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 .
REQUEST FOR CONTINUED EXAMINATION
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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 10/21/2025 has been entered.
Information Disclosure Statement
The IDS filed 6/29/2021, 3/15/2023 and 7/11/2023 have been considered by the Examiner.
Priority
Applicant’s claim for the benefit of a prior-filed application under 35 U.S.C. 119(e) or under 35 U.S.C. 120, 121, or 365(c) is acknowledged. Priority of US application 62/759630 filed 11/07/2018 is acknowledged.
Status of Claims
Amendments to the claims are acknowledged.
Claims 1-13 and 17 are under consideration.
Claims 14-16 and 18 are cancelled.
Claim Rejections - 35 USC § 101
The rejection of claims 1-13 and 17 under 35 U.S.C. 101 is withdrawn in view of amendments filed 4/07/2026.
Claim Rejections - 35 USC § 103
The instant rejection is maintained from the Office Action of 1/07/2026 and modified to address amendments filed 4/07/2026
The following is a quotation of 35 U.S.C. 103(a) which forms the basis for all obviousness rejections set forth in this Office action:
(a) A patent may not be obtained though the invention is not identically disclosed or described as set forth in section 102 of this title, if the differences between the subject matter sought to be patented and the prior art are such that the subject matter as a whole would have been obvious at the time the invention was made to a person having ordinary skill in the art to which said subject matter pertains. Patentability shall not be negatived by the manner in which the invention was made.
This application currently names joint inventors. In considering patentability of the claims under 35 U.S.C. 103(a), the examiner presumes that the subject matter of the various claims was commonly owned at the time any inventions covered therein were made absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and invention dates of each claim that was not commonly owned at the time a later invention was made in order for the examiner to consider the applicability of 35 U.S.C. 103(c) and potential 35 U.S.C. 102(e), (f) or (g) prior art under 35 U.S.C. 103(a).
Claims 1-13 and 17 are rejected under 35 U.S.C. 103(a) as being unpatentable over Neemuchwala et al. (2018/0272063; IDS filed 6/29/2021) in view of Moller et al. (Temporal Illness Prediction using a Bayesian Model, Master Thesis, 2014)
Neemuchwala et al. teach predicting the physiological condition of a patient by forecasting glucose levels in the future based on measured blood glucose levels (par. 0005-0007); Neemuchwala et al. teach using several models including patient historical data to make future patient glucose level predictions (par. 0007 and 0010).
Neemuchwala et al. teach obtaining current glucose measurement data from a patient (par. 0010); continuous glucose monitoring and forecasting is taught including while the patient is sleeping (par. 0003 and 0125)(i.e. providing spot monitoring blood glucose measurement data representing a plurality of blood glucose measurement values for a measurement time period, the spot monitoring blood glucose measurement data including respective measurement times at which measurements have been made), as in claims 1 and 13.
Neemuchwala et al. teach measuring different types of glucose excursion events including hyperglycemic event, hypoglycemic event or acute diabetic ketoacidosis)(par. 0061); Neemuchwala et al. teach forecasting glucose values below a lower threshold for a patient’s target glucose range and therefore indicating a hypoglycemic event (par. 0129)(i.e. blood glucose assigned to a first adverse blood glucose range at the prediction time) or predicting hyperglycemic event which suggests blood glucose assigned to a second adverse blood glucose range at the prediction time (par. 0152), as in claims 1 and 13.
It is noted that hypoglycemic levels are known to those of ordinary skill in the art to be below a predetermined threshold and hyperglycemic levels are above a predetermined threshold. The instant specification (par. 0026) discloses an embodiment where the blood glucose levels pertain to determining hyperglycemia and hypoglycemia.
Neemuchwala et al. teach determining a physiological condition in the future based on current measurement data (par. 0005) including an hourly forecasting model associated with the patient (par. 0007, 0011, 0012); Neemuchwala et al. teach (par. 0152) performing an ensemble prediction process to predict a patient’s glucose level and probabilistically determining the likelihood of a physiological event including a hypoglycemic or hyperglycemic event over the next 12 hours (i.e. applying an analysis algorithm to determining from the spot monitoring blood glucose measurement data a probability of (i) the blood glucose value being in the first adverse range or (ii) in the second adverse range at the predicted time), as in claims 1 and 13.
Neemuchwala et al. teach displaying on a display a graphical representation of the simulated glucose level with respect to the time in the future (par. 0007)(i.e. providing output data indicative of the prediction time and the probability at the prediction time), as in claims 1 and 13.
Neemuchwala et al. teach an infusion device that adjusts of modifies delivery of fluid based on the patient’s risk score (par. 0168) and delivers insulin by an infusion device (par. 0082 and 0102)(i.e. instructing an insulin pump to administer insulin based on the prediction time and probability that the patient’s blood glucose level is in an adverse range), as in claims 1 and 13, step (f).
Neemuchwala et al. teach an infusion pump that delivers insulin to the body according to an infusion program including receiving a target or commanded glucose to maintain glucose above a sensed level (par. 0102)(i.e. instructing an insulin pump to administer insulin based on the prediction time and probability that the patient’s blood glucose level is in an adverse range), as in claims 1 and 13.
Neemuchwala et al. teach hourly forecasting (par. 0010), time windows, sampling times (par. 0138)(i.e. a plurality of prediction times in a prediction period of time and a continuous course of the probability), as in claims 2 and 3.
Neemuchwala et al. teach (par. 0152) performing an ensemble prediction process to predict a patient’s glucose level and probabilistically determining the likelihood of a physiological event including a hypoglycemic or hyperglycemic event over the next 12 hours (i.e. determining a probability of being in the first adverse blood glucose range and in the second blood glucose range), as in claim 4.
Neemuchwala et al. teach determining threshold glucose values (par. 0103) and a target range of 80 mg/dL to 140 mg/dL (i.e. values assigned to a non-adverse range) and then determining glucose values in the target range (par. 0129)(i.e. non-adverse blood glucose range at the prediction time), as in claim 5.
Neemuchwala et al. teach blood glucose thresholds indicative of hypoglycemia and hyperglycemia (par. 0152 and 0168)(i.e. a first and second range of blood glucose values indicative of a hypoglycemic and hyperglycemic state), as in claim 10.
Neemuchwala et al. teach a processor and computer readable medium (par. 0068), as in claims 11-12.
Neemuchwala et al. teach an infusion device that adjusts of modifies delivery of fluid based on the patient’s risk score (par. 0168) and delivers insulin by an infusion device (par. 0082 and 0102), which inherently means an insulin parameter is transmitted, as in claim 17.
Neemuchwala et al. teach predicative models for predicting future meals and future medication dosages (par. 0123)(i.e. which suggests the carbohydrate dose is self administered), as in claim 18.
Neemuchwala et al. teach predicative models for determining physiological state of a patient based on blood glucose measurements, including predicting hypoglycemia and hyperglycemia. Neemuchwala et al. do not specifically teach applying a kernel density estimation and Bayes’ rule to determine the probability of a patient’s blood glucose to be in a first and second adverse blood glucose range.
Moller et al. teach predicting illnesses based on analysis samples using Kernel Density Estimation and a Bayesian model (Abstract) in particular, a Bayes’ model (page 27, par. 3) using Bays’ rule (page 28, par. 1 and page 40, par. 2). Moller et al. teach measuring a medical property of a patient including blood sugar level (i.e. blood glucose) at various time points (page 5, par. 3 and Figures 1 and 3). Moller et al. teach determining a probability of illness based on blood sugar (page 27, par. 1) and determining probability of illness using Bayes’ rule (page 28)(i.e. applying an analysis algorithm comprising application of Bayes’ rule), including from measurements take over time in an observation interval to arrive at a prediction interval to predict an illness (page 32, par. 4 and Figure 20), as in claim 1 and 13.
Moller et al. teach applying Kernel Density Estimation (page 34) to predict a medical condition for a given medical property based on time (i.e. applying an analysis algorithm comprising a kernel density estimation), as in claims 1 and 13.
Moller et al. teach that bandwidth variable is used to control the certainty with which a diagnosis can be predicted and teach two kernel density estimations with two different bandwidths (page 36, par. 1 and Figure 22)(i.e. wherein a first kernel bandwidth is applied for the first glucose measurement and a second different kernel bandwidth is applied to the second blood glucose measurement), as in claims 1 and 13.
It would be obvious to one or ordinary skill in the art to fit different measurement data to different bandwidths so as to control the certainty with which a diagnosis can be predicted, as taught my Moller et al. (page 36 and page 42). It is known to those of ordinary skill in the art (page 42) that kernel bandwidths can be adjusted and determined based on the data that is modelled. Therefore determining a first, second and third bandwidth for measured temporal data from a glucose blood monitor is merely a combination of known elements taught by the prior art. Performing a fitting for a first, second and third band width where one bandwidth is broader than the second (as in Figure 22) would therefore be obvious, as in independent claims 1 and 13 and dependent claims 6 and 8.
Moller et al. teach applying a first and second bandwidth value (page 36, par. 1 and Figure 22) and that bandwidth would be tuned for any given data set (page 42, last line), as in claim 9.
Moller et al. teach applying a chosen kernel function which is a Gaussian kernel function (page 43)(i.e. a periodic kernel in the kernel density estimation), as in claim 7.
It would have been obvious to one of ordinary skill in the art at the time the invention was made to have combined the teachings of Neemuchwala et al. for predicting adverse blood glucose states from blood glucose measurements with the teachings of Moller et al. for performing Kernel Density Estimate and Bayes’ Rules modeling of physiological data to predict a future medical condition based on the modeled data. Moller et al. provide motivation by teaching that Kernel Density Estimation applied to temporal (time related) data resulted in a model that outperformed naïve approaches (page v, Abstract). One of skill in the art would have had a reasonable expectation of success at combining the teachings of Neemuchwala et al. and Moller et al. because both teach that blood glucose (or blood sugar as in Moller et al.) data can be modelled to predict future patient conditions based on the data.
Response to Arguments
Applicant's arguments filed 4/07/2026 have been fully considered but they are not persuasive.
With respect to applicant’s Amendments to claims 1 and 13, Neemuchwala et al. teach a simulated glucose level with respect to time in the future (par. 0007) and administering insulin with a pump according to a sensed level (par. 0102), as set forth above. Neemuchwala et al. therefore make obvious instructing an insulin pump to administer insulin based on the prediction time and probability that the patient’s blood glucose level is in an adverse range.
Applicants argue (Remarks, page 6, par. 5-6) that Neemuchwala et al. does not teach applying an analysis algorithm comprising a kernel density estimation and application of Bayes’ rule. Applicants argue that Moller teaches predicting whether a person has diabetes and not whether their blood sugar is likely to be high or low at any given future time. Applicants argue that combining Neemuchwala et al. with Moller et al. would not be obvious.
In response, Moller et al. teach Applicant’s claimed a kernel density estimation and application of Bayes’ rule, as applied to temporal illness prediction (Moller, title). The temporal illness prediction is a prediction of illness occurrent at a future time. While Moller et al. is not specific with respect to the data inputted and analyzed by the kernel density estimation and Bayes’ rule, Moller et al. suggest that the medical property analyzed by kernel density estimation (page 34) is blood sugar (page 27, par. 1). However, the instant claims are also drawn to applying a kernel density estimation to a blood glucose measurement and are not specific with respect to how the kernel density estimation is applied. Moller et al. teach that their kernel density estimation is a probability estimation for a predicted time t (page 34). It would therefore be obvious to apply Moller’s kernel density estimation to the measured glucose data of Neemuchwala et al. to arrive at Applicant’s limitation of applying a kernel density estimation to the blood glucose monitoring data. Moller et al.’s teaching that the probability that the patient has illness condition “i” would predict blood glucose in an adverse glucose range as taught by Neemuchwala et al. Such is a combination of known elements to arrive at a predictable result.
Additional Noted Prior Art
Ghosh, Anil K., Probal Chaudhuri, and Debasis Sengupta. "Classification using kernel density estimates: Multiscale analysis and visualization." Technometrics 48.1 (2006): 120-132.
E-mail communication Authorization
Per updated USPTO Internet usage policies, Applicant and/or applicant’s representative is encouraged to authorize the USPTO examiner to discuss any subject matter concerning the above application via Internet e-mail communications. See MPEP 502.03. To approve such communications, Applicant must provide written authorization for e-mail communication by submitting the following statement via EFS Web (using PTO/SB/439) or Central Fax (571-273-8300):
Recognizing that Internet communications are not secure, I hereby authorize the USPTO to communicate with the undersigned and practitioners in accordance with 37 CFR 1.33 and 37 CFR 1.34 concerning any subject matter of this application by video conferencing, instant messaging, or electronic mail. I understand that a copy of these communications will be made of record in the application file.
Written authorizations submitted to the Examiner via e-mail are NOT proper. Written authorizations must be submitted via EFS-Web (using PTO/SB/439) or Central Fax (571-273-8300). A paper copy of e-mail correspondence will be placed in the patent application when appropriate. E-mails from the USPTO are for the sole use of the intended recipient, and may contain information subject to the confidentiality requirement set forth in 35 USC § 122. See also MPEP 502.03.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Anna Skibinsky whose telephone number is (571) 272-4373. The examiner can normally be reached on 12 pm - 8:30 pm.
If attempts to reach the examiner by telephone are unsuccessful, the examiner's supervisor, Ram Shukla can be reached on (571) 272-7035. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/Anna Skibinsky/
Primary Examiner, AU 1635
Prosecution Insights