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 Shvets et al. (hereinafter Shvets) U.S. Patent Pub No. 2020/0227170 in view of Zhong et al. (hereinafter Zhong) U.S. Patent Pub No. 2018/0271455.
With respect to independent claim 16, Shvets teaches a method implemented by a computer system (see e.g. Para [68]-[78] – “the invention provides method for assisting a subject in treating diabetes via a computer system comprising one or more processors and a memory storing a data structure comprising”), the method comprising:
identifying, from the medical records, a type of insulin that the patient uses (see e.g. Para [17][71][107]- “ The first data set further comprises 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 type stamp of the insulin medicament injected. “ “Each record comprises a timestamp also specifying an amount of injected insulin medicament and the type of insulin injected.”);
selecting, from among a plurality of models in a machine learning system (see e.g., Para [8][44]-[48][113]-[116] - “in addition the first algorithm, a risk prediction module 140 that receives input from a plurality of separate algorithm modules. One such module is the subject's pattern recognition algorithm module 150 that is adapted to analyze the correlations between the BG measurement data and insulin injection data of the first data set 110 in order to identify historic hyper- and hypoglycemic events over a predetermined period of time and the severity as to BG level of each of these events.”), a first machine learning model that has been trained for the identified type of insulin (see e.g., Fig. 1 Para [17][71][107][44]-[48][113]-[116]),
wherein the first machine learning model is trained using training data that comprises data representing medical records of a plurality of training patients and corresponding rates of hypoglycemic events for the respective training patients (see e.g. Para [51]-[63] [113]– “During the training stage coefficients (a) are identified indicating how much influence each the individual algorithm modules of the risk prediction module impacts a dose reduction. These coefficients will be used to calculate a second dose size. The steps to identify coefficients (weights) include defining an effect factor Z being indicative of the effect the injected insulin doses from the first data set had on the blood glucose level of the subject. Z depends on the target set for the various BG levels and an example of such targets is shown in the table below. These targets are usually set by the patient's HCP and are included in the first set of data (minimum target fasting BG level (FGL2), minimum post prandial BG level (PPL2), a maximum target fasting BG level (FGH), a maximum post prandial BG level (PPH), and a hypoglycemic blood glucose alert level (FGL1/PPL1).” Training is based on historical insulin/BG data and outcomes indicating safe doses/non-hypoglycemic states.),
wherein each of the plurality of training patients uses the same type of insulin that was identified in the medical records of the patient (see e.g. Para [44]-[45][107]), and wherein each model in the machine learning system is trained for a respective type of insulin from among a plurality of types of insulins (see e.g. Para [44]-[48][107] - Shvets does not expressly show each model is based on a certain type of insulin. However, it would have been obvious to include such features because this is merely a design choice.);
determining a predicted rate of hypoglycemic events for the patient by processing the medical records of the patient using the first machine learning model (see e.g. Para [75]-[77][98] – “ A machine learning model assesses the BG measurements and produces predictive hypoglycemic warnings at e.g. 24 hours, 15 hours, 12 hours, 3 hours, 2 hours, 60 minutes, 30 minutes or 15 minutes prediction horizons.”).
Shvets does not expressly show receiving data representing medical records of a patient, the patient having been diagnosed with diabetes mellitus and comparing the predicted rate to a predetermined threshold value; and in response to determining that the predicted rate exceeds the predetermined threshold value, sending a notification to the patient or a physician. However, Shvets indicates that data related to patient with diabetes are obtained (see e.g. Para [1]-[7] – “the algorithms being based on retrospective use of historical blood glucose data, either self-monitored (SMPG) or Continuous Glucose Measuring (CGM) data, to calculate the dose recommendations. Titration algorithms are often based on ADA (American Diabetes Association) Standards of care recommendations. Patients are often under titrated due to fear of low BG levels (hypoglycemic events).”). Furthermore, Zhong teaches receiving data representing medical records of a patient, the patient having been diagnosed with diabetes mellitus (see e.g. Para [22]-[26]) and comparing the predicted rate to a predetermined threshold value (see e.g. Para [23][24][167] – “perform one or more actions when the risk score is greater than a threshold”); and in response to determining that the predicted rate exceeds the predetermined threshold value, sending a notification to the patient or a physician (see e.g. Para [23][24][167]). Both Shvets and Zhong 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 Shvets to include the above feature. The motivation to combine Shvets and Zhong comes from Zhong. Zhong discloses the motivation to monitor a threshold value so that action can be taken when threshold is met (see e.g. para [22]-[26]). This motivation for combination also applies to the remaining claims which depend on this combination.
With respect to dependent claim 17, the modified Shvets teaches determining the predicted rate of hypoglycemic events includes determining one or both of a frequency or a severity of hypoglycemic events based on the medical records of the patient (see e.g. Para [18][40][97] [98] – “said BG measurements of said data sets and corresponding insulin dose size data of said data sets and identify hyper- and hypoglycemic events within said time interval and the severity as to blood glucose level of each of these events.” “A machine learning model assesses the BG measurements and produces predictive hypoglycemic warnings at e.g. 24 hours, 15 hours, 12 hours, 3 hours, 2 hours, 60 minutes, 30 minutes or 15 minutes prediction horizons. “).
With respect to dependent claim 18, the modified Shvets teaches receiving multiple respective medical records of multiple patients, wherein at least one covariate is shared between all of the multiple medical records (see e.g. Zhong Fig. 17 and Para [161]-[164] – “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 … the patient population may be tailored for a particular demographic or combination of demographic attributes (e.g., by age, gender, income, and/or the like). “); determining a predicted rate of hypoglycemic event that corresponds to the at least one covariate by using the machine learning system on the medical records of the plurality of patients (see e.g. Zhong Para [163] [164] – “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, the server 102 may analyze the electronic medical records data for the patient population by performing stepwise feature selection to identify which fields or attributes of the patient medical records (e.g., age, gender, income, education level, smoking, A1C values or other laboratory values, insulin status or other medications or therapies, other medical conditions, and/or the like) are correlative to or predictive of occurrence of that medical condition. It should be noted that in some embodiments, operating context data for the patient population may also be analyzed to identify whether any particular operating contexts (e.g., geographic location, temperature, humidity, and/or the like) are correlative to or predictive of occurrence of a particular medical condition.”); and generating a report that identifies the at least one covariate and the determined predicted rate that corresponds to the at least one covariate (see e.g. Zhong Para [161]-[164][227][228]).
With respect to dependent claim 19, the modified Shvets teaches each patient in the multiple patients uses the same type of insulin that the patient uses (see e.g. Para [44] [45][107] – Shvets does not expressly show that the same type of insulin is used. However, it would have been obvious to include this feature because data regarding the type of insulin is already gathered and the requirement is merely a design choice. ), and wherein the predicted rate is determined by using the first machine learning model on each of the multiple medical records (see e.g. Zhong Fig. 17 Para [165]-“Still referring to FIG. 17, the illustrated risk management process 1700 receives or otherwise 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). “).
With respect to dependent claim 20, the modified Shvets teaches a first patient in the multiple patients uses a first type of insulin, and a second patient in the multiple patients uses a second type of insulin (see e.g. Para [44] [45][107]), and wherein the predicated rate is determined, at least in part, by running multiple machine learning models that each is trained for a respective one of the first and the second types of insulin (see e.g. Para [44] [45][107] - Shvets does not expressly show this feature. However, it would have been obvious to include this feature because data regarding the type of insulin is already gathered, and the requirement is merely a design choice.).
With respect to dependent claim 21, the modified Shvets 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 patients (see e.g. Para [118] and Zhong Para [72] – “ information associated with the patient (e.g., age, income, education, location, gender), past medical procedures, clinical observations or other habitual behavior information (e.g., smoking, alcohol usage, etc.), family medical history, physician notes and care plans, and/or the like.”).
With respect to dependent claim 22, the modified Shvets teaches the notification indicates that the predicted rate exceeds the predetermined threshold value (see e.g. Zhong Para [23] [24][167] –“ when the patient's risk score is greater than a notification threshold, the risk management process 1700 generates or otherwise provides a user notification that indicates the potential risk to the patient (tasks 1714, 1716). “).
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 claim 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