DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after 16 March 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Amendment
The preliminary amendment to the claims filed 29 February 2024 has been entered. Claim(s) 1-6, 11, 13-17 and 19-26 is/are currently amended. New claim(s) 30 has/have been added. Claim(s) 1-30 is/are pending.
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.
The claims in this application are given their broadest reasonable interpretation ("BRI") using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The BRI of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) (or pre-AIA 35 U.S.C. 112, sixth paragraph) is invoked.
As explained in MPEP § 2181(I), claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f):
(A) the claim limitation uses the term "means" or "step" or a term used as a substitute for "means" that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term "means" or "step" or the generic placeholder is modified by functional language, typically, but not always linked by the transition word "for" (e.g., "means for") or another linking word or phrase, such as "configured to" or "so that"; and
(C) the term "means" or "step" or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word "means" (or "step") in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f). The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word "means" (or "step") in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f). The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word "means" (or "step") are being interpreted under 35 U.S.C. 112(f), except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word "means" (or "step") are not being interpreted under 35 U.S.C. 112(f), except as otherwise indicated in an Office action.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of pre-AIA 35 U.S.C. 112, 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.
Claim(s) 3-4, 10-13, 17, 22, 25 and claims dependent thereon is/are rejected under 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, 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 pre-AIA the applicant regards as the invention.
Regarding claims 3-4 and 10-12, it is unclear how the various rule-based determinations for identifying a candidate series, or sub-sequence thereof, relate the first machine learning model. For example, is it unclear if the determinations of claims 3-4 and 10-12 are made in addition to the determination by the first machine learning model, if the model utilizes the recited rules in determining a candidate series, etc.?
Regarding claim 10 and claims dependent thereon, there is insufficient antecedent basis for "the rise time-window" and "the drop time-window" in the claim. Claim 10 will be further discussed with the understanding it is dependent on claim 4, which provides sufficient antecedent basis for said terms, rather than claim 1 as written.
Regarding claim 13 and claims dependent thereon, the limitations "input a time series sub-sequence of at least one time series of glucose measurements into at least one machine learning model; and generate, using at least one machine learning model, a signal output indicating that at least one glucose measurement was obtained while the at least one sensor was subject to compression" are indefinite. The relationship between the machine learning model into which the time series sub-sequence is input and the machine learning model generating the signal output is indefinite, particularly as there is no clear link in the claim because the determined candidate series, the time series sub-sequence and the output indicating that at least one glucose measurement was obtained while the sensor was subject to compression. It is unclear if this is the same model, or the use of two model is encompassed by the claim.
Regarding claim 17 and claims dependent thereon, the limitations "determine a maximum probability value of plural probability values, the plural probability values being associated with plural time stamps in the time series sub-sequence that are contained within a drop time-window; and determine the probability that the time series sub-sequence includes a glucose measurement obtained while the at least one sensor was subject to compression based on the maximum probability value" are indefinite, particularly in the view of the indefiniteness of claim 13 discussed above. Specifically, as discussed above, claim 13 does not clearly link generating a signal output indicating that at least one glucose measurement was obtained while the at least one sensor was subject to compression to the time series sub-sequence input to a machine learning model. Accordingly, it is unclear if determining the probability that the time series sub-sequence includes a glucose measurement obtained while the at least one sensor was subject to compression based on the maximum probability value, as recited in claim 17, further limits the generation of the signal output of claim 13, or is separate determination specific to the time series sub-sequence input to (potentially a second) machine learning model.
Regarding claim 22 and claims dependent thereon, the limitation "determine a rolling mean for the at least one time series of glucose measurements including a smooth glucose value associated with each glucose measurement and time stamp pair" is indefinite. It is unclear if "pair" refers to the pair of time stamps, or a paired time stamp and glucose measurement.
Regarding claim 25 and claims dependent thereon, the limitation "a difference between a first smooth glucose value associated with the first time stamp and a second smooth glucose value associated with the second time stamp is greater than 7.5 mg/dL" is indefinite. The relationship, if any, between the difference of claim 25 and the threshold of claim 22, which is a difference value, is unclear.
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of pre-AIA 35 U.S.C. 112, first paragraph:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claim(s) 3-4 and 10-12 and claims dependent thereon is/are rejected under 35 U.S.C. 112(a) or pre-AIA 35 U.S.C. 112, first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for pre-AIA the inventor(s), at the time the application was filed, had possession of the claimed invention.
Regarding claims 3-4 and 10-12 and claims dependent thereon, the examiner first notes that claims, including original claims, may fail to satisfy the written description requirement when the invention is claimed and described in functional language (whether or not the functional claim language invokes 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph) but the specification does not sufficiently identify how the invention achieves the claimed function. For computer-implemented limitations, if the specification does not provide a disclosure of the computer and algorithm in sufficient detail to demonstrate to one of ordinary skill in the art that the inventor possessed the invention including how to program the disclosed computer to perform the claimed function, a rejection under 35 U.S.C. 112(a) or pre-AIA 35 U.S.C. 112, first paragraph, for lack of written description must be made. See MPEP 2161.01(I).
Applicant fails to sufficiently identify a first machine learning model that incorporates the recited rules-based identifications of the above-noted claims and/or disclose how a machine learning model may incorporate or be used in combination with said rules-based identifications.
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.
Claim(s) 1-6, 8-17, 19-28 and 30 is/are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception(s) without significantly more.
Claims 1-6, 8-16, 18-25 and 30 recite the steps of determining that at least one time series of glucose measurements is a candidate series, such as a time series sub-sequence, including a compression artifact or onset of sensor compression; and determining or predicting that a time series of glucose measurements includes at least one glucose measurement was obtained while the at least one sensor was subject to compression. Several of the dependent claims merely further describe the steps or manner by which the above-noted determinations may be made, such as identifying changes exceeding a threshold, identifying a drop time-window and associated rise-time window, identifying features of the time series of measurements (including merely observing/identifying raw measurement value(s)), etc.
These limitations, as drafted, are a process that, under its broadest reasonable interpretation (BRI), covers performance of the limitations in the mind but for the recitation of generic computer components (e.g., generic processor executing a generic machine learning model). That is, other than reciting the steps are performed by a processor and/or machine learning model(s), nothing in the claim elements precludes the steps from practically being performed in the mind. For example, a user can mentally/manually determine that at least one time series of glucose measurements (real-time, historical, etc.), time series sub-sequence, or individual measurements within said time series, is a compression artifact (or candidate compression artifact), and determine at least one glucose measurement was obtained while a sensor was subject to compression, e.g., by visually observing a glucose time series obtained by the sensor, by considering various rate of change and/or point-to-point difference thresholds indicative or characteristic of a compression artifact, etc. In support of this assertion, Applicant expressly discloses such time series may be manually reviewed and labeled for PISAs, or compression artifacts (e.g., ¶ [0183]). If claim limitations, under their BRI, covers performance of the limitations in the mind but for the recitation of generic computer components, then they fall within the "mental processes" grouping of abstract ideas. Accordingly, claims 1-6, 8-16, 18-25 and 30 recite an abstract idea.
Claims 26-28 recite the steps of determining plural time series sub-sequences based on the training dataset, labeling each of the plural time series sub-sequences with an indication that the time series sub-sequence includes a compression artifact or that the time series sub-sequence does not include a compression artifact, extracting features from each of the plural time series sub-sequences; inputting the one or more features from the plural time series sub-sequences into at least one machine learning model for training; and detecting a sensor compression based on providing at least one time series glucose measurements as input to a trained machine learning model(s). These steps are similarly capable of being performed in the mind, e.g., visually observing a glucose time series obtained by the sensor. Alternatively/Additionally, said steps are comparable to methods of organizing human activity, particularly the steps involved in supervised machine learning training and testing.
The above-noted judicial exception(s) is not integrated into a practical application. Claims 1-6, 8-17, 19-28 and 30 include the additional elements of the generic computer components for performing the abstract idea; a generic sensor for measuring the glucose data and transmitting said glucose data to the computer; and generating a signal output indicative of the result of performing the abstract idea. The computer components (e.g., processor, machine learning model(s), etc.) recited at a high-level of generality (i.e., as a generic processor executing a generic machine learning model to make a determination and/or prediction) such that it amounts no more than mere instructions to apply the exception using a generic computer component. The sensor and steps of receiving measured data from the sensor merely add necessary data gathering elements/activities to the judicial exception comparable to concepts that have identified by the courts as insignificant extra-solution activity (see MPEP 2106.05(g), e.g., performing clinical tests on individuals to obtain input for an equation, determining the level of a biomarker in blood). Lastly, generating the signal output indicative of the determination(s)/prediction merely add necessary outputting step to the judicial exception, which is similarly comparable to concepts that have identified by the courts as insignificant extra-solution activity (see MPEP 2106.05(g), printing generated data). Even when considered in combination, the additional elements do no more than require the use of software to tailor information and provide it to the user using generic computer components.
Claims 1-6, 8-17, 19-28 and 30 do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using generic computer components to perform the abstract idea amounts to no more than mere instructions to apply the exception using generic computer components. Additionally, there is sufficient evidence of record to suggest the data gathering elements/activities are well-understood, routine, and/or conventional in the field. For example, Navarathna discloses, "A CGM is a sensor that is worn on the body and provides glucose readings from the interstitial fluid usually every 5 minutes. A CGM typically is comprised of a wearable sensor, a wireless transmitter, and a receiver" (pg. 9). Similarly, generating a signal output as claimed reasonably encompasses a generic display of generated information, transmitting or storing an indication of a determination/prediction that at least one glucose measurement was obtained while the at least one sensor was subject to compression, etc. These are comparable to concepts that have been identified by the courts as well‐understood, routine, and conventional computer functions (see MPEP 2106.05(d)(II), receiving or transmitting data over a network, electronic recordkeeping, storing and retrieving information in memory, etc.). Mere instructions to apply an exception using a generic computer component, adding insignificant extra-solution activity to the judicial exception and/or adding insignificant extra-solution activity to the judicial exception cannot provide an inventive concept. See MPEP 2106.05. Accordingly, claims 1-6, 8-17, 19-28 and 30 are not patent eligible.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(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.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1-2, 5, 8-9, 13-14, 19-21 and 30 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Artificial Intelligence to Improve Blood Glucose Control for People with Type 1 Diabetes" ("Navarathna").
Regarding claims 1 and 30, Navarathna discloses a system for automatically detecting sensor compression in continuous glucose monitoring, the system comprising:
at least one sensor for generating measurement data comprising a time series of glucose measurements including at least one of a blood glucose measurement or an interstitial glucose measurement (throughout document, CGM data; e.g., Abstract, CGMs provide blood glucose values at 5 min intervals; pg. 9, 1.3.4 Continuous Glucose Monitoring, CGM is a sensor that provides glucose readings from the interstitial fluid; etc.); and
at least one processor in communication with the at least one sensor, the at least one processor executing at least two machine learning models (4.4.2 Algorithms, machine(s) or computer(s) executing the disclosed machine learning algorithm(s), e.g., ensemble methods consisting of multiple sub-classifiers (e.g., RF, GBM, etc.), start-PISA classifier consisting of two sub-classifiers, etc.), wherein the at least one processor is programmed or configured to cause the processor to:
receive, from the at least one sensor, the measurement data (4.3 Data, Enlite™ CGM data for training; CGM real-world dataset; etc.);
determine that the at least one time series of glucose measurements is a candidate series including a compression artifact using a first machine learning model (e.g., output of a first sub-classifier of an ensemble algorithm (e.g., pgs. 32-36); 4.4.2 Algorithms, start classifier (SC) for detecting the starting CGM reading of a PISA event);
generate, using a second machine learning model, a signal output indicating that the at least one time series of glucose measurements was obtained while the at least one sensor was subject to compression (e.g., final PISA/not-PISA classification based on a combination of outputs of sub-classifiers of an ensemble algorithm; 4.4.2 Algorithms, PISA classifier detecting the PISA probabilities of CGM readings and/or classifying said CGM readings as PISA or not based on pisaCutoff following a detection of a starting CGM reading of a PISA event by the start classifier, e.g., pg. 97, Algorithm 1; etc.).
Regarding claim 2, Navarathna discloses at least one time series of glucose measurements includes plural time stamps, each time stamp being associated with a glucose measurement (e.g., pg. 95, CGM features used by the PISA classifier include "Δt" features, indicating the time of each CGM measurement is known).
Regarding claim 5, Navarathna discloses the at least one processor is programmed or configured to cause the processor to: identify one or more features of the at least one time series of glucose measurements; and input the one or more features into the second machine learning model (pg. 96, 4.4.2 Algorithms, Features for CGM readings (e.g., Table 4.4, CGM features) are input to the algorithms, with the output being the PISA probabilities of those CGM readings).
Regarding claim 8, Navarathna discloses the plural time stamps are separated by any one or more of 30 second intervals, 1-minute intervals, 2.5-minute intervals, and/or 5-minute intervals (1.3.4 Continuous Glucose Monitoring, glucose readings are provided every 5 minutes; 4.3 Data, CGM data is collected mostly at 5-minute intervals; etc.).
Regarding claim 9, Navarathna discloses the at least one processor is programmed or configured to cause the processor to execute the first machine learning model and the second machine learning model concurrently (e.g., Figure 2.3, individual trees/sub-classifiers run concurrently to generate an aggregate decision).
Regarding claim 13, Navarathna discloses a system for automatically detecting onset of sensor compression in continuous glucose monitoring, the system comprising:
at least one sensor for generating measurement data comprising a time series of glucose measurements (throughout document, CGM data; e.g., Abstract, CGMs provide blood glucose values at 5 min intervals; pg. 9, 1.3.4 Continuous Glucose Monitoring, CGM is a sensor that provides glucose readings from the interstitial fluid; etc.); and
at least one processor in communication with the at least one sensor, the at least one processor executing program code for at least one machine learning model (4.4.2 Algorithms, machine(s) or computer(s) executing the disclosed machine learning algorithm(s)), wherein the at least one processor is programmed or configured to cause the processor to:
receive, from the at least one sensor, the measurement data (4.3 Data, Enlite™ CGM data for training; CGM real-world dataset; etc.);
determine that the at least one time series of glucose measurements is a candidate series including glucose measurements representing onset of sensor compression (4.4.2 Algorithms, start classifier (SC) for detecting the starting CGM reading of a PISA event); and
input a time series sub-sequence of at least one time series of glucose measurements into at least one machine learning model, and generate, using the at least one machine learning model, a signal output indicating that at least one glucose measurement was obtained while the at least one sensor was subject to compression (4.4.2 Algorithms, PISA classifier detecting the PISA probabilities of CGM readings and/or classifying said CGM readings as PISA or not based on pisaCutoff following a detection of a starting CGM reading of a PISA event by the start classifier, e.g., pg. 97, Algorithm 1).
Regarding claim 14, Navarathna discloses at least one time series of glucose measurements includes plural time stamps, each time stamp being associated with a glucose measurement (e.g., pg. 95, CGM features used by the PISA classifier include "Δt" features, indicating the time of each CGM measurement is known).
Regarding claim 19, Navarathna discloses at least one time series of glucose measurements spans 30 minutes of measurement data measured by at least one sensor (4.3 Data, CGM data contains at least 4 hours of data; 5.3 Data, CGM data contains an overnight period from 10 PM to 10 AM).
Regarding claim 20, Navarathna discloses the at least one processor, as configured to input a time series sub-sequence of the at least one time series of glucose measurements into at least one machine learning model, is programmed or configured to cause the processor to: identify one or more features of the time series sub-sequence of the at least one time series of glucose measurements; and input the one or more features into the at least one machine learning model (pg. 96, 4.4.2 Algorithms, Features for CGM readings (e.g., Table 4.4, CGM features) are input to the algorithms, with the output being the PISA probabilities of those CGM readings).
Regarding claim 21, Navarathna discloses the one or more features include at least one or more of a raw glucose measurement, a start glucose value at a first time stamp of the drop time-window, an end glucose value at a last time stamp of the drop time-window, a difference between the start glucose value and the end glucose value, a slope of glucose values of the drop time-window, a standard deviation of glucose values of the drop time-window, a time of day, a temperature value, a comparison value between glucose measurements and raw glucose measurements, and/or any combination thereof (e.g., Table 4.4, CGM features).
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:
Determining the scope and contents of the prior art.
Ascertaining the differences between the prior art and the claims at issue.
Resolving the level of ordinary skill in the pertinent art.
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.
Claim(s) 6-7, 16 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Navarathna.
Regarding claim 6, Navarathna discloses the limitations of claim 1, as discussed above. Navarathna further explicitly suggests predicting, in real time, that the at least one sensor is subject to compression while the at least one sensor is obtaining a glucose (5.7 Conclusions and Future Work, using a PISA classification algorithm, e.g., start-PISA classifier, while running in real time). Navarathna further discloses/suggests the output of said prediction may be utilized to, e.g., control an insulin delivery system, such as a pump, to avoid unnecessary pump shut-offs (5.7 Conclusions and Future Work, using the algorithm(s) in real-time to avoid unnecessary pump shut-offs; 4.2 Introduction, automatically detecting PISAs can prevent undesirable pump shutoffs and overnight hyper-glycemic events; etc.), thereby suggesting an indication of the output (e.g., PISA classification) may be utilized by a controller of the delivery system to determine whether or not said delivery system should be shut off. In view of the above, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Navarathna with the at least one processor, as configured to generate a signal output, is programmed or configured to cause the processor to: predict, in real time via outputting an indication, that the at least one sensor is subject to compression (e.g., outputting an indication of a PISA classification to, e.g., a pump controller) while the at least one sensor is obtaining a glucose measurement in order to avoid unnecessary pump shut-offs and overnight hyperglycemic events (4.2 Introduction; 5.7 Conclusions and Future Work; etc.).
Regarding claim 7, Navarathna discloses the limitations of claim 1, as discussed above, and further discloses/suggests the system comprises and/or is usable in combination with an insulin delivery system in communication with the at least one processor (e.g., 1.5 Type 1 Diabetes Control, insulin pump in communication with a mobile device; 4.3 Data, insulin pump in communication with a laptop running a PISA detection algorithm). Navarathna discloses one challenge with closed-loop glucose control systems is PISAs causing undesired insulin pump shut-offs (pg. 16, Sensor Related Issues). Navarathna further explicitly suggests predicting that the sensor(s) is subject to compression while the sensor(s) is obtaining a glucose (e.g., detecting PISAs in real time) in order to avoid these unnecessary pump shutoffs (5.7 Conclusions and Future Work). In view of the above, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Navarathna with the at least one processor being programmed or configured to cause the processor to transmit the signal output to the insulin delivery system indicating that the at least one sensor is subject to compression (e.g., indication of PISA classification), wherein the signal output will cause the insulin delivery system to perform continuing insulin delivery in order to avoid unnecessary pump shut-offs and overnight hyperglycemic events (4.2 Introduction; 5.7 Conclusions and Future Work; etc.).
Regarding claim 16, Navarathna discloses the limitations of claim 13, as discussed above. Navarathna further explicitly suggests predicting, in real time, that the at least one sensor is subject to compression while the at least one sensor is obtaining a glucose (5.7 Conclusions and Future Work, using a PISA classification algorithm, e.g., start-PISA classifier, while running in real time), wherein the prediction is based on a probability value representing a probability that a time series sub-sequence includes a glucose measurement obtained while the at least one sensor was subject to compression (4.4.2 Algorithms). Navarathna further discloses/suggests the output of said prediction may be utilized to, e.g., control an insulin delivery system, such as a pump, to avoid unnecessary pump shut-offs (5.7 Conclusions and Future Work, using the algorithm(s) in real-time to avoid unnecessary pump shut-offs; 4.2 Introduction, automatically detecting PISAs can prevent undesirable pump shutoffs and overnight hyper-glycemic events; etc.), thereby suggesting an indication of the output (e.g., PISA classification) may be utilized by a controller of the delivery system to determine whether or not said delivery system should be shut off. In view of the above, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Navarathna with the at least one processor, as configured to generate a signal output, is programmed or configured to cause the processor to: predict, in real time via outputting an indication, that the at least one sensor is subject to compression (e.g., outputting an indication of a PISA classification to, e.g., a pump controller) while the at least one sensor is obtaining a glucose measurement, wherein the prediction is based on a probability value representing a probability that a time series sub-sequence includes a glucose measurement obtained while the at least one sensor was subject to compression, in order to avoid unnecessary pump shut-offs and overnight hyperglycemic events (4.2 Introduction; 5.7 Conclusions and Future Work; etc.).
Regarding claim 18, Navarathna discloses the limitations of claim 13, as discussed above, and further discloses/suggests the system comprises and/or is usable in combination with an insulin delivery system in communication with the at least one processor (e.g., 1.5 Type 1 Diabetes Control, insulin pump in communication with a mobile device; 4.3 Data, insulin pump in communication with a laptop running a PISA detection algorithm). Navarathna discloses one challenge with closed-loop glucose control systems is PISAs causing undesired insulin pump shut-offs (pg. 16, Sensor Related Issues). Navarathna further explicitly suggests predicting that the sensor(s) is subject to compression while the sensor(s) is obtaining a glucose (e.g., detecting PISAs in real time) in order to avoid these unnecessary pump shutoffs (5.7 Conclusions and Future Work). In view of the above, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Navarathna with the at least one processor being programmed or configured to cause the processor to transmit the signal output to the insulin delivery system indicating that the at least one sensor is subject to compression (e.g., indication of PISA classification), wherein the signal output will cause the insulin delivery system to perform continuing insulin delivery in order to avoid unnecessary pump shut-offs and overnight hyperglycemic events (4.2 Introduction; 5.7 Conclusions and Future Work; etc.).
Claim(s) 1-4, 8, 10-11, 13-15, 22-25 and 30 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 2015/0351670 A1 ("Vanslyke") in view of Navarathna.
Regarding claims 1 and 30, Vanslyke discloses/suggests a system for automatically detecting sensor compression in continuous glucose monitoring, the system comprising:
at least one sensor for generating measurement data comprising a time series of glucose measurements including at least one of a blood glucose measurement or an interstitial glucose measurement (continuous glucose sensor 10, 100, etc.; ¶ [0067]); and
at least one processor in communication with the at least one sensor, the at least one processor executing at least two models (signal artifacts detector 29; ¶ [0163]), wherein the at least one processor is programmed or configured to cause the processor to:
receive, from the at least one sensor, the measurement data (Fig. 5, step 52);
determine that the at least one time series of glucose measurements is a candidate series including a compression artifact using a first model (Fig. 5, step 56; ¶ [0405] received signal may be analyzed for shifts in sensor signal, greater than a predetermined threshold, at the beginning and end of a significant or sustained decrease in sensor signal, e.g., one characterized by a steep decline in signal value, followed by a period of sustained decreased value, followed by a steep increase in the signal value; ¶ [0435] possible compression artifact);
generate, using a second model, a signal output indicating that the at least one time series of glucose measurements was obtained while the at least one sensor was subject to compression (Fig. 5, step 56; ¶ [0204], ¶¶ [0429]-[0435], etc. evaluating each possible compression artifact against a known compression artifact signature, e.g., Fig. 24C, to determine if that respective fault (compression) has occurred).
Vanslyke does not disclose the first and second models are/each include a machine learning model.
Navarathna discloses machine learning algorithms for determining that at least one time series of glucose measurements is a candidate series including a compression artifact (PISA) and generating a signal output indicating at least one time series of glucose measurements was obtained while the glucose sensor was subject to compression, disclosing said machine learning algorithms outperformed rules-based algorithm(s) (4.6 Discussion).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Vanslyke with each of the first and second model comprising a machine learning model(s) as taught/suggested by Navarathna in order to extract more information pertaining to compression (PISA) behavior, thereby more accurately and/or reliably detecting compression candidates and/or faults/artifacts.
Regarding claims 2 and 8, Vanslyke as modified discloses/suggests the at least one time series of glucose measurements includes plural time stamps, each time stamp being associated with a glucose measurement (e.g., Fig. 33D; ¶ [0232]; etc.), wherein plural time stamps are separated by 30-second intervals, 1-minute intervals, 2.5-minute intervals, and/or 5-minute intervals (e.g., ¶ [0206]).
Regarding claim 3, Vanslyke discloses/suggests the at least one processor, as configured to determine that the at least one time series of glucose measurements is a candidate series, is programmed or configured to cause the processor to determine that the at least one time series of glucose measurements includes a change in glucose measurements across plural time stamps, wherein the change in glucose measurements exceeds a threshold (e.g., ¶ [0405] received signal may be analyzed for shifts in sensor signal, greater than a predetermined threshold, at the beginning and end of a significant or sustained decrease in sensor signal).
Regarding claim 4, Vanslyke discloses/suggests the at least one processor, as configured to determine that the at least one time series of glucose measurements is a candidate series, is programmed or configured to cause the processor to: determine, using the first machine learning model, that the at least one time series of glucose measurements includes a time series sub-sequence having a drop time-window and having a rise time-window associated with the drop time-window (¶ [0405] received signal may be analyzed for shifts in sensor signal, greater than a predetermined threshold, at the beginning and end of a significant or sustained decrease in sensor signal, e.g., one characterized by a steep decline in signal value, followed by a period of sustained decreased value, followed by a steep increase in the signal value), wherein the time series sub-sequence includes a sequence of time stamps corresponding to at least a portion of the drop time-window and at least a portion of the rise time-window (Fig. 33D; Fig. 34C; etc.).
Regarding claim 10, Vanslyke discloses/suggests the limitations of claim 4, as discussed above, and further discloses the at least one processor is programmed or configured to cause the processor to: identify the rise time-window associated with the drop time-window as occurring later than the drop-time window by a period of sustained decreased value, but does not expressly disclose said period is within a range of 15 minutes to 180 minutes. However, Vanslyke discloses said period of time (or compression faults generally) occur for relatively short periods of time, such as 5 or 20 minutes to 60 minutes up to several hours (e.g., ¶ [0441]), such that one of ordinary skill in the art would readily appreciate the associated rise-time window following a drop-time window should occur within the above noted range, which encompasses the range as claimed. Accordingly, since Vanslyke discloses/suggests the range of 15 minutes to 180 minutes is characteristic of a compression artifact(s), it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Vanslyke with the first model identifying the rise time-window associated with the drop time-window as occurring within a range of 15 minutes to 180 minutes later than the drop-time window in the at least one time series in order to accurately/reliably identify candidate/possible compression faults for further analysis.
Regarding claim 11, Vanslyke discloses/suggests the at least one processor, as configured to determine that the at least one time series of glucose measurements is a candidate series, is programmed or configured to cause the processor to: determine a drop time-window within the at least one time series based on a difference between a first glucose measurement and a second glucose measurement exceeding a drop time-threshold, wherein the drop time-window begins at a first time stamp associated with the first glucose measurement and ends at a second time stamp associated with the second glucose measurement; and determine a rise time-window within the at least one time series based on a difference between a third glucose measurement and a fourth glucose measurement exceeding a rise time-threshold, wherein the rise time-window begins at a third time stamp associated with the third glucose measurement and ends at a fourth time stamp associated with the fourth glucose measurement (¶ [0405] received signal may be analyzed for shifts in sensor signal, greater than a predetermined threshold, at the beginning and end of a significant or sustained decrease in sensor signal, e.g., one characterized by a steep decline in signal value, followed by a period of sustained decreased value, followed by a steep increase in the signal value; ¶ [0309] upward and downward spikes may be detected by point to point difference and thresholding; etc.).
Regarding claim 12, Vanslyke discloses/suggests the limitations of claim 11, as discussed above, but does not expressly disclose the drop time-threshold is 10 mg/dL and the rise time-threshold is 6 mg/dL. However, Vanslyke discloses the drop time- and rise time-windows are characterized by a "steep" decrease and increase, respectively. Vanslyke further discloses such steep changes (i.e., downward or upward spikes, respectively) may be detected by a point-to-point difference and thresholding (e.g., ¶ [0309]). Since Vanslyke discloses/suggests the threshold value (i.e., difference) provides a quality which can be optimized (e.g., a cutoff for "steepness" of the spikes that are detected), the specific claimed thresholds would have been obvious because it has been held that the discovery of optimum or workable values by routine experimentation is not inventive. See MPEP 2144.05(II).
Alternatively/Additionally, at the time the invention was effectively filed, it would have been an obvious matter of design choice to a person of ordinary skill in the art to modify the system of Vanslyke with the drop time-threshold being 10 mg/dL and the rise time-threshold being 6 mg/dL because Applicant has not disclosed that said thresholds provide an advantage, are used for a particular purpose, or solve a stated problem. Rather, Applicant discloses/suggests the claimed thresholds are exemplary (e.g., ¶ [0078]; ¶ [0241]; etc.). Accordingly, as no evidence has been provided to the contrary, one of ordinary skill in the art, furthermore, would have expected Applicant's invention to perform equally well with the point-to-point thresholds as disclosed and/or suggested by Vanslyke because either arrangement enables identifying shifts in sensor signal indicative of a possible compression fault.
Regarding claim 13, Vanslyke discloses/suggests a system for automatically detecting onset of sensor compression in continuous glucose monitoring, the system comprising:
at least one sensor for generating measurement data comprising a time series of glucose measurements (continuous glucose sensor 10, 100, etc.); and
at least one processor in communication with the at least one sensor, the at least one processor executing program code for at least one model (signal artifacts detector 29; ¶ [0163]), wherein the at least one processor is programmed or configured to cause the processor to:
receive, from the at least one sensor, the measurement data (Fig. 5, step 52);
determine that the at least one time series of glucose measurements is a candidate series including glucose measurements representing onset of sensor compression (Fig. 5, step 56; ¶ [0405] received signal may be analyzed for shifts in sensor signal, greater than a predetermined threshold, at the beginning and end of a significant or sustained decrease in sensor signal, e.g., one characterized by a steep decline in signal value, followed by a period of sustained decreased value, followed by a steep increase in the signal value; ¶ [0435] possible compression artifact); and
input a time series sub-sequence of at least one time series of glucose measurements into the at least one model to generate a signal output indicating that at least one glucose measurement was obtained while the at least one sensor was subject to compression (Fig. 5, step 56; ¶ [0204], ¶¶ [0429]-[0435], etc. evaluating each possible compression artifact against a known compression artifact signature, e.g., Fig. 24C, to determine if that respective fault (compression) has occurred).
Vanslyke does not disclose the at least one model is/includes a machine learning model.
Navarathna discloses machine learning algorithms for classifying a sub-sequence of glucose measurements as subject to compression (PISA) or not subject to compression (not-PISA), disclosing machine learning algorithms outperformed rules-based algorithm(s) (4.6 Discussion).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Vanslyke with the at least one model comprising a machine learning model(s) as taught/suggested by Navarathna in order to extract more information pertaining to compression (PISA) behavior, thereby more accurately and/or reliably detecting compression faults/artifacts.
Regarding claim 14, Vanslyke as modified discloses/suggests the at least one time series of glucose measurements includes plural time stamps, each time stamp being associated with a glucose measurement (e.g., Fig. 33D; ¶ [0232]; etc.).
Regarding claim 15, Vanslyke as modified discloses/suggests the at least one processor, as configured to determine that the at least one time series of glucose measurements is a candidate series, is programmed or configured to cause the processor to determine that at least one time series of glucose measurements includes a drop time-window, wherein the time series sub-sequence includes plural time stamps within the drop time-window (e.g., ¶ [0405] signal determined to have steep decline in signal value; Fig. 33D, Fig. 34C, etc.).
Regarding claim 22, Vanslyke as modified discloses/suggests the at least one processor, as configured to determine that at least one time series of glucose measurements is a candidate series, is programmed or configured to cause the processor to: determine a rolling mean for the at least one time series of glucose measurements including a smooth glucose value associated with each glucose measurement and time stamp pair (e.g., ¶ [0077]); calculating an indicator value for the smooth glucose value at each time stamp t, wherein the indicator value is equivalent to the claimed Boolean true; and identify a time series sub-sequence in the at least one time series of glucose measurements wherein the time series sub-sequence has a set of indicator values, the set of indicator values beginning at a first time stamp and ending at a second time stamp (¶ [0405] received signal may be analyzed for shifts in sensor signal, greater than a predetermined threshold, at the beginning and end of a significant or sustained decrease in sensor signal, e.g., one characterized by a steep decline in signal value, followed by a period of sustained decreased value, followed by a steep increase in the signal value; ¶ [0309] upward and downward spikes may be detected by point to point difference and thresholding; etc.).
Regarding claims 23 and 25, Vanslyke as modified discloses/suggests discloses the limitations of claim 22, as discussed above, and discloses/suggests lag may be equivalent to 5 minutes, but does not disclose the BG threshold is equivalent to 10.0 mg/dL, or a difference between a first smooth glucose value associated with the first time stamp and a second smooth glucose value associated with the second time stamp is greater than 7.5 mg/dL. However, Vanslyke discloses the drop time-window is characterized by a "steep" decrease. Vanslyke further discloses such steep changes (i.e., downward spike) may be detected by a point-to-point difference and thresholding (e.g., ¶ [0309]). Since Vanslyke discloses/suggests the threshold value (i.e., difference) provides a quality which can be optimized (e.g., a cutoff for "steepness" of the spikes that are detected), the specific claimed glucose thresholds would have been obvious because it has been held that the discovery of optimum or workable values by routine experimentation is not inventive. See MPEP 2144.05(II).
Alternatively/Additionally, at the time the invention was effectively filed, it would have been an obvious matter of design choice to a person of ordinary skill in the art to modify the system of Vanslyke with the threshold being 10 mg/dL or greater than 7.5 mg/dL because Applicant has not disclosed that said thresholds provide an advantage, are used for a particular purpose, or solve a stated problem. Accordingly, as no evidence has been provided to the contrary, one of ordinary skill in the art, furthermore, would have expected Applicant's invention to perform equally well with the point-to-point thresholds as disclosed/suggested by Vanslyke because either arrangement enables identifying shifts in sensor signal indicative of a possible compression fault.
Regarding claim 24, Vanslyke as modified discloses/suggests the time series sub-sequence spans at least 2.5 minutes in duration (e.g., sampling interval of 5 minutes, throughout document, which indicates a time between first and second timestamps is at least 2.5 minutes).
Claim(s) 26-29 is/are rejected under 35 U.S.C. 103 as being unpatentable over Navarathna; or alternatively, over Navarathna in view of US 2010/0056992 A1 ("Hayter").
Regarding claim 26, Navarathna discloses/suggests a computer-implemented method for generating at least one machine learning model to accurately detect sensor compression in continuous glucose monitoring, the method comprising:
receiving, as an input to a processor, at least one training dataset, the at least one training dataset including plural time series of glucose measurements (4.3 Data, CGM data used for training);
determining plural time series sub-sequences based on the training dataset (4.3 Data, PISA CGM readings were labeled by an expert engineer who inspected each CGM reading using an in-house developed online data analysis tool);
extracting one or more features from each of the plural time series sub-sequence (4.4.1 Feature Selection);
inputting the one or more features from the plural time series sub-sequences into at least one machine learning model for training (4.4.3 Cross Validation Procedure, an algorithm is trained using features generated from training nights; 5.4 Methods, GBM start-PISA algorithm is trained on the entire trial dataset); and
detecting a sensor compression based on providing at least one time series of glucose measurements as input to the at least one machine learning model (4.4.3 Cross Validation Procedure, the trained algorithm is then used to output the PISA probability of every CGM reading in the test nights; 5.4 Methods, the GBM start-PISA is run on the RWD).
Navarathna does not disclose at least one time series sub-sequence includes at least one glucose measurement value that is less than a compression estimate threshold. However, at the time the invention was effectively filed, it would have been an obvious matter of design choice to a person of ordinary skill in the art to modify the method of Navarathna with the plural time series sub-sequences to include at least one glucose measurement value that is less than a compression estimate threshold because Applicant has not disclosed that said criterion provides an advantage, is used for a particular purpose, or solves a stated problem. At best, Applicant appears to disclose sub-sequences or PISAs meeting this criterion are "hypo- or near hypo-PISAs" (¶ [0183]), but discloses no reason and/or benefit to limiting sub-sequences to this glucose range or including sub-sequences within said range. Accordingly, as no evidence has been provided to the contrary, one of ordinary skill in the art, furthermore, would have expected Applicant's invention to perform equally well with determining any/all sub-sequences indicative of compression artifact, including those which comprise at least one glucose measurement value that is less than a compression estimate threshold, as disclosed by Navarathna because either arrangement enables subsequent real-time or retrospective analysis of CGM data to accurately detect compression artifacts (PISAs) (Navarthna, 5.7 Conclusions and Future Work).
Alternatively/Additionally, Navarthna discloses popular CGM devices often include alarms indicative of low glucose levels (pg. 10, Table 1.1), wherein low glucose levels are less than about 80 mg/dL (1.3 Treatment for Type 1 Diabetes). Hayter similarly discloses comparable systems may include an alarm system that warns a patient of, e.g., detected hypoglycemia (i.e., ¶ [0087] glucose level below an alarm threshold). Hayter further discloses said alarms may be modified or disabled when, e.g., signal dropout, is detected (e.g., ¶ [0082]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Navarthna with at least one time series sub-sequence including at least one glucose measurement value that is less than a compression estimate threshold in order to train the machine learning model(s) (and/or increase the sensitivity of the model(s)) to identify compression artifacts in the hypoglycemic or approximately hypoglycemic range to facilitate reducing initiation of false hypoglycemic/low glucose alarms (Hayter, ¶ [0082]).
Regarding claim 27, Navarthna as modified discloses/suggests the limitations of claim 26, as discussed above, but does not disclose the compression estimate threshold is equivalent to 85 mg/dL. However, at the time the invention was effectively filed, it would have been an obvious matter of design choice to a person of ordinary skill in the art to modify the method of Navarthna the compression estimate threshold being equivalent to 85 mg/dL because Applicant has not disclosed that said threshold provides an advantage, is used for a particular purpose, or solves a stated problem. At best, Applicant appears to disclose sub-sequences or PISAs meeting this criterion are "hypo- or near hypo-PISAs" (¶ [0183]), and further discloses only "PISA candidates" meeting this criterion may be kept (¶ [0243]), but discloses no reason and/or benefit to including, or only keeping, sub-sequences having a minimum value within this glucose range. Accordingly, as no evidence has been provided to the contrary, one of ordinary skill in the art, furthermore, would have expected Applicant's invention to perform equally well with determining any/all sub-sequences indicative of compression artifact as disclosed by Navarathna, including those sub-sequences that have at least one glucose measurement value that is below 85 mg/dL, because either arrangement enables subsequent real-time or retrospective analysis of CGM data to accurately detect compression artifacts (PISAs) (Navarthna, 5.7 Conclusions and Future Work).
Regarding claim 28, Navarthna as modified discloses/suggests labelling each of the plural time series sub-sequences with an indication that the time series sub-sequence includes a compression artifact or that the time series sub-sequence does not include a compression artifact (4.3 Data, PISA CGM readings were labeled by an expert engineer who inspected each CGM reading using an in-house developed online data analysis tool).
Regarding claim 29, Navarathna as modified discloses/suggests the limitations of claim 26, as discussed above, and further discloses/suggests the system comprises and/or is usable in combination with an insulin delivery system in communication with the at least one processor (e.g., 1.5 Type 1 Diabetes Control, insulin pump in communication with a mobile device; 4.3 Data, insulin pump in communication with a laptop running a PISA detection algorithm). Navarathna discloses one challenge with closed-loop glucose control systems is PISAs causing undesired insulin pump shut-offs (pg. 16, Sensor Related Issues). Navarathna further explicitly suggests predicting that the sensor(s) is subject to compression while the sensor(s) is obtaining a glucose (e.g., detecting PISAs in real time) in order to avoid these unnecessary pump shutoffs (5.7 Conclusions and Future Work). In view of the above, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method of Navarathna with transmitting a signal output to the insulin delivery system indicating detection of sensor compression (e.g., indication of PISA classification), wherein the signal output causes the insulin delivery system to perform continuing insulin delivery in order to avoid unnecessary pump shut-offs and overnight hyperglycemic events (4.2 Introduction; 5.7 Conclusions and Future Work; etc.).
Conclusion
The prior art made of record and not relied upon is considered pertinent to Applicant's disclosure: see attached PTO-892.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Meredith Weare whose telephone number is 571-270-3957. The examiner can normally be reached Monday - Friday, 9 AM - 5 PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. Applicant is encouraged to use the USPTO Automated Interview Request at http://www.uspto.gov/interviewpractice to schedule an interview.
If attempts to reach the examiner by telephone are unsuccessful, the examiner's supervisor, Tse Chen, can be reached on 571-272-3672. 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.
/Meredith Weare/Primary Examiner, Art Unit 3791
Prosecution Insights