DETAILED CORRESPONDENCE
This is a non-final office action on merits in response to the arguments and/or amendments filed on 04/17/2026 and 04/24/2026 and the request for continued examination filed on 04/28/2026.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of claims
Amendments to claims 1, 3-6, 8-9, 11-14, 17, 19-20 are acknowledged and have been carefully considered. Claims 1-20 are pending and considered below.
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 04/28/2026 has been entered.
Subject Matter Free of Art
Claims 1-20 include subject matter that is free of prior art. The cited prior art of record fails to expressly teach or suggest, either alone or in combination, the features found within independent claims 1, 9, and 17.
For claims 1, 9, and 17, the cited prior art of record fails to expressly teach or suggest, either alone or in combination, identifying, from a plurality of historical EHR data of a plurality of historical patients, a list of indicator phrases correlated to an Alzheimer's disease (AD) diagnosis; locating and retrieving, from current EHR data of a patient, one or more indicator phrases from the historically identified list, including at least one environmental risk factor correlated to an AD diagnosis; using the retrieved indicator phrases together with structured EHR data in an ML predictive model to determine a likelihood of the patient developing AD; and updating the ML predictive model with the current EHR data of the patient and a subsequent diagnosis of the patient relating to AD.
The closest prior art of record includes 1) Kartoun et al. (U.S. Patent Publication 2019/0189253 A1), referred to hereinafter as Kartoun, 2) Spurlock et al. (International Publication No. WO2019071098 A2), referred to hereinafter as Spurlock, and 3) Zhou et al. (Zhou et al., Automatic extraction and assessment of lifestyle exposures for Alzheimer’s disease using natural language processing, 2019, International Journal of Medical Informatics,130, pages 1-9 (Year: 2019)), referred to hereinafter as Zhou.
Kartoun teaches a computer implemented medical condition verification system that processes patient EHR data, including structured and unstructured information, uses natural language processing to identify medica -condition indicators and terms or phrases within patient EHR data, and uses structured and unstructured covariates to generate a risk score or probability for a medical condition. Kartoun further teaches learning structured and unstructured covariates relevant to specific medical conditions, including terms or phrases extracted from clinical narrative notes, and training the medical condition verification system using a pool of patient EMRs and medical condition information. However, Kartoun fails to teach or suggest identifying a list of indicator phrases correlated to an Alzheimer's disease (AD) diagnosis from historical EHR data of historical patients and subsequently locating, in the current EHR data of a patient, indicator phrases from the AD list based on one or more ontologies associating the indicator phrases with clinical phenotypes. Kartoun further fails to teach or suggest using these retrieved AD indicator phrases, including an environmental risk factor correlated to AD, with structured EHR data in an ML predictive model to output a prediction representing a likelihood that the patient will develop AD, or updating the ML predictive model with the current EHR data of the patient and a subsequent diagnosis of that patient relating to AD.
Spurlock teaches using machine learning to discover patterns and associations within clinical data obtained from a population and correlating those associations with future disease outcomes. Spurlock further teaches training machine learning models using data from a plurality of patients with known disease outcomes, where the training data may include phenotypic data, environmental data, demographic data, and geographic data, and using the trained models to identify patients having an increased likelihood of developing a disease (Alzheimer's disease). However, Spurlock fails to teach or suggest identifying, from historical EHR data of historical patients, a list of indicator phrases correlated to an Alzheimer's disease diagnosis and subsequently locating and parsing, using an NLP model and one or more ontologies associating the indicator phrases with clinical phenotypes, indicator phrases from the list within the unstructured EHR data or metadata of a current patient. Spurlock further fails to teach or suggest the claimed arrangement in which the indicator phrases retrieved from the current patient's EHR include an environmental risk factor correlated to an AD diagnosis and those retrieved indicator phrases are input with structured EHR data into the ML predictive model to predict the patient's likelihood of developing AD.
Zhou teaches using natural language processing to extract lifestyle exposures from free text clinical notes of patients diagnosed with AD dementia and cognitively unimpaired controls. Zhou further teaches establishing a Unified Medical Language System (UMLS) concept dictionary corresponding to previously identified lifestyle risk factors, mapping clinical note text to UMLS concepts, identifying lifestyle exposures occurring in the clinical notes, and statistically comparing the extracted exposures between AD patients and controls to determine associations between lifestyle exposures and AD dementia. However, Zhou fails to teach or suggest identifying, from a plurality of historical EHR data of a plurality of historical patients, a list of indicator phrases correlated to an AD diagnosis. Rather, Zhou begins with lifestyle risk factors previously identified from AD literature and constructs a UMLS concept dictionary corresponding to those predetermined risk factors before extracting the corresponding concepts from the clinical notes. Zhou further fails to teach or suggest using the retrieved indicator phrases together with structured EHR data as inputs to an ML predictive model to output a prediction representing a likelihood that a current patient will develop AD, or updating such an ML predictive model with the current EHR data of the patient and a subsequent AD diagnosis of that patient.
Claim Rejections - 35 USC § 112
The rejections of claims 3, 5, and 20 under 35 U.S.C. 112(a) are withdrawn. Applicant has amended the claims to remove the language upon which the written description rejections were based.
Claim 1 is rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Claim 1 recites “update the ML predictive model with the current EHR data of the patient and any subsequent diagnosis of the patient relating to AD”, and the specification fails to provide adequate written description support for the claimed limitation. The specification discloses that the predictive model may be a machine learning (ML) model trained using electronic health record (EHR) data associated with a large number of patients to correlate risk factors extracted from the EHR data with clinical outcomes relating to Alzheimer’s Disease (AD), and that the analytics computing device may train the ML model based on EHR data stored in the database (see [0022]). The specification also discloses building the ML model using EHR data from the database as training data (see [0050]). However, the specification does not disclose updating the ML predictive model with the current EHR data of the patient and a subsequent diagnosis of that patient relating to AD. The disclosed training of an ML model using EHR data does not reasonably convey possession of subsequently updating the ML predictive model using the current EHR data of the patient being evaluated with a subsequent AD diagnosis of that patient. Accordingly, the specification does not reasonably convey to one skilled in the art that the inventor had possession of the claimed subject matter as of the effective filing date.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1
Under step 1, the analysis is based on MPEP 2106.03, and claims 1-8 are drawn to an analytics computing device, claims 9-16 are drawn to a computing-implemented method, and claims 17-20 are drawn to at least one non-transitory computer-readable media having computer-executable instructions. Thus, each claim, on its face, is directed to one of the statutory categories (i.e., useful process, machine, manufacture, or composition of matter) of 35 U.S.C. 101.
Claim 1 recites the limitations of identifying a list of indicator phrases correlated to an Alzheimer's disease (AD) diagnosis from a plurality of historical EHR data of a plurality of historical patients; locating one or more indicator phrases from the list of indicator phrases included within at least one of the unstructured EHR data or the metadata of the current EHR data of the patient; parsing the unstructured EHR data and the metadata to retrieve the one or more indicator phrases located for the patient, the one or more indicator phrases including at least one environmental risk factor correlated to an AD diagnosis; outputting a prediction representing a likelihood of a patient developing AD; and identifying the patient as being at risk for AD based on the retrieved indicator phrases and the structured EHR data. These limitations, as drafted, recite reviewing and analyzing health information to identify information correlated to AD, locating AD indicators and risk factors from patient health information, evaluating the identified information to determine a likelihood of the patient developing AD, and making a judgment as to whether the patient is at risk for AD. These limitations constitute observations, evaluations, and judgments, under their broadest reasonable interpretation, can be performed in the human mind or by using pen and paper. For example, a person can review historical patient records to identify phrases associated with AD, review a patient's health information to locate identified phrases and risk factors, evaluate the identified information with structured patient information, and make a judgment regarding the patient's likelihood of developing AD. Accordingly, these limitations fall within the mental processes grouping of abstract ideas. Although the claim also recites performing certain operations using a natural language processing model and an ML predictive model, these computer limitations are considered additional elements under Step 2A, Prong Two. Thus, claim 1 recites a mental process, which is an abstract idea.
Step 2A Prong One
Independent claims 9 and 17 recite identical or nearly identical steps with respect to claim 1 (and therefore also recite limitations that fall within this subject matter grouping of abstract ideas), and these claims are therefore determined to recite an abstract idea under the same analysis.
Under Step 2A Prong Two
The claimed limitations, as per claim 1, include:
a processor in communication with a database, the database configured to store current electronic health record (EHR) data including (i)metadata, (ii) structured EHR data including at least one data structure, and (iii) unstructured EHR data including text data for a patient, the processor configured to:
identify a list of indicator phrases correlated to an Alzheimer's disease (AD) diagnosis from a plurality of historical EHR data of a plurality of historical patients;
retrieve the current EHR data from the database for a patient;
locate, using a natural language processing model and based on one or more ontologies that associate the indicator phrases with one or more clinical phenotypes, one or more indicator phrase from the list of indicator phrases included within at least one of the unstructured EHR data or the metadata of the current EHR data of the patient;
parse, using the natural language processing model, the unstructured EHR data and the metadata to retrieve the one or more indicator phrases located for the patient, the one or more indicator phrases including at least one environmental risk factor correlated to an AD diagnosis;
input the retrieved one or more indicator phrases and the structured EHR data for the patient into a machine learning (ML) predictive model that is trained to analyze labeled health data and output a prediction representing a likelihood of a patient developing AD;
identify, using the ML predictive model, the patient as being at risk for AD based on the retrieved indicator phrases and on the structured EHR data; and
update the ML predictive model with the current EHR data of the patient and any subsequent diagnosis of the patient relating to AD.
Examiner Note: underlined elements indicate additional elements of the claimed invention identified as performing the steps of the claimed invention.
The judicial exception expressed in claim 1 is not integrated into a practical application. The claim as a whole merely describes how to generally “apply” the concept of analyzing and evaluating patient health information to predict a patient’s risk of developing AD in a computer environment. The claimed computer components (i.e., a processor in communication with a database configured to store current electronic health record (EHR) data including metadata, structured EHR data, and unstructured EHR data; a natural language processing model and one or more ontologies that associate indicator phrases with one or more clinical phenotypes; and a machine learning (ML) predictive model trained to analyze labeled health data) are recited at a high level of generality and are merely invoked as tools to perform the process of analyzing and evaluating patient health information and making a prediction or judgment regarding the patient’s risk of developing AD (see MPEP 2106.05(f)). The claim does not recite a specific improvement to the functioning of the processor, database, natural language processing model, or ML predictive model, but instead uses these components to implement the abstract idea. Implementing the abstract idea using computer components as tools does not integrate the judicial exception into a practical application. Accordingly, alone and in combination, these additional elements do not integrate the abstract idea into a practical application.
The judicial exception expressed in claim 1 is not integrated into a practical application. The claim recites the additional elements of retrieving the current EHR data from the database for a patient, inputting the retrieved one or more indicator phrases and the structured EHR data for the patient into the ML predictive model, and updating the ML predictive model with the current EHR data of the patient and any subsequent diagnosis of the patient relating to AD. These limitations are recited at a high level of generality (i.e., as a general means of obtaining and providing data used in connection with the claimed analysis and prediction and updating the ML predictive model). Retrieving the current EHR data and inputting the retrieved indicator phrases and structured EHR data into the ML predictive model constitutes data gathering performed to obtain the information used in the analysis and prediction. Additionally, the claim recites updating the ML predictive model with the current EHR data and subsequent diagnosis to the ML predictive model, and this constitutes insignificant application without specifying any specific technique by which the model is updated. This data gathering and insignificant application are ancillary to the abstract idea and amount to insignificant extra solution activities (see MPEP 2106.05(g)). Accordingly, even when considered in combination, these additional elements do not integrate the abstract idea into a practical application.
Therefore, under step 2A, the claims are directed to the abstract idea, and require further analysis under Step 2B.
Under step 2B
Claim 1 does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed with respect to Step 2A, the claim as a whole merely describes how to generally “apply” the concept of analyzing and evaluating patient health information to predict risk of developing AD in a computer environment. Thus, even when viewed as a whole, nothing in the claim adds significantly more (i.e., an inventive concept) to the abstract idea.
For claim 1, under Step 2B, the additional elements of retrieving the current EHR data from the database for a patient; inputting the retrieved one or more indicator phrases and the structured EHR data for the patient into the ML predictive model; and updating the ML predictive model with the current EHR data of the patient and any subsequent diagnosis of the patient relating to AD have been reevaluated. As noted in Electric Power Group, LLC v. Alstom S.A., 830 F.3d 1350, 1354-55, 119 USPQ2d 1739, 1742 (Fed. Cir. 2016), merely collecting information for analysis without a technological improvement does not add significantly more to an abstract idea. Retrieving the current EHR data from the database and inputting the retrieved indicator phrases and structured EHR data into the ML predictive model amount to collecting and providing information to use for performing the analysis and prediction of AD. These limitations are recited at a high level of generality and amount to data gathering activities that do not provide an inventive concept. Additionally, as noted in In re Brown, 645 Fed. App'x 1014, 1016-17 (Fed. Cir. 2016), merely appending an additional step after performance of an abstract analysis does not provide an inventive concept where the additional step amounts to an insignificant application of the abstract idea. The limitation of updating the ML predictive model does not recite a particular technological manner of performing the update or require the updating step to provide an improvement to the operation of the predictive model. Instead, the limitation generally applies the results and information associated with the claimed analysis in a subsequent model update step. Accordingly, when considered individually and in combination, these additional elements do not provide an inventive concept sufficient to transform the judicial exception into patent eligible subject matter.
Claims 4, 7, 10-13, and 15-16 recite no further additional elements, and only further narrow the abstract idea. The previously identified additional elements, individually and as a combination, do not integrate the narrowed abstract idea into a practical application for reasons similar to those explained above, and do not amount to significantly more than the narrowed abstract idea for reasons similar to those explained above.
Claims 2-3, 5-6, 8, 14, and 18-20 recite the additional elements of the processor (claims 2-3, 5-6, 8, and 18-20), in the database (claim 14). However, these additional element amount to implementing an abstract idea on generic computer components. As such, these additional elements, when considered individually or in combination with the previously identified additional elements, do not integrate the abstract idea into a practical application or amount to significantly more than the abstract idea.
Thus, as the dependent claims remain directed to a judicial exception, and as the additional elements of the claims do not amount to significantly more, the dependent claims are not patent eligible.
Therefore, the claims here fail to contain any additional element(s) or combination of additional elements that can be considered as significantly more and the claims are rejected under 35 U.S.C. 101 for lacking eligible subject matter.
Response to Arguments
Applicant’s arguments and amendments, see Remarks/Amendments submitted on 04/17/2026 with respect to the rejection of the claims have been carefully considered and is addressed below.
Claim Rejections - 35 USC § 112
The rejections of the claims under 35 U.S.C. 112(a) are withdrawn. Applicant has amended the claims to remove the language upon which the written description rejections were based. A new rejection of claim 1 under 35 U.S.C. 112(a) has been added based on the claim language introduced by the amendment.
Claim Rejections - 35 USC § 101
Applicant's arguments have been considered but are not persuasive. For Step 2A, Prong One, claim 1 recites concepts of identifying information correlated to AD from historical health information, locating AD indicators and risk factors from patient health information, evaluating the identified information to determine a likelihood of the patient developing AD, and identifying the patient as being at risk for AD based on the evaluated information. These limitations recite observations, evaluations, and judgments that fall within the mental process grouping. The processor, database, natural language processing (NLP) model, and machine learning (ML) predictive model are separately considered as additional elements under Step 2A, Prong Two. Accordingly, Applicant's statements from Example 39 do not demonstrate error in the rejection and the rejection does not characterize the mere ML training or updating of an ML model as itself a mental process, but instead evaluates the computer related limitations of the claim as a whole.
With respect to Step 2A, Prong Two, Applicant's statement on the asserted technical improvements described in the specification is also unpersuasive. Although the specification characterizes the invention as addressing the extraction of AD related clinical phenotypes from unstructured EHR data, development of a predictive model based on this data, and identification of patients at risk for AD, claim 1 does not recite a specific improvement to the operation of a computer, database, NLP model, or ML predictive model. Instead, the claim uses these components to obtain and analyze EHR information and generate an AD risk prediction. While Applicant states that the use of ontologies reduces computer memory requirements, claim 1 does not require a reduction in memory usage or a specific technological mechanism that achieves this reduction. Accordingly, when considered individually and in combination, the additional elements do not integrate the identified abstract idea into a practical application.
Applicant's arguments regarding Step 2B are also unpersuasive. In this step, the additional elements merely use the recited processor, database, NLP model, and ML predictive model as tools to implement the claimed information analysis; retrieve and provide information for that analysis; and update the model without specifying a specific technological manner of performing the update. Considered individually and as an ordered combination, the additional elements do not transform the identified abstract idea into significantly more than the judicial exception. Accordingly, Applicant's arguments do not overcome the rejection of claims 1-20 under 35 U.S.C. 101.
Claim Rejections - 35 USC § 103
In view of Applicant’s amendments and arguments, the rejection of claims 1-20 under 35 U.S.C. 103 is withdrawn.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Crafts et al. (U.S. Publication 2017/0124263) teaches scalable clinical, genomic, and patient health records data, analyzes data in response to queries through condition specific workflows, and dynamically presents role and workflow based visualizations using predefined templates.
Kukreja et al. (U.S. Publication 2021/0334462 A1) teaches a system and method that parses unstructured text and detects negation, and also integrates patient data, computes disease and risk scores, and flags patients for intervention.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KYRA R LAGOY whose telephone number is (703)756-1773. The examiner can normally be reached Monday - Friday, 8:00 am - 5:00 pm EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Kambiz Abdi can be reached at (571)272-6702. 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.
/K.R.L./Examiner, Art Unit 3685
/KAMBIZ ABDI/Supervisory Patent Examiner, Art Unit 3685
Prosecution Insights