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
Claims 1-20 were previously pending and subject to a non-final Office Action having a notification date of March 12, 2026 (“non-final Office Action”). Following the non-final Office Action, Applicant filed an amendment on June 9, 2026 (the “Amendment”), amending claims 1-6, 8, and 10-20.
The present Final Office Action addresses pending claims 1-20 in the Amendment.
Response to Arguments
Response to Applicant’s Arguments Regarding Claim Interpretation Under 35 USC §112(f)
On pages 11-13 of the Amendment, Applicant repeatedly asserts that "training component," "alert component," and "output component" do not invoke 35 112(f) because they are recited in connection with sufficient structure (processor-executed computational components within a defined AI-based monitoring architecture). The Examiner disagrees. While the cardiotocograph pattern ID model, maternal health analysis model, and multistage AI model are recited in claim 1 as being processor-executed computational components, the "training component," "alert component," and "output component" are just recited as being part of the system in general in claims 6, 8, and 9. Therefore, these claim terms continue to invoke 35 USC 112(f). If Applicant desires for these terms to not invoke 35 USC 112(f), then Applicant is recommended to amend claims 6, 8, and 9 to recite how the "computer-processor executable components" further include a "training component," "alert component," and "output component" or similar language.
Response to Applicant’s Arguments Regarding Claim Rejections Under 35 USC §101
Starting on page 13 of the Amendment, Applicant asserts that the Office Action has characterized the claims at an "impermissibly high level of abstraction divorced from the actual claim language" in determining that the claims are directed to an abstract idea. The Examiner disagrees and refers Applicant's attention to the rejection below whereby the Examiner has underlined the exact limitations reciting an abstract idea and provided a detailed explanation regarding why such limitations recite an abstract idea.
On page 14 of the Amendment, Applicant asserts that training the cardiotocograph pattern ID model using annotated CTG data associated with monitored labor/delivery cases and corresponding clinical outcomes cannot be mentally performed by a physician reviewing fetal monitoring plots. While the Examiner agrees, the Examiner nevertheless asserts that this limitation amounts to merely reciting the idea of a solution or outcome without reciting details of how a solution to a problem is accomplished which is equivalent to the words “apply it” (see MPEP § 2106.05(f)). For instance, as the CTG pattern identification model is already configured to perform the (mental process of) receiving the CTG data and generating CTG analysis data such as FHR accelerations/decelerations, etc., then specifying that the model is trained based on annotated CTG data patterns and corresponding clinical outcomes does not recite any specific details regarding how the training is accomplished. Claims that do no more than apply established methods of machine learning to a new data environment are not patent eligible. Recentive Analytics, Inc. v. Fox Corp., Fox Broadcasting Company, LLC, Fox Sports Productions, LLC, Case No. 23-2437, (Fed. Cir. 2025), pp. 10, 14. An abstract idea does not become nonabstract by limiting the invention to a particular field of use or technological environment. Id. Requirements that the machine learning model be “iteratively trained” or dynamically adjusted do not represent a technological improvement because iterative training using selected training material and dynamic adjustments based on real-time changes are incident to the very nature of machine learning. Id., p. 12. “[T]he way machine learning works is the inputs are defined, the model is trained, and then the algorithm is actually updated and improved over time based on the input.” Id.
Applicant also asserts that dynamically updating the labor-and-delivery predictions during monitoring based on changes in the streaming cardiotocograph waveform data and maternal health analysis data cannot be mentally performed by a physician reviewing fetal monitoring plots. The Examiner disagrees. For instance, in the case where the medical professional observes an increased change in the number of late FHR decelerations on a screen in combination with an increase in maternal temperature on a screen, the medical professional could, based on their experience, guidelines, etc., dynamically update a previous prediction regarding labor induction to now recommend labor induction.
At the bottom of page 14, Applicant then asserts:
The claims are therefore not directed merely to collecting information, analyzing information, and displaying results. Rather, the claims recite a concrete processor-implemented physiological signal-processing and inferencing architecture specifically configured for labor-and-delivery monitoring. The claims recite specialized waveform processing, dynamic physiological-event extraction, supervised machine-learning analysis, multistage inferencing, continuous prediction updating, and integrated maternal-health analysis performed within a real-time physiological monitoring environment. The claims therefore improve computerized cardiotocograph interpretation systems themselves rather than merely using generic computers as tools to perform mental processes.
However, many of the features discussed above (e.g., waveform processing, dynamic physiological-event extraction, inferencing, continuous prediction updating, maternal health analysis) are practically performable in the human mind with pen and paper as repeatedly discussed herein. Furthermore, use of the processor just amounts to using a computer or other machinery as tools performing their typical functionality in conjunction with performing the above-noted at least one abstract idea (see MPEP § 2106.05(f)) while recitation of the ML models are recited at such a high level of generality such that they amount to merely reciting the idea of a solution or outcome without reciting details of how a solution to a problem is accomplished which is equivalent to the words “apply it” (see MPEP § 2106.05(f)).
On page 15 of the Amendment, Applicant asserts that the present claims are directed to improvements in computer functionality or specialized data-processing architectures similar to the claims in Enfish and McRO because the present claims recite a specific technological process for transforming streaming physiological waveform inputs into dynamically updated physiological-event data used within a staged AI inferencing architecture to improve automated labor-and-delivery monitoring and prediction systems. The Examiner disagrees because a person can readily dynamically determine physiological event data by mentally reviewing physiological waveform inputs and use such event data to dynamically determine labor-and-delivery monitoring and prediction systems as repeatedly noted herein. Furthermore, there are little to no details regarding the recited models such that they amount to merely reciting the idea of a solution or outcome without reciting details of how a solution to a problem is accomplished which is equivalent to the words “apply it” (see MPEP § 2106.05(f)) as also noted herein.
Applicant next asserts that the present claims are analogous to those in CardioNet, LLC v. InfoBionic, Inc. (955 F.3d 1358, 1368-69 (Fed. Cir. 2020)) because they are directed to an improved computerized fetal and maternal monitoring system through continuous streaming cardiotocograph waveform analysis, dynamically identified physiological-event extraction, machine-trained inferencing, multistage AI prediction architectures, and integrated maternal-health analysis. However, medical professionals (e.g., OBGYN) routinely monitor CTG waveforms, identify physiological events from the waveforms (e.g., FHR decelerations, contractions, etc.), perform inferencing, generate labor/delivery predictions (e.g., regarding premature labor, fetal hypoxia, etc.) based on a wide variety of data, and perform "integrated" maternal-health analysis (e.g., by way of analyzing EHR data, physiological sensor data, etc.).
Furthermore, [0037], [0042] of Applicant's specification even discusses how labor/delivery predictions are commonly generated based on information from CTG waveforms and maternal health parameters. In contrast, nothing in the record in CardioNet suggested that doctors were previously employing the techniques recited in the claimed invention. While [0037]-[0044] of the present specification generally discusses how the present claims provide a machine-driven system that dynamically analyzes both CTG and maternal health data to generate labor/delivery predictions in a real-time/automatic manner while reducing errors, there are no details in the present claims regarding how the various models analyze/process the data in a manner that provides such labor/delivery predictions in a real-time/automatic/dynamic with reduced errors. For instance, independent claim 1 merely recites how the CTG pattern ID model processes the CTG waveform data and generates CTG analysis data (e.g., FHR acceleration, etc.) without detailing how it does so. Similarly, claim 1 merely recites how the maternal health analysis model processes the EMR data and maternal health parameter data to generate maternal health analysis/risk data without detailing how it does so. Still further, claim 1 recites how the multistage AI model receives the CTG and maternal analysis data and generates based on some (unknown) combined analysis labor/delivery predictions and updates such predictions based on changes in the streaming/maternal data without detailing how it does so. Therefore, the present claims do not amount to an "improved" computerized fetal/maternal monitoring system that provides a practical application of the abstract idea.
The Examiner also disagrees that the present claims are similar to those in Thales Visionix Inc. v. United States (850 F.3d 1343 1348-49 (Fed. Cir. 2017)) because the Thales claims require use of two inertial sensors mounted on a tracked object for generating signals used to determine an orientation of the object relative to a moving reference frame whereas in contrast the present claims are merely implemented by a general purpose processor executing computer-executable components including various generically recited models with no details regarding how such models generate the CTG/maternal analysis data and labor/delivery predictions.
On the top of page 16 of the Amendment, Applicant again repeats the alleged limitations of the present claims and asserts they "apply any alleged abstract concept within a specialized medical-monitoring environment to improve computerized physiological interpretation and clinical decision-support functionality." The Examiner disagrees for reasons presented herein.
Applicant then recites the above limitations recite a non-conventional technological architecture specifically configured to improve automated labor and delivery prediction systems. While the Examiner has not asserted the additional limitations are conventional, they still fail to provide a practical application of or significantly more than the abstract idea for the various other reasons discussed herein (e.g., mere "idea of solution," using computers as tools to carry out the abstract idea, etc.)..
Applicant then asserts the claims improve the underlying analysis/interpretation of physiological waveforms, reduce reliance of subjective human interpretation, and improve automated detection of clinically significant fetal and maternal conditions through specialized ML processing pipelines operating on continuously updated physiological telemetry. The Examiner disagrees. There are almost no details regarding how the alleged "specialized ML processing pipelines" actually process the streaming/updated data that provides the above-alleged benefits other than to recite that they generate such data. For instance, independent claim 1 merely recites how the CTG pattern ID model processes the CTG waveform data and generates CTG analysis data (e.g., FHR acceleration, etc.) without detailing how it does so. Similarly, claim 1 merely recites how the maternal health analysis model processes the EMR data and maternal health parameter data to generate maternal health analysis/risk data without detailing how it does so. Still further, claim 1 recites how the multistage AI model receives the CTG and maternal analysis data and generates based on some (unknown) combined analysis labor/delivery predictions and updates such predictions based on changes in the streaming/maternal data without detailing how it does so. Applicant is reading way more into the present claims than is actually recited which does not facilitate prosecution.
The 35 USC 101 rejection is maintained.
Response to Applicant’s Arguments Regarding Claim Rejections Under 35 USC §103
On pages 18-19 of the Amendment, Applicant takes the position that Holder does not disclose a cardiotocograph pattern identification model distinct from the outcome model that continuously processes streaming CTG waveform data and generates structured CTG
analysis data including dynamically identified physiological events (e.g., FHR accelerations, decelerations, contractions, variability values or tracing classifications) for use as inputs to a different prediction model as now recited in amended claims 1, 10, and 18. The Examiner disagrees because [0056] discloses how a signal analysis module ("CTG pattern ID model") extracts first features 350 ("CTG analysis data") from first patient data 346 ("streaming CTG waveform data" because it includes fetal heart rate, uterine contractions, etc. captured over time per [0036], [0077], [0085]) in a continuous manner per [0073]; [0056], [0069]-[0070] discloses how the first features can include accelerations/decelerations, FHR variability, etc. while [0077] discloses how the first features 350 can include contractions; and the physiological event data is "dynamically" identified because [0028] discloses continuous monitoring to support real-time decision-making. Furthermore, the above-noted first features (FHR accelerations/decelerations, FHR variability, etc.) from the signal analysis module/CTG pattern ID model are provided as input to the AI engine/multistage AI model 302 because [0081] discloses how the AI engine 302 analyzes the first features 350 (the "CTG analysis data" generated by the "CTG pattern ID model" noted above) and generates predicted outcomes regarding fetal/maternal biometric/physiological parameters (such as C-section delivery, preeclampsia, neonatal destination after birth, other neonatal complications, etc. per [0086]-[0108]).
Applicant then asserts that Holder does not disclose continuously processing streaming cardiotocograph waveform telemetry during active labor monitoring. The Examiner disagrees because [0073], [0036] discloses how the sensors 152 of the wearable device 150 continuously acquire physiological signals of the mother/fetus and [0028] discloses continuous monitoring to support real-time decision-making all of which necessarily requires continuously processing streaming CTG waveform telemetry during active labor monitoring.
Applicant then asserts that Holder does not disclose dynamically updating prediction outputs during monitoring based on evolving physiological telemetry. The Examiner disagrees because [0028] discusses continuous monitoring and continuous updates to predicted maternal/fetal outcomes to support real-time decision-making such that the predictions are "dynamically" updated during the monitoring based on changes related to the first/second data (the streaming CTG waveform data and the maternal health analysis data)).
Applicant then asserts that Holder further fails to disclose or suggest the claimed "multistage artificial intelligence model comprising respective prediction models respectively directed to different labor and delivery predictions." The Examiner disagrees because the AI engine 302 of Figure 1 makes use of a plurality of different ML/AI models that respectively predict respective ones of labor/delivery predictions per [0086]-[0108], [0111].
In this regard, Applicant's assertion "The Office Action appears to equate any predictive medical system with the presently claimed multistage AI architecture, but such a characterization improperly abstracts the claims and ignores the specific structural and operational limitations recited therein" is clearly erroneous.
Furthermore, Applicant's implicit assertion on page 20 of the Amendment that the Examiner has boiled the present claims down to "merely applying AI to medical data" is clearly erroneous as the Examiner has analyzed each and every limitation of the present claims in detail in the present office action.
Applicant's arguments regarding Cheung are moot as such reference is no longer utilized in the present Final Office Action as necessitated by the Amendment.
Furthermore, Applicant's remaining arguments on pages 21-27 have already been addressed above.
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, 365(c), or 386(c) is acknowledged.
The later-filed application must be an application for a patent for an invention which is also disclosed in the prior application (the parent or original nonprovisional application or provisional application). The disclosure of the invention in the parent application and in the later-filed application must be sufficient to comply with the requirements of 35 U.S.C. 112(a) or the first paragraph of pre-AIA 35 U.S.C. 112, except for the best mode requirement. See Transco Products, Inc. v. Performance Contracting, Inc., 38 F.3d 551, 32 USPQ2d 1077 (Fed. Cir. 1994).
The disclosure of the prior-filed application, Application No. 17/517,251 (“Prior Application”), fails to provide adequate support or enablement in the manner provided by 35 U.S.C. 112(a) or pre-AIA 35 U.S.C. 112, first paragraph for one or more claims of the present application.
Specifically, independent claims 1, 10, and 18 (and thus the dependent claims by virtue of their dependency) in the present application recite, inter alia, a combination of three different AI models, the second and third that respectively generate CTG and maternal health analysis data and the first that generates labor and delivery predictions applicable to one or more fetuses and a corresponding mother by analyzing the CTG and maternal health analysis data. However, the Prior Application does not disclose or support at least these limitations.
Accordingly, claims 1-20 of the present application are not entitled to the benefit of the Prior Application and thus the effective filing date of claims 1-20 of the present application is April 10, 2024, the actual filing date of the present application.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are: "training component" in claim 6, "alert component" in claim 8, and "output component" in claim 9.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1-20 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Each of independent claims 1, 10, and 18 has been amended to recite, inter alia, "wherein the cardiotocograph pattern identification model is trained using annotated cardiotocograph data associated with a plurality of monitored labor-and-delivery cases and corresponding clinical outcomes." While [0058] and [0064] of the present specification discusses how the cardiotocograph pattern identification model can be trained using training data including CTG data annotated with information identifying patterns and defined physiological events corresponding to the patterns, neither these nor any other portions of the specification appear to disclose that the cardiotocograph pattern identification model is trained using "corresponding clinical outcomes." In contrast, it appears that the multistage AI model that generates labor/delivery predictions would be trained using corresponding clinical outcomes rather than the CTG pattern ID model.
Furthermore, each of independent claims 1, 10, and 18 has been amended to recite "wherein the one or more labor and delivery predictions are dynamically updated during the monitoring based on changes in the streaming cardiotocograph waveform data and the maternal health analysis data." The Examiner cannot identify any portion of the original specification that supports this limitation.
The remaining claims are rejected based on their dependency from the above rejected claims.
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 3, 12, and 20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Each of these claims recites how the CTG analysis data includes one or more types selected from, inter alia, FHR acceleration, deceleration, etc. However, claims 1, 10, and 18, from which these claims respectively depend, already recite that the CTG analysis data includes physiological event data that includes one or more of FHR acceleration, deceleration, etc.
Furthermore, claim 20 recites "generate, via the cardiotocograph pattern identification model executed by the processor, the cardiotocography (CTG) analysis data by processing the fetal heart rate (FHR) data associated with the one or more fetuses and the uterine activity (UA) data associated with the mother." However, claim 18, from which this claim depends, already recites "receive, during labor of a mother, streaming cardiotocograph waveform data comprising fetal heart rate (FHR) data associated with one or more fetuses and uterine activity (UA) data associated with the mother; and continuously process, via a cardiotocograph pattern identification model executed by the processor, the streaming cardiotocograph waveform data [which includes the FHR and UA data] to identify dynamically updated physiological event data associated with the one or more fetuses and the mother." In other words, claim 18 already recites generating, via the cardiotocograph pattern identification model executed by the processor, the CTG analysis data by processing the FHR and UA data as recited in claim 20.
Therefore, it is recommended that Applicant amends claims 3, 12, and 20 so that such subject matter is not doubly included.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. §101 because the claimed invention is directed to an abstract idea without significantly more:
Subject Matter Eligibility Criteria - Step 1:
Claims 1-9 are directed to a system (i.e., a machine), claims 10-17 are directed to a method (i.e., a process), and claims 18-20 are directed to a computer program product including a non-transitory computer-readable medium (i.e., a manufacture). Accordingly, claims 1-20 are all within at least one of the four statutory categories. 35 USC §101.
Subject Matter Eligibility Criteria - Alice/Mayo Test: Step 2A - Prong One:
Regarding Prong One of Step 2A of the Alice/Mayo test (which collectively includes the guidance in the January 7, 2019 Federal Register notice and the October 2019 and July 2024 updates issued by the USPTO as incorporated into the MPEP, as supported by relevant case law), the claim limitations are to be analyzed to determine whether, under their broadest reasonable interpretation, they “recite” a judicial exception or in other words whether a judicial exception is “set forth” or “described” in the claims. MPEP 2106.04(II)(A)(1). An “abstract idea” judicial exception is subject matter that falls within at least one of the following groupings: a) certain methods of organizing human activity, b) mental processes, and/or c) mathematical concepts. MPEP 2106.04(a).
Representative independent claim 1 includes limitations that recite at least one abstract idea. Specifically, independent claim 1 recites:
A system, comprising:
a processor that executes computer-executable components stored in memory, wherein the computer-executable components comprise:
a cardiotocograph pattern identification model configured to continuously process streaming cardiotocograph waveform data comprising fetal heart rate (FHR) data and uterine activity (UA) data generated during monitoring of one or more fetuses and a mother during labor, and generate cardiotocography (CTG) analysis data comprising dynamically identified physiological event data associated with the one or more fetuses and the mother, wherein the identified physiological event data comprises one or more of: an FHR acceleration, an FHR deceleration, a contraction, an FHR variability value, or a fetal tracing classification, and wherein the cardiotocograph pattern identification model is trained using annotated cardiotocograph data associated with a plurality of monitored labor-and-delivery cases and corresponding clinical outcomes;
a maternal health analysis model configured to process electronic medical record (EMR) data and maternal health parameter data associated with the mother to generate maternal health analysis data comprising maternal risk factor data or pregnancy complication data; and
a multistage artificial intelligence (AI) model comprising respective prediction models respectively directed to different labor and delivery predictions, wherein the multistage Al model is configured to:
receive, during continuous monitoring of the one or more fetuses and the mother during labor, the CTG analysis data generated by the cardiotocograph pattern identification model and the maternal health analysis data generated by the maternal health analysis model; and
generate, based on combined analysis of the CTG analysis data and the maternal health analysis data, first data comprising one or more labor and delivery predictions applicable to the one or more fetuses and the mother during labor, wherein the one or more labor and delivery predictions are dynamically updated during the monitoring based on changes in the streaming cardiotocograph waveform data and the maternal health analysis data.
The Examiner submits that the foregoing underlined limitations recite “mental processes” because they are observations/evaluations/judgments/analyses that can, at the currently claimed high level of generality, be practically performed in the human mind (e.g., with pen and paper). As an example, a medical professional (e.g., OBGYN) could practically continuously process (e.g., by visually reviewing on a screen and mentally thinking about) streaming CTG waveform data including FHR and UA data generated during monitoring of one or more fetuses and a mother during labor and generate CTG analysis data including dynamically identified physiological event data (e.g., an FHR acceleration, an FHR deceleration, a contraction, an FHR variability value, or a fetal tracing classification) associated with the one or more fetuses and the mother. For instance, in response to visually observing an abrupt increase in FHR from baseline, the medical professional could dynamically identify an FHR acceleration and generate "CTG analysis data" indicative of the same. The medical professional could also readily review/process EMR data and other health parameter data of the mother to generate/determine "maternal health analysis data" such as risk factor data (e.g., in relation to diabetes, hypertension, prior pregnancy complications, etc.).
Thereafter, the medical professional could, based on the CTG analysis data, the maternal health analysis data, and their experience, guidelines, etc., generate "first data" that includes labor and delivery predictions applicable to the one or more fetuses and the mother during labor (e.g., predictions of fetal hypoxia, fetal acidemia, fetal acidosis, labor progression indicating a C-section, cervical dilation progression, a postpartum hemorrhage risk assessment, a preeclampsia prediction, a labor induction recommendation, a sepsis possibility, etc.). Furthermore, the medical professional could dynamically update the labor and delivery predictions based on changes in the streaming cardiotocograph waveform data and the maternal health analysis data. For instance, in the case where the medical professional observes an increased change in the number of late FHR decelerations in combination with an increase in maternal temperature, the medical professional could, based on their experience, guidelines, etc., dynamically update a previous prediction regarding labor induction to now recommend labor induction.
These recitations, under their broadest reasonable interpretation, are similar to the concepts of collecting information, analyzing it and displaying certain results of the collection and analysis found to be "mental processes" in Electric Power Group, LLC, v. Alstom (830 F.3d 1350, 119 USPQe2d 1739 (Fed. Cir. 2016)). MPEP 2106.04(a)(2)(III).
The foregoing underlined limitations recite also recite "certain methods of organizing human activity" because they relate to managing personal behavior or relationships or interactions between people (e.g., social activities, teaching, and following rules or instructions). These recitations, under their broadest reasonable interpretation, are similar to the concept of a mental process that a neurologist should follow when testing a patient for nervous system malfunctions, In re Meyer, 688 F.2d 789, 791-93, 215 USPQ 193, 194-96 (CCPA 1982). MPEP 2106.04(a)(2)(II)(C).
Accordingly, the claim recites at least one abstract idea.
Furthermore, dependent claims 2-9, 11-17, 19, and 20 further define the at least one abstract idea (and thus fail to make the abstract idea any less abstract) as set forth below:
-Claims 2, 11, and 19 recite how the first data includes one or more types of data selected from a group comprising fetal hypoxia, fetal acidemia, fetal acidosis, labor progression indicating a C-section, cervical dilation progression, a postpartum hemorrhage risk assessment, a preeclampsia prediction, a labor induction recommendation, a sepsis possibility, and one or more additional labor and delivery predictions which just further defines the abstract idea(s) discussed above.
-Claims 3, 12, and 20 recite how the CTG analysis data is generated by processing fetal heart rate (FHR) data of the one or more fetuses and uterine activity (UA) data of the mother, where the CTG analysis data comprises one or more types of data selected from a group consisting of an FHR baseline value calculation, an FHR acceleration, an FHR deceleration, a contraction, an FHR variability value calculation, fetal tracing classification, and one or more additional CTG analysis data types, all of which just further defines the abstract idea(s) discussed above.
-Claims 4, 13, and 20 recite how the maternal health analysis data is generated by employing rule-based algorithms to process electronic medical records (EMRs) and health parameters of the mother, where the maternal health analysis data comprises one or more types of data selected from a group consisting of maternal health related risk factors, pregnancy related complications, dystocia, genetic disorders and one or more additional maternal health analysis data types, all of which just further defines the abstract idea(s) discussed above.
-Claims 5 and 14 recites how the CTG analysis data and the maternal health analysis data are generated during fetal monitoring of the one or more fetuses and maternal monitoring of the mother, where the CTG analysis data and the maternal health analysis data are available for analysis during the fetal monitoring of the one or more fetuses and the maternal monitoring of the mother, all of which just further defines the abstract idea(s) discussed above.
-Claims 6 and 15 call for identifying patterns in training cardiotocograph data that correspond to defined physiological events associated with respective fetuses and mothers of the fetuses represented in the training cardiotocograph data which is practically performable in the human mind such as by a medical professional visually reviewing and thinking about CTG trace features and/or the like and thus just further defines the abstract idea(s) discussed above.
-Claim 7 recites how at least some of the training cardiotocograph data comprises annotated cardiotocograph data annotated with information identifying the patterns and the defined physiological events that respectively correspond to the patterns which is mentally reviewable by a medical professional and thus just further defines the abstract idea(s) discussed above.
-Claims 8 and 16 call for generating an alert component that generates an alert in response to the first data being indicative of an emergency situation associated with the one or more fetuses or the mother during labor which is practically performable in the human mind with pen and paper and relates to managing personal behavior or relationships or interactions between people (e.g., social activities, teaching, and following rules or instructions) and therefore just further defines the abstract idea(s) discussed above.
-Claims 9 and 17 call for displaying the first data for further analysis of the first data to identify actions to be executed by the entity for safe delivery of the one or more fetuses which again just further defines the abstract idea(s) discussed above.
Subject Matter Eligibility Criteria - Alice/Mayo Test: Step 2A - Prong Two:
Regarding Prong Two of Step 2A of the Alice/Mayo test, it must be determined whether the claim as a whole integrates the abstract idea into a practical application. As noted at MPEP §2106.04(II)(A)(2), it must be determined whether any additional elements in the claim beyond the abstract idea integrate the exception into a practical application in a manner that imposes a meaningful limit on the judicial exception. The courts have indicated that additional elements such as merely using a computer to implement an abstract idea, adding insignificant extra solution activity, or generally linking use of a judicial exception to a particular technological environment or field of use do not integrate a judicial exception into a “practical application.” MPEP §2106.05(I)(A).
In the present case, the additional limitations beyond the above-noted at least one abstract idea recited in the claim are as follows (where the bolded portions are the “additional limitations” while the underlined portions continue to represent the at least one “abstract idea”):
A system, comprising:
a processor that executes computer-executable components stored in memory, wherein the computer-executable components comprise:
a cardiotocograph pattern identification model configured to continuously process streaming cardiotocograph waveform data comprising fetal heart rate (FHR) data and uterine activity (UA) data generated during monitoring of one or more fetuses and a mother during labor, and generate cardiotocography (CTG) analysis data comprising dynamically identified physiological event data associated with the one or more fetuses and the mother, wherein the identified physiological event data comprises one or more of: an FHR acceleration, an FHR deceleration, a contraction, an FHR variability value, or a fetal tracing classification, and wherein the cardiotocograph pattern identification model is trained using annotated cardiotocograph data associated with a plurality of monitored labor-and-delivery cases and corresponding clinical outcomes;
a maternal health analysis model configured to process electronic medical record (EMR) data and maternal health parameter data associated with the mother to generate maternal health analysis data comprising maternal risk factor data or pregnancy complication data; and
a multistage artificial intelligence (AI) model comprising respective prediction models respectively directed to different labor and delivery predictions, wherein the multistage Al model is configured to:
receive, during continuous monitoring of the one or more fetuses and the mother during labor, the CTG analysis data generated by the cardiotocograph pattern identification model and the maternal health analysis data generated by the maternal health analysis model; and
generate, based on combined analysis of the CTG analysis data and the maternal health analysis data, first data comprising one or more labor and delivery predictions applicable to the one or more fetuses and the mother during labor, wherein the one or more labor and delivery predictions are dynamically updated during the monitoring based on changes in the streaming cardiotocograph waveform data and the maternal health analysis data.
For the following reasons, the Examiner submits that the above-identified additional limitations, when considered as a whole with the limitations reciting the at least one abstract idea, do not integrate the above-noted at least one abstract idea into a practical application.
Regarding the additional limitations of the system including a processor that executes computer-executable components stored in memory, the Examiner submits that these limitations amount to merely using a computer or other machinery as tools performing their typical functionality in conjunction with performing the above-noted at least one abstract idea (see MPEP § 2106.05(f)).
Regarding the additional limitations of the generically recited CTG pattern identification model trained using annotated cardiotocograph data associated with a plurality of monitored labor-and-delivery cases and corresponding clinical outcomes, the maternal health analysis model, and the "multistage" AI model having respective models for predicting different labor and delivery predictions, the Examiner submits that these limitations amount to merely reciting the idea of a solution or outcome without reciting details of how a solution to a problem is accomplished which is equivalent to the words “apply it” (see MPEP § 2106.05(f)).
Claims that do no more than apply established methods of machine learning to a new data environment are not patent eligible. Recentive Analytics, Inc. v. Fox Corp., Fox Broadcasting Company, LLC, Fox Sports Productions, LLC, Case No. 23-2437, (Fed. Cir. 2025), pp. 10, 14. An abstract idea does not become nonabstract by limiting the invention to a particular field of use or technological environment. Id. Requirements that the machine learning model be “iteratively trained” or dynamically adjusted do not represent a technological improvement because iterative training using selected training material and dynamic adjustments based on real-time changes are incident to the very nature of machine learning. Id., p. 12. “[T]he way machine learning works is the inputs are defined, the model is trained, and then the algorithm is actually updated and improved over time based on the input.” Id. Using existing machine learning technology to perform a task previously undertaken by humans with greater speed and efficiency than could previously be achieved does not confer patent-eligibility. Id., p. 15. For instance, as the CTG pattern identification model is already configured to perform the (mental process of) receiving the CTG data and generating CTG analysis data such as FHR accelerations/decelerations, etc., then specifying that the model is trained based on annotated CTG data patterns and corresponding clinical outcomes does not recite any specific details regarding how the training is accomplished.
Thus, taken alone, the additional elements do not integrate the at least one abstract idea into a practical application. Furthermore, looking at the additional limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. MPEP §2106.05(I)(A) and §2106.04(II)(A)(2).
For these reasons, representative independent claim 1 and analogous independent claims 10 and 18 do not recite additional elements that integrate the judicial exception into a practical application. Accordingly, representative independent claim 1 and analogous independent claims 10 and 18 are directed to at least one abstract idea.
The remaining dependent claim limitations not addressed above fail to integrate the abstract idea into a practical application as set forth below:
-Claims 6 and 15 call for training the multistage model to generate the first data by employing the CTG analysis data and the material health analysis data as input data to the multistage AI model and employing known labor and delivery predictions corresponding to the input data as output data for the multistage AI model which amounts to merely reciting the idea of a solution or outcome without reciting details of how a solution to a problem is accomplished which is equivalent to the words “apply it” (see MPEP § 2106.05(f)). Requirements that the machine learning model be “iteratively trained” or dynamically adjusted do not represent a technological improvement because iterative training using selected training material and dynamic adjustments based on real-time changes are incident to the very nature of machine learning. Recentive Analytics, Inc. v. Fox Corp., Fox Broadcasting Company, LLC, Fox Sports Productions, LLC, Case No. 23-2437, (Fed. Cir. 2025), p. 12. “[T]he way machine learning works is the inputs are defined, the model is trained, and then the algorithm is actually updated and improved over time based on the input.” Id. For instance, as the multistage AI model is already configured to perform the (mental process of) receiving the CTG analysis and maternal health analysis data and outputting labor and delivery predictions, then specifying that the model is trained based on the input CTG analysis and maternal health analysis data and known labor and delivery predictions corresponding to the input data (the same type of data configured to be input into and output from the model) does not recite any specific details regarding how the training is accomplished. These claims also generically recite how the CTG pattern ID model is trained with a supervised ML process which again does not represent a technological improvement because iterative training using selected training material and dynamic adjustments based on real-time changes are incident to the very nature of machine learning. Recentive Analytics, Inc. v. Fox Corp., Fox Broadcasting Company, LLC, Fox Sports Productions, LLC, Case No. 23-2437, (Fed. Cir. 2025), p. 12. “[T]he way machine learning works is the inputs are defined, the model is trained, and then the algorithm is actually updated and improved over time based on the input.” Id.
-Claim 7 recites how the supervised machine learning process comprises employing the annotated cardiotocograph data as ground truth which amounts to merely reciting the idea of a solution or outcome without reciting details of how a solution to a problem is accomplished which is equivalent to the words “apply it” (see MPEP § 2106.05(f)). Requirements that the machine learning model be “iteratively trained” or dynamically adjusted do not represent a technological improvement because iterative training using selected training material and dynamic adjustments based on real-time changes are incident to the very nature of machine learning. Recentive Analytics, Inc. v. Fox Corp., Fox Broadcasting Company, LLC, Fox Sports Productions, LLC, Case No. 23-2437, (Fed. Cir. 2025), p. 12. “[T]he way machine learning works is the inputs are defined, the model is trained, and then the algorithm is actually updated and improved over time based on the input.” Id.
-Claims 8 and 16 recite how the alert is generated by an "alert component" or the "device" which amounts to merely using a computer or other machinery as tools performing their typical functionality in conjunction with performing the above-noted at least one abstract idea (see MPEP § 2106.05(f)).
-Claims 9 and 17 recite how the first data is displayed at a "device" by an "output component" or the "device" which amounts to merely using a computer or other machinery as tools performing their typical functionality in conjunction with performing the above-noted at least one abstract idea (see MPEP § 2106.05(f)).
When the above additional limitations are considered as a whole along with the limitations directed to the at least one abstract idea, the at least one abstract idea is not integrated into a practical application. Therefore, the claims are directed to at least one abstract idea.
Subject Matter Eligibility Criteria - Alice/Mayo Test: Step 2B:
Regarding Step 2B of the Alice/Mayo test, representative independent claim 1 does not include additional elements (considered both individually and as an ordered combination) that are sufficient to amount to significantly more than the judicial exception for reasons the same as those discussed above with respect to determining that the claim does not integrate the abstract idea into a practical application.
Regarding the additional limitations of the system including a processor that executes computer-executable components stored in memory, the Examiner submits that these limitations amount to merely using a computer or other machinery as tools performing their typical functionality in conjunction with performing the above-noted at least one abstract idea (see MPEP § 2106.05(f)).
Regarding the additional limitations of the generically recited CTG pattern identification model trained using annotated cardiotocograph data associated with a plurality of monitored labor-and-delivery cases and corresponding clinical outcomes, the maternal health analysis model, and the "multistage" AI model having respective models for predicting different labor and delivery predictions, the Examiner submits that these limitations amount to merely reciting the idea of a solution or outcome without reciting details of how a solution to a problem is accomplished which is equivalent to the words “apply it” (see MPEP § 2106.05(f)).
Claims that do no more than apply established methods of machine learning to a new data environment are not patent eligible. Recentive Analytics, Inc. v. Fox Corp., Fox Broadcasting Company, LLC, Fox Sports Productions, LLC, Case No. 23-2437, (Fed. Cir. 2025), pp. 10, 14. An abstract idea does not become nonabstract by limiting the invention to a particular field of use or technological environment. Id. Requirements that the machine learning model be “iteratively trained” or dynamically adjusted do not represent a technological improvement because iterative training using selected training material and dynamic adjustments based on real-time changes are incident to the very nature of machine learning. Id., p. 12. “[T]he way machine learning works is the inputs are defined, the model is trained, and then the algorithm is actually updated and improved over time based on the input.” Id. Using existing machine learning technology to perform a task previously undertaken by humans with greater speed and efficiency than could previously be achieved does not confer patent-eligibility. Id., p. 15. For instance, as the CTG pattern identification model is already configured to perform the (mental process of) receiving the CTG data and generating CTG analysis data such as FHR accelerations/decelerations, etc., then specifying that the model is trained based on annotated CTG data patterns and corresponding clinical outcomes does not recite any specific details regarding how the training is accomplished.
The dependent claims also do not include additional elements (considered both individually and as an ordered combination) that are sufficient to amount to significantly more than the judicial exception for the same reasons to those discussed above with respect to determining that the dependent claims do not integrate the at least one abstract idea into a practical application.
-Claims 6 and 15 call for training the multistage model to generate the first data by employing the CTG analysis data and the material health analysis data as input data to the multistage AI model and employing known labor and delivery predictions corresponding to the input data as output data for the multistage AI model which amounts to merely reciting the idea of a solution or outcome without reciting details of how a solution to a problem is accomplished which is equivalent to the words “apply it” (see MPEP § 2106.05(f)). Requirements that the machine learning model be “iteratively trained” or dynamically adjusted do not represent a technological improvement because iterative training using selected training material and dynamic adjustments based on real-time changes are incident to the very nature of machine learning. Recentive Analytics, Inc. v. Fox Corp., Fox Broadcasting Company, LLC, Fox Sports Productions, LLC, Case No. 23-2437, (Fed. Cir. 2025), p. 12. “[T]he way machine learning works is the inputs are defined, the model is trained, and then the algorithm is actually updated and improved over time based on the input.” Id. For instance, as the multistage AI model is already configured to perform the (mental process of) receiving the CTG analysis and maternal health analysis data and outputting labor and delivery predictions, then specifying that the model is trained based on the input CTG analysis and maternal health analysis data and known labor and delivery predictions corresponding to the input data (the same type of data configured to be input into and output from the model) does not recite any specific details regarding how the training is accomplished. These claims also generically recite how the CTG pattern ID model is trained with a supervised ML process which again does not represent a technological improvement because iterative training using selected training material and dynamic adjustments based on real-time changes are incident to the very nature of machine learning. Recentive Analytics, Inc. v. Fox Corp., Fox Broadcasting Company, LLC, Fox Sports Productions, LLC, Case No. 23-2437, (Fed. Cir. 2025), p. 12. “[T]he way machine learning works is the inputs are defined, the model is trained, and then the algorithm is actually updated and improved over time based on the input.” Id.
-Claim 7 recites how the supervised machine learning process comprises employing the annotated cardiotocograph data as ground truth which amounts to merely reciting the idea of a solution or outcome without reciting details of how a solution to a problem is accomplished which is equivalent to the words “apply it” (see MPEP § 2106.05(f)). Requirements that the machine learning model be “iteratively trained” or dynamically adjusted do not represent a technological improvement because iterative training using selected training material and dynamic adjustments based on real-time changes are incident to the very nature of machine learning. Recentive Analytics, Inc. v. Fox Corp., Fox Broadcasting Company, LLC, Fox Sports Productions, LLC, Case No. 23-2437, (Fed. Cir. 2025), p. 12. “[T]he way machine learning works is the inputs are defined, the model is trained, and then the algorithm is actually updated and improved over time based on the input.” Id.
-Claims 8 and 16 recite how the alert is generated by an "alert component" or the "device" which amounts to merely using a computer or other machinery as tools performing their typical functionality in conjunction with performing the above-noted at least one abstract idea (see MPEP § 2106.05(f)).
-Claims 9 and 17 recite how the first data is displayed at a "device" by an "output component" or the "device" which amounts to merely using a computer or other machinery as tools performing their typical functionality in conjunction with performing the above-noted at least one abstract idea (see MPEP § 2106.05(f)).
Therefore, claims 1-20 are ineligible under 35 USC §101.
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 1-3, 5, 8-12, 14, and 16-19 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent App. Pub. No. 2023/0200746 to Holder et al. ("Holder") in view of U.S. Patent App. Pub. No. 2021/0321890 to Iyer et al. ("Iyer"):
Regarding claim 1, Holder discloses a system (Figure 1), comprising:
a processor (processor 322 in Figure 3) that executes computer-executable components stored in memory ([0145]), wherein the computer-executable components comprise:
a cardiotocograph pattern identification model configured to continuously process streaming cardiotocograph waveform data comprising fetal heart rate (FHR) data and uterine activity (UA) data generated during monitoring of one or more fetuses and a mother during labor, and generate cardiotocography (CTG) analysis data ([0056] discloses how a signal analysis module ("CTG pattern ID model") extracts first features 350 ("CTG analysis data") from first patient data 346 ("streaming CTG waveform data" because it includes fetal heart rate, uterine contractions, etc. captured over time per [0036], [0077], [0085]) in a continuous manner per [0073]) comprising dynamically identified physiological event data associated with the one or more fetuses and the mother, wherein the identified physiological event data comprises one or more of: an FHR acceleration, an FHR deceleration, a contraction, an FHR variability value, or a fetal tracing classification ([0056], [0069]-[0070] discloses how the first features can include accelerations/decelerations, FHR variability, etc. while [0077] discloses how the first features 350 can include contractions; as [0028] discloses continuous monitoring to support real-time decision-making, then the physiological event data is "dynamically" identified), and …;
a maternal health analysis model ([0056] discloses how signal analysis modules/models can extract the first and second features; thus, the signal analysis module that extract second features 351 from second patient data 347 is a "maternal health analysis model") configured to process electronic medical record (EMR) data and maternal health parameter data associated with the mother to generate maternal health analysis data (the end of [0004] of Holder discloses how the second patient data can include medical history and/or profile of the patient including current conditions such as gestational diabetes (collectively, EHR data and maternal health parameter data associated with the mother); accordingly, when the "maternal health analysis model" extracts the second features ("maternal health analysis data") from the second the second patient data per [0056] of Holder, it does so from the "EHRs and health parameters of the mother") comprising maternal risk factor data or pregnancy complication data (e.g., stress level, breathing rate, etc. per [0074], mental health assessment features per [0077], etc.); and
a multistage artificial intelligence (AI) model comprising respective prediction models respectively directed to different labor and delivery predictions (AI engine 302 of Figure 1 which makes use of a plurality of different ML/AI models that respectively predict respective ones of labor/delivery predictions per [0086]-[0108], [0111]), wherein the multistage Al model is configured to:
receive, during continuous monitoring of the one or more fetuses and the mother during labor, the CTG analysis data generated by the cardiotocograph pattern identification model and the maternal health analysis data generated by the maternal health analysis model ([0081] discloses how the AI engine 302 analyzes first features 350 (the "CTG analysis data" generated by the "CTG pattern ID model" noted above) and second features 351 (the "maternal health analysis data" generated by the "maternal health analysis model" noted above); furthermore, such receipt/analysis of the first and second features is during "continuous monitoring" as [0028] discloses continuous monitoring to support real-time decision-making); and
generate, based on combined analysis of the CTG analysis data and the maternal health analysis data, first data comprising one or more labor and delivery predictions applicable to the one or more fetuses and the mother during labor ([0081]-[0082] discloses how AI engine 302 generates predicted outcomes 380 regarding fetal/maternal biometric/physiological parameters (such as C-section delivery, preeclampsia, neonatal destination after birth, other neonatal complications, etc. per [0086]-[0108]) based on the first and second features (combined analysis of the "CTG analysis data" and the "maternal health analysis data"), which can be during labor per the end of [0035], [0075]), wherein the one or more labor and delivery predictions are dynamically updated during the monitoring based on changes in the streaming cardiotocograph waveform data and the maternal health analysis data ([0028] discusses continuous monitoring and continuous updates to predicted maternal/fetal outcomes to support real-time decision-making such that the predictions are "dynamically" updated during the monitoring based on changes related to the first/second data (the streaming CTG waveform data and the maternal health analysis data)).
However, Holder might be silent regarding wherein the cardiotocograph pattern identification model is trained using annotated cardiotocograph data associated with a plurality of monitored labor-and-delivery cases and corresponding clinical outcomes.
Nevertheless, Iyer teaches ([0055]) that it was known in the healthcare informatics art for an NN to be trained to generate FHR probabilities (analysis data) using labeled (annotated) ECG/ultrasound data collected from a number of pregnant subjects (plurality of monitored labor and delivery cases) and corresponding heart rate categories (corresponding clinical outcomes) which advantageously facilitates identification of FHR accelerations/decelerations indicative of fetal movement to support pregnancy care ([0015]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention for the CTG pattern ID model of Holder to be trained using annotated ECG/ultrasound data (CTG data as already disclosed by Holder) associated with a plurality of monitored labor-and-delivery cases and corresponding clinical outcomes as taught by Iyer to advantageously facilitate identification of FHR accelerations/decelerations indicative of fetal movement to support pregnancy care. A person of ordinary skill in the art would have been motivated to combine the prior art to achieve the claimed invention and there would have been a reasonable expectation of success in doing so. KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398 (2007). Furthermore, all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination yielded nothing more than predictable results to one of ordinary skill in the art. Id.
Regarding claim 2, the Holder/Iyer combination discloses system of claim 1, further including wherein the first data comprises one or more types of data selected from a group comprising fetal hypoxia, fetal acidemia, fetal acidosis, labor progression indicating a Caesarean-section (C-section), cervical dilation progression, a postpartum hemorrhage risk assessment, a preeclampsia prediction, a labor induction recommendation, a sepsis possibility, and one or more additional labor and delivery predictions ([0086]-[0108] of Holder discloses C-section delivery, preeclampsia, neonatal destination after birth, other neonatal complications, etc.; also, [0084] discloses fetal acidemia/hypoxia).
Regarding claim 3, the Holder/Iyer combination discloses system of claim 1, further including wherein the cardiotocograph pattern identification model generates the CTG analysis data by processing fetal heart rate (FHR) data of the one or more fetuses and uterine activity (UA) data of the mother ([0081] of Holder discloses how the first features 350 (the recited "CTG analysis data") are extracted from first patient data 346 acquired by wearable device 150 while [0036] discloses how the data from the wearable device 150 can include fetal cardiac activity (FHR) and uterine activity (UA)), and wherein the CTG analysis data comprises one or more types of data selected from a group consisting of an FHR baseline value calculation, an FHR acceleration, an FHR deceleration, a contraction, an FHR variability value calculation, a fetal tracing classification, and one or more additional CTG analysis data types ([0056] of Holder discloses how the signal analysis module (the "CTG pattern ID model") can extract baseline of the first patient data (which would thus include baseline FHR, a baseline variability, number of accelerations/decelerations, etc.)).
Regarding claim 5, the Holder/Iyer combination discloses system of claim 1, further including wherein the CTG analysis data and the maternal health analysis data are generated during fetal monitoring of the one or more fetuses and maternal monitoring of the mother, and wherein the CTG analysis data and the maternal health analysis data are available for analysis by the multistage AI model during the fetal monitoring of the one or more fetuses and the maternal monitoring of the mother ([0035], [0042], [0053], [0073]-[0074], [0081], [0111] of Holder disclose obtaining the first and second patient data, extracting the first and second features (the CTG and maternal health analysis data) and using the AI model (the multistage AI model) to generate the predicted outcomes based on the first and second features (the CTG and maternal health analysis data) during a current monitoring session of the fetus and mother).
Regarding claim 8, the Holder/Iyer combination discloses system of claim 1, further including an alert component that generates an alert in response to the first data being indicative of an emergency situation associated with the one or more fetuses or the mother during labor ([0028] of Holder discloses alert triggering and [0116] discloses how a provider module (alert component) generates reports (alert) when a predicted outcome (the "first data," which is in relation to fetus/mother during labor per [0082]) is determined to be an adverse outcome (an emergency situation) which can be during labor per the end of [0035], [0075]).
Regarding claim 9, the Holder/Iyer combination discloses system of claim 1, further including an output component that displays the first data at a device accessible to an entity for further analysis of the first data to identify actions to be executed by the entity for safe delivery of the one or more fetuses ([0115]-[0116] of Holder discloses how a provider or patient module (output component) generates and displays reports with the predicted (adverse) outcomes (first data) and suggested actions for the provider or patient to address the predicted adverse outcomes such as intervention suggestion, care plan suggestion, etc.; as the purpose of the disclosure of Holder is to provide a system to support real-time decision-making by a clinical team to decrease overall costs associated with adverse maternal and fetal outcomes per [0028], [0084], then the identified suggested intervention would necessarily be for "safe delivery" of the one or more fetuses).
Claims 10-12, 14, 16, and 17 are rejected in view of the Holder/Iyer combination as respectively discussed above in relation to claims 1-3, 5, 8, and 9.
Claims 18 and 19 are rejected in view of the Holder/Iyer combination as respectively discussed above in relation to claims 1 and 2.
Claims 4, 13, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent App. Pub. No. 2023/0200746 to Holder et al. ("Holder") in view of U.S. Patent App. Pub. No. 2021/0321890 to Iyer et al. ("Iyer"), and further in view of U.S. Patent App. Pub. No. 2022/0101987 to Tuysuzoglu et al. ("Tuysuzoglu"):
Regarding claim 4, the Holder/Iyer combination discloses system of claim 1, further including wherein the maternal health analysis model generates the maternal health analysis data by employing … algorithms to process electronic medical records (EMRs) and maternal health parameter data associated with the mother (the end of [0004] of Holder discloses how the second patient data can include medical history and/or profile of the patient including current conditions such as gestational diabetes (collectively, EHRs and health parameters of the mother); accordingly, when the maternal health/signal analysis module/model extracts the maternal health analysis data from the second patient data per [0056] of Holder, it extracts/generates such maternal health analysis data from the "EHRs and health parameters of the mother"; furthermore, the signal analysis module/model necessarily employ algorithms), and wherein the maternal health analysis data comprises one or more types of data selected from a group consisting of maternal health related risk factors, pregnancy related complications, dystocia, genetic disorders and one or more additional maternal health analysis data types (as the second patient data from which the maternal health analysis data/features are extracted includes e.g., mental health assessment features, SDoH assessments, current conditions such as gestational diabetes, etc. (which amount to of maternal health related risk factors, pregnancy related complications, additional maternal health analysis data types, etc. per [0004], [0077], then the features (maternal health analysis data) of such second patient data necessarily also includes one or more data types selected from a group consisting of maternal health related risk factors, pregnancy related complications, one or more additional maternal health analysis data types, etc.).
However, the Holder/Iyer combination might not specifically discloses the algorithms of the third AI model to be rule-based algorithms.
Nevertheless, Tuysuzoglu teaches ([0069]) that it was known in the healthcare informatics and machine learning art for a rule-based NN to associate a level of risk to medical data (which can include recorded patient data such as temperature, weight, medical history, etc. including textual data per [0043]-[0044]) based on a set of predetermined rules so that a trained NN can associate higher risk to more urgent conditions to ensure that more urgent pieces of medical data are analyzed in a prioritized manner ([0071]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention for the algorithms of the third AI model of the Holder/Iyer combination to be rule-based algorithms similar to as taught by Tuysuzoglu so that a trained ML model (e.g., NN, etc.) can associate higher risk to more urgent conditions to ensure that more urgent pieces of medical data are analyzed in a prioritized manner. A person of ordinary skill in the art would have been motivated to combine the prior art to achieve the claimed invention and there would have been a reasonable expectation of success in doing so. KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398 (2007). Furthermore, all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination yielded nothing more than predictable results to one of ordinary skill in the art. Id.
Claim 13 is rejected in view of the Holder/Iyer/Tuysuzoglu combination similar to the rejection of claim 4 above.
Claim 20 is rejected in view of the Holder/Iyer/Tuysuzoglu combination similar to the rejection of claims 3-4 above.
Claims 6, 7, and 15 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent App. Pub. No. 2023/0200746 to Holder et al. ("Holder") in view of U.S. Patent App. Pub. No. 2021/0321890 to Iyer et al. ("Iyer"), and further in view of NPL "Detection of preventable fetal distress during labor from scanned cardiotocogram tracings using deep learning" to Frasch et al. ("Frasch"):
Regarding claim 6, the Holder/Iyer combination discloses system of claim 1, further including a training component configured to:
train the multistage model to generate the first data by employing the CTG analysis data and the maternal health analysis data as input data to the multistage AI model and employing known labor and delivery predictions corresponding to the input data as output data for the multistage AI model ([0080] of Holder discloses how the AI engine applies a training set of the first and second features (the recited CTG and maternal health analysis data) and associated outcomes obtained for each of a plurality of patients (known labor and delivery predictions corresponding to the input data as output data) to train the one or more ML models to predict maternal/fetal outcomes (a training components that trains the multistage AI model to generate the first data), …
However, the Holder/Iyer combination appears to be silent regarding the training component training the CTG pattern ID model by employing a supervised machine learning process to identify patterns in training cardiotocograph data that correspond to defined physiological events associated with respective fetuses and mothers of the fetuses represented in the training cardiotocograph data.
Nevertheless, Frasch teaches (page 10, third paragraph) that it was known in the healthcare informatics and machine learning art to perform supervised training of an AI/ML model using FHR and UC data (training cardiotocograph data associated with fetuses and mothers of the fetuses)) and classifying (page 4 and page 12, second paragraph) patterns in EFM/cardiotocography data as signatures/features/events (e.g., Point A, Point B, etc.) associated with respective fetuses and mothers (top of page 3). Accordingly, as part of using the training data to train the AI/ML model per the third paragraph of page 10, such graphical patterns in cardiotocograph graphical tracings (e.g., Figure 1 on page 3) of the training data corresponding to physiological events associated with hearts of the fetuses and uteruses of the mothers of the fetuses during labor are identified in the training data. This arrangement advantageously identifies critical features in the EFM/CTG data that indicate critical and timely points of either conservative or operative intervention to thereby tailor treatment approaches to specific patient parameters resulting in improved outcomes (page 12).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have trained the CTG pattern ID model of the Holder/Iyer combination by employing a supervised machine learning process to identify patterns in training cardiotocograph data that correspond to defined physiological events associated with respective fetuses and mothers of the fetuses represented in the training cardiotocograph data similar to as taught by Frasch to advantageously identify critical features in the EFM/CTG data that indicate critical and timely points of either conservative or operative intervention to thereby tailor treatment approaches to specific patient parameters resulting in improved outcomes. A person of ordinary skill in the art would have been motivated to combine the prior art to achieve the claimed invention and there would have been a reasonable expectation of success in doing so. KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398 (2007). Furthermore, all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination yielded nothing more than predictable results to one of ordinary skill in the art. Id.
Claim 15 is rejected in view of the Holder/Iyer/Frasch combination similar to as discussed in relation to claim 6.
Regarding claim 7, the Holder/Iyer/Frasch combination discloses system of claim 6, further including wherein at least some of the training cardiotocograph data comprises annotated cardiotocograph data annotated with information identifying the patterns and the defined physiological events that respectively correspond to the patterns (page 10, second, third, and fifth paragraphs of Frasch discuss how the FHR/UC data (the training cardiotocograph data) can have markers/labels/annotations assigned to features (events) for use in supervised training of the ML model; the particular cardiotocograph data making up each particular event are graphical patterns), and wherein the supervised machine learning process comprises employing the annotated cardiotocograph data as ground truth (as the above-noted markers/labels of the patterns are used in supervised training of the ML model, it is employed as "ground truth" because that is how supervised training performs; similar to as discussed above, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have trained the second AI model of the Holder/Iyer combination by employing a supervised machine learning process to identify patterns in annotated training cardiotocograph data that correspond to defined physiological events associated with respective fetuses and mothers of the fetuses represented in the training cardiotocograph data and using the annotated data as ground truth similar to as taught by Frasch to advantageously identify critical features in the EFM/CTG data that indicate critical and timely points of either conservative or operative intervention to thereby tailor treatment approaches to specific patient parameters resulting in improved outcomes. A person of ordinary skill in the art would have been motivated to combine the prior art to achieve the claimed invention and there would have been a reasonable expectation of success in doing so. KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398 (2007). Furthermore, all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination yielded nothing more than predictable results to one of ordinary skill in the art. Id.).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
CN 114159039 discloses an intelligent antenatal fetal heart monitoring model, comprising a fetal heart rate signal, uterine contraction signal, pre-processing pregnant woman age and pregnant week to obtain pre-produced standardized fetal heart rate, uterine contraction signal and pregnant woman basic information data set; then convolutional neural network module the pre-processed fetal heart rate signal and uterine contraction signal to perform the high-dimensional feature extraction; designing the base classifier LGBM according to the feature design of the monitoring data of the antenatal fetal heart; then fusing the extracted signal high-dimensional feature with the pre-processed pregnant woman basic information; forming multi-mode characteristic, then inputting the multi-mode characteristic input base classifier LGBM to obtain the classification judging result. The intelligent antenatal fetal heart monitoring model of the invention makes the fetal heart rate signal and uterine contraction signal, pregnant woman age and pregnancy on different modalities of different modalities, using multi-mode characteristic deep learning train, selecting design base classifier LGBM for classifying and judging, comparing with other machine learning model based on fetal heart rate uterine contraction signal, compared with other traditional machine learning model based on clinical features, compared with the deep learning model combinations of different features, it has better classification performance.
US 20190133536 discloses a decision support tool for predicting the neonatal vitality scores of a fetus during delivery, the scores being an indicator of future health for the infant anticipated to be born within a future time interval, measured as time to birth. The predicted neonatal vitality score is determined from measurements of physiological variables monitored during labor, such as uterine activity and fetal heart rate. Fetal heart rate variability and patterns may be detected and computed using the monitored physiological variables, and neonatal vitality scores may be predicted based, at least in part, on the variability metrics and fetal heart rate patterns. Scores may be predicted for different delivery methods, such as vaginal delivery or cesarean delivery, for different time-to-birth intervals. In this way, these scores may be used for decision support for care plans during labor, such as increased monitoring and/or modifying the delivery type.
WO 2025079365 A1 discloses a pregnancy state estimation device including an information acquisition unit that acquires an electrical activity record which has been derived from a mother and percutaneously measured; an inference unit that infers the pregnancy state of the mother by inputting the electrical activity record into a trained model which sets, as an input, the electrical activity record and sets, as an output, a pregnancy state including information related to at least one of the uterine contractions of the mother and the fetal heart rate in the mother; and an output unit that outputs the pregnancy state generated by the inference unit.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 JONATHON A. SZUMNY whose telephone number is (303) 297-4376. The examiner can normally be reached Monday-Friday 7-5.
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, Jason Dunham, can be reached at 571-272-8109. 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.
/JONATHON A. SZUMNY/Primary Examiner, Art Unit 3686
Prosecution Insights