DETAILED ACTION
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 .
Notice to Applicant
This communication is in response to application filed 4/16/2025. It is noted that application is a continuation of 18/439,550 filed 2/12/2024 which is a continuation of 18/386,056 filed 11/01/2023 (now US Patent No. 11,972,869) which is a continuation of 17/552/246 filed 12/15/2021 (now US Patent No. 12,327,638) claims priority to provisional application 63/156,531 filed 3/4/2021 and to provisional application 63/126,331 filed 12/16/2020. Claims 1-27 are pending.
Information Disclosure Statement
Information disclosure statement dated 4/16/2025 has been acknowledged and considered.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1-27 are provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over claim 1, 3-24 of copending Application No. 18/439,550 (reference application).
Although the claims at issue are not identical, they are not patentably distinct from each other because the same core invention as presently claimed, namely predicting that a patient is at risk of developing a health condition based on patient electrocardiogram time series data using one or more trained neural network models. In particular, claims 1 and 11 of Application No. 18/439,550 recite receiving patient electrocardiogram data measured prior to a diagnosis date, executing one or more trained neural network models trained using electrocardiogram data measured only within diagnosis windows and not preemptively to diagnoses, preprocessing the patient time series data by extracting one or more discrete metrics, and predicting that the patient is at risk of developing the health condition within the next 5 years. Claims 3-24 of Application No. 18/439,550 further recite training sets comprising ethnicity of patients, QT intervals, recommending an intervention, obtaining training sets for cohorts using a search query, receiving patient information including ethnicity, selecting one or more highest performing models, calculating a numerical risk score, vector representations of patient time series data, and pulmonary hypertension diagnoses determined as a function of mPAP and/or TRV.
The presently pending claims are not patentably distinct from the claims of Application No. 18/439,550 because they merely recite an obvious variation of the same ECG-based neural-network diagnostic framework. Pending claims 1 and 14 recite receiving ECG waveform data from an adult patient at risk of heart failure, identifying a trained neural network model trained on health records correlated to positive diagnoses, preprocessing the waveform by segmenting the waveform into at least a segment over at least a time window, executing the trained model, and predicting whether the patient is at risk of a health condition. Such limitations define the same basic invention as the claims of Application No. 18/439,550, differing primarily in claim phrasing and in reciting segmentation over a time window rather than the particular diagnosis-window, convolutional-branch, and concatenation-layer language of the copending claims.
The remaining pending claims likewise do not render the claims patentably distinct. Numerical risk output in claims 2 and 15, intervention recommendation in claims 5 and 18, cohort/model selection in claims 4 and 17, search-query-based cohort acquisition in claims corresponding to cohort selection, and risk-score calculation are all claimed in Application No. 18/439,550 or constitute obvious variations thereof. Positive and negative training cohorts, diagnostic and preemptive timing windows, multiple ECG segments/windows and aggregation of outputs, and patient-specific training refinements such as age filtering or physician-reviewed records likewise represent no more than obvious variations of the same claimed ECG-based neural-network prediction framework. Claim 27 merely combines such features into a single system claim and therefore also is not patentably distinct.
Accordingly, claims 1-27 are provisionally rejected on the ground of nonstatutory obviousness-type double patenting over copending Application No. 18/439,550. This rejection is provisional because the reference application has not yet issued as a patent.
Claims 1-27 are rejected on the ground of nonstatutory obviousness-type double patenting as being unpatentable over U.S. Patent No. 11,972,869 and, alternatively, over U.S. Patent No. 12,327,638.
U.S. Patent No. 11,972,869 claims use of ECG waveform data, selection of one or more highest performing models, outputting a numerical risk score, and recommending an intervention as a function of the predicted heart condition. U.S. Patent No. 12,327,638 claims and/or clearly teaches diagnosed and non-diagnosed training cohorts, preemptive patient time-series data, segmentation of patient time-series data into multiple time windows, and aggregation of outputs across windows to generate an aggregate diagnosis.
Pending claims 1 and 14 are not patentably distinct because they recite the same core ECG-based neural-network diagnostic framework already claimed in the cited patents, including receiving ECG waveform data, identifying a trained neural-network model trained on health records correlated to positive diagnoses, preprocessing the ECG waveform by segmenting the waveform into at least a segment over a time window, executing the trained model, and predicting whether the patient is at risk of a health condition. The remaining claims merely recite obvious variations of that same patented framework, including numerical risk output (claims 2 and 15), binary output formatting (claims 3 and 16), cohort/model selection (claims 4 and 17), intervention recommendation (claims 5 and 18), age-based filtering (claims 6 and 19), physician-reviewed records (claims 7 and 20), segmentation into multiple ECG windows and aggregation of outputs (claims 8, 9, 21, and 22), positive and negative training cohorts (claims 10 and 23), diagnostic and preemptive ECG timing windows (claims 11, 12, 24, and 25), non-exercise ECG acquisition conditions (claims 13 and 26), and combination of such features (claim 27). Such limitations do not render the claims patentably distinct, but instead constitute obvious variations of the patented subject matter.
Accordingly, claims 1-27 are rejected on the ground of nonstatutory obviousness-type double patenting over U.S. Patent No. 11,972,869 and, alternatively, over U.S. Patent No. 12,327,638. A timely filed terminal disclaimer in compliance with 37 C.F.R. 1.321(c) may overcome this rejection, if otherwise appropriate.
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 1-27 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claims 1-13 are drawn to a method for diagnosing a health condition based on patient time series data, which is within the four statutory categories (i.e., process). Claims 14-27 are drawn to a system for diagnosing a health condition based on patient time series data, which is within the four statutory categories (i.e., machine).
Representative independent claim 1 includes limitations that recite at least one abstract idea. Specifically, independent claim 1 recites:
A method for diagnosing a health condition based on patient time series data, wherein the method comprises:
receiving, using one or more hardware processors, patient time series data, wherein the patient time series data comprises an electrocardiogram (ECG) waveform from an adult patient at risk of heart failure;
identifying, using the one or more hardware processors, a trained neural network model which has been trained using a training set of health records, wherein the training set of health records comprised:
health records of patients who have been diagnosed with a health condition of interest; and
ECG waveforms of the patients correlated to positive diagnoses of the health condition of interest;
pre-processing, using the one or more hardware processors, the time series data, wherein preprocessing the time series data comprises:
segmenting, using the one or more hardware processors, the patient time series data comprising the ECG waveforms into at least a segment of the ECG waveform over at least a time window; and
inputting, using the one or more hardware processors, the patient time series data comprising the at least a segment of the ECG waveform into the trained neural network model;
executing, using the one or more hardware processors, the trained neural network model; and
predicting, using the one or more hardware processors, whether the adult patient at risk of heart failure is at risk from the health condition of interest as a function of the patient time series data comprising the at least a segment of the ECG waveform and the trained neural network model.
These recited underlined limitations fall within the mental processes grouping of abstract ideas because they amount to observation, evaluation, judgment, and opinion regarding whether a patient is at risk from a health condition based on ECG data and prior diagnosed cases. At the level of generality presently claimed, the steps of reviewing patient ECG waveform data, comparing the data to waveforms associated with diagnosed patients, evaluating one or more waveform characteristics, and reaching a conclusion regarding whether the patient is at risk from a health condition can practically be performed in the human mind or with pen and paper. That is other than reciting “hardware processors” and “neural network” language, nothing precludes the steps from practically being performed mentally in one’s head or by pen and paper. At a high level, a user could practically perform in his or head the steps of training a model, extracting metrics from a set of data and making a prediction from the data. Accordingly, the claim describes at least one abstract idea.
In the present case, the additional limitations beyond the above-noted at least one abstract idea 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 method for diagnosing a health condition based on patient time series data, wherein the method comprises:
receiving, using one or more hardware processors, patient time series data, wherein the patient time series data comprises an electrocardiogram (ECG) waveform from an adult patient at risk of heart failure;
identifying, using the one or more hardware processors, a trained neural network model which has been trained using a training set of health records, wherein the training set of health records comprised:
health records of patients who have been diagnosed with a health condition of interest; and
ECG waveforms of the patients correlated to positive diagnoses of the health condition of interest;
pre-processing, using the one or more hardware processors, the time series data, wherein preprocessing the time series data comprises:
segmenting, using the one or more hardware processors, the patient time series data comprising the ECG waveforms into at least a segment of the ECG waveform over at least a time window; and
inputting, using the one or more hardware processors, the patient time series data comprising the at least a segment of the ECG waveform into the trained neural network model;
executing, using the one or more hardware processors, the trained neural network model; and
predicting, using the one or more hardware processors, whether the adult patient at risk of heart failure is at risk from the health condition of interest as a function of the patient time series data comprising the at least a segment of the ECG waveform and the trained neural network model.
For the following reasons, the Examiner submits that the above identified additional limitations do not integrate the above-noted at least one abstract idea into a practical application.
The additional elements (i.e. the limitations not identified as part of the abstract idea) amount to no more than limitations which:
add insignificant extrasolution activity to the abstract idea, see MPEP 2106.05(g).
receiving patient time series data, identifying a training set of health records and pre-processing the data amounts to mere data gathering.
amount to mere instructions to apply an exception, see MPEP 2106.05(f).
the recitations performing the functions by the at least one or more hardware processors and applying neural network models amounts to merely invoking a computer as a tool to perform the abstract idea, e.g. see paragraph [0099] of the present Specification.
Examiner submits the broad application of neural network models amount to merely using software to tailor information and provide it to the user on a generic computer. The recited claims teach the training of the model, however recites the training in a generic manner. Applicant does not provide adequate evidence or technical reasoning on how the process improves the efficiency of the computer and is beyond conventional use of components, as opposed to the efficiency of the process, or of any other technological aspect of the computer.
generally link the abstract idea to a particular technological environment or field of use, see MPEP 2106.05(h)– for example, the recitation of by the at least one or more hardware processors and applying neural network models merely limits the abstract idea the environment of a computer,
Thus, taken alone, the additional elements do not integrate the at least one abstract idea into a practical application.
Independent claim 1 does not include additional elements that are sufficient to amount to “significantly more” than the judicial exception. As discussed above with respect to discussion of integration of the abstract idea into a practical application, the additional elements amount to no more than mere instructions to apply an exception and generally linking the abstract idea to a particular technological environment or field of use and the same analysis applies with regards to whether they amount to “significantly more.” Additionally, the additional limitations, other than the abstract idea per se, amount to no more than limitations which have been recognized as well-understood, routine, and conventional activity in particular fields, as demonstrated by:
Specifically, for the receiving, identifying and pre-processing steps that were considered extra-solution activity in Step 2A, this has been re-evaluated in Step 2B and determined to be well-understood, routine, conventional activity in the field.
The background does not provide any indication that the network appliance is anything other than a generic, off-the-shelf computer component and there is no indication that the combination of steps collect the data in an unconventional way to provide an inventive concept.
The Specification expressly disclosing that the additional elements are well-understood, routine, and conventional in nature: paragraph [0099] of the Specification discloses that the current invention embodiments include both general and special purpose microprocessors, and any one or more processor of any kind of digital computer, none of which, even when programmed to perform the limitations of the current invention, may properly be deemed a “particular machine” for the purposes of subject matter eligibility and performing generic computer functions that are well-understood, routine, and conventional activities previously known to the pertinent industry (i.e. receiving and identifying data and conventional activities previously known to the pertinent industry (i.e. healthcare).
Relevant court decisions: The following are examples of court decisions demonstrating well-understood, routine and conventional activities, e.g. see MPEP § 2106.05(g) and MPEP 2106.05(d)(II),:
Receiving or transmitting data over a network, e.g., using the Internet to gather data, see Intellectual Ventures v. Symantec – similarly, the current invention receives the document and link data, and transmits the data to a user
Storing and retrieving information in memory, e.g. see Versata Dev. Group, Inc. v. SAP Am., Inc. – similarly, the current invention recites storing document and link data in a database and/or electronic memory, and retrieving the document and link data from storage in order to display it to a user.
Therefore, the additional elements do not add significantly more to the at least one abstract idea.
Independent claim 14 teaches limitations similar to claim 1 and recites the same abstract idea for the same reasons set forth above. Claim 14 further teaches a system containing one or more processors and a non-transitory memory configured to store instructions executable by the processor to perform the functionality of claim 1. These limitations of a processor and memory, as generally recited, amount to mere instructions to apply an exception and generally link the abstract idea to a particular technological environment or field of use. Independent claim 14 is therefore directed to an abstract idea.
Independent claim 27 also is directed to an abstract idea. Claim 27 recites a system that receives patient ECG waveform data, identifies a trained neural network model trained using health records and ECG waveforms correlated to positive diagnoses, where the training set was filtered based upon age, at least a portion of the training-set records were comprehensively assessed by a physician, the training set included diagnosed and non-diagnosed patients, and the ECG waveforms were captured while the patients were not challenged by exercise, then pre-processes the ECG waveform by segmenting it into at least a segment over at least a time window, inputs the segment into the trained neural network model, executes the model, predicts whether the patient is at risk from the health condition of interest, specifies that the prediction may be binary, and recommends an intervention as a function of the predicted heart condition. These limitations still amount to evaluating medical information to determine whether a patient is at risk from a health condition and then using the result of that evaluation. The additional training-set conditions, binary output, and recommendation limitation do not alter the abstract character of the claim.
Furthermore, for similar reasons as representative independent claim 1, analogous independent claims 14 and 27 do not recite additional elements that integrate the judicial exception into a practical application or add significantly more.
The following dependent claims further define the abstract idea or are also directed to an abstract idea itself:
In relation to claims 2 and 15, these claims specify outputting a numerical score representative of risk from the health condition of interest. Such limitations amount to reporting or expressing the result of the underlying abstract analysis and therefore recite insignificant extrasolution activity.
In relation to claims 3, 16, and the corresponding binary-prediction language of claim 27, these claims specify that the prediction is a binary prediction of either “positive” or “negative.” Such limitations merely define the format of the abstract risk determination and therefore further define the abstract idea itself.
In relation to claims 4 and 17, these claims specify selecting the trained neural network model from a plurality of trained neural network models as a function of model performance with a cohort common to the adult patient at risk of heart failure. Such selection constitutes evaluation and judgment in choosing which model to apply and is therefore also a mental process at the currently claimed high level of generality.
In relation to claims 5, 18, and the recommendation limitation of claim 27, these claims specify recommending an intervention as a function of the predicted heart condition. Under the broadest reasonable interpretation, such recommendation merely uses the result of the abstract idea to suggest a course of action. As such, these claims remain directed to the abstract idea and do not integrate the exception into a practical application.
In relation to claims 6, 19, and the age-filtering limitation of claim 27, these claims specify that the training set was filtered based upon age of the patients. Such filtering merely defines which data are included in the analysis and therefore amounts to further narrowing of the abstract idea to a particular data set.
In relation to claims 7, 20, and the physician-assessment limitation of claim 27, these claims specify that at least a portion of the patient health records of the training set were comprehensively assessed by a physician. Such limitations merely define the provenance or quality of the training data and therefore amount to further narrowing of the abstract idea to a particular data set.
In relation to claims 8 and 21, these claims specify segmenting the patient ECG waveform into first and second segments over first and second time windows and inputting those segments into the trained neural network model. Such limitations merely further define the manner of preprocessing the data used in the abstract analysis and therefore do not integrate the abstract idea into a practical application.
In relation to claims 9 and 22, these claims specify outputting first and second outputs for the first and second ECG segments, aggregating the outputs, and predicting as a function of the aggregated output. Such limitations amount to further analysis, evaluation, and reporting of the ECG data and therefore are directed to a mental process and further define the abstract idea itself.
In relation to claims 10 and 23, these claims specify that the training set comprised a first set of health records associated with patients diagnosed with the health condition of interest and a second set of health records associated with patients not diagnosed with the health condition of interest. Such limitations merely define the data used to train or select the analytical model and therefore amount to further narrowing of the abstract idea to a particular data set.
In relation to claims 11 and 24, these claims specify that the ECG waveforms in the training set comprised diagnostic ECG waveforms captured within a predetermined amount of time of a date on which the patients received the positive diagnoses. Such limitations merely define the timing of the data used in the abstract analysis and therefore do not integrate the abstract idea into a practical application.
In relation to claims 12 and 25, these claims specify that the ECG waveforms in the training set comprised preemptive ECG waveforms captured at least a predetermined amount of time before the date on which the patients received the positive diagnoses. Such limitations likewise merely define the timing of the data used in the abstract analysis and do not integrate the abstract idea into a practical application.
In relation to claims 13 and 26, these claims specify that the ECG waveforms in the training set were captured while the patients were not challenged by exercise. Such limitations merely define the circumstances under which the data were gathered and therefore amount to further narrowing of the abstract idea to a particular data set.
The dependent claims also do not include additional elements, considered both individually and as an ordered combination, that amount to significantly more than the judicial exception. The additional limitations either further define the abstract idea itself, amount to insignificant extra-solution activity, or amount to no more than instructions to apply the abstract idea using generic computer components in a particular field of use.
Therefore, claims 1-27 are ineligible under 35 U.S.C. 101.
Subject Matter free from Prior Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Tran (2007/0273504) a health care monitoring system to detect a heart attack or stroke. In particular, Tran para. [0178] teaches cluster operations and algorithms are used to detect patterns in the data.
Chen (CN 107301409 A), the closest foreign reference of record, teaches a system and method for processing an ECG based on wrapper characteristic selection and Bagging learning.
Yoo (Yoo, Sun Kook; Lee, Kwanghyun; Lee, Moon H. “Empirical determination of an ECG compression ratio for mobile telecardiology applications.” Telemedicine and e-Health 14.2: 156(8). Mary Ann Liebert, Inc. (Mar 2008)), the closes non-patent literature of record teaches analyzing ECG databases including both normal and abnormal ECG data, and evaluating the relationship between the subjective and objective indices. The study included subjective and objective indices to determine the permissible CR for telecardiology applications over a mobile network that required continuous ECG transmission with little delay.
The prior art of record, whether taken alone or in combination, fails to teach or suggest the presently claimed subject matter, particularly the use of ECG waveform time-series data from an adult patient at risk of heart failure, preprocessing the ECG waveform by segmenting it into one or more time-window segments, and inputting the segmented ECG waveform into a trained neural network model trained using health records and ECG waveforms correlated to positive diagnoses of a health condition of interest, to thereby predict whether the adult patient is at risk from the health condition of interest as a function of the segmented ECG waveform and the trained neural network model. In particular, the prior art does not teach or fairly suggest the claimed combination of segmenting patient ECG waveform data over at least one time window for model input and using that segmented ECG waveform, in the claimed diagnostic framework, to generate the recited patient-specific risk prediction.
No final decision on patentability has been made in light of pending rejections.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to LINH GIANG MICHELLE LE whose telephone number is (571)272-8207. The examiner can normally be reached Mon- Fri 8:30am - 5:30pm PST.
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.
LINH GIANG "MICHELLE" LE
PRIMARY EXAMINER
Art Unit 3686
/LINH GIANG LE/Primary Examiner, Art Unit 3686 6/27/26
Prosecution Insights