DETAILED ACTION
Applicant’s response, filed 22 June 2026, has been fully considered. The following rejections and/or objections are either reiterated or newly applied. They constitute the complete set presently being applied to the instant application.
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 Status
Claims 1-3, 5-8, 12, 13, 15, 16, 18, and 20 are pending and examined herein.
Claims 1-3, 5-8, 12, 13, 15, 16, 18, and 20 are rejected.
This Non-Final Office Action is being mailed to applicant to add rejections under 35 U.S.C. 112/b, 35 U.S.C. 102, and 35 U.S.C. 103 not necessitated by amendment.
Priority
Claims 1-3, 5-8, 12, 13, 15, 16, 18, and 20 are granted the claim to the benefit of priority to U.S. Provisional applications 62/947787 and 63/017705 filed 13 December 2019 and 30 April 2020. Thus, the effective filling date of claims 1-3, 5-8, 12, 13, 15, 16, 18, and 20 is 13 December 2019.
Drawings
The drawings received 22 June 2026 are accepted.
Claim Objections
Claim 13 is objected to because of the following informalities:
Claim 13 includes a period under the last line of the claim and should be removed. The MPEP states “Each claim begins with a capital letter and ends with a period. Periods may not be used elsewhere in the claims except for abbreviations” (MPEP 608.01(m)).
Appropriate correction is required.
Claim Interpretation
112/f Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier.
Such claim limitation are:
“a learning element that stores the set of features used for the prediction… and compares the predicted future value to the actual value to generate an error value for the predicted future value” in claim 6,
“wherein the learning element stores a series of error values associated with a corresponding series of predicted future values and provides an alert if the error values exceed a threshold value for a predetermined period of time” in claim 7,
“wherein the learning element provides an alert if the patient parameter deviates from a desired range for a predetermined period of time” in claim 8,
“a learning element that stores the features used for the prediction, the predicted future value, and an actual value… compares the predicted future value… and provides an alert if the error values exceed a threshold value for a predetermined period of time” in claim 20.
The corresponding algorithm for the learning element for performing the function of comparing predicted values is provided in [0034] of the instant disclosure and encompasses a numerical method for determining the difference between a predicted value and the actual value. The corresponding algorithm for the learning element for providing alerts is provided in [0036] of the instant disclosure.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 112
The rejection on the ground of 112/a of claims 1-12 and 18-20 for claims 1 and 18 reciting “a feature extractor that…”, “a therapeutic delivery system controller that…”, and claims 6-8 and 20 reciting “a learning element that…” in Office action mailed 19 February 2026 is withdrawn in view of the amendment of “a processor; and a non-transitory computer readable medium storing instructions executable by the processor to provide… a therapeutic delivery system controller…” in claims 1 and 18 and “the instructions being executable by the processor to further provide a learning element…” in claims 6 and 20 received 22 June 2026.
The rejection on the ground of 112/a of claims 10, 11, 17, and 19 for reciting the predictive model is implemented as (or expressed) as a multi-parameter partial differential equation in Office action mailed 19 February 2026 is withdrawn in view of the amendment which cancels these claims received 22 June 2026.
The rejection on the ground of 112/b of claims 1-12 for claim 1 reciting “the patient parameter” in Office action mailed 19 February 2026 is withdrawn in view of the amendment of “the biometric parameter” received 22 June 2026.
The rejection on the ground of 112/b of claims 1-12 and 18-20 for claims 1 and 18 reciting “the patient” in the feature extractor limitation of the claims in Office action mailed 19 February 2026 is withdrawn in view of the amendment which removes this limitation received 22 June 2026.
The rejection on the ground of 112/b of claims 9 and 12 for claim 9 reciting “a user interface that displays” and claim 12 reciting “a network interface that provides data” in Office action mailed 19 February 2026 is withdrawn in view of the amendment which cancels claims 9 and claim 12 “a network interface configured to provide patient data…” received 22 June 2026.
The rejection on the ground of 112/b of claims 1-12 and 18-20 for claims 1 and 18 reciting “a feature extractor that…”, “a therapeutic delivery system controller that…”, and claims 6-8 and 20 reciting “a learning element that…” in Office action mailed 19 February 2026 is withdrawn in view of the amendment which removes limitation of “a feature extractor that…” in claims 1 and 18 and the amendment of “a processor; and a non-transitory computer readable medium storing instructions executable by the processor to provide… a therapeutic delivery system controller…” in claims 1 and 18 and “the instructions being executable by the processor to further provide a learning element…” in claims 6 and 20 received 22 June 2026.
The rejection on the ground of 112/b of claims 1-12 and 18-20 for claims 1 and 18 for reciting “each of the set of features being associated with one of the patient and the therapeutic delivery system” in Office action mailed 19 February 2026 is withdrawn in view of the amendment of “each of the set of features being associated with one of the patient or the infusion pump” received 22 June 2026.
112/b
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.
The rejection below is newly recited.
Claims 1-3, 5-8, 12, 13, 15, 16, 18, and 20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claims 1 and 18 recite “at least one hyperparameter of a set of hyperparameters associated with the predictive model” and claim 13 recites “a set of hyperparameter values for the predictive model… adjusting the predictive model according to the received hyperparameter values” which renders the metes and bounds of the claim indefinite. The indefiniteness arises because it is unclear what is meant to be encompassed by the limitation of “hyperparameters” or “hyperparameter values”. The BRI of hyperparameters in the context of machine learning models includes configurable variables set before training to govern the learning process and includes variables such as learning rates, epochs, and batch sizes. While the instant disclosure provides examples of hyperparameters as “Hyperparameter values, representing expected physiological patient reactions…” (see instant disclosure [0034]), “the hyperparameter that represents the patient’s sensitivity to phenylephrine…” (see instant disclosure [0038]), and “the hyperparameters can represent, for example, the patient’s expected sensitivity to the therapeutic or other therapeutics provided to the patient” (see instant disclosure [0046]) which are parameters that govern the model prediction itself rather than the learning process of the model. Thus, it is unclear what configurable variables are encompassed by the limitation of “hyperparameters”. The specification does not provide a clear and precise definition of the limitation, nor would one skilled in the art recognize the metes and bounds of said limitation. Dependent claims 2, 3, 5, 6-8, 12, 15, 16, and 20 are rejected by virtue of their dependency on a rejected claim without alleviating the indefiniteness. For the sake of furthering examination, “hyperparameters” will be interpreted as configurable variables that govern the model prediction of the future biometric parameter.
Claim Rejections - 35 USC § 101
The rejection on the ground of 101 of claims 1-20 in Office action mailed 19 February 2026 is withdrawn in view of the amendment to claim 1 of “an infusion pump that delivers a therapeutic to a patient at a determined dosage… a therapeutic delivery system controller that determines the determined dosage for the therapeutic according to the predicted future value for the biometric parameter, and a user interface that is configured to display… and allow a user to change at least one hyperparameter”, the amendment to claim 13 of “an infusion pump according to a monitored patient parameter… selecting a dosage for the infusion pump according to the predicted future value of the monitored patient parameter, delivering the selected dosage of the therapeutic at the infusion pump… receiving a set of hyperparameter values for the predictive model… adjusting the predictive model according to the received set of hyperparameter values”, the amendment to claim 18 of “an infusion pump that delivers a therapeutic to a patient at a desired dosage… a processor and a non-transitory computer readable medium storing instructions executable by the processor to provide…a therapeutic delivery system controller that determines the desired dosage for the therapeutic according to the predicted future value for the biometric parameter, and a user interface that is configured to display… and allow a user to change at least one hyperparameter” received 22 June 2026. The claims are patent eligible because claims 1 and 18 provide a particular machine including an infusion pump, monitoring devices, and a computer system for determining a dosage of a drug which the infusion pump delivers to a patient and claim 13 provides an additional element of a particular treatment by delivering a selected dosage of the therapeutic at the infusion pump where the selected dosage is determined based on a predicted future value.
Claim Rejections - 35 USC § 102
The rejection on the ground of 102(a)(1) claims 1, 3-7, 13, 15, 18, and 20 as being anticipated by Cinar et al. (US 2016/0354543 A1; previously cited) in Office action mailed 19 February 2026 is withdrawn in view of the amendment of claims 1 and 18 of “a user interface that is configured to display the predicted future value for the biometric parameter and the determined dosage to a user and allow a user to change at least one hyperparameter of a set of hyperparameters associated with the predictive model” and the amendment of claim 13 of “displaying each of the monitored patient parameter and the predicted future value to a user at a user interface, receiving a set of hyperparameters values for the predictive model from a user via the user interface and adjusting the predictive model according to the received set of hyperparameter values” received 22 June 2026.
The rejection on the ground of 102(a)(1) claims 13 and 15 as being anticipated by Mulligan et al. (US 20150065826 A1; previously cited) in Office action mailed 19 February 2026 is withdrawn in view of the amendment of claim 13 of “displaying each of the monitored patient parameter and the predicted future value to a user at a user interface, receiving a set of hyperparameters values for the predictive model from a user via the user interface and adjusting the predictive model according to the received set of hyperparameter values” received 22 June 2026.
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 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)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
The rejection below is newly recited.
Claims 1, 3, 5, and 13 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Mazlish et al. (US 20180200435; newly cited).
Claim 1 is directed to a system comprising an infusion pump that delivers a therapeutic to a patient at a determined dosage,
Mazlish et al. shows a system comprising an infusion pump that delivers insulin to a patient at a determined dosage (Mazlish et al. [0039] and [0040]).
a monitoring device that includes a sensor for measuring a biometric parameter of the patient,
Mazlish et al. shows the system includes a glucose monitoring device for measuring glucose for a patient (Mazlish et al. [0041]).
a processor and a non-transitory computer readable medium storing instructions executable by the processor to provide: a predictive model that predicts a future value for the biometric parameter at a given time according to a set of features, each of the set of features being associated with one of the patient or the infusion pump
Mazlish et al. shows the system includes a control device which is a computing device which can predict future blood glucose levels (Mazlish et al. [0041]). Mazlish et al. shows a predictive model that predicts future glucose values at a given time using a set of features of past and current carbohydrate, insulin, and blood glucose values (Mazlish et al. [0221]-[0235]).
a therapeutic delivery system controller that determines the determined dosage for the therapeutic according to the predicted future value for the biometric parameter
Mazlish et al. shows the control device can determine the basal delivery rate based on projected blood glucose levels (Mazlish et al. [0041]).
and a user interface that is configured to display the predicted future value for the biometric parameter and the determined dosage to a user and allow a user to change at least one hyperparameter of a set of hyperparameters associated with the predictive model.
Mazlish et al. shows a user interface that is configured to display the predicted future value for the biometric parameter (Mazlish et al. Fig. 20) and allows a user to change at least one hyperparameter of a set of hyperparameters associated with the predictive model as the ability to change a carbohydrate ratio and an insulin sensitivity factor which are configurable variables that govern the prediction of the future glucose values (Mazlish et al. Fig. 6 and [0221]-[0235]).
Claim 3 is directed to wherein the biometric parameter is a blood glucose of a patient.
Mazlish et al. shows the biometric parameter is a blood glucose of a patient (Mazlish et al. [0221]).
Claim 5 is directed to wherein the set of features includes one of a current and a past dosage associated with the infusion pump.
Mazlish et al. shows a physiology model to predict future blood glucose values using past and current insulin values (Mazlish et al. [0221]).
Claim 13 is directed to a method for controlling an infusion pump according to a monitored patient parameter, the method comprising: monitoring a patient parameter
Mazlish et al. shows using information from a glucose measurement device such as a continuous glucose monitor to have up-to-date blood glucose data in order to determine how to adjust basal insulin delivery rates (Mazlish et al. [0194]).
extracting a set of features for a patient including at least the monitored patient parameter, predicting a future value for the monitored patient parameter at a predictive model according to the extracted set of features
Mazlish et al. shows determining a future blood glucose level for a time interval using features of past and current carbohydrate, insulin and blood glucose levels (Mazlish et al. [0007], [0195], and [0221]-[0235])
selecting a dosage for the infusion pump according to the predicted future value of the monitored patient parameter, delivering the selected dosage of the therapeutic at the infusion pump,
Mazlish et al. shows determining a basal insulin delivery for the time interval based on the determined future blood glucose level (Mazlish et al. [0007], [0194], and [0196]). Mazlish et al. shows configuring an insulin delivery system to deliver insulin during the time interval according to the determined basal insuling delivery (Mazlish et al. [0007], [0194], and [0196]).
displaying each of the monitored patient parameter and the predicted future value to a user at a user interface
Mazlish et al. shows a user interface that is configured to display the monitored blood glucose level and the predicted future glucose value (Mazlish et al. Fig. 20)
receiving a set of hyperparameter values for the predictive model from a user via the user interface and adjusting the predictive model according to the received set of hyperparameter values.
Mazlish et al. shows receiving a set of hyperparameter values for the predictive model from a user interface as receiving a carbohydrate ratio and an insulin sensitivity factor which are configurable variables of the model that govern the prediction of the future glucose values (Mazlish et al. Fig. 6 and [0221]-[0235]).
The rejection below is newly recited.
Claims 1, 2, and 12 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Hanh et al. (US 20200038587 A1; effective filling date of 12 February 2018 and newly cited).
Claim 1 is directed to a system comprising an infusion pump that delivers a therapeutic to a patient at a determined dosage,
Hanh et al. shows a system comprising a treatment unit configured to administer a fluid volume of a drug to a subject (Hanh et al. [0020] and [0021]).
a monitoring device that includes a sensor for measuring a biometric parameter of the patient,
Hanh et al. shows the system comprises a device to acquire physiological signals such as blood pressure (Hanh et al. [0021]).
a processor and a non-transitory computer readable medium storing instructions executable by the processor to provide: a predictive model that predicts a future value for the biometric parameter at a given time according to a set of features, each of the set of features being associated with one of the patient or the infusion pump
Hahn et al. shows the system includes a processor and a memory that is configured to forecast a future cardio vascular (CV) parameter, such as blood pressure, based on prior BP trend data and prior volume administration data (Hahn et al. [0040]).
a therapeutic delivery system controller that determines the determined dosage for the therapeutic according to the predicted future value for the biometric parameter
Hanh et al. shows that the processor uses the predicted future prediction to determine and implement an optimized treatment for controlling the cardiovascular state of the subject (Hanh et al. [0028]).
and a user interface that is configured to display the predicted future value for the biometric parameter and the determined dosage to a user and allow a user to change at least one hyperparameter of a set of hyperparameters associated with the predictive model.
Hanh et al. shows displaying a report on a graphical user interface which includes information of future time trajectory for one or more CV parameters and an indication regarding the timing of volume administration for maintaining or achieving a target CV states (such as maintaining a CV parameter within a pre-specified range) (Hanh et al. [0027]). Hahn et al. further shows allowing a user to change configurable parameters associated with the predictive model through the input portion of the system (Hanh et al. [0042]).
Dependent claim 2 is directed to wherein the biometric parameter is a blood pressure of the patient.
Hanh et al. shows the system comprises a device to acquire physiological signals such as blood pressure (Hanh et al. [0021]).
Dependent claim 12 is directed to the system further comprises a network interface configured to provide patient data from an electronic health records database, at least one feature of the set of featured being determined from the patient data.
Hanh et al. shows that a subjects information may be retrieved from the subject’s electronic medical record via a wired or wireless connection to a server or database containing such information (Hanh et al. [0034]). Hahn et al. shows that information of volume administered over time and type of fluid (such as drug or medication) is obtained from the subject’s electronic medical records which is interpreted as a feature in the feature set for predicting the future biometric parameter being determined from the patient data (Hahn et al. [0035]).
Claim Rejections - 35 USC § 103
The rejection on the ground of 103 of claims 1, 2, 5, 6, 8, 12, and 18 as being unpatentable over Mulligan et al. (US 20150065826 A1; previously cited) in view of Jeong et al. (Appl. Sci. 2019, 9, 5135; previously cited) in Office action mailed 19 February 2026 is withdrawn in view of the amendment to claims 1 and 18 of “a user interface that is configured to display the predicted future value.. and allow a user to change at least one hyperparameter of a set of hyperparameters associated with the predictive model” received 22 June 2026.
The rejection on the ground of 103 of claim 9 as being unpatentable over Cinar et al. (US 20160354543 A1; previously cited) as applied to claim 1 in the 35 U.S.C. 102 rejection above, and further in view of Mazlish et al. (US 20190221307 A1; previously cited) in Office action mailed 19 February 2026 is withdrawn in view of the amendment which cancels claims 9 received 22 June 2026.
The rejection on the ground of 103 of claim 16 as being unpatentable over Mulligan et al. (US 20150065826 A1; previously cited) as applied to claim 13 in the 35 U.S.C. 102 rejection above, and further in view of Jeong et al. (Appl. Sci. 2019, 9, 5135; newly cited) in Office action mailed 19 February 2026 is withdrawn in view of the amendment to claim 13 of “delivering the selected dosage of the therapeutic at the infusion pump, displaying each of the monitored patient parameter and the predicted future value to a user at a user interface, receiving a set of hyperparameters values for the predictive model from a user via the user interface and adjusting the predictive model according to the received set of hyperparameter values” received 22 June 2026.
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The rejection below is newly recited.
Claims 6, 7, and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Mazlish et al. (US 20180200435; newly cited) as applied to claims 1 and 13 under 35 U.S.C. 102 above, and further in view of Doron et al. (US 20200197606 A1; effective filling date 13 July 2018 and newly cited).
Claim 6 is directed to a learning element that stores the set of features used for the prediction, the predicted future value, and an actual value for the monitored biometric parameter at the given time and compares the predicted future value to the actual value to generate an error value for the predicted future value.
Mazlish et al. shows the system that predicts future glucose values and stores blood glucose data and historical pump usage information such as dosage logs of insulin (Mazlish et al. [0061] and [0216]).
Mazlish et al. does not show storing the predicted future value or comparing the predicted future value to the actual value to generate an error value for the predicted future value.
Like Mazlish et al., Doron et al. shows predicting future glucose values of a patient. Doron et al. shows calculating an indicator representative of the error between the blood glucose estimated from a model that predicts the future evolution of a patients blood glucose over a period of time and the real blood glucose measured by the sensor (Doron et al. abstract). Doron et al. shows that the numerical indicator includes a difference between the real glucose measured by the sensor and the blood glucose estimated by the model at a given time which provides a value of an error (Doron et al. [0016]). It would have been obvious to one of ordinary skill in the art to have stored that predicted future glucose value estimated by the model to facilitate the comparison of the estimated future value with the measured glucose value during the same time period by calculating the difference between these values.
Claim 7 is directed to wherein the learning element stores a series of error values associated with a corresponding series of predicted future values and provides an alert if the error values exceed a threshold value for a predetermined period of time.
Mazlish et al. shows a system which provides alerts or alarms when information for the prediction of future glucose appears abnormal (Mazlish et al. [0080] and [0218]).
Mazlish et al. does not show error values associated with a corresponding series of predicted future values and providing an alert if the error values exceed a threshold value for a predetermined period of time.
Like Mazlish et al., Doron et al. shows predicting future glucose values of a patient. Doron et al. shows analyzing the quality/reliability of the prediction model using numerical indicators representative of the error between the blood sugar estimated based on the model and the real blood sugar measured by the sensor and is considered unreliable when a value of these indicators exceeds a threshold value during a time period (Doron et al. [0059]). Doron et al. shows if the physiological model is considered to be insufficiently reliable the system stops the use of this model to regulate the delivery of insulin (Doron et al. [0060]).
Claim 15 is directed to storing the set of features used for the prediction, the predicted future value, and an actual value for the monitored patient parameter at the given time and comparing the predicted future value to the actual value to generate an error value for the predicted future value.
Mazlish et al. shows the system stores blood glucose data and historical pump usage information such as dosage logs of insulin (Mazlish et al. [0061] and [0216]).
Mazlish et al. does not show storing the predicted future value or comparing the predicted future value to the actual value to generate an error value for the predicted future value.
Like Mazlish et al., Doron et al. shows predicting future glucose values of a patient. Doron et al. shows calculating an indicator representative of the error between the blood glucose estimated from a model that predicts the future evolution of a patients blood glucose over a period of time and the real blood glucose measured by the sensor (Doron et al. abstract). Doron et al. shows that the numerical indicator includes a difference between the real glucose measured by the sensor and the blood glucose estimated by the model at a given time which provides a value of an error (Doron et al. [0016]). It would have been obvious to one of ordinary skill in the art to have stored that predicted future glucose value estimated by the model to facilitate the comparison of the estimated future value with the measured glucose value during the same time period by calculating the difference between these values.
It would have been obvious to one of ordinary skill in the art before the effective filling date of the invention to have combined the system and process of predicting future glucose values utilizing a model which intakes features of past and current blood glucose values and insulin values for determining a dosage of insulin to deliver to a patient of Mazlish et al. with the procedure of determining a reliability of a model which predicts future glucose values when determining a dosage of insulin to deliver of Doron et al. because this would allow for a system and process capable of determining the reliability of the model predicting the future glucose value that is used to determine the dosage of insulin administered to a patient and to stop the use of the model in determining the dosage if the model is identified as unreliable thus limiting the risk of placing a patient in a hyperglycemia or hypoglycemia situation (Doron et al. [0005] and [0060]). It would have been further obvious to one of ordinary skill in the art before the effective filling date of the invention to have modified the condition of triggering the alerts/alarms of Mazlish et al. in view of Cinar et al. to be the condition when the model is determined to be unreliable causing the system to stop the use of the model in determining the dosage of insulin of Doron et al. because this would provide information to the user that the mode of operation (e.g., how insulin dosage is being determined and administered to the patient) has changed (Doron et al. [0059]-[0060]). One would have a reasonable expectation of success because Mazlish et al. shows a systems and process of controlling the blood glucose level of a patient using a model which predicts a future glucose level of a patient while Doron et al. provides a procedure of analyzing the reliability of a model which predicts a future glucose level when controlling the blood glucose level of a patient.
The rejection below is newly recited.
Claims 6 and 8 are rejected under 35 U.S.C. 103 as being unpatentable over Hanh et al. (US 20200038587 A1; effective filling date of 12 February 2018 and newly cited) as applied to claim 1 under 35 U.S.C. 102 above, and further in view of Doron et al. (US 20200197606 A1; effective filling date 13 July 2018 and newly cited).
Claim 6 is directed to a learning element that stores the set of features used for the prediction, the predicted future value, and an actual value for the monitored biometric parameter at the given time and compares the predicted future value to the actual value to generate an error value for the predicted future value.
Hahn et al. shows the system includes a processor and a memory that is configured to forecast a future CV parameter, such as blood pressure, based on prior BP trend data and prior volume administration data (Hahn et al. [0040]). Hahn et al. shows storing measurement data of the subject is stored in the memory of the system (Hanh et al. [0023]).
Hahn et al. does not show storing the predicted future value or comparing the predicted future value to the actual value to generate an error value for the predicted future value.
Like Hanh et al., Doron et al. shows predicting future values of a biometric parameter of a patient in an automated drug delivery system. Doron et al. shows calculating an indicator representative of the error between estimated future values of a biometric parameter from a model and a biometric parameter of a patient measured by the sensor (Doron et al. abstract). Doron et al. shows that the numerical indicator includes a difference between the real measured biometric parameter by the sensor and the biometric parameter estimated by the model at a given time which provides a value of an error (Doron et al. [0016]).
Claim 8 is directed to wherein the learning element provides an alert if the patient parameter deviates from a desired range for a predetermined period of time.
Hahn et al. shows a system which includes a model for predicting the future cardiovascular parameter of a patient can provide and alert or notification related to a likelihood that the one or more cardiovascular parameters will fall outside one or more threshold at one or more pre-determined timepoints (Hanh et al. [0027]).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the invention to have combined the system of predicting future biometric parameters utilizing a model which intakes features of past biometric parameters and therapeutic interventions for determining a fluid volume of a therapeutic to deliver to a patient of Hanh et al. with the procedure of determining a reliability of a model which predicts future biometric parameters when determining a dosage of a therapy to deliver to a patient of Doron et al. because this would allow for a system capable of determining the reliability of the model predicting the future biometric parameter value that is used to determine the dosage of therapy administered to a patient and to stop the use of the model in determining the dosage if the model is identified as unreliable thus limiting risk of providing inaccurate dosages (Doron et al. [0005] and [0060]). One would have a reasonable expectation of success because Hahn et al. shows a system of controlling a biometric parameter of a patient using a model which predicts a future biometric value of a patient while Doron et al. provides a procedure of analyzing the reliability of a model which predicts a future biometric value when controlling the biometric parameter of a patient.
The rejection below is newly recited.
Claims 16 is rejected under 35 U.S.C. 103 as being unpatentable over Mazlish et al. (US 20180200435; newly cited) as applied to claim 13 under 35 U.S.C. 102 above, and further in view of Cinar et al. (US 20160354543 A1; previously cited).
Claim 16 is directed to wherein monitoring a patient parameter comprises monitoring a plurality of patient parameters and the set of features includes a feature representing a current dosage and a past dosage of the therapeutic being provided by the infusion pump and at least two features derived from the plurality of patient parameters.
Mazlish et al. shows monitoring a patient parameter such as a blood glucose level using a continuous glucose monitor (Mazlish et al. [0194]). Mazlish et al. shows a predictive model that predicts future glucose values at a given time using a set of features of past and current insulin, and blood glucose values (Mazlish et al. [0221]-[0235]).
Mazlish et al. does not show monitoring a plurality of patient parameters and at least two features derived from the plurality of patient parameters.
Like Mazlish et al., Cinar et al. shows monitoring patient parameters to predict a future glucose value and controls insulin infusion based on predicted future glucose levels. Cinar et al. shows monitoring physiological data such as heart rate of a patient and using this measured value along with blood glucose values to predict future blood glucose values (Cinar et al. [0010], [0013], and [0040]).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the invention to have modified the process of predicting future glucose levels of a patient using features of past and current blood glucose and insulin values of Mazlish et al. to incorporate the use of additional monitored physiological information such as heart rate for the prediction of future glucose values of a patient of Cinar et al. because this allows for a process that incorporates information on the physiological state of the patient which impacts blood glucose values of a patient in the prediction of the future glucose prediction used to control the automatic infusion of insulin (Cinar et al. [0009] and [0011]). One would have a reasonable expectation of success because both Mazlish et al. and Cinar et al. utilizes patient biometric information to predict future glucose values for controlling the infusion of insulin to a patient.
The rejection below is newly recited.
Claims 18 is rejected under 35 U.S.C. 103 as being unpatentable over Mazlish et al. (US 20180200435; newly cited) in view of Cinar et al. (US 20160354543 A1; previously cited).
Claim 18 is directed to a system comprising: an infusion pump that delivers a therapeutic to a patient at a desired dosage, a monitoring device that includes a plurality of sensors for measuring a plurality of patient parameters of the patient, the plurality of patient parameters comprising a target patient parameter
Mazlish et al. shows a system comprising an infusion pump that delivers insulin to a patient at a determined dosage (Mazlish et al. [0039] and [0040]). Mazlish et al. shows the system includes a glucose monitoring device for measuring glucose for a patient (Mazlish et al. [0041]).
a processor; and a non-transitory computer readable medium storing instructions executable by the processor to provide: a predictive model that predicts a future value for the target patient parameter at a given time according to a set of features, each of the set of features being associated with one of the patient or the infusion pump and the and the set of features including a feature representing one of a current dosage and a past dosage of the therapeutic being provided by the infusion pump and at least two features derived from the plurality of patient parameters
Mazlish et al. shows the system includes a control device which is a computing device which can predict future blood glucose levels (Mazlish et al. [0041]). Mazlish et al. shows a predictive model that predicts future glucose values at a given time using a set of features of past and current insulin and blood glucose values (Mazlish et al. [0221]-[0235]).
a therapeutic delivery system controller that determines the desired dosage for the therapeutic according to the predicted future value for the target patient parameter,
Mazlish et al. shows the control device can determine the basal delivery rate based on projected blood glucose levels (Mazlish et al. [0041]).
and a user interface that is configured to display the predicted future value for the biometric parameter and the desired dosage to a user and allow a user to change at least one hyperparameter of a set of hyperparameters associated with the predictive model.
Mazlish et al. shows a user interface that is configured to display the predicted future value for the biometric parameter (Mazlish et al. Fig. 20) and allows a user to change at least one hyperparameter of a set of hyperparameters associated with the predictive model as the ability to change a carbohydrate ratio and an insulin sensitivity factor which are configurable variables that govern the prediction of the future glucose values (Mazlish et al. Fig. 6 and [0221]-[0235]).
Mazlish et al. does not show a plurality of sensors for measuring a plurality of patient parameters of the patient or the set of features include at least two features derived from the plurality of patient parameters.
Like Mazlish et al., Cinar et al. shows monitoring patient parameters to predict a future glucose value and controls insulin infusion based on predicted future glucose levels. Cinar et al. shows sensors for monitoring blood glucose and physiological data such as heart rate of a patient and using this measured physiological data along with blood glucose values to predict future blood glucose values (Cinar et al. [0010], [0013], and [0040]).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the invention to have modified the system of predicting future glucose levels of a patient using features of past and current blood glucose and insulin values of Mazlish et al. to incorporate the use of additional sensors for monitoring physiological information such as heart rate for the prediction of future glucose values of a patient of Cinar et al. because this allows for a comprehensive system that incorporates information on physiological data (which describes the physiological state of a patient that impacts blood glucose values) and blood glucose data of the patient of a patient in the prediction of the future glucose prediction used to control the automatic infusion of insulin (Cinar et al. [0009] and [0011]). One would have a reasonable expectation of success because both Mazlish et al. and Cinar et al. provide systems for measuring patient biometric information to predict future glucose values for controlling the infusion of insulin to a patient.
The rejection below is newly recited.
Claim 20 is rejected under 35 U.S.C. 103 as being unpatentable over Mazlish et al. (US 20180200435; newly cited) in view of Cinar et al. (US 20160354543 A1; previously cited) as applied to claim 18 above, and further in view of Doron et al. (US 20200197606 A1; effective filling date 13 July 2018 and newly cited).
Claim 20 is directed to the executable instruction being executable to further provide a learning element that stores the features used for the prediction, the predicted future value, and an actual value for the target patient parameter at the given time, compares the predicted future value to the actual value to generate an error value for the predicted future value, stores a series of error values associated with a corresponding series of predicted future values, and provides an alert if the error values exceed a threshold value for a predetermined period of time.
Mazlish et al. in view of Cinar et al. shows the system stores blood glucose data and historical pump usage information such as dosage logs of insulin (Mazlish et al. [0061] and [0216]). Mazlish et al. in view of Cinar et al. shows a system which provides alerts or alarms based on abnormalities (Mazlish et al. [0080] and [0218]).
Mazlish et al. in view of Cinar et al. does not show storing the predicted future value or comparing the predicted future value to the actual value to generate an error value for the predicted future value.
Like Mazlish et al. in view of Cinar et al., Doron et al. shows predicting future glucose values of a patient. Doron et al. shows calculating an indicator representative of the error between the blood glucose estimated from a model that predicts the future evolution of a patients blood glucose over a period of time and the real blood glucose measured by the sensor (Doron et al. abstract). Doron et al. shows that the numerical indicator includes a difference between the real glucose measured by the sensor and the blood glucose estimated by the model at a given time which provides a value of an error (Doron et al. [0016]). It would have been obvious to one of ordinary skill in the art to have stored that predicted future glucose value estimated by the model to facilitate the comparison of the estimated future value with the measured glucose value during the same time period. Doron et al. shows analyzing the quality/reliability of the prediction model using numerical indicators representative of the error between the blood sugar estimated based on the model and the real blood sugar measured by the sensor and is considered unreliable when a value of these indicators exceeds a threshold value during a time period (Doron et al. [0059]). Doron et al. shows if the physiological model is considered to be insufficiently reliable the system stops the use of this model to regulate the delivery of insulin (Doron et al. [0060]).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the invention to have combined the system of predicting future glucose values utilizing a model which intakes features of past and current blood glucose values and insulin values for determining a dosage of insulin to deliver to a patient of Mazlish et al. in view of Cinar et al. with the procedure of determining a reliability of a model which predicts future glucose values when determining a dosage of insulin to deliver of Doron et al. because this would allow for a system and process capable of determining the reliability of the model predicting the future glucose value that is used to determine the dosage of insulin administered to a patient and to stop the use of the model in determining the dosage if the model is identified as unreliable thus limiting the risk of placing a patient in a hyperglycemia or hypoglycemia situation (Doron et al. [0005] and [0060]). It would have been further obvious to one of ordinary skill in the art before the effective filling date of the invention to have modified the condition of triggering the alerts/alarms of Mazlish et al. in view of Cinar et al. to be the condition when the model is determined to be unreliable causing the system to stop the use of the model in determining the dosage of insulin of Doron et al. because this would provide information to the user that the mode of operation (e.g., how insulin dosage is being determined and administered to the patient) has changed (Doron et al. [0059]-[0060]). One would have a reasonable expectation of success because Mazlish et al. in view of Cinar et al. shows a systems and process of controlling the blood glucose level of a patient using a model which predicts a future glucose level of a patient while Doron et al. provides a procedure of analyzing the reliability of a model which predicts a future glucose level when controlling the blood glucose level of a patient.
Conclusion
No claims are allowed.
This Office action is a Non-Final action. A shortened statutory period for reply to this action is set to expire THREE MONTHS from the mailing date of this action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JONATHAN EDWARD HAYES whose telephone number is (571)272-6165. The examiner can normally be reached M-F 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, Olivia Wise can be reached at 571-272-2249. 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.
/JONATHAN EDWARD HAYES/Examiner, Art Unit 1685
Prosecution Insights