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 .
DETAILED ACTION
This action is responsive to the following communication: Preliminary Amendment filed Jul. 18, 2024.
Claims 16-35 are pending in the case. Claims 16, 23 and 30 are independent claims.
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.
Claims 16-35 are rejected under 35 U.S.C. 103 as being unpatentable over Zhong et al. (hereinafter Zhong) U.S. Patent Pub No. 2018/0271455 in view of Shvets et al. (hereinafter Shvets) U.S. Patent Pub No. 2020/0227170 and further in view of.
With respect to independent claim 16, Zhong teaches a method implemented by a computer system (see e.g. Para [68][107]), the method comprising:
receiving data representing respective medical records of a plurality of first patients, each patient in the plurality of first patients having been diagnosed with diabetes mellitus, and using a first type of insulin (see e.g. Para [161] – “the risk management process 1700 begins by receiving or otherwise obtaining measurement data and medical records data for a patient population (tasks 1702, 1704). For example, the server 102 may retrieve from the database 104, a subset of historical patient data 120 for a population of patients and a corresponding subset of the electronic medical records data 122 for that patient population.”);
determining respective first predicted rates of hypoglycemic events for each first patient by processing the medical records using a first machine learning model that has been trained using first training data that comprises data representing first medical records of a plurality of first training patients and corresponding rate of hypoglycemic events for the respective first training patients (see e.g. Fig. 17 and Para [61][122] [165]-[167] –“calculate or otherwise determine, based on the patient's recent measurement data and medical record fields, an output value representing the patient's probability of developing or experiencing the medical condition associated with the risk prediction model, that is, the patient's risk score for that condition. “),
identifying, in the medical records of the plurality of first patients and based on the first predicated rates, one or more first covariates that correlate to a first predicted rate of hypoglycemic events (see e.g. Fig. 17 and Para [161]-[167] –“ stepwise feature selection, such as recursive feature elimination, is performed to identify which fields or attributes of the patient measurement data and medical records data are most correlative to or predictive of the occurrence of a particular condition within the patient population.”); and
generating a report that indicates the identified first covariates, and a correlation between the identified first covariates and the first predicted rate of hypoglycemic event (see e.g. Para [227]-“ The reporting layer 2530 may include a report wizard program that pulls data from selected locations in the database 2529 and generates report information from the desired parameters of interest. The reporting layer 2530 may be configured to generate multiple different types of reports, each having different information and/or showing information in different formats (arrangements or styles), where the type of report may be selectable by the user. A plurality of pre-set types of report (with pre-defined types of content and format) may be available and selectable by a user. “).
Zhong does not expressly show each of the first training patients uses the first type of insulin. However, Zhong expressly discloses defining a cohort by common features (see e.g., Para [171] –“ patient cohorts may be characterized or defined utilizing clustering techniques to classify similar patients using other available data sets, such as, for example, mood logs, program interactions, personal goals, and/or the like, which, for example, may be tracked, monitored or logged by an application at a client device 106.”) Furthermore, Shvets teaches that insulin type is recorded for each patient’s insulin injection (see e.g. Para [68]-[92] –“a plurality of injected insulin dose size taken over a time course, and for each respective injected dose size in the plurality of injected doses, a corresponding timestamp representing when in the time course the respective dose was injected and a respective typestamp of the insulin medicament injected”). It would have been obvious to include the above feature because insulin type data is already gathered based on each patient and training patients using the first type of insulin would be a clear design choice. Both Zhong and Shvets are directed to machine learning based patient glucose prediction system. Accordingly, it would have been obvious to the skilled artisan before the effective filing date of the claimed invention having Shvets and Zhong in front of them to modify the system of Zhong to include the above feature. The motivation to combine Shvets and Zhong comes from Shvets. Shvets discloses the motivation to monitor insulin type for each patient so that prediction can be more accurate (see e.g. para [71]). This motivation for combination also applies to the remaining claims which depend on this combination.
With respect to dependent claim 17, the modified Zhong teaches identifying in the medical records of the plurality of first patients one or more second covariates that correspond to a second predicted rate of hypoglycemic events (see e.g. Fig. 17 Para [163]-[172]-“ for a given medical diagnosis code of interest (e.g., hypoglycemia, diabetic ketoacidosis, hyperosmolarity, cardiovascular disease, and/or the like), the server 102 may perform stepwise feature selection across of the different sensor glucose measurement metrics associated with the population patients to identify or otherwise determine a subset of the sensor glucose measurement metrics that are correlative to or predictive of occurrence of that medical condition's diagnostic code within the electronic medical records data 122. Similarly, for the medical condition of interest … stepwise feature selection may be performed to identify which fields or attributes of patient measurement data and medical records data are most correlative to or predictive of the amount of A1C reduction within the patient cohort. “), the one or more second covariates being different from the one or more first covariates (see e.g. para [163]-[172] – the selection can identify different fields/attributes for different rates/groups), and wherein the report further indicates the identified second covariates and a respective correlation between the identified second covariates and the second predicted rate of hypoglycemic event (see e.g. para [227] –“The reporting layer 2530 may be configured to generate multiple different types of reports, each having different information and/or showing information in different formats (arrangements or styles), where the type of report may be selectable by the user.”).
With respect to dependent claim 18, the modified Zhong teaches receiving data representing respective medical records of a plurality of second patients, each second patient having been diagnosed with diabetes mellitus (see e.g. para [161][171][178]-“receives or otherwise obtains historical observational data, medical records data, and medical claims data for a patient population from a database (tasks 1902, 1904, 1906). The adherence recommendation process 1900 calculates or otherwise determines adherence metrics for different therapy interventions or regimens based on the relationships between the historical observational data, medical records data, and medical claims data for a patient population”), and using a second type of insulin that is different from the first type of insulin (see e.g. Shvets Para [44][45] – different insulin types are disclosed); determining respective second predicted rates of hypoglycemic events for each second patient by processing the medical records of the plurality of second patient using a second machine learning model that has been trained using second training data that comprises data representing second medical records of a plurality of second training patients and corresponding rates of hypoglycemic events for the respective second training patients, wherein each of the plurality of second training patients uses the second type of insulin (see e.g. Fig. 17 Para [165]-“ obtains measurement data and medical records data for an individual patient and applies one or more risk prediction models to the patient's measurement data and medical records data to determine the patient's individual risk of experiencing the condition(s) associated with the respective risk prediction model(s) (tasks 1708, 1710, 1712). In this regard, an individual patient's sensor glucose measurement data and electronics medical records data may be periodically or continually analyzed using the risk prediction models to ascertain whether the patient's risk of a particular medical condition is above a threshold risk tolerance. In one or more exemplary embodiments” Also see e.g. Shvets Para [72]-[77] – “a long term risk prediction classification machine learning algorithm using an activation function to compute, based upon the last up to 24 hours of BG data from said first data set, the probability of hypoglycaemia occurring within a time period of up to 24 hours from start of computing the risk … a subject's pattern recognition machine learning algorithm to analyses correlations between said BG measurements and insulin dose size data of said first data set and identify historic hyper- and hypoglycemic events over a predetermined period of time and the severity as to blood glucose level of each of these events,”); and identifying, in the medical records of the plurality of second patients and based on the second predicated rates, one or more second covariates that correlate to a second predicted rate of hypoglycemic events, wherein the report further indicates the identified second covariates, and a correlation between the identified second covariates and the second predicted rate of hypoglycemic event (see e.g. para [172][217] –“stepwise feature selection may be performed to identify which fields or attributes of patient measurement data and medical records data are most correlative to or predictive of the amount of A1C reduction within the patient cohort. An uplift model for calculating the estimated A1C reduction for patients within that particular patient cohort may then be determined as a function of the correlative subset of sensor glucose measurement variables, medical record variables, and/or operating context variables. In this regard, for each of the different patient cohorts identified for different potential therapy interventions”).
With respect to dependent claim 19, the modified Zhong teaches the one or more first covariates are identified by using a linear regression model (see e.g. Para [162] and Shvets para [57]-[63]).
With respect to dependent claim 20, the modified Zhong teaches the covariates include one or more of demographics, socioeconomics, comorbidities, diabetes complications, diabetes status, medication use, gender, age range, insurance carrier, body mass index, blood pressure range, or alcohol or drug use of respective first patients (see e.g. para [171] – “ the patient cohorts may be defined by common demographic attributes (e.g., gender, income, and/or the like), common medical diagnoses, common therapy regimens or therapy types (e.g., monotherapy patients, dual therapy patients, etc.), common medications or prescriptions, and/or other medical records commonalities. For example, in addition to defining patient cohorts demographically (e.g., by age, location, race, gender, socioeconomic status, profession, etc.), patient cohorts may be characterized or defined utilizing clustering techniques to classify similar patients using other available data sets, such as, for example, mood logs, program interactions, personal goals, and/or the like, which, for example, may be tracked, monitored or logged by an application at a client device 106.”).
With respect to dependent claim 21, the modified Zhong teaches the first predicted rates include respective severities of hypoglycemic events predicted for respective patients (see e.g. Shvets para [74]-[77]).
With respect to dependent claim 22, the modified Zhong teaches the first machine learning model is further trained to cluster the first patients based on respective predicted rates and severities of hypoglycemic events across different covariates (see e.g. para [164] - “calculates or otherwise determines an equation, function, or model for calculating the probability or likelihood of the occurrence of the medical condition of interest based on that predictive subset of sensor glucose measurement variables and medical record variables.” and Shvets Fig. 18 and para [74]-[77]).
Claim 23 is rejected for the similar reason discussed above with respect to claim 16.
Claim 24 is rejected for the similar reason discussed above with respect to claim 17.
Claim 25 is rejected for the similar reason discussed above with respect to claim 18.
Claim 26 is rejected for the similar reason discussed above with respect to claim 19.
Claim 27 is rejected for the similar reason discussed above with respect to claim 20.
Claim 28 is rejected for the similar reason discussed above with respect to claim 21.
Claim 29 is rejected for the similar reason discussed above with respect to claim 22.
Claim 30 is rejected for the similar reason discussed above with respect to claim 16.
Claim 31 is rejected for the similar reason discussed above with respect to claim 17.
Claim 32 is rejected for the similar reason discussed above with respect to claim 18.
Claim 33 is rejected for the similar reason discussed above with respect to claim 19.
Claim 34 is rejected for the similar reason discussed above with respect to claim 20.
Claim 35 is rejected for the similar reason discussed above with respect to claims 21 and 22.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PEIYONG WENG whose telephone number is (571)270-1660. The examiner can normally be reached on Mon.-Fri. 8 am to 5 pm.
If attempts to reach the examiner by telephone are unsuccessful, the examiner's supervisor, Matthew Ell, can be reached on (571) 270-3264. 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://portal.uspto.gov/external/portal. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
/PEI YONG WENG/Primary Examiner, Art Unit 2141
Prosecution Insights