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 .
Applicant Response
Applicant's response, filed 07/06/2026, has been fully considered. Rejections and/or objections not reiterated from previous Office Actions are hereby withdrawn. The following rejections and/or objections are either reiterated or newly applied. They constitute the complete set presently being applied to the instant application.
Claim Status
Claims 12-16 are canceled.
Claims 21-25 are newly added.
Claims 1-11 and 17-25 are pending and under examination herein.
Claims 1-11 and 17-25 are rejected.
Priority
The instant application claims priority to US Provisional Application 63/186101, filed 05/08/2021. As such, the effective filing date assigned to each of claims 1-25 is 05/08/2021.
Drawings
The drawings filed 05/06/2022 were accepted by the examiner in the office action mailed 04/07/2026.
Specification
The disclosure remains objected to because of the following informalities: When there are drawings, there shall be a brief description of the several views of the drawings. The current description is insufficient as it does not provide a brief description for the individual figures, but rather lists “FIGS. 2-25”. Applicant is required to provide a brief description for each figure, including figures with multiple parts (such as Fig. 3A-3C).
Appropriate correction is required.
Response to Applicant’s Arguments
Applicant’s Arguments have been fully considered, but the amendments do not fully address the issue discussed above.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 25 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention. This rejection is newly recited and necessitated by claim amendments.
As set forth in MPEP 2111.04.I, "wherein" clauses raise the question as to the limiting effect of the language in a claim. As claim 21 on which claim 25 does not recite binary values, the metes and bounds of the claims are unclear. For the purposes of examination, this limitation is interpreted as “further comprising”.
Claim Rejections - 35 USC § 101
The rejection of claims 12-16 under 35 U.S.C. 101 is withdrawn in view of cancelation of the claims in the claim amendments filed 07/06/2026.
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 1-11 and 17-25 remain rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea/law of nature/natural phenomenon without significantly more. Newly recited portions are necessitated by claim amendments.
In accordance with MPEP § 2106, claims found to recite statutory subject matter (Step 1: YES) are then analyzed to determine if the claims recite any concepts that equate to an abstract idea, law of nature or natural phenomenon (Step 2A, Prong 1). For example, in the instant application, the claims recite the following limitations that equate to an abstract idea:
Claim 1 recites identifying features from the reference data, the features comprising medication features and diagnosis features; transforming continuous features and vitals features of the features from initially entered values into transformed feature values having one or more standardized units of measurement; based at least on the transformed feature values, generating a fall risk prediction model; extracting feature values, corresponding to the features, from the patient data of an EMR created for a post-acute care patient; generating a prediction of whether the post-acute care patient will suffer a future fall by inputting the feature values extracted from the patient data into the fall risk prediction model; comparing the prediction with a threshold; and in response to the prediction satisfying the threshold, automatically initiating an action to reduce a risk of the future fall.
Claim 17 recites identifying features from the reference data, the features comprising medication features and diagnosis features; transforming continuous features and vitals features of the features from initially entered values into transformed feature values having one or more standardized units of measurement; based at least on selecting the subset of the features transformed feature values, generating the a fall risk prediction model; extracting feature values, corresponding to the features, from patient data of an EMR created for a post-acute care patient; generating a prediction of whether the post-acute care patient will suffer a future fall by inputting the feature values extracted from the patient data into the fall risk prediction model; comparing the prediction with a threshold; and in response to the prediction satisfying the threshold, automatically initiating an action to reduce a risk of the future fall.
Claim 21 recites identifying features from the reference data, the features comprising medication features and diagnosis features; transforming continuous features and vitals features of the features from initially entered values into transformed feature values having one or more standardized units of measurement; based at least on the transformed feature values, generating a fall risk prediction model; extracting feature values, corresponding to the features, from patient data of an EMR created for a post-acute care patient; generating a prediction of whether the post-acute care patient will suffer a future fall by inputting the feature values extracted from the patient data into the fall risk prediction model; comparing the prediction with a threshold; and in response to the prediction satisfying the threshold, automatically initiating an action to reduce a risk of the future fall.
These recitations equate to steps of collecting information, analyzing data and making observations, evaluations and judgements that can be carried out in the human mind. Specifically, identifying and extracting features from data, transforming the data into a standardized units of measure, generating a fall risk prediction model (which could be as simple as linear regression, as disclosed by para 0033 in the instant specification), generating a prediction by inputting the values into the model, determining a prediction is above a threshold, and initiating an action can be performed mentally and are similar to the concepts of collecting and comparing known information in Classen Immunotherapies, Inc. v. Biogen IDEC, 659 F.3d 1057, 1067, 100 USPQ2d 1492, 1500 (Fed. Cir. 2011) and collecting information, analyzing it, and reporting certain results of the collection and analysis in Electric Power Group v. Alstom, S.A., 830 F.3d 1350, 1353-54, 119 USPQ2d 1739, 1741-42 (Fed. Cir. 2016) that the courts have identified as concepts that can be practically performed in the human mind. Therefore, each of the above recited limitations fall under the “Mental Processes” grouping of abstract ideas. Furthermore, the steps of generating a prediction by inputting values into a model equate to organizing information and manipulating information through mathematical correlations and reciting a mathematical equation, similar to the concepts of taking existing information, manipulating the data using mathematical functions, and organizing this information into a new form in Digitech Image Techs., LLC v. Electronics for Imaging, Inc., 758 F.3d 1344, 1350, 111 USPQ2d 1717, 1721 (Fed. Cir. 2014). Therefore, these limitations fall under the “mathematical concepts” grouping of abstract ideas. Claims 2-4, 7-9, 11, 18-20 and 22-25 recite further judicial exceptions or further qualify the judicial exceptions. As such, claims 1-11 and 17-25 recite an abstract idea (Step 2A, Prong 1: YES).
Claims found to recite a judicial exception under Step 2A, Prong 1 are then further analyzed to determine if the claims as a whole integrate the recited judicial exception into a practical application or not (Step 2A, Prong 2). This judicial exception is not integrated into a practical application because the claims do not recite an additional element that reflects an improvement to technology, applies or uses the recited judicial exception to affect a particular treatment for a condition, implements a judicial exception with, or uses a judicial exception in conjunction with, a particular machine or manufacture that is integral to the claim, effects a transformation or reduction of a particular article to a different state or thing or applies or uses the judicial exception in some other meaningful way beyond generally linking the use of the judicial exception to a particular technological environment, such that the claim as a whole is more than a drafting effort designed to monopolize the exception. Rather, the instant claims recite additional elements that amount to mere data gathering and mere instructions to implement the abstract idea in a generic computing environment. Specifically, the claims recite the following additional elements:
Claim 1, 17 and 21 recites receiving patient data for the post-acute care patient; receiving reference data for a plurality of patients from disparate data sources, wherein at least a subset of the reference data is associated with one or more patients who experienced a fall; wherein at least one of the features is identified by applying natural language processing to one or more free-text fields of at least one electronic medical record (EMR); and the action comprising electronically communicating a notification indicating the prediction to a clinician user interface.
Claim 1 also recites a non-transitory computer storage media.
Claim 17 also recites computer-implemented and one or more hardware processors.
Claim 21 also recites one or more hardware processors.
Claims 4 recites using one or more natural language processing techniques.
Claims 5 and 6 recite limitations for types of data included in the patient data.
Claims 8-9 and 25 recite using an XGBoost model.
Claim 23 recites wherein each of the plurality of patients experienced one or more falls during a patient encounter.
Claims 1, 17 and 21 recite limitations of how data is obtained and claims 5-6 and 23 recites further limitations on that data. These limitations equate to mere data gathering activity to obtain the data necessary for the mental evaluations and judgements (see MPEP 2106.05(g)). Claims 1, 17 and 21 also recite outputting data using a computer. Claims 1, 4, 8-9, 17, 21, and 24 merely indicates a field of use or technological environment in which the judicial exception is performed and confines the use of the abstract idea to a particular technological environment (NLP and XGBoost models). See MPEP 2106.05(h). Furthermore, claims 1, 17 and 21 merely recites using a generic computing systems and computer program products to carry out instructions to implement an abstract idea on a computer. The computer system and computer program product as claimed fails to recite details of how a solution to a problem is accomplished and only recites the idea of a solution or outcome. There are no limitations that indicate that the claimed steps require anything other than generic computing systems. As such, these limitations equate to mere instructions to implement the abstract idea on a generic computer that the courts have stated does not render an abstract idea eligible in Alice Corp., 573 U.S. at 223, 110 USPQ2d at 1983. See also 573 U.S. at 224, 110 USPQ2d at 1984. Furthermore, the use of a computer or other machinery in its ordinary capacity for economic or other tasks (e.g., to receive, store, or transmit data) or simply adding a general purpose computer or computer components after the fact to an abstract idea (e.g., a fundamental economic practice or mathematical equation) does not integrate a judicial exception into a practical application. See Affinity Labs v. DirecTV, 838 F.3d 1253, 1262, 120 USPQ2d 1201, 1207 (Fed. Cir. 2016) (cellular telephone); TLI Communications LLC v. AV Auto, LLC, 823 F.3d 607, 613, 118 USPQ2d 1744, 1748 (Fed. Cir. 2016) (computer server and telephone unit). There is no indication that any of these additional elements provide a practical application of the recited judicial exception outside of the judicial exception itself. As such, claims 1-11 and 17-25 are directed to an abstract idea (Step 2A, Prong 2: NO).
Claims found to be directed to a judicial exception are then further evaluated to determine if the claims recite an inventive concept that provides significantly more than the judicial exception itself (Step 2B). Further analyzing the additional elements under step 2B, the additional elements as described above do not rise to the level of significantly more than the judicial exception. As set forth in the MPEP, determinations of whether or not additional elements (or a combination of additional elements) may provide significantly more and/or an inventive concept rests in whether or not the additional elements (or combination of elements) represents well-understood, routine, conventional activity. Said assessment is made by a factual determination stemming from a conclusion that an element (or combination of elements) is widely prevalent or in common use in the relevant industry, which is determined by either a citation to an express statement in the specification or to a statement made by an applicant during prosecution that demonstrates a well-understood, routine or conventional nature of the additional element(s); a citation to one or more of the court decisions as discussed in MPEP 2106(d)(II) as noting the well-understood, routine, conventional nature of the additional element(s); a citation to a publication that demonstrates the well-understood, routine, conventional nature of the additional element(s); and/or a statement that the examiner is taking official notice with respect to the well-understood, routine, conventional nature of the additional element(s).
With respect to the instant claims under the 2B analysis, claims 1, 4, 8-9 , 17, 21 and 24 merely are at best mere instructions to “apply” the abstract ideas, which cannot provide an inventive concept. See MPEP 2106.05(f).e claims significantly more than the judicial exception (MPEP2106.05(g)&(h)). Furthermore, the use of a computer or other machinery in its ordinary capacity for economic or other tasks (e.g., to receive, store, or transmit data) or simply adding a general purpose computer or computer components after the fact to an abstract idea (e.g., a fundamental economic practice or mathematical equation) does not provide significantly more. See Affinity Labs v. DirecTV, 838 F.3d 1253, 1262, 120 USPQ2d 1201, 1207 (Fed. Cir. 2016) (cellular telephone); TLI Communications LLC v. AV Auto, LLC, 823 F.3d 607, 613, 118 USPQ2d 1744, 1748 (Fed. Cir. 2016) (computer server and telephone unit). Therefore, the additional elements do not comprise an inventive concept when considered individually or as an ordered combination that transforms the claimed judicial exception into a patent-eligible application of the judicial exception, and the claims do not amount to significantly more than the judicial exception itself (Step 2B: NO). As such, claims 1-11 and 17-25 are not patent eligible under 35 U.S.C. 101.
Response to Applicant’s Arguments
Applicant states that the claims do not as a whole recite a mental process, even if it recites a steps that could in isolation be characterized as an evaluation, and further that steps like using an NLP, transforming feature values to have standardized units and generating a machine learning model cannot be performed in the mind, similar to example 39 (Applicant’s Arguments, p 10, para 3-p 11, para 1).
It is respectfully submitted that this is not persuasive, and not commensurate with the scope of the claims. As discussed in MPEP 2106.04(I)(A), Step 2A is a two-prong inquiry, in which examiners determine in Prong One whether a claim recites a judicial exception. In other words, Step 2A, Prong 1 simply evaluates whether the claim recites any judicial exceptions, and the absence or presence of additional elements which are not judicial exceptions do not influence the evaluation. If any judicial exceptions are found to be recited by the claim under the analysis under Step 2A, Prong 1, the analysis then moves to Step 2A, Prong 2. And, as discussed above, the claims were found to recite judicial exceptions under Step 2A, Prong 1.
Furthermore, unlike example 39, the instant do not recite transforming facial images and using training a neural network using those images. Rather, the instant claims transform features from patient data into a standardized units and generates a fall risk prediction model. The claims no longer require using a machine learning model, and even if it did recite it generically, it could be as simple as linear regression, as disclosed by para 0033 in the instant specification, as discussed above.
Applicant further states any recited judicial exceptions are integrated into practical application by reflecting an improvement to technology or technical field and by applying any exception in aa particular meaningful manner by improving the predictive capacity of the computerized decision support tool by applying NLP to free-text fields of an EMR to identify predictive features and allows the tool to generate a fall risk prediction earlier in the encounter, and also improving the functioning of the decision support tool by enabling to ingest and process heterogeneous data from disparate data sources, and the transformation of the data and model generation is tied to a concrete technical benefit rather than reciting model generation in the abstract, and by integrating the prediction into a specified, automated clinical support workflow (Applicant’s Arguments, p 11, para 2- p 12, para 2).
It is respectfully submitted that this is not persuasive. As discussed in MPEP 2106.05(a), the improvement cannot be to or provided solely by the judicial exception itself. And as discussed above, the additional elements of the claim amount to mere data gathering and outputting, mere indicating a field of use or technological environment, and mere instructions to implement the abstract idea in a generic computing environment. Therefore, there is no indication that any of these additional elements provide a practical application of the recited judicial exception outside of the judicial exception itself. The improvement appears to be to and solely provided by the steps of extracting and transforming the features, generating the model, inputting the values into the model to generate a prediction and then comparing the prediction to the threshold, which were found to recite judicial exceptions. As such, the claims are directed to an abstract idea.
Applicant further states the combination of identifying predictive features by NLP of free-text fields, transforming labs and vitals features into standardized units of measurements, generating a fall risk prediction model, generating a prediction using the model, and automatically initiating an electronic notification to a clinician interface in response to the prediction satisfying a threshold in not well-understood, routine or conventional activity, and therefore request withdrawal of the rejection (Applicant’s Arguments, p 12, para 3-.p 14, para 1).
It is respectfully submitted that this is not persuasive. As discussed in MPEP 2106.05, 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 an inventive concept "cannot be furnished by the unpatentable law of nature (or natural phenomenon or abstract idea) itself. Therefore, only the additional elements of the claims are evaluated both individual and in combination to determine whether they amount to an inventive concept under step 2B. With respect to the instant claims under the 2B analysis, the additional elements of claims 1, 4, 8-9 , 17, 21 and 24 are amount to mere instructions to “apply” the abstract ideas, which cannot provide an inventive concept. See MPEP 2106.05(f).e claims significantly more than the judicial exception (MPEP2106.05(g)&(h)). Furthermore, the use of a computer or other machinery in its ordinary capacity for economic or other tasks (e.g., to receive, store, or transmit data) or simply adding a general purpose computer or computer components after the fact to an abstract idea (e.g., a fundamental economic practice or mathematical equation) does not provide significantly more. See Affinity Labs v. DirecTV, 838 F.3d 1253, 1262, 120 USPQ2d 1201, 1207 (Fed. Cir. 2016) (cellular telephone); TLI Communications LLC v. AV Auto, LLC, 823 F.3d 607, 613, 118 USPQ2d 1744, 1748 (Fed. Cir. 2016) (computer server and telephone unit). Therefore, the additional elements do not comprise an inventive concept when considered individually or as an ordered combination that transforms the claimed judicial exception into a patent-eligible application of the judicial exception, and the claims do not amount to significantly more than the judicial exception itself (Step 2B: NO). As such, the claims are not not patent eligible under 35 U.S.C. 101 and the rejections are maintained.
Claim Rejections - 35 USC § 102
The rejection of claims 12-13 and 15-16 under 35 U.S.C. 102(a)(1) as being anticipated by Ye et al. (International journal of medical informatics 2020, 137, p.1-7; hereafter referred to as Ye) is withdrawn in view of cancelation of the claims in the claim amendments filed 07/06/2026.
The rejection of claims 1, 3, and 5-11 under 35 U.S.C. 102(a)(1) as being anticipated by Ye et al. (International journal of medical informatics 2020, 137, p.1-7; hereafter referred to as Ye) is withdrawn in view of the claim amendments filed 07/06/2026, as Ye does not disclose identifying at least one feature by applying a natural language processing to one or more free-text fields of an EMR.
Claim Rejections - 35 USC § 103
The rejection of claim 14 under 35 U.S.C. 103 as being unpatentable over Ye et al. (International journal of medical informatics 2020, 137, p.1-7; hereafter referred to as Ye) as applied to claims 12-13 above, and further in view of Wang et al. (NPJ digital medicine, 2(1), 127, p 1-7; hereafter referred to as Wang) is withdrawn in view of cancelation of the claims in the claim amendments filed 07/06/2026.
The rejection of claim 2 under 35 U.S.C. 103 as being unpatentable over Ye et al. (International journal of medical informatics 2020, 137, p.1-7; hereafter referred to as Ye), is withdrawn in view of the claim amendments filed 07/06/2026, as Ye does not disclose identifying at least one feature by applying a natural language processing to one or more free-text fields of an EMR.
The rejection of claims 4 and 17-20 under 35 U.S.C. 103 as being unpatentable over Ye et al. (International journal of medical informatics 2020, 137, p.1-7; hereafter referred to as Ye) as applied to claim 1 above, and further in view of Ford et al. (Journal of the American Medical Informatics Association 2016, 23(5), p 1-9; hereafter referred to as Ford) is withdrawn in view of the claim amendments filed 07/06/2026, as neither Ye nor Ford disclose identifying at least one feature by applying an natural language processing to one or more free-text fields of an EMR..
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-11, 17-22, and 24-25 are rejected under 35 U.S.C. 103 as being unpatentable over Ye et al. (International journal of medical informatics 2020, 137, p.1-7; previously cited; hereafter referred to as Ye), further in view of Ford et al. (Journal of the American Medical Informatics Association 2016, 23(5), p 1-9; previously cited; hereafter referred to as Ford), Nakatani et al. (MIR medical informatics 2020, 8(4), pp.e1-14; newly cited; hereafter referred to as Nakatani) and Abhyankar et al. (Journal of biomedical informatics 2012, 45(4), pp.642-650; newly cited; hereafter referred to as Abhyankar). This rejection is newly recited and necessitated by claim amendments.
With respect to claims 1, 17, 21-22 and 24-25, Ye discloses an EHR-based risk assessment tool, wherein a one-year fall prediction model was developed using the machine-learning-based algorithm, XGBoost, and tested on an independent validation cohort to identify elders at a higher risk of falls (highlights; abstract).
Ye discloses obtaining electronic health records (EHR) of Maine from 2016 to 2018, comprising 265,225 older patients (≥65 years of age) that visited Maine health care facilities, including 35 hospitals, 34 federally qualified health centers, from April 1, 2016, to March 30, 2018, which is used to train the machine learning models (i.e. included post-acute care patients)(abstract; section 21-2.2).
Ye discloses candidate predictors were extracted from the EHR dataset, including medication prescriptions and disease diagnoses (section 2.2).
Ye discloses patients who suffered multiple falls during the targeted time frame were chart-reviewed by internal physician curators such that only the first fall records were utilized in our analysis, and further extracting predictors from standard nomenclature and clinical ontology codes, including binarizing medication information, indicating transformation and standardization of data (section 2.2; section 4.4, para 2).
Ye discloses identifying and separating continuous values and binary values for features (section 2.2; section 4.4, para 2). Ye further discloses using a member of tree-based modeling algorithm, XGBoost, for the prediction models using the extracted features, and determining a relative risk of diseases (continuous values) and a relative risk of medications (binary values) against confirmed falls for the validation, and that based on a pool of 10,198 predictor candidates, the XGBoost algorithm eventually captured 157 impactful features to form the final predictive model and these identified predictors were mainly demographic features (age and gender), chronic disease diagnoses, medication prescriptions and clinical utilization indicators (section 3.2-3.3.; section 4.4, para 2; fig 4).
Ye further discloses predicting risk of fall in the next year, and that the stratified (low/intermediate/high) risk groups were assigned according to the relative risk, which was calculated by the calibrated risk score divided by population-based fall incidence rate, with the intermediate-risk group formed by a group of patients with averaged relative risk greater than 1 but less than 5, indicating a moderate risk of fall for the next year, while the high-risk category caught the individuals with averaged relative risk of fall equal to or greater than 5, indicating a much higher risk of fall for the next year comparing to the general population (i.e. above a threshold) (section 2.3; fig 1).
Ye further discloses that with the advantages of diverse and readily accessible data source, the EHR-based fall prediction could be an ideal and beneficial tool as the first step to a feasible fall prevention strategy, and when those older adults with high risk of fall were identified (i.e. above a threshold), their personal unique risk factors would be captured, and their fall preventing strategies could be designed and proposed accordingly, such as educations to improve the awareness of fall risk, minimization or withdrawal of specific psychoactive or cardiovascular medications, detailed exercise therapies for patients with balance and gait issues (section 4.4).
Ye discloses using software, indicating the method is computer implemented (section 2.3, para 1).
With respect to claim 2, Ye further discloses this constructed fall risk assessment tool could be immediately deployed to provide early warnings to older adults with increased fall risk and identifying their personalized risk factors to facilitate customized fall interventions (Section 5). Therefore, it would have been prima facie obvious to one of ordinary skill in the art to have applied this model within 36 hours of the post- acute care patient being admitted into a post-acute care facility to predict the fall risk of older adults, since it can be immediately deployed to provide early warnings.
With respect to claim 3, Ye discloses the candidate features extracted from the EHR data included a disease diagnosis from ICD-10 codes (section 2.2, para 2).
With respect to claim 4, Ye discloses the limitations of claim 1, as applied above. Ye further discloses the candidate features extracted from the EHR data included a disease diagnosis from ICD-10 codes (section 2.2, para 2).
With respect to claims 5-7, Ye discloses the extracted predictors included demographic characteristics, clinical utilization features, disease diagnosis from ICD-10 codes, medication prescriptions from National Drug Code (NDC), and laboratory test results from Logical Observation Identifiers Names and Codes (LOINC), indicating the EHR data included these data types (section 2.2).
With respect to claims 8 and 24, Ye discloses the obtaining medication information, considering concurrent medication therapies, and counts of unique medications (section 2.2, para 2; section 2.3, para 3; fig 4; section 3.3, para 3; fig 5).
With respect to claims 9-10 and 25, Ye discloses XGBoost, to automatically integrate useful clinical information of disease diagnoses, medication consumption, clinical utilization, lab-test results and predicted an older individual’s risk of fall in the future one year (section 2.3; section 4.1).
With respect to claim 11, Ye discloses using logistic regression as part of the pipeline for generating fall risk (section 2.3).
Ye further discloses an initial univariate logistic regression was introduced in the derivation cohort to perform the feature pre-screening routine, using a member of tree-based modeling algorithm, XGBoost, for the prediction models, and determining a relative risk of diseases (continuous values) and a relative risk of medications (binary values) against confirmed falls for the validation, and further that most existing EHR-based fall risk models were developed using traditional statistical approaches, such as logistic regressions (section 2.2; section 3.2-3.3; section 4.4, para 2; fig 4; summary points). Ye further discloses they wonder whether the accuracy of such tools could be further improved if advanced machine learning algorithms were introduced (introduction, para 3). Therefore, it would have been prima facie obvious to have applied logistic regression model to the permutated features above the permuted feature total gain threshold to the methods of Ye, as most existing EHR-based fall risk models were developed using traditional statistical approaches, such as logistic regressions and therefore this technique is known in the art, and Ye teaches improving the accuracy of known tools using advanced machine learning algorithms.
With respect to claims 18-20, 22, and 25, Ye discloses the extracted predictors included demographic characteristics, clinical utilization features, disease diagnosis from ICD-10 codes, medication prescriptions from National Drug Code (NDC), and laboratory test results from Logical Observation Identifiers Names and Codes (LOINC), (section 2.2).
Ye also discloses patients who suffered multiple falls during the targeted time frame were chart-reviewed by internal physician curators such that only the first fall records were utilized in our analysis, and further extracting predictors from standard nomenclature and clinical ontology codes, including binarizing medication information, indicating transforming and standardizing of data (section 2.2; section 4.4, para 2).
However, with respect to claims 1, 4, 17, and 21, Ye does not disclose using a natural language processing techniques to extract the features.
However, the prior art to Ford, in the same field of endeavor, reviews extracting information from the free-form text of electronic medical records (EMRs) to improve case detection and discloses text in EMRs is accessible, especially with open source information extraction algorithms, and significantly improves case detection when combined with code, and further discloses numerous established NLP algorithms used for information extraction from EMRs (title; abstract; p 4, col 1, para 2-4).
Furthermore, with respect to claims 1, 17, and 21, the prior art to Nakatani, in the same field of endeavor, discloses verifying whether hospital inpatient falls can be predicted through the analysis of a single input—unstructured nursing records obtained from Japanese electronic medical records (EMRs)—using a natural language processing (NLP) algorithm and machine learning (abstract; p 3, col 1, para 1-p 4, col 1, para 2; textbox 1).
Nakatani discloses the nursing records of 335 fallers and 408 nonfallers for a 12-month period were extracted from the EMRs of an acute care hospital and randomly divided into two sets and the learning data set was subjected to NLP and machine learning to extract morphemes that contributed to separating fallers from nonfallers to construct a model for predicting falls (abstract).
Nakatani further discloses the EMRs contained (1) patients’ statements, (2) observations of the nurses, (3) results of vital check and various assessments, (4) descriptions of medical treatment and administration of drugs (or plan for them), (5) messages to and from patients, and (6) any other
comments by nurses (p 2, col 2, para 5-p3, col 2, para 1).
Nakatani discloses that because nursing records contain continuous information covering a broad context regardless of the underlying disease or complications and results of various medical tests and vital signs, this algorithm can be applied to construct models for predicting other specific medical interests, such as a sudden change of the patient’s condition or recurrence of acute illness and also has the potential to be used as the basis of a multipurpose diagnosis and caregiving support system (p 11, col 1, para 3).
Nakatani further discloses NLP algorithm combined with machine learning can effectively extract risk factors for falls from nursing records and falls among hospital inpatients can be predicted by analyzing nursing records using an NLP algorithm and machine learning.
Therefore, it would have been prima facie obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have used an NPL model to extract the features from free-form text in the EHR as this was a known technique at the effective filing date of the claimed invention, as disclosed by Ford. Furthermore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the steps for determining fall risk based on analysis of the EMR disclosed by Ye, with the use of NLP processing to identify features as disclosed by Nakatani because NLP algorithm combined with machine learning can effectively extract risk factors for falls from nursing records and falls among hospital inpatients can be predicted by analyzing nursing records using an NLP algorithm and machine learning. There would be a reasonable expectation of success because augmenting the manual process of identifying feature vectors through clinician review by applying NPL would not impede the steps of Ye.
Furthermore, while Ye discloses extracting predictors from standard nomenclature and clinical ontology codes, including binarizing medication information, indicating transformation and standardization of data, Ye does not appear to disclose transforming continuous features and vitals features of the features from initially entered values into transformed feature values having one or more standardized units of measurement (section 2.2; section 4.4, para 2).
However, with respect to claims 1, 17, 19 and 21-22, the prior art to Abhyankar, in the same field of endeavor, discloses clinical databases provide a rich source of data for answering clinical research questions but the variables recorded in clinical data systems are often identified by local, idiosyncratic, and sometimes redundant and/or ambiguous names (or codes) rather than unique, well-organized codes from standard code systems, and this reality discourages research use of such databases, because researchers must invest considerable time in cleaning up the data before they can ask their first research question, and further discloses standardizing clinical laboratory data for secondary use by cleaning up the data and mapping the variable names and codes to LOINC codes (title; abstract).
Abhyankar further discloses the LOINC database is maintained by the Regenstrief Institute and the latest release contains over 68,000 standard codes for identifying laboratory tests, clinical measures, survey instruments and narrative reports, and that each LOINC term has six main parts: (1) component (the specific lab analyte or physiologic measure); (2) property (such as mass concentration or ratio); (3) timing (such as 24-h collection or one point in time); (4) specimen type (e.g., blood or urine); (5) scale (such as quantitative or qualitative); and (6) method used (such as a specific lab technique or estimated versus measured), and that LOINC variables also include example units of measure when appropriate, short name, and frequency statistics for the most common tests (section 2.2).
Abhyankar discloses extracting the data from EMRs, by tackling the laboratory test results first, gathering supporting data for disambiguation, and assigning codes (sections 3-4.2).
Abhyankar discloses working on mapping other patient data such as vital signs, ventilator parameters, and lab tests from chart events to LOINC (section 5.4).
Therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the steps for determining fall risk based on analysis of the EMR disclosed by Ye, with the steps of transforming the continuous and vitals data to from initially entered values into transformed feature values having one or more standardized units of measurement as disclosed by Abyhyankar because while clinical databases provide a rich source of data for answering clinical research questions but the variables recorded in clinical data systems are often identified by local, idiosyncratic, and sometimes redundant and/or ambiguous names (or codes) rather than unique, well-organized codes from standard code systems, and this reality discourages research use of such databases, because researchers must invest considerable time in cleaning up the data before they can ask their first research question. There would be a reasonable expectation of success because Ye also discloses standardizing data into binary and continuous forms, and also uses LOINC codes, indicating that the data input into the machine learning models are standardized.
Therefore, the invention is prima facie obvious.
Claim 23 is rejected under 35 U.S.C. 103 as being unpatentable over Ye et al. (International journal of medical informatics 2020, 137, p.1-7; previously cited; hereafter referred to as Ye), in view of Ford et al. (Journal of the American Medical Informatics Association 2016, 23(5), p 1-9; previously cited; hereafter referred to as Ford), Nakatani et al. (MIR medical informatics 2020, 8(4), pp.e1-14; newly cited; hereafter referred to as Nakatani) and Abhyankar et al. (Journal of biomedical informatics 2012, 45(4), pp.642-650; newly cited; hereafter referred to as Abhyankar) as applied to claim 21 above, and further in view of Wang et al. (NPJ digital medicine, 2(1), 127, p 1-7; hereafter referred to as Wang).
With respect to claim 21, Ye, in view of Ford, Nakatani and Abyhyankar, discloses the steps of claim 21, as applied above. Ye discloses record of fall in EHR-based data essentially requires injury and subsequent visit to the doctor/hospital (section 3.1; section 4.3).
However, Ye does not disclose labeling the reference data based on the severity of injury.
However, the prior art to Wang, in the same field of endeavor, discloses develop a general predictive model for severity of falls among patient populations and predicting the severity of all kinds of injuries of inpatient falls, using an advanced machine learning method multi-view ensemble leaning to efficiently exploit the multidimensional patient data, and studying the data in further detail, statistical tests indicated some differences between minor and severe injury levels with respect to certain variables, indicating the severity of the injury cause by a fall was labeled in the training data (abstract; p 1, col 2, para 3-p 2 col 1, para 1; table 1).
Wang further discloses patient falls lead to increased medical care costs, lengthened hospital stays, more litigation, and even death, and existing methods and technology to address this problem mostly focus on stratifying inpatients at risk, without predicting fall severity or injuries, and the severe fall index is calculated to identify inpatients who are at risk of having severe injuries if they fall, thus triggering additional steps of intervention to prevent a harmful fall, beyond the standard-of-care procedure for all high-risk fall patients (abstract).
Therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the steps of Ye for determining fall risk with the method for predicting the severity of injury associated with a fall, by including labeled severity of injury reference data as disclosed by Wang, because patient falls lead to increased medical care costs, lengthened hospital stays, more litigation, and even death, and existing methods and technology to address this problem mostly focus on stratifying inpatients at risk, without predicting fall severity or injuries, and the severe fall index is calculated to identify inpatients who are at risk of having severe injuries if they fall, thus triggering additional steps of intervention to prevent a harmful fall, beyond the standard-of-care procedure for all high-risk fall patients. There would be a reasonable expectation of success because extracting and using severity injury data that is available in the EHR as a predictor would not impede the methods of Ye. Therefore, the invention is prima facie obvious.
Response to Applicant’s Arguments
Applicant’s Arguments have been fully considered and new art has been applied to teach the amended limitations.
Conclusion
No claims allowed.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Inquiries
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NIDHI DHARITHREESAN whose telephone number is (571)272-5486. The examiner can normally be reached Monday - Friday 9:00 - 5:00.
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, Larry D Riggs II can be reached at (571) 270-3062. 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.
/N.D./ Examiner, Art Unit 1686
/Karlheinz R. Skowronek/ Supervisory Patent Examiner, Art Unit 1687
Prosecution Insights