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 .
Status of Claims
This action is in reply to the application filed on 2/27/2025, wherein:
Claims 1-16 are currently pending and have been examined.
Drawing Objection
The following is a quotation of 37 CFR 1.84 (l):
(l) Character of lines, numbers, and letters. All drawings must be made by a process which will give them satisfactory reproduction characteristics. Every line, number, and letter must be durable, clean, black (except for color drawings), sufficiently dense and dark, and uniformly thick and well-defined. The weight of all lines and letters must be heavy enough to permit adequate reproduction. This requirement applies to all lines however fine, to shading, and to lines representing cut surfaces in sectional views. Lines and strokes of different thicknesses may be used in the same drawing where different thicknesses have a different meaning.
The following is a quotation of 37 CFR 1.84 (p):
(p) Numbers, letters, and reference characters.
(1) Reference characters (numerals are preferred), sheet numbers, and view numbers must be plain and legible, and must not be used in association with brackets or inverted commas, or enclosed within outlines, e.g., encircled. They must be oriented in the same direction as the view so as to avoid having to rotate the sheet. Reference characters should be arranged to follow the profile of the object depicted.
(2) The English alphabet must be used for letters, except where another alphabet is customarily used, such as the Greek alphabet to indicate angles, wavelengths, and mathematical formulas.
(3) Numbers, letters, and reference characters must measure at least .32 cm. (1/8 inch) in height. They should not be placed in the drawing so as to interfere with its comprehension. Therefore, they should not cross or mingle with the lines. They should not be placed upon hatched or shaded surfaces. When necessary, such as indicating a surface or cross section, a reference character may be underlined and a blank space may be left in the hatching or shading where the character occurs so that it appears distinct.
(4) The same part of an invention appearing in more than one view of the drawing must always be designated by the same reference character, and the same reference character must never be used to designate different parts.
(5) Reference characters not mentioned in the description shall not appear in the drawings. Reference characters mentioned in the description must appear in the drawings.
The drawings are objected to because:
Figs. 1, 2A, 2B, 3, and 4 contain text that is less than 1/8 inch in height as required by 37 CFR 1.84(p)(3); and
Figs. 2A, 2B, and 4 contain lines that are not sufficiently dense and dark to give the line satisfactory reproduction characteristics as required by 37 CFR 1.84(l).
Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application.
Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-16 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claims recite an apparatus and method for processing adjudication decisions which is considered a judicial exception because it falls under Certain Methods of Organizing Human Activity such as fundamental economic principles or practices, including insurance. This judicial exception is not integrated into a practical application as discussed below and the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception as discussed below.
This rejection follows the 2019 Revised Patent Subject Matter Eligibility Guidance, 84 Fed Reg 4, January 7, 2019, pp. 50-57 (“2019 PEG”)(MPEP 2106).
Analysis
Step 1 (Statutory Categories) – 2019 PEG pg. 53 (See MPEP 2106.03)
Claims 1-16 are directed to the statutory category of a process, machine, or manufacture.
Step 2A, Prong 1 (Do the claims recite an abstract idea?) – 2019 PEG pg. 54 (See MPEP 2106.04(a)-(c))
For independent claims 1 and 9, the claims recite an abstract idea of: processing adjudication decisions. The steps of independent claim 1 recite the abstract idea (in bold below) of: An apparatus for processing a plurality of records associated with respective adjudication decisions, comprising: a computer network interface to a network; a processor operatively connected to the computer network interface; and a memory storage operatively connected to the processor and having stored thereon machine-readable instructions that cause the processor, when executed, to: obtain, via the computer network interface, a plurality of records associated with respective one or more adjudication decisions; proceed, starting with a plurality of factors comprised in the obtained plurality of records and in an iterative or recursive manner, to: determine a number of factors for evaluating the obtained plurality of records, select the determined number factors from a plurality of factors comprised in the obtained plurality of records, identify a subset of records described by the selected factors, record the identified subset of records in association with the selected factors as a factor set to a data storage, and remove the subset of records from the obtained plurality of records for a next iteration until the obtained plurality of records have been all removed; and output a plurality of factor sets and associated subsets of records from the data storage for displaying the plurality of factor sets and associated subsets of records in correspondence with one or more adjudication decisions comprised in the associated subsets of records. Independent claim 9 recites similar steps that recite the abstract idea. Independent claims 1 and 9, as drafted, are a process that, under the broadest reasonable interpretation, covers Certain Methods of Organizing Human Activity, since they recite fundamental economic principles or practices, including insurance. If the claim limitations, under the broadest reasonable interpretation, covers methods of organizing human activity but for the recitation of additional elements including generic computer components, then it falls within the “Certain Methods of Organizing Human Activity” grouping of abstract ideas. Other than reciting the abstract idea, the independent claims recite additional elements including generic computer components such as “an apparatus, a computer apparatus, a computer network interface, a network, a processor, memory storage, data storage, and a computer apparatus”, and nothing in the claims precludes the steps from being performed as a method of organizing human activity. Accordingly, the independent claims recite an abstract idea.
Dependent claims 2-8, and 10-16 recite similar limitations as independent claims 1 and 9; and when analyzed as a whole are held to be patent ineligible under 35 U.S.C 101 because the additional recited limitations only refine the abstract idea further. Other than reciting the abstract idea, the dependent claims recite similar additional elements including generic computer components as the independent claims, such as “the apparatus, and the data storage”. If a claim limitation, under its broadest reasonable interpretation, covers fundamental economic principles or practices, but for the recitation of generic computer components, then it falls within the “Certain Methods of Organizing Human Activity” grouping of abstract ideas.
Step 2A, Prong 2 (Does the claim recite additional elements that integrate the judicial exception into a practical application?) – 2019 PEG pg. 54 (See MPEP 2106.04(d)-(c))
This judicial exception is not integrated into a practical application. In particular, independent claims 1 and 9 only recite the additional elements of “an apparatus, a computer apparatus, a computer network interface, a network, a processor, memory storage, data storage, and a computer apparatus”. A plain reading of the Figures and associated descriptions in the specification reveals that generic processors may be used to execute the claimed steps. The additional elements are recited at a high level of generality (i.e., as a generic processor performing generic computer functions) such that it amounts to no more than mere instructions to apply the exception using generic computer components (See MPEP 2106.05(f)) and limits the judicial exception to a particular environment (See MPEP 2106.05(h)). Mere instructions to apply an exception using a generic computer component and limiting the judicial exception to a particular environment doesn’t integrate the abstract idea into a practical application in Step 2A. Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. Hence, independent claims 1 and 9 are directed to an abstract idea.
Dependent claims 2-8, and 10-16, recite similar additional elements as the independent claims including generic computer components, such as “the apparatus, and the data storage”. The judicial exception is not integrated into a practical application because the additional elements in the dependent claims are also recited at a high-level of generality such that it amounts to more no more than mere instructions to apply the exception using generic computer components. Therefore, the additional elements do not integrate the abstract idea into a practical application because they also do not impose any meaningful limits on practicing the abstract idea. Also, the claims do not affect an improvement to another technology or technical field; the claims do not amount to an improvement of the functioning of a computer system itself; the claims do not effect a transformation or reduction of a particular article to a different state or thing; and the claims do not move beyond a general link of the use of an abstract idea to a particular technological environment.
Step 2B (Does the claim recite additional elements that amount to significantly more than the judicial exception?) – 2019 PEG pg. 56 (See MPEP 2106.05)
Independent claims 1 and 9 do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the recited additional elements amount to no more than mere instructions to apply the exception using a generic computer component (See MPEP 2106.05(f)) and limits the judicial exception to the particular environment of computers (See MPEP 2106.05(h)). The additional elements of the instant underlying process, when taken in combination, together do not offer substantially more than the sum of the function of the elements when each is taken alone. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept in Step 2B.
In addition, the dependent claims 2-8, and 10-16 do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of the dependent claims to perform the claimed limitations, amounts to no more than mere instructions to apply the exception using a generic computer component (See MPEP 2106.05(f)). Similar to the independent claims, mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. Also, for the same reasoning as the independent claims, the additional elements of the limitations of the dependent claims, when considered individually and as an ordered combination, together do not offer significantly more than the sum of the functions of the elements when each is taken alone and the dependent claims as a whole, do not amount to significantly more than the abstract idea itself. For these reasons, the dependent claims also are not patent eligible.
Claim Rejections - 35 USC § 102
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 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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-16 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by US 20260134486 to Hatfield et al. (hereinafter referred to as Hatfield).
In regards to claim 1, Hatfield discloses an apparatus for processing a plurality of records associated with respective adjudication decisions (system and method are provided for claim integrity in healthcare revenue cycle management, para. 0008), comprising: a computer network interface to a network (receiving operations may be performed by the CPU 1005 shown in FIG. 10, accessing data through the network interface 1020 and storing the received data in the system memory 1015, para. 0177); a processor operatively connected to the computer network interface; and a memory storage operatively connected to the processor (special-purpose computer 1000, shown in FIG. 10, includes CPU 1005, including multicore processors, AI processors 1010, including Graphics Processing Units (GPU) 1010A, Field-Programmable Gate Arrays (FPGA) 1010B, Application-Specific Integrated Circuits (ASIC) 1010C, Neural Processing Units (NPU) 1010D, Tensor Processing Units (TPU) 1010E, system memory 1015, network interface 1020, hard disk drive (HDD) interface 1025, external disk drive interface 1030, and input/output (I/O) interfaces 1035A, 1035B, 1035C, para. 0206, fig. 10) and having stored thereon machine-readable instructions that cause the processor, when executed (CPU 1005 may execute arithmetic, logic, and /or control operations by accessing the system memory 1015, para. 0206), to: obtain, via the computer network interface (receiving operations may be performed by the CPU 1005 shown in FIG. 10, accessing data through the network interface 1020 and storing the received data in the system memory 1015, par. 0177), a plurality of records associated with respective one or more adjudication decisions (receiving a first dataset from first data sources, including electronic health records and payer records, and historical medical claims, including those associated with approval and denial outcomes, para. 0009); proceed, starting with a plurality of factors comprised in the obtained plurality of records and in an iterative or recursive manner (receiving remittance data comprises parsing electronic remittance advice files in ANSI X12 835 format to extract denial codes, including claim adjustment reason codes and remittance advice remark codes, and mapping them to internal denial taxonomies, para. 0199), to: determine a number of factors for evaluating the obtained plurality of records (ACIS 304 may receive this normalized data and execute feature extraction operations to identify relevant attributes for claim analysis. The extracted features may include temporal patterns such as submission lag times, historical denial rates for specific payer-provider combinations, and coding relationship patterns, para. 0065), select the determined number factors from a plurality of factors comprised in the obtained plurality of records (data preprocessing module 402 may execute operations to generate feature vectors for each claim by identifying payer-specific denial rates over rolling time windows, encoding categorical variables using target encoding methods, and computing interaction features between procedure codes and diagnosis codes, para. 0072), identify a subset of records described by the selected factors (denial management module 408 may parse claim adjustment reason codes to classify denials into the following categories: authorization related, coverage-related, coding-related, timely filing, and medical necessity. The denial management module 408 may correlate denied claims with their original submission records to identify root causes of denial and patterns of denial behavior across payers, providers, and service lines, para. 0075), record the identified subset of records in association with the selected factors as a factor set to a data storage (machine learning models repository module 432 may be configured to store trained machine learning model artifacts, including model parameters, hyperparameters, feature schemas, preprocessing transformations, calibration curves, explainability summaries, and training metadata, para. 0091), and remove the subset of records from the obtained plurality of records for a next iteration until the obtained plurality of records have been all removed (ACIS applies the trained machine learning models to generate a denial probability score and a denial category classification for each medical claim, para. 0193); and output a plurality of factor sets and associated subsets of records from the data storage for displaying (EDA & pattern mining 616 component may perform exploratory data analysis and may identify patterns in claim denial data. The EDA & pattern mining 616 may implement clustering algorithms to group similar denial patterns and may use association rule mining to identify frequently co-occurring denial reasons, para. 0140) the plurality of factor sets and associated subsets of records in correspondence with one or more adjudication decisions comprised in the associated subsets of records (ACIS generates explainability values using SHAP to identify features that contribute to the denial probability score, providing the critical technical advantage of regulatory-compliant, transparent AI decisions. This enables every prediction to be traced back to specific claim features with quantified contribution values, which are essential for audit trails and payer appeals, para. 0193).
In regards to claim 2, Hatfield discloses the apparatus of claim 1, and further discloses wherein the number of factors is determined according to a probability distribution (next step may include correlating actual denial outcomes with predicted probabilities through probabilistic record linkage, utilizing claim control numbers and service line identifiers as matching keys, para. 0199).
In regards to claim 3, Hatfield discloses the apparatus of claim 1, and further discloses wherein the determined number of factors (ACIS 304 may receive this normalized data and execute feature extraction operations to identify relevant attributes for claim analysis. The extracted features may include temporal patterns such as submission lag times, historical denial rates for specific payer-provider combinations, and coding relationship patterns, para. 0065) are each selected (data preprocessing module 402 may execute operations to generate feature vectors for each claim by identifying payer-specific denial rates over rolling time windows, encoding categorical variables using target encoding methods, and computing interaction features between procedure codes and diagnosis codes, para. 0072) according to a probability distribution generated based on respective numbers of records described by respective ones of the plurality of factors (system and method provide receiving remittance data comprising parsing electronic remittance advice files to extract denial codes, correlating actual denial outcomes with predicted probabilities, and calculating a population stability index to detect distribution drift, para. 0016).
In regards to claim 4, Hatfield discloses the apparatus of claim 1, and further discloses wherein determining of the number of factors (ACIS 304 may receive this normalized data and execute feature extraction operations to identify relevant attributes for claim analysis. The extracted features may include temporal patterns such as submission lag times, historical denial rates for specific payer-provider combinations, and coding relationship patterns, para. 0065), the selecting of the determined number factors (data preprocessing module 402 may execute operations to generate feature vectors for each claim by identifying payer-specific denial rates over rolling time windows, encoding categorical variables using target encoding methods, and computing interaction features between procedure codes and diagnosis codes, para. 0072), and identifying of the subset of records (denial management module 408 may parse claim adjustment reason codes to classify denials into the following categories: authorization related, coverage-related, coding-related, timely filing, and medical necessity. The denial management module 408 may correlate denied claims with their original submission records to identify root causes of denial and patterns of denial behavior across payers, providers, and service lines, para. 0075) are performed in an iterative or recursive manner (receiving remittance data comprises parsing electronic remittance advice files in ANSI X12 835 format to extract denial codes, including claim adjustment reason codes and remittance advice remark codes, and mapping them to internal denial taxonomies, para. 0199) to generate a plurality of factor sets and associated subsets of records (denial management module 408 may correlate denied claims with their original submission records to identify root causes of denial and patterns of denial behavior across payers, providers, and service lines, para. 0075), and recording of the subset of records further comprises selecting from the plurality of factor sets and associated subsets of records for the recording to the data storage (machine learning models repository module 432 may be configured to store trained machine learning model artifacts, including model parameters, hyperparameters, feature schemas, preprocessing transformations, calibration curves, explainability summaries, and training metadata, para. 0091).
In regards to claim 5, Hatfield discloses the apparatus of claim 4, and further discloses wherein selecting from the plurality of factor sets and associated subsets of records further comprises comparing utility scores for each of the plurality of factor sets (feature engineering 614 may maintain feature metadata, including statistical distributions, cardinality, and importance scores, para. 0139).
In regards to claim 6, Hatfield discloses the apparatus of claim 5, wherein the utility scores are generated based on an objective function executed for each of the plurality of factor sets and associated subsets of records (prediction engine 426 may use the loaded machine learning models to process input feature vectors, executing model inference operations to generate numerical denial probability scores ranging from 0 to 1 for each claim. The prediction engine 426 may produce multi-label denial-category classification probabilities, assigning probability scores to various denial categories, including authorization-related, coverage-related, coding-related, timely filing, and other types of denials. The prediction engine 426 may implement gradient-boosted decision tree ensemble models, processing claims through a sequence of shallow decision trees that perform binary threshold splits on input features and aggregate tree outputs additively to produce final scores, para. 0086).
In regards to claim 7, Hatfield discloses the apparatus of claim 6, wherein the objective function weighs lengths of the plurality of factor sets more than respective sizes of the associated subsets of records (prediction engine 426 may compute explainability values, for example, using SHAP analysis techniques, thereby calculating the contribution of each input feature to the overall denial probability score. The prediction engine 426 may rank features by absolute SHAP values to identify the top contributing factors driving denial risk for each claim, para. 0086).
In regards to claim 8, Hatfield discloses the apparatus of claim 1, and further discloses wherein the one or more adjudication decisions are selected from the group consisting of: CO 181 procedure invalid (denial management module 408 may receive remittance data from payer systems, including electronic remittance advice files in formats such as X12 835, which may include claim adjustment reason codes and remittance advice remark codes for denied claims, para. 0075), C097 service not paid separately, C096 non-covered service, C022 incorrect payer, C016 missing or incorrect documentation, CO 185 invalid provider, PI204 non-covered service, and CO29 timely filing limit expired.
In regards to claim 9, Hatfield discloses a method (system and method are provided for claim integrity in healthcare revenue cycle management, para. 0008) of a computer apparatus (special-purpose computer 1000, shown in FIG. 10, includes CPU 1005, including multicore processors, AI processors 1010, including Graphics Processing Units (GPU) 1010A, Field-Programmable Gate Arrays (FPGA) 1010B, Application-Specific Integrated Circuits (ASIC) 1010C, Neural Processing Units (NPU) 1010D, Tensor Processing Units (TPU) 1010E, system memory 1015, network interface 1020, hard disk drive (HDD) interface 1025, external disk drive interface 1030, and input/output (I/O) interfaces 1035A, 1035B, 1035C, para. 0206, fig. 10) for processing a plurality of records associated with respective adjudication decisions (system and method are provided for claim integrity in healthcare revenue cycle management, para. 0008), said method comprising: obtaining, at the computer apparatus via a computer network interface (receiving operations may be performed by the CPU 1005 shown in FIG. 10, accessing data through the network interface 1020 and storing the received data in the system memory 1015, par. 0177), a plurality of records associated with respective one or more adjudication decisions (receiving a first dataset from first data sources, including electronic health records and payer records, and historical medical claims, including those associated with approval and denial outcomes, para. 0009); proceeding, at the computer apparatus and starting with a plurality of factors comprised in the obtained plurality of records and in an iterative or recursive manner (receiving remittance data comprises parsing electronic remittance advice files in ANSI X12 835 format to extract denial codes, including claim adjustment reason codes and remittance advice remark codes, and mapping them to internal denial taxonomies, para. 0199), to: determine a number of factors for evaluating the obtained plurality of records (ACIS 304 may receive this normalized data and execute feature extraction operations to identify relevant attributes for claim analysis. The extracted features may include temporal patterns such as submission lag times, historical denial rates for specific payer-provider combinations, and coding relationship patterns, para. 0065), select the determined number factors from a plurality of factors comprised in the obtained plurality of records (data preprocessing module 402 may execute operations to generate feature vectors for each claim by identifying payer-specific denial rates over rolling time windows, encoding categorical variables using target encoding methods, and computing interaction features between procedure codes and diagnosis codes, para. 0072), identify a subset of records described by the selected factors (denial management module 408 may parse claim adjustment reason codes to classify denials into the following categories: authorization related, coverage-related, coding-related, timely filing, and medical necessity. The denial management module 408 may correlate denied claims with their original submission records to identify root causes of denial and patterns of denial behavior across payers, providers, and service lines, para. 0075), record the identified subset of records in association with the selected factors as a factor set to a data storage (machine learning models repository module 432 may be configured to store trained machine learning model artifacts, including model parameters, hyperparameters, feature schemas, preprocessing transformations, calibration curves, explainability summaries, and training metadata, para. 0091), and remove the subset of records from the obtained plurality of records for a next iteration until the obtained plurality of records have been all removed (ACIS applies the trained machine learning models to generate a denial probability score and a denial category classification for each medical claim, para. 0193); and outputting, at the computer apparatus, a plurality of factor sets and associated subsets of records from the data storage for displaying (EDA & pattern mining 616 component may perform exploratory data analysis and may identify patterns in claim denial data. The EDA & pattern mining 616 may implement clustering algorithms to group similar denial patterns and may use association rule mining to identify frequently co-occurring denial reasons, para. 0140) the plurality of factor sets and associated subsets of records in correspondence with one or more adjudication decisions comprised in the associated subsets of records (ACIS generates explainability values using SHAP to identify features that contribute to the denial probability score, providing the critical technical advantage of regulatory-compliant, transparent AI decisions. This enables every prediction to be traced back to specific claim features with quantified contribution values, which are essential for audit trails and payer appeals, para. 0193).
In regards to claim 10, Hatfield discloses the method of claim 9, and further discloses wherein the number of factors is determined according to a probability distribution (next step may include correlating actual denial outcomes with predicted probabilities through probabilistic record linkage, utilizing claim control numbers and service line identifiers as matching keys, para. 0199).
In regards to claim 11, Hatfield discloses the method of claim 9, and further discloses wherein the determined number of factors (ACIS 304 may receive this normalized data and execute feature extraction operations to identify relevant attributes for claim analysis. The extracted features may include temporal patterns such as submission lag times, historical denial rates for specific payer-provider combinations, and coding relationship patterns, para. 0065) are each selected (data preprocessing module 402 may execute operations to generate feature vectors for each claim by identifying payer-specific denial rates over rolling time windows, encoding categorical variables using target encoding methods, and computing interaction features between procedure codes and diagnosis codes, para. 0072) according to a probability distribution generated based on respective numbers of records described by respective ones of the plurality of factors (system and method provide receiving remittance data comprising parsing electronic remittance advice files to extract denial codes, correlating actual denial outcomes with predicted probabilities, and calculating a population stability index to detect distribution drift, para. 0016).
In regards to claim 12, Hatfield discloses the method of claim 9, and further discloses wherein determining of the number of factors (ACIS 304 may receive this normalized data and execute feature extraction operations to identify relevant attributes for claim analysis. The extracted features may include temporal patterns such as submission lag times, historical denial rates for specific payer-provider combinations, and coding relationship patterns, para. 0065), the selecting of the determined number factors (data preprocessing module 402 may execute operations to generate feature vectors for each claim by identifying payer-specific denial rates over rolling time windows, encoding categorical variables using target encoding methods, and computing interaction features between procedure codes and diagnosis codes, para. 0072), and identifying of the subset of records (denial management module 408 may parse claim adjustment reason codes to classify denials into the following categories: authorization related, coverage-related, coding-related, timely filing, and medical necessity. The denial management module 408 may correlate denied claims with their original submission records to identify root causes of denial and patterns of denial behavior across payers, providers, and service lines, para. 0075) are performed in an iterative or recursive manner (receiving remittance data comprises parsing electronic remittance advice files in ANSI X12 835 format to extract denial codes, including claim adjustment reason codes and remittance advice remark codes, and mapping them to internal denial taxonomies, para. 0199) to generate a plurality of factor sets and associated subsets of records (denial management module 408 may correlate denied claims with their original submission records to identify root causes of denial and patterns of denial behavior across payers, providers, and service lines, para. 0075), and recording of the subset of records further comprises selecting from the plurality of factor sets and associated subsets of records for the recording to the data storage (machine learning models repository module 432 may be configured to store trained machine learning model artifacts, including model parameters, hyperparameters, feature schemas, preprocessing transformations, calibration curves, explainability summaries, and training metadata, para. 0091).
In regards to claim 13, Hatfield discloses the method of claim 12, and further discloses wherein selecting from the plurality of factor sets and associated subsets of records further comprises comparing utility scores for each of the plurality of factor sets (feature engineering 614 may maintain feature metadata, including statistical distributions, cardinality, and importance scores, para. 0139).
In regards to claim 14, Hatfield discloses the method of claim 13, and further discloses wherein the utility scores are generated based on an objective function executed for each of the plurality of factor sets and associated subsets of records (prediction engine 426 may use the loaded machine learning models to process input feature vectors, executing model inference operations to generate numerical denial probability scores ranging from 0 to 1 for each claim. The prediction engine 426 may produce multi-label denial-category classification probabilities, assigning probability scores to various denial categories, including authorization-related, coverage-related, coding-related, timely filing, and other types of denials. The prediction engine 426 may implement gradient-boosted decision tree ensemble models, processing claims through a sequence of shallow decision trees that perform binary threshold splits on input features and aggregate tree outputs additively to produce final scores, para. 0086).
In regards to claim 15, Hatfield discloses the method of claim 14, and further discloses wherein the objective function weighs lengths of the plurality of factor sets more than respective sizes of the associated subsets of records (prediction engine 426 may compute explainability values, for example, using SHAP analysis techniques, thereby calculating the contribution of each input feature to the overall denial probability score. The prediction engine 426 may rank features by absolute SHAP values to identify the top contributing factors driving denial risk for each claim, para. 0086).
In regards to claim 16, Hatfield discloses the method of claim 9, and further discloses wherein the one or more adjudication decisions are selected from the group consisting of: CO181 procedure invalid (denial management module 408 may receive remittance data from payer systems, including electronic remittance advice files in formats such as X12 835, which may include claim adjustment reason codes and remittance advice remark codes for denied claims, para. 0075), C097 service not paid separately, C096 non-covered service, CO22 incorrect payer, CO16 missing or incorrect documentation, CO185 invalid provider, PI204 non-covered service, and CO29 timely filing limit expired.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Zahora et al. (US 12626305) teaches systems and methods for prediction and estimation of medical claims payments.
Cruise (US 8447627) teaches a medical services claim management system and method.
Edgar (US 20150317337) teaches systems and methods for Identifying and driving actionable insights from data.
Menard et al. (US12210590) teaches systems and methods for an artificial intelligence/machine learning medical claims platform.
Zahora et al. (US 20250029714) teaches systems and methods for medical claims analytics and processing support.
Wojtusiak et al. (US 20130054259) teaches rule-based prediction of medical claims' payments.
LIgon (US 20170308652) teaches systems and methods of reducing healthcare claims denials.
Singh et al. (US11538112) teaches machine learning systems and methods for processing data for healthcare applications
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Paul Schwarzenberg whose telephone number is (313) 446-6611. The examiner can normally be reached on Monday-Thursday (7:30-6:30).
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Christine Behncke, can be reached on (571) 272-8103. 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.
/PAUL S SCHWARZENBERG/Primary Examiner, Art Unit 3695 5/15/2026
Prosecution Insights