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 .
This is a Non-Final Office Action in response to application 19/097,966 entitled "METHOD AND SYSTEM FOR PREDICTING THE MOST LIKELY SUPPLEMENTARY MEDICAL SERVICES FOR A GIVEN PRIMARY SERVICE BY IDENTIFYING PATTERNS BETWEEN CO-OCCURRING BILLED SUPPLEMENTARY SERVICES IN HISTORICAL CLAIMS DATA" originally filed on April 2, 2025, with claims 1 to 22 pending.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on July 1, 2025, is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the Examiner.
Claim Objection
Claims 4 and 15 are objected to because of the following informalities: They redundantly state, “removing CPT codes with frequencies below a predetermined frequency threshold are removed;” Examiner interprets the limitation as reading, “removing CPT codes with frequencies below a predetermined frequency;” Appropriate correction is required.
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 1-22 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Please see MPEP 2106 for additional information regarding Patent Subject Matter Eligibility Guidance.
Claims 1-22 are directed to a method/process, machine/apparatus, (article of) manufacture, or composition of matter, which are/is one of the statutory categories of invention, which are/is one of the statutory categories of invention. (Step 1: YES).
The claimed invention is directed to an abstract idea without significantly more.
Independent Claim 1 recites:
“A method of preprocessing and …a…model to predict the most commonly billed supplementary Current Procedural Terminology (CPT) codes for a combination of a primary CPT code and a treatment avenue comprising the steps of:
preprocessing a set of historical claims data, the step of preprocessing the set of historical claims data further comprising the steps of:
a. extracting relevant data from the set of historical claims data to include claims associated with a treatment visit on a single day;
b. for each particular treatment visit, combining a primary CPT code that represents the main procedure or service provided, a list of supplementary CPT codes, and a treatment avenue to compile a model input data set, wherein the treatment avenue is a place of treatment or a provider type;
splitting the model input data set into a … set and a testing set to identify patterns in the … set;
… at least one model with the … set of the model input data set;
and … the at least one model so that the at least one model can predict a set of commonly billed supplementary CPT codes from an inputted primary CPT code and an inputted treatment avenue.”
These limitations, under their broadest reasonable interpretation, cover performance of the limitation as certain methods of organizing human activity. Specific instances include instructing for “extracting relevant data from the set of historical claims data” and to “predict a set of commonly billed supplementary CPT codes” recite a fundamental economic principles or practice and/or commercial or legal interactions in light of the Specification that reads:
[0002] identifying patterns between co-occurring billed supplementary services in historical claims data
[0003] Patients rarely understand which procedures they will be billed for. This makes it difficult for patients to financially plan for medical procedures, driving them to seek reactive rather than proactive care. This eventually leads to higher costs of care and more uncertainty about what additional procedures will be needed
[0004] allowing healthcare consumers to better account for upcoming care, and shifting habits towards proactive care. This is a win for both consumers and payers and increases the efficiency of overall healthcare consumption.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation as a fundamental economic, commercial, or financial action, principle, or practice then it falls within the “Certain Methods of Organizing Human Activity” grouping of abstract ideas. Accordingly, the claim recites an abstract idea. (Step 2A-Prong 1: YES. The claims recite an abstract idea).
This judicial exception is not integrated into a practical application. In particular, the claims recite the additional elements of:
[training/trained] [machine learning]:
merely applying machine learning technology as a tool to perform an abstract idea
are recited at a high-level of generality (i.e., as a generic processor performing a generic computer function) such that it amounts no more than mere instructions to apply the exception using a generic computer components and/or electronic processes. For example, the Applicant’s Specification reads:
[0007] storing the historical claims data in a memory storage device
Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The additional elements merely add instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea, see MPEP 2106.05(f). Accordingly, these additional elements, when considered separately and as an ordered combination, do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea and are at a high level of generality.
Furthermore, these limitations, under their broadest reasonable interpretation, covers performance of the limitation as mental processes but for the recitation of generic computer components. For example, extracting relevant data from the set of historical claims data and splitting the model input data set encompasses a person simply determining which data is most important and prioritizing some data ahead of other data. “The courts consider a mental process (thinking) that ‘can be performed in the human mind, or by a human using a pen and paper’ to be an abstract idea… The courts do not distinguish between mental processes that are performed entirely in the human mind and mental processes that require a human to use a physical aid (e.g., pen and paper or a slide rule) to perform the claim limitation… Nor do the courts distinguish between claims that recite mental processes performed by humans and claims that recite mental processes performed on a computer. As the Federal Circuit has explained, ‘[c]ourts have examined claims that required the use of a computer and still found that the underlying, patent-ineligible invention could be performed via pen and paper or in a person’s mind.’”, see MPEP 2106 – III. MENTAL PROCESSES. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation as a one that a person may perform by thinking then it falls within the “Mental Processes” grouping of abstract ideas.
Therefore, Claim 1 is directed to an abstract idea without a practical application. (Step 2A-Prong 2: NO. The additional claimed elements are not integrated into a practical application)
Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The additional elements merely add instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea, see MPEP 2106.05(f). Accordingly, the additional elements, do not change the outcome of the analysis, when considered separately and as an ordered combination. The claim further defines the abstract idea and hence is abstract for the reasons presented above. The claim does not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception when considered both individually and as an ordered combination. Therefore, the claim is directed to an abstract idea. Thus, the claim is not patent eligible. (Step 2B: NO. The claim does not provide significantly more)
Dependent Claims recite additional elements.
This judicial exception is not integrated into a practical application. In particular, the recited additional elements of
Claim 2:
“trained using the Frequent Pattern (FP) Growth algorithm”: merely applying machine learning technologies as a tool to perform an abstract idea
Claim 3: (none found: does not include additional elements and merely narrows the abstract idea)
Claim 4:
“training”: merely applying machine learning technologies as a tool to perform an abstract idea
Claims 5-7: (none found: does not include additional elements and merely narrows the abstract idea)
Claim 8:
“trained”: merely applying machine learning technologies as a tool to perform an abstract idea
Claims 9-11: (none found: does not include additional elements and merely narrows the abstract idea)
Claims 12 and 13:
“creating an alert”: insignificant extra-solution activity
are recited at a high-level of generality (i.e., as a generic processor performing a generic computer function) such that it amounts no more than mere instructions to apply the exception using a generic computer components and/or electronic processes. For support from the Applicant’s Specification, see the analysis as applied to Independent Claim 1 (Step 2A-Prong 2) earlier. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The additional elements merely add instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea, see MPEP 2106.05(f). Accordingly, these additional elements, when considered separately and as an ordered combination, do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea and are at a high level of generality. Therefore, the claim is directed to an abstract idea without a practical application. (Step 2A-Prong 2: NO. The additional claimed elements are not integrated into a practical application)
Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The additional elements merely add instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea, see MPEP 2106.05(f). Accordingly, these additional elements, do not change the outcome of the analysis, when considered separately and as an ordered combination. Dependent claims further define the abstract idea that is present in their respective independent claims and hence are abstract for the reasons presented above. The dependent claims do not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception when considered both individually and as an ordered combination. Therefore, the dependent claims are directed to an abstract idea. Thus, the dependent claims are not patent eligible. (Step 2B: NO. The claims do not provide significantly more)
Independent Claim 14 recites:
“A method of preprocessing and … a … model to predict the most commonly billed supplementary Current Procedural Terminology (CPT) codes for a combination of a primary CPT code and a treatment avenue comprising the steps of:
preprocessing a set of historical claims data, the step of preprocessing the set of historical claims data further comprising the steps of:
a. extracting relevant data from the set of historical claims data to include claims associated with a treatment visit on a single day;
b. for each particular treatment visit, combining a primary CPT code that represents the main procedure or service provided, a list of supplementary CPT codes, and a treatment avenue to compile a model input data set, wherein the treatment avenue is a place of treatment or a provider type;
splitting the model input data set into a … set and a testing set to identify patterns in the … set;
… at least one model with the … set of the model input data set;
… the at least one model so that the at least one model can predict a set of commonly billed supplementary CPT codes from an inputted primary CPT code and an inputted treatment avenue;
inputting combinations of one primary CPT code with one treatment avenue into the … at least one model;
predicting at least one supplementary CPT code for each of the inputted combinations using the … at least one model; and
outputting a similarity score that represents a level of confidence for each prediction.”
These limitations, under their broadest reasonable interpretation, cover performance of the limitation as certain methods of organizing human activity. Specific instances include instructing for “extracting relevant data from the set of historical claims data” and to “predict a set of commonly billed supplementary CPT codes” recite a fundamental economic principles or practice and/or commercial or legal interactions in light of the Specification that reads:
[0002] identifying patterns between co-occurring billed supplementary services in historical claims data
[0003] Patients rarely understand which procedures they will be billed for. This makes it difficult for patients to financially plan for medical procedures, driving them to seek reactive rather than proactive care. This eventually leads to higher costs of care and more uncertainty about what additional procedures will be needed
[0004] allowing healthcare consumers to better account for upcoming care, and shifting habits towards proactive care. This is a win for both consumers and payers and increases the efficiency of overall healthcare consumption.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation as a fundamental economic, commercial, or financial action, principle, or practice then it falls within the “Certain Methods of Organizing Human Activity” grouping of abstract ideas. Accordingly, the claim recites an abstract idea. (Step 2A-Prong 1: YES. The claims recite an abstract idea).
This judicial exception is not integrated into a practical application. In particular, the claims recite the additional elements of:
[training/trained] [machine learning]:
merely applying machine learning technology as a tool to perform an abstract idea
are recited at a high-level of generality (i.e., as a generic processor performing a generic computer function) such that it amounts no more than mere instructions to apply the exception using a generic computer components and/or electronic processes. For example, the Applicant’s Specification reads:
[0007] storing the historical claims data in a memory storage device
Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The additional elements merely add instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea, see MPEP 2106.05(f). Accordingly, these additional elements, when considered separately and as an ordered combination, do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea and are at a high level of generality.
Furthermore, these limitations, under their broadest reasonable interpretation, covers performance of the limitation as mental processes but for the recitation of generic computer components. For example, extracting relevant data from the set of historical claims data and splitting the model input data set encompasses a person simply determining which data is most important and prioritizing some data ahead of other data. “The courts consider a mental process (thinking) that ‘can be performed in the human mind, or by a human using a pen and paper’ to be an abstract idea… The courts do not distinguish between mental processes that are performed entirely in the human mind and mental processes that require a human to use a physical aid (e.g., pen and paper or a slide rule) to perform the claim limitation… Nor do the courts distinguish between claims that recite mental processes performed by humans and claims that recite mental processes performed on a computer. As the Federal Circuit has explained, ‘[c]ourts have examined claims that required the use of a computer and still found that the underlying, patent-ineligible invention could be performed via pen and paper or in a person’s mind.’”, see MPEP 2106 – III. MENTAL PROCESSES. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation as a one that a person may perform by thinking then it falls within the “Mental Processes” grouping of abstract ideas.
Therefore, Claim 14 is directed to an abstract idea without a practical application. (Step 2A-Prong 2: NO. The additional claimed elements are not integrated into a practical application)
Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The additional elements merely add instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea, see MPEP 2106.05(f). Accordingly, the additional elements, do not change the outcome of the analysis, when considered separately and as an ordered combination. The claim further defines the abstract idea and hence is abstract for the reasons presented above. The claim does not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception when considered both individually and as an ordered combination. Therefore, the claim is directed to an abstract idea. Thus, the claim is not patent eligible. (Step 2B: NO. The claim does not provide significantly more)
Dependent Claims recite NO additional elements and merely narrows the abstract idea.
Any alleged additional element are recited at a high-level of generality (i.e., as a generic processor performing a generic computer function) such that it amounts no more than mere instructions to apply the exception using a generic computer components and/or electronic processes. For support from the Applicant’s Specification, see the analysis as applied to Independent Claim 1 (Step 2A-Prong 2) earlier. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The additional elements merely add instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea, see MPEP 2106.05(f). Accordingly, these additional elements, when considered separately and as an ordered combination, do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea and are at a high level of generality. Therefore, the claim is directed to an abstract idea without a practical application. (Step 2A-Prong 2: NO. The additional claimed elements are not integrated into a practical application)
Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The additional elements merely add instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea, see MPEP 2106.05(f). Accordingly, these additional elements, do not change the outcome of the analysis, when considered separately and as an ordered combination. Dependent claims further define the abstract idea that is present in their respective independent claims and hence are abstract for the reasons presented above. The dependent claims do not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception when considered both individually and as an ordered combination. Therefore, the dependent claims are directed to an abstract idea. Thus, the dependent claims are not patent eligible. (Step 2B: NO. The claims do not provide significantly more)
Independent Claim 22 recites:
“A method of preprocessing and … a … model to predict the most commonly billed supplementary Current Procedural Terminology (CPT) codes for a combination of a primary CPT code and a treatment avenue comprising the steps of:
preprocessing a set of historical claims data, the step of preprocessing the set of historical claims data further comprising the steps of:
a. extracting relevant data from the set of historical claims data to include claims associated with a treatment visit on a single day;
b. for each particular treatment visit, combining a primary OPT code that represents the main procedure or service provided, a list of supplementary CPT codes, and a treatment avenue to compile a model input data set, wherein the treatment avenue is a place of treatment or a provider type;
splitting the model input data set into a … set and a testing set to identify patterns in the … set;
… at least one model with the … set of the model input data set;
… the at least one model so that the at least one model can predict a set of commonly billed supplementary CPT codes from an inputted primary CPT code and an inputted treatment avenue;
inputting combinations of one primary CPT code with one treatment avenue into the … at least one model;
predicting at least one supplementary CPT code for each of the inputted combinations using the … at least one model;
outputting a similarity score that represents a level of confidence for each prediction;
preparing a personalized cost prediction for a first particular patient using the first particular patient's demographic data and the list of predicted supplementary CPT code generated by the at least one model;
identifying potential fraudulent billing by comparing the personalized predicted cost with an actual billed amount; and
creating an alert when the predicted cost is lower than the actual billed amount.”
These limitations, under their broadest reasonable interpretation, cover performance of the limitation as certain methods of organizing human activity. Specific instances include instructing for “extracting relevant data from the set of historical claims data” and to “predict a set of commonly billed supplementary CPT codes” recite a fundamental economic principles or practice and/or commercial or legal interactions in light of the Specification that reads:
[0002] identifying patterns between co-occurring billed supplementary services in historical claims data
[0003] Patients rarely understand which procedures they will be billed for. This makes it difficult for patients to financially plan for medical procedures, driving them to seek reactive rather than proactive care. This eventually leads to higher costs of care and more uncertainty about what additional procedures will be needed
[0004] allowing healthcare consumers to better account for upcoming care, and shifting habits towards proactive care. This is a win for both consumers and payers and increases the efficiency of overall healthcare consumption.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation as a fundamental economic, commercial, or financial action, principle, or practice then it falls within the “Certain Methods of Organizing Human Activity” grouping of abstract ideas. Accordingly, the claim recites an abstract idea. (Step 2A-Prong 1: YES. The claims recite an abstract idea).
This judicial exception is not integrated into a practical application. In particular, the claims recite the additional elements of:
[training/trained] [machine learning]:
merely applying machine learning technology as a tool to perform an abstract idea
are recited at a high-level of generality (i.e., as a generic processor performing a generic computer function) such that it amounts no more than mere instructions to apply the exception using a generic computer components and/or electronic processes. For example, the Applicant’s Specification reads:
[0007] storing the historical claims data in a memory storage device
Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The additional elements merely add instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea, see MPEP 2106.05(f). Accordingly, these additional elements, when considered separately and as an ordered combination, do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea and are at a high level of generality.
Furthermore, these limitations, under their broadest reasonable interpretation, covers performance of the limitation as mental processes but for the recitation of generic computer components. For example, extracting relevant data from the set of historical claims data and splitting the model input data set encompasses a person simply determining which data is most important and prioritizing some data ahead of other data. “The courts consider a mental process (thinking) that ‘can be performed in the human mind, or by a human using a pen and paper’ to be an abstract idea… The courts do not distinguish between mental processes that are performed entirely in the human mind and mental processes that require a human to use a physical aid (e.g., pen and paper or a slide rule) to perform the claim limitation… Nor do the courts distinguish between claims that recite mental processes performed by humans and claims that recite mental processes performed on a computer. As the Federal Circuit has explained, ‘[c]ourts have examined claims that required the use of a computer and still found that the underlying, patent-ineligible invention could be performed via pen and paper or in a person’s mind.’”, see MPEP 2106 – III. MENTAL PROCESSES. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation as a one that a person may perform by thinking then it falls within the “Mental Processes” grouping of abstract ideas.
Therefore, Claim 22 is directed to an abstract idea without a practical application. (Step 2A-Prong 2: NO. The additional claimed elements are not integrated into a practical application)
Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The additional elements merely add instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea, see MPEP 2106.05(f). Accordingly, the additional elements, do not change the outcome of the analysis, when considered separately and as an ordered combination. The claim further defines the abstract idea and hence is abstract for the reasons presented above. The claim does not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception when considered both individually and as an ordered combination. Therefore, the claim is directed to an abstract idea. Thus, the claim is not patent eligible. (Step 2B: NO. The claim does not provide significantly more)
Claim Rejections - 35 USC § 103
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
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 set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied 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, 9, and 11 are rejected under 35 U.S.C. 103 as being unpatentable over Miller ("USE DETERMINATION RISK COVERAGE DATASTRUCTURE FOR ON-DEMAND AND INCREASED EFFICIENCY COVERAGE DETECTION AND REBALANCING APPARATUSES, PROCESSES AND SYSTEMS", U.S. Publication Number: US 12266018 B1), in view of Pakhomov (“METHOD FOR GENERATING TRAINING DATA FOR MEDICAL TEXT ABBREVIATION AND ACRONYM NORMALIZATION”, U.S. Patent Number: US 7028038 B1).
Regarding Claim 1,
Miller teaches,
A method of preprocessing and training a machine learning model to predict the most commonly billed supplementary Current Procedural Terminology (CPT) codes for a combination of a primary CPT code and a treatment avenue
(Miller [Col 21, Lines 44-45] A claim pre-processor 330 facilitates connecting to systems of health plan networks
Miller [Col 35, Lines 5-6] the claim administration platform includes a claim pre-processor component 1201
Miller [Col 38, Lines 6-10] model training data (e.g., Truven and/or other historical training data), historical and/or real time claims data
Miller [Col 52, Lines 37-39] using historical claims data and/or identification of CPT codes provided to individuals that have a diagnosis code associated with the condition.
Miller [Col 63, Lines 46-48] HCPCS/CPT, UB04 rev codes, ICD-10 procedure codes
Miller [Col 89, Line 63 - Col 90, Line 3] shows the predictions of a 2-variable logistic regression. Each point is a medical encounter...Each encounter has codes on it, and each code has an associated props ratio. The maximum HCPCS (service codes: “this was done”) props ratio, and the maximum ICD-10-CM (diagnosis code: “this is why it was done”) are taken)
comprising the steps of: preprocessing a set of historical claims data, the step of preprocessing the set of historical claims data further comprising the steps of:
(Miller [Col 21, Lines 44-45] A claim pre-processor 330 facilitates connecting to systems of health plan networks
Miller [Col 35, Lines 5-6] the claim administration platform includes a claim pre-processor component 1201
Miller [Col 38, Lines 6-10] model training data (e.g., Truven and/or other historical training data), historical and/or real time claims data)
a. extracting relevant data from the set of historical claims data to include claims associated with a treatment visit on a single day;
(Miller [Col 58, Lines 3-5] the member state (e.g., the member's claim history based on X12 837 health care claims) may be analyzed
Miller [Col 85, Lines 46-50] an episode archetype may specify how claims data for various coverage families should be processed.... may specify analysis window (e.g., 90 days post-trigger, same day)
Miller [Col 95, Lines 24-28] the encounter grouping type may be by stay (e.g., group claims related to an inpatient stay into an encounter), by day (e.g., group claims that occurred on the same day into an encounter), and/or the like.)
b. for each particular treatment visit, combining a primary CPT code that represents the main procedure or service provided, a list of supplementary CPT codes, and a treatment avenue
(Miller [Col 89, Line 63 - Col 90, Line 3] shows the predictions of a 2-variable logistic regression. Each point is a medical encounter...Each encounter has codes on it, and each code has an associated props ratio. The maximum HCPCS (service codes: “this was done”) props ratio, and the maximum ICD-10-CM (diagnosis code: “this is why it was done”) are taken
Miller [Col 29, Lines 31-38] Atomized procedures (e.g., ACL repair) may be determined at 629. In one implementation, captured data (e.g., Current Procedural Terminology (CPT)) may be utilized to determine a care taxonomy that specifies atomized procedures. In another implementation, machine learning processes may be utilized to analyze captured data (e.g., X12 data, HL7 data) to determine a care taxonomy that specifies atomized procedures.
Miller [Col 56, Lines 53-58] This may involve getting potential list of diagnosis codes, and clinical condition curation and categorization. Getting potential list of diagnosis codes may involve taking trigger codes for a given add-in, identifying triggered encounters (e.g., dates and member identifiers))
to compile a model input data set, wherein the treatment avenue is a place of treatment or a provider type;
(Miller [Col 11, Lines 4-7] may be conceptualized as a benefit design and pricing system that is built upon an underlying division of care into units based on treatment, location
Miller [Col 12, Lines 28-33] information for different treatments when using a provider (e.g., a provider may be defined at different levels of granularity from hospital systems to individual medical professionals depending on the nature of the data.)
Miller [Col 16, Lines 39-44] health outcomes are calculated for each provider, location of service, etc.... determined to be available to the covered individual vary by person, location or provider)
training at least one model with the training set of the model input data set;
(Miller [Col 244, Lines 28-31] depending on the particular needs and/or characteristics of a UDRCD) individual and/or enterprise user, database configuration and/or relational model, data type
Miller [Col 38, Lines 8-11] model training data (e.g., Truven and/or other historical training data), historical and/or real time claims data, and/or the like may be utilized)
and training the at least one model so that the at least one model can predict a set of commonly billed supplementary CPT codes from an inputted primary CPT code and an inputted treatment avenue.
(Miller [Col 38, Lines 6-10] model training data
Miller [Col 63, Lines 46-48] HCPCS/CPT, UB04 rev codes, ICD-10 procedure codes
Miller [Col 52, Lines 37-39] using historical claims data and/or identification of CPT codes provided to individuals that have a diagnosis code associated with the condition.
Miller [Col 89, Line 63 - Col 90, Line 3] shows the predictions of a 2-variable logistic regression. Each point is a medical encounter...Each encounter has codes on it, and each code has an associated props ratio. The maximum HCPCS (service codes: “this was done”) props ratio, and the maximum ICD-10-CM (diagnosis code: “this is why it was done”) are taken)
Miller does not teach splitting the model input data set into a training set and a testing set to identify patterns in the training set;
Pakhomov teaches,
splitting the model input data set into a training set and a testing set to identify patterns in the training set;
(Pakhomov [Col 7, Lines 26-30] data compiled for each set and subset was split at random in the 80/20 fashion into training and testing data.)
It is prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the medical code prediction of Miller to incorporate the training and testing data sets of Pakhomov for a “split … into training and testing data.” (Pakhomov [Col 7, Lines 26-30]). The modification would have been obvious, because it is merely applying a known technique (i.e. training and testing data sets ) to a known concept (i.e. medical code prediction) ready for improvement to yield predictable result (i.e. “generating high-quality feature vectors that can be used in connection with electronic data processing systems” Pakhomov [Abstract])
Regarding Claim 9,
Miller and Pakhomov teach the medical code prediction of Claim 1 as described earlier.
Miller teaches,
including multi-day procedures into the model input data set;
(Miller [Col 139 - Table - Benefits Highlights] Rehabilitative care (30 days per calendar year; 60 days $250 per day/Up To $500 per day/Up To)
connecting the model input data set with associated costs; and
(Miller [Col 12, Lines 41-43] method for using this information with patient data to estimate benefits and costs
Miller [Col 14, Lines 64-66] takes costs and efficacies of the various treatments (or treatment-provider combinations) for a condition and unambiguously assigns a waste value to each by which pricing can be modified)
personalizing procedure and cost predictions using member demographic, regional and plan data.
(Miller [Col 11, Lines 22-25] includes a method for personalizing pricing of treatments and services based on the benefit to individuals.
Miller [Col 27, Lines 48-52] modeling data may be generated for a specified plan sponsor, ODHI plan, locality, provider network, plan term, plan member type (e.g., individual, family, member demographic), and/or the like)
Regarding Claim 11,
Miller and Pakhomov teach the medical code prediction of Claim 1 as described earlier.
Miller teaches,
preparing a personalized cost prediction for a first particular patient using the first particular patient's demographic data
(Miller [Col 11, Lines 22-25] includes a method for personalizing pricing of treatments and services based on the benefit to individuals.
Miller [Col 27, Lines 48-52] modeling data may be generated for a specified plan sponsor, ODHI plan, locality, provider network, plan term, plan member type (e.g., individual, family, member demographic), and/or the like)
and the list of predicted supplementary CPT code generated by the at least one model.
(Miller [Col 52, Lines 23-25] conditions may be determined by grouping ICD-10 Diagnosis codes for related ailments into conditions or related condition groups
Miller [Col 63, Lines 46-48] HCPCS/CPT, UB04 rev codes, ICD-10 procedure codes
Miller [Col 89, Line 63 - Col 90, Line 3] shows the predictions of a 2-variable logistic regression. Each point is a medical encounter...Each encounter has codes on it
Miller [Col 220, Lines 46-48] calculating code module for the coverage family comprises a vector of model parameters)
Claims 2 and 3 are rejected under 35 U.S.C. 103 as being unpatentable over Miller and Pakhomov in view of Tanner (“SYSTEM AND METHOD FOR DYNAMIC HEALTHCARE INSURANCE CLAIMS DECISION SUPPORT”, U.S. Publication Number: US 20170351821 A1).
Regarding Claim 2,
Miller and Pakhomov teach the medical code prediction of Claim 1 as described earlier.
Miller does not teach wherein the at least one model is trained using the Frequent Pattern (FP) Growth algorithm to identify patterns between frequent, co- occurring supplementary CPT codes.
Tanner teaches,
wherein the at least one model is trained using the Frequent Pattern (FP) Growth algorithm to identify patterns between frequent, co- occurring supplementary CPT codes.
(Tanner [0102] FP-Growth is a method for determining frequent itemsets
Tanner [0054] Below is an example of when the FP-Growth process is used to perform the frequency item set analysis process.
Tanner [0035] tracking and analyzing streams of data from multiple sources and deriving real-time patterns.
Tanner [0046] determine which diagnosis codes are most frequently/infrequently associated to each procedure code and offer suggestions on possible missing or inappropriate diagnosis codes. The result of this analysis may be: calc_cpt_cooccurrence_probibility([99213′, ‘29888’]) >>0.12)
It is prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the medical code prediction of Miller to incorporate the Frequent Pattern (FP) Growth algorithm teachings of Tanner for “an FP tree example that may be used by the healthcare claim decision support system.” (Tanner [0100]). The modification would have been obvious, because it is merely applying a known technique (i.e. Frequent Pattern (FP) Growth algorithm) to a known concept (i.e. medical code prediction) ready for improvement to yield predictable result (i.e. “a function that trains an FP-Growth model to mine frequent ICD9/10 itemsets for a given CPT code” Tanner [0100])
Regarding Claim 3,
Miller, Pakhomov, and Tanner teach the medical code prediction of Claim 2 as described earlier.
Miller teaches,
using trees to track and count the frequent, co-occurring supplementary codes to improve performance on distributed systems.
(Miller [Col 123, Lines 29-33] the associated price range tree datastructure for a second coverage family, and a record that specifies a coverage family identifier and the associated code module link
Miller [Col 87, Lines 44-47] An occurrence count for the selected encounter type for each claim code associated with the determined other claims may be updated)
Claims 4 and 10 are rejected under 35 U.S.C. 103 as being unpatentable over Miller, Pakhomov, and Tanner in view of Snider (“SEQUENCING MEDICAL CODES METHODS AND APPARATUS”, U.S. Publication Number: US 20180081859 A1).
Regarding Claim 4,
Miller and Pakhomov teach the medical code prediction of Claim 1 as described earlier.
Miller teaches,
determining the frequency for every CPT code in the training set;
(Miller [Col 52, Lines 37-39] using historical claims data and/or identification of CPT codes provided to individuals that have a diagnosis code associated with the condition.
Miller [Col 15, Lines 17-20] alternative treatments affect the waste calculation, but their “weight” in the calculation depends on the frequency of their use in the population
Miller [Col 43, Lines 48-50] based on the frequency with which the services are used
Miller [Col 44, Lines 7-9] the frequency with which surgical and less invasive treatment paths are used
Miller [Col 38, Lines 6-10] model training data)
with frequencies below a predetermined frequency threshold are removed;
(Miller [Col 87, Lines 44-46] An occurrence count for the selected encounter type for each claim code associated with the determined other claims may be updated
Miller [Col 109, Lines 32-40] truncation (e.g., to remove episodes that have costs below a threshold value), payer type (e.g., to remove episodes associated with non-commercial payer types), inflation (e.g., to adjust episode costs for inflation (e.g., 6% per year)), and/or the like.... datastructure may be determined via a MySQL database command )
and its associated frequency;
(Miller [Col 87, Lines 44-46] An occurrence count for the selected encounter type for each claim code associated with the determined other claims may be updated)
updating the associated frequencies as the at least one model grows;
(Miller [Col 87, Lines 44-51] if a claim code occurs multiple (e.g., 3) times in the other claims, the occurrence count for the claim code for the selected encounter type may be increased by 1 (e.g., to indicate that the claim code occurred during the analysis window associated with the anchor claim).)
(removing combinations of CPT codes) below a minimum confidence threshold.
(Miller [Col 18, Lines 1-5] truncate the model in various manners when the data become too sparse to have a specified level of confidence
Miller [Col 33-39] such a determination may be made based on determining (e.g., based on analysis of clinical records, treatments, providers, etc.) that ODHI coverage may be provided more efficiently by removing a treatment (e.g., an ineffective treatment, an unused treatment) from the ACG
Miller [Col 55, Lines 32-36] Therapy treatment object should be deleted... these deletions and/or insertions may be executed.
Miller [Col 52, Lines 37-39] using historical claims data and/or identification of CPT codes provided to individuals that have a diagnosis code associated with the condition.)
Miller does not teach assigning a tree node to each CPT code remaining; removing CPT codes; removing combinations of CPT codes;
Tanner teaches,
assigning a tree node to each CPT code remaining;
(Tanner [0017] an FP tree example that may be used by the healthcare claim decision support system.
Tanner [0100] an FP-Growth model to mine frequent ICD9/10 itemsets for a given CPT code
Tanner [0102] a frequent pattern tree (FP-tree) which encodes the itemset association information.
Tanner [0104] creates an FP-tree instance to represent the frequent itemsets.)
It is prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the medical code prediction of Miller to incorporate the Frequent Pattern (FP) Growth algorithm teachings of Tanner for “an FP tree example that may be used by the healthcare claim decision support system.” (Tanner [0100]). The modification would have been obvious, because it is merely applying a known technique (i.e. Frequent Pattern (FP) Growth algorithm) to a known concept (i.e. medical code prediction) ready for improvement to yield predictable result (i.e. “a function that trains an FP-Growth model to mine frequent ICD9/10 itemsets for a given CPT code” Tanner [0100])
Tanner does not teach removing CPT codes; removing combinations of CPT codes
Snider teaches,
removing CPT codes; removing combinations of CPT codes
(Snider [0036] According to some embodiments, corrections to the medical billing codes, including re-ordering of the sequence and/or additions or deletions of medical codes are provided as feedback to improve the performance of the sequencing engine)
It is prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the medical code prediction of Miller to incorporate the medical code removal teachings of Snider for “corrections to the medical billing codes, including re-ordering of the sequence and/or additions or deletions of medical codes are provided as feedback.” (Snider [0036]). The modification would have been obvious, because it is merely applying a known technique (i.e. medical code removal) to a known concept (i.e. medical code prediction) ready for improvement to yield predictable result (i.e. “to improve the performance of the sequencing engine” Snider [0036])
Regarding Claim 10,
Miller and Pakhomov teach the medical code prediction of Claim 1 as described earlier.
Miller teaches,
i. determining a frequency that each of the supplementary CPT codes appear in the list of supplementary CPT codes for each unique combination;
(Miller [Col 52, Lines 37-39] identification of CPT codes provided to individuals that have a diagnosis code associated with the condition.
Miller [Col 15, Lines 17-20] their “weight” in the calculation depends on the frequency of their use in the population
Miller [Col 43, Lines 48-50] based on the frequency with which the services are used
Miller [Col 44, Lines 7-9] the frequency with which surgical and less invasive treatment paths are used
Miller [Col 56, Line 19] unique treatment paths
Miller [Col 235, Line 67 to Col 236, Line 3] Primary keys represent fields that uniquely identify the rows of a table in a relational database. Alternative key fields may be used from any of the fields having unique value sets)
ii. comparing the frequency of each of the supplementary CPT codes to a frequency threshold;
(Miller [Col 56, Lines 20-24] High frequency treatment paths (e.g., that account for at least a specified threshold percentage of members) may be determined by the treatment pathway analytic engine.
Miller [Col 69, Lines 3-4] when the member is at a pathway node having a level of influence or variance above a specified threshold, and/or the like.)
(removing supplementary CPT codes) if the frequency is below a predetermined minimum frequency threshold;
(Miller [Col 55, Lines 32-36] Therapy treatment object should be deleted... these deletions and/or insertions may be executed.
Miller [Col 87, Lines 44-46] An occurrence count for the selected encounter type for each claim code associated with the determined other claims may be updated
Miller [Col 109, Lines 32-40] truncation (e.g., to remove episodes that have costs below a threshold value), payer type (e.g., to remove episodes associated with non-commercial payer types), inflation (e.g., to adjust episode costs for inflation (e.g., 6% per year)), and/or the like.... datastructure may be determined via a MySQL database command )
iv. determining a number of times, a particular pair of supplementary CPT codes is found together
(Miller [Abstract] A props ratio relevance function associated with the encounter type is determined, and used to determine a set of accessory encounter datastructures for the anchor encounter datastructure
Miller [Col 76, Lines 60-63] relevance may be determined by fields such as diagnosis and/or procedure codes using props ratios datastructures
Miller [Col 87, Lines 44-46] An occurrence count for the selected encounter type for each claim code associated with the determined other claims may be updated)
v. removing the particular pair of supplementary CPT codes if the number of times a particular pair of supplementary CPT codes is found is not more than a minimum confidence threshold.
(Miller [Col 18, Lines 1-5] truncate the model in various manners when the data become too sparse to have a specified level of confidence
Miller [Col 33-39] such a determination may be made based on determining (e.g., based on analysis of clinical records, treatments, providers, etc.) that ODHI coverage may be provided more efficiently by removing a treatment (e.g., an ineffective treatment, an unused treatment) from the ACG
Miller [Col 55, Lines 32-36] Therapy treatment object should be deleted... these deletions and/or insertions may be executed.
Miller [Col 52, Lines 37-39] using historical claims data and/or identification of CPT codes provided to individuals that have a diagnosis code associated with the condition.)
Miller does not teach compared to the number of times one of the supplementary CPT codes of the particular pair is found; iii. removing supplementary CPT codes
Tanner teaches,
compared to the number of times one of the supplementary CPT codes of the particular pair is found;
(Tanner [0091] for a particular claim may include a CPT code notices portion 602 and a detailed analysis portion 604 for each CPT code in a particular claim. The CPT code notices portion identifies CPT codes that may not be accepted in the same claim that is identified based on the procedure co-occurrence process described above.
Tanner [0092] detailed analysis portion 604 for each CPT code may include various indications of problems with the claim....identified based on the price analysis process described above and/or an incorrect ICD code for a particular CPT 608 that may be identified by the frequent item set analysis described above)
It is prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the medical code prediction of Miller to incorporate the occurrence counting teachings of Tanner for the “procedure co-occurrence process.” (Tanner [0091]). The modification would have been obvious, because it is merely applying a known technique (i.e. occurrence counting ) to a known concept (i.e. medical code prediction) ready for improvement to yield predictable result (i.e. “identifies CPT codes that may not be accepted” Tanner [0091])
Tanner does not teach iii. removing supplementary CPT codes
Snider teaches,
iii. removing supplementary CPT codes
(Snider [0036] According to some embodiments, corrections to the medical billing codes, including re-ordering of the sequence and/or additions or deletions of medical codes are provided as feedback to improve the performance of the sequencing engine)
It is prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the medical code prediction of Miller to incorporate the medical code removal teachings of Snider for “corrections to the medical billing codes, including re-ordering of the sequence and/or additions or deletions of medical codes are provided as feedback.” (Snider [0036]). The modification would have been obvious, because it is merely applying a known technique (i.e. medical code removal) to a known concept (i.e. medical code prediction) ready for improvement to yield predictable result (i.e. “to improve the performance of the sequencing engine” Snider [0036])
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over Miller, and Pakhomov in view of Zizzamia (“FRAUD DETECTION METHODS AND SYSTEMS”, U.S. Publication Number: US 20140058763 A1) in view of Karlov (“DIAGNOSING INAPPARENT DISEASES FROM COMMON CLINICAL TESTS USING BAYESIAN ANALYSIS”, U.S. Publication Number: US 20030065535 A1)
Regarding Claim 6,
Miller and Pakhomov teach the medical code prediction of Claim 1 as described earlier.
Miller does not teach determining a similarity score for each particular treatment visit in the testing et by determining the similarity between predicted supplementary CPT codes and actual supplementary CPT codes for each particular treatment visit in the testing set.
Zizzamia teaches,
determining a similarity score; determining the similarity between.
(Zizzamia [0063] clustering score
Zizzamia [0047] multivariate basis and chosen to maximize the similarity of the claims
Zizzamia [0082] In order to cluster the claims into like groups it is recommended to remove variables with high degrees of correlation to avoid double counting when measuring similarity between two claims
Zizzamia [0191] clusters can then be evaluated based on a heat map to enable patterns, similarities and differences between the different clusters to be readily identifiable.
Zizzamia [0064] for scoring)
It is prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the medical code prediction of Miller to incorporate the clustering score teachings of Zizzamia with its “clustering score.” (Zizzamia [0063]). The modification would have been obvious, because it is merely applying a known technique (i.e. clustering score) to a known concept (i.e. medical code prediction) ready for improvement to yield predictable result (i.e. “cluster the claims into like groups it is recommended to remove variables with high degrees of correlation to avoid double counting when measuring similarity between two claims” Zizzamia [0082])
Zizzamia does not teach for each particular treatment visit in the testing set; predicted supplementary CPT codes and actual supplementary CPT codes for each particular treatment visit in the testing set.
Karlov teaches,
for each particular treatment visit in the testing set; predicted supplementary CPT codes and actual supplementary CPT codes for each particular treatment visit in the testing set.
(Karlov [0345] The resulting predictions were then compared with the actual diagnosis codes in the test population records in order to generate accuracy (sensitivity and specificity) statistics.)
It is prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the medical code prediction of Miller to incorporate the actual versus predictive comparison teachings of Karlov with its “predictions were then compared with the actual diagnosis codes.” (Karlov [0345]). The modification would have been obvious, because it is merely applying a known technique (i.e. actual versus predictive comparison) to a known concept (i.e. medical code prediction) ready for improvement to yield predictable result (i.e. “in order to generate accuracy (sensitivity and specificity) statistics” Karlov [0345])
Claims 5, 7, 8, and 14-22 are rejected under 35 U.S.C. 103 as being unpatentable over Miller, Pakhomov, Zizzamia, Karlov, and Tanner.
Regarding Claim 5,
Miller, Pakhomov, Zizzamia, and Karlov teach the medical code prediction of Claim 6 as described earlier.
Miller teaches,
wherein the minimum confidence threshold
(Miller [Col 18, Lines 1-5] truncate the model in various manners when the data become too sparse to have a specified level of confidence
Miller [Col 77, Lines 41-45] the confidence level that the episodes attributed to the location are actually representative for that location is low)
is a ratio describing the number of times that a particular pair of procedures must be seen,
(Miller [Abstract] A props ratio relevance function associated with the encounter type is determined, and used to determine a set of accessory encounter datastructures for the anchor encounter datastructure
Miller [Col 76, Lines 60-63] relevance may be determined by fields such as diagnosis and/or procedure codes using props ratios datastructures
Miller [Col 87, Lines 44-46] An occurrence count for the selected encounter type for each claim code associated with the determined other claims may be updated)
Miller does not teach compared to the total number of times one of the procedures of the pair of procedures is seen.
Tanner teaches,
compared to the total number of times one of the procedures of the pair of procedures is seen.
(Tanner [0091] for a particular claim may include a CPT code notices portion 602 and a detailed analysis portion 604 for each CPT code in a particular claim. The CPT code notices portion identifies CPT codes that may not be accepted in the same claim that is identified based on the procedure co-occurrence process described above.
Tanner [0092] detailed analysis portion 604 for each CPT code may include various indications of problems with the claim....identified based on the price analysis process described above and/or an incorrect ICD code for a particular CPT 608 that may be identified by the frequent item set analysis described above)
It is prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the medical code prediction of Miller to incorporate the occurrence counting teachings of Tanner for the “procedure co-occurrence process.” (Tanner [0091]). The modification would have been obvious, because it is merely applying a known technique (i.e. occurrence counting ) to a known concept (i.e. medical code prediction) ready for improvement to yield predictable result (i.e. “identifies CPT codes that may not be accepted” Tanner [0091])
Regarding Claim 7,
Miller, Pakhomov, Zizzamia, and Karlov teach the medical code prediction of Claim 6 as described earlier.
Miller teaches,
determining the most appropriate parameters by using optimization; ….by selecting the set of parameters that produces the best results.
(Miller [Col 12, Lines 65-68] predicts how the usage of healthcare services/treatments will change as prices change and that enables adjustment of parameters to achieve desired cost
Miller [Col 120, Lines 49-51] Treatment paths data (e.g., optimal path, available paths) for the population for the associated condition may be determined
Miller [Col 133, Lines 49-54] cost of following an //optimal treatment algorithm which delivers the same average benefit. For simplicity //we assume here that the optimal treatment algorithm has a small number of paths)
Miller does not teach selecting the (optimal) model.
Karlov teaches,
selecting the (optimal) model.
(Karlov [0110] to select and build an appropriate architecture of the statistical model.
Karlov [0302] develop a predictive DBA algorithm to identify the possible presence of the diseases)
It is prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the medical code prediction of Miller to incorporate the model selection teachings of Karlov to “select and build an appropriate architecture of the statistical model.” (Karlov [0110]). The modification would have been obvious, because it is merely applying a known technique (i.e. model selection) to a known concept (i.e. medical code prediction) ready for improvement to yield predictable result (i.e. “for improved disease diagnosis [Abstract])
Regarding Claim 8,
Miller, Pakhomov, Zizzamia, and Karlov teach the medical code prediction of Claim 6 as described earlier.
Miller teaches,
inputting combinations of one primary CPT code with one treatment avenue into the trained at least one model;
(Miller [Col 29, Lines 31-38] Atomized procedures (e.g., ACL repair) may be determined at 629. In one implementation, captured data (e.g., Current Procedural Terminology (CPT)) may be utilized to determine a care taxonomy that specifies atomized procedures.
Miller [Col 38, Lines 8-10] model training data (e.g., Truven and/or other historical training data),)
predicting at least one supplementary CPT code for each of the inputted combinations using the trained at least one model
(Miller [Col 52, Lines 23-25] conditions may be determined by grouping ICD-10 Diagnosis codes for related ailments into conditions or related condition groups
Miller [Col 54, Lines 50-55] Asthma condition object may be linked with treatment objects (e.g., existing treatment objects for treatments that may be used for asthma, new treatment objects created for treatments that may be used for asthma) related to asthma
Miller [Col 156, Lines 52-53] determined by grouping diagnosis codes for related ailments)
Miller does not teach outputting a similarity score that represents a level of confidence for each prediction.
Zizzamia teaches,
outputting a similarity score that represents a level of confidence for each prediction.
(Zizzamia [0085] various clustering runs to output
Zizzamia [0306] where the Confidence is 90%
Zizzamia [0047] multivariate basis and chosen to maximize the similarity of the claims
Zizzamia [0082] high degrees of correlation )
It is prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the medical code prediction of Miller to incorporate the confidence score teachings of Zizzamia where “Confidence is 90%.” (Zizzamia [0306]). The modification would have been obvious, because it is merely applying a known technique (i.e. confidence score) to a known concept (i.e. medical code prediction) ready for improvement to yield predictable result (i.e. “Confidence is defined as the conditional probability of the RHS given the LHS: P(RHS|LHS)=Confidence.” Zizzamia [0305])
Claim 14 is rejected on the same basis as Claims 1 and 8, combined.
Claim 15 is rejected on the same basis as Claim 4.
Claim 16 is rejected on the same basis as Claim 5.
Claim 17 is rejected on the same basis as Claim 6.
Claim 18 is rejected on the same basis as Claim 7.
Claim 19 is rejected on the same basis as Claim 11.
Claim 20 is rejected on the same basis as Claim 12.
Claim 21 is rejected on the same basis as Claim 13.
Claim 22 is rejected on the same basis as Claims 1, 8, 11, and 12, combined.
Claims 12 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Miller, Pakhomov, Tanner, and Zizzamia
Regarding Claim 12,
Miller and Pakhomov teach the medical code prediction of Claim 11 as described earlier.
Miller does not teach identifying potential fraudulent billing by comparing the personalized predicted cost with an actual billed amount; and creating an alert when the predicted cost is lower than the actual billed amount.
Tanner teaches,
creating an alert
(Tanner [0069] user may be alerted)
It is prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the medical code prediction of Miller to incorporate the alerts of Tanner for “user may be alerted” (Tanner [0069]). The modification would have been obvious, because it is merely applying a known technique (i.e. alerts) to a known concept (i.e. medical code prediction) ready for improvement to yield predictable result (i.e. “alerting the user to any errors that occur during the claims processing” Tanner [0142])
Tanner does not teach identifying potential fraudulent billing by comparing the personalized predicted cost with an actual billed amount; …when the predicted cost is lower than the actual billed amount
Zizzamia teaches,
identifying potential fraudulent billing by comparing the personalized predicted cost with an actual billed amount;
(Zizzamia [0422] business rules would be customized to a particular user's individual claims department
Zizzamia [0003] for uncovering fraud, particularly, but not limited to, insurance fraud
Zizzamia [0046] equally applicable to detecting fraud in any context, in claims, transactions, submissions, negotiations of instruments, etc.,
Zizzamia [0257] Evaluate actual data and create anomaly flag
Zizzamia [0013] Predictive models are analytical tools that segment claims to identify claims with a higher propensity to be fraudulent. These models are based on historical databases of claims and patterns of fraud within those databases)
…when the predicted cost is lower than the actual billed amount
(Zizzamia [0473] Set fraud rate acceptace threshold
Zizzamia [0314] setting the rules violation thresholds begins by evaluating the rate of fraud among all claims violating a single rule. If the rate of fraud is not better than the rate of fraud found in the set of all claims referred to SIU..., multiple thresholds may be used)
It is prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the medical code prediction of Miller to incorporate the confidence score teachings of Zizzamia where “Confidence is 90%.” (Zizzamia [0306]). The modification would have been obvious, because it is merely applying a known technique (i.e. confidence score) to a known concept (i.e. medical code prediction) ready for improvement to yield predictable result (i.e. “Confidence is defined as the conditional probability of the RHS given the LHS: P(RHS|LHS)=Confidence.” Zizzamia [0305])
Regarding Claim 13,
Miller and Pakhomov teach the medical code prediction of Claim 11 as described earlier.
Miller teaches,
by comparing a list of predicted supplementary CPT codes generated by the at least one model with a list of billed supplementary CPT codes from an actual patient invoice
(Miller [Col 52, Lines 37-39] using historical claims data and/or identification of CPT codes provided to individuals that have a diagnosis code associated with the condition.
Miller [Col 63, Lines 46-48] HCPCS/CPT, UB04 rev codes, ICD-10 procedure codes
Miller [Col 89, Line 63 - Col 90, Line 3] shows the predictions of a 2-variable logistic regression. Each point is a medical encounter...Each encounter has codes on it, and each code has an associated props ratio. The maximum HCPCS (service codes: “this was done”) props ratio, and the maximum ICD-10-CM (diagnosis code: “this is why it was done”) are taken
Miller [Abstract] A props ratio relevance function associated with the encounter type is determined, and used to determine a set of accessory encounter datastructures for the anchor encounter datastructure.
Miller [Col 12, Lines 33-38] enables calculation of predicted averages or distributional information about the outcomes of treatments performed by particular providers (e.g., billed cost, total related patient medical cost from all providers, change in condition, mortality, etc.).)
supplementary CPT codes;
(Miller [Col 52, Lines 37-39] using historical claims data and/or identification of CPT codes provided to individuals that have a diagnosis code associated with the condition.
Miller [Col 63, Lines 46-48] HCPCS/CPT, UB04 rev codes, ICD-10 procedure codes)
Miller does not teach identifying potential fraudulent billing; to identify fraudulently billed; creating an alert when the potential fraudulent billing is detected.
Tanner teaches,
creating an alert
(Tanner [0069] user may be alerted)
It is prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the medical code prediction of Miller to incorporate the alerts of Tanner for “user may be alerted” (Tanner [0069]). The modification would have been obvious, because it is merely applying a known technique (i.e. alerts) to a known concept (i.e. medical code prediction) ready for improvement to yield predictable result (i.e. “alerting the user to any errors that occur during the claims processing” Tanner [0142])
Tanner does not teach identifying potential fraudulent billing; to identify fraudulently billed; … when the potential fraudulent billing is detected.
Zizzamia teaches,
identifying potential fraudulent billing; to identify fraudulently billed;
(Zizzamia [0003] for uncovering fraud, particularly, but not limited to, insurance fraud
Zizzamia [0046] equally applicable to detecting fraud in any context, in claims, transactions, submissions, negotiations of instruments, etc.,)
… when the potential fraudulent billing is detected.
(Zizzamia [0473] Set fraud rate acceptance threshold
Zizzamia [Abstract] detecting fraud utilizes cluster analysis)
It is prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the medical code prediction of Miller to incorporate the confidence score teachings of Zizzamia where “Confidence is 90%.” (Zizzamia [0306]). The modification would have been obvious, because it is merely applying a known technique (i.e. confidence score) to a known concept (i.e. medical code prediction) ready for improvement to yield predictable result (i.e. “Confidence is defined as the conditional probability of the RHS given the LHS: P(RHS|LHS)=Confidence.” Zizzamia [0305])
Prior Art Cited But Not Applied
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Wikipedia (“MATHEMATICAL OPTIMIZATION”, U.S. Publication Number: 7 June 2022) an optimization problem consists of maximizing or minimizing a real function by systematically choosing input values from within an allowed set and computing the value of the function.
Foley (“SEGMENT-WISE PREDICTION MACHINE LEARNING FRAMEWORKS”, U.S. Patent: US 12160609 B2) proposes a segment-wise prediction machine learning framework. In one example, an embodiment provides for generating, using a segment-wise prediction machine learning framework, and based at least in part on a document segment for an input segment and a respective predictive code for the input segment, a segment-wise prediction score for the input segment. The segment-wise prediction machine learning framework may comprise a text embedding machine learning model and may be configured to generate a segment-wise prediction score for the input segment based at least in part on a document embedding for the input segment and a code embedding for the respective predictive code for the input segment. Additionally, the text embedding machine learning model may be trained as part of a code prediction machine learning model that is configured to generate, for a particular input document data object, a selected code subset.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHINEDU EKECHUKWU whose telephone number is (571)272-4493. The examiner can normally be reached on Mon-Fri 10am to 4pm ET.
Examiner interviews are available via telephone 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 Tran, 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.
/C.E./Examiner, Art Unit 3695
/CHRISTINE M Tran/Supervisory Patent Examiner, Art Unit 3695
Prosecution Insights