DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 12/29/2025 has been entered.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 09/08/2026 was considered by the examiner.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 3 and 15 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 3 recites “wherein correlating the in vitro features based on the in vivo features for a training set of glucose sensors comprises” in lines 1-4, which suggests that a previously presented step of correlating is further limited in claim 3. However, the claims do not previously present a step of correlating, so it is not clear how it is further limited in claim 3. Claim 1 only recites, “in vitro features… which have been correlated to in vivo features” in lines 5-9, which does not positively recite a correlating step. Additionally, it is unclear how the correlation in lines 5-9 of claim 1 are related to the recitation in claim 3. Claim 15 recites a similar limitation, so it is rejected on similar grounds.
Claim 3 recites “desired clinical outcomes” in line 5, which is a relative term which renders the claim indefinite. The term is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. In this case, “desired clinical outcomes” is a subjective term, and the specification does not provide a standard for ascertaining what is desired or not. Claim 15 recites a similar limitation, so it is rejected on similar grounds.
Claim Rejections - 35 USC § 103
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 factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-4, 7-15, 19, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over US 2019/0339221 A1 to Bhavaraju et al. (“Bhavaraju”) (previously cited).
Regarding claim 1, Bhavaraju discloses a method for calibrating (see abstract, “Systems and methods are provided that address the need to frequently calibrate analyte sensors...”) a glucose sensor (see Fig. 1 and [0227], “... the analyte sensor 138 may comprise a glucose sensor configured to measure glucose in the blood or interstitial fluid...”, sensor 138), the method comprising:
determining, by one or more processors, a set of electrical parameters for the glucose sensor (see Fig. 5 and [0256] discloses processing circuitry 5012 uses testing operations to verify/determine electrical properties of sensor 138);
determining, by the one or more processors, a cluster for the glucose sensor from a plurality of clusters (see Fig. 4 and ¶ [0260], [0262] depict reading an identifier 450 which may be used for tracking a sensor based on testing data. See also ¶ [0071] which indicates that the identifier is associated with a manufacturing lot from which the analyte sensor was obtained), wherein each cluster of the plurality of clusters identifies respective configuration information (see [0279] depicts calibration codes being set for each sensor lot), and
configuring, by the one or more processors, the glucose sensor to determine a glucose level of a patient based on configuration information identified by the determined cluster (¶ [0296] depicts configuring sensor 138 to determine analyte concentration (glucose value) based on configuration information identified by the determined cluster (calibration codes assigned to sensor lots).
The above embodiment is silent regarding whether the determination of the cluster is based on the set of electrical parameters, wherein determining the cluster comprises applying a machine learning algorithm that has been trained using in vitro features, corresponding to the set of electrical parameters, which have been correlated to in vivo features.
In a related embodiment, Bhavaraju teaches determination of a cluster is based on the set of electrical parameters (¶¶ [0023]-[0024] depict collated measurements such as impedance, temperature, current measurements, time, etc. can be interpreted and used to determine lot classification, wherein the large amount of data can be input into tools such as machine learning algorithms to identify correlations), wherein determining the cluster comprises applying a machine learning algorithm that has been trained using in vitro features, corresponding to the set of electrical parameters (¶¶ [0022]-[0024] depict the use of machine learning algorithms, which are necessarily trained on features of the impedance, temperature, current measurements, time, etc., ¶¶ [0022]-[0023] depicts the measurements being taken during various phases of manufacture, which is necessarily in vitro), which have been correlated to in vivo features (¶ [0022] depicts the input from the manufacturing and/or calibration equipment being correlated to output measurements during an in vivo phase). It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the determination of the cluster of the embodiment corresponding to Figs. 4-5 to incorporate the lot classification of ¶¶ [0022]-[0024] of Bhavaraju. The motivation would have been to provide a lot classification based on the measurements, thereby allowing for a more accurate determination of sensors with similar characteristics.
Regarding claim 2, Bhavaraju teaches or suggests the method as claimed in claim 1 above. Bhavaraju further discloses wherein the set of electrical parameters comprise a voltage at the glucose sensor, an electrical current for the glucose sensor, or an impedance for the glucose sensor (¶ [0023] discloses impedance and current measurements).
Regarding claim 3, Bhavaraju teaches or suggests the method as claimed in claim 1 above. Bhavaraju further discloses correlating the in vitro features based on the in vivo features for a training set of glucose sensors comprising identifying in vitro features that predict in vivo features representative of desired clinical outcomes (¶¶ [0022]-[0024] depicts correlating input from manufacturing and/or calibration equipment and output measurements during in vivo phase by reference measurements of blood analyte levels (e.g. YSI, finger stick blood glucose meters, laboratory analysis, etc.), which is necessarily applied to a training set of glucose sensors).
Regarding claim 7, Bhavaraju discloses the method as claimed in claim 3 above. Bhavaraju further discloses training, by the one or more processors, the machine learning algorithm using in the vitro features and the in vivo features for the training set of glucose sensors (¶¶ [0022]-[0024] depict the machine learning algorithms for correlating the input and outputs (i.e., training) which is necessarily performed by processors).
Regarding claim 8, Bhavaraju discloses the method as claimed in claim 3 above. Bhavaraju further discloses determining, by the one or more processors, a respective cluster for each glucose sensor of the training set of glucose sensors based on the in vitro features and the in vivo features for the training set of glucose sensors (¶¶ [0023]-[0024] depict collated measurements such as impedance, temperature, current measurements, time, etc. can be interpreted and used to determine lot classification of sensors) and applying a validation model (see [0215], “...determinations of sensor sensitivity change or drift can be used to provide self-calibration, update calibration, supplement calibration based on measurements of known values (e.g., from a reference analyte monitor), and/or validate or reject reference analyte measurements from a reference analyte monitor....based on whether the reference analyte measurements are within a range of values associated with the predetermined sensor sensitivity profile...”, validation of training measurements with respect to reference measurements (of the training set)), wherein determining the cluster for the glucose sensor is based on the in vitro features for the training set of glucose sensors in each respective cluster (see [0271], “... change or drift in sensitivity over a sensor session is not only substantially consistent among sensors manufactured in substantially the same way under substantially same conditions...estimative algorithm function may be generated by testing a sample set (comprising one or more sensors) from a sensor lot under in vivo and/or in vitro conditions...’”, model is trained based on a sample set (training set) of glucose sensors. Sensors originating from the same lot (cluster) experience similar sensitivity profiles, allowing for determining a cluster for a sensor based on the measured sensitivity of the training set of sensors).
However, Bhavaraju is silent regarding the validation model verifying the respective cluster for each glucose sensor of the training set of glucose sensors.
Bhavaraju further discloses that information about sensor lots for individual sensors may be stored (see [0045] “... In addition to using data gathered about individual sensors as feedback during the manufacturing process, sensor lot information may be obtained and stored. In this way additional information may be obtained that can be used as feedback during the manufacturing process...”, sensor lot information gather and stored), and sensor tracking and calibration information may be stored and transmitted for use in calibration and performance data (see [0260], “... Identifier 450 may be used for tracking each sensor through the manufacturing process for that sensor (e.g., by storing a history of testing and/or calibration data for each sensor). For example, identifier 450 may be used for binning of testing and calibration performance data...”, information stored in identifier 450 can be stored and used to associate a sensor from a training set to a sensor lot (cluster)). It is within reasonable expectation of one of ordinary skill in the art to automate a process of validating the sensor lot information from which a sensor under test originated from. To provide a mechanical or automatic means to replace manual activity, which accomplishes the same result, is within the ambit of a person of ordinary skill in the art. See In re Venner, 120 USPQ 192 (CCPA 1958) (see MPEP § 2144.04).
Therefore, 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 validation model disclosed by Bhavaraju to include the step of validating the respective cluster of the glucose sensor with the reasonable expectation that it would result in an improved accuracy of sensor lot tracing.
Regarding claim 9, Bhavaraju discloses the method as claimed in claim 3 above. Bhavaraju further discloses the configuration information comprises a correction factor (see [0283], “... the continuous analyte system may comprise a library of stored sensor sensitivity functions or calibration functions associated with one or more calibration codes...”, calibration code (correction factor)) determined based on a subset of sensor devices of the training set of glucose sensors that are assigned to the cluster (see [0271], “...testing a sample set (comprising one or more sensors) from a sensor lot under in vivo and/or in vitro conditions...”, determined by testing a sample set (subset of sensor devices) from a sensor lot (assigned to the same cluster)).
Regarding claim 10, Bhavaraju discloses the method as claimed in claim 1 above. Bhavaraju further discloses wherein the configuration information comprises a correction factor (see [0283], “... the continuous analyte system may comprise a library of stored sensor sensitivity functions or calibration functions associated with one or more calibration codes...”, calibration code (correction factor)).
Regarding claim 11, Bhavaraju discloses the method as claimed in claim 1 above. Bhavaraju further discloses, wherein the glucose sensor is a first glucose sensor of a plurality of glucose sensors, wherein the cluster is a first cluster, and the set of electrical parameters is a first set of electrical parameters (see [0272], “... the above-described test may be performed on each individual sensor, or alternatively on one or more sample sensors of a sensor lot...”, Examiner is interpreting the first glucose sensor, associated with a first set of electrical parameters and a first cluster, to be a first sample sensor of a sensor lot, where testing of “each individual sensor” indicates the presence of a plurality of sensors) the method further comprising:
determining, by the one or more processors, a second set of electrical parameters for a second glucose sensor of the plurality of glucose sensors (see [0256], “... Testing operations may include verifying electrical properties of a sensor 138...”, electrical parameters determined for each sensor in the sample sensor set);
determining, by the one or more processors, a second cluster of the plurality of clusters for the second glucose sensor based on the second set of electrical parameters (see Fig. 4 and [0260], “... Identifier 450 may be used for tracking each sensor through the manufacturing process for that sensor (e.g., by storing a history of testing and/or calibration data for each sensor)...”, identifier 450 identifies and tracks a sensor based on testing data (electrical parameters)). See also [0108], “... the transmitting further comprises transmitting a sensor tracking number...whereby a lot associated with the sensor can be identified...”, identification of a lot (cluster) of each sensor based on identifier. Examiner is interpreting identifying a sensor lot (cluster) implies the presence of multiple sensor lots (plurality of clusters));
determining, by the one or more processors, that the second glucose sensor does not satisfy a quality metric (see [0248]; “...sensor electronics 112 (e.g., via processor module 214) may be implemented to execute prospective algorithms used to generate transformed sensor data and/or displayable sensor information, including, for example, algorithms that: evaluate a clinical acceptability of optional reference and/or sensor data, evaluate a quality of the calibration...”, processor module 214 (processor) determines satisfaction of a quality metric) in response to determining that the second glucose sensor is associated with the second cluster (see [0279], “...calibration codes may be assigned to each sensor or sensor set to define parameters that can affect sensor sensitivity or provide additional information about the sensitivity profile......”, each sensor lot (cluster) contains information specific to the sensitivity profile of the sensor lot to assign a calibration code (configuration information)) ; and
outputting, by the one or more processors, an indication (see [0248], “... generate transformed sensor data and/or displayable sensor information, including... evaluate a quality of the calibration...”, displayable information to evaluate a quality of a calibration is interpreted as outputting an indication of a quality metric) that the second glucose sensor does not satisfy the quality metric (see [0273], “...If the curve fit is determined to be satisfactory (e.g., if the standard deviation of the generated data points is less a certain threshold), then the sensor sensitivity profile or curve may be judged to have passed a quality control...”, determination of whether or not sensitivity profile (determined using measured electrical parameters) satisfies a quality metric).
Regarding claim 12, Bhavaraju discloses the method as claimed in claim 1 above. Bhavaraju further discloses wherein configuring the glucose sensor comprises outputting an indication of the cluster (see [0238], “.... processor module 214 may further include a data generator (not shown) configured to generate data packages for transmission to devices, such as the display devices 114, 116, 118, and/or 120... data packages may include an identifier code for the sensor and/or sensor electronics...”, identifier code for the sensor is output to display. See also [0071], “... the identifier is associated with a manufacturing lot from which the analyte sensor was obtained”, identifier indicates the lot (cluster) with which the sensor is associated).
Regarding independent claim 13, Bhavaraju discloses a device for calibrating (see Fig. 5 and [0255], "... one more calibration stations 5004...each configured to receive sensor interposer 402 and to communicatively couple to sensor 138 via sensor interposer 402...”, sensor interposer 402 (device for calibrating) for calibrating sensor 138 (glucose sensor)), the device comprising:
a memory (see Fig. 4 and [0260], “Identifier 450 may be used for digitally storing data in non-volatile memory on substrate 404 or as a reference number for storing data external to interposer 402...”, memory of substrate 404); and
one or more processors implemented in circuitry and in communication with the memory (see Fig. 5 and [0256], “Processing circuitry 5012 may be communicatively coupled with sensor 138 for testing operations by inserting substrate 404 into a receptacle 5006...”, processing circuitry 5012 (processor implemented in circuitry) communicates with memory (memory stored on substrate 404) when substrate is inserted into system 5000), the one or more processors configured to:
determine a set of electrical parameters for the glucose sensor (see Fig. 5 and [0256], “... processing circuitry 5012 configured to perform testing operations with sensor 138 to determine parameters and/or to verify the operational integrity of sensor 138. Testing operations may include verifying electrical properties of a sensor 138...”, processing circuitry (processor) determines electrical properties (electrical parameters) of sensor 138);
determine a cluster for the glucose sensor from a plurality of clusters (see Fig. 4 and [0260], “... Identifier 450 may be used for tracking each sensor through the manufacturing process for that sensor (e.g., by storing a history of testing and/or calibration data for each sensor)...”, identifier 450 identifies and tracks a sensor based on testing data (electrical parameters)). See also [0108], “... the transmitting further comprises transmitting a sensor tracking number...whereby a lot associated with the sensor can be identified...”, identification of a lot (cluster) of each sensor based on identifier. Examiner is interpreting identifying a sensor lot (cluster) implies the presence of multiple sensor lots (plurality of clusters)), wherein each cluster of the plurality of clusters identifies respective configuration information (see [0279], “...calibration codes may be assigned to each sensor or sensor set to define parameters that can affect sensor sensitivity or provide additional information about the sensitivity profile......”, each sensor lot (cluster) contains information specific to the sensitivity profile of the sensor lot to assign a calibration code (configuration information); and
configure the glucose sensor to determine a glucose level of a patient based on configuration information identified by the determined cluster (see [0296], “...calibration process may use any available a priori information comprising sensor sensitivity information in order to obtain a calibration factor that can be used to convert sensor data (e.g., in units of current or counts) into estimated analyte values (e.g., in unit of analyte concentration)...”, configuring sensor 138 to determine analyte concentration (glucose value) based on configuration information identified by the determined cluster (calibration codes assigned to sensor lots).
The above embodiment is silent regarding whether the determination of the cluster is based on the set of electrical parameters, wherein determining the cluster comprises applying a machine learning algorithm that has been trained using in vitro features, corresponding to the set of electrical parameters, which have been correlated to in vivo features.
In a related embodiment, Bhavaraju teaches determination of a cluster is based on the set of electrical parameters (¶¶ [0023]-[0024] depict collated measurements such as impedance, temperature, current measurements, time, etc. can be interpreted and used to determine lot classification, wherein the large amount of data can be input into tools such as machine learning algorithms to identify correlations), wherein determining the cluster comprises applying a machine learning algorithm that has been trained using in vitro features, corresponding to the set of electrical parameters (¶¶ [0022]-[0024] depict the use of machine learning algorithms, which are necessarily trained on features of the impedance, temperature, current measurements, time, etc., ¶¶ [0022]-[0023] depicts the measurements being taken during various phases of manufacture, which is necessarily in vitro), which have been correlated to in vivo features (¶ [0022] depicts the input from the manufacturing and/or calibration equipment being correlated to output measurements during an in vivo phase). It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the determination of the cluster of the embodiment corresponding to Figs. 4-5 to incorporate the lot classification of ¶¶ [0022]-[0024] of Bhavaraju. The motivation would have been to provide a lot classification based on the measurements, thereby allowing for a more accurate determination of sensors with similar characteristics.
Regarding claim 14, Bhavaraju discloses the device as claimed in claim 13 above. Bhavaraju further discloses wherein the set of electrical parameters comprise a voltage at the glucose sensor, an electrical current for the glucose sensor, or an impedance for the glucose sensor (¶ [0023] discloses impedance and current measurements).
Regarding claim 15, Bhavaraju discloses the device as claimed in claim 13 above. Bhavaraju further discloses correlating the in vitro features based on the in vivo features for a training set of glucose sensors comprising identifying in vitro features that predict in vivo features representative of desired clinical outcomes (¶¶ [0022]-[0024] depicts correlating input from manufacturing and/or calibration equipment and output measurements during in vivo phase by reference measurements of blood analyte levels (e.g. YSI, finger stick blood glucose meters, laboratory analysis, etc.), which is necessarily applied to a training set of glucose sensors).
Regarding claim 19, Bhavaraju discloses the device as claimed in claim 15 above. Bhavaraju further discloses wherein the one or more processors are configured to train the machine learning algorithm using in the vitro features and the in vivo features for the training set of glucose sensors (¶¶ [0022]-[0024] depict the machine learning algorithms for correlating the input and outputs (i.e., training) which is necessarily performed by processors).
Regarding independent claim 20, Bhavaraju discloses a non-transitory computer-readable storage medium having instructions stored thereon (see Fig. 2 and [0240], “...program memory 216 may be implemented as a semi-static memory for storing data...and for storing code (also referred to as program code) to configure the ASIC 205 to perform one or more of the operations/functions described herein...”, memory 216 stores program code (instructions)) that when executed, configure a processor to (see Fig. 2 and [0240], “...the program code may configure processor module 214 to process data streams or counts, filter, perform the calibration methods described below, perform fail-safe checking, and the like....”, program code (instructions) when executed configure processor module 214 (processor) to process data) :
determine a set of electrical parameters for a glucose sensor (see Fig. 5 and [0256], “... processing circuitry 5012 configured to perform testing operations with sensor 138 to determine parameters and/or to verify the operational integrity of sensor 138. Testing operations may include verifying electrical properties of a sensor 138...”, processing circuitry (processor) determines electrical properties (electrical parameters) of sensor 138 (glucose sensor));
determine a cluster for the glucose sensor from a plurality of clusters (see Fig. 4 and [0260], “... Identifier 450 may be used for tracking each sensor through the manufacturing process for that sensor (e.g., by storing a history of testing and/or calibration data for each sensor)...”, identifier 450 identifies and tracks a sensor based on testing data (electrical parameters)). See also [0108], “... the transmitting further comprises transmitting a sensor tracking number...whereby a lot associated with the sensor can be identified...”, identification of a lot (cluster) of each sensor based on identifier. Examiner is interpreting identifying a sensor lot (cluster) implies the presence of multiple sensor lots (plurality of clusters)), wherein each cluster of the plurality of clusters identifies respective configuration information (see [0279], “...calibration codes may be assigned to each sensor or sensor set to define parameters that can affect sensor sensitivity or provide additional information about the sensitivity profile......”, each sensor lot (cluster) contains information specific to the sensitivity profile of the sensor lot to assign a calibration code (configuration information)); and
configure the glucose sensor to determine a glucose level of a patient based on configuration information identified by the determined cluster (see [0296], “...calibration process may use any available a priori information comprising sensor sensitivity information in order to obtain a calibration factor that can be used to convert sensor data (e.g., in units of current or counts) into estimated analyte values (e.g., in unit of analyte concentration)...”, configuring sensor 138 to determine analyte concentration (glucose value) based on configuration information identified by the determined cluster (calibration codes assigned to sensor lots).
The above embodiment is silent regarding whether the electrical parameters comprise a voltage at the glucose sensor, an electrical current for the glucose sensor, or an impedance for the glucose sensor, whether the determination of the cluster is based on the set of electrical parameters, wherein determining the cluster comprises applying a machine learning algorithm that has been trained using in vitro features, corresponding to the set of electrical parameters, which have been correlated to in vivo features.
In a related embodiment, Bhavaraju teaches determination of a cluster is based on the set of electrical parameters (¶¶ [0023]-[0024] depict collated measurements such as impedance, temperature, current measurements, time, etc. can be interpreted and used to determine lot classification, wherein the large amount of data can be input into tools such as machine learning algorithms to identify correlations), wherein the set of electrical parameters comprise a voltage at the glucose sensor, an electrical current for the glucose sensor, or an impedance for the glucose sensor (¶ [0023] discloses impedance and current measurements), wherein determining the cluster comprises applying a machine learning algorithm that has been trained using in vitro features, corresponding to the set of electrical parameters (¶¶ [0022]-[0024] depict the use of machine learning algorithms, which are necessarily trained on features of the impedance, temperature, current measurements, time, etc., ¶¶ [0022]-[0023] depicts the measurements being taken during various phases of manufacture, which is necessarily in vitro), which have been correlated to in vivo features (¶ [0022] depicts the input from the manufacturing and/or calibration equipment being correlated to output measurements during an in vivo phase). It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the determination of the cluster of the embodiment corresponding to Figs. 4-5 to incorporate the lot classification based on the electrical parameters of ¶¶ [0022]-[0024] of Bhavaraju. The motivation would have been to provide a lot classification based on the measurements, thereby allowing for a more accurate determination of sensors with similar characteristics.
Claims 4 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Bhavaraju, as applied to respective claims 3 and 15 above, and in view of a dissertation entitled “Study of reconstruction ICA for feature extraction in images and signals” by Marc Beltrán Segarra (“Segarra”) (previously cited).
Regarding claims 4 and 16, Bhavaraju teaches or suggests respective claims 3 and 15 above. Bhavaraju further discloses wherein the machine learning algorithm is applied to the set of electrical parameters (¶¶ [0022]-[0024] depict the use of machine learning algorithms, which are necessarily trained on features of the impedance, temperature, current measurements, time, etc., ¶¶ [0022]-[0023] depicts the measurements being taken during various phases of manufacture, which is necessarily in vitro), wherein the machine learning algorithm has been trained using the in vitro features and the in vivo features for the training set of glucose sensors(¶¶ [0022]-[0024] depicts correlating input from manufacturing and/or calibration equipment and output measurements during in vivo phase by reference measurements of blood analyte levels (e.g. YSI, finger stick blood glucose meters, laboratory analysis, etc.), which is necessarily applied to a training set of glucose sensors).
However, Bhavaraju fails to disclose applying a reconstruction independent component analysis (RICA) algorithm to the set of electrical parameters.
Segarra teaches methods of reconstruction independent component analysis for feature extraction in signals (see pg. 22-25, RICA algorithm applied to signal input parameters). Therefore, 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 machine learning algorithm disclosed by Bhavaraju to include the RICA algorithm taught by Segarra with the reasonable expectation that it would result in an algorithm that accounts for the weight associated with measured electrical parameters and increases algorithm robustness.
Claims 5 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Bhavaraju, as applied to respective claims 3 and 15 above, and in view of a research article entitled “Multi-Ion-Sensing Emulator and Multivariate Calibration Optimization by Machine Learning Models” by Hanitra et al. (“Hanitra”) (previously cited).
Regarding claims 5 and 17, Bhavaraju teaches or suggests respective claims 3 and 15 above. Bhavaraju further discloses wherein the machine learning algorithm is applied to the set of electrical parameters (¶¶ [0022]-[0024] depict the use of machine learning algorithms, which are necessarily trained on features of the impedance, temperature, current measurements, time, etc., ¶¶ [0022]-[0023] depicts the measurements being taken during various phases of manufacture, which is necessarily in vitro), wherein the machine learning algorithm has been trained using the in vitro features and the in vivo features for the training set of glucose sensors(¶¶ [0022]-[0024] depicts correlating input from manufacturing and/or calibration equipment and output measurements during in vivo phase by reference measurements of blood analyte levels (e.g. YSI, finger stick blood glucose meters, laboratory analysis, etc.), which is necessarily applied to a training set of glucose sensors).
However, Bhavaraju fails to disclose applying a principal components analysis (PCA) algorithm to the set of electrical parameters.
Hanitra teaches machine learning models for a multivariate calibration procedure to optimize sensor calibration (see abstract) including applying a principal component analysis (PCA) algorithm to signal tensors (see pg. 46828, Section(V), “... the signals output by an array of sensors are processed by a multivariate model... let X...denote the tensor of OCP signals...application of PCA to X will generate a matrix T...”, applying a PCA algorithm to sensor signal tensors). Therefore, 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 machine learning algorithm disclosed by Bhavaraju to include the PCA algorithm taught by Hanitra with the reasonable expectation that it would result in an algorithm that accounts for the variance in measured electrical parameters and decreases the computational load.
Claims 6 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Bhavaraju, as applied to respective claims 3 and 15 above, and in view of Hanitra and Segarra.
Regarding claims 6 and 18, Bhavaraju teaches or suggests respective claims 3 and 15 above. Bhavaraju further discloses wherein the machine learning algorithm is applied to the set of electrical parameters (¶¶ [0022]-[0024] depict the use of machine learning algorithms, which are necessarily trained on features of the impedance, temperature, current measurements, time, etc., ¶¶ [0022]-[0023] depicts the measurements being taken during various phases of manufacture, which is necessarily in vitro), wherein the machine learning algorithm has been trained using the in vitro features and the in vivo features for the training set of glucose sensors(¶¶ [0022]-[0024] depicts correlating input from manufacturing and/or calibration equipment and output measurements during in vivo phase by reference measurements of blood analyte levels (e.g. YSI, finger stick blood glucose meters, laboratory analysis, etc.), which is necessarily applied to a training set of glucose sensors).
However, Bhavaraju fails to disclose applying both a reconstruction independent component analysis (RICA) algorithm and a principal components analysis (PCA) algorithm to the set of electrical parameters.
Hanitra teaches machine learning models for a multivariate calibration procedure to optimize sensor calibration (see abstract) including applying a PCA algorithm as a pre-processing step before applying an additional multi-variable algorithm (see pg. 46829 Section(C), “Prior to multivariate calibration, PCA is applied to the input tensor X”). Therefore, 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 machine learning algorithm disclosed by Bhavaraju to include the pre-processing PCA algorithm taught by Hanitra with the reasonable expectation that it would result in an algorithm that accounts for the variance in measured electrical parameters.
However, the model taught by the Bhavaraju/Hanitra combination fails to disclose that the multi-variable algorithm used to optimize sensor calibration is a RICA model.
Segarra teaches methods of reconstruction independent component analysis for feature extraction in signals, using a PCA algorithm as a pre-processing step (see pg. 29, training data is pre-processed with PCA algorithm before RICA algorithm is applied to signal input parameters). Therefore, 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 machine learning algorithm taught by the Bhavaraju/Hanitra combination to include the RICA algorithm taught by Hanitra with the reasonable expectation that it would result in an algorithm that accounts for the weight associated with measured electrical parameters and decreases computational cost.
Response to Arguments
Claim Rejections under 35 U.S.C. §§ 102 and 103
Applicant’s arguments, see pages 8-9 of the Remarks filed 12/29/2025, with respect to the rejection of claims 3 and 20 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of a different interpretation of Bhavaraju.
Specifically, the disclosure corresponding to Figs. 4-5 and ¶¶ [0256]-[0296] of Bhavaraju is silent regarding whether the electrical parameters comprise a voltage at the glucose sensor, an electrical current for the glucose sensor, or an impedance for the glucose sensor, whether the determination of the cluster is based on the set of electrical parameters, wherein determining the cluster comprises applying a machine learning algorithm that has been trained using in vitro features, corresponding to the set of electrical parameters, which have been correlated to in vivo features.
In a related embodiment, Bhavaraju teaches determination of a cluster is based on the set of electrical parameters (¶¶ [0023]-[0024] depict collated measurements such as impedance, temperature, current measurements, time, etc. can be interpreted and used to determine lot classification, wherein the large amount of data can be input into tools such as machine learning algorithms to identify correlations), wherein the set of electrical parameters comprise a voltage at the glucose sensor, an electrical current for the glucose sensor, or an impedance for the glucose sensor (¶ [0023] discloses impedance and current measurements), wherein determining the cluster comprises applying a machine learning algorithm that has been trained using in vitro features, corresponding to the set of electrical parameters (¶¶ [0022]-[0024] depict the use of machine learning algorithms, which are necessarily trained on features of the impedance, temperature, current measurements, time, etc., ¶¶ [0022]-[0023] depicts the measurements being taken during various phases of manufacture, which is necessarily in vitro), which have been correlated to in vivo features (¶ [0022] depicts the input from the manufacturing and/or calibration equipment being correlated to output measurements during an in vivo phase). It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the determination of the cluster of the embodiment corresponding to Figs. 4-5 to incorporate the lot classification based on the electrical parameters of ¶¶ [0022]-[0024] of Bhavaraju. The motivation would have been to provide a lot classification based on the measurements, thereby allowing for a more accurate determination of sensors with similar characteristics.
The rejections of claims 1, 13, and 20 reflect the different interpretation which has not been specifically challenged in the arguments.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 2019/0175082 A (Varsavsky) teaches using machine learning to determine a type of sensor being used based on EIS data (¶ [0730]) and calibrating the sensor based on the determined type (¶ [0731]).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SAMUEL C KIM whose telephone number is (571)272-8637. The examiner can normally be reached M-F 8:00 AM - 5:00 PM EST.
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, Jacqueline Cheng can be reached at (571) 272-5596. 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.
/S.C.K./Examiner, Art Unit 3791
/JACQUELINE CHENG/Supervisory Patent Examiner, Art Unit 3791