DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 03/13/2026 has been entered.
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(s) 1-13, 15-17, and 19-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Prud’homme et al., US 2010/0125241, in view of Chen, WO 2019/125932 A1.
Regarding Claim 1
Prud’homme discloses a method for determining a bolus dose for a user (Prud’homme, Abstract), comprising:
receiving a macronutrient profile for a meal (meal composition and not only meal carbohydrate content) (Prud’homme, [0005] and [0021]);
determining an initial bolus dose (Prud’homme, [0029]);
predicting, based on the macronutrient profile and using a trained machine-learning model [neural network model] (Prud’homme, [0027]), a post-prandial blood glucose trace comprising one or more blood glucose readings of the user at one or more time points in a post-prandial window, given the initial bolus dose (Prud’homme, [0029]-[0031], Figure 1);
iteratively evaluating the predicted post-prandial blood glucose trace, adjusting the bolus dose (Prud’homme, [0029]-[0030], Figure 1), and re-predicting the post-prandial blood glucose trace using the trained machine-learning model until the prediction shows desired blood glucose readings (Prud’homme, [0030]); and
providing an indication of the bolus dose that produced the prediction of the desired blood glucose readings (Prud’homme, [0031]).
However, Prud’homme does not explicitly disclose that the macronutrient profile comprises an estimated total quantity of carbohydrates, fat, and protein from the meal.
Chen teaches determining a bolus dose for a user by receiving a macronutrient profile for a meal, the macronutrient profile comprising an estimated total quantity of carbohydrates, fat, and protein from the meal (Chen, [0197] and [0070]).
At the time the claimed invention was filed it would have been obvious to one of ordinary skill in the art to substitute the macronutrient profile comprising an estimated total quantity of carbohydrates, fat, and protein from the meal as taught by Chen with the macronutrient profile determination taught by Prud’homme since this would provide the advantage of covering meals of varying macronutrient composition to accurately determine bolus dosing.
Regarding Claim 2
Prud’homme and Chen teach the method as rejected in Claim 1 above. Prud’homme further discloses that the bolus dose comprises a bolus quantity and a bolus split (Prud’homme, [0030], Figures 3, 6B, 7B, 8B), the bolus split comprising a first portion of the bolus quantity to be administered at the start of the post-prandial window, and a second portion of the bolus quantity to be administered later in the post-prandial window (Prud’homme, [0030], Figures 3, 6B, 7B, 8B).
Regarding Claim 3
Prud’homme and Chen teach the method as rejected in Claims 1-2 above. Prud’homme further discloses that the machine-learning model [neural network model] is trained using historical data comprising macronutrient profiles of meals previously ingested by the user and corresponding post-prandial blood glucose traces of the user (Prud’homme, [0027] and [0078]-[0079]).
Regarding Claim 4
Prud’homme and Chen teach the method as rejected in Claims 1-3 above. Prud’homme further discloses deriving a set of one or more metrics (objective function) (Prud’homme, [0030]) from the predicted post-prandial blood glucose trace; and using the set of one or more derived metrics (objective function) to evaluate the predicted post-prandial blood glucose trace (Prud’homme, [0030]).
Regarding Claim 5
Prud’homme and Chen teach the method as rejected in Claim 3 above. Prud’homme further discloses receiving a blood glucose trace of the user from the post-prandial window (Prud’homme, [0031]); and updating the machine learning model using the received blood glucose trace or one or more metrics derived from the actual blood glucose trace all (Prud’homme, [0029]-[0031] and [0052]).
Regarding Claim 6
Prud’homme and Chen teach the method as rejected in Claims 1-3 and 5 above. Prud’homme further discloses that the blood glucose trace of the user is received from a continuous glucose monitor (212) (Prud’homme, [0071], Figure 4) worn by the user (Prud’homme, [0071]-[0074], Figure 4).
Regarding Claim 7
Prud’homme and Chen teach the method as rejected in Claims 1-3 above. Prud’homme further discloses that the input to the machine-learning model comprises insulin on board for the user, a basal insulin rate and one or more current and recent blood glucose readings (Prud’homme, [0031]).
Regarding Claim 8
Prud’homme and Chen teach the method as rejected in Claim 3 above. Prud’homme further discloses that the initial bolus dose is determined by: identifying, in a catalog of past meals consumed by the user (Prud’homme, [0078]), a closely-matched meal having a macronutrient profile that is a closest match to the macronutrient profile of the current meal (Prud’homme, [0079]); retrieving the bolus dose and a blood glucose trace for the closely-matched meal (Prud’homme, [0079]); adjusting the bolus dose to compensate for any undesirable blood glucose readings in the blood glucose trace for the closely-matched meal or for differences between the closely-matched meal and the meal; and using the adjusted bolus dose as the initial bolus dose (Prud’homme, [0081]).
Regarding Claim 9
Prud’homme and Chen teach the method as rejected in Claim 3 above. Prud’homme further discloses that the bolus dose that produced the prediction of the desired blood glucose trace is provided to an automatic drug delivery device (210) (Prud’homme, [0031]) that administers the first and second portions of the bolus dose to the user (Prud’homme, [0031] and [0071]-[0074], Figure 4).
Regarding Claim 10
Prud’homme and Chen teach the method as rejected in Claim 9 above. Prud’homme further discloses that the automatic drug delivery device receives information regarding the bolus dose that produced the prediction of the desired blood glucose trace via a wireless interface (Prud’homme, [0071]-[0074], Figure 4).
Regarding Claim 11
Prud’homme and Chen teach the method as rejected in Claim 3 above. Prud’homme further discloses that the second portion of the bolus quantity is delivered at a predetermined time after the start of the post-prandial window (Prud’homme, [0030]-[0031], Figures 3, 6B, 7B, 8B).
Regarding Claim 12
Prud’homme and Chen teach the method as rejected in Claim 3 above. Prud’homme further discloses that the second portion of the bolus quantity is delivered in one or more timed doses after the start of the post-prandial window (Prud’homme, [0030]-[0031], Figures 3, 6B, 7B, 8B).
Regarding Claim 13
Prud’homme and Chen teach the method as rejected in Claim 3 above. Prud’homme further discloses utilizing not only meal carbohydrate content to distinguish between different meal types (Prud’homme, [0005] and [0036]), while Chen teaches a macronutrient profile comprising an estimated total quantity of carbohydrates, fat, and protein from the meal (Chen, [0197] and [0070]).
Chen further teaches that the timing of the delivery of the second portion of the bolus quantity is based on a characterization of the fat and protein concentrations in the macronutrient profile of the meal (Chen, [0197]).
At the time the claimed invention was filed it would have been obvious to one of ordinary skill in the art to have the bolus quantity based on fat and protein concentrations in the macronutrient profile of the current meal as taught by Chen with that taught by Prud’homme since this would provide the advantage of covering meals of varying macronutrient composition.
Regarding Claim 15
Prud’homme and Chen teach the method as rejected in Claim 3 above. Prud’homme further discloses that the macronutrient profile of the meal is provided by the user (Prud’homme, [0058] and [0071]-[0074], Figure 4).
Regarding Claim 16
Prud’homme and Chen teach the method as rejected in Claim 15 above. Prud’homme further discloses that information regarding the meal is entered on an application running on a personal computing device (214) (Prud’homme, [0071], Figure 4) of the user (Prud’homme, [0027] and [0071]-[0074], Figure 4).
Regarding Claim 17
Prud’homme and Chen teach the method as rejected in Claim 15 above. Prud’homme further discloses that the machine-learning model executes on a personal computing device (214) (Prud’homme, [0071], Figure 4) of the user or is provided as a cloud-based service (Prud’homme, [0027] and [0071]-[0074], Figure 4).
Regarding Claim 19
Prud’homme discloses a system comprising:
a personal computing device (214) (Prud’homme, [0071]) of a user running an application (216) (Prud’homme, [0071]) enabling the user to input a macronutrient profile for a meal (Prud’homme, [0058] and [0071]-[0074], Figure 4);
a trained machine-learning model [neural network model] that predicts a post-prandial blood glucose trace comprising one or more blood glucose readings of the user at one or more points in a post-prandial window, given the macronutrient profile for the meal and an initial bolus dose (Prud’homme, [0027] and [0029]-[0031]); and
an automatic drug delivery device (210) (Prud’homme, [0071], Figure 4) in wireless communication (Prud’homme, [0072], Figure 4) with a personal computing device (214) (Prud’homme, [0071]-[0074], Figure 4);
wherein the initial bolus dose is determined based on the macronutrient profile of the meal (Prud’homme, [0021] and [0079]) and further wherein the initial bolus dose is iteratively adjusted until the machine-learning model predicts a post-prandial blood glucose trace having desired blood glucose readings (Prud’homme, [0027] and [0030]).
However, Prud’homme does not explicitly disclose that the macronutrient profile comprises an estimated total quantity of carbohydrates, fat, and protein from the meal.
Chen teaches a macronutrient profile comprising an estimated total quantity of carbohydrates, fat, and protein from the meal (Chen, [0197] and [0070]).
At the time the claimed invention was filed it would have been obvious to one of ordinary skill in the art to substitute the macronutrient profile comprising an estimated total quantity of carbohydrates, fat, and protein from the meal as taught by Chen with the macronutrient profile determination taught by Prud’homme since this would provide the advantage of covering meals of varying macronutrient composition to accurately determine bolus dosing.
Regarding Claim 20
Prud’homme and Chen teach the system as rejected in Claim 19 above. Prud’homme further discloses a continuous glucose monitor (212) worn by the user (Prud’homme, [0071]) and in wireless communication (Prud’homme, [0072]) with the personal computing device (214) (Prud’homme, [0071], Figure 4); wherein the machine-learning model is updated using actual blood glucose readings from the continuous glucose monitor (212) or using one or more metrics derived from the actual blood glucose readings (Prud’homme, [0026]-[0027] and [0071]-[0072], Figure 4).
Claim(s) 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Prud’homme et al., US 2010/0125241, in view of Chen, WO 2019/125932 A1, in view of Leifer et al., US 2019/0228856, and further in view of Hayter et al., US 2021/0050085.
Regarding Claim 14
Prud’homme and Chen teach the method as rejected in Claim 3 above. Prud’homme discloses a model (114) that is defined by a neural network model (Prud’homme, [0027]) to extract one or more features from data input to the model (Prud’homme, [0022]), and to utilize the features to provide the prediction of the post-prandial blood glucose trace (Prud’homme, [0029]-[0030]).
However, Prud’homme and Chen do not disclose that the machine-learning model comprises: a convolutional neural network that extracts one or more features from data input to the model; and a recurrent neural network that uses the features identified by the convolutional neural network to provide the prediction of the post-prandial blood glucose trace.
Leifer teaches the use of neural networks such as convolutional neural networks (CNNs) to process food related data to generate vector representations of food-related data (Leifer, [0018]). While Hayter teaches the use of a recurrent neural network (RNN) in a glucose value prediction algorithm that is continuously trained with data from the patient (user) (Hayter, [0310]).
Therefore, as Prud’homme discloses a neural network model, it would have been obvious to one of ordinary skill in the art that the functions of the neural network model of Prud’homme/Chen are performed by a convolution neural network (as taught by Leifer) and a recurrent neural network (as taught by Hayter) in order to improve glucose management.
Claim(s) 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Prud’homme et al., US 2010/0125241, in view of Chen, WO 2019/125932 A1, and further in view of Finan, US 2014/0005633.
Regarding Claim 18
Prud’homme and Chen teach the method as rejected in Claim 5 above. Prud’homme further discloses that the machine-learning model is updated based on subsequent meals entered by the user and the resulting post-prandial blood glucose traces (Prud’homme, [0078]-[0079]).
However, Prud’homme does not explicitly disclose that the machine-learning model is initially trained on a wide population of users or a cluster of users similar to the user.
Finan teaches a model that is trained on a wide population of users (Finan, [0039]).
At the time the claimed invention was filed it would have been obvious to one of ordinary skill in the art to have the machine-learning model is initially trained on a wide population of users or a cluster of users similar to the user as taught by Finan with that taught by Prud’homme/Chen since this would provide the advantage of desired insulin infusion to an average user.
Response to Arguments
Applicant’s arguments, filed 03/13/2026, with respect to the rejection of claims 1-13, 15-17, and 19-20 under 35 U.S.C. 103 (Prud’homme et al., US 2010/0125241, in view of Chen, WO 2019/125932 A1) have been fully considered and are not persuasive.
With regards to the Applicant’s argument, on page 8, that Prud’homme does not consider the overall macronutrient profile, and the combination of Prud’homme and Chen would not change this, the Examiner is unconvinced.
Prud’homme discloses that the meal composition (overall macronutrient profile) is accounted for and not only meal carbohydrate content (Prud’homme, [0005]). While Prud’homme does not disclose what else makes up the meal composition (overall macronutrient profile), Chen teaches that in a system/method that determines a bolus dose for a user utilizing a macronutrient profile that includes an estimated total quantity of carbohydrates, fat, and protein from the meal (Chen, [0070] and [0097]). Therefore, it is known in the art that a meal composition (overall macronutrient profile) includes carbohydrates, fat, and protein, and it would be obvious to one of ordinary skill in the art that the meal composition (macronutrient profile) of Prud’homme accounts for fat and protein in addition to carbohydrate content.
With regards to the Applicant’s argument, on pages 9-10, that the Application discloses a time-varying profile because the relative amounts of fat, protein, and carbohydrates in the meal are considered, and that this is not possible in Prud’homme because Prud’homme models select between constant rates, the Examiner is unconvinced.
In response to applicant's argument that the references fail to show certain features of the invention, it is noted that the features upon which applicant relies (i.e., the time-varying profile due to the relative amounts of fat, protein, and carbohydrates in the meal) are not recited in the rejected claim(s). Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993).
With regards to the Applicant’s argument, on page 10, that Chen does not suggest calculating the post-prandial blood glucose trace with the macronutrients (and instead determines the total bolus amount), and therefore, the combination of Prud’homme and Chen does not disclose “predicting, based on the macronutrient profile and using a trained machine-learning model, a post-prandial blood glucose trace”, the Examiner in unconvinced.
In response to applicant's arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986).
Chen is relied upon to simply teach that a macronutrient profile of a meal comprises an estimated totally quantity of carbohydrates, fat, and protein from the meal. The combination of Prud’homme and Chen teach the claimed limitations.
Applicant’s arguments, see page 11, with respect to the rejection of claim 14 under 35 U.S.C. 103 have been fully considered and are persuasive. The 35 U.S.C. 103 rejection of claim 14 has been withdrawn. However, a new ground(s) of rejection is made under 35 U.S.C. 103.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KELSEY L STANEK whose telephone number is (571)272-3565. The examiner can normally be reached Mon - Fri 8:30am-3:00pm.
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, DEVON KRAMER can be reached at (571) 272-7118. 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.
/K.L.S/Examiner, Art Unit 3741 /DEVON C KRAMER/Supervisory Patent Examiner, Art Unit 3741
Prosecution Insights