DETAILED ACTION
Notice to Applicant
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This communication is in response to the amendment filed 4/1/26. Claims 1-20 are pending.
Claim Rejections - 35 USC § 112
The rejections of claims 1-20 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as failing to comply with the written description requirement, as discussed in the previous office action, are hereby withdrawn based upon the incorporation by reference of application 18/395,399. The specification of the incorporated application discloses the features which were the basis of the rejection.
The rejections of claims 1-20, under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite are withdrawn due to the amendment filed on 4/1/26.
The following is a quotation of 35 U.S.C. 112(d):
(d) REFERENCE IN DEPENDENT FORMS.—Subject to subsection (e), a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
The following is a quotation of pre-AIA 35 U.S.C. 112, fourth paragraph:
Subject to the following paragraph [i.e., the fifth paragraph of pre-AIA 35 U.S.C. 112], a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
Claims 2-10 and 12-20 are rejected under 35 U.S.C. 112(d) or pre-AIA 35 U.S.C. 112, 4th paragraph, as being of improper dependent form for failing to further limit the subject matter of the claim upon which it depends, or for failing to include all the limitations of the claim upon which it depends.
In particular, claims 2 and 12 recite: “wherein time-series data comprises electrocardiogram data.” However, independent claims 1 and 11 have been amended to recite “wherein the time-series data comprises an electrocardiogram signal,” a similar, but narrower limitation than the language of claims 2 and 12. Therefore claims 2 and 12 fail to further limit the subject matter of claims 1 and 11 respectively. Applicant may cancel the claim(s), amend the claim(s) to place the claim(s) in proper dependent form, rewrite the claim(s) in independent form, or present a sufficient showing that the dependent claim(s) complies with the statutory requirements.
Claims 3-10 and 13-20 inherit the deficiencies of claims 2 and 12, respectively, through dependency, and are therefore also rejected.
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 a judicial exception (i.e, a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
35 USC 101 enumerates four categories of subject matter that Congress deemed to be appropriate subject matter for a patent: processes, machines, manufactures and compositions of matter. As explained by the courts, these “four categories together describe the exclusive reach of patentable subject matter. If a claim covers material not found in any of the four statutory categories, that claim falls outside the plainly expressed scope of Section 101 even if the subject matter is otherwise new and useful.” In re Nuijten, 500 F.3d 1346, 1354, 84 USPQ2d 1495, 1500 (Fed. Cir. 2007). Step 1 of the eligibility analysis asks: Is the claim to a process, machine, manufacture or composition of matter? Applicant’s claims fall within at least one of the four categories of patent eligible subject matter because claims 1-10 are drawn to a system/apparatus, and claims 11-20 are drawn to a method.
Determining that a claim falls within one of the four enumerated categories of patentable subject matter recited in 35 USC 101 (i.e., process, machine, manufacture, or composition of matter) in Step 1 does not complete the eligibility analysis. Claims drawn only to an abstract idea, a natural phenomenon, and laws of nature are not eligible for patent protection. As described in MPEP 2106, subsection III, Step 2A of the Office’s eligibility analysis is the first part of the Alice/Mayo test, i.e., the Supreme Court’s “framework for distinguishing patents that claim laws of nature, natural phenomena, and abstract ideas from those that claim patent-eligible applications of those concepts.” Alice Corp. Pty. Ltd. v. CLS Bank Int'l,134 S. Ct. 2347, 2355, 110 USPQ2d 1976, 1981 (2014) (citing Mayo, 566 U.S. at 77-78, 101 USPQ2d at 1967-68).
In 2019, the United States Patent and Trademark Office (USPTO) prepared revised guidance (2019 Revised Patent Subject Matter Eligibility Guidance) for use by USPTO personnel in evaluating subject matter eligibility. The framework for this revised guidance, which sets forth the procedures for determining whether a patent claim or patent application claim is directed to a judicial exception (laws of nature, natural phenomena, and abstract ideas), is described in MPEP sections 2106.03 and 2106.04.
As explained in MPEP 2106.04(a)(2), the 2019 Revised Patent Subject Matter Eligibility Guidance explains that abstract ideas can be grouped as, e.g., mathematical concepts, certain methods of organizing human activity, and mental processes. Moreover, this guidance explains that a patent claim or patent application claim that recites a judicial exception is not ‘‘directed to’’ the judicial exception if the judicial exception is integrated into a practical application of the judicial exception. A claim that recites a judicial exception, but is not integrated into a practical application, is directed to the judicial exception under Step 2A and must then be evaluated under Step 2B (inventive concept) to determine the subject matter eligibility of the claim.
Step 2A asks: Does the claim recite a law of nature, a natural phenomenon (product of nature) or an abstract idea? If so, is the judicial exception integrated into a practical application of the judicial exception? A claim recites a judicial exception when a law of nature, a natural phenomenon, or an abstract idea is set forth or described in the claim. While the terms “set forth” and “describe” are thus both equated with “recite”, their different language is intended to indicate that there are different ways in which an exception can be recited in a claim. For instance, the claims in Diehr set forth a mathematical equation in the repetitively calculating step, while the claims in Mayo set forth laws of nature in the wherein clause, meaning that the claims in those cases contained discrete claim language that was identifiable as a judicial exception. The claims in Alice Corp., however, described the concept of intermediated settlement without ever explicitly using the words “intermediated” or “settlement.” A claim that integrates a judicial exception into a practical application will apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception, such that the claim is more than a drafting effort designed to monopolize the judicial exception.
Claims 1-20 recite(s) a method and system for recites an apparatus and method for analyzing time series data using a first and second women’s health model to generate women’s health attribute. As drafted, the claims are directed to mathematical concepts and mathematical relationships, and mental processes.
In particular, the claims 1 and 11 recite a method and system for (mathematical relationships):
generate a first women's health model comprising a machine learning model, wherein generating the first women's health model comprises:
training the first women's health model as a function of the sanitized training data to generate a trained first women's health model; and
training, further and iteratively, the trained first women's health model, wherein the iterative training of the trained first women's health model comprises retraining the trained first women's health model using results of previous iterations of the first women's health model to generate a retrained first women's health model;
input the time-series data into a women's health panel, wherein the women's health panel comprises a plurality of women's health models including the retrained first women's health model and a second women's health model;
generate at least one women's health attribute from the women's health panel as a function of the time-series data and the plurality of women's health models, wherein generating the at least one women's health attribute comprises:
generating, using the retrained first women's health model, a first women's health attribute as a function of the time-series data; and
generating, using the second women's health model, a second women's health attribute;
generate a time series model comprising the time series data;
overlay the at least one recommendation datum onto the time series model, wherein overlaying the at least one recommendation datum onto the time series model comprises superimposing information onto a visual representation of a digital model; (interpreted as a graphing step)
MENTAL PROCESS-ANALYSIS
Moreover, the language of claims 1 and 11 encompasses performance of the limitations(s) in the mind, but for the recitation of generic computer components.
In the instant case, the following limitations cover the performance of the limitations in the mind but for the recitation of generic computer components:
generate at least one time series label as a function of the time series data, wherein the at least one time series label indicates an anomaly;
generate a first women's health model comprising a machine learning model, wherein generating the first women's health model comprises:
training the first women's health model as a function of the sanitized training data to generate a trained first women's health model; and
training, further and iteratively, the trained first women's health model, wherein the iterative training of the trained first women's health model comprises retraining the trained first women's health model using results of previous iterations of the first women's health model to generate a retrained first women's health model;
input the time-series data into a women's health panel, wherein the women's health panel comprises a plurality of women's health models including the retrained first women's health model and a second women's health model;
generate at least one women's health attribute from the women's health panel as a function of the time-series data and the plurality of women's health models, wherein generating the at least one women's health attribute comprises:
generating, using the retrained first women's health model, a first women's health attribute as a function of the time-series data; and generating, using the second women's health model, a second women's health attribute;
determine at least one recommendation datum for the at least one time series label as a function of at least one of the first and second women's health attributes;
generate a time series model comprising the time series data;
Other than reciting “a processor;” “a memory communicatively connected to the at least a processor… contains instructions configuring the at least a processor” to nothing in the claim element precludes the step from practically being performed in the mind.
For example, “generate a first women's health model,” “generate at least one women's health attribute,” in the context of this claim encompasses the user manually reviewing/evaluating patient data, recognizing patterns in the data, and deciding which parameters/ attributes in data should be further evaluated/ analyzed. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas.
As explained in MPEP 2106.04(a)(2)(III), the courts consider a mental process (thinking) that "can be performed in the human mind, or by a human using a pen and paper" to be an abstract idea. CyberSource Corp. v. Retail Decisions, Inc., 654 F.3d 1366, 1372, 99 USPQ2d 1690, 1695 (Fed. Cir. 2011). (emphasis added) As the Federal Circuit explained, "methods which can be performed mentally, or which are the equivalent of human mental work, are unpatentable abstract ideas the ‘basic tools of scientific and technological work’ that are open to all.’" 654 F.3d at 1371, 99 USPQ2d at 1694 (citing Gottschalk v. Benson, 409 U.S. 63, 175 USPQ 673 (1972)). See also Mayo Collaborative Servs. v. Prometheus Labs. Inc., 566 U.S. 66, 71, 101 USPQ2d 1961, 1965 ("‘[M]ental processes[] and abstract intellectual concepts are not patentable, as they are the basic tools of scientific and technological work’" (quoting Benson, 409 U.S. at 67, 175 USPQ at 675)); Parker v. Flook, 437 U.S. 584, 589, 198 USPQ 193, 197 (1978).
Accordingly, the "mental processes" abstract idea grouping is defined as concepts performed in the human mind, and examples of mental processes include observations, evaluations, judgments, and opinions.
The courts do not distinguish between mental processes that are performed entirely in the human mind and mental processes that require a human to use a physical aid (e.g., pen and paper or a slide rule) to perform the claim limitation. See, e.g., Benson, 409 U.S. at 67, 65, 175 USPQ at 674-75, 674 (noting that the claimed "conversion of [binary-coded decimal] numerals to pure binary numerals can be done mentally," i.e., "as a person would do it by head and hand."); Synopsys, Inc. v. Mentor Graphics Corp., 839 F.3d 1138, 1139, 120 USPQ2d 1473, 1474 (Fed. Cir. 2016) (holding that claims to a mental process of "translating a functional description of a logic circuit into a hardware component description of the logic circuit" are directed to an abstract idea, because the claims "read on an individual performing the claimed steps mentally or with pencil and paper").
Moreover, courts do not distinguish between claims that recite mental processes performed by humans and claims that recite mental processes performed on a computer. As the Federal Circuit has explained, "[c]ourts have examined claims that required the use of a computer and still found that the underlying, patent-ineligible invention could be performed via pen and paper or in a person’s mind." Versata Dev. Group v. SAP Am., Inc., 793 F.3d 1306, 1335, 115 USPQ2d 1681, 1702 (Fed. Cir. 2015). See also Intellectual Ventures I LLC v. Symantec Corp., 838 F.3d 1307, 1318, 120 USPQ2d 1353, 1360 (Fed. Cir. 2016) (‘‘[W]ith the exception of generic computer-implemented steps, there is nothing in the claims themselves that foreclose them from being performed by a human, mentally or with pen and paper.’’); Mortgage Grader, Inc. v. First Choice Loan Servs. Inc., 811 F.3d 1314, 1324, 117 USPQ2d 1693, 1699 (Fed. Cir. 2016) (holding that computer-implemented method for "anonymous loan shopping" was an abstract idea because it could be "performed by humans without a computer").
This judicial exception is not integrated into a practical application because the claim language does not recite any improvements to the functioning of a computer, or to any other technology or technical field (See MPEP 2106.04(d)(1); see also MPEP 2106.05(a)(I-II)). Moreover, the claims do not integrate the judicial exception into a practical application because the claimed invention does not: apply the judicial exception with, or by use of, a particular machine (see MPEP 2106.05(b)); effect a transformation or reduction of a particular article to a different state or thing (see MPEP 2106.05(c)); or apply or using the judicial exception in some other meaningful way beyond generally linking the use of the judicial exception to a particular technological environment see MPEP 2106.05(e). (Considerations for integration into a practical application in Step 2A, prong two and for recitation of significantly more than the judicial exception in Step 2B)
While abstract ideas, natural phenomena, and laws of nature are not eligible for patenting by themselves, claims that integrate these exceptions into an inventive concept are thereby transformed into patent-eligible inventions. Alice Corp. Pty. Ltd. v. CLS Bank Int'l, 134 S. Ct. 2347, 2354, 110 USPQ2d 1976, 1981 (2014) (citing Mayo Collaborative Servs. v. Prometheus Labs., Inc., 566 U.S. 66, 71-72, 101 USPQ2d 1961, 1966 (2012)). Thus, the second part of the Alice/Mayo test is often referred to as a search for an inventive concept. Id. An “inventive concept” is furnished by an element or combination of elements that is recited in the claim in addition to (beyond) the judicial exception, and is sufficient to ensure that the claim as a whole amounts to significantly more than the judicial exception itself. Alice Corp., 134 S. Ct. at 2355, 110 USPQ2d at 1981 (citing Mayo, 566 U.S. at 72-73, 101 USPQ2d at 1966). Although the courts often evaluate considerations such as the conventionality of an additional element in the eligibility analysis, the search for an inventive concept should not be confused with a novelty or non-obviousness determination. See Mayo, 566 U.S. at 91, 101 USPQ2d at 1973 (rejecting “the Government’s invitation to substitute Sections 102, 103, and 112 inquiries for the better established inquiry under Section 101”). As made clear by the courts, the “‘novelty’ of any element or steps in a process, or even of the process itself, is of no relevance in determining whether the subject matter of a claim falls within the Section 101 categories of possibly patentable subject matter.” Intellectual Ventures I v. Symantec Corp.,838 F.3d 1307, 1315, 120 USPQ2d 1353, 1358 (Fed. Cir. 2016) (quoting Diamond v. Diehr, 450 U.S. at 188–89, 209 USPQ at 9).
As described in MPEP 2106.05, Step 2B of the Office’s eligibility analysis is the second part of the Alice/Mayo test, i.e., the Supreme Court’s “framework for distinguishing patents that claim laws of nature, natural phenomena, and abstract ideas from those that claim patent-eligible applications of those concepts.” Alice Corp. Pty. Ltd. v. CLS Bank Int'l, 573 U.S. _, 134 S. Ct. 2347, 2355, 110 USPQ2d 1976, 1981 (2014) (citing Mayo, 566 U.S. 66, 101 USPQ2d 1961 (2012)). Step 2B asks: Does the claim recite additional elements that amount to significantly more than the judicial exception? The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
The additional steps amount to insignificant extra-solution activity to the judicial exception (see MPEP 2106.05(g)). Examples of insignificant extra-solution activity include mere data gathering, selecting a particular data source or type of data to be manipulated, and insignificant application. In the instant case, claims 1 and 11 additionally recite: “receive time series data associated with a female classification; input the time-series data into a women’s health panel…” “sanitize the training data configured to perform signal processing operations, wherein sanitizing the training data comprises: determining that at least one training data entry of the training data has a signal to noise ratio below a threshold value; and removing the at least one training data entry from the training data to create sanitized training data” (data gathering and preparation); “circle…, a portion of the time series model as a function of the anomaly.” The additional steps amount to necessary data gathering and outputting, (i.e., all uses of the recited judicial exception require such data gathering or data output). See Mayo, 566 U.S. at 79, 101 USPQ2d at 1968; OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015) (presenting offers and gathering statistics amounted to mere data gathering)
Claims 1 and 11 have been further amended to recite: generate, through a graphical user interface of a display device, a visual element superimposed on the time series model …and wherein the visual element is further associated with an event handler configured to receive a user input in response to the displayed anomaly. The additional steps also amount to insignificant extra-solution activity to the judicial exception (see MPEP 2106.05(g)). As understood by the examiner, the additional step amounts to a display step ((i.e. outputting)
Claim 1 recite(s) additional limitation(s), including: at least a processor; and a memory communicatively connected to the at least a processor. Claims 1 and 11 further recite “a dedicated hardware unit comprising circuitry configured to perform signal processing operations.” The additional components is/are generic components that perform functions which are well-understood, routine and conventional and that amount to no more than implementing the abstract idea with a computerized system.
The generic nature of the computer system used to carryout steps of the recited method is underscored by the system description in the instant application, which discloses: “Processor 804 may include any suitable processor, such as without limitation a processor incorporating logical circuitry for performing arithmetic and logical operations, such as an arithmetic and logic unit (ALU), which may be regulated with a state machine and directed by operational inputs from memory and/or sensors; processor 804 may be organized according to Von Neumann and/or Harvard architecture as a non-limiting example. Processor 804 may include, incorporate, and/or be incorporated in, without limitation, a microcontroller, microprocessor, digital signal processor (DSP), Field Programmable Gate Array (FPGA), Complex Programmable Logic Device (CPLD), Graphical Processing Unit (GPU), general purpose GPU, Tensor Processing Unit (TPU), analog or mixed signal processor, Trusted Platform Module (TPM), a floating point unit (FPU), system on module (SOM), and/or system on a chip (SoC). " (par. 99) The disclosure also states: “Memory 808 may include various components (e.g., machine-readable media) including, but not limited to, a random-access memory component, a read only component, and any combinations thereof. In one example, a basic input/output system 816 (BIOS), including basic routines that help to transfer information between elements within computer system 800, such as during start-up, may be stored in memory 808. Memory 808 may also include (e.g., stored on one or more machine-readable media) instructions (e.g., software) 820 embodying any one or more of the aspects and/or methodologies of the present disclosure. In another example, memory 808 may further include any number of program modules including, but not limited to, an operating system, one or more application programs, other program modules, program data, and any combinations thereof..” (par. 100) Such language underscores that the applicant's perceived invention/ novelty focuses on the computerized implementation of the abstract idea, not the underlying structure of the additional (generic) components.
Claims 2-10 are dependent from Claim 1 and include(s) all the limitations of claim(s) 1. However, the additional limitations of the claims 2-10 fail to recite significantly more than the abstract idea. Claims 2-10 recite additional steps and limitations which further define the abstract idea (i.e. the type of data; type of models additional data manipulation; training; comparing data) and/or recite additional extra-solution activities (i.e. receiving additional time-series data; displaying output in claims in claims 6, 9-10) Therefore, claim(s) 2-10 are also rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
Claims 12-20 are dependent from Claim 11 and include(s) all the limitations of claim(s) 11. However, the additional limitations of the claims 12-20 fail to recite significantly more than the abstract idea. Claims 12-20 recite additional steps and limitations which further define the abstract idea (i.e. the type of data; type of models additional data manipulation; training; comparing data) and/or recite additional extra-solution activities (i.e. receiving additional time-series data; displaying output in claims in claims 16,19-20) Therefore, claim(s) 12-20 are also rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
Because Applicant’s claimed invention recites a judicial exception that is not integrated into a practical application and does not include additional elements that are sufficient to amount to significantly more than the judicial exception itself, the claimed invention is not patent eligible.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-6; 8-16; and 18-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kaur et al (US 20240290496 A1) in view of Upadhyay et al (US 20240206821 A1), and in further view of Davies et al (US 20180292978 A1)
Claim 1. Kaur discloses an apparatus for determining women’s health attributes in time-series data, the apparatus comprising:
at least a processor; and (par. 29- Each device may include one or more processors and memory. Memory may comprise a non-transitory computer readable medium. Instructions stored within memory may be executed by the one or more processors.)
a memory communicatively connected to the at least a processor, wherein the memory contains instructions configuring the at least a processor (par. 29) to:
receive time series data associated with a female classification; (par. 17- assessing Postpartum depression on obstetric patients; par. 35: as data is collected from individual end-users (patients), stored as historical patient data 222 (also referred to herein as historical data) under the user's profile in the user accounts database 220; par. 47-collecting datasets; par. 58-collecting data points at different times),
receive training data, wherein the training data contains a plurality of data entries correlating a plurality of time-series data to a plurality of women's health attributes; (par. 18- (1) receiving, at a mental health risk assessment system, a first training dataset including data representing women during and in the year following pregnancy;
input the time-series data into a women’s health panel wherein the women’s health panel comprises a plurality of women’s health models; (par. 47- as a first set of data (e.g., corresponding to a first window of time) is received for a particular patient via the app 240, an initial prediction 460 may be generated by the prediction model 270. In some embodiments, these predictions can be produced automatically in response to incoming data) and
generate at least one women’s health attribute from the women’s health panel as a function of the time-series data and the plurality of women’s health models, wherein generating the women’s health attribute (Fig. 5; par. 46-48) comprises:
generating, using a first women’s health model, a first women’s health attribute as a function of time series data; (Fig. 5; par. 48-49)-and
generating, using a second women’s health model, a second women’s health attribute. (Fig. 5; par. 49-50)
Claim 1 further recites, but Kaur does not expressly disclose:
generate at least one time series label as a function of the time series data, wherein the at least one time series label indicates an anomaly
sanitize the training data using a dedicated hardware unit comprising circuitry configured to perform signal processing operations, wherein sanitizing the training data comprises:
determining by the dedicated hardware unit that at least one training data entry of the training data has a signal to noise ratio below a threshold value; and
removing the at least one training data entry from the training data to create sanitized training data;
generate a first women's health model comprising a machine learning model, wherein generating the first women's health model comprises:
training the first women's health model as a function of the sanitized training data to generate a trained first women's health model; and
training, further and iteratively, the trained first women's health model, wherein the iterative training of the trained first women's health model comprises retraining the trained first women's health model using results of previous iterations of the first women's health model to generate a retrained first women's health model;
wherein the women's health panel comprises… the retrained first women's health model and a second women's health model
Upadhyay teaches:
generate at least one time series label as a function of the time series data, wherein the at least one time series label indicates an anomaly (par. 22- Time series inputs 108 may be used in the diagnostic process to detect anomalies, patterns, or trends that indicate the presence of a medical condition. For example, an abnormal ECG pattern might suggest a cardiac arrhythmia. Time series inputs 108 may include information from a plurality of electronic health records (EHRs); par. 32: he extracted features are continuously analyzed as new data becomes available. This can involve using a trained machine learning model to detect patterns, anomalies, or specific events related to the physiological indicators 120 of interest. The real-time calculation of physiological indicators 120 can trigger alerts or provide feedback to the user or a healthcare provider. For instance, in a medical setting, abnormal values might trigger an alert, or a fitness wearable might provide immediate feedback to the user during exercise.)
receive training data, wherein the training data contains a plurality of data entries correlating a plurality of time-series data to a plurality of women's health attributes; (abstract: The memory instructs the processor to receive a time series input from a user; par. 23- a time series input 108 may include a plurality of electrocardiogram (ECG) signals 112 from a patient)
sanitize the training data, wherein sanitizing the training data comprises: (par. 60- computer, processor, and/or module may be configured to sanitize training data.; par. 76- FIG. 2, one or more processes or algorithms described above may be performed by at least a dedicated hardware unit 236. A “dedicated hardware unit,” for the purposes of this figure, is a hardware component, circuit… aside from a principal control circuit and/or processor performing method steps)
determining by the dedicated hardware unit that at least one training data entry of the training data has a signal to noise ratio below a threshold value; and (par. 60)
removing the at least one training data entry from the training data to create sanitized training data; (par. 60)
generate a first health model comprising a machine learning model, wherein generating the first health model comprises: (par. 40-generating machine learning model: machine learning plays a crucial role in enhancing the function of software for generating an prediction machine-learning model 124. This may include identifying patterns within the time series input 108 that lead to changes in the capabilities and type of the prediction machine-learning model 124… By applying machine learning techniques, the software can generate the prediction machine-learning model 124 extremely accurately)
training the first health model as a function of the sanitized training data to generate a trained first health model; and (par. 74; par. 76- preconditioning and/or sanitization of training data and/or training a machine-learning algorithm and/or model.)
training, further and iteratively, the trained first health model, wherein the iterative training of the trained first health model comprises retraining the trained first women's health model using results of previous iterations of the first women's health model to generate a retrained first women's health model; (par. 92-94: training and iterative retraining and fine tuning of a model: shown in FIG. 7, the model 703 can be updated or fine-tuned when an unknown, new, unlabeled data set 705 is added (760). The trained model 703 is run on the new data set 705 to calculate the estimated continuous value and uncertainty for each sample. A subset of K samples with the highest uncertainty is selected to create a new/uncertain dataset 706 (761). The training set 701 and the new/uncertain data set 706 can then be combined to create a mixed dataset 707 (762), and this mixed data set 707 can be used to finetune the model 703 (763).)
wherein the women's health panel comprises… the retrained first women's health model and a second women's health model (par. 57; par. 77: inputting time series data; par. 73-74: retraining and/or additional training may be performed using any process for training described above, using any currently or previously deployed version of a machine-learning model and/or algorithm as a starting point. Training data for retraining may be collected, preconditioned, sorted, classified, sanitized or otherwise processed according to any process described in this disclosure)
determine at least one recommendation datum for the at least one time series label as a function of at least one of the first and second women's health attributes; (par. 53- Relevant features may be extracted from the physiological indicator 120, such as peaks, trends, or statistical metrics. These features can help in characterizing the physiological parameter. In an embodiment, algorithms and machine learning techniques can be applied to recognize patterns and anomalies within the data. For instance, identifying irregular heart rhythms or unusual temperature fluctuations. The processor 104 may compare the collected physiological indicator 120 to reference data or established norms to assess whether the measurements fall within expected ranges; par. 56)
generate a time series model comprising the time series data; (par. 65-66; par. 70)
overlay the at least one recommendation datum onto the time series model, wherein overlaying the at least one recommendation datum onto the time series model comprises superimposing information onto a visual representation of a digital model; and (par. 70-developing models and assessing fitness; Fig. 6; par. 84-85)
circle, using the at least a processor, a portion of the time series model as a function of the anomaly.(par. 87-89)
At the time of filing, it would have been obvious to one of ordinary skill in the art to modify the method/system of Kaur with the teachings of Upadhyay to include details on pre-processing/sanitizing training data, and on refining of trained models to generate multiple women’s health models. As suggested by Upadhyay, one would have been motivated to include these features to generated a model(s) that becomes/become more responsive to user needs and preferences and enables the machine learning model to deliver more personalized and relevant results, ultimately enhancing the overall user experience. (Upadhyay: par. 41)
Claim 1 further recites: wherein the time-series data comprises an electrocardiogram signal; and generate, through a graphical user interface of a display device, a visual element superimposed on the time series model, wherein the visual element identifies a specific portion of the electrocardiogram signal corresponding to the anomaly, wherein the anomaly comprises a deformation in at least one waveform component of the electrocardiogram signal, and wherein the visual element is further associated with an event handler configured to receive a user input in response to the displayed anomaly.
Kaur does not disclose, but Upadhyay teaches a method and system wherein the time-series data comprises an electrocardiogram signal (par. 23-25: a time series input 108 may include a plurality of electrocardiogram (ECG) signals 112 from a patient. As used in the current disclosure, a “electrocardiogram signal” is a signal representative of electrical activity of heart. The ECG signal 112 may consist of several distinct waves and intervals, each representing a different phase of the cardiac cycle.) At the time of the effective filing date, it would have been obvious to one ordinary skill in the art to modify the method /system of Kaur with the teaching of to include time series data on ECG, with the motivation of helping diagnose various heart conditions and gaining valuable insights into the complex temporal dynamics of cardiac activities and aids in understanding cardiac function, pathology, and treatment evaluation. (Upadhyay :par. 24).
Kaur and Upadhyay do not expressly disclose, but Davies teaches generating via a GUI of a display device, a visual overlay of time series data, wherein the visual overlay element includes annotations/ comments, which identifies an anomaly in the results/displayed information (par. 60; par. 68-69- data may be highlighted by changing a text color, changing a background color, changing a text format (for example, bolding, italicizing or changing typeface), using an indicator (for example, a pointer, box or balloon), using an animation, animating an existing feature, or overlaying an indicator or other feature; Fig. 3; Fig. 6 par. 73- encircled data point highlighted by the system (102); par. 104-108). Davies further discloses wherein the visual element is further associated with an event handler configured to receive a user input in response to the displayed anomaly. (par. 108-109: the highlighting circuitry 28 is configured to change the scale of one or more of the time based panels in dependence on the selection of a time range on a different one of the time based panels… the selection circuitry 26 receives a selection of a time range in presentation panel 110 and alters a scale of the plots of presentation panels 114 and 116 such that they only show the selected time range.) At the time of the effective filing date, it would have been obvious to one of ordinary skill in the art to further modify the system and method of Kaur and Upadhyay in combination with the teaching of Davies to generate, through a graphical user interface of a display device, a visual element superimposed on the time series model, wherein the visual element identifies a specific portion of the electrocardiogram signal corresponding to the anomaly comprising a deformation in at least one waveform component of the electrocardiogram signal, and to include an event handler configured to receive a user input in response to the displayed anomaly.
As suggested by Davies, one would have been motivated to include these features to facilitate a user easily switching between different displays that align best with one or more clinical tasks, while avoiding an effort in re-finding a record of interest in a new context. (Davies: par. 6)
Claim 2 Kaur teaches the method/apparatus of claim 1, as explained but does not expressly disclose that the time-series data comprises electrocardiogram data.
Upadhyay teaches a method/apparatus wherein the time-series data comprises electrocardiogram data. (par. 22- his temporal aspect allows healthcare professionals to track changes in a patient's condition over time. Time series inputs 108 may encompass various types of data, such as vital signs (e.g., heart rate, blood pressure, temperature), electrocardiograms (ECG), electroencephalograms (EEG), lab test results, imaging data (e.g., MRI or CT scans), pulse oximetry, blood pressure and more) At the time of the effective filing date, it would have been obvious to one ordinary skill in the art to modify the method/apparatus of Kaur with the teaching of Upadhyay to incorporate time series data that includes ECG data, with the motivation of gaining a comprehensive view of a patient’s health and diagnosing possible heart conditions, such as arrhythmias, myocardial infarction (heart attack), conduction abnormalities, and electrolyte imbalances. (par. 22, par. 23)
Claim 3 Kaur and Upadhyay in combination teach the method/apparatus of claim 2, as explained. Kaur further discloses that the apparatus includes a device with sensors. (Kaur: par. 29-devices with sensors)
Kaur does not expressly disclose, but Upadhyay teaches wherein the apparatus further comprises a measurement device, wherein the measurement device comprises one or more transducers. (par. 22, par. 25-ECG with electrodes, sensors) At the time of the effective filing date, it would have been obvious to one ordinary skill in the art to modify the method/apparatus of Kaur with the teaching of Upadhyay to include a measurement device, wherein the measurement device comprises one or more transducers. One would have been motivated to include these features to facilitate recording of physiological, clinical, or health-related parameter observations or measurements which are essential for monitoring, diagnosing, and treating medical conditions. (Upadhyay: par. 22)
Claim 4. Kaur and Upadhyay in combination teach the method/apparatus of claim 2, as explained.
Kaur does not disclose, but Upadhyay teaches an apparatus, wherein the plurality of models comprises a loss function, (par. 35- processor 104 may address class imbalance is by using a weighted loss function. In this approach, you assign different weights to each class, typically giving more weight to the minority class when training a machine-learning model; par. 66) and the instructions further configure the at least a processor to generate a confidence score as a function of the time-series data and at least one of the first health model and the second health model (par. 45-46: uncertainty score/ confidence score for data points- Processor 104 may generate an uncertainty metric 140 based on the model's prediction confidence, such as variance, entropy, or Bayesian probabilities; par. 48: adjust the confidence scores or probabilities generated by a model to make them better reflect the true uncertainty or reliability of the model's predictions; See also: par. 66- supervised learning algorithm may include time series inputs 108…, physiological indicators 120 as outputs, and a scoring function representing a desired form of relationship to be detected between inputs and outputs; scoring function may… seek to maximize the probability that a given input and/or combination of elements inputs is associated with a given output to minimize the probability that a given input is not associated with a given output. Scoring function may be expressed as a risk function representing an “expected loss” of an algorithm relating inputs to outputs, where loss is computed as an error function representing a degree to which a prediction generated by the relation is incorrect when compared to a given input-output pair provided in training data 204).
At the time of the effective filing date, it would have been obvious to one ordinary skill in the art to modify the method/apparatus of Kaur with the teaching of Upadhyay to incorporate the use of a loss function and confidence scores, with the motivation of determining the uncertainty of a given model/ set of models and to ultimately increase the confidence in its/their predictions. (Upadhyay: par. 48)
Claim 5 Kaur teaches the apparatus of claim 2, wherein the plurality of women’s health models comprises a women’s health classifier model (Kaur: par. 32-33; par. 38), a women’s health prediction model,(par. 30-31) and a women’s health correlation model. (par. 31; par. 50-53- assigning and adjusting weights to variables)
Claim 6. Kaur teaches the apparatus of claim 2, wherein training the women’s health model comprises: receiving a plurality of time-series data examples associated with the female classification (Fig. 1 (110); See also par. 57) ; pretraining the women’s health model in the women’s health panel as a function of the plurality of time-series data examples by adjusting one or more parameter attributes of the women’s health model; (par. 27; par. 30-33) and training the women’s health model as a function of the parameter attributes and a database. (par. 30-32- the training module 276 incorporates a digital matrix of time-bound variables that is created and stored in the database (e.g., knowledge repository 280)).
Claim 8. Kaur teaches the apparatus of claim 2, wherein the women’s health attribute comprises a women’s health deviation, wherein the women’s health deviation comprises a change in the women’s health attribute. (par. 38; par. 41-42: gathering and evaluating changes in data collected over time; par. 49-52)
Claim 9. Kaur teaches the apparatus of claim 2, wherein inputting the time-series data into the women’s health panel comprises selecting the women’s health model from a plurality of women’s health models as a function of an input and a graphical user interface. (par. 37-39: ML techniques can include one or more of the following features: executing automated time-series process segmentation includes processing each of the two or more time-series data sequences using a deep learning (DL) model provided as one of a bidirectional long short-term memory (LSTM) sequence classifier using supervised learning, and an autoencoder using unsupervised learning; the at least one time-series transformation includes one or more of a temporal transformation, a spectral transformation, a shape transformation, a statistical transformation, an autoencoder transformation, and a decomposition transformation, a pass-through transformation, processing each feature data set through a reinforcement learning framework; Par. 57)
Claim 10 Kaur and Upadhyay in combination teach the apparatus of claim 2, as explained in the rejection of claim 2. Kaur does not disclose wherein the apparatus is further configured to display the at least one women's health attribute, wherein displaying the women’s health attribute comprises: comparing the at least one women’s health attribute to a nominal women’s health attribute; and displaying the women’s health attribute as a function of the comparison.
Upadhyay teaches wherein the apparatus is further configured to display the at least one women's health attribute, and wherein the displaying the at least one attribute comprises comparing subject health attributes to nominal health attributes, and displaying this information as a function of the comparison. (par. 53- The processor 104 may compare the collected physiological indicator 120 to reference data or established norms to assess whether the measurements fall within expected ranges. Processors 104 may use specialized diagnostic algorithms, which consider multiple parameters and historical data to make informed assessments. These algorithms can be based on clinical guidelines or specific domain knowledge. In some embodiments, if an abnormality or diagnostic insight is detected, the processor may generate a diagnostic report.)
At the time of the effective filing date, it would have been obvious to one ordinary skill in the art to modify the method/apparatus of Kaur with the teaching of Upadhyay to include comparing the women’s health attribute to a nominal women’s health attribute; and displaying the women’s health attribute as a function of the comparison. One would have been motivated to include these features to consider multiple parameters and historical data to make informed assessments about the patient's condition, potential diagnoses, and recommended actions. (par. 53)
claim 11 Kaur discloses a method for determining women’s health attributes in time-series data, the method comprising:
receiving time-series data associated with a female classification; (par. 17- assessing Postpartum depression on obstetric patients; par. 35: as data is collected from individual end-users (patients), stored as historical patient data 222 (also referred to herein as historical data) under the user's profile in the user accounts database 220; par. 47-collecting datasets)
receiving training data, wherein the training data contains a plurality of data entries correlating a plurality of time-series data to a plurality of women's health attributes; (par. 18- (1) receiving, at a mental health risk assessment system, a first training dataset including data representing women during and in the year following pregnancy;
inputting the time-series data into a women’s health panel wherein the women’s health panel comprises of a plurality of women’s health models; and (par. 47- as a first set of data (e.g., corresponding to a first window of time) is received for a particular patient via the app 240, an initial prediction 460 may be generated by the prediction model 270. In some embodiments, these predictions can be produced automatically in response to incoming data)
generating at least one women’s health attribute from the women’s health panel as a function of the time-series data and the plurality of women’s health models, wherein generating the women’s health attribute (Fig. 5; par. 46-48) comprises:
generating, using a first women’s health model, a first women’s health attribute as a function of time series data; (Fig. 5; par. 48-49)-and
generating, using a second women’s health model, a second women’s health attribute. (Fig. 5; par. 49-50)
Claim 11 has been amended to further recite, but Kaur does not expressly disclose:
generate at least one time series label as a function of the time series data, wherein the at least one time series label indicates an anomaly
sanitize the training data using a dedicated hardware unit comprising circuitry configured to perform signal processing operations, wherein sanitizing the training data comprises:
determining by the dedicated hardware unit that at least one training data entry of the training data has a signal to noise ratio below a threshold value; and
removing the at least one training data entry from the training data to create sanitized training data;
generate a first women's health model comprising a machine learning model, wherein generating the first women's health model comprises:
training the first women's health model as a function of the sanitized training data to generate a trained first women's health model; and
training, further and iteratively, the trained first women's health model, wherein the iterative training of the trained first women's health model comprises retraining the trained first women's health model using results of previous iterations of the first women's health model to generate a retrained first women's health model;
wherein the women's health panel comprises… the retrained first women's health model and a second women's health model
Upadhyay teaches:
generate at least one time series label as a function of the time series data, wherein the at least one time series label indicates an anomaly (par. 22- Time series inputs 108 may be used in the diagnostic process to detect anomalies, patterns, or trends that indicate the presence of a medical condition. For example, an abnormal ECG pattern might suggest a cardiac arrhythmia. Time series inputs 108 may include information from a plurality of electronic health records (EHRs); par. 32: he extracted features are continuously analyzed as new data becomes available. This can involve using a trained machine learning model to detect patterns, anomalies, or specific events related to the physiological indicators 120 of interest. The real-time calculation of physiological indicators 120 can trigger alerts or provide feedback to the user or a healthcare provider. For instance, in a medical setting, abnormal values might trigger an alert, or a fitness wearable might provide immediate feedback to the user during exercise.)
receive training data, wherein the training data contains a plurality of data entries correlating a plurality of time-series data to a plurality of women's health attributes; (abstract: The memory instructs the processor to receive a time series input from a user; par. 23- a time series input 108 may include a plurality of electrocardiogram (ECG) signals 112 from a patient)
sanitize the training data using a dedicated hardware unit comprising circuitry configured to perform signal processing operations, wherein sanitizing the training data comprises: (par. 60- computer, processor, and/or module may be configured to sanitize training data.; par. 76- FIG. 2, one or more processes or algorithms described above may be performed by at least a dedicated hardware unit 236. A “dedicated hardware unit,” for the purposes of this figure, is a hardware component, circuit… aside from a principal control circuit and/or processor performing method steps)
determining by the dedicated hardware unit that at least one training data entry of the training data has a signal to noise ratio below a threshold value; and (par. 60)
removing the at least one training data entry from the training data to create sanitized training data; (par. 60)
generate a first health model comprising a machine learning model, wherein generating the first health model comprises: (par. 40-generating machine learning model: machine learning plays a crucial role in enhancing the function of software for generating an prediction machine-learning model 124. This may include identifying patterns within the time series input 108 that lead to changes in the capabilities and type of the prediction machine-learning model 124… By applying machine learning techniques, the software can generate the prediction machine-learning model 124 extremely accurately)
training the first health model as a function of the sanitized training data to generate a trained first health model; and (par. 74; par. 76- preconditioning and/or sanitization of training data and/or training a machine-learning algorithm and/or model.)
training, further and iteratively, the trained first health model, wherein the iterative training of the trained first health model comprises retraining the trained first women's health model using results of previous iterations of the first women's health model to generate a retrained first women's health model; (par. 92-94: training and iterative retraining and fine tuning of a model: shown in FIG. 7, the model 703 can be updated or fine-tuned when an unknown, new, unlabeled data set 705 is added (760). The trained model 703 is run on the new data set 705 to calculate the estimated continuous value and uncertainty for each sample. A subset of K samples with the highest uncertainty is selected to create a new/uncertain dataset 706 (761). The training set 701 and the new/uncertain data set 706 can then be combined to create a mixed dataset 707 (762), and this mixed data set 707 can be used to finetune the model 703 (763).)
wherein the women's health panel comprises… the retrained first women's health model and a second women's health model (par. 57; par. 77: inputting time series data; par. 73-74: retraining and/or additional training may be performed using any process for training described above, using any currently or previously deployed version of a machine-learning model and/or algorithm as a starting point. Training data for retraining may be collected, preconditioned, sorted, classified, sanitized or otherwise processed according to any process described in this disclosure)
determine at least one recommendation datum for the at least one time series label as a function of at least one of the first and second women's health attributes; (par. 53- Relevant features may be extracted from the physiological indicator 120, such as peaks, trends, or statistical metrics. These features can help in characterizing the physiological parameter. In an embodiment, algorithms and machine learning techniques can be applied to recognize patterns and anomalies within the data. For instance, identifying irregular heart rhythms or unusual temperature fluctuations. The processor 104 may compare the collected physiological indicator 120 to reference data or established norms to assess whether the measurements fall within expected ranges; par. 56)
generate a time series model comprising the time series data; (par. 65-66; par. 70)
overlay the at least one recommendation datum onto the time series model, wherein overlaying the at least one recommendation datum onto the time series model comprises superimposing information onto a visual representation of a digital model; and (par. 70-developing models and assessing fitness; Fig. 6; par. 84-85)
circle, using the at least a processor, a portion of the time series model as a function of the anomaly.(par. 87-89)
At the time of filing, it would have been obvious to one of ordinary skill in the art to modify the method/system of Kaur with the teachings of Upadhyay to include details on pre-processing/sanitizing training data, and on refining of trained models to generate multiple women’s health models. As suggested by Upadhyay, one would have been motivated to include these features to generated a model(s) that becomes/become more responsive to user needs and preferences and enables the machine learning model to deliver more personalized and relevant results, ultimately enhancing the overall user experience. (Upadhyay: par. 41)
Claim 11 further recites: wherein the time-series data comprises an electrocardiogram signal; and generate, through a graphical user interface of a display device, a visual element superimposed on the time series model, wherein the visual element identifies a specific portion of the electrocardiogram signal corresponding to the anomaly, wherein the anomaly comprises a deformation in at least one waveform component of the electrocardiogram signal, and wherein the visual element is further associated with an event handler configured to receive a user input in response to the displayed anomaly.
Kaur does not disclose, but Upadhyay teaches a method and system wherein the time-series data comprises an electrocardiogram signal (par. 23-25: a time series input 108 may include a plurality of electrocardiogram (ECG) signals 112 from a patient. As used in the current disclosure, a “electrocardiogram signal” is a signal representative of electrical activity of heart. The ECG signal 112 may consist of several distinct waves and intervals, each representing a different phase of the cardiac cycle.) At the time of the effective filing date, it would have been obvious to one ordinary skill in the art to modify the method /system of Kaur with the teaching of to include time series data on ECG, with the motivation of helping diagnose various heart conditions and gaining valuable insights into the complex temporal dynamics of cardiac activities and aids in understanding cardiac function, pathology, and treatment evaluation. (Upadhyay :par. 24).
Kaur and Upadhyay do not expressly disclose, but Davies teaches generating via a GUI of a display device, a visual overlay of time series data, wherein the visual overlay element includes annotations/ comments, which identifies an anomaly in the results/displayed information (par. 60; par. 68-69- data may be highlighted by changing a text color, changing a background color, changing a text format (for example, bolding, italicizing or changing typeface), using an indicator (for example, a pointer, box or balloon), using an animation, animating an existing feature, or overlaying an indicator or other feature; Fig. 3; Fig. 6 par. 73- encircled data point highlighted by the system (102); par. 104-108). Davies further discloses wherein the visual element is further associated with an event handler configured to receive a user input in response to the displayed anomaly. (par. 108-109: the highlighting circuitry 28 is configured to change the scale of one or more of the time based panels in dependence on the selection of a time range on a different one of the time based panels… the selection circuitry 26 receives a selection of a time range in presentation panel 110 and alters a scale of the plots of presentation panels 114 and 116 such that they only show the selected time range.)
At the time of the effective filing date, it would have been obvious to one of ordinary skill in the art to further modify the system and method of Kaur and Upadhyay in combination with the teaching of Davies to generate, through a graphical user interface of a display device, a visual element superimposed on the time series model, wherein the visual element identifies a specific portion of the electrocardiogram signal corresponding to the anomaly comprising a deformation in at least one waveform component of the electrocardiogram signal, and to include an event handler configured to receive a user input in response to the displayed anomaly.
As suggested by Davies, one would have been motivated to include these features to facilitate a user easily switching between different displays that align best with one or more clinical tasks, while avoiding an effort in re-finding a record of interest in a new context. (Davies: par. 6)
Claim 12 Kaur teaches the method of claim 11, as explained but does not expressly disclose that the time-series data comprises electrocardiogram data.
Upadhyay teaches a method/apparatus wherein the time-series data comprises electrocardiogram data. (par. 22- his temporal aspect allows healthcare professionals to track changes in a patient's condition over time. Time series inputs 108 may encompass various types of data, such as vital signs (e.g., heart rate, blood pressure, temperature), electrocardiograms (ECG), electroencephalograms (EEG), lab test results, imaging data (e.g., MRI or CT scans), pulse oximetry, blood pressure and more) At the time of the effective filing date, it would have been obvious to one ordinary skill in the art to modify the method/apparatus of Kaur with the teaching of Upadhyay to incorporate time series data that includes ECG data, with the motivation of gaining a comprehensive view of a patient’s health and diagnosing possible heart conditions, such as arrhythmias, myocardial infarction (heart attack), conduction abnormalities, and electrolyte imbalances. (par. 22, par. 23)
Claim 13. Kaur and Upadhyay in combination teach the method/apparatus of claim 12, as explained. Kaur further discloses that the apparatus includes a device with sensors. (Kaur: par. 29-devices with sensors)
Kaur does not expressly disclose, but Upadhyay teaches wherein the apparatus further comprises a measurement device, wherein the measurement device comprises one or more transducers. (par. 22, par. 25-ECG with electrodes, sensors) At the time of the effective filing date, it would have been obvious to one ordinary skill in the art to modify the method/apparatus of Kaur with the teaching of Upadhyay to include a measurement device, wherein the measurement device comprises one or more transducers. One would have been motivated to include these features to facilitate recording of physiological, clinical, or health-related parameter observations or measurements which are essential for monitoring, diagnosing, and treating medical conditions. (Upadhyay: par. 22)
Claim 14. Kaur and Upadhyay in combination teach the method/apparatus of claim 12, as explained.
Kaur does not disclose, but Upadhyay teaches an apparatus and method, wherein the plurality of models comprises a loss function, (par. 35- processor 104 may address class imbalance is by using a weighted loss function. In this approach, you assign different weights to each class, typically giving more weight to the minority class when training a machine-learning model; par. 66) and the instructions further configure the at least a processor to generate a confidence score as a function of the time-series data and at least one of the first health model and the second health model (par. 45-46: uncertainty score/ confidence score for data points- Processor 104 may generate an uncertainty metric 140 based on the model's prediction confidence, such as variance, entropy, or Bayesian probabilities; par. 48: adjust the confidence scores or probabilities generated by a model to make them better reflect the true uncertainty or reliability of the model's predictions; See also: par. 66- supervised learning algorithm may include time series inputs 108…, physiological indicators 120 as outputs, and a scoring function representing a desired form of relationship to be detected between inputs and outputs; scoring function may… seek to maximize the probability that a given input and/or combination of elements inputs is associated with a given output to minimize the probability that a given input is not associated with a given output. Scoring function may be expressed as a risk function representing an “expected loss” of an algorithm relating inputs to outputs, where loss is computed as an error function representing a degree to which a prediction generated by the relation is incorrect when compared to a given input-output pair provided in training data 204).
At the time of the effective filing date, it would have been obvious to one ordinary skill in the art to modify the method/apparatus of Kaur with the teaching of Upadhyay to incorporate the use of a loss function and confidence scores, with the motivation of determining the uncertainty of a given model/ set of models and to ultimately increase the confidence in its/their predictions. (Upadhyay: par. 48)
Claim 15. Kaur teaches the apparatus/method of claim 12, wherein the plurality of women’s health models comprises a women’s health classifier model (Kaur: par. 32-33; par. 38), a women’s health prediction model,(par. 30-31) and a women’s health correlation model. (par. 31; par. 50-53- assigning and adjusting weights to variables)
Claim 16. Kaur teaches the method of claim 12, wherein training the women’s health model comprises: receiving a plurality of time-series data examples associated with the female classification (Fig. 1 (110); See also par. 57) ; pretraining the women’s health model in the women’s health panel as a function of the plurality of time-series data examples by adjusting one or more parameter attributes of the women’s health model; (par. 27; par. 30-33) and training the women’s health model as a function of the parameter attributes and a database. (par. 30-32- the training module 276 incorporates a digital matrix of time-bound variables that is created and stored in the database (e.g., knowledge repository 280)).
Claim 18. Kaur teaches the method of claim 12, wherein the at least one women’s health attribute comprises a women’s health attribute deviation, wherein the women’s health attribute deviation comprises a change in the at least one women’s health attribute. (par. 38; par. 41-42: gathering and evaluating changes in data collected over time; par. 49-52)
Claim 19. Kaur teaches the method of claim 12, wherein inputting the time-series data into the women’s health panel comprises selecting the women’s health model from a plurality of women’s health models as a function of an input and a graphical user interface. (par. 37-39: ML techniques can include one or more of the following features: executing automated time-series process segmentation includes processing each of the two or more time-series data sequences using a deep learning (DL) model provided as one of a bidirectional long short-term memory (LSTM) sequence classifier using supervised learning, and an autoencoder using unsupervised learning; the at least one time-series transformation includes one or more of a temporal transformation, a spectral transformation, a shape transformation, a statistical transformation, an autoencoder transformation, and a decomposition transformation, a pass-through transformation, processing each feature data set through a reinforcement learning framework; Par. 57)
Claim 20 Kaur and Upadhyay in combination teach the method of claim 12. Kaur does not disclose wherein displaying the at least one women’s health attribute comprises: comparing the women’s health attribute to a nominal women’s health attribute; and displaying the women’s health attribute as a function of the comparison.
Upadhyay teaches comparing subject health attributes to nominal health attributes, and displaying this information as a function of the comparison. (par. 53- The processor 104 may compare the collected physiological indicator 120 to reference data or established norms to assess whether the measurements fall within expected ranges. Processors 104 may use specialized diagnostic algorithms, which consider multiple parameters and historical data to make informed assessments. These algorithms can be based on clinical guidelines or specific domain knowledge. In some embodiments, if an abnormality or diagnostic insight is detected, the processor may generate a diagnostic report.)
At the time of the effective filing date, it would have been obvious to one ordinary skill in the art to modify the method/apparatus of Kaur with the teaching of Upadhyay to include comparing the women’s health attribute to a nominal women’s health attribute; and displaying the women’s health attribute as a function of the comparison. One would have been motivated to include these features to consider multiple parameters and historical data to make informed assessments about the patient's condition, potential diagnoses, and recommended actions. (par. 53)
Claim(s) 7 and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kaur et al (US 20240290496 A1), Upadhyay et al (US 20240206821 A1), and Davies (US 20180292978 A1) as applied to claims 1-2 and 11-12, and in further view of Rosenweig et al ( US 20200031940 A1)
Claims 7 and 17 Kaur and Upadhyay in combination disclose the apparatus of claim 2/ method of claim 12 as explained in the rejections of claim 2 and claim 12. Kaur and Upadhyay do not expressly disclose wherein the first women’s health attribute comprises a peripartum cardiomyopathy attribute, and the second women’s health attribute comprises a coronary heart disease attribute.
Rosenzweig teaches a method and system for assessing the risks for peripartum cardiomyopathy and coronary heart disease (par. 8-9; par. 197) At the time of the effective filing date, it would have been obvious to one ordinary skill in the art to further modify the method/apparatus of Kaur and Upadhyay in combination with the teaching of Rosenzweig, to include evaluation of first women’s health attributes comprising a peripartum cardiomyopathy attribute, and a coronary heart disease attribute. One would have been motivated to include these features to gain a comprehensive view of a patient’s health and diagnosing possible heart conditions, which may contribute to heart failure. (par. 2, par. 6)
Response to Arguments
Applicant's arguments filed 4/1/26 have been fully considered but they are not persuasive.
Applicant argues the claim rejections under 35 USC 112 have been overcome in light of the amendments.
In response, the previously identified issues raised regarding 35 USC 112(a) and (b) have been withdrawn in light of applicant’s response and the claim amendments filed on 4/1/26.
However, applicant’s response has raised addition issues under 35 USC 112(d), which have been explained under the 112 heading in the current office action.
(B) Applicant argues that the rejections of the claims under 35 USC 101. Applicant argues that the claims as amended are patent eligible.
In response, the examiner respectfully disagrees. The claim amendments are noted. However, the additional claim language is not sufficient to render the claims patent eligible. The newly added claim limitations recite insignificant extra-solution activity, as it amounts to a display step. As such, the claims are drawn a judicial exception without reciting substantially more, and without integrating the judicial exception into a practical application. The rejection has been updated to reflect the amended claim language.
The judicial exception is not integrated into a practical application because the claim language does not recite any improvements to the functioning of a computer, or to any other technology or technical field (See MPEP 2106.04(d)(1); see also MPEP 2106.05(a)(I-II)). Moreover, the claims do not integrate the judicial exception into a practical application because the claimed invention does not: apply the judicial exception with, or by use of, a particular machine (see MPEP 2106.05(b)); effect a transformation or reduction of a particular article to a different state or thing (see MPEP 2106.05(c)); or apply or using the judicial exception in some other meaningful way beyond generally linking the use of the judicial exception to a particular technological environment see MPEP 2106.05(e). (Considerations for integration into a practical application in Step 2A, prong two and for recitation of significantly more than the judicial exception in Step 2B)
(C) Applicant argues that the claims do not recite mental processes, or mathematical concepts.
In response, the examiner disagrees. The Examiner disagrees that the claims do not recite mathematical concepts and mental processes for the reasons set forth in the updated 101 rejection. As previously stated, the applicant’s amended claim language is noted. Namely, applicant argues that the newly added step: “generate, through a graphical user interface of a display device, a visual element superimposed on the time series model …and wherein the visual element is further associated with an event handler configured to receive a user input in response to the displayed anomaly,” cannot be performed in the human mind, and that the claims are therefore recite more than a mental process.
However, as understood by the examiner the additional step amounts to a display step ((i.e. outputting). As such the additional steps also amount to insignificant extra-solution activity to the judicial exception (see MPEP 2106.05(g)). Moreover, The courts do not distinguish between mental processes that are performed entirely in the human mind and mental processes that require a human to use a physical aid (e.g., pen and paper or a slide rule) to perform the claim limitation. See, e.g., Benson, 409 U.S. at 67, 65, 175 USPQ at 674-75, 674 (noting that the claimed "conversion of [binary-coded decimal] numerals to pure binary numerals can be done mentally," i.e., "as a person would do it by head and hand."); Synopsys, Inc. v. Mentor Graphics Corp., 839 F.3d 1138, 1139, 120 USPQ2d 1473, 1474 (Fed. Cir. 2016) (holding that claims to a mental process of "translating a functional description of a logic circuit into a hardware component description of the logic circuit" are directed to an abstract idea, because the claims "read on an individual performing the claimed steps mentally or with pencil and paper").
Moreover, as explained in the current rejection, courts do not distinguish between claims that recite mental processes performed by humans and claims that recite mental processes performed on a computer. As the Federal Circuit has explained, "[c]ourts have examined claims that required the use of a computer and still found that the underlying, patent-ineligible invention could be performed via pen and paper or in a person’s mind." Versata Dev. Group v. SAP Am., Inc., 793 F.3d 1306, 1335, 115 USPQ2d 1681, 1702 (Fed. Cir. 2015). See also Intellectual Ventures I LLC v. Symantec Corp., 838 F.3d 1307, 1318, 120 USPQ2d 1353, 1360 (Fed. Cir. 2016) (‘‘[W]ith the exception of generic computer-implemented steps, there is nothing in the claims themselves that foreclose them from being performed by a human, mentally or with pen and paper.’’); Mortgage Grader, Inc. v. First Choice Loan Servs. Inc., 811 F.3d 1314, 1324, 117 USPQ2d 1693, 1699 (Fed. Cir. 2016) (holding that computer-implemented method for "anonymous loan shopping" was an abstract idea because it could be "performed by humans without a computer").
(D) Applicant argues that “visual element” is not merely displaying data, it generates a computer-rendered graphical object superimposed on a time-series model.
In response, the applicant’s argued interpretation of the “visual element” is much narrower than that required by the claim language or explained in the applicant’s disclosure. More specifically, the specification of the instant application states: “a “visual element” is any individual component that expresses an idea and/or conveys a message. A visual element may include visual data such as, but not limited to, images, colors, shapes, lines, arrows, icons, photographs, infographics, text, any combinations thereof, and the like. A visual element may include any data transmitted to display device, client device, and/or graphical user interface.”
Moreover, the limitation “associated with an event handler to receive user input” is broad, and may be interpreted as a displayed element which is linked to a prompt or input elsewhere on the screen. Additionally, the event handler is being further defined, not the “visual element,” and the additional description of the event handler is an intended use limitation.
(E) Applicant argues that a claimed invention represents an improvement to technology, and refines the functionality of systems that display physiological data.
In response, the examiner disagrees. In accordance with MPEP 2106.05 (a), if it is asserted that the invention improves upon conventional functioning of a computer, or upon conventional technology or technological processes, a technical explanation as to how to implement the invention should be present in the specification. That is, the disclosure must provide sufficient details such that one of ordinary skill in the art would recognize the claimed invention as providing an improvement. An indication that the claimed invention provides an improvement can include a discussion in the specification that identifies a technical problem and explains the details of an unconventional technical solution expressed in the claim, or identifies technical improvements realized by the claim over the prior art.
For example, in McRO, the court relied on the specification’s explanation of how the particular rules recited in the claim enabled the automation of specific animation tasks that previously could only be performed subjectively by humans, when determining that the claims were directed to improvements in computer animation instead of an abstract idea. McRO, 837 F.3d at 1313-14, 120 USPQ2d at 1100-01. In contrast, the court in Affinity Labs of Tex. v. DirecTV, LLC relied on the specification’s failure to provide details regarding the manner in which the invention accomplished the alleged improvement when holding the claimed methods of delivering broadcast content to cellphones ineligible. 838 F.3d 1253, 1263-64, 120 USPQ2d 1201, 1207-08 (Fed. Cir. 2016).
An important consideration in determining whether a claim is directed to an improvement in technology is the extent to which the claim covers a particular solution to a problem or a particular way to achieve a desired outcome, as opposed to merely claiming the idea of a solution or outcome. McRO, 837 F.3d at 1314-15, 120 USPQ2d at 1102-03; DDR Holdings, 773 F.3d at 1259, 113 USPQ2d at 1107. In this respect, the improvement consideration overlaps with other Step 2B considerations, specifically the particular machine consideration (see MPEP § 2106.05(b)), and the mere instructions to apply an exception consideration (see MPEP § 2106.05(f)). Thus, evaluation of those other considerations may assist examiners in making a determination of whether a claim satisfies the improvement consideration.
However, it is important to keep in mind that an improvement in the judicial exception itself (e.g., a recited fundamental economic concept) is not an improvement in technology. For example, in Trading Technologies Int' l v. IBG LLC, the court determined that the claim simply provided a trader with more information to facilitate market trades, which improved the business process of market trading but did not improve computers or technology. (921 F.3d 1084, 1093-94 (Fed. Cir. 2019) Note, there is no requirement for the judicial exception to provide the improvement.
In the instant case, the applicant’s argued improvement is to an abstract idea. (i.e. more efficient computations; improved review of medical information to develop diagnoses).
As drafted the claims, particularly claims 1 and 11, do not recite any particular type of time series data, nor does it recite or reflect the (improved) display of physiological data.
(F) Applicant argues that the amendments to claims 1 and 11 are not taught by the prior art of record.
In response, the examiner has provided new grounds of rejection with the Davies reference to address the newly added claim limitations.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Ukrit et al (M. F. Ukrit, R. B. Jeyavathana, A. L. Rani and V. Chandana, "Maternal Health Risk Prediction with Machine Learning Methods," 2024 Second International Conference on Emerging Trends in Information Technology and Engineering (ICETITE), Apr. 18, 2024, pp. 1-9.) discusses machine learning techniques to assess and predict maternal health risks.
Wagner et al ( US 20240312629 A1)- discloses digital analysis of patient time series data and specifically to techniques for diagnosing a health condition based on patient time series data.
Anthony et al (WO 2023201285 A2)-discloses computational analysis of health data and the determination of a user’s biological age. The disclosure also relates to the systematic analysis and identification of high- priority data markers for a user.
Fulcher et al (WO 2024102495 A1)-discloses machine-learning architectures for healthcare, including prediction models for early identification of pregnancy disorders; and more specifically relates to machine learning models and techniques for predicting potential complications in the second and third trimesters of pregnancy.
Peri et al ( US 20240038402 A1)- discloses a modeling system to predict the risk of maternal mortality by detecting diseases early and identifying possible risks in mothers, fetuses and infants across pre, peri and post-natal stages of pregnancy. The system quantifies risk as a single MIHIC score, which through quantification assigns possible risks to the mother, fetus and infant.
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 Rachel L Porter whose telephone number is (571)272-6775. The examiner can normally be reached M-F, 10-6:30.
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, Shahid Merchant can be reached on 571-270-1360. 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.
/Rachel L. Porter/Primary Examiner, Art Unit 3626
Prosecution Insights