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 .
Status of Claims
This office action for the 18/540583 application is in response to the communications filed June 24, 2026.
Claims 1, 12 and 15 were amended June 24, 2026.
Claims 1-7 and 9-21 are currently pending and considered below.
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 1-7 and 9-21 are rejected under 35 U.S.C. 103 as being unpatentable over McElrath et al. (US 2024/0339220; herein referred to as McElrath) in view of Agrawal et al. (US 2020/0125961; herein referred to as Agrawal) in further view of Penders et al. (US 2020/0196958; herein referred to as Penders).
As per claim 1,
McElrath teaches a system for identifying a maternity severity index of a subject user:
(Paragraph [0033] of McElrath. The teaching describes methods and systems to predict adverse gestational outcomes, such as preterm birth, and to manage the care of pregnant females at increased risk for such adverse gestational outcomes)
McElrath further teaches a computing unit, the computing unit comprising an input/output unit adapted to present or formulate at least one query based at least in part on one or more of health states, socio-economic states, or behavioral states of said subject user, said at least one query being configured to elicit at least one response from said subject user; a backend server communicably connected to the computing unit via a communication medium, a data receiving component adapted to receive data-sets from one or more data sources, the received data-sets pertaining to at least one risk associated to maternity within the subject user and a constantly upgraded risk assessment database comprising at least one of a plurality of sample maternity data parameters, assessments, risk evaluations, suggested recommendations or intervention plans for treating said at least one risk from a plurality of users of different ages, demographic regions, ethnicity, psycho or social-economic, health, and biological variables:
(Paragraphs [0024], [0113] and [0118]-[0121] of McElrath. The teaching describes a controller 602 may include one or more servers and/or one or more processors running on a cloud platform (e.g., Microsoft Azure®, Amazon® web services, IBM® cloud computing, etc.). The server(s) and/or processor(s) may be any suitable processing device configured to run and/or execute a set of instructions or code, and may include one or more data processors, image processors, graphics processing units, digital signal processors, and/or central processing units. In one aspect, a method of treating a pregnant subject is described herein. The method can comprise (I) during pregnancy: inferring a gestational outcome in a pregnant subject by executing a model on a first meta-dataset that includes measures of a plurality of diagnostic features for the subject, and tracking the subject into one of three treatment tracks selected from: traditional prenatal care, prenatal care with telemedicine and enhanced at risk care based on an inference of low, average, or high risk of an adverse gestational outcome. The measures of the plurality of diagnostic features for the subject can be from one or more first datasets comprising measures of clinical data. The clinical data can comprise maternal data inputs and/or conception data inputs. Inference models as described herein can be executed on subject data to predict (e.g., estimate risk of) a gestational outcome and/or recommendations for therapeutic track/treatment track. In one embodiment, after making an inference about a state of gestational outcome, the method can comprise developing a model for therapeutic intervention in the subject. Such inferences and/or recommendations can be displayed on a webpage connected to the clickable icon. Subject can receive at an Internet connected server notification that inferences and/or recommendations for the subject are available. Data can be transmitted electronically, e.g., over the Internet. Electronic communication can be, for example, over any communications network include, for example, a high-speed transmission network including, without limitation, Digital Subscriber Line (DSL), Cable Modem, Fiber, Wireless, Satellite and, Broadband over Powerlines (BPL). After therapeutic interventions are implemented, the effect of these interventions on the subject's condition can be remeasured. Such remeasurements can be used to generate updated inferences and/or recommendations)
McElrath further teaches a maternity risk assessment module adapted to assess the at least one risk associated to said subject user, the maternity risk assessment module being configured to determine at least one of threats or a maternity severity index related to the subject user using the received data-sets, the maternity risk assessment module comprising one or more programming instruction using at least one machine learning or deep learning model configured to cause the computing unit to: determine a current risk persona of the subject user on a basis of response of the subject user to the at least one query, the received data-sets, and the sample maternity data parameters, the risk persona being categorized in a form of one or more risk-based clusters, the one or more risk-based clusters having a pre-pregnancy risk cluster and a pregnancy risk cluster, calculate a series of predicted maternity risk realizations for a predetermined future time span by at least partially correlating the response of the subject user to the query with the sample maternity data parameters, generate a risk report for the predetermined time period, the report at least determining a risk possibility of at least one of a preterm birth or a cesarean delivery at a point of a birth time, and generate an intervention strategy adapted to reduce a possibility of maternity risk realizations:
(Paragraphs [0104] and [0119]-[0121] of McElrath. The teaching describes inference models as described herein can be executed on subject data to predict (e.g., estimate risk of) a gestational outcome and/or recommendations for therapeutic track/treatment track. In one embodiment, after making an inference about a state of gestational outcome, the method can comprise developing a model for therapeutic intervention in the subject. The model can comprise, for example, a treatment track for the subject, or pharmaceutical compositions to administer to the subject to treat the condition. Such a model can be communicated to the subject, for example, transmitting the model and, optionally, the diagnosis, to a user interface of a personal computing device of the subject. Inferences on a subject's state and/or recommendations for therapeutic intervention can be provided to subjects through an Internet website. A website can be provided which can be accessed by a subject, e.g. a customer, through a password-protected portal. The website can include a clickable icon. Upon clicking the icon, the subject can receive personalized food recommendations. Such inferences and/or recommendations can be displayed on a webpage connected to the clickable icon. Subject can receive at an Internet connected server notification that inferences and/or recommendations for the subject are available. Predictions made using the models described herein can be used to guide treatment of subjects. For example, based on the predicted risk level for an adverse gestational outcome, Individual subjects can be placed on different treatment tracks. The tracks can include, low risk (normal), medium risk and high risk for a particular adverse gestational outcome, such as preterm birth.)
McElrath does not explicitly teach wherein the machine or deep learning model is configured to: partition the received data-sets into at least one of a training dataset or a testing dataset; run a first selected learning model on the training dataset; select and tune at least a second selected model based on the result of the first selected model running on the training dataset, to thereby establish an error percentage; use the error percentage to apply a cross validation for learning model stability; and dynamically select a model argument for each run of a learning model.
However, Agrawal teaches wherein the machine or deep learning model is configured to: partition the received data-sets into at least one of a training dataset or a testing dataset; run a first selected learning model on the training dataset; select and tune at least a second selected model based on the result of the first selected model running on the training dataset, to thereby establish an error percentage; use the error percentage to apply a cross validation for learning model stability; and dynamically select a model argument for each run of a learning model, wherein the machine or deep learning model continuously evaluates by incorporating assessment results in to the sample data, thereby reducing the error percentage in subsequent runs:
(Paragraphs [0017]-[0023], [0033] and [0034] of Agrawal. The teaching describes applying a machine learning algorithm on a training data set, for which outcome(s) are known, with initialized parameters which values are modified in each training iteration to more accurately yield the known outcome(s) (referred herein as “label(s)”). Based on such application(s), the techniques generate a machine learning model with known parameters. Thus, a machine learning model includes a model data representation or model artifact. Accordingly, the term “machine learning algorithm” (or simply “algorithm”) refers herein to a process or set of rules to be followed in calculations in which model artifact, comprising one or more parameters for the calculations, is unknown, while, the term “machine learning model” (or simply “model”) refers herein to the process or set of rules to be followed in the calculations in which the model artifact, comprising the one or more parameters, is known and have been derived based on the training of the respective machine learning algorithm using one or more training data sets. Once trained, the input is applied to the machine learning model to make a prediction, which may also be referred to herein as a predicted outcome or output. In an embodiment, the supervised training algorithm is an iterative procedure. In each iteration, the machine learning algorithm applies the model artifact and the input to generate a predicted output. An error or variance between the predicted output and the known output is calculated using an objective function. With distinct sets of hyper-parameters values selected based on one or more of these techniques, each machine learning algorithm variant is trained on a training data set. A test data set is used as an input to the trained model for calculating the predicted result values. The predicted result values are compared with the corresponding label values to determine the performance score. The performance score may be computed based on calculating the error rate of predicted results in relation to the corresponding labels. For example, in a categorical domain if out of 10,000 inputs to the model only 9,000 matched the labels for the inputs, then the performance score is computed to be 90%. The term “trial” refers herein to the training of a machine learning algorithm using a distinct set of hyper-parameter values and testing the machine learning algorithm using at least one test data set. In an embodiment, cross-validation techniques, such as k-fold cross-validation, is used to create many pairs of training and test datasets from an original training data set. Each pair of data sets, together, contains the original training data set but the pairs partition the original data set in different ways between a training data set and a test data set. For each pair of data sets, the training data set is used to train a model based on the selected set of hyperparameters, and the corresponding test data set is used for calculating the predicted result values with the trained model. Based on inputting the test data set to the trained machine learning model, the performance score for the pair (or fold) is calculated. If there are more than one pairs (i.e., fold), then the performance scores are statistically aggregated (e.g., average, mean, min, max) to yield a final performance score for the variant of the machine learning algorithm. In an embodiment, to iteratively train an algorithm to generate a trained model, a training data set may be arranged such that each row of the data set is input to a machine learning algorithm and further stores the corresponding actual outcome, label value, for the row. For example, each row of the adult income data set represents a particular adult for whom the outcome is known, such as whether the adult has a gross income over $500,000. Each column of the adult training dataset contains numerical representations of a particular adult characteristic (e.g. whether an adult has a college degree, age of an adult . . . ) based on which the algorithm when trained can accurately predict whether any adult (even one who has not been described by the training data set) has a gross income over $500,000. At each training iteration, based on calculated one or more predicted values, the corresponding loss values for the iteration is calculated. For the next training iteration, one or more parameters are modified to reduce the loss based on the current loss. Any number of iterations on a training data sets may be performed to reduce the loss. The training iterations using a training data set may be stopped when the change in the losses between the iterations is within a threshold. In other words, the iterations are stopped when the loss for different iterations is substantially the same.)
It would have been obvious to one of ordinary skill in the art before the time of filing to add to the machine learning models of McElrath, the hyperparameter tuning of machine learning models of Agrawal. Paragraph [0064] of Agrawal teaches that the disclosed methods of training and tuning the machine learning models result in improved computation costs and better efficiency. One of ordinary skill in the art would have added to the teaching of McElrath, the teaching of Agrawal based on this incentive without yielding unexpected results.
The combined teaching of McElrath and Agrawal would have then taught wherein the machine or deep learning model continuously evaluates an effectiveness of the intervention strategy and reduces predicted maternity risk realizations by incorporating assessment results from subject users into the sample maternity data parameters, thereby reducing the error percentage in subsequent maternity risk realizations.
(Paragraphs [0104] and [0119]-[0121] of McElrath and Paragraphs [0017]-[0023], [0033] and [0034] of Agrawal.)
The combined teaching of McElrath and Agrawal does not explicitly teach wherein the computing unit further comprises one or more data sensors configured to capture at least one biological parameter of the subject user.
However, Penders teaches a machine learning-based pregnancy risk predictor which further comprises one or more data sensors configured to capture at least one biological parameter of the subject user:
(Paragraphs [0011], [0014] and [0159]-[0161] of Penders. The teaching describes aspects include a system for uterine activity monitoring, the system including: a plurality of sensors coupled to a belly region of a pregnant female; a processor communicatively coupled to the plurality of sensors; and a computer-readable medium having non-transitory, processor-executable instructions stored thereon, wherein execution of the instructions causes the processor to perform a method including: acquiring a plurality of signals from the plurality of sensors during uterine activity, processing the plurality of signals to extract a plurality of uterine electrical activity characteristics, analyzing the plurality of uterine electrical activity characteristics, and classifying the uterine activity as one of: a preterm labor contraction, a labor contraction, a Braxton-Hicks contraction, and a state of no contraction, based at least in part on the plurality of uterine electrical activity characteristics. In some embodiments, analyzing the plurality of uterine electrical activity characteristics is performed using machine learning techniques. Current systems and methods may monitor a subset of these known risk factors but are unable to monitor all of these risk factors consistently and over time. Further, additional risk factors that are less well characterized or that can be extrapolated from population data are currently not part of the monitoring process. Thus, there exists a need for systems and methods for monitoring pre-term birth risk over time, for example pre-conception and throughout pregnancy. A promising noninvasive marker of labor and pre-term labor is the electrical activity of the uterus, or electrohysterogram (EHG). EHG is a very promising tool for different applications, from per-term prediction to contraction and labor detection. One of the earliest signs of labor is a change in uterine activity, typically reflected as an increase in frequency and regularity of uterine contractions. Recent developments in wearable sensor technology, as well as signal processing and machine learning have made it possible to detect changes in uterine activity and contractions non-invasively. Analysis of the electrical activity of the uterus, or electrohystergraphy (EHG), reflects the source of the contractions.)
It would have obvious to one of ordinary skill in the art before the time of filing to add to pregnancy risk prediction teachings of the combined teaching of McElrath and Agrawal, the pregnancy risk prediction teachings of Penders. Paragraph [0157] of Penders teaches that the disclosed methods provide improving health outcomes for the mother and child involved in the pregnancy. One of ordinary skill in the art would have added to the combined teaching of McElrath and Agrawal, the teaching of Penders based on this incentive without yielding unexpected results.
As per claim 2,
The combined teaching of McElrath, Agrawal and Penders teaches the limitations of claim 1.
McElrath further teaches further comprising a visualization generation component comprising a user interface graphically depicting the at least one risk or the at least one threat onto an interactive dashboard:
(Paragraph [0120] of McElrath. The teaching describes that information regarding the pregnancy risk can be provided to subjects through an Internet website. A website can be provided which can be accessed by a subject, e.g. a customer, through a password-protected portal. The website can include a clickable icon. Upon clicking the icon, the subject can receive personalized food recommendations. This constitutes a GUI that depicts risk (results via the icon) on an interactive dashboard (clickable interface with the website))
As per claim 3,
The combined teaching of McElrath, Agrawal and Penders teaches the limitations of claim 1.
McElrath further teaches further comprising a data sharing component adapted to share the risk report with external systems via an application programming interface (API):
(Paragraph [0116] of McElrath. The teaching describes that the output of the longitudinal model(s) may be accessible to health care providers via an application software 608 executable on a computing device. Some non-limiting examples of the computing device include computers (e.g., desktops, personal computers, laptops etc.), tablets and e-readers (e.g., Apple iPad®, Samsung Galaxy® Tab, Microsoft Surface®, Amazon Kindle®, etc.), mobile devices and smart phones (e.g., Apple iPhone®, Samsung Galaxy®, Google Pixel®, etc.), etc. In some variations, the application software 608 (e.g., web apps, desktop apps, mobile apps, etc.) may be pre-installed on the computing device. Alternatively, the application software 608 may be rendered on the computing device in any suitable way. For example, in some variations, the application software 608 (e.g., web apps, desktop apps, mobile apps, etc.) may be downloaded on the computing device from a digital distribution platform such as an app store or application store (e.g., Chrome® web store, Apple® web store, etc.). Additionally or alternatively, the computing device may render a web browser (e.g., Google®, Mozilla®, Safari®, Internet Explorer®, etc.) on the computing device. The web browser may include browser extensions, browser plug-ins, etc. that may render the application software 608 on the computing device. In yet another alternative variation, the browser extensions, browser plug-ins, etc. may include installation instructions to install the application software 608 on the computing device. These features are construed to include an API)
As per claim 4,
The combined teaching of McElrath, Agrawal and Penders teaches the limitations of claim 1.
McElrath further teaches wherein the received data-sets comprise maternity related data selected from one or more of insurance claims data, medication data, or behavioral data:
(Paragraph [0025] of McElrath. The teaching describes enhanced at-risk care can comprise one or more of: 1. Referral to Preterm Birth Prevention Clinic, 2. Referral to Maternal Fetal Medicine specialist, 3. Education on signs/symptoms of preterm labor, 4. Evaluation of medical (i.e. progestogen supplementation, low-dose aspirin) or surgical (i.e. cervical cerclage) options, 5. Modification of behaviors, lifestyle and diet to support a healthy birth outcome, 6. Increased office visits and modified content of office visits, 7. Increased surveillance via ultrasound and cervical length measurements, and 8. Preparation for acute-stage events (i.e. planning for NICU access, education on medicines that can be given upon initiation of preterm labor to extend gestation, mature the baby's lungs, and provide neuroprotective agents for the baby's brain development))
As per claim 5,
The combined teaching of McElrath, Agrawal and Penders teaches the limitations of claim 1.
McElrath further teaches wherein the risk assessment module comprises a plurality of sub-modules, each catering to a different perspective related to the maternity within the subject user:
(Paragraph [0025] of McElrath. The teaching describes enhanced at-risk care can comprise one or more of: 1. Referral to Preterm Birth Prevention Clinic, 2. Referral to Maternal Fetal Medicine specialist, 3. Education on signs/symptoms of preterm labor, 4. Evaluation of medical (i.e. progestogen supplementation, low-dose aspirin) or surgical (i.e. cervical cerclage) options, 5. Modification of behaviors, lifestyle and diet to support a healthy birth outcome, 6. Increased office visits and modified content of office visits, 7. Increased surveillance via ultrasound and cervical length measurements, and 8. Preparation for acute-stage events (i.e. planning for NICU access, education on medicines that can be given upon initiation of preterm labor to extend gestation, mature the baby's lungs, and provide neuroprotective agents for the baby's brain development))
As per claim 6,
The combined teaching of McElrath, Agrawal and Penders teaches the limitations of claim 1.
McElrath further teaches wherein the step of determining the current risk persona comprises a data correlation to draw a relation between user submitted data, the received data-sets from the one or more data sources and a maternity sample database:
(Paragraph [0032] of McElrath. The teaching describes a method for creating a model that infers a gestational outcome in a subject in post-conception is described herein. The method can comprise: a) receiving into a database a plurality of datasets comprising data on each of a plurality of subjects, wherein the datasets include: i) a dataset comprising measures of pre-pregnancy maternal data, and ii) a dataset comprising measures of conception status data, and wherein each dataset includes a gestational outcome identifier for each subject. The method can also comprise b) performing, an analysis on each of the datasets by the controller. The analyses identify one or a plurality of dataset features that infer a gestational outcome in subject from each dataset. The method can also comprise c) receiving into a database a meta-dataset that includes, for each subject, measures of a plurality of the identified features from each of the datasets and the gestational outcome identifier, and d) performing, by the controller, an analysis on the meta-dataset. The analysis produces a model that infers a gestational outcome for a subject from the identified features.)
As per claim 7,
The combined teaching of McElrath, Agrawal and Penders teaches the limitations of claim 1.
McElrath further teaches wherein the subject user is in a state of maternity selected from at least one of: pre-maternity, first trimester, a second trimester, a third trimester, a post pregnancy period:
(Paragraph [0034] of McElrath. The teaching describes technology disclosed herein can predict the risk levels with improved accuracy over existing technology. For instance, the area under the receiver operating characteristic curve shows an improvement of at least 20 points over existing methodologies. Additionally, the technology described herein incorporates data into a diagnostic model (described below) in a manner such that the computational time to predict the risk levels is reduced. For example, rather than incorporating the entire first trimester microparticle data and the entire second trimester microparticle data at the second trimester point, the technology described herein incorporates a difference between the first trimester data and the second trimester data into the diagnostic model, thereby cutting down on execution time and/or runtime. Furthermore, the adaptive nature of the diagnostic model may improve prediction with each subsequent time point.)
As per claim 9,
The combined teaching of McElrath, Agrawal and Penders teaches the limitations of claim 1.
McElrath further teaches wherein the one or more risk-based clusters comprise one or more categories defined in accordance with a severity level thereof:
(Paragraph [0033] of McElrath. The teaching describes treatment tracks can be tiered based on risk levels, such as “low risk,” “moderate risk,” and “high risk.”)
As per claim 10,
The combined teaching of McElrath, Agrawal and Penders teaches the limitations of claim 1.
McElrath further teaches wherein the intervention strategy comprises a plurality of: recommendations, lifestyle plans, or therapy plans suitable for the subject user based on the risk predicted by the risk assessment module:
(Paragraphs [0025] and [0120] and of McElrath. The teaching describes that information regarding the pregnancy risk can be provided to subjects through an Internet website. A website can be provided which can be accessed by a subject, e.g. a customer, through a password-protected portal. The website can include a clickable icon. Upon clicking the icon, the subject can receive personalized food recommendations. The teaching describes enhanced at-risk care can comprise one or more of: 1. Referral to Preterm Birth Prevention Clinic, 2. Referral to Maternal Fetal Medicine specialist, 3. Education on signs/symptoms of preterm labor, 4. Evaluation of medical (i.e. progestogen supplementation, low-dose aspirin) or surgical (i.e. cervical cerclage) options, 5. Modification of behaviors, lifestyle and diet to support a healthy birth outcome, 6. Increased office visits and modified content of office visits, 7. Increased surveillance via ultrasound and cervical length measurements, and 8. Preparation for acute-stage events (i.e. planning for NICU access, education on medicines that can be given upon initiation of preterm labor to extend gestation, mature the baby's lungs, and provide neuroprotective agents for the baby's brain development)
As per claim 11,
The combined teaching of McElrath, Agrawal and Penders teaches the limitations of claim 6.
McElrath further teaches wherein the programming instructions are further configured to assess an assessment result of said intervention strategy onto the subject, wherein said assessment result is added to the sample maternity database:
(Paragraphs [0120] and [0121] of McElrath. The teaching describes inferences on a subject's state and/or recommendations for therapeutic intervention can be provided to subjects through an Internet website. A website can be provided which can be accessed by a subject, e.g. a customer, through a password-protected portal. The website can include a clickable icon. Upon clicking the icon, the subject can receive personalized food recommendations. Such inferences and/or recommendations can be displayed on a webpage connected to the clickable icon. Subject can receive at an Internet connected server notification that inferences and/or recommendations for the subject are available. After therapeutic interventions are implemented, the effect of these interventions on the subject's condition can be remeasured. Such remeasurements can be used to generate updated inferences and/or recommendations as described herein.)
As per claim 12,
The combined teaching of McElrath, Agrawal and Penders teaches the limitations of claim 1.
McElrath further teaches wherein the programming instructions are based on a learning model selected from are one or more of: a natural language processing (NLP) model, a deep learning algorithm model, or a statistical model:
(Paragraph [0076] of McElrath. The teaching describes that the term “analysis” refers to any algorithm that transforms inputs into outputs. Analyses include, without limitation, statistical analyses, machine learning analyses and neural net analyses. The term “data” may include data received from various data sources, metadata associated with the data, and/or a combination of both data and metadata.)
As per claim 13,
The combined teaching of McElrath, Agrawal and Penders teaches the limitations of claim 11.
McElrath further teaches wherein the programming instructions are improvised or trained with the assessment result from the subject user and/or from the plurality of users:
(Paragraphs [0120] and [0121] of McElrath. The teaching describes inferences on a subject's state and/or recommendations for therapeutic intervention can be provided to subjects through an Internet website. A website can be provided which can be accessed by a subject, e.g. a customer, through a password-protected portal. The website can include a clickable icon. Upon clicking the icon, the subject can receive personalized food recommendations. Such inferences and/or recommendations can be displayed on a webpage connected to the clickable icon. Subject can receive at an Internet connected server notification that inferences and/or recommendations for the subject are available. After therapeutic interventions are implemented, the effect of these interventions on the subject's condition can be remeasured. Such remeasurements can be used to generate updated inferences and/or recommendations as described herein.)
As per claim 14,
The combined teaching of McElrath, Agrawal and Penders teaches the limitations of claim 1.
McElrath further teaches wherein the computing unit comprises a mobile, touch-based computing hardware selected from at least one of: a smart phone or a tablet:
(Paragraph [0116] of McElrath. The teaching describes that the output of the longitudinal model(s) may be accessible to health care providers via an application software 608 executable on a computing device. Some non-limiting examples of the computing device include computers (e.g., desktops, personal computers, laptops etc.), tablets and e-readers (e.g., Apple iPad®, Samsung Galaxy® Tab, Microsoft Surface®, Amazon Kindle®, etc.), mobile devices and smart phones (e.g., Apple iPhone®, Samsung Galaxy®, Google Pixel®, etc.), etc. In some variations, the application software 608 (e.g., web apps, desktop apps, mobile apps, etc.) may be pre-installed on the computing device. Alternatively, the application software 608 may be rendered on the computing device in any suitable way. For example, in some variations, the application software 608 (e.g., web apps, desktop apps, mobile apps, etc.) may be downloaded on the computing device from a digital distribution platform such as an app store or application store (e.g., Chrome® web store, Apple® web store, etc.). Additionally or alternatively, the computing device may render a web browser (e.g., Google®, Mozilla®, Safari®, Internet Explorer®, etc.) on the computing device. The web browser may include browser extensions, browser plug-ins, etc. that may render the application software 608 on the computing device. In yet another alternative variation, the browser extensions, browser plug-ins, etc. may include installation instructions to install the application software 608 on the computing device.)
As per claim 15,
Claim 15 is substantially similar to claim 1. Accordingly, claim 15 is rejected for the same reasons as claim 1.
The combined teaching of McElrath and Agrawal does not explicitly teach a second set of parameters comprising one or more medical utilization patterns of the subject user to correlate with patient outcome, wherein the one or more medical utilization patterns comprise preventative care visits, medication usage, and office visit patterns.
However, Penders teaches a machine learning-based pregnancy risk predictor which further comprises one or more data sensors configured to capture at least one biological parameter of the subject user which incorporate parameters comprising one or more medical utilization patterns of the subject user to correlate with patient outcome, wherein the one or more medical utilization patterns comprise preventative care visits, medication usage, and office visit patterns:
(Paragraphs [0011], [0014], [0159]-[0161] and [0254] of Penders. The teaching describes aspects include a system for uterine activity monitoring, the system including: a plurality of sensors coupled to a belly region of a pregnant female; a processor communicatively coupled to the plurality of sensors; and a computer-readable medium having non-transitory, processor-executable instructions stored thereon, wherein execution of the instructions causes the processor to perform a method including: acquiring a plurality of signals from the plurality of sensors during uterine activity, processing the plurality of signals to extract a plurality of uterine electrical activity characteristics, analyzing the plurality of uterine electrical activity characteristics, and classifying the uterine activity as one of: a preterm labor contraction, a labor contraction, a Braxton-Hicks contraction, and a state of no contraction, based at least in part on the plurality of uterine electrical activity characteristics. In some embodiments, analyzing the plurality of uterine electrical activity characteristics is performed using machine learning techniques. Current systems and methods may monitor a subset of these known risk factors but are unable to monitor all of these risk factors consistently and over time. Further, additional risk factors that are less well characterized or that can be extrapolated from population data are currently not part of the monitoring process. Thus, there exists a need for systems and methods for monitoring pre-term birth risk over time, for example pre-conception and throughout pregnancy. A promising noninvasive marker of labor and pre-term labor is the electrical activity of the uterus, or electrohysterogram (EHG). EHG is a very promising tool for different applications, from per-term prediction to contraction and labor detection. One of the earliest signs of labor is a change in uterine activity, typically reflected as an increase in frequency and regularity of uterine contractions. Recent developments in wearable sensor technology, as well as signal processing and machine learning have made it possible to detect changes in uterine activity and contractions non-invasively. Analysis of the electrical activity of the uterus, or electrohystergraphy (EHG), reflects the source of the contractions. In some embodiments, the method 500 includes: comparing the instant pre-term birth risk score to a baseline pre-term birth risk score; and when the instant pre-term birth risk score differs from the baseline pre-term birth risk score, updating the baseline pre-term birth risk score with the instant pre-term birth risk score. In such embodiments, the system provides the user, for example pregnant female or healthcare provider, with an accurate, up-to-date pre-term birth risk score. As such, the pregnant female may make changes to her lifestyle, eating habits, exercise schedule, or other habits or activities to positively affect or at least maintain her pre-term birth risk score. Further, the healthcare provider may make changes to a therapy or medication regimen, a consultation or office visit schedule, or other recommendations to encourage the pregnant female to positively affect or at least maintain her pre-term birth risk score. By changing the medication regimen, it suggests that the medication usage was a relevant factor in determining the risk score generated by the machine learning model.)
It would have obvious to one of ordinary skill in the art before the time of filing to add to pregnancy risk prediction teachings of the combined teaching of McElrath and Agrawal, the pregnancy risk prediction teachings of Penders. Paragraph [0157] of Penders teaches that the disclosed methods provide improving health outcomes for the mother and child involved in the pregnancy. One of ordinary skill in the art would have added to the combined teaching of McElrath and Agrawal, the teaching of Penders based on this incentive without yielding unexpected results.
As per claim 16,
Claim 16 is substantially similar to claim 6. Accordingly, claim 16 is rejected for the same reasons as claim 6.
As per claim 17,
Claim 17 is substantially similar to claim 11. Accordingly, claim 17 is rejected for the same reasons as claim 11.
As per claim 18,
Claim 18 is substantially similar to claim 13. Accordingly, claim 18 is rejected for the same reasons as claim 13.
As per claim 19,
Claim 19 is substantially similar to claim 12. Accordingly, claim 19 is rejected for the same reasons as claim 12.
As per claim 20,
The combined teaching of McElrath, Agrawal and Penders teaches the limitations of claim 1.
Penders further teaches wherein the received data-sets further comprise: a first set of parameters comprising at least one risk associated to maternity within the subject user, and a second set of parameters comprising one or more medical utilization patterns of the subject user to correlate with patient outcome, wherein the one or more medical utilization patterns comprise preventative care visits, medication usage, and office visit patterns:
(Paragraphs [0011], [0014], [0159]-[0161] and [0254] of Penders. The teaching describes aspects include a system for uterine activity monitoring, the system including: a plurality of sensors coupled to a belly region of a pregnant female; a processor communicatively coupled to the plurality of sensors; and a computer-readable medium having non-transitory, processor-executable instructions stored thereon, wherein execution of the instructions causes the processor to perform a method including: acquiring a plurality of signals from the plurality of sensors during uterine activity, processing the plurality of signals to extract a plurality of uterine electrical activity characteristics, analyzing the plurality of uterine electrical activity characteristics, and classifying the uterine activity as one of: a preterm labor contraction, a labor contraction, a Braxton-Hicks contraction, and a state of no contraction, based at least in part on the plurality of uterine electrical activity characteristics. In some embodiments, analyzing the plurality of uterine electrical activity characteristics is performed using machine learning techniques. Current systems and methods may monitor a subset of these known risk factors but are unable to monitor all of these risk factors consistently and over time. Further, additional risk factors that are less well characterized or that can be extrapolated from population data are currently not part of the monitoring process. Thus, there exists a need for systems and methods for monitoring pre-term birth risk over time, for example pre-conception and throughout pregnancy. A promising noninvasive marker of labor and pre-term labor is the electrical activity of the uterus, or electrohysterogram (EHG). EHG is a very promising tool for different applications, from per-term prediction to contraction and labor detection. One of the earliest signs of labor is a change in uterine activity, typically reflected as an increase in frequency and regularity of uterine contractions. Recent developments in wearable sensor technology, as well as signal processing and machine learning have made it possible to detect changes in uterine activity and contractions non-invasively. Analysis of the electrical activity of the uterus, or electrohystergraphy (EHG), reflects the source of the contractions. In some embodiments, the method 500 includes: comparing the instant pre-term birth risk score to a baseline pre-term birth risk score; and when the instant pre-term birth risk score differs from the baseline pre-term birth risk score, updating the baseline pre-term birth risk score with the instant pre-term birth risk score. In such embodiments, the system provides the user, for example pregnant female or healthcare provider, with an accurate, up-to-date pre-term birth risk score. As such, the pregnant female may make changes to her lifestyle, eating habits, exercise schedule, or other habits or activities to positively affect or at least maintain her pre-term birth risk score. Further, the healthcare provider may make changes to a therapy or medication regimen, a consultation or office visit schedule, or other recommendations to encourage the pregnant female to positively affect or at least maintain her pre-term birth risk score. By changing the medication regimen, it suggests that the medication usage was a relevant factor in determining the risk score generated by the machine learning model.)
As per claim 21,
The combined teaching of McElrath, Agrawal and Penders teaches the limitations of claim 15.
Penders further teaches wherein the computing unit further comprises one or more data sensors configured to capture at least one biological parameter of the subject user:
(Paragraphs [0011], [0014], [0159]-[0161] and [0254] of Penders. The teaching describes aspects include a system for uterine activity monitoring, the system including: a plurality of sensors coupled to a belly region of a pregnant female; a processor communicatively coupled to the plurality of sensors; and a computer-readable medium having non-transitory, processor-executable instructions stored thereon, wherein execution of the instructions causes the processor to perform a method including: acquiring a plurality of signals from the plurality of sensors during uterine activity, processing the plurality of signals to extract a plurality of uterine electrical activity characteristics, analyzing the plurality of uterine electrical activity characteristics, and classifying the uterine activity as one of: a preterm labor contraction, a labor contraction, a Braxton-Hicks contraction, and a state of no contraction, based at least in part on the plurality of uterine electrical activity characteristics. In some embodiments, analyzing the plurality of uterine electrical activity characteristics is performed using machine learning techniques. Current systems and methods may monitor a subset of these known risk factors but are unable to monitor all of these risk factors consistently and over time. Further, additional risk factors that are less well characterized or that can be extrapolated from population data are currently not part of the monitoring process. Thus, there exists a need for systems and methods for monitoring pre-term birth risk over time, for example pre-conception and throughout pregnancy. A promising noninvasive marker of labor and pre-term labor is the electrical activity of the uterus, or electrohysterogram (EHG). EHG is a very promising tool for different applications, from per-term prediction to contraction and labor detection. One of the earliest signs of labor is a change in uterine activity, typically reflected as an increase in frequency and regularity of uterine contractions. Recent developments in wearable sensor technology, as well as signal processing and machine learning have made it possible to detect changes in uterine activity and contractions non-invasively. Analysis of the electrical activity of the uterus, or electrohystergraphy (EHG), reflects the source of the contractions. In some embodiments, the method 500 includes: comparing the instant pre-term birth risk score to a baseline pre-term birth risk score; and when the instant pre-term birth risk score differs from the baseline pre-term birth risk score, updating the baseline pre-term birth risk score with the instant pre-term birth risk score. In such embodiments, the system provides the user, for example pregnant female or healthcare provider, with an accurate, up-to-date pre-term birth risk score. As such, the pregnant female may make changes to her lifestyle, eating habits, exercise schedule, or other habits or activities to positively affect or at least maintain her pre-term birth risk score. Further, the healthcare provider may make changes to a therapy or medication regimen, a consultation or office visit schedule, or other recommendations to encourage the pregnant female to positively affect or at least maintain her pre-term birth risk score. By changing the medication regimen, it suggests that the medication usage was a relevant factor in determining the risk score generated by the machine learning model.)
Response to Arguments
Applicant's arguments filed June 24, 2026 have been fully considered.
Applicant’s arguments pertaining to rejections made under 35 U.S.C. 101 are persuasive.
The Applicant argues that the continuously updated risk assessment database provides a practical application to any alleged abstract idea because the datasets produced by incorporating user feedback data make the model more accurate as it is used with the particular subject. The Examiner agrees. As the claimed model is iteratively trained with subject users, the dataset that is updated would have produced a specialized form of data that would not have arisen from any other circumstance other than in the manner claimed. This fundamentally provides basis to conclude that data would become more accurate and specific to the subject user’s usage of the claimed invention. Accordingly, the Examiner withdraws these rejections.
Applicant’s arguments pertaining to rejections made under 35 U.S.C. 103 are not persuasive.
The Applicant argues that the prior art does not teach a “pre-pregnancy risk cluster” in addition to the pregnancy risk cluster disclosed by McElrath. McElrath only teaches the one option when the pending claims require both types of clusters.
The Examiner respectfully disagrees. The limitation in question is “the risk persona being categorized in a form of one or more risk-based clusters, the one or more risk-based clusters having a pre-pregnancy risk cluster and a pregnancy risk cluster”. This limitation does not require both “pre-pregnancy risk cluster and a pregnancy risk cluster”, rather it requires “one or more risk-based clusters”. Since the Applicant readily admits and correctly recognizes that McElrath discloses a pregnancy risk cluster classification of data, this element satisfies the “one” of the “one or more risk-based clusters” required by the pending claims. The Applicant has argued for features that are not claimed.
The Applicant further argues that McElrath does not disclose the continuously updated machine or deep learning models.
The Examiner respectfully disagrees. The Examiner does not rely on McElrath to teach this argued limitation but rather on the combined teaching of McElrath and Agrawal. The Applicant has merely relied on piecemeal analysis to criticize a reference for which it was not relied on to teach. Accordingly, this argument is not persuasive.
The Applicant further argues that McElrath does not teach the risk persona clustering claimed because McElrath does not teach the specific ML-Driven clustering mechanism. Predictive modeling is not the same as clustering a subject’s risk persona as claimed.
The Examiner respectfully disagrees for the foregoing reasons. Furthermore, the Applicant has presented a distinction without a difference. There is no functional difference between the risk profiling in McElrath and the claimed risk persona. The only difference between these two things appears to only be semantic as the Applicant has failed to clarify how the two are dissimilar functionally.
The Applicant further argues that there is no cited reason as to why one of ordinary skill in the art would have combined McElrath and Agrawal.
The Examiner respectfully disagrees. The Examiner had explicitly provided reasoning in the rejection above. Please refer to the above.
Applicant’s remaining arguments pertaining to rejections made under 35 U.S.C. 103 are rendered moot in light of the foregoing.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHAD A NEWTON whose telephone number is (313)446-6604. The examiner can normally be reached M-F 8:00AM-4:00PM (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, PETER H. CHOI can be reached at (469) 295-9171. 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.
/CHAD A NEWTON/Primary Examiner, Art Unit 3681
Prosecution Insights