an excursion start time of the CGM data based at least in part on an excursion initiation probability for a first temporal unit associated with the CGM data (Page 596, Col 2, paragraph 1, wherein the beginning of the meals was marked when the CGM changed with more than 1mg/dL/min; Page 601, Col 1, paragraph 2, wherein a pattern recognition performed by LDA was used to differentiate between meal onset and no meal onset based on CGM data and estimated glucose rate of appearance Ra. The LDA assigns posterior probabilities than an observation belong to the class “meal onset”. “Meal onset” is interpreted to be an excursion start time as Kölle focuses on the glucose excursion caused by meals);
determining an excursion end time (Page 596, Col 2, paragraph 2, wherein the window defining the meal ends no later than 60 min after meal onset);
identifying a time interval within the CGM data that corresponds to a glucose surge excursion based at least in part on the excursion start time and the excursion end time (Page 596, Col 2, paragraph 1, wherein the meal is defined by the “meal onset”, or the beginning of the CGM data changing by more than 1mg/dL/min; Page 596, Col 2, paragraph 4, wherein the meal is considered having ended no later than 60 min after meal onset; The “meal onset” is interpreted as a glucose surge excursion as the measured glucose rapidly rises and is marked by both the meal onset and the end of the meal, where glucose would be elevated).
Kölle does not disclose calculating an excursion termination probability for the excursion end time. While Kölle discusses that meal detection and classification may be used to estimate an appropriate insulin bolus (Page 599, Col 1, paragraph 5) and that meal detection with subsequent insulin bolus administration can improve the outcomes of fully automated closed-loop glucose control (Page 594, Col 1, paragraph 1), Kölle fails to disclose generating a glucose-insulin prediction and initiating one or more prediction-based actions.
Kölle and Cappon are in the same field of endeavor of measuring glucose. Cappon teaches identifying maximum and minimum post-prandial levels to classify post-prandial glycemic status. The classification is based off of, among other variables, user input data (i.e., “ground-truth data”), including estimated amount of ingested carbohydrates (Page 4, section 2.2.1). The glycemic status is defined by the minimum postprandial CGM level within a predefined postprandial time window. This time window is chosen as two – six hours after mealtime to determine the minimum glucose level after the glucose peak time (Page 2, paragraph 4; Fig. 1). Cappon further teaches that glycemic control can be obtained by adjusting the insulin bolus according to the predicted glycemic status (Page 2, paragraph 2), and that a classifier for forecasting the post-prandial glycemic status can be used to generate alerts for future adverse events, suspend basal insulin delivery, suggest carbohydrate intake to prevent hypoglycemia, and/or further modulate the insulin dose to be delivered at mealtime (Page 6, paragraph 5 – Page 7, paragraph 1). Cappon discusses this management system is accurate at discriminating between the different post-prandial glycemic classes and improve post-prandial glycemic control (Pages 8-9, discussion and conclusions). As Kölle discusses their method may be applied for insulin bolus administration to improve the outcomes of fully automated closed-loop glucose control, Cappon teaches the method of classifying future postprandial glycemic status to modulate insulin doses to be delivered at mealtime. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Kölle with the future postprandial glycemic status classification as taught by Cappon, the benefit being improving postprandial glycemic control.
Regarding claim 13, the combination of Kölle and Cappon disclose the method of claim 11. Kölle further discloses wherein:
the excursion initiation probability is determined by providing CGM measurements to the machine learning model,
the machine learning model is configured to process the CGM measurements to generate the excursion initiation probability, and
the machine learning model is trained using the ground-truth data, wherein the ground-truth data is determined based at least in part on one or more user-supplied meal session initiation indicators (Page 596, Col 2, paragraph 3 – Page 597, Col 1, paragraph 2: wherein the Bergman model uses the moving horizon estimator and LDA to determine/classify “meal onset”; Page 599, Col 1, paragraph 3, “The classification method (LDA), on the other hand, could adapt automatically: The user would need to confirm the onset of meals occasionally”. Examiner interprets this step as training the classification method based in part of the user confirming the onset of meals as the method would calibrate the CGM per user input).
Regarding claim 14, the combination of Kölle and Cappon disclose the method of claim 11. Cappon discloses, as described above, wherein the one or more prediction-based actions comprise administration of an insulin sensitizing drug or an insulin stimulating drug to the end-user (Page 6, paragraph 5 – Page 7, paragraph 1, wherein the XGB classifier is used to adjust meal insulin bolus. Applicant described an insulin stimulating drug as being exogenous insulin an insulin sensitizing drug as any suitable chemical, substance, compound, or combination thereof that increases the rate at which glucose is removed from the blood stream (Paragraph 0253 of the instant application) and. The method of Cappon uses the forecast of the glycemic status to adjust the insulin delivery, which Examiner interprets as adjusting the administration of an insulin stimulating/sensitizing drug, i.e., exogenous insulin).
Regarding claim 17, Kölle discloses one or more non-transitory computer-readable storage media including instructions that, when executed by one or more processors, cause the one or more processors to:
receive, originating from a continuous glucose monitoring (CGM) device, CGM data for an end-user (Page 595, Col 2, paragraph 2, “The data set consists of CGM measurements from a subcutaneous sensor”);
determine an excursion start time of the CGM data based at least in part on an excursion initiation probability for a first temporal unit associated with the CGM data (Page 596, Col 2, paragraph 1, wherein the beginning of the meals was marked when the CGM changed with more than 1mg/dL/min; Page 601, Col 1, paragraph 2, wherein a pattern recognition performed by LDA was used to differentiate between meal onset and no meal onset based on CGM data and estimated glucose rate of appearance Ra. The LDA assigns posterior probabilities than an observation belong to the class “meal onset”. “Meal onset” is interpreted to be an excursion start time as Kölle focuses on the glucose excursion caused by meals);
determine an excursion end time (Page 596, Col 2, paragraph 2, wherein the window defining the meal ends no later than 60 min after meal onset);
identify a time interval within the CGM data that corresponds to a glucose surge excursion based at least in part on the excursion start time and the excursion end time (Page 596, Col 2, paragraph 1, wherein the meal is defined by the “meal onset”, or the beginning of the CGM data changing by more than 1mg/dL/min; Page 596, Col 2, paragraph 4, wherein the meal is considered having ended no later than 60 min after meal onset; The “meal onset” is interpreted as a glucose surge excursion as the measured glucose rapidly rises and is marked by both the meal onset and the end of the meal, where glucose would be elevated).
Kölle does not disclose calculating an excursion termination probability for the excursion end time. While Kölle discusses that meal detection and classification may be used to estimate an appropriate insulin bolus (Page 599, Col 1, paragraph 5) and that meal detection with subsequent insulin bolus administration can improve the outcomes of fully automated closed-loop glucose control (Page 594, Col 1, paragraph 1), Kölle fails to disclose generating a glucose-insulin prediction and initiating one or more prediction-based actions.
Kölle and Cappon are in the same field of endeavor of measuring glucose. Cappon teaches identifying maximum and minimum post-prandial levels to classify post-prandial glycemic status. The classification is based off of, among other variables, user input data (i.e., “ground-truth data”), including estimated amount of ingested carbohydrates (Page 4, section 2.2.1). The glycemic status is defined by the minimum postprandial CGM level within a predefined postprandial time window. This time window is chosen as two – six hours after mealtime to determine the minimum glucose level after the glucose peak time (Page 2, paragraph 4; Fig. 1). Cappon further teaches that glycemic control can be obtained by adjusting the insulin bolus according to the predicted glycemic status (Page 2, paragraph 2), and that a classifier for forecasting the post-prandial glycemic status can be used to generate alerts for future adverse events, suspend basal insulin delivery, suggest carbohydrate intake to prevent hypoglycemia, and/or further modulate the insulin dose to be delivered at mealtime (Page 6, paragraph 5 – Page 7, paragraph 1). Cappon discusses this management system is accurate at discriminating between the different post-prandial glycemic classes and improve post-prandial glycemic control (Pages 8-9, discussion and conclusions). As Kölle discusses their method may be applied for insulin bolus administration to improve the outcomes of fully automated closed-loop glucose control, Cappon teaches the method of classifying future postprandial glycemic status to modulate insulin doses to be delivered at mealtime. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Kölle with the future postprandial glycemic status classification as taught by Cappon, the benefit being improving postprandial glycemic control.
Regarding claim 18, the combination of Kölle and Cappon disclose the method of claim 17. Cappon discloses, as described above, wherein the one or more prediction-based actions comprise administration of an insulin sensitizing drug or an insulin stimulating drug to the end-user (Page 6, paragraph 5 – Page 7, paragraph 1, wherein the XGB classifier is used to adjust meal insulin bolus. Applicant described an insulin stimulating drug as being exogenous insulin an insulin sensitizing drug as any suitable chemical, substance, compound, or combination thereof that increases the rate at which glucose is removed from the blood stream (Paragraph 0253 of the instant application) and. The method of Cappon uses the forecast of the glycemic status to adjust the insulin delivery, which Examiner interprets as adjusting the administration of an insulin stimulating/sensitizing drug, i.e., exogenous insulin).
Claims 3, 5, and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Kölle et. al. (“Pattern Recognition Reveals Characteristic Postprandial Glucose Changes: Non-Individualized Meal Detection in Diabetes Mellitus Type 1”) and Cappon et. al. (“Classification of Postprandial Glycemic Status with Application to Insulin Dosing in Type 1 Diabetes—An In Silico Proof-of-Concept”) as applied to claims 1 and 11 above, and further in view of Budiman (US 20110098548).
Regarding claims 3 and 12, the combination of Kölle and Cappon disclose the method of claim 1. Kölle suggests that a user would confirm the onset of meals (Page 599, Col 1, paragraph 3). However, Kölle and Cappon fail to explicitly disclose wherein the excursion termination probability is determined based at least in part on one or more user-supplied meal session termination indicators.
Kölle, Cappon, and Budiman are in the same field of glucose prediction. Budiman teaches a method for improving model based predictions of future blood glucose control. Budiman teaches that the system user supplied information, such as information relating to a meal or snack that has been ingested, is being ingested, or will be ingested (Paragraphs 0055 and 0066). Examiner interprets the user supplying information has the meal being “ingested” to read on the limitation of a meal session termination indicator, as the meal being ingested would necessarily be when the meal session has terminated. Budiman further discusses that user supplied data is used to identify the overall glucose absorption, speed of absorption, peak absorption, and duration of the meal, i.e., initiation and termination (Paragraph 0069). As the combination of Kölle and Cappon are concerned with measuring glucose intake, defining meals, and predicting future glucose, the method of the user supplying when they ingested a meal, taught by Budiman, would provide better accuracy to those measurements. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the meal session termination probability determination disclosed by Kölle and Cappon with the user supplying when a meal has been ingested as taught by Budiman, the benefit being providing more information for glucose absorption, speed and peak absorption, and duration of a meal.
Regarding claim 5, the combination of Kölle and Cappon disclose the method of claim 1. As discussed above, Cappon discloses determining an excursion termination probability using a machine learning model and providing the model CGM measurements (Page 3, paragraph 5 – Page 4, section 2.2.1.).
Kölle suggests that a user would confirm the onset of meals (Page 599, Col 1, paragraph 3). Separately, Cappon suggests user input to train the machine learning model (Page 4, section 2.2.1., for example, the estimated amount of ingested carbohydrates). However, the combination of Kölle and Cappon fail to explicitly disclose wherein the excursion termination probability is determined based at least in part on one or more user-supplied meal session termination indicators.
Kölle, Cappon, and Budiman are in the same field of glucose prediction. Budiman teaches a method for improving model based predictions of future blood glucose control. Budiman teaches that the system user supplied information, such as information relating to a meal or snack that has been ingested, is being ingested, or will be ingested (Paragraphs 0055 and 0066). Examiner interprets the user supplying information has the meal being “ingested” to read on the limitation of a meal session termination indicator, as the meal being ingested would necessarily be when the meal session has terminated. Budiman further discusses that user supplied data is used to identify the overall glucose absorption, speed of absorption, peak absorption, and duration of the meal, i.e., initiation and termination (Paragraph 0069). As the combination of Kölle and Cappon are concerned with measuring glucose intake, defining meals, and predicting future glucose, the method of the user supplying when they ingested a meal, taught by Budiman, would provide better accuracy to those measurements. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the meal session termination probability determination disclosed by Kölle and Cappon with the user supplying when a meal has been ingested as taught by Budiman, the benefit being providing more information for glucose absorption, speed and peak absorption, and duration of a meal.
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Kölle et. al. (“Pattern Recognition Reveals Characteristic Postprandial Glucose Changes: Non-Individualized Meal Detection in Diabetes Mellitus Type 1”) and Cappon et. al. (“Classification of Postprandial Glycemic Status with Application to Insulin Dosing in Type 1 Diabetes—An In Silico Proof-of-Concept”) as applied to claim 1 above, and further in view of Zheng et. al. (“Automated meal detection from continuous glucose monitor data through simulation and explanation”), hereinafter Zheng.
Regarding claim 7, the combination of Kölle and Cappon disclose the method of claim 1 above. Kölle further discloses wherein determining the excursion end time comprises determining one or more potential excursion end times based at least in part on the excursion initiation probability (Page 596, Col 2, paragraphs 4-5, wherein the horizon ends no later than 60 minutes after meal onset). The combination of Kölle and Cappon fail to disclose or suggest determining one or more excursion probabilities for the one or more potential excursion end times based on a temporal deviation between the excursion start time and the potential excursion end time and determining the excursion end time based on the one or more excursion probabilities.
Kölle, Cappon, and Zheng are in the same field of glucose measurements. Zheng teaches a method of automatic meal detection. The algorithm used by Zheng searches for a meal that has begun before a time t (Page 1594, Col 2, paragraphs 1-5). The model simulates meals for the future. After simulating all of the potential meals, the model determines if any of the simulated meals match the observed glucose. The model finds when the predicted glucose diverges from the observed glucose, searching for meals that may explain the difference, and generate predicted glucose trajectories. This prediction represents the best representative meal for the observed glucose (Page 1595, Col 1, paragraph 1-4). In other words, the model is using the start time of a meal and predicts different meal end times based on how the glucose is rising in the current measurements. The Examiner interprets the trajectory of the future glucose to also represent a meal end time as a meal end time would necessarily be included in this prediction when the glucose level peaks and then falls back to a baseline level or threshold. Zheng discusses this method outperforms other methods of meal detection, reliably inferring mealtimes and quantities based on the CGM data (Page 1597, Col 2). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of determining an excursion end time probability disclosed by the combination of Kölle and Cappon with the deviation of predicted meal trajectories from the meal start time as taught by Zheng, the benefit being a more reliable mealtime detection system.
Claims 9, 15, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Kölle et. al. (“Pattern Recognition Reveals Characteristic Postprandial Glucose Changes: Non-Individualized Meal Detection in Diabetes Mellitus Type 1”) and Cappon et. al. (“Classification of Postprandial Glycemic Status with Application to Insulin Dosing in Type 1 Diabetes—An In Silico Proof-of-Concept”) as applied to claims 8, 14, and 18 above, and further in view of Constantin (US 20190252079).
Regarding claims 9, 15, and 19, the combination of Kölle and Cappon disclose the method of claims 8, 14, and 18 above. Cappon discusses using insulin sensitivity as an input in the model (Page 5, paragraph 3). Kölle and Cappon fail to disclose wherein the one or more glucose-insulin predictions comprises an insulin sensitivity prediction and the administration of the insulin sensitizing drug is based at least in part on the insulin sensitivity prediction satisfying a threshold.
Kölle, Cappon, and Constantin are in the same field of glucose measurement. Constantin teaches a system for providing guidance to a user based on glucose measurements. A physiological state bay be determined by applying input into a physiology model. From the model, insulin sensitivity may be determined (Paragraph 0383). The system identifies when insulin sensitivity changes and changes appropriate percentage changes to all treatment parameters. When the system identifies insulin sensitivity has returned to a baseline, the treatment parameters are changed back to baseline (Paragraphs 0421-0422). This change from baseline that prompts changes to treatment parameters is interpreted as a threshold, as the insulin sensitivity changes enough for the system to modify treatment. As an example, Constantin discusses that the user may take less insulin due to increased insulin sensitivity (Paragraph 0322). In combination, the automatic administration of insulin as taught by Kölle and Cappon would benefit from modifying administration of insulin due to insulin sensitivity as taught by Constantin, as changes in insulin sensitivity may make the body insulin resistant (Paragraph 0404). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method administering insulin of Kölle and Cappon with the insulin sensitivity threshold as taught by Constantin, the benefit being reacting to the bodies changing resistance to insulin.
Claims 10, 16, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Kölle et. al. (“Pattern Recognition Reveals Characteristic Postprandial Glucose Changes: Non-Individualized Meal Detection in Diabetes Mellitus Type 1”) and Cappon et. al. (“Classification of Postprandial Glycemic Status with Application to Insulin Dosing in Type 1 Diabetes—An In Silico Proof-of-Concept”) as applied to claims 8, 14, and 18 above, and further in view of D’Alessandro (US 10398389).
Regarding claims 10, 16, and 20, the combination of Kölle and Cappon disclose the method of claims 8, 14, and 18 above. Kölle and Cappon fail to disclose wherein the one or more glucose-insulin predictions comprise a beta cell capacity prediction and the administration of the insulin stimulating drug is based at least in part on the beta cell capacity prediction satisfying a threshold.
D’Alessandro is pertinent art to Kölle and Cappon as it is directed to the relationship of insulin and beta cells. D’Alessandro teaches an insulin production module that estimates an individual’s current pancreatic reserve of beta cells and the amount of insulin the pancreas produces. D’Alessandro discusses that a decreasing capacity of the pancreas will reduce the amount of insulin produced. The combination of Kölle and Cappon would benefit from incorporating the prediction of beta cell capacity into their model and administering insulin in response to it, as D’Alessandro discusses that the rate of insulin production is proportional to the beta cell number and functional capacity (Col 22, line 35 – Col 23, line 15). Assigning a threshold amount to this prediction would allow the combination of Kölle and Cappon to modify the amount of insulin administered based on how much insulin the pancreas is able to produce. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of administering insulin in response to thresholds as taught by Kölle and Cappon to incorporate the beta cell capacity prediction as taught by D’Alessandro, the benefit being able to predict the amount of insulin the body can create on its own before exogenous insulin administration.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NOAH MICHAEL HEALY whose telephone number is (703)756-5534. The examiner can normally be reached Monday - Friday 8:30am - 5:30pm ET.
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, Jason Sims can be reached at (571)272-7540. 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.
/NOAH M HEALY/Examiner, Art Unit 3791
/ADAM J EISEMAN/Primary Examiner, Art Unit 3791
Prosecution Insights