DETAILED ACTION
Applicant's response, filed 03/12/2026, has been fully considered. The following rejections and/or objections are either reiterated or newly applied. They constitute the complete set presently being applied to the instant application.
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 .
Claim Status
Claims 1-20 are pending.
Claims 1-20 are rejected.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 12/08/2025 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 112
Response to Amendment
In view of applicant’s amendments to the claims, specifically regarding claims 1, 5, 9, and 15, previous rejections under 35 U.S.C. 112 have been withdrawn.
Claim Rejections - 35 USC § 101
Response to Amendment
In view of applicant’s amendments to the claims the previous rejection under 35 U.S.C. 101 has been reviewed, updated, and provided below.
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.
Any newly recited portions herein are necessitated by claim amendments.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to abstract ideas without significantly more. The claims recite a method, system and CRM for modeling severity attributes of cancer treatments through patient data. The judicial exception is not integrated into a practical application because while claims 1-20 attempt to integrate the exception into a practical application, said application is either generically recited computer elements that do not add a meaningful limitation to the abstract idea or it is insignificant extra solution activity and simply implementing the abstract idea on a computer. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the computer elements only store and retrieve information in memory as well as perform basic calculations that are known to be well-understood, routine and conventional computer functions as recognized by the decisions listed in MPEP § 2106.05(d).
Framework with which to Analyze Subject Matter Eligibility:
Step 1: Are the claims directed to a category of statutory subject matter (a process, machine, manufacture, or composition of matter)? [see MPEP § 2106.03]
Claims are directed to stator subject matter, specifically methods (1-8), a machine (9-14), and a CRM (15-20).
Step 2A Prong One: Do the claims recite a judicially recognized exception, i.e., an abstract idea, a law of nature, or a natural phenomenon? [see MPEP § 2106.04(a)]
The claims herein recite abstract ideas, mental processes and mathematical concepts.
With respect to the Step 2A Prong One evaluation, the instant claims are found herein to recite abstract ideas that fall into the grouping of mental processes and mathematical concepts.
Claims 1, 9 and 15: Identifying a condition-specific subset of data records, initiating a pre-processing process, excluding one or more data records based upon a criteria, generating a set of output data, selecting a machine learning model, generating a merged set of data, are all processes of receiving, evaluating, and manipulating data, or calculating specific functions, all of which can be performed in the human mind and are therefore, mental processes and/or mathematical concepts.
Claims 2, 10 and 16: Selecting a pre-processing process from a subset of three that have been trained using a subset of patient data specific to each process and a cancer type identifier to generate model input data is a process of selecting a methodology and evaluating data requisite for such, which a human mind is capable of and is therefore a mental process.
Claims 3, 11 and 17: Specify the filtering criteria based upon a specified cancer identifier along with the creation of a dataset following such criteria for the three pre-processing models, which merely describe processes of selecting a methodology and evaluating data requisite for such, which a human mind is capable of and is therefore a mental process.
Claims 4, 12 and 18: Specifying a data-based filter, a source-based filter, and/or a content-based filter for selecting data records is merely describing a process of selecting a methodology and evaluating data requisite for such, which a human mind is capable of and is therefore a mental process.
Claims 5, 13 and 19: The machine-learning model being specified as a linear regression model is an algorithm/equation, which is a mathematical concept.
Claims 6, 14 and 20: Excluding observational data for failing to a satisfy a rule of a sub-process is merely filtering data, which is a process of evaluating data which a human mind is capable of and is therefore, a mental process.
Claim 7: Determining observation data to retain is merely receiving, evaluating, and manipulating data which a human mind is capable of and is therefore, a mental process.
Claim 8: Generating a derived data element within an observational data record is the imputation of data which is merely filling in missing data based on surrounding data, which a human mind is capable of and is therefore, a mental process.
Step 2A Prong Two: If the claims recite a judicial exception under prong one, then is the judicial exception integrated into a practical application? [see MPEP § 2106.04(d) and MPEP §
2106.05(a)-(c) & (e)-(h)]
Because the claims do recite judicial exceptions, direction under Step 2A Prong Two provides that the claims must be examined further to determine whether they integrate the abstract ideas into a practical application.
The following claims recite the following additional elements in the form of non-abstract elements:
Claims 1-20: Receiving a set of observation data records, retrieving data, and providing output data records are insignificant extra solution activities that do not add a meaningful limitation, specifically mere data gathering and necessary data outputting (See Performing clinical tests on individuals to obtain input for an equation, In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989), Performing repetitive calculations, Flook, 437 U.S. at 594, 198 USPQ2d at 199 (recomputing or readjusting alarm limit values); Bancorp Services v. Sun Life, 687 F.3d 1266, 1278, 103 USPQ2d 1425, 1433 (Fed. Cir. 2012) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis)) [see MPEP § 2106.5(g)]. A computer-implemented method is a generic and nonspecific element of computers [See MPEP § 2106.04(d)(1) and MPEP § 2106.05(f)]. Training the selected machine learning model merely recites only the idea of a solution or outcome and therefore amounts to nothing more than the words “apply it” (See Electric Power Group, LLC v. Alstom, S.A., 830 F.3d 1350, 1356, 119 USPQ2d 1739, 1743-44 (Fed. Cir. 2016); Intellectual Ventures I v. Symantec, 838 F.3d 1307, 1327, 120 USPQ2d 1353, 1366 (Fed. Cir. 2016); Internet Patents Corp. v. Active Network, Inc., 790 F.3d 1343, 1348, 115 USPQ2d 1414, 1417 (Fed. Cir. 2015)) [See MPEP § 2106.05(f)].
Claims 9-14: A system, memory storage areas, and processors are all generic and nonspecific elements of computers [See MPEP § 2106.04(d)(1) and MPEP § 2106.05(f)].
Claims 15-20: A computer program product, non-transitory computer readable storage medium, and computer readable program code portions are all generic and nonspecific elements of computers [See MPEP § 2106.04(d)(1) and MPEP § 2106.05(f)].
Step 2B: If the claims do not integrate the judicial exception, do the claims provide an inventive concept? [see MPEP § 2106.05]
Because the additional claim elements do not integrate the abstract idea into a practical application, the claims are further examined under Step 2B, which evaluates whether the additional elements individually and in combination amount to significantly more than the judicial exception itself by providing an inventive concept.
The claims do not recite additional elements that are sufficient to amount to significantly more than the judicial exception because the claims recite additional elements that are generic, conventional or nonspecific. These additional elements include:
The additional elements of a system, memory storage areas, processors, computer program product, non-transitory computer readable storage medium, a computer-implemented method, and computer readable program code portions are all generic computer elements used to perform abstract ideas and therefore do not provide an inventive concept, and similarly, non-particular instructions to gather or produce data for analysis do not provide an inventive concept [see MPEP § 2106.5(d), 2106.05(f) and 2106.05(g)]. The use of said computer components to perform data manipulation is a well-known, routine, and conventional activity to one of ordinary skill in the art. The judicial exceptions alone cannot provide that inventive concept or practical application [see MPEP § 2106.5]. Therefore, taken both individually and as a whole, the additional elements do not amount to significantly more than the judicial exception by providing an inventive concept.
The additional element of receiving a set of observation data records, training the selected machine learning model (Conventional: Alzubi et al. Page 6, Paragraph 1), and providing output data records data gathering is a necessary process that is a well-known and insignificant extra-solution activity that does not add significantly more (See Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information), Performing repetitive calculations, Flook, 437 U.S. at 594, 198 USPQ2d at 199 (recomputing or readjusting alarm limit values); Bancorp Services v. Sun Life, 687 F.3d 1266, 1278, 103 USPQ2d 1425, 1433 (Fed. Cir. 2012), OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network) and Performing repetitive calculations, Flook, 437 U.S. at 594, 198 USPQ2d at 199 (recomputing or readjusting alarm limit values); Bancorp Services v. Sun Life, 687 F.3d 1266, 1278, 103 USPQ2d 1425, 1433 (Fed. Cir. 2012)) [see MPEP § 2106.5(d)]. The judicial exceptions alone cannot provide that inventive concept or practical application [see MPEP § 2106.5]. Therefore, taken both individually and as a whole, the additional elements do not amount to significantly more than the judicial exception by providing an inventive concept.
Therefore, claims 1-20, when the limitations are considered individually and as a whole are rejected under 35 USC § 101 as being directed to non-statutory subject matter.
Response to Arguments
Applicant's arguments filed 03/12/2026 have been fully considered but they are not persuasive.
Applicant asserts on page 12 of the Remarks filed 3/12/2026 that the claims are directed to an improvement to technology, specifically citing improvements to the accuracy and processing speed. However, examiner reminds applicant that according to MPEP 2106.05(a) - It is important to note, the judicial exception alone cannot provide the improvement. The improvement can be provided by one or more additional elements. Furthermore, according Ex Parte Desjardins, Appeal No. 2024-000567 (PTAB September 26, 2025, Appeals Review Panel Decision) (precedential) - the claimed invention was a method of training a machine learning model on a series of tasks. The Appeals Review Panel (ARP) overall credited benefits including reduced storage, reduced system complexity and streamlining, and preservation of performance attributes associated with earlier tasks during subsequent computational tasks as technological improvements that were disclosed in the patent application specification – which are improvements to the additional elements. Conversely within the instant application improvements are directed to the abstract ideas, as described further below in comments addressing applicants concerns regarding Step 2A Prong Two. As such, the improvement must be directed to the additional elements of the claim, or additional elements in conjunction with the judicial exception. However, in this case the additional elements are merely generically recited computer elements or data gathering/outputting which cannot be the basis for such as shown in the above rejection and described further below in comments addressing applicants Step 2B concerns. Therefore, the claims are not directed to an improvement to technology.
Applicant asserts on page 16 of the Remarks filed 3/12/2026 that regarding Step 2A Prong One that “claim 1 recites specific implementation steps that cannot practically be performed in a human mind”, more specifically that “human cannot train a selected machine-learning model using a generated merged set of data records - notably these operations are grounded in machine operations by definition. Moreover, a human mind cannot use the selected machine-learning model to generate a predicted severity score”. However, examiner reminds applicant that while a machine learning technique or the training of such is considered an additional element, the mere use of an additional element to perform an abstract idea does not make said abstract idea no less abstract. Additionally, the generation of a predicted severity score is merely the mathematical calculation or process of using said trained machine learning techniques. The generation of a merged set of data records too is therefore a mental process as it is merely combining information based upon some shared characteristic irrespective of the machine learning technique under the broadest reasonable interpretation. Furthermore, applicant asserts similarity to Example 39 of the Subject Matter Eligibility Examples, however the difference between the instant application and Example 39 lies in the additional elements used as basis for the improvements. In the example the recited additional elements are decidedly not recitations of judicial exceptions for the fact that they recite methods that cannot be performed within the human mind, specifically related to computer vision and the transformation of images that cannot be performed in the human mind because of the way computers “read” images. Conversely the instant application merely uses and transforms existing data records which are definitionally interpretable by human minds.
Applicant asserts on page 17 of the Remarks filed 3/12/2026 that regarding Step 2A Prong Two, the invention of claim 1 is an improvement to a computer or other technology. However, examiner reminds applicant that any improvement must come from the additional elements either alone or in conjunction with the judicial exception, as according to MPEP 2106.05(a) - It is important to note, the judicial exception alone cannot provide the improvement. However, applicant asserts the improvement is the outcome of the method, the rectified data, as this rectified data improves the accuracy of the model. However these improvements are themselves directed to the abstract ideas, and not the additional elements either alone or in conjunction with the judicial exception as required by MPEP 2106.05(a).
Applicant asserts regarding Step 2B that the additional elements of claim 1 are not conventional, on page 20 under Step 2B, specifically that the combination of operations and data structures is not conventional. However, examiner reminds applicant that the additional elements as recited are merely insignificant extra solution activity of gathering data or are generic computer elements which according to MPEP 2106.05(d) are already recognized by the courts as well-understood, routine, and conventional (See Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network)).
Claim Rejections - 35 USC § 103
Response to Amendment
In view of applicant’s amendments to the claims the previous rejections under 35 U.S.C. 103 have been updated and provided below.
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.
Claims 1-6 and 9-20 are rejected under 35 U.S.C. 103 as being unpatentable over Bess et al. (US 10572461 B2; previously cited) in view of Tucker et al. (US 20180089376 A1; previously cited), Potter et al. (US 20170293734 A1; previously cited), Ehrenstein et al. (Agency for Healthcare Research and Quality (2019) 52-80; previously cited), Farhangfar et al. (IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans (2007) 692-709; previously cited), Alzubi et al. (Journal of physics: conference series (2018) 1-15; newly cited), and van Buuren et al. (Journal of Statistical Software (2011) 1-67; previously cited).
Claim 1 is directed to a method for automatically modeling severity attributes of cancer treatments via the use of patient data and trained machine learning models for data repair.
Claim 9 is directed to a system for automatically modeling severity attributes of cancer treatments via the use of patient data and trained machine learning models for data repair.
Claim 15 is directed to a CRM for automatically modeling severity attributes of cancer treatments via the use of patient data and trained machine learning models for data repair.
Bess et al. teaches in paragraph 8 “receiving, by a processor, a plurality of electronic healthcare records each having a plurality of different fields”, reading on receiving, by one or more processors, a set of independently generated observation data records comprising structured observation data for the patient. Bess et al. further teaches on page 30, column 33, line 24 “An example of information returned in a search according to selected filters is provided. The information includes a) a user 714, which is associated with an action on the MPI database, b) a date/time 716 recorded for the action”, and in claim 1 “performing real-time searches across all of the plurality of electronic healthcare records to find duplicate matches among the plurality of electronic healthcare records”, reading on initiating, by one or more processors, a pre-processing process for the condition-specific subset of observation data records. Bass et al. further teaches on page 27, column 28, line 50 “The filter/sort 322 buttons can be selected to provide options for filtering and sorting results returned from a search. A selection of the options button 324 can cause different search query options to be displayed”, and on page 30, column 33, line 12 “As an example, a filter 702 can be provided which allows all or a subset of users to be selected. As another example, a filter 704 can be provided which allows a time period to be selected. In yet another example, a filter 706 can be provided which allows actions associated with a particular software application (module) to be selected. In a further example, a filter 708 can be provided which allows a user to select from one or more types of actions performed, such as an update or a merge. The filters can be selected alone or in combination with one another and then a search can be initiated when the go button 710 is selected”, reading on executing one or more first subprocesses to exclude one or more data records from the condition-specific subset of observation data records, wherein the excluded one or more data records fail to satisfy one or more filter criteria and executing one or more second subprocesses to generate a set of output data records comprising one or more output data records of the condition-specific subset of observation data records.
Tucker et al. teaches on page 6, paragraph 70, lines 1-2 “Biomarker status selector 610 enables the user to select a biomarker status” with figures 8-14 and figure 16 illustrating KRAS indicators and a ROS1 indicator as “health data associated with a selected patient” according to page 7, paragraph 72, line 8, reading on a common cancer type identifier and based at least in part on the common cancer type identifier and in view of Bess et al. teachings of merging data records, renders obvious having at least one shared identifier, wherein the at least one shared identifier indicates a cancer stage associated with the common cancer type identifier.
Potter et al. teaches in claim 1 “receiving, by communications circuitry of a computing device, a medical report; deriving, by natural language processing (NLP) circuitry of the computing device, a textual component of the medical report; identifying, by the NLP circuitry of the computing device, one or more medical findings from the textual component; determining, by the NLP circuitry of the computing device, a clinical context for each of the one or more medical findings; identifying, by incidental finding circuitry of the computing device, one or more clinical cues comprising a gradient severity from the one or more medical findings”, specifically Potter et al. teaches in paragraph [0029] that their gradient severity is generated from medical findings and clinical cues and in paragraph [0072] expressly state “the clinical cue severities and condition signal risks thus comprise a “gradient” score that drives the overall risk” which are calculated from gradient levels of various cues and risks (paragraph [0070]), thereby reading on a predicted severity score indicating a complexity associated with one or more cancer treatments for the patient, wherein the predicted severity score is based at least in part on one or more health aspects of the patient.
Ehrenstein et al. teaches on page 54, paragraph 1 “EHRs provide various types of data that can be linked, integrated, or merged directly into a registry. The Meaningful Use program has led to the collection of a Common Clinical Data Set (CCDS) across most providers. These data are now generally available in EHRs; the data that are commonly available will likely continue to expand as Office of the National Coordinator, under the 21st Century Cures Act, moves toward building Core Data for Interoperability (USCDI) requirement.8 EHRs can also provide data types of emerging interest to registries”, page 55, paragraphs 1-2 “In addition to these data, EHRs capture a considerable amount of unstructured data (e.g., clinical notes) that can be further processed to extract specific data of importance to a registry (e.g., specific information extracted from radiology reports to determine eligibility). Data types commonly extracted from EHRs and imported into registries are patient identifiers, demographics, diagnoses, medications, procedures, laboratory results, vital signs, and utilization events”, and Table 4-2 details types of HER data that can be integrated and interfaced with additional registries and datasets, reading on generating, by the one or more processors linking the one or more output data records and one or more externally-provided results data records, a merged set of data records, wherein the one or more externally-provided results data records indicate one or more objective severity attributes associated with a performed treatment.
Alzubi et al. teaches on page 6, paragraph 1 as part of the Genertic Model of ML, the six components of ML models including “Training: After selecting the appropriate algorithm and suitable parameter values, the model needs to be trained using a part of the dataset as training data”.
Van Buuren et al. teaches in the abstract “The R package mice imputes incomplete multivariate data by chained equations. The software mice 1.0 appeared in the year 2000 as an S-PLUS library, and in 2001 as an R package. mice 1.0 introduced predictor selection, passive imputation and automatic pooling. This article documents mice 2.9, which extends the functionality of mice 1.0 in several ways. In mice 2.9, the analysis of imputed data is made completely general, whereas the range of models under which pooling works is substantially extended. mice 2.9 adds new functionality for imputing multilevel data, automatic predictor selection, data handling, post-processing imputed values, specialized pooling routines, model selection tools, and diagnostic graphs”, and on page 2, paragraph 1 “FCS specifies the multivariate imputation model on a variable-by-variable basis by a set of conditional densities, one for each incomplete variable. Starting from an initial imputation, FCS draws imputations by iterating over the conditional densities. A low number of iterations (say 10{20) is often sufficient. FCS is attractive as an alternative to JM in cases where no suitable multivariate distribution can be found. The basic idea of FCS is already quite old, and has been proposed using a variety of names: stochastic relaxation (Kennickell 1991), variable-by-variable imputation (Brand 1999), regression switching (van Buuren et al. 1999), sequential regressions (Raghunathan et al. 2001), ordered pseudo-Gibbs sampler (Heckerman et al. 2001), partially incompatible MCMC (Rubin 2003), iterated univariate imputation (Gelman 2004), MICE (van Buuren and Oudshoorn 2000; van Buuren and Groothuis-Oudshoorn 2011) and FCS (van Buuren 2007)”, reading on selecting, by one or more processors, a machine-learning model selected from a plurality of machine-learning based models based at least in part on health aspects of the patient which impact a complexity associated with one or more identifiers present within at least one of the one or more output data records, and in view of Alzubi et al., training, using the merged set of data records and the predicted severity score, the selected machine-learning model. Additionally, the MICE method outlined uses linear regression to jointly model a multivariate normal distribution for a given condition, specified on page 7 paragraph 2, which reads on generating by one or more processors and by providing the set of output data records to the machine learning model, a predicted severity score indicative of the one or more severity attributes for the patient, wherein the one or more severity attributes are based at least in part on health aspects of the patient which impact a complexity associated with one or more cancer treatments.
It would have been obvious at the time of invention to combine the methods of Bess et al. for managing index databases, the teachings of Ehrenstein et al. for merging EHR datasets based on various information including diagnosis and severity, and the teachings of van Buuren et al. for imputing missing data using regression modeling to predict missing values as each source revolves around the building of data through evaluating, filtering, or predicting missing values which are common amongst EHR datasets. As Farhangfar et al. points out in the abstract “Many of the industrial and research databases are plagued by the problem of missing values”. It would have also been obvious to incorporate the teachings of Alzubi et al. as they specifically provide a review of the best practices in machine learning, for which regression modeling is machine learning. Additionally, it would have then been obvious to incorporate the teachings of Tucker et al. for visualizing medical data, particularly cancer data, to better integrate, merge, and impute missing data from said EHR datasets, along with the teachings of Potter et al. for then using said EHR datasets to calculate a clinical context or gradient severity score for a clinical outcome based on the diagnosis or severity that was previously used in Ehrenstein et al. and imputed by van Buuren et al. One would have had a reasonable expectation of success given that each revolves around database and/or dataset management, and van Buuren et al. provides a unique way for integrating filtering along with machine learning for imputing missing data, or in the case of the application predicting a severity score from surrounding missing information. Therefore, it would have been obvious to one with ordinary skill in the art to incorporate the teachings of each and to be successful.
Claim 2 is directed to the method of claim 1 but further specifies that the subprocess of pre-processing be split into three processes that effectively create three models defined by the relevant cancer identifiers and corresponding data.
Claim 10 is directed to the system of claim 9 but further specifies that the subprocess of pre-processing be split into three processes that effectively create three models defined by the relevant cancer identifiers and corresponding data.
Claim 16 is directed to the CRM of claim 15 but further specifies that the subprocess of pre-processing be split into three processes that effectively create three models defined by the relevant cancer identifiers and corresponding data.
Bess et al. teaches in paragraph 6 “The inverted index formulation enables faster, more complete and more flexible duplicate detection as compared to traditional master patient database management techniques”, reading on the limitation of selecting a methodology from multiple methodologies.
Tucker et al. teaches on page 6, paragraph 70, lines 1-2 “Biomarker status selector 610 enables the user to select a biomarker status”, with figures 8-14 and figure 16 illustrating KRAS indicators and a ROS1 indicator as “health data associated with a selected patient” according to page 7, paragraph 72, line 8, reading on the limitation of a methodology related to cancer.
Claim 3 is directed to the method of claim 2 and thus claim 1, but further specifies the first cancer identifier to comprise a Small-Cell Lung Cancer identifier, the second identifier to be one or more of a breast, colon, rectal, or non-Small-Cell Cancer Identifier, and the third identifier to comprise a prostate identifier.
Claim 11 is directed to the system of claim 10 and thus claim 9, but further specifies the first cancer identifier to comprise a Small-Cell Lung Cancer identifier, the second identifier to be one or more of a breast, colon, rectal, or non-Small-Cell Cancer Identifier, and the third identifier to comprise a prostate identifier.
Claim 17 is directed to the CRM of claim 16 and thus claim 15, but further specifies the first cancer identifier to comprise a Small-Cell Lung Cancer identifier, the second identifier to be one or more of a breast, colon, rectal, or non-Small-Cell Cancer Identifier, and the third identifier to comprise a prostate identifier.
Bess et al. teaches in paragraph 172 “An example of information returned in a search according to selected filters is provided. The information includes a) a user 714, which is associated with an action on the MPI database, b) a date/time 716 recorded for the action”, reading on the limitation of filtering records.
Tucker et al. teaches on page 6, paragraph 70, lines 1-2 “Biomarker status selector 610 enables the user to select a biomarker status”, with figures 8-14 and figure 16 illustrating KRAS indicators and a ROS1 indicator as “health data associated with a selected patient” according to page 7, paragraph 72, line 8, reading on the limitation of a methodology related to cancer.
Claim 4 is directed to the method of claim 1 but further specifies that the filtering subprocesses be done via date, source, and/or content.
Claim 12 is directed to the system of claim 9 but further specifies that the filtering subprocesses be done via date, source, and/or content.
Claim 18 is directed to the CRM of claim 15 but further specifies that the filtering subprocesses be done via date, source, and/or content.
Bess et al. teaches in paragraph 172 “An example of information returned in a search according to selected filters is provided. The information includes a) a user 714, which is associated with an action on the MPI database, b) a date/time 716 recorded for the action”, reading on filtering records by date.
Tucker et al. teaches on page 6, paragraph 70, lines 1-2 “Biomarker status selector 610 enables the user to select a biomarker status”, with figures 8-14 and figure 16 illustrating KRAS indicators and a ROS1 indicator as “health data associated with a selected patient” according to page 7, paragraph 72, line 8, reading on the limitation of a methodology related to cancer.
Claim 5 is directed to the method of claim 1 but further specifies that the machine learning model selected is a linear regression.
Claim 13 is directed to the system of claim 9 but further specifies that the machine learning model selected is a linear regression.
Claim 19 is directed to the CRM of claim 15 but further specifies that the machine learning model selected is a linear regression.
Van Buuren et al. teaches in the abstract “The R package mice imputes incomplete multivariate data by chained equations. The software mice 1.0 appeared in the year 2000 as an S-PLUS library, and in 2001 as an R package. mice 1.0 introduced predictor selection, passive imputation and automatic pooling. This article documents mice 2.9, which extends the functionality of mice 1.0 in several ways. In mice 2.9, the analysis of imputed data is made completely general, whereas the range of models under which pooling works is substantially extended. mice 2.9 adds new functionality for imputing multilevel data, automatic predictor selection, data handling, post-processing imputed values, specialized pooling routines, model selection tools, and diagnostic graphs”, and on page 2, paragraph 1 “FCS specifies the multivariate imputation model on a variable-by-variable basis by a set of conditional densities, one for each incomplete variable. Starting from an initial imputation, FCS draws imputations by iterating over the conditional densities. A low number of iterations (say 10{20) is often sufficient. FCS is attractive as an alternative to JM in cases where no suitable multivariate distribution can be found. The basic idea of FCS is already quite old, and has been proposed using a variety of names: stochastic relaxation (Kennickell 1991), variable-by-variable imputation (Brand 1999), regression switching (van Buuren et al. 1999), sequential regressions (Raghunathan et al. 2001), ordered pseudo-Gibbs sampler (Heckerman et al. 2001), partially incompatible MCMC (Rubin 2003), iterated univariate imputation (Gelman 2004), MICE (van Buuren and Oudshoorn 2000; van Buuren and Groothuis-Oudshoorn 2011) and FCS (van Buuren 2007)”, reading on the selected machine-learning model being a linear regression model.
Claim 6 is directed to the method of claim 1 but further specifies that the subprocesses are configured to exclude one or more observation data records that fail to satisfy an intra-date conflict between cancer stage identifiers with both common and different dates.
Claim 14 is directed to the system of claim 9 but further specifies that the subprocesses are configured to exclude one or more observation data records that fail to satisfy an intra-date conflict between cancer stage identifiers with both common and different dates.
Claim 20 is directed to the CRM of claim 15 but further specifies that the subprocesses are configured to exclude one or more observation data records that fail to satisfy an intra-date conflict between cancer stage identifiers with both common and different dates.
Bess et al. teaches in paragraph 172 “An example of information returned in a search according to selected filters is provided. The information includes a) a user 714, which is associated with an action on the MPI database, b) a date/time 716 recorded for the action”, reading on filtering records by date.
Tucker et al. teaches on page 6, paragraph 70, lines 1-2 “Biomarker status selector 610 enables the user to select a biomarker status”, with figures 8-14 and figure 16 illustrating KRAS indicators and a ROS1 indicator as “health data associated with a selected patient” according to page 7, paragraph 72, line 8, reading on the limitation of a methodology related to cancer.
Claims 7 and 8 are rejected under 35 U.S.C. 103 as being unpatentable over Bess et al. (US 10572461 B2; previously cited) in view of Tucker et al. (US 20180089376 A1; previously cited), Potter et al. (US 20170293734 A1; previously cited), Ehrenstein et al. (Agency for Healthcare Research and Quality (2019) 52-80), Alzubi et al. (Journal of physics: conference series (2018) 1-15; newly cited), and van Buuren et al. (Journal of Statistical Software (2011) 1-67; newly cited) as applied to claims 1-6 and 9- 20 above, and further in view of Koopman et al. (International Journal of Medical Informatics (2015) 956-965).
Claim 7 is directed to the method of claim 1, but further specifies wherein at least one of the one or more second subprocesses is configured to retrieve one or more claims data records comprising diagnostic data to identify at least one observation data record to retain within the set of output data records.
Claim 8 is directed to the method of claim 7 and thus claim 1, but further specifies, wherein the at least one of the one or more second subprocesses is further configured to generate a derived data element within an observation data record based at least in part on the one or more claims data records.
Bess et al., Tucker et al., Potter et al., and van Buuren et al. teach the method of claims 1-6 and 9-20 as previously described.
Bess et al., Tucker et al., Potter et al., and van Buuren et al. do not teach that the subprocesses are configured to retrieve one or more claims data records comprising diagnostic data or to generate a derived data element within an observation data record, that are based at least in part on the one or more claims data records.
Koopman et al. teaches on page 957, column 1, paragraph 2 “we propose a system for the automatic classification of cancers from free-text death certificates. The system has two main components: (i) a natural language processing (NLP) pipeline that extracts detailed features (e.g., terms, n-grams, SNOMED CT codes and ICD-O properties) from death certificates; and (ii) a set of machine learning classifiers that exploit these features to determine the presence of cancers. The classifiers are deployed in a two-level, cascaded architecture: the first level identified the presence of cancer (i.e., binary cancer/nocancer) and the second level identifies the type of cancer (according to the ICD-10 classification system)”, reading on wherein at least one of the of one or more second subprocesses is configured to retrieve one or more claims data records comprising diagnostic data to identify at least one observation data record to retain within the set of output data records, and wherein the at least one of the one or more second subprocesses is further configured to generate a derived data element within an observation data record based at least in part on the one or more claims data records.
It would have been obvious at the time of invention to modify the teachings of Bess et al., Tucker et al., Potter et al., and van Buuren et al., for the method of claims 1-6 and 9-20, with the teachings of Koopman et al. for the incorporation of subprocesses that retrieve and generate datasets based on observation data for cancer data classification, because as Koopman et al. suggests on page 956, column 2, paragraph 1 “German et al. demonstrated the importance of analysing death certificates to record cancer-related causes of death for population-based cancer mortality statistics; such statistics from Cancer Registries are vital to measure the effectiveness of health-care systems and guide cancer control strategies”. One would have had a reasonable expectation of success given that the method aligns with the previous cited prior art in terms of field and goals, and is merely an additional avenue for teaching a machine learning model. Therefore, it would have been obvious to one with ordinary skill in the art to incorporate the teachings of each and to be successful.
Response to Arguments
Applicant's arguments filed 03/12/2026 have been fully considered but they are not persuasive.
Applicant asserts on page 20 of the Remarks filed 3/12/2026 that the cited references do not teach the claim limitations as currently recited. Examiner has provided new art which reads on the newly recited limitations, specifically looking at the training of the machine learning model and linking it with previous citations, specifically Potter et al. and van Burren et al. for an obviousness rationale in regards to training their models.
Applicant asserts on page 21 of the Remarks filed 3/12/2026 that the cited reference Potter et al. does not teach the severity score reflecting a complexity associated cancer treatments that reflects health aspects of the patient. However, paragraph [0103] of Potter et al. does teach a severity score for the one or more clinical cues and provides an example of lung consolidation, lesion or nodule. This is no different from the severity score of the instant application particularly in view of paragraph [0050] of Potter et al. – “The medical reports may comprise any report or set of reports describing a medical exam or patient treatment”.
Double Patenting
Response to Amendment
In view of applicant’s amendments to the claims, previous rejections to the claims under Double Patenting have been reviewed, updated, and provided below.
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, 4-5, 9, 12-13, 15, and 18-19 are provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1, 7-9, 13-15, and 19-20 of copending Application No. 17/344,510 (reference application) in view of Potter et al. (US 20170293734 A1) 2017. Although the claims at issue are not identical, they are not patentably distinct from each other because both are describing an invention for reconciling inconsistent cancer stage data records, and both are describing the same overall steps. The instant application involves the generation of a severity score, which is rendered obvious in view of Potter et al. teaching in claim 1 “receiving, by communications circuitry of a computing device, a medical report; deriving, by natural language processing (NLP) circuitry of the computing device, a textual component of the medical report; identifying, by the NLP circuitry of the computing device, one or more medical findings from the textual component; determining, by the NLP circuitry of the computing device, a clinical context for each of the one or more medical findings; identifying, by incidental finding circuitry of the computing device, one or more clinical cues comprising a gradient severity from the one or more medical findings”, specifically Potter et al. teaches in paragraph [0029] that their gradient severity is generated from medical findings and clinical cues and in paragraph [0072] expressly state “the clinical cue severities and condition signal risks thus comprise a “gradient” score that drives the overall risk” which are calculated from gradient levels of various cues and risks (paragraph [0070]).
It would have been obvious at the time of filing to modify the teachings of Application 17/344,510 for the overall method of claims 1, 9, and 15, with the teachings of Potter et al. for then using EHR datasets to calculate a clinical context or gradient severity score for a clinical outcome based on the diagnosis or severity to improve the method of Application 17/344,510. One would have had a reasonable expectation of success given this would be a mere substitution of methods, calculating a gradient score instead of using another machine learning method. Therefore, it would have been obvious at the time of filing to modify the teachings of each and to be successful.
This is a provisional nonstatutory double patenting rejection because the patentably indistinct claims have not in fact been patented.
Application 17/344,466
Application 17/344,510
Claims 1, 9 and 15: A computer-implemented method comprising: receiving, by one or more processors, a set of independently generated observation data records comprising structured observation data for a patient; identifying, by the one or more processors, a condition-specific subset of observation data records from the set of independently generated observation data records, wherein the condition- specific subset of observation data records comprise a common cancer type identifier; initiating, by the one or more processors and based at least in part on the common cancer type identifier, a pre-processing process for the condition-specific subset of observation data records, wherein the pre-processing process comprises: executing one or more first subprocesses to exclude one or more data records from the condition-specific subset of observation data records, wherein the one or more data records fail to satisfy one or more filter criteria, and executing one or more second subprocesses to generate a set of output data records comprising one or more output data records of the condition-specific subset of observation data records having at least one shared identifier, wherein the at least one shared identifier indicates a cancer stage associated with the common cancer type identifier; selecting, by the one or more processors, a machine-learning model from a plurality of machine-learning based models based at least in part on the at least one shared identifier; generating, by the one or more processors linking the one or more output data records and one or more externally-provided results data records, a merged set of data records, wherein the one or more externally-provided results data records indicate one or more objective severity attributes associated with a performed treatment; and training, using the merged set of data records, the selected machine-learning model to produce a predicted severity score indicating a complexity associated with one or more cancer treatments for the patient, wherein the predicted severity score is based at least in part on one or more health aspects of the patient.
Claim 1, 9 and 15: A computer-implemented method comprising: receiving, by one or more processors, a plurality of observation data records, wherein an observation data record of the plurality of observation data records comprises (i) a biomarker mutation indicator that indicates a mutation status of at least one gene and (ii) a timestamp; generating, by one or more processors, an input data set comprising a validated subset of the plurality of observation data records that comprises the observation data record, by applying a first filter and a second filter configured to identify and eliminate an inconsistent observation data record of the plurality of observation data records that fails to satisfy at least one of the first filter or the second filter, wherein: (i) the first filter is configured to identify the inconsistent observation data record responsive to (a) the inconsistent observation data record and a second observation data record comprising a corresponding timestamp and (b) the inconsistent observation data record comprising a first biomarker mutation indicator that conflicts with a second biomarker mutation indicator of the second observation data record, and (ii) the second filter is configured to identify inconsistent observation data record responsive to an inconsistent mutation status or an invalid progression of a set of biomarker mutation indicators associated with a plurality of timestamps within a set of observation data records that comprises the inconsistent observation data record generating, by one or more processors, a plurality of derived biomarker mutation indicators for each of the validated subset wherein a derived biomarker mutation indicator of the plurality of derived biomarker mutation indicators comprises a first derived biomarker mutation indicator generated based at least in part on the biomarker mutation indicator of the observation data record; and generating, by one or more processors and using a machine learning model, an output for the input data set based at least in part on the first derived biomarker mutation indicator of the validated subset.
Potter et al. teaches in claim 1 “receiving, by communications circuitry of a computing device, a medical report; deriving, by natural language processing (NLP) circuitry of the computing device, a textual component of the medical report; identifying, by the NLP circuitry of the computing device, one or more medical findings from the textual component; determining, by the NLP circuitry of the computing device, a clinical context for each of the one or more medical findings; identifying, by incidental finding circuitry of the computing device, one or more clinical cues comprising a gradient severity from the one or more medical findings”, specifically Potter et al. teaches in paragraph [0029] that their gradient severity is generated from medical findings and clinical cues, in paragraph [0072] expressly state “the clinical cue severities and condition signal risks thus comprise a “gradient” score that drives the overall risk” which are calculated from gradient levels of various cues and risks (paragraph [0070]), in paragraph [0050] “The medical reports may comprise any report or set of reports describing a medical exam or patient treatment”, and Paragraph [0103] “In some examples, the severity of the clinical cues is in turn used to generate the one or more condition signals. The properties and rules used to identify the clinical cues may also be used to evaluate the medical findings and corresponding clinical contexts to apply a gradient severity level for the clinical cues, such as strong, weak, or moderate. For example, a weak clinical cue for cancer (condition of concern) may include “lung consolidation” or “lesion” or “nodule.” In contrast, a strong clinical cue may include “malignancy” or “mass” or “tumor” or “neoplasm.” In this way, the incidental finding circuitry uses the condition of concern properties and rules for identifying the clinical cues and, in some examples, assigning a clinical severity for each of the identified clinical cues. In some embodiments, the clinical severity is determined from consultation of a repository of clinical expert guidance in combination with data analysis and trending of results. Additionally or alternatively, machine learning methods may be applied to refine the clinical severity of individual certain clinical cues”.
Claims 4, 12, and 18: The computer-implemented method of claim 1, wherein one or more filter criteria of the one or more first subprocesses comprise one or more of:a date-based filter criterion for selecting independently generated observation data records for further analysis as generated within a defined date range;a data source filter criterion for selecting independently generated observation data records for further analysis as generated by one or more defined data sources; or a data content filter criterion for selecting independently generated observation data records for further analysis as containing an identifier selected from a plurality of available identifiers eligible for further analysis.
Claims 7, 13, and 19: The computer-implemented method of claim 1, further comprising applying a preliminary filter criteria before generating the input data set, wherein the preliminary filter criteria comprises one or more of: a date-based filter criterion for selecting observation data records generated within a defined date range; a data source filter criterion for selecting observation data records generated by one or more defined data sources; or a data content filter criterion for selecting observation data records containing an identifier selected from a plurality of available identifiers eligible for further analysis.
Claims 5, 13, and 19: The computer-implemented method of claim 1, wherein the machine-learning model is a linear regression model.
Claims 8, 14, and 20: The computer-implemented method of claim 1, wherein the machine learning model is a linear regression model.
Response to Arguments
Applicant's arguments filed 3/12/2026 have been fully considered but they are not persuasive.
Applicant asserts on page 22 of the Remarks filed 3/12/2026 that the newly recited do not read on claims of co-pending application 17/344,510, specifically in view of amendments. However, examiner directs applicant to paragraphs [0050] and [0103] which teach the currently amended limitations of the independent claims as provided in the above rejection.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KEENAN NEIL ANDERSON-FEARS whose telephone number is (571)272-0108. The examiner can normally be reached M-Th, alternate F, 8-5.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Karlheinz Skowronek can be reached at 571-272-9047. 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.N.A./Examiner, Art Unit 1687
/OLIVIA M. WISE/Supervisory Patent Examiner, Art Unit 1685
Prosecution Insights